Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next into for-davem
diff --git a/.gitignore b/.gitignore
index 7e9932e..42fa0d5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -92,3 +92,6 @@
signing_key.priv
signing_key.x509
x509.genkey
+
+# Kconfig presets
+all.config
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 38f8444..07de7e1 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -29,6 +29,8 @@
- How to do DMA with ISA (and LPC) devices.
DMA-attributes.txt
- listing of the various possible attributes a DMA region can have
+dmatest.txt
+ - how to compile, configure and use the dmatest system.
DocBook/
- directory with DocBook templates etc. for kernel documentation.
EDID/
@@ -77,6 +79,8 @@
- directory with info about Linux on the ARM architecture.
arm64/
- directory with info about Linux on the 64 bit ARM architecture.
+assoc_array.txt
+ - generic associative array intro.
atomic_ops.txt
- semantics and behavior of atomic and bitmask operations.
auxdisplay/
@@ -87,6 +91,8 @@
- how to use kernel parameters to exclude bad RAM regions.
basic_profiling.txt
- basic instructions for those who wants to profile Linux kernel.
+bcache.txt
+ - Block-layer cache on fast SSDs to improve slow (raid) I/O performance.
binfmt_misc.txt
- info on the kernel support for extra binary formats.
blackfin/
@@ -171,6 +177,8 @@
- info about initramfs, klibc, and userspace early during boot.
edac.txt
- information on EDAC - Error Detection And Correction
+efi-stub.txt
+ - How to use the EFI boot stub to bypass GRUB or elilo on EFI systems.
eisa.txt
- info on EISA bus support.
email-clients.txt
@@ -195,8 +203,8 @@
- info on requeueing of tasks from a non-PI futex to a PI futex
gcov.txt
- use of GCC's coverage testing tool "gcov" with the Linux kernel
-gpio.txt
- - overview of GPIO (General Purpose Input/Output) access conventions.
+gpio/
+ - gpio related documentation
hid/
- directory with information on human interface devices
highuid.txt
@@ -255,6 +263,8 @@
- listing of various WWW + books that document kernel internals.
kernel-parameters.txt
- summary listing of command line / boot prompt args for the kernel.
+kernel-per-CPU-kthreads.txt
+ - List of all per-CPU kthreads and how they introduce jitter.
kmemcheck.txt
- info on dynamic checker that detects uses of uninitialized memory.
kmemleak.txt
@@ -299,8 +309,6 @@
- directory with info on parts like the Texas Instruments EMIF driver
memory-hotplug.txt
- Hotpluggable memory support, how to use and current status.
-memory.txt
- - info on typical Linux memory problems.
metag/
- directory with info about Linux on Meta architecture.
mips/
@@ -311,6 +319,8 @@
- directory with info about the MMC subsystem
mn10300/
- directory with info about the mn10300 architecture port
+module-signing.txt
+ - Kernel module signing for increased security when loading modules.
mtd/
- directory with info about memory technology devices (flash)
mono.txt
@@ -343,6 +353,8 @@
- info on the Linux PCMCIA driver.
percpu-rw-semaphore.txt
- RCU based read-write semaphore optimized for locking for reading
+phy.txt
+ - Description of the generic PHY framework.
pi-futex.txt
- documentation on lightweight priority inheritance futexes.
pinctrl.txt
@@ -431,6 +443,8 @@
- info on the magic SysRq key.
target/
- directory with info on generating TCM v4 fabric .ko modules
+this_cpu_ops.txt
+ - List rationale behind and the way to use this_cpu operations.
thermal/
- directory with information on managing thermal issues (CPU/temp)
trace/
@@ -469,6 +483,8 @@
- directory with info about Intel Wireless Wimax Connections
workqueue.txt
- information on the Concurrency Managed Workqueue implementation
+ww-mutex-design.txt
+ - Intro to Mutex wait/would deadlock handling.s
x86/x86_64/
- directory with info on Linux support for AMD x86-64 (Hammer) machines.
xtensa/
diff --git a/Documentation/ABI/testing/sysfs-bus-mdio b/Documentation/ABI/testing/sysfs-bus-mdio
index 6349749..491baaf 100644
--- a/Documentation/ABI/testing/sysfs-bus-mdio
+++ b/Documentation/ABI/testing/sysfs-bus-mdio
@@ -7,3 +7,23 @@
by the device during bus enumeration, encoded in hexadecimal.
This ID is used to match the device with the appropriate
driver.
+
+What: /sys/bus/mdio_bus/devices/.../phy_interface
+Date: February 2014
+KernelVersion: 3.15
+Contact: netdev@vger.kernel.org
+Description:
+ This attribute contains the PHY interface as configured by the
+ Ethernet driver during bus enumeration, encoded in string.
+ This interface mode is used to configure the Ethernet MAC with the
+ appropriate mode for its data lines to the PHY hardware.
+
+What: /sys/bus/mdio_bus/devices/.../phy_has_fixups
+Date: February 2014
+KernelVersion: 3.15
+Contact: netdev@vger.kernel.org
+Description:
+ This attribute contains the boolean value whether a given PHY
+ device has had any "fixup" workaround running on it, encoded as
+ a boolean. This information is provided to help troubleshooting
+ PHY configurations.
diff --git a/Documentation/ABI/testing/sysfs-class-net-mesh b/Documentation/ABI/testing/sysfs-class-net-mesh
index 4793d3d..c464062 100644
--- a/Documentation/ABI/testing/sysfs-class-net-mesh
+++ b/Documentation/ABI/testing/sysfs-class-net-mesh
@@ -76,6 +76,15 @@
is used to classify clients as "isolated" by the
Extended Isolation feature.
+What: /sys/class/net/<mesh_iface>/mesh/multicast_mode
+Date: Feb 2014
+Contact: Linus Lüssing <linus.luessing@web.de>
+Description:
+ Indicates whether multicast optimizations are enabled
+ or disabled. If set to zero then all nodes in the
+ mesh are going to use classic flooding for any
+ multicast packet with no optimizations.
+
What: /sys/class/net/<mesh_iface>/mesh/network_coding
Date: Nov 2012
Contact: Martin Hundeboll <martin@hundeboll.net>
diff --git a/Documentation/ABI/testing/sysfs-ptp b/Documentation/ABI/testing/sysfs-ptp
index 05aeedf..44806a6 100644
--- a/Documentation/ABI/testing/sysfs-ptp
+++ b/Documentation/ABI/testing/sysfs-ptp
@@ -54,6 +54,26 @@
This file contains the number of programmable periodic
output channels offered by the PTP hardware clock.
+What: /sys/class/ptp/ptpN/n_pins
+Date: March 2014
+Contact: Richard Cochran <richardcochran@gmail.com>
+Description:
+ This file contains the number of programmable pins
+ offered by the PTP hardware clock.
+
+What: /sys/class/ptp/ptpN/pins
+Date: March 2014
+Contact: Richard Cochran <richardcochran@gmail.com>
+Description:
+ This directory contains one file for each programmable
+ pin offered by the PTP hardware clock. The file name
+ is the hardware dependent pin name. Reading from this
+ file produces two numbers, the assigned function (see
+ the PTP_PF_ enumeration values in linux/ptp_clock.h)
+ and the channel number. The function and channel
+ assignment may be changed by two writing numbers into
+ the file.
+
What: /sys/class/ptp/ptpN/pps_avaiable
Date: September 2010
Contact: Richard Cochran <richardcochran@gmail.com>
diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt
index a8d0100..10a9369 100644
--- a/Documentation/PCI/MSI-HOWTO.txt
+++ b/Documentation/PCI/MSI-HOWTO.txt
@@ -82,7 +82,19 @@
has to request that the PCI layer set up the MSI capability for this
device.
-4.2.1 pci_enable_msi_range
+4.2.1 pci_enable_msi
+
+int pci_enable_msi(struct pci_dev *dev)
+
+A successful call allocates ONE interrupt to the device, regardless
+of how many MSIs the device supports. The device is switched from
+pin-based interrupt mode to MSI mode. The dev->irq number is changed
+to a new number which represents the message signaled interrupt;
+consequently, this function should be called before the driver calls
+request_irq(), because an MSI is delivered via a vector that is
+different from the vector of a pin-based interrupt.
+
+4.2.2 pci_enable_msi_range
int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
@@ -147,6 +159,11 @@
return pci_enable_msi_range(pdev, nvec, nvec);
}
+Note, unlike pci_enable_msi_exact() function, which could be also used to
+enable a particular number of MSI-X interrupts, pci_enable_msi_range()
+returns either a negative errno or 'nvec' (not negative errno or 0 - as
+pci_enable_msi_exact() does).
+
4.2.1.3 Single MSI mode
The most notorious example of the request type described above is
@@ -158,7 +175,27 @@
return pci_enable_msi_range(pdev, 1, 1);
}
-4.2.2 pci_disable_msi
+Note, unlike pci_enable_msi() function, which could be also used to
+enable the single MSI mode, pci_enable_msi_range() returns either a
+negative errno or 1 (not negative errno or 0 - as pci_enable_msi()
+does).
+
+4.2.3 pci_enable_msi_exact
+
+int pci_enable_msi_exact(struct pci_dev *dev, int nvec)
+
+This variation on pci_enable_msi_range() call allows a device driver to
+request exactly 'nvec' MSIs.
+
+If this function returns a negative number, it indicates an error and
+the driver should not attempt to request any more MSI interrupts for
+this device.
+
+By contrast with pci_enable_msi_range() function, pci_enable_msi_exact()
+returns zero in case of success, which indicates MSI interrupts have been
+successfully allocated.
+
+4.2.4 pci_disable_msi
void pci_disable_msi(struct pci_dev *dev)
@@ -172,7 +209,7 @@
Failure to do so results in a BUG_ON(), leaving the device with
MSI enabled and thus leaking its vector.
-4.2.3 pci_msi_vec_count
+4.2.4 pci_msi_vec_count
int pci_msi_vec_count(struct pci_dev *dev)
@@ -257,8 +294,8 @@
static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
{
- return pci_enable_msi_range(adapter->pdev, adapter->msix_entries,
- 1, nvec);
+ return pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
+ 1, nvec);
}
Note the value of 'minvec' parameter is 1. As 'minvec' is inclusive,
@@ -269,8 +306,8 @@
static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
{
- return pci_enable_msi_range(adapter->pdev, adapter->msix_entries,
- FOO_DRIVER_MINIMUM_NVEC, nvec);
+ return pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
+ FOO_DRIVER_MINIMUM_NVEC, nvec);
}
4.3.1.2 Exact number of MSI-X interrupts
@@ -282,10 +319,15 @@
static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
{
- return pci_enable_msi_range(adapter->pdev, adapter->msix_entries,
- nvec, nvec);
+ return pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
+ nvec, nvec);
}
+Note, unlike pci_enable_msix_exact() function, which could be also used to
+enable a particular number of MSI-X interrupts, pci_enable_msix_range()
+returns either a negative errno or 'nvec' (not negative errno or 0 - as
+pci_enable_msix_exact() does).
+
4.3.1.3 Specific requirements to the number of MSI-X interrupts
As noted above, there could be devices that can not operate with just any
@@ -332,7 +374,64 @@
any error code other than -ENOSPC indicates a fatal error and should not
be retried.
-4.3.2 pci_disable_msix
+4.3.2 pci_enable_msix_exact
+
+int pci_enable_msix_exact(struct pci_dev *dev,
+ struct msix_entry *entries, int nvec)
+
+This variation on pci_enable_msix_range() call allows a device driver to
+request exactly 'nvec' MSI-Xs.
+
+If this function returns a negative number, it indicates an error and
+the driver should not attempt to allocate any more MSI-X interrupts for
+this device.
+
+By contrast with pci_enable_msix_range() function, pci_enable_msix_exact()
+returns zero in case of success, which indicates MSI-X interrupts have been
+successfully allocated.
+
+Another version of a routine that enables MSI-X mode for a device with
+specific requirements described in chapter 4.3.1.3 might look like this:
+
+/*
+ * Assume 'minvec' and 'maxvec' are non-zero
+ */
+static int foo_driver_enable_msix(struct foo_adapter *adapter,
+ int minvec, int maxvec)
+{
+ int rc;
+
+ minvec = roundup_pow_of_two(minvec);
+ maxvec = rounddown_pow_of_two(maxvec);
+
+ if (minvec > maxvec)
+ return -ERANGE;
+
+retry:
+ rc = pci_enable_msix_exact(adapter->pdev,
+ adapter->msix_entries, maxvec);
+
+ /*
+ * -ENOSPC is the only error code allowed to be analyzed
+ */
+ if (rc == -ENOSPC) {
+ if (maxvec == 1)
+ return -ENOSPC;
+
+ maxvec /= 2;
+
+ if (minvec > maxvec)
+ return -ENOSPC;
+
+ goto retry;
+ } else if (rc < 0) {
+ return rc;
+ }
+
+ return maxvec;
+}
+
+4.3.3 pci_disable_msix
void pci_disable_msix(struct pci_dev *dev)
diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX
index 1d7a885..fa57139 100644
--- a/Documentation/RCU/00-INDEX
+++ b/Documentation/RCU/00-INDEX
@@ -8,6 +8,8 @@
- Using RCU to Protect Read-Mostly Linked Lists
lockdep.txt
- RCU and lockdep checking
+lockdep-splat.txt
+ - RCU Lockdep splats explained.
NMI-RCU.txt
- Using RCU to Protect Dynamic NMI Handlers
rcubarrier.txt
diff --git a/Documentation/arm/00-INDEX b/Documentation/arm/00-INDEX
index 36420e1..a94090c 100644
--- a/Documentation/arm/00-INDEX
+++ b/Documentation/arm/00-INDEX
@@ -4,6 +4,8 @@
- requirements for booting
Interrupts
- ARM Interrupt subsystem documentation
+IXP4xx
+ - Intel IXP4xx Network processor.
msm
- MSM specific documentation
Netwinder
@@ -24,8 +26,16 @@
- ST SPEAr platform Linux Overview
VFP/
- Release notes for Linux Kernel Vector Floating Point support code
+cluster-pm-race-avoidance.txt
+ - Algorithm for CPU and Cluster setup/teardown
empeg/
- Ltd's Empeg MP3 Car Audio Player
+firmware.txt
+ - Secure firmware registration and calling.
+kernel_mode_neon.txt
+ - How to use NEON instructions in kernel mode
+kernel_user_helpers.txt
+ - Helper functions in kernel space made available for userspace.
mem_alignment
- alignment abort handler documentation
memory.txt
@@ -34,3 +44,7 @@
- NWFPE floating point emulator documentation
swp_emulation
- SWP/SWPB emulation handler/logging description
+tcm.txt
+ - ARM Tightly Coupled Memory
+vlocks.txt
+ - Voting locks, low-level mechanism relying on memory system atomic writes.
diff --git a/Documentation/blackfin/00-INDEX b/Documentation/blackfin/00-INDEX
index 2df0365..c54fcdd 100644
--- a/Documentation/blackfin/00-INDEX
+++ b/Documentation/blackfin/00-INDEX
@@ -1,8 +1,10 @@
00-INDEX
- This file
-
+Makefile
+ - Makefile for gptimers example file.
bfin-gpio-notes.txt
- Notes in developing/using bfin-gpio driver.
-
bfin-spi-notes.txt
- Notes for using bfin spi bus driver.
+gptimers-example.c
+ - gptimers example
diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
index 929d990..e840b47 100644
--- a/Documentation/block/00-INDEX
+++ b/Documentation/block/00-INDEX
@@ -14,6 +14,8 @@
- Deadline IO scheduler tunables
ioprio.txt
- Block io priorities (in CFQ scheduler)
+null_blk.txt
+ - Null block for block-layer benchmarking.
queue-sysfs.txt
- Queue's sysfs entries
request.txt
diff --git a/Documentation/device-mapper/cache.txt b/Documentation/device-mapper/cache.txt
index e6b72d3..68c0f51 100644
--- a/Documentation/device-mapper/cache.txt
+++ b/Documentation/device-mapper/cache.txt
@@ -124,12 +124,11 @@
Updating on-disk metadata
-------------------------
-On-disk metadata is committed every time a REQ_SYNC or REQ_FUA bio is
-written. If no such requests are made then commits will occur every
-second. This means the cache behaves like a physical disk that has a
-write cache (the same is true of the thin-provisioning target). If
-power is lost you may lose some recent writes. The metadata should
-always be consistent in spite of any crash.
+On-disk metadata is committed every time a FLUSH or FUA bio is written.
+If no such requests are made then commits will occur every second. This
+means the cache behaves like a physical disk that has a volatile write
+cache. If power is lost you may lose some recent writes. The metadata
+should always be consistent in spite of any crash.
The 'dirty' state for a cache block changes far too frequently for us
to keep updating it on the fly. So we treat it as a hint. In normal
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 8a7a3d4..05a27e9 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -116,6 +116,35 @@
userspace daemon can use this to detect a situation where a new table
already exceeds the threshold.
+A low water mark for the metadata device is maintained in the kernel and
+will trigger a dm event if free space on the metadata device drops below
+it.
+
+Updating on-disk metadata
+-------------------------
+
+On-disk metadata is committed every time a FLUSH or FUA bio is written.
+If no such requests are made then commits will occur every second. This
+means the thin-provisioning target behaves like a physical disk that has
+a volatile write cache. If power is lost you may lose some recent
+writes. The metadata should always be consistent in spite of any crash.
+
+If data space is exhausted the pool will either error or queue IO
+according to the configuration (see: error_if_no_space). If metadata
+space is exhausted or a metadata operation fails: the pool will error IO
+until the pool is taken offline and repair is performed to 1) fix any
+potential inconsistencies and 2) clear the flag that imposes repair.
+Once the pool's metadata device is repaired it may be resized, which
+will allow the pool to return to normal operation. Note that if a pool
+is flagged as needing repair, the pool's data and metadata devices
+cannot be resized until repair is performed. It should also be noted
+that when the pool's metadata space is exhausted the current metadata
+transaction is aborted. Given that the pool will cache IO whose
+completion may have already been acknowledged to upper IO layers
+(e.g. filesystem) it is strongly suggested that consistency checks
+(e.g. fsck) be performed on those layers when repair of the pool is
+required.
+
Thin provisioning
-----------------
@@ -258,10 +287,9 @@
should register for the event and then check the target's status.
held metadata root:
- The location, in sectors, of the metadata root that has been
+ The location, in blocks, of the metadata root that has been
'held' for userspace read access. '-' indicates there is no
- held root. This feature is not yet implemented so '-' is
- always returned.
+ held root.
discard_passdown|no_discard_passdown
Whether or not discards are actually being passed down to the
diff --git a/Documentation/devicetree/00-INDEX b/Documentation/devicetree/00-INDEX
index b78f691..8c4102c 100644
--- a/Documentation/devicetree/00-INDEX
+++ b/Documentation/devicetree/00-INDEX
@@ -8,3 +8,5 @@
- this file
booting-without-of.txt
- Booting Linux without Open Firmware, describes history and format of device trees.
+usage-model.txt
+ - How Linux uses DT and what DT aims to solve.
\ No newline at end of file
diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt
index 34dc40c..af9b4a0 100644
--- a/Documentation/devicetree/bindings/arm/omap/omap.txt
+++ b/Documentation/devicetree/bindings/arm/omap/omap.txt
@@ -91,7 +91,7 @@
compatible = "ti,omap3-beagle", "ti,omap3"
- OMAP3 Tobi with Overo : Commercial expansion board with daughter board
- compatible = "ti,omap3-tobi", "ti,omap3-overo", "ti,omap3"
+ compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap3"
- OMAP4 SDP : Software Development Board
compatible = "ti,omap4-sdp", "ti,omap4430"
diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
index a6a352c..5992dce 100644
--- a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
@@ -21,9 +21,9 @@
must appear in the same order as the output clocks.
- #clock-cells: Must be 1
- clock-output-names: The name of the clocks as free-form strings
- - renesas,indices: Indices of the gate clocks into the group (0 to 31)
+ - renesas,clock-indices: Indices of the gate clocks into the group (0 to 31)
-The clocks, clock-output-names and renesas,indices properties contain one
+The clocks, clock-output-names and renesas,clock-indices properties contain one
entry per gate clock. The MSTP groups are sparsely populated. Unimplemented
gate clocks must not be declared.
diff --git a/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt b/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
index 68b83ec..ee9be99 100644
--- a/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
+++ b/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt
@@ -1,12 +1,16 @@
* Freescale Smart Direct Memory Access (SDMA) Controller for i.MX
Required properties:
-- compatible : Should be "fsl,imx31-sdma", "fsl,imx31-to1-sdma",
- "fsl,imx31-to2-sdma", "fsl,imx35-sdma", "fsl,imx35-to1-sdma",
- "fsl,imx35-to2-sdma", "fsl,imx51-sdma", "fsl,imx53-sdma" or
- "fsl,imx6q-sdma". The -to variants should be preferred since they
- allow to determnine the correct ROM script addresses needed for
- the driver to work without additional firmware.
+- compatible : Should be one of
+ "fsl,imx25-sdma"
+ "fsl,imx31-sdma", "fsl,imx31-to1-sdma", "fsl,imx31-to2-sdma"
+ "fsl,imx35-sdma", "fsl,imx35-to1-sdma", "fsl,imx35-to2-sdma"
+ "fsl,imx51-sdma"
+ "fsl,imx53-sdma"
+ "fsl,imx6q-sdma"
+ The -to variants should be preferred since they allow to determnine the
+ correct ROM script addresses needed for the driver to work without additional
+ firmware.
- reg : Should contain SDMA registers location and length
- interrupts : Should contain SDMA interrupt
- #dma-cells : Must be <3>.
diff --git a/Documentation/devicetree/bindings/mmc/atmel-hsmci.txt b/Documentation/devicetree/bindings/mmc/atmel-hsmci.txt
index 0a85c70..07ad020 100644
--- a/Documentation/devicetree/bindings/mmc/atmel-hsmci.txt
+++ b/Documentation/devicetree/bindings/mmc/atmel-hsmci.txt
@@ -13,6 +13,9 @@
- #address-cells: should be one. The cell is the slot id.
- #size-cells: should be zero.
- at least one slot node
+- clock-names: tuple listing input clock names.
+ Required elements: "mci_clk"
+- clocks: phandles to input clocks.
The node contains child nodes for each slot that the platform uses
@@ -24,6 +27,8 @@
interrupts = <12 4>;
#address-cells = <1>;
#size-cells = <0>;
+ clock-names = "mci_clk";
+ clocks = <&mci0_clk>;
[ child node definitions...]
};
diff --git a/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt b/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt
index b90bfcd..10640b1 100644
--- a/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt
+++ b/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt
@@ -1,20 +1,17 @@
* Allwinner EMAC ethernet controller
Required properties:
-- compatible: should be "allwinner,sun4i-emac".
+- compatible: should be "allwinner,sun4i-a10-emac" (Deprecated:
+ "allwinner,sun4i-emac")
- reg: address and length of the register set for the device.
- interrupts: interrupt for the device
-- phy: A phandle to a phy node defining the PHY address (as the reg
- property, a single integer).
+- phy: see ethernet.txt file in the same directory.
- clocks: A phandle to the reference clock for this device
-Optional properties:
-- (local-)mac-address: mac address to be used by this driver
-
Example:
emac: ethernet@01c0b000 {
- compatible = "allwinner,sun4i-emac";
+ compatible = "allwinner,sun4i-a10-emac";
reg = <0x01c0b000 0x1000>;
interrupts = <55>;
clocks = <&ahb_gates 17>;
diff --git a/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt b/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt
index 00b9f9a..4ec5641 100644
--- a/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt
+++ b/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt
@@ -1,7 +1,8 @@
* Allwinner A10 MDIO Ethernet Controller interface
Required properties:
-- compatible: should be "allwinner,sun4i-mdio".
+- compatible: should be "allwinner,sun4i-a10-mdio"
+ (Deprecated: "allwinner,sun4i-mdio").
- reg: address and length of the register set for the device.
Optional properties:
@@ -9,7 +10,7 @@
Example at the SoC level:
mdio@01c0b080 {
- compatible = "allwinner,sun4i-mdio";
+ compatible = "allwinner,sun4i-a10-mdio";
reg = <0x01c0b080 0x14>;
#address-cells = <1>;
#size-cells = <0>;
diff --git a/Documentation/devicetree/bindings/net/altera_tse.txt b/Documentation/devicetree/bindings/net/altera_tse.txt
new file mode 100644
index 0000000..a706297
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/altera_tse.txt
@@ -0,0 +1,114 @@
+* Altera Triple-Speed Ethernet MAC driver (TSE)
+
+Required properties:
+- compatible: Should be "altr,tse-1.0" for legacy SGDMA based TSE, and should
+ be "altr,tse-msgdma-1.0" for the preferred MSGDMA based TSE.
+ ALTR is supported for legacy device trees, but is deprecated.
+ altr should be used for all new designs.
+- reg: Address and length of the register set for the device. It contains
+ the information of registers in the same order as described by reg-names
+- reg-names: Should contain the reg names
+ "control_port": MAC configuration space region
+ "tx_csr": xDMA Tx dispatcher control and status space region
+ "tx_desc": MSGDMA Tx dispatcher descriptor space region
+ "rx_csr" : xDMA Rx dispatcher control and status space region
+ "rx_desc": MSGDMA Rx dispatcher descriptor space region
+ "rx_resp": MSGDMA Rx dispatcher response space region
+ "s1": SGDMA descriptor memory
+- interrupts: Should contain the TSE interrupts and it's mode.
+- interrupt-names: Should contain the interrupt names
+ "rx_irq": xDMA Rx dispatcher interrupt
+ "tx_irq": xDMA Tx dispatcher interrupt
+- rx-fifo-depth: MAC receive FIFO buffer depth in bytes
+- tx-fifo-depth: MAC transmit FIFO buffer depth in bytes
+- phy-mode: See ethernet.txt in the same directory.
+- phy-handle: See ethernet.txt in the same directory.
+- phy-addr: See ethernet.txt in the same directory. A configuration should
+ include phy-handle or phy-addr.
+- altr,has-supplementary-unicast:
+ If present, TSE supports additional unicast addresses.
+ Otherwise additional unicast addresses are not supported.
+- altr,has-hash-multicast-filter:
+ If present, TSE supports a hash based multicast filter.
+ Otherwise, hash-based multicast filtering is not supported.
+
+- mdio device tree subnode: When the TSE has a phy connected to its local
+ mdio, there must be device tree subnode with the following
+ required properties:
+
+ - compatible: Must be "altr,tse-mdio".
+ - #address-cells: Must be <1>.
+ - #size-cells: Must be <0>.
+
+ For each phy on the mdio bus, there must be a node with the following
+ fields:
+
+ - reg: phy id used to communicate to phy.
+ - device_type: Must be "ethernet-phy".
+
+Optional properties:
+- local-mac-address: See ethernet.txt in the same directory.
+- max-frame-size: See ethernet.txt in the same directory.
+
+Example:
+
+ tse_sub_0_eth_tse_0: ethernet@0x1,00000000 {
+ compatible = "altr,tse-msgdma-1.0";
+ reg = <0x00000001 0x00000000 0x00000400>,
+ <0x00000001 0x00000460 0x00000020>,
+ <0x00000001 0x00000480 0x00000020>,
+ <0x00000001 0x000004A0 0x00000008>,
+ <0x00000001 0x00000400 0x00000020>,
+ <0x00000001 0x00000420 0x00000020>;
+ reg-names = "control_port", "rx_csr", "rx_desc", "rx_resp", "tx_csr", "tx_desc";
+ interrupt-parent = <&hps_0_arm_gic_0>;
+ interrupts = <0 41 4>, <0 40 4>;
+ interrupt-names = "rx_irq", "tx_irq";
+ rx-fifo-depth = <2048>;
+ tx-fifo-depth = <2048>;
+ address-bits = <48>;
+ max-frame-size = <1500>;
+ local-mac-address = [ 00 00 00 00 00 00 ];
+ phy-mode = "gmii";
+ altr,has-supplementary-unicast;
+ altr,has-hash-multicast-filter;
+ phy-handle = <&phy0>;
+ mdio {
+ compatible = "altr,tse-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ phy0: ethernet-phy@0 {
+ reg = <0x0>;
+ device_type = "ethernet-phy";
+ };
+
+ phy1: ethernet-phy@1 {
+ reg = <0x1>;
+ device_type = "ethernet-phy";
+ };
+
+ };
+ };
+
+ tse_sub_1_eth_tse_0: ethernet@0x1,00001000 {
+ compatible = "altr,tse-msgdma-1.0";
+ reg = <0x00000001 0x00001000 0x00000400>,
+ <0x00000001 0x00001460 0x00000020>,
+ <0x00000001 0x00001480 0x00000020>,
+ <0x00000001 0x000014A0 0x00000008>,
+ <0x00000001 0x00001400 0x00000020>,
+ <0x00000001 0x00001420 0x00000020>;
+ reg-names = "control_port", "rx_csr", "rx_desc", "rx_resp", "tx_csr", "tx_desc";
+ interrupt-parent = <&hps_0_arm_gic_0>;
+ interrupts = <0 43 4>, <0 42 4>;
+ interrupt-names = "rx_irq", "tx_irq";
+ rx-fifo-depth = <2048>;
+ tx-fifo-depth = <2048>;
+ address-bits = <48>;
+ max-frame-size = <1500>;
+ local-mac-address = [ 00 00 00 00 00 00 ];
+ phy-mode = "gmii";
+ altr,has-supplementary-unicast;
+ altr,has-hash-multicast-filter;
+ phy-handle = <&phy1>;
+ };
diff --git a/Documentation/devicetree/bindings/net/arc_emac.txt b/Documentation/devicetree/bindings/net/arc_emac.txt
index bcbc3f0..7fbb027 100644
--- a/Documentation/devicetree/bindings/net/arc_emac.txt
+++ b/Documentation/devicetree/bindings/net/arc_emac.txt
@@ -6,19 +6,12 @@
- interrupts: Should contain the EMAC interrupts
- clock-frequency: CPU frequency. It is needed to calculate and set polling
period of EMAC.
-- max-speed: Maximum supported data-rate in Mbit/s. In some HW configurations
-bandwidth of external memory controller might be a limiting factor. That's why
-it's required to specify which data-rate is supported on current SoC or FPGA.
-For example if only 10 Mbit/s is supported (10BASE-T) set "10". If 100 Mbit/s is
-supported (100BASE-TX) set "100".
-- phy: PHY device attached to the EMAC via MDIO bus
+- max-speed: see ethernet.txt file in the same directory.
+- phy: see ethernet.txt file in the same directory.
Child nodes of the driver are the individual PHY devices connected to the
MDIO bus. They must have a "reg" property given the PHY address on the MDIO bus.
-Optional properties:
-- mac-address: 6 bytes, mac address
-
Examples:
ethernet@c0fc2000 {
diff --git a/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt b/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt
new file mode 100644
index 0000000..f2febb9
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt
@@ -0,0 +1,121 @@
+* Broadcom BCM7xxx Ethernet Controller (GENET)
+
+Required properties:
+- compatible: should contain one of "brcm,genet-v1", "brcm,genet-v2",
+ "brcm,genet-v3", "brcm,genet-v4".
+- reg: address and length of the register set for the device
+- interrupts: must be two cells, the first cell is the general purpose
+ interrupt line, while the second cell is the interrupt for the ring
+ RX and TX queues operating in ring mode
+- phy-mode: see ethernet.txt file in the same directory
+- #address-cells: should be 1
+- #size-cells: should be 1
+
+Optional properties:
+- clocks: When provided, must be two phandles to the functional clocks nodes
+ of the GENET block. The first phandle is the main GENET clock used during
+ normal operation, while the second phandle is the Wake-on-LAN clock.
+- clock-names: When provided, names of the functional clock phandles, first
+ name should be "enet" and second should be "enet-wol".
+
+- phy-handle: See ethernet.txt file in the same directory; used to describe
+ configurations where a PHY (internal or external) is used.
+
+- fixed-link: When the GENET interface is connected to a MoCA hardware block or
+ when operating in a RGMII to RGMII type of connection, or when the MDIO bus is
+ voluntarily disabled, this property should be used to describe the "fixed link".
+ See Documentation/devicetree/bindings/net/fsl-tsec-phy.txt for information on
+ the property specifics
+
+Required child nodes:
+
+- mdio bus node: this node should always be present regarless of the PHY
+ configuration of the GENET instance
+
+MDIO bus node required properties:
+
+- compatible: should contain one of "brcm,genet-mdio-v1", "brcm,genet-mdio-v2"
+ "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", the version has to match the
+ parent node compatible property (e.g: brcm,genet-v4 pairs with
+ brcm,genet-mdio-v4)
+- reg: address and length relative to the parent node base register address
+- #address-cells: address cell for MDIO bus addressing, should be 1
+- #size-cells: size of the cells for MDIO bus addressing, should be 0
+
+Ethernet PHY node properties:
+
+See Documentation/devicetree/bindings/net/phy.txt for the list of required and
+optional properties.
+
+Internal Gigabit PHY example:
+
+ethernet@f0b60000 {
+ phy-mode = "internal";
+ phy-handle = <&phy1>;
+ mac-address = [ 00 10 18 36 23 1a ];
+ compatible = "brcm,genet-v4";
+ #address-cells = <0x1>;
+ #size-cells = <0x1>;
+ reg = <0xf0b60000 0xfc4c>;
+ interrupts = <0x0 0x14 0x0>, <0x0 0x15 0x0>;
+
+ mdio@e14 {
+ compatible = "brcm,genet-mdio-v4";
+ #address-cells = <0x1>;
+ #size-cells = <0x0>;
+ reg = <0xe14 0x8>;
+
+ phy1: ethernet-phy@1 {
+ max-speed = <1000>;
+ reg = <0x1>;
+ compatible = "brcm,28nm-gphy", "ethernet-phy-ieee802.3-c22";
+ };
+ };
+};
+
+MoCA interface / MAC to MAC example:
+
+ethernet@f0b80000 {
+ phy-mode = "moca";
+ fixed-link = <1 0 1000 0 0>;
+ mac-address = [ 00 10 18 36 24 1a ];
+ compatible = "brcm,genet-v4";
+ #address-cells = <0x1>;
+ #size-cells = <0x1>;
+ reg = <0xf0b80000 0xfc4c>;
+ interrupts = <0x0 0x16 0x0>, <0x0 0x17 0x0>;
+
+ mdio@e14 {
+ compatible = "brcm,genet-mdio-v4";
+ #address-cells = <0x1>;
+ #size-cells = <0x0>;
+ reg = <0xe14 0x8>;
+ };
+};
+
+
+External MDIO-connected Gigabit PHY/switch:
+
+ethernet@f0ba0000 {
+ phy-mode = "rgmii";
+ phy-handle = <&phy0>;
+ mac-address = [ 00 10 18 36 26 1a ];
+ compatible = "brcm,genet-v4";
+ #address-cells = <0x1>;
+ #size-cells = <0x1>;
+ reg = <0xf0ba0000 0xfc4c>;
+ interrupts = <0x0 0x18 0x0>, <0x0 0x19 0x0>;
+
+ mdio@0e14 {
+ compatible = "brcm,genet-mdio-v4";
+ #address-cells = <0x1>;
+ #size-cells = <0x0>;
+ reg = <0xe14 0x8>;
+
+ phy0: ethernet-phy@0 {
+ max-speed = <1000>;
+ reg = <0x0>;
+ compatible = "brcm,bcm53125", "ethernet-phy-ieee802.3-c22";
+ };
+ };
+};
diff --git a/Documentation/devicetree/bindings/net/can/sja1000.txt b/Documentation/devicetree/bindings/net/can/sja1000.txt
index f2105a4..b4a6d53 100644
--- a/Documentation/devicetree/bindings/net/can/sja1000.txt
+++ b/Documentation/devicetree/bindings/net/can/sja1000.txt
@@ -12,6 +12,10 @@
Optional properties:
+- reg-io-width : Specify the size (in bytes) of the IO accesses that
+ should be performed on the device. Valid value is 1, 2 or 4.
+ Default to 1 (8 bits).
+
- nxp,external-clock-frequency : Frequency of the external oscillator
clock in Hz. Note that the internal clock frequency used by the
SJA1000 is half of that value. If not specified, a default value
diff --git a/Documentation/devicetree/bindings/net/cavium-mix.txt b/Documentation/devicetree/bindings/net/cavium-mix.txt
index 5da628d..8d7c309 100644
--- a/Documentation/devicetree/bindings/net/cavium-mix.txt
+++ b/Documentation/devicetree/bindings/net/cavium-mix.txt
@@ -18,12 +18,7 @@
- interrupts: Two interrupt specifiers. The first is the MIX
interrupt routing and the second the routing for the AGL interrupts.
-- mac-address: Optional, the MAC address to assign to the device.
-
-- local-mac-address: Optional, the MAC address to assign to the device
- if mac-address is not specified.
-
-- phy-handle: Optional, a phandle for the PHY device connected to this device.
+- phy-handle: Optional, see ethernet.txt file in the same directory.
Example:
ethernet@1070000100800 {
diff --git a/Documentation/devicetree/bindings/net/cavium-pip.txt b/Documentation/devicetree/bindings/net/cavium-pip.txt
index d4c53ba..7dbd158 100644
--- a/Documentation/devicetree/bindings/net/cavium-pip.txt
+++ b/Documentation/devicetree/bindings/net/cavium-pip.txt
@@ -35,12 +35,7 @@
- reg: The port number within the interface group.
-- mac-address: Optional, the MAC address to assign to the device.
-
-- local-mac-address: Optional, the MAC address to assign to the device
- if mac-address is not specified.
-
-- phy-handle: Optional, a phandle for the PHY device connected to this device.
+- phy-handle: Optional, see ethernet.txt file in the same directory.
Example:
diff --git a/Documentation/devicetree/bindings/net/cdns-emac.txt b/Documentation/devicetree/bindings/net/cdns-emac.txt
index 09055c2..abd67c1 100644
--- a/Documentation/devicetree/bindings/net/cdns-emac.txt
+++ b/Documentation/devicetree/bindings/net/cdns-emac.txt
@@ -6,11 +6,7 @@
or the generic form: "cdns,emac".
- reg: Address and length of the register set for the device
- interrupts: Should contain macb interrupt
-- phy-mode: String, operation mode of the PHY interface.
- Supported values are: "mii", "rmii".
-
-Optional properties:
-- local-mac-address: 6 bytes, mac address
+- phy-mode: see ethernet.txt file in the same directory.
Examples:
diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index 05d660e..ae2b8b7 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -28,9 +28,8 @@
Slave Properties:
Required properties:
- phy_id : Specifies slave phy id
-- phy-mode : The interface between the SoC and the PHY (a string
- that of_get_phy_mode() can understand)
-- mac-address : Specifies slave MAC address
+- phy-mode : See ethernet.txt file in the same directory
+- mac-address : See ethernet.txt file in the same directory
Optional properties:
- dual_emac_res_vlan : Specifies VID to be used to segregate the ports
diff --git a/Documentation/devicetree/bindings/net/davicom-dm9000.txt b/Documentation/devicetree/bindings/net/davicom-dm9000.txt
index 2d39c99..28767ed 100644
--- a/Documentation/devicetree/bindings/net/davicom-dm9000.txt
+++ b/Documentation/devicetree/bindings/net/davicom-dm9000.txt
@@ -9,8 +9,6 @@
- interrupts : interrupt specifier specific to interrupt controller
Optional properties:
-- local-mac-address : A bytestring of 6 bytes specifying Ethernet MAC address
- to use (from firmware or bootloader)
- davicom,no-eeprom : Configuration EEPROM is not available
- davicom,ext-phy : Use external PHY
diff --git a/Documentation/devicetree/bindings/net/davinci_emac.txt b/Documentation/devicetree/bindings/net/davinci_emac.txt
index 6e356d1..0328088 100644
--- a/Documentation/devicetree/bindings/net/davinci_emac.txt
+++ b/Documentation/devicetree/bindings/net/davinci_emac.txt
@@ -17,9 +17,8 @@
Miscellaneous Interrupt>
Optional properties:
-- phy-handle: Contains a phandle to an Ethernet PHY.
+- phy-handle: See ethernet.txt file in the same directory.
If absent, davinci_emac driver defaults to 100/FULL.
-- local-mac-address : 6 bytes, mac address
- ti,davinci-rmii-en: 1 byte, 1 means use RMII
- ti,davinci-no-bd-ram: boolean, does EMAC have BD RAM?
diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt
new file mode 100644
index 0000000..9ecd43d
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ethernet.txt
@@ -0,0 +1,25 @@
+The following properties are common to the Ethernet controllers:
+
+- local-mac-address: array of 6 bytes, specifies the MAC address that was
+ assigned to the network device;
+- mac-address: array of 6 bytes, specifies the MAC address that was last used by
+ the boot program; should be used in cases where the MAC address assigned to
+ the device by the boot program is different from the "local-mac-address"
+ property;
+- max-speed: number, specifies maximum speed in Mbit/s supported by the device;
+- max-frame-size: number, maximum transfer unit (IEEE defined MTU), rather than
+ the maximum frame size (there's contradiction in ePAPR).
+- phy-mode: string, operation mode of the PHY interface; supported values are
+ "mii", "gmii", "sgmii", "tbi", "rev-mii", "rmii", "rgmii", "rgmii-id",
+ "rgmii-rxid", "rgmii-txid", "rtbi", "smii", "xgmii"; this is now a de-facto
+ standard property;
+- phy-connection-type: the same as "phy-mode" property but described in ePAPR;
+- phy-handle: phandle, specifies a reference to a node representing a PHY
+ device; this property is described in ePAPR and so preferred;
+- phy: the same as "phy-handle" property, not recommended for new bindings.
+- phy-device: the same as "phy-handle" property, not recommended for new
+ bindings.
+
+Child nodes of the Ethernet controller are typically the individual PHY devices
+connected via the MDIO bus (sometimes the MDIO bus controller is separate).
+They are described in the phy.txt file in this same directory.
diff --git a/Documentation/devicetree/bindings/net/fsl-fec.txt b/Documentation/devicetree/bindings/net/fsl-fec.txt
index 845ff84..6bc84ad 100644
--- a/Documentation/devicetree/bindings/net/fsl-fec.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fec.txt
@@ -4,12 +4,9 @@
- compatible : Should be "fsl,<soc>-fec"
- reg : Address and length of the register set for the device
- interrupts : Should contain fec interrupt
-- phy-mode : String, operation mode of the PHY interface.
- Supported values are: "mii", "gmii", "sgmii", "tbi", "rmii",
- "rgmii", "rgmii-id", "rgmii-rxid", "rgmii-txid", "rtbi", "smii".
+- phy-mode : See ethernet.txt file in the same directory
Optional properties:
-- local-mac-address : 6 bytes, mac address
- phy-reset-gpios : Should specify the gpio for phy reset
- phy-reset-duration : Reset duration in milliseconds. Should present
only if property "phy-reset-gpios" is available. Missing the property
diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
index d2ea460..737cdef 100644
--- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
+++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
@@ -38,22 +38,17 @@
- model : Model of the device. Can be "TSEC", "eTSEC", or "FEC"
- compatible : Should be "gianfar"
- reg : Offset and length of the register set for the device
- - local-mac-address : List of bytes representing the ethernet address of
- this controller
- interrupts : For FEC devices, the first interrupt is the device's
interrupt. For TSEC and eTSEC devices, the first interrupt is
transmit, the second is receive, and the third is error.
- - phy-handle : The phandle for the PHY connected to this ethernet
- controller.
+ - phy-handle : See ethernet.txt file in the same directory.
- fixed-link : <a b c d e> where a is emulated phy id - choose any,
but unique to the all specified fixed-links, b is duplex - 0 half,
1 full, c is link speed - d#10/d#100/d#1000, d is pause - 0 no
pause, 1 pause, e is asym_pause - 0 no asym_pause, 1 asym_pause.
- - phy-connection-type : a string naming the controller/PHY interface type,
- i.e., "mii" (default), "rmii", "gmii", "rgmii", "rgmii-id", "sgmii",
- "tbi", or "rtbi". This property is only really needed if the connection
- is of type "rgmii-id", as all other connection types are detected by
- hardware.
+ - phy-connection-type : See ethernet.txt file in the same directory.
+ This property is only really needed if the connection is of type
+ "rgmii-id", as all other connection types are detected by hardware.
- fsl,magic-packet : If present, indicates that the hardware supports
waking up via magic packet.
- bd-stash : If present, indicates that the hardware supports stashing
diff --git a/Documentation/devicetree/bindings/net/lpc-eth.txt b/Documentation/devicetree/bindings/net/lpc-eth.txt
index 585021a..b92e927 100644
--- a/Documentation/devicetree/bindings/net/lpc-eth.txt
+++ b/Documentation/devicetree/bindings/net/lpc-eth.txt
@@ -6,10 +6,9 @@
- interrupts: Should contain ethernet controller interrupt
Optional properties:
-- phy-mode: String, operation mode of the PHY interface.
- Supported values are: "mii", "rmii" (default)
+- phy-mode: See ethernet.txt file in the same directory. If the property is
+ absent, "rmii" is assumed.
- use-iram: Use LPC32xx internal SRAM (IRAM) for DMA buffering
-- local-mac-address : 6 bytes, mac address
Example:
diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt
index 70af2ec..aaa6964 100644
--- a/Documentation/devicetree/bindings/net/macb.txt
+++ b/Documentation/devicetree/bindings/net/macb.txt
@@ -8,16 +8,12 @@
the Cadence GEM, or the generic form: "cdns,gem".
- reg: Address and length of the register set for the device
- interrupts: Should contain macb interrupt
-- phy-mode: String, operation mode of the PHY interface.
- Supported values are: "mii", "rmii", "gmii", "rgmii".
+- phy-mode: See ethernet.txt file in the same directory.
- clock-names: Tuple listing input clock names.
Required elements: 'pclk', 'hclk'
Optional elements: 'tx_clk'
- clocks: Phandles to input clocks.
-Optional properties:
-- local-mac-address: 6 bytes, mac address
-
Examples:
macb0: ethernet@fffc4000 {
diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
index 859a6fa..750d577 100644
--- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
+++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
@@ -4,10 +4,8 @@
- compatible: should be "marvell,armada-370-neta".
- reg: address and length of the register set for the device.
- interrupts: interrupt for the device
-- phy: A phandle to a phy node defining the PHY address (as the reg
- property, a single integer).
-- phy-mode: The interface between the SoC and the PHY (a string that
- of_get_phy_mode() can understand)
+- phy: See ethernet.txt file in the same directory.
+- phy-mode: See ethernet.txt file in the same directory
- clocks: a pointer to the reference clock for this device.
Example:
diff --git a/Documentation/devicetree/bindings/net/marvell-orion-net.txt b/Documentation/devicetree/bindings/net/marvell-orion-net.txt
index c233b61..bce52b2 100644
--- a/Documentation/devicetree/bindings/net/marvell-orion-net.txt
+++ b/Documentation/devicetree/bindings/net/marvell-orion-net.txt
@@ -36,7 +36,7 @@
"marvell,kirkwood-eth-port".
- reg: port number relative to ethernet controller, shall be 0, 1, or 2.
- interrupts: port interrupt.
- - local-mac-address: 6 bytes MAC address.
+ - local-mac-address: See ethernet.txt file in the same directory.
Optional port properties:
- marvell,tx-queue-size: size of the transmit ring buffer.
@@ -48,7 +48,7 @@
and
- - phy-handle: phandle reference to ethernet PHY.
+ - phy-handle: See ethernet.txt file in the same directory.
or
diff --git a/Documentation/devicetree/bindings/net/micrel-ks8851.txt b/Documentation/devicetree/bindings/net/micrel-ks8851.txt
index 11ace3c..d54d0cc 100644
--- a/Documentation/devicetree/bindings/net/micrel-ks8851.txt
+++ b/Documentation/devicetree/bindings/net/micrel-ks8851.txt
@@ -6,4 +6,4 @@
- interrupts : interrupt connection
Optional properties:
-- local-mac-address : Ethernet mac address to use
+- vdd-supply: supply for Ethernet mac
diff --git a/Documentation/devicetree/bindings/net/micrel.txt b/Documentation/devicetree/bindings/net/micrel.txt
new file mode 100644
index 0000000..98a3e61
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/micrel.txt
@@ -0,0 +1,18 @@
+Micrel PHY properties.
+
+These properties cover the base properties Micrel PHYs.
+
+Optional properties:
+
+ - micrel,led-mode : LED mode value to set for PHYs with configurable LEDs.
+
+ Configure the LED mode with single value. The list of PHYs and
+ the bits that are currently supported:
+
+ KSZ8001: register 0x1e, bits 15..14
+ KSZ8041: register 0x1e, bits 15..14
+ KSZ8021: register 0x1f, bits 5..4
+ KSZ8031: register 0x1f, bits 5..4
+ KSZ8051: register 0x1f, bits 5..4
+
+ See the respective PHY datasheet for the mode values.
diff --git a/Documentation/devicetree/bindings/net/opencores-ethoc.txt b/Documentation/devicetree/bindings/net/opencores-ethoc.txt
new file mode 100644
index 0000000..2dc127c
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/opencores-ethoc.txt
@@ -0,0 +1,22 @@
+* OpenCores MAC 10/100 Mbps
+
+Required properties:
+- compatible: Should be "opencores,ethoc".
+- reg: two memory regions (address and length),
+ first region is for the device registers and descriptor rings,
+ second is for the device packet memory.
+- interrupts: interrupt for the device.
+
+Optional properties:
+- clocks: phandle to refer to the clk used as per
+ Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+Examples:
+
+ enet0: ethoc@fd030000 {
+ compatible = "opencores,ethoc";
+ reg = <0xfd030000 0x4000 0xfd800000 0x4000>;
+ interrupts = <1>;
+ local-mac-address = [00 50 c2 13 6f 00];
+ clocks = <&osc>;
+ };
diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index 58307d0..5b8c589 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -21,10 +21,18 @@
elements.
- max-speed: Maximum PHY supported speed (10, 100, 1000...)
+ If the phy's identifier is known then the list may contain an entry
+ of the form: "ethernet-phy-idAAAA.BBBB" where
+ AAAA - The value of the 16 bit Phy Identifier 1 register as
+ 4 hex digits. This is the chip vendor OUI bits 3:18
+ BBBB - The value of the 16 bit Phy Identifier 2 register as
+ 4 hex digits. This is the chip vendor OUI bits 19:24,
+ followed by 10 bits of a vendor specific ID.
+
Example:
ethernet-phy@0 {
- compatible = "ethernet-phy-ieee802.3-c22";
+ compatible = "ethernet-phy-id0141.0e90", "ethernet-phy-ieee802.3-c22";
interrupt-parent = <40000>;
interrupts = <35 1>;
reg = <0>;
diff --git a/Documentation/devicetree/bindings/net/samsung-sxgbe.txt b/Documentation/devicetree/bindings/net/samsung-sxgbe.txt
new file mode 100644
index 0000000..989f6c9
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/samsung-sxgbe.txt
@@ -0,0 +1,52 @@
+* Samsung 10G Ethernet driver (SXGBE)
+
+Required properties:
+- compatible: Should be "samsung,sxgbe-v2.0a"
+- reg: Address and length of the register set for the device
+- interrupt-parent: Should be the phandle for the interrupt controller
+ that services interrupts for this device
+- interrupts: Should contain the SXGBE interrupts
+ These interrupts are ordered by fixed and follows variable
+ trasmit DMA interrupts, receive DMA interrupts and lpi interrupt.
+ index 0 - this is fixed common interrupt of SXGBE and it is always
+ available.
+ index 1 to 25 - 8 variable trasmit interrupts, variable 16 receive interrupts
+ and 1 optional lpi interrupt.
+- phy-mode: String, operation mode of the PHY interface.
+ Supported values are: "sgmii", "xgmii".
+- samsung,pbl: Integer, Programmable Burst Length.
+ Supported values are 1, 2, 4, 8, 16, or 32.
+- samsung,burst-map: Integer, Program the possible bursts supported by sxgbe
+ This is an interger and represents allowable DMA bursts when fixed burst.
+ Allowable range is 0x01-0x3F. When this field is set fixed burst is enabled.
+ When fixed length is needed for burst mode, it can be set within allowable
+ range.
+
+Optional properties:
+- mac-address: 6 bytes, mac address
+- max-frame-size: Maximum Transfer Unit (IEEE defined MTU), rather
+ than the maximum frame size.
+
+Example:
+
+ aliases {
+ ethernet0 = <&sxgbe0>;
+ };
+
+ sxgbe0: ethernet@1a040000 {
+ compatible = "samsung,sxgbe-v2.0a";
+ reg = <0 0x1a040000 0 0x10000>;
+ interrupt-parent = <&gic>;
+ interrupts = <0 209 4>, <0 185 4>, <0 186 4>, <0 187 4>,
+ <0 188 4>, <0 189 4>, <0 190 4>, <0 191 4>,
+ <0 192 4>, <0 193 4>, <0 194 4>, <0 195 4>,
+ <0 196 4>, <0 197 4>, <0 198 4>, <0 199 4>,
+ <0 200 4>, <0 201 4>, <0 202 4>, <0 203 4>,
+ <0 204 4>, <0 205 4>, <0 206 4>, <0 207 4>,
+ <0 208 4>, <0 210 4>;
+ samsung,pbl = <0x08>
+ samsung,burst-map = <0x20>
+ mac-address = [ 00 11 22 33 44 55 ]; /* Filled in by U-Boot */
+ max-frame-size = <9000>;
+ phy-mode = "xgmii";
+ };
diff --git a/Documentation/devicetree/bindings/net/sh_eth.txt b/Documentation/devicetree/bindings/net/sh_eth.txt
new file mode 100644
index 0000000..e7106b5
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/sh_eth.txt
@@ -0,0 +1,55 @@
+* Renesas Electronics SH EtherMAC
+
+This file provides information on what the device node for the SH EtherMAC
+interface contains.
+
+Required properties:
+- compatible: "renesas,gether-r8a7740" if the device is a part of R8A7740 SoC.
+ "renesas,ether-r8a7778" if the device is a part of R8A7778 SoC.
+ "renesas,ether-r8a7779" if the device is a part of R8A7779 SoC.
+ "renesas,ether-r8a7790" if the device is a part of R8A7790 SoC.
+ "renesas,ether-r8a7791" if the device is a part of R8A7791 SoC.
+ "renesas,ether-r7s72100" if the device is a part of R7S72100 SoC.
+- reg: offset and length of (1) the E-DMAC/feLic register block (required),
+ (2) the TSU register block (optional).
+- interrupts: interrupt specifier for the sole interrupt.
+- phy-mode: see ethernet.txt file in the same directory.
+- phy-handle: see ethernet.txt file in the same directory.
+- #address-cells: number of address cells for the MDIO bus, must be equal to 1.
+- #size-cells: number of size cells on the MDIO bus, must be equal to 0.
+- clocks: clock phandle and specifier pair.
+- pinctrl-0: phandle, referring to a default pin configuration node.
+
+Optional properties:
+- interrupt-parent: the phandle for the interrupt controller that services
+ interrupts for this device.
+- pinctrl-names: pin configuration state name ("default").
+- renesas,no-ether-link: boolean, specify when a board does not provide a proper
+ Ether LINK signal.
+- renesas,ether-link-active-low: boolean, specify when the Ether LINK signal is
+ active-low instead of normal active-high.
+
+Example (Lager board):
+
+ ethernet@ee700000 {
+ compatible = "renesas,ether-r8a7790";
+ reg = <0 0xee700000 0 0x400>;
+ interrupt-parent = <&gic>;
+ interrupts = <0 162 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&mstp8_clks R8A7790_CLK_ETHER>;
+ phy-mode = "rmii";
+ phy-handle = <&phy1>;
+ pinctrl-0 = <ðer_pins>;
+ pinctrl-names = "default";
+ renesas,ether-link-active-low;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ phy1: ethernet-phy@1 {
+ reg = <1>;
+ interrupt-parent = <&irqc0>;
+ interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+ pinctrl-0 = <&phy1_pins>;
+ pinctrl-names = "default";
+ };
+ };
diff --git a/Documentation/devicetree/bindings/net/smsc-lan91c111.txt b/Documentation/devicetree/bindings/net/smsc-lan91c111.txt
index 5a41a865..0f8487b8 100644
--- a/Documentation/devicetree/bindings/net/smsc-lan91c111.txt
+++ b/Documentation/devicetree/bindings/net/smsc-lan91c111.txt
@@ -6,8 +6,7 @@
- interrupts : interrupt connection
Optional properties:
-- phy-device : phandle to Ethernet phy
-- local-mac-address : Ethernet mac address to use
+- phy-device : see ethernet.txt file in the same directory
- reg-io-width : Mask of sizes (in bytes) of the IO accesses that
are supported on the device. Valid value for SMSC LAN91c111 are
1, 2 or 4. If it's omitted or invalid, the size would be 2 meaning
diff --git a/Documentation/devicetree/bindings/net/smsc911x.txt b/Documentation/devicetree/bindings/net/smsc911x.txt
index adb5b57..3fed3c1 100644
--- a/Documentation/devicetree/bindings/net/smsc911x.txt
+++ b/Documentation/devicetree/bindings/net/smsc911x.txt
@@ -6,9 +6,7 @@
- interrupts : Should contain SMSC LAN interrupt line
- interrupt-parent : Should be the phandle for the interrupt controller
that services interrupts for this device
-- phy-mode : String, operation mode of the PHY interface.
- Supported values are: "mii", "gmii", "sgmii", "tbi", "rmii",
- "rgmii", "rgmii-id", "rgmii-rxid", "rgmii-txid", "rtbi", "smii".
+- phy-mode : See ethernet.txt file in the same directory
Optional properties:
- reg-shift : Specify the quantity to shift the register offsets by
@@ -23,7 +21,6 @@
external PHY
- smsc,save-mac-address : Indicates that mac address needs to be saved
before resetting the controller
-- local-mac-address : 6 bytes, mac address
Examples:
diff --git a/Documentation/devicetree/bindings/net/sti-dwmac.txt b/Documentation/devicetree/bindings/net/sti-dwmac.txt
new file mode 100644
index 0000000..3dd3d0b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/sti-dwmac.txt
@@ -0,0 +1,58 @@
+STMicroelectronics SoC DWMAC glue layer controller
+
+The device node has following properties.
+
+Required properties:
+ - compatible : Can be "st,stih415-dwmac", "st,stih416-dwmac" or
+ "st,stid127-dwmac".
+ - reg : Offset of the glue configuration register map in system
+ configuration regmap pointed by st,syscon property and size.
+
+ - reg-names : Should be "sti-ethconf".
+
+ - st,syscon : Should be phandle to system configuration node which
+ encompases this glue registers.
+
+ - st,tx-retime-src: On STi Parts for Giga bit speeds, 125Mhz clocks can be
+ wired up in from different sources. One via TXCLK pin and other via CLK_125
+ pin. This wiring is totally board dependent. However the retiming glue
+ logic should be configured accordingly. Possible values for this property
+
+ "txclk" - if 125Mhz clock is wired up via txclk line.
+ "clk_125" - if 125Mhz clock is wired up via clk_125 line.
+
+ This property is only valid for Giga bit setup( GMII, RGMII), and it is
+ un-used for non-giga bit (MII and RMII) setups. Also note that internal
+ clockgen can not generate stable 125Mhz clock.
+
+ - st,ext-phyclk: This boolean property indicates who is generating the clock
+ for tx and rx. This property is only valid for RMII case where the clock can
+ be generated from the MAC or PHY.
+
+ - clock-names: should be "sti-ethclk".
+ - clocks: Should point to ethernet clockgen which can generate phyclk.
+
+
+Example:
+
+ethernet0: dwmac@fe810000 {
+ device_type = "network";
+ compatible = "st,stih416-dwmac", "snps,dwmac", "snps,dwmac-3.710";
+ reg = <0xfe810000 0x8000>, <0x8bc 0x4>;
+ reg-names = "stmmaceth", "sti-ethconf";
+ interrupts = <0 133 0>, <0 134 0>, <0 135 0>;
+ interrupt-names = "macirq", "eth_wake_irq", "eth_lpi";
+ phy-mode = "mii";
+
+ st,syscon = <&syscfg_rear>;
+
+ snps,pbl = <32>;
+ snps,mixed-burst;
+
+ resets = <&softreset STIH416_ETH0_SOFTRESET>;
+ reset-names = "stmmaceth";
+ pinctrl-0 = <&pinctrl_mii0>;
+ pinctrl-names = "default";
+ clocks = <&CLK_S_GMAC0_PHY>;
+ clock-names = "stmmaceth";
+};
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index 9d92d42..5748351 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -10,8 +10,7 @@
- interrupt-names: Should contain the interrupt names "macirq"
"eth_wake_irq" if this interrupt is supported in the "interrupts"
property
-- phy-mode: String, operation mode of the PHY interface.
- Supported values are: "mii", "rmii", "gmii", "rgmii".
+- phy-mode: See ethernet.txt file in the same directory.
- snps,reset-gpio gpio number for phy reset.
- snps,reset-active-low boolean flag to indicate if phy reset is active low.
- snps,reset-delays-us is triplet of delays
@@ -28,12 +27,10 @@
ignored if force_thresh_dma_mode is set.
Optional properties:
-- mac-address: 6 bytes, mac address
- resets: Should contain a phandle to the STMMAC reset signal, if any
- reset-names: Should contain the reset signal name "stmmaceth", if a
reset phandle is given
-- max-frame-size: Maximum Transfer Unit (IEEE defined MTU), rather
- than the maximum frame size.
+- max-frame-size: See ethernet.txt file in the same directory
Examples:
diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/brcm,bcm11351-pinctrl.txt
similarity index 98%
rename from Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt
rename to Documentation/devicetree/bindings/pinctrl/brcm,bcm11351-pinctrl.txt
index 9e9e9ef..c119deb 100644
--- a/Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/brcm,bcm11351-pinctrl.txt
@@ -1,4 +1,4 @@
-Broadcom Capri Pin Controller
+Broadcom BCM281xx Pin Controller
This is a pin controller for the Broadcom BCM281xx SoC family, which includes
BCM11130, BCM11140, BCM11351, BCM28145, and BCM28155 SoCs.
@@ -7,14 +7,14 @@
Required Properties:
-- compatible: Must be "brcm,capri-pinctrl".
+- compatible: Must be "brcm,bcm11351-pinctrl"
- reg: Base address of the PAD Controller register block and the size
of the block.
For example, the following is the bare minimum node:
pinctrl@35004800 {
- compatible = "brcm,capri-pinctrl";
+ compatible = "brcm,bcm11351-pinctrl";
reg = <0x35004800 0x430>;
};
@@ -119,7 +119,7 @@
Example:
// pin controller node
pinctrl@35004800 {
- compatible = "brcm,capri-pinctrl";
+ compatible = "brcmbcm11351-pinctrl";
reg = <0x35004800 0x430>;
// pin configuration node
diff --git a/Documentation/devicetree/bindings/power/bq2415x.txt b/Documentation/devicetree/bindings/power/bq2415x.txt
new file mode 100644
index 0000000..d0327f0
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/bq2415x.txt
@@ -0,0 +1,47 @@
+Binding for TI bq2415x Li-Ion Charger
+
+Required properties:
+- compatible: Should contain one of the following:
+ * "ti,bq24150"
+ * "ti,bq24150"
+ * "ti,bq24150a"
+ * "ti,bq24151"
+ * "ti,bq24151a"
+ * "ti,bq24152"
+ * "ti,bq24153"
+ * "ti,bq24153a"
+ * "ti,bq24155"
+ * "ti,bq24156"
+ * "ti,bq24156a"
+ * "ti,bq24158"
+- reg: integer, i2c address of the device.
+- ti,current-limit: integer, initial maximum current charger can pull
+ from power supply in mA.
+- ti,weak-battery-voltage: integer, weak battery voltage threshold in mV.
+ The chip will use slow precharge if battery voltage
+ is below this value.
+- ti,battery-regulation-voltage: integer, maximum charging voltage in mV.
+- ti,charge-current: integer, maximum charging current in mA.
+- ti,termination-current: integer, charge will be terminated when current in
+ constant-voltage phase drops below this value (in mA).
+- ti,resistor-sense: integer, value of sensing resistor in milliohm.
+
+Optional properties:
+- ti,usb-charger-detection: phandle to usb charger detection device.
+ (required for auto mode)
+
+Example from Nokia N900:
+
+bq24150a {
+ compatible = "ti,bq24150a";
+ reg = <0x6b>;
+
+ ti,current-limit = <100>;
+ ti,weak-battery-voltage = <3400>;
+ ti,battery-regulation-voltage = <4200>;
+ ti,charge-current = <650>;
+ ti,termination-current = <100>;
+ ti,resistor-sense = <68>;
+
+ ti,usb-charger-detection = <&isp1704>;
+};
diff --git a/Documentation/devicetree/bindings/spi/spi_atmel.txt b/Documentation/devicetree/bindings/spi/spi_atmel.txt
index 07e04cd..4f8184d 100644
--- a/Documentation/devicetree/bindings/spi/spi_atmel.txt
+++ b/Documentation/devicetree/bindings/spi/spi_atmel.txt
@@ -5,6 +5,9 @@
- reg: Address and length of the register set for the device
- interrupts: Should contain spi interrupt
- cs-gpios: chipselects
+- clock-names: tuple listing input clock names.
+ Required elements: "spi_clk"
+- clocks: phandles to input clocks.
Example:
@@ -14,6 +17,8 @@
interrupts = <13 4 5>;
#address-cells = <1>;
#size-cells = <0>;
+ clocks = <&spi1_clk>;
+ clock-names = "spi_clk";
cs-gpios = <&pioB 3 0>;
status = "okay";
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 3f900cd..40ce2df 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -8,6 +8,7 @@
adi Analog Devices, Inc.
aeroflexgaisler Aeroflex Gaisler AB
ak Asahi Kasei Corp.
+allwinner Allwinner Technology Co., Ltd.
altr Altera Corp.
amcc Applied Micro Circuits Corporation (APM, formally AMCC)
amstaos AMS-Taos Inc.
@@ -40,6 +41,7 @@
gumstix Gumstix, Inc.
haoyu Haoyu Microelectronic Co. Ltd.
hisilicon Hisilicon Limited.
+honeywell Honeywell
hp Hewlett Packard
ibm International Business Machines (IBM)
idt Integrated Device Technologies, Inc.
@@ -55,6 +57,7 @@
microchip Microchip Technology Inc.
mosaixtech Mosaix Technologies, Inc.
national National Semiconductor
+neonode Neonode Inc.
nintendo Nintendo
nvidia NVIDIA
nxp NXP Semiconductors
@@ -64,7 +67,7 @@
picochip Picochip Ltd
powervr PowerVR (deprecated, use img)
qca Qualcomm Atheros, Inc.
-qcom Qualcomm, Inc.
+qcom Qualcomm Technologies, Inc
ralink Mediatek/Ralink Technology Corp.
ramtron Ramtron International
realtek Realtek Semiconductor Corp.
@@ -78,6 +81,7 @@
simtek
sirf SiRF Technology, Inc.
snps Synopsys, Inc.
+spansion Spansion Inc.
st STMicroelectronics
ste ST-Ericsson
stericsson ST-Ericsson
diff --git a/Documentation/fb/00-INDEX b/Documentation/fb/00-INDEX
index 30a7054..fe85e7c 100644
--- a/Documentation/fb/00-INDEX
+++ b/Documentation/fb/00-INDEX
@@ -5,6 +5,8 @@
00-INDEX
- this file.
+api.txt
+ - The frame buffer API between applications and buffer devices.
arkfb.txt
- info on the fbdev driver for ARK Logic chips.
aty128fb.txt
@@ -51,12 +53,16 @@
- info on the SH7760/SH7763 integrated LCDC Framebuffer driver.
sisfb.txt
- info on the framebuffer device driver for various SiS chips.
+sm501.txt
+ - info on the framebuffer device driver for sm501 videoframebuffer.
sstfb.txt
- info on the frame buffer driver for 3dfx' Voodoo Graphics boards.
tgafb.txt
- info on the TGA (DECChip 21030) frame buffer driver.
tridentfb.txt
info on the framebuffer driver for some Trident chip based cards.
+udlfb.txt
+ - Driver for DisplayLink USB 2.0 chips.
uvesafb.txt
- info on the userspace VESA (VBE2+ compliant) frame buffer device.
vesafb.txt
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 632211c..ac28149 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -2,6 +2,8 @@
- this file (info on some of the filesystems supported by linux).
Locking
- info on locking rules as they pertain to Linux VFS.
+Makefile
+ - Makefile for building the filsystems-part of DocBook.
9p.txt
- 9p (v9fs) is an implementation of the Plan 9 remote fs protocol.
adfs.txt
diff --git a/Documentation/filesystems/nfs/00-INDEX b/Documentation/filesystems/nfs/00-INDEX
index 66eb6c8..53f3b59 100644
--- a/Documentation/filesystems/nfs/00-INDEX
+++ b/Documentation/filesystems/nfs/00-INDEX
@@ -12,6 +12,8 @@
- info on the Linux server implementation of NFSv4 minor version 1.
nfs-rdma.txt
- how to install and setup the Linux NFS/RDMA client and server software
+nfsd-admin-interfaces.txt
+ - Administrative interfaces for nfsd.
nfsroot.txt
- short guide on setting up a diskless box with NFS root filesystem.
pnfs.txt
@@ -20,5 +22,5 @@
- introduction to the caching mechanisms in the sunrpc layer.
idmapper.txt
- information for configuring request-keys to be used by idmapper
-knfsd-rpcgss.txt
+rpc-server-gss.txt
- Information on GSS authentication support in the NFS Server
diff --git a/Documentation/i2c/instantiating-devices b/Documentation/i2c/instantiating-devices
index c70e7a7..0d85ac19 100644
--- a/Documentation/i2c/instantiating-devices
+++ b/Documentation/i2c/instantiating-devices
@@ -8,8 +8,8 @@
several ways to achieve this, depending on the context and requirements.
-Method 1: Declare the I2C devices by bus number
------------------------------------------------
+Method 1a: Declare the I2C devices by bus number
+------------------------------------------------
This method is appropriate when the I2C bus is a system bus as is the case
for many embedded systems. On such systems, each I2C bus has a number
@@ -51,6 +51,43 @@
they sit on goes away (if ever.)
+Method 1b: Declare the I2C devices via devicetree
+-------------------------------------------------
+
+This method has the same implications as method 1a. The declaration of I2C
+devices is here done via devicetree as subnodes of the master controller.
+
+Example:
+
+ i2c1: i2c@400a0000 {
+ /* ... master properties skipped ... */
+ clock-frequency = <100000>;
+
+ flash@50 {
+ compatible = "atmel,24c256";
+ reg = <0x50>;
+ };
+
+ pca9532: gpio@60 {
+ compatible = "nxp,pca9532";
+ gpio-controller;
+ #gpio-cells = <2>;
+ reg = <0x60>;
+ };
+ };
+
+Here, two devices are attached to the bus using a speed of 100kHz. For
+additional properties which might be needed to set up the device, please refer
+to its devicetree documentation in Documentation/devicetree/bindings/.
+
+
+Method 1c: Declare the I2C devices via ACPI
+-------------------------------------------
+
+ACPI can also describe I2C devices. There is special documentation for this
+which is currently located at Documentation/acpi/enumeration.txt.
+
+
Method 2: Instantiate the devices explicitly
--------------------------------------------
diff --git a/Documentation/ide/00-INDEX b/Documentation/ide/00-INDEX
index d6b7788..22f98ca 100644
--- a/Documentation/ide/00-INDEX
+++ b/Documentation/ide/00-INDEX
@@ -10,3 +10,5 @@
- info on the IDE ATAPI streaming tape driver
ide.txt
- important info for users of ATA devices (IDE/EIDE disks and CD-ROMS).
+warm-plug-howto.txt
+ - using sysfs to remove and add IDE devices.
\ No newline at end of file
diff --git a/Documentation/laptops/00-INDEX b/Documentation/laptops/00-INDEX
index fa68853..d13b9a9 100644
--- a/Documentation/laptops/00-INDEX
+++ b/Documentation/laptops/00-INDEX
@@ -1,13 +1,15 @@
00-INDEX
- This file
-acer-wmi.txt
- - information on the Acer Laptop WMI Extras driver.
+Makefile
+ - Makefile for building dslm example program.
asus-laptop.txt
- information on the Asus Laptop Extras driver.
disk-shock-protection.txt
- information on hard disk shock protection.
dslm.c
- Simple Disk Sleep Monitor program
+hpfall.c
+ - (HP) laptop accelerometer program for disk protection.
laptop-mode.txt
- how to conserve battery power using laptop-mode.
sony-laptop.txt
diff --git a/Documentation/leds/00-INDEX b/Documentation/leds/00-INDEX
index 1ecd159..b4ef1f3 100644
--- a/Documentation/leds/00-INDEX
+++ b/Documentation/leds/00-INDEX
@@ -1,3 +1,7 @@
+00-INDEX
+ - This file
+leds-blinkm.txt
+ - Driver for BlinkM LED-devices.
leds-class.txt
- documents LED handling under Linux.
leds-lp3944.txt
@@ -12,3 +16,7 @@
- description about lp55xx common driver.
leds-lm3556.txt
- notes on how to use the leds-lm3556 driver.
+ledtrig-oneshot.txt
+ - One-shot LED trigger for both sporadic and dense events.
+ledtrig-transient.txt
+ - LED Transient Trigger, one shot timer activation.
diff --git a/Documentation/m68k/00-INDEX b/Documentation/m68k/00-INDEX
index a014e9f..2be8c6b 100644
--- a/Documentation/m68k/00-INDEX
+++ b/Documentation/m68k/00-INDEX
@@ -1,5 +1,7 @@
00-INDEX
- this file
+README.buddha
+ - Amiga Buddha and Catweasel IDE Driver
kernel-options.txt
- command line options for Linux/m68k
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index f11580f..557b6ef 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -6,8 +6,14 @@
- information on the 3Com Etherlink III Series Ethernet cards.
6pack.txt
- info on the 6pack protocol, an alternative to KISS for AX.25
-DLINK.txt
- - info on the D-Link DE-600/DE-620 parallel port pocket adapters
+LICENSE.qla3xxx
+ - GPLv2 for QLogic Linux Networking HBA Driver
+LICENSE.qlge
+ - GPLv2 for QLogic Linux qlge NIC Driver
+LICENSE.qlcnic
+ - GPLv2 for QLogic Linux qlcnic NIC Driver
+Makefile
+ - Makefile for docsrc.
PLIP.txt
- PLIP: The Parallel Line Internet Protocol device driver
README.ipw2100
@@ -17,7 +23,7 @@
README.sb1000
- info on General Instrument/NextLevel SURFboard1000 cable modem.
alias.txt
- - info on using alias network devices
+ - info on using alias network devices.
arcnet-hardware.txt
- tons of info on ARCnet, hubs, jumper settings for ARCnet cards, etc.
arcnet.txt
@@ -80,7 +86,7 @@
- info on using Frame Relay/Data Link Connection Identifier (DLCI).
gen_stats.txt
- Generic networking statistics for netlink users.
-generic_hdlc.txt
+generic-hdlc.txt
- The generic High Level Data Link Control (HDLC) layer.
generic_netlink.txt
- info on Generic Netlink
@@ -88,6 +94,8 @@
- Gianfar Ethernet Driver.
i40e.txt
- README for the Intel Ethernet Controller XL710 Driver (i40e).
+i40evf.txt
+ - Short note on the Driver for the Intel(R) XL710 X710 Virtual Function
ieee802154.txt
- Linux IEEE 802.15.4 implementation, API and drivers
igb.txt
@@ -102,6 +110,8 @@
- AppleTalk-IP Decapsulation and AppleTalk-IP Encapsulation
iphase.txt
- Interphase PCI ATM (i)Chip IA Linux driver info.
+ipsec.txt
+ - Note on not compressing IPSec payload and resulting failed policy check.
ipv6.txt
- Options to the ipv6 kernel module.
ipvs-sysctl.txt
@@ -120,6 +130,8 @@
- programming information of the LAPB module.
ltpc.txt
- the Apple or Farallon LocalTalk PC card driver
+mac80211-auth-assoc-deauth.txt
+ - authentication and association / deauth-disassoc with max80211
mac80211-injection.txt
- HOWTO use packet injection with mac80211
multiqueue.txt
@@ -134,6 +146,10 @@
- info on network device driver functions exported to the kernel.
netif-msg.txt
- Design of the network interface message level setting (NETIF_MSG_*).
+netlink_mmap.txt
+ - memory mapped I/O with netlink
+nf_conntrack-sysctl.txt
+ - list of netfilter-sysctl knobs.
nfc.txt
- The Linux Near Field Communication (NFS) subsystem.
openvswitch.txt
@@ -176,7 +192,7 @@
- SysKonnect FDDI (SK-5xxx, Compaq Netelligent) driver info.
smc9.txt
- the driver for SMC's 9000 series of Ethernet cards
-spider-net.txt
+spider_net.txt
- README for the Spidernet Driver (as found in PS3 / Cell BE).
stmmac.txt
- README for the STMicro Synopsys Ethernet driver.
@@ -188,6 +204,8 @@
- short blurb on how TCP output takes place.
tcp-thin.txt
- kernel tuning options for low rate 'thin' TCP streams.
+team.txt
+ - pointer to information for ethernet teaming devices.
tlan.txt
- ThunderLAN (Compaq Netelligent 10/100, Olicom OC-2xxx) driver info.
tproxy.txt
@@ -200,6 +218,8 @@
- info on using 3Com Vortex (3c590, 3c592, 3c595, 3c597) Ethernet cards.
vxge.txt
- README for the Neterion X3100 PCIe Server Adapter.
+vxlan.txt
+ - Virtual extensible LAN overview
x25.txt
- general info on X.25 development.
x25-iface.txt
diff --git a/Documentation/networking/3c505.txt b/Documentation/networking/3c505.txt
deleted file mode 100644
index 72f38b1..0000000
--- a/Documentation/networking/3c505.txt
+++ /dev/null
@@ -1,45 +0,0 @@
-The 3Com Etherlink Plus (3c505) driver.
-
-This driver now uses DMA. There is currently no support for PIO operation.
-The default DMA channel is 6; this is _not_ autoprobed, so you must
-make sure you configure it correctly. If loading the driver as a
-module, you can do this with "modprobe 3c505 dma=n". If the driver is
-linked statically into the kernel, you must either use an "ether="
-statement on the command line, or change the definition of ELP_DMA in 3c505.h.
-
-The driver will warn you if it has to fall back on the compiled in
-default DMA channel.
-
-If no base address is given at boot time, the driver will autoprobe
-ports 0x300, 0x280 and 0x310 (in that order). If no IRQ is given, the driver
-will try to probe for it.
-
-The driver can be used as a loadable module.
-
-Theoretically, one instance of the driver can now run multiple cards,
-in the standard way (when loading a module, say "modprobe 3c505
-io=0x300,0x340 irq=10,11 dma=6,7" or whatever). I have not tested
-this, though.
-
-The driver may now support revision 2 hardware; the dependency on
-being able to read the host control register has been removed. This
-is also untested, since I don't have a suitable card.
-
-Known problems:
- I still see "DMA upload timed out" messages from time to time. These
-seem to be fairly non-fatal though.
- The card is old and slow.
-
-To do:
- Improve probe/setup code
- Test multicast and promiscuous operation
-
-Authors:
- The driver is mainly written by Craig Southeren, email
- <craigs@ineluki.apana.org.au>.
- Parts of the driver (adapting the driver to 1.1.4+ kernels,
- IRQ/address detection, some changes) and this README by
- Juha Laiho <jlaiho@ichaos.nullnet.fi>.
- DMA mode, more fixes, etc, by Philip Blundell <pjb27@cam.ac.uk>
- Multicard support, Software configurable DMA, etc., by
- Christopher Collins <ccollins@pcug.org.au>
diff --git a/Documentation/networking/altera_tse.txt b/Documentation/networking/altera_tse.txt
new file mode 100644
index 0000000..3f24df8
--- /dev/null
+++ b/Documentation/networking/altera_tse.txt
@@ -0,0 +1,263 @@
+ Altera Triple-Speed Ethernet MAC driver
+
+Copyright (C) 2008-2014 Altera Corporation
+
+This is the driver for the Altera Triple-Speed Ethernet (TSE) controllers
+using the SGDMA and MSGDMA soft DMA IP components. The driver uses the
+platform bus to obtain component resources. The designs used to test this
+driver were built for a Cyclone(R) V SOC FPGA board, a Cyclone(R) V FPGA board,
+and tested with ARM and NIOS processor hosts seperately. The anticipated use
+cases are simple communications between an embedded system and an external peer
+for status and simple configuration of the embedded system.
+
+For more information visit www.altera.com and www.rocketboards.org. Support
+forums for the driver may be found on www.rocketboards.org, and a design used
+to test this driver may be found there as well. Support is also available from
+the maintainer of this driver, found in MAINTAINERS.
+
+The Triple-Speed Ethernet, SGDMA, and MSGDMA components are all soft IP
+components that can be assembled and built into an FPGA using the Altera
+Quartus toolchain. Quartus 13.1 and 14.0 were used to build the design that
+this driver was tested against. The sopc2dts tool is used to create the
+device tree for the driver, and may be found at rocketboards.org.
+
+The driver probe function examines the device tree and determines if the
+Triple-Speed Ethernet instance is using an SGDMA or MSGDMA component. The
+probe function then installs the appropriate set of DMA routines to
+initialize, setup transmits, receives, and interrupt handling primitives for
+the respective configurations.
+
+The SGDMA component is to be deprecated in the near future (over the next 1-2
+years as of this writing in early 2014) in favor of the MSGDMA component.
+SGDMA support is included for existing designs and reference in case a
+developer wishes to support their own soft DMA logic and driver support. Any
+new designs should not use the SGDMA.
+
+The SGDMA supports only a single transmit or receive operation at a time, and
+therefore will not perform as well compared to the MSGDMA soft IP. Please
+visit www.altera.com for known, documented SGDMA errata.
+
+Scatter-gather DMA is not supported by the SGDMA or MSGDMA at this time.
+Scatter-gather DMA will be added to a future maintenance update to this
+driver.
+
+Jumbo frames are not supported at this time.
+
+The driver limits PHY operations to 10/100Mbps, and has not yet been fully
+tested for 1Gbps. This support will be added in a future maintenance update.
+
+1) Kernel Configuration
+The kernel configuration option is ALTERA_TSE:
+ Device Drivers ---> Network device support ---> Ethernet driver support --->
+ Altera Triple-Speed Ethernet MAC support (ALTERA_TSE)
+
+2) Driver parameters list:
+ debug: message level (0: no output, 16: all);
+ dma_rx_num: Number of descriptors in the RX list (default is 64);
+ dma_tx_num: Number of descriptors in the TX list (default is 64).
+
+3) Command line options
+Driver parameters can be also passed in command line by using:
+ altera_tse=dma_rx_num:128,dma_tx_num:512
+
+4) Driver information and notes
+
+4.1) Transmit process
+When the driver's transmit routine is called by the kernel, it sets up a
+transmit descriptor by calling the underlying DMA transmit routine (SGDMA or
+MSGDMA), and initites a transmit operation. Once the transmit is complete, an
+interrupt is driven by the transmit DMA logic. The driver handles the transmit
+completion in the context of the interrupt handling chain by recycling
+resource required to send and track the requested transmit operation.
+
+4.2) Receive process
+The driver will post receive buffers to the receive DMA logic during driver
+intialization. Receive buffers may or may not be queued depending upon the
+underlying DMA logic (MSGDMA is able queue receive buffers, SGDMA is not able
+to queue receive buffers to the SGDMA receive logic). When a packet is
+received, the DMA logic generates an interrupt. The driver handles a receive
+interrupt by obtaining the DMA receive logic status, reaping receive
+completions until no more receive completions are available.
+
+4.3) Interrupt Mitigation
+The driver is able to mitigate the number of its DMA interrupts
+using NAPI for receive operations. Interrupt mitigation is not yet supported
+for transmit operations, but will be added in a future maintenance release.
+
+4.4) Ethtool support
+Ethtool is supported. Driver statistics and internal errors can be taken using:
+ethtool -S ethX command. It is possible to dump registers etc.
+
+4.5) PHY Support
+The driver is compatible with PAL to work with PHY and GPHY devices.
+
+4.7) List of source files:
+ o Kconfig
+ o Makefile
+ o altera_tse_main.c: main network device driver
+ o altera_tse_ethtool.c: ethtool support
+ o altera_tse.h: private driver structure and common definitions
+ o altera_msgdma.h: MSGDMA implementation function definitions
+ o altera_sgdma.h: SGDMA implementation function definitions
+ o altera_msgdma.c: MSGDMA implementation
+ o altera_sgdma.c: SGDMA implementation
+ o altera_sgdmahw.h: SGDMA register and descriptor definitions
+ o altera_msgdmahw.h: MSGDMA register and descriptor definitions
+ o altera_utils.c: Driver utility functions
+ o altera_utils.h: Driver utility function definitions
+
+5) Debug Information
+
+The driver exports debug information such as internal statistics,
+debug information, MAC and DMA registers etc.
+
+A user may use the ethtool support to get statistics:
+e.g. using: ethtool -S ethX (that shows the statistics counters)
+or sees the MAC registers: e.g. using: ethtool -d ethX
+
+The developer can also use the "debug" module parameter to get
+further debug information.
+
+6) Statistics Support
+
+The controller and driver support a mix of IEEE standard defined statistics,
+RFC defined statistics, and driver or Altera defined statistics. The four
+specifications containing the standard definitions for these statistics are
+as follows:
+
+ o IEEE 802.3-2012 - IEEE Standard for Ethernet.
+ o RFC 2863 found at http://www.rfc-editor.org/rfc/rfc2863.txt.
+ o RFC 2819 found at http://www.rfc-editor.org/rfc/rfc2819.txt.
+ o Altera Triple Speed Ethernet User Guide, found at http://www.altera.com
+
+The statistics supported by the TSE and the device driver are as follows:
+
+"tx_packets" is equivalent to aFramesTransmittedOK defined in IEEE 802.3-2012,
+Section 5.2.2.1.2. This statistics is the count of frames that are successfully
+transmitted.
+
+"rx_packets" is equivalent to aFramesReceivedOK defined in IEEE 802.3-2012,
+Section 5.2.2.1.5. This statistic is the count of frames that are successfully
+received. This count does not include any error packets such as CRC errors,
+length errors, or alignment errors.
+
+"rx_crc_errors" is equivalent to aFrameCheckSequenceErrors defined in IEEE
+802.3-2012, Section 5.2.2.1.6. This statistic is the count of frames that are
+an integral number of bytes in length and do not pass the CRC test as the frame
+is received.
+
+"rx_align_errors" is equivalent to aAlignmentErrors defined in IEEE 802.3-2012,
+Section 5.2.2.1.7. This statistic is the count of frames that are not an
+integral number of bytes in length and do not pass the CRC test as the frame is
+received.
+
+"tx_bytes" is equivalent to aOctetsTransmittedOK defined in IEEE 802.3-2012,
+Section 5.2.2.1.8. This statistic is the count of data and pad bytes
+successfully transmitted from the interface.
+
+"rx_bytes" is equivalent to aOctetsReceivedOK defined in IEEE 802.3-2012,
+Section 5.2.2.1.14. This statistic is the count of data and pad bytes
+successfully received by the controller.
+
+"tx_pause" is equivalent to aPAUSEMACCtrlFramesTransmitted defined in IEEE
+802.3-2012, Section 30.3.4.2. This statistic is a count of PAUSE frames
+transmitted from the network controller.
+
+"rx_pause" is equivalent to aPAUSEMACCtrlFramesReceived defined in IEEE
+802.3-2012, Section 30.3.4.3. This statistic is a count of PAUSE frames
+received by the network controller.
+
+"rx_errors" is equivalent to ifInErrors defined in RFC 2863. This statistic is
+a count of the number of packets received containing errors that prevented the
+packet from being delivered to a higher level protocol.
+
+"tx_errors" is equivalent to ifOutErrors defined in RFC 2863. This statistic
+is a count of the number of packets that could not be transmitted due to errors.
+
+"rx_unicast" is equivalent to ifInUcastPkts defined in RFC 2863. This
+statistic is a count of the number of packets received that were not addressed
+to the broadcast address or a multicast group.
+
+"rx_multicast" is equivalent to ifInMulticastPkts defined in RFC 2863. This
+statistic is a count of the number of packets received that were addressed to
+a multicast address group.
+
+"rx_broadcast" is equivalent to ifInBroadcastPkts defined in RFC 2863. This
+statistic is a count of the number of packets received that were addressed to
+the broadcast address.
+
+"tx_discards" is equivalent to ifOutDiscards defined in RFC 2863. This
+statistic is the number of outbound packets not transmitted even though an
+error was not detected. An example of a reason this might occur is to free up
+internal buffer space.
+
+"tx_unicast" is equivalent to ifOutUcastPkts defined in RFC 2863. This
+statistic counts the number of packets transmitted that were not addressed to
+a multicast group or broadcast address.
+
+"tx_multicast" is equivalent to ifOutMulticastPkts defined in RFC 2863. This
+statistic counts the number of packets transmitted that were addressed to a
+multicast group.
+
+"tx_broadcast" is equivalent to ifOutBroadcastPkts defined in RFC 2863. This
+statistic counts the number of packets transmitted that were addressed to a
+broadcast address.
+
+"ether_drops" is equivalent to etherStatsDropEvents defined in RFC 2819.
+This statistic counts the number of packets dropped due to lack of internal
+controller resources.
+
+"rx_total_bytes" is equivalent to etherStatsOctets defined in RFC 2819.
+This statistic counts the total number of bytes received by the controller,
+including error and discarded packets.
+
+"rx_total_packets" is equivalent to etherStatsPkts defined in RFC 2819.
+This statistic counts the total number of packets received by the controller,
+including error, discarded, unicast, multicast, and broadcast packets.
+
+"rx_undersize" is equivalent to etherStatsUndersizePkts defined in RFC 2819.
+This statistic counts the number of correctly formed packets received less
+than 64 bytes long.
+
+"rx_oversize" is equivalent to etherStatsOversizePkts defined in RFC 2819.
+This statistic counts the number of correctly formed packets greater than 1518
+bytes long.
+
+"rx_64_bytes" is equivalent to etherStatsPkts64Octets defined in RFC 2819.
+This statistic counts the total number of packets received that were 64 octets
+in length.
+
+"rx_65_127_bytes" is equivalent to etherStatsPkts65to127Octets defined in RFC
+2819. This statistic counts the total number of packets received that were
+between 65 and 127 octets in length inclusive.
+
+"rx_128_255_bytes" is equivalent to etherStatsPkts128to255Octets defined in
+RFC 2819. This statistic is the total number of packets received that were
+between 128 and 255 octets in length inclusive.
+
+"rx_256_511_bytes" is equivalent to etherStatsPkts256to511Octets defined in
+RFC 2819. This statistic is the total number of packets received that were
+between 256 and 511 octets in length inclusive.
+
+"rx_512_1023_bytes" is equivalent to etherStatsPkts512to1023Octets defined in
+RFC 2819. This statistic is the total number of packets received that were
+between 512 and 1023 octets in length inclusive.
+
+"rx_1024_1518_bytes" is equivalent to etherStatsPkts1024to1518Octets define
+in RFC 2819. This statistic is the total number of packets received that were
+between 1024 and 1518 octets in length inclusive.
+
+"rx_gte_1519_bytes" is a statistic defined specific to the behavior of the
+Altera TSE. This statistics counts the number of received good and errored
+frames between the length of 1519 and the maximum frame length configured
+in the frm_length register. See the Altera TSE User Guide for More details.
+
+"rx_jabbers" is equivalent to etherStatsJabbers defined in RFC 2819. This
+statistic is the total number of packets received that were longer than 1518
+octets, and had either a bad CRC with an integral number of octets (CRC Error)
+or a bad CRC with a non-integral number of octets (Alignment Error).
+
+"rx_runts" is equivalent to etherStatsFragments defined in RFC 2819. This
+statistic is the total number of packets received that were less than 64 octets
+in length and had either a bad CRC with an integral number of octets (CRC
+error) or a bad CRC with a non-integral number of octets (Alignment Error).
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index 5cdb229..a383c00 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -270,16 +270,15 @@
arp_validate
Specifies whether or not ARP probes and replies should be
- validated in the active-backup mode. This causes the ARP
- monitor to examine the incoming ARP requests and replies, and
- only consider a slave to be up if it is receiving the
- appropriate ARP traffic.
+ validated in any mode that supports arp monitoring, or whether
+ non-ARP traffic should be filtered (disregarded) for link
+ monitoring purposes.
Possible values are:
none or 0
- No validation is performed. This is the default.
+ No validation or filtering is performed.
active or 1
@@ -293,31 +292,68 @@
Validation is performed for all slaves.
- For the active slave, the validation checks ARP replies to
- confirm that they were generated by an arp_ip_target. Since
- backup slaves do not typically receive these replies, the
- validation performed for backup slaves is on the ARP request
- sent out via the active slave. It is possible that some
- switch or network configurations may result in situations
- wherein the backup slaves do not receive the ARP requests; in
- such a situation, validation of backup slaves must be
- disabled.
+ filter or 4
- The validation of ARP requests on backup slaves is mainly
- helping bonding to decide which slaves are more likely to
- work in case of the active slave failure, it doesn't really
- guarantee that the backup slave will work if it's selected
- as the next active slave.
+ Filtering is applied to all slaves. No validation is
+ performed.
- This option is useful in network configurations in which
- multiple bonding hosts are concurrently issuing ARPs to one or
- more targets beyond a common switch. Should the link between
- the switch and target fail (but not the switch itself), the
- probe traffic generated by the multiple bonding instances will
- fool the standard ARP monitor into considering the links as
- still up. Use of the arp_validate option can resolve this, as
- the ARP monitor will only consider ARP requests and replies
- associated with its own instance of bonding.
+ filter_active or 5
+
+ Filtering is applied to all slaves, validation is performed
+ only for the active slave.
+
+ filter_backup or 6
+
+ Filtering is applied to all slaves, validation is performed
+ only for backup slaves.
+
+ Validation:
+
+ Enabling validation causes the ARP monitor to examine the incoming
+ ARP requests and replies, and only consider a slave to be up if it
+ is receiving the appropriate ARP traffic.
+
+ For an active slave, the validation checks ARP replies to confirm
+ that they were generated by an arp_ip_target. Since backup slaves
+ do not typically receive these replies, the validation performed
+ for backup slaves is on the broadcast ARP request sent out via the
+ active slave. It is possible that some switch or network
+ configurations may result in situations wherein the backup slaves
+ do not receive the ARP requests; in such a situation, validation
+ of backup slaves must be disabled.
+
+ The validation of ARP requests on backup slaves is mainly helping
+ bonding to decide which slaves are more likely to work in case of
+ the active slave failure, it doesn't really guarantee that the
+ backup slave will work if it's selected as the next active slave.
+
+ Validation is useful in network configurations in which multiple
+ bonding hosts are concurrently issuing ARPs to one or more targets
+ beyond a common switch. Should the link between the switch and
+ target fail (but not the switch itself), the probe traffic
+ generated by the multiple bonding instances will fool the standard
+ ARP monitor into considering the links as still up. Use of
+ validation can resolve this, as the ARP monitor will only consider
+ ARP requests and replies associated with its own instance of
+ bonding.
+
+ Filtering:
+
+ Enabling filtering causes the ARP monitor to only use incoming ARP
+ packets for link availability purposes. Arriving packets that are
+ not ARPs are delivered normally, but do not count when determining
+ if a slave is available.
+
+ Filtering operates by only considering the reception of ARP
+ packets (any ARP packet, regardless of source or destination) when
+ determining if a slave has received traffic for link availability
+ purposes.
+
+ Filtering is useful in network configurations in which significant
+ levels of third party broadcast traffic would fool the standard
+ ARP monitor into considering the links as still up. Use of
+ filtering can resolve this, as only ARP traffic is considered for
+ link availability purposes.
This option was added in bonding version 3.1.0.
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index f3089d4..0cbe6ec 100644
--- a/Documentation/networking/can.txt
+++ b/Documentation/networking/can.txt
@@ -554,12 +554,6 @@
not specified in the struct can_frame and therefore it is only valid in
CANFD_MTU sized CAN FD frames.
- As long as the payload length is <=8 the received CAN frames from CAN FD
- capable CAN devices can be received and read by legacy sockets too. When
- user-generated CAN FD frames have a payload length <=8 these can be send
- by legacy CAN network interfaces too. Sending CAN FD frames with payload
- length > 8 to a legacy CAN network interface returns an -EMSGSIZE error.
-
Implementation hint for new CAN applications:
To build a CAN FD aware application use struct canfd_frame as basic CAN
diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index a06b48d..81f940f 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -546,6 +546,130 @@
For BPF JIT developers, bpf_jit_disasm, bpf_asm and bpf_dbg provides a useful
toolchain for developing and testing the kernel's JIT compiler.
+BPF kernel internals
+--------------------
+Internally, for the kernel interpreter, a different BPF instruction set
+format with similar underlying principles from BPF described in previous
+paragraphs is being used. However, the instruction set format is modelled
+closer to the underlying architecture to mimic native instruction sets, so
+that a better performance can be achieved (more details later).
+
+It is designed to be JITed with one to one mapping, which can also open up
+the possibility for GCC/LLVM compilers to generate optimized BPF code through
+a BPF backend that performs almost as fast as natively compiled code.
+
+The new instruction set was originally designed with the possible goal in
+mind to write programs in "restricted C" and compile into BPF with a optional
+GCC/LLVM backend, so that it can just-in-time map to modern 64-bit CPUs with
+minimal performance overhead over two steps, that is, C -> BPF -> native code.
+
+Currently, the new format is being used for running user BPF programs, which
+includes seccomp BPF, classic socket filters, cls_bpf traffic classifier,
+team driver's classifier for its load-balancing mode, netfilter's xt_bpf
+extension, PTP dissector/classifier, and much more. They are all internally
+converted by the kernel into the new instruction set representation and run
+in the extended interpreter. For in-kernel handlers, this all works
+transparently by using sk_unattached_filter_create() for setting up the
+filter, resp. sk_unattached_filter_destroy() for destroying it. The macro
+SK_RUN_FILTER(filter, ctx) transparently invokes the right BPF function to
+run the filter. 'filter' is a pointer to struct sk_filter that we got from
+sk_unattached_filter_create(), and 'ctx' the given context (e.g. skb pointer).
+All constraints and restrictions from sk_chk_filter() apply before a
+conversion to the new layout is being done behind the scenes!
+
+Currently, for JITing, the user BPF format is being used and current BPF JIT
+compilers reused whenever possible. In other words, we do not (yet!) perform
+a JIT compilation in the new layout, however, future work will successively
+migrate traditional JIT compilers into the new instruction format as well, so
+that they will profit from the very same benefits. Thus, when speaking about
+JIT in the following, a JIT compiler (TBD) for the new instruction format is
+meant in this context.
+
+Some core changes of the new internal format:
+
+- Number of registers increase from 2 to 10:
+
+ The old format had two registers A and X, and a hidden frame pointer. The
+ new layout extends this to be 10 internal registers and a read-only frame
+ pointer. Since 64-bit CPUs are passing arguments to functions via registers
+ the number of args from BPF program to in-kernel function is restricted
+ to 5 and one register is used to accept return value from an in-kernel
+ function. Natively, x86_64 passes first 6 arguments in registers, aarch64/
+ sparcv9/mips64 have 7 - 8 registers for arguments; x86_64 has 6 callee saved
+ registers, and aarch64/sparcv9/mips64 have 11 or more callee saved registers.
+
+ Therefore, BPF calling convention is defined as:
+
+ * R0 - return value from in-kernel function
+ * R1 - R5 - arguments from BPF program to in-kernel function
+ * R6 - R9 - callee saved registers that in-kernel function will preserve
+ * R10 - read-only frame pointer to access stack
+
+ Thus, all BPF registers map one to one to HW registers on x86_64, aarch64,
+ etc, and BPF calling convention maps directly to ABIs used by the kernel on
+ 64-bit architectures.
+
+ On 32-bit architectures JIT may map programs that use only 32-bit arithmetic
+ and may let more complex programs to be interpreted.
+
+ R0 - R5 are scratch registers and BPF program needs spill/fill them if
+ necessary across calls. Note that there is only one BPF program (== one BPF
+ main routine) and it cannot call other BPF functions, it can only call
+ predefined in-kernel functions, though.
+
+- Register width increases from 32-bit to 64-bit:
+
+ Still, the semantics of the original 32-bit ALU operations are preserved
+ via 32-bit subregisters. All BPF registers are 64-bit with 32-bit lower
+ subregisters that zero-extend into 64-bit if they are being written to.
+ That behavior maps directly to x86_64 and arm64 subregister definition, but
+ makes other JITs more difficult.
+
+ 32-bit architectures run 64-bit internal BPF programs via interpreter.
+ Their JITs may convert BPF programs that only use 32-bit subregisters into
+ native instruction set and let the rest being interpreted.
+
+ Operation is 64-bit, because on 64-bit architectures, pointers are also
+ 64-bit wide, and we want to pass 64-bit values in/out of kernel functions,
+ so 32-bit BPF registers would otherwise require to define register-pair
+ ABI, thus, there won't be able to use a direct BPF register to HW register
+ mapping and JIT would need to do combine/split/move operations for every
+ register in and out of the function, which is complex, bug prone and slow.
+ Another reason is the use of atomic 64-bit counters.
+
+- Conditional jt/jf targets replaced with jt/fall-through:
+
+ While the original design has constructs such as "if (cond) jump_true;
+ else jump_false;", they are being replaced into alternative constructs like
+ "if (cond) jump_true; /* else fall-through */".
+
+- Introduces bpf_call insn and register passing convention for zero overhead
+ calls from/to other kernel functions:
+
+ After a kernel function call, R1 - R5 are reset to unreadable and R0 has a
+ return type of the function. Since R6 - R9 are callee saved, their state is
+ preserved across the call.
+
+Also in the new design, BPF is limited to 4096 insns, which means that any
+program will terminate quickly and will only call a fixed number of kernel
+functions. Original BPF and the new format are two operand instructions,
+which helps to do one-to-one mapping between BPF insn and x86 insn during JIT.
+
+The input context pointer for invoking the interpreter function is generic,
+its content is defined by a specific use case. For seccomp register R1 points
+to seccomp_data, for converted BPF filters R1 points to a skb.
+
+A program, that is translated internally consists of the following elements:
+
+ op:16, jt:8, jf:8, k:32 ==> op:8, a_reg:4, x_reg:4, off:16, imm:32
+
+Just like the original BPF, the new format runs within a controlled environment,
+is deterministic and the kernel can easily prove that. The safety of the program
+can be determined in two steps: first step does depth-first-search to disallow
+loops and other CFG validation; second step starts from the first insn and
+descends all possible paths. It simulates execution of every insn and observes
+the state change of registers and stack.
+
Misc
----
@@ -561,3 +685,4 @@
Jay Schulist <jschlst@samba.org>
Daniel Borkmann <dborkman@redhat.com>
+Alexei Starovoitov <ast@plumgrid.com>
diff --git a/Documentation/networking/gianfar.txt b/Documentation/networking/gianfar.txt
index ad474ea..ba1daea 100644
--- a/Documentation/networking/gianfar.txt
+++ b/Documentation/networking/gianfar.txt
@@ -1,38 +1,8 @@
The Gianfar Ethernet Driver
-Sysfs File description
Author: Andy Fleming <afleming@freescale.com>
Updated: 2005-07-28
-SYSFS
-
-Several of the features of the gianfar driver are controlled
-through sysfs files. These are:
-
-bd_stash:
-To stash RX Buffer Descriptors in the L2, echo 'on' or '1' to
-bd_stash, echo 'off' or '0' to disable
-
-rx_stash_len:
-To stash the first n bytes of the packet in L2, echo the number
-of bytes to buf_stash_len. echo 0 to disable.
-
-WARNING: You could really screw these up if you set them too low or high!
-fifo_threshold:
-To change the number of bytes the controller needs in the
-fifo before it starts transmission, echo the number of bytes to
-fifo_thresh. Range should be 0-511.
-
-fifo_starve:
-When the FIFO has less than this many bytes during a transmit, it
-enters starve mode, and increases the priority of TX memory
-transactions. To change, echo the number of bytes to
-fifo_starve. Range should be 0-511.
-
-fifo_starve_off:
-Once in starve mode, the FIFO remains there until it has this
-many bytes. To change, echo the number of bytes to
-fifo_starve_off. Range should be 0-511.
CHECKSUM OFFLOADING
diff --git a/Documentation/networking/igb.txt b/Documentation/networking/igb.txt
index 4ebbd65..43d3549 100644
--- a/Documentation/networking/igb.txt
+++ b/Documentation/networking/igb.txt
@@ -36,54 +36,6 @@
This parameter adds support for SR-IOV. It causes the driver to spawn up to
max_vfs worth of virtual function.
-QueuePairs
-----------
-Valid Range: 0-1
-Default Value: 1 (TX and RX will be paired onto one interrupt vector)
-
-If set to 0, when MSI-X is enabled, the TX and RX will attempt to occupy
-separate vectors.
-
-This option can be overridden to 1 if there are not sufficient interrupts
-available. This can occur if any combination of RSS, VMDQ, and max_vfs
-results in more than 4 queues being used.
-
-Node
-----
-Valid Range: 0-n
-Default Value: -1 (off)
-
- 0 - n: where n is the number of the NUMA node that should be used to
- allocate memory for this adapter port.
- -1: uses the driver default of allocating memory on whichever processor is
- running insmod/modprobe.
-
- The Node parameter will allow you to pick which NUMA node you want to have
- the adapter allocate memory from. All driver structures, in-memory queues,
- and receive buffers will be allocated on the node specified. This parameter
- is only useful when interrupt affinity is specified, otherwise some portion
- of the time the interrupt could run on a different core than the memory is
- allocated on, causing slower memory access and impacting throughput, CPU, or
- both.
-
-EEE
----
-Valid Range: 0-1
-Default Value: 1 (enabled)
-
- A link between two EEE-compliant devices will result in periodic bursts of
- data followed by long periods where in the link is in an idle state. This Low
- Power Idle (LPI) state is supported in both 1Gbps and 100Mbps link speeds.
- NOTE: EEE support requires autonegotiation.
-
-DMAC
-----
-Valid Range: 0-1
-Default Value: 1 (enabled)
- Enables or disables DMA Coalescing feature.
-
-
-
Additional Configurations
=========================
diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt
index b261229..c6af4ba 100644
--- a/Documentation/networking/netlink_mmap.txt
+++ b/Documentation/networking/netlink_mmap.txt
@@ -226,9 +226,9 @@
void *rx_ring, *tx_ring;
/* Configure ring parameters */
- if (setsockopt(fd, NETLINK_RX_RING, &req, sizeof(req)) < 0)
+ if (setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, &req, sizeof(req)) < 0)
exit(1);
- if (setsockopt(fd, NETLINK_TX_RING, &req, sizeof(req)) < 0)
+ if (setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, &req, sizeof(req)) < 0)
exit(1)
/* Calculate size of each individual ring */
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index 1404674..6fea79e 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -453,7 +453,7 @@
enabled previously with setsockopt() and
the PACKET_COPY_THRESH option.
- The number of frames than can be buffered to
+ The number of frames that can be buffered to
be read with recvfrom is limited like a normal socket.
See the SO_RCVBUF option in the socket (7) man page.
diff --git a/Documentation/networking/phy.txt b/Documentation/networking/phy.txt
index ebf2707..3544c98 100644
--- a/Documentation/networking/phy.txt
+++ b/Documentation/networking/phy.txt
@@ -48,7 +48,7 @@
time, so it is safe for them to block, waiting for an interrupt to signal
the operation is complete
- 2) A reset function is necessary. This is used to return the bus to an
+ 2) A reset function is optional. This is used to return the bus to an
initialized state.
3) A probe function is needed. This function should set up anything the bus
@@ -253,16 +253,25 @@
Each driver consists of a number of function pointers:
+ soft_reset: perform a PHY software reset
config_init: configures PHY into a sane state after a reset.
For instance, a Davicom PHY requires descrambling disabled.
probe: Allocate phy->priv, optionally refuse to bind.
PHY may not have been reset or had fixups run yet.
suspend/resume: power management
config_aneg: Changes the speed/duplex/negotiation settings
+ aneg_done: Determines the auto-negotiation result
read_status: Reads the current speed/duplex/negotiation settings
ack_interrupt: Clear a pending interrupt
+ did_interrupt: Checks if the PHY generated an interrupt
config_intr: Enable or disable interrupts
remove: Does any driver take-down
+ ts_info: Queries about the HW timestamping status
+ hwtstamp: Set the PHY HW timestamping configuration
+ rxtstamp: Requests a receive timestamp at the PHY level for a 'skb'
+ txtsamp: Requests a transmit timestamp at the PHY level for a 'skb'
+ set_wol: Enable Wake-on-LAN at the PHY level
+ get_wol: Get the Wake-on-LAN status at the PHY level
Of these, only config_aneg and read_status are required to be
assigned by the driver code. The rest are optional. Also, it is
diff --git a/Documentation/networking/pktgen.txt b/Documentation/networking/pktgen.txt
index 5a61a240..0e30c78 100644
--- a/Documentation/networking/pktgen.txt
+++ b/Documentation/networking/pktgen.txt
@@ -102,13 +102,18 @@
The 'minimum' MAC is what you set with dstmac.
pgset "flag [name]" Set a flag to determine behaviour. Current flags
- are: IPSRC_RND #IP Source is random (between min/max),
- IPDST_RND, UDPSRC_RND,
- UDPDST_RND, MACSRC_RND, MACDST_RND
+ are: IPSRC_RND # IP source is random (between min/max)
+ IPDST_RND # IP destination is random
+ UDPSRC_RND, UDPDST_RND,
+ MACSRC_RND, MACDST_RND
+ TXSIZE_RND, IPV6,
MPLS_RND, VID_RND, SVID_RND
+ FLOW_SEQ,
QUEUE_MAP_RND # queue map random
QUEUE_MAP_CPU # queue map mirrors smp_processor_id()
- IPSEC # Make IPsec encapsulation for packet
+ UDPCSUM,
+ IPSEC # IPsec encapsulation (needs CONFIG_XFRM)
+ NODE_ALLOC # node specific memory allocation
pgset spi SPI_VALUE Set specific SA used to transform packet.
@@ -233,13 +238,22 @@
flag
IPSRC_RND
- TXSIZE_RND
IPDST_RND
UDPSRC_RND
UDPDST_RND
MACSRC_RND
MACDST_RND
+ TXSIZE_RND
+ IPV6
+ MPLS_RND
+ VID_RND
+ SVID_RND
+ FLOW_SEQ
+ QUEUE_MAP_RND
+ QUEUE_MAP_CPU
+ UDPCSUM
IPSEC
+ NODE_ALLOC
dst_min
dst_max
diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt
index b89bc82e..16a924c 100644
--- a/Documentation/networking/rxrpc.txt
+++ b/Documentation/networking/rxrpc.txt
@@ -27,6 +27,8 @@
(*) AF_RXRPC kernel interface.
+ (*) Configurable parameters.
+
========
OVERVIEW
@@ -864,3 +866,82 @@
This is used to allocate a null RxRPC key that can be used to indicate
anonymous security for a particular domain.
+
+
+=======================
+CONFIGURABLE PARAMETERS
+=======================
+
+The RxRPC protocol driver has a number of configurable parameters that can be
+adjusted through sysctls in /proc/net/rxrpc/:
+
+ (*) req_ack_delay
+
+ The amount of time in milliseconds after receiving a packet with the
+ request-ack flag set before we honour the flag and actually send the
+ requested ack.
+
+ Usually the other side won't stop sending packets until the advertised
+ reception window is full (to a maximum of 255 packets), so delaying the
+ ACK permits several packets to be ACK'd in one go.
+
+ (*) soft_ack_delay
+
+ The amount of time in milliseconds after receiving a new packet before we
+ generate a soft-ACK to tell the sender that it doesn't need to resend.
+
+ (*) idle_ack_delay
+
+ The amount of time in milliseconds after all the packets currently in the
+ received queue have been consumed before we generate a hard-ACK to tell
+ the sender it can free its buffers, assuming no other reason occurs that
+ we would send an ACK.
+
+ (*) resend_timeout
+
+ The amount of time in milliseconds after transmitting a packet before we
+ transmit it again, assuming no ACK is received from the receiver telling
+ us they got it.
+
+ (*) max_call_lifetime
+
+ The maximum amount of time in seconds that a call may be in progress
+ before we preemptively kill it.
+
+ (*) dead_call_expiry
+
+ The amount of time in seconds before we remove a dead call from the call
+ list. Dead calls are kept around for a little while for the purpose of
+ repeating ACK and ABORT packets.
+
+ (*) connection_expiry
+
+ The amount of time in seconds after a connection was last used before we
+ remove it from the connection list. Whilst a connection is in existence,
+ it serves as a placeholder for negotiated security; when it is deleted,
+ the security must be renegotiated.
+
+ (*) transport_expiry
+
+ The amount of time in seconds after a transport was last used before we
+ remove it from the transport list. Whilst a transport is in existence, it
+ serves to anchor the peer data and keeps the connection ID counter.
+
+ (*) rxrpc_rx_window_size
+
+ The size of the receive window in packets. This is the maximum number of
+ unconsumed received packets we're willing to hold in memory for any
+ particular call.
+
+ (*) rxrpc_rx_mtu
+
+ The maximum packet MTU size that we're willing to receive in bytes. This
+ indicates to the peer whether we're willing to accept jumbo packets.
+
+ (*) rxrpc_rx_jumbo_max
+
+ The maximum number of packets that we're willing to accept in a jumbo
+ packet. Non-terminal packets in a jumbo packet must contain a four byte
+ header plus exactly 1412 bytes of data. The terminal packet must contain
+ a four byte header plus any amount of data. In any event, a jumbo packet
+ may not exceed rxrpc_rx_mtu in size.
diff --git a/Documentation/networking/tcp.txt b/Documentation/networking/tcp.txt
index 7d11bb5..bdc4c0d 100644
--- a/Documentation/networking/tcp.txt
+++ b/Documentation/networking/tcp.txt
@@ -30,7 +30,7 @@
tcp_cong.c. The functions used by the congestion control mechanism are
registered via passing a tcp_congestion_ops struct to
tcp_register_congestion_control. As a minimum name, ssthresh,
-cong_avoid, min_cwnd must be valid.
+cong_avoid must be valid.
Private data for a congestion control mechanism is stored in tp->ca_priv.
tcp_ca(tp) returns a pointer to this space. This is preallocated space - it
diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
index 661d3c3..bc35541 100644
--- a/Documentation/networking/timestamping.txt
+++ b/Documentation/networking/timestamping.txt
@@ -21,26 +21,38 @@
SO_TIMESTAMPING:
-Instructs the socket layer which kind of information is wanted. The
-parameter is an integer with some of the following bits set. Setting
-other bits is an error and doesn't change the current state.
+Instructs the socket layer which kind of information should be collected
+and/or reported. The parameter is an integer with some of the following
+bits set. Setting other bits is an error and doesn't change the current
+state.
-SOF_TIMESTAMPING_TX_HARDWARE: try to obtain send time stamp in hardware
-SOF_TIMESTAMPING_TX_SOFTWARE: if SOF_TIMESTAMPING_TX_HARDWARE is off or
- fails, then do it in software
-SOF_TIMESTAMPING_RX_HARDWARE: return the original, unmodified time stamp
- as generated by the hardware
-SOF_TIMESTAMPING_RX_SOFTWARE: if SOF_TIMESTAMPING_RX_HARDWARE is off or
- fails, then do it in software
-SOF_TIMESTAMPING_RAW_HARDWARE: return original raw hardware time stamp
-SOF_TIMESTAMPING_SYS_HARDWARE: return hardware time stamp transformed to
- the system time base
-SOF_TIMESTAMPING_SOFTWARE: return system time stamp generated in
- software
+Four of the bits are requests to the stack to try to generate
+timestamps. Any combination of them is valid.
-SOF_TIMESTAMPING_TX/RX determine how time stamps are generated.
-SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the
-following control message:
+SOF_TIMESTAMPING_TX_HARDWARE: try to obtain send time stamps in hardware
+SOF_TIMESTAMPING_TX_SOFTWARE: try to obtain send time stamps in software
+SOF_TIMESTAMPING_RX_HARDWARE: try to obtain receive time stamps in hardware
+SOF_TIMESTAMPING_RX_SOFTWARE: try to obtain receive time stamps in software
+
+The other three bits control which timestamps will be reported in a
+generated control message. If none of these bits are set or if none of
+the set bits correspond to data that is available, then the control
+message will not be generated:
+
+SOF_TIMESTAMPING_SOFTWARE: report systime if available
+SOF_TIMESTAMPING_SYS_HARDWARE: report hwtimetrans if available
+SOF_TIMESTAMPING_RAW_HARDWARE: report hwtimeraw if available
+
+It is worth noting that timestamps may be collected for reasons other
+than being requested by a particular socket with
+SOF_TIMESTAMPING_[TR]X_(HARD|SOFT)WARE. For example, most drivers that
+can generate hardware receive timestamps ignore
+SOF_TIMESTAMPING_RX_HARDWARE. It is still a good idea to set that flag
+in case future drivers pay attention.
+
+If timestamps are reported, they will appear in a control message with
+cmsg_level==SOL_SOCKET, cmsg_type==SO_TIMESTAMPING, and a payload like
+this:
struct scm_timestamping {
struct timespec systime;
@@ -190,6 +202,9 @@
and not free the skb. A driver not supporting hardware time stamping doesn't
do that. A driver must never touch sk_buff::tstamp! It is used to store
software generated time stamps by the network subsystem.
+- Driver should call skb_tx_timestamp() as close to passing sk_buff to hardware
+ as possible. skb_tx_timestamp() provides a software time stamp if requested
+ and hardware timestamping is not possible (SKBTX_IN_PROGRESS not set).
- As soon as the driver has sent the packet and/or obtained a
hardware time stamp for it, it passes the time stamp back by
calling skb_hwtstamp_tx() with the original skb, the raw
@@ -200,6 +215,3 @@
this would occur at a later time in the processing pipeline than other
software time stamping and therefore could lead to unexpected deltas
between time stamps.
-- If the driver did not set the SKBTX_IN_PROGRESS flag (see above), then
- dev_hard_start_xmit() checks whether software time stamping
- is wanted as fallback and potentially generates the time stamp.
diff --git a/Documentation/phy.txt b/Documentation/phy.txt
index 0103e4b..ebff6ee 100644
--- a/Documentation/phy.txt
+++ b/Documentation/phy.txt
@@ -75,14 +75,26 @@
it. This framework provides the following APIs to get a reference to the PHY.
struct phy *phy_get(struct device *dev, const char *string);
+struct phy *phy_optional_get(struct device *dev, const char *string);
struct phy *devm_phy_get(struct device *dev, const char *string);
+struct phy *devm_phy_optional_get(struct device *dev, const char *string);
-phy_get and devm_phy_get can be used to get the PHY. In the case of dt boot,
-the string arguments should contain the phy name as given in the dt data and
-in the case of non-dt boot, it should contain the label of the PHY.
-The only difference between the two APIs is that devm_phy_get associates the
-device with the PHY using devres on successful PHY get. On driver detach,
-release function is invoked on the the devres data and devres data is freed.
+phy_get, phy_optional_get, devm_phy_get and devm_phy_optional_get can
+be used to get the PHY. In the case of dt boot, the string arguments
+should contain the phy name as given in the dt data and in the case of
+non-dt boot, it should contain the label of the PHY. The two
+devm_phy_get associates the device with the PHY using devres on
+successful PHY get. On driver detach, release function is invoked on
+the the devres data and devres data is freed. phy_optional_get and
+devm_phy_optional_get should be used when the phy is optional. These
+two functions will never return -ENODEV, but instead returns NULL when
+the phy cannot be found.
+
+It should be noted that NULL is a valid phy reference. All phy
+consumer calls on the NULL phy become NOPs. That is the release calls,
+the phy_init() and phy_exit() calls, and phy_power_on() and
+phy_power_off() calls are all NOP when applied to a NULL phy. The NULL
+phy is useful in devices for handling optional phy devices.
5. Releasing a reference to the PHY
diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX
index a4d682f..ad04cc8 100644
--- a/Documentation/power/00-INDEX
+++ b/Documentation/power/00-INDEX
@@ -4,6 +4,8 @@
- basic info about the APM and ACPI support.
basic-pm-debugging.txt
- Debugging suspend and resume
+charger-manager.txt
+ - Battery charger management.
devices.txt
- How drivers interact with system-wide power management
drivers-testing.txt
@@ -22,6 +24,8 @@
- info on Linux PM Quality of Service interface
power_supply_class.txt
- Tells userspace about battery, UPS, AC or DC power supply properties
+runtime_pm.txt
+ - Power management framework for I/O devices.
s2ram.txt
- How to get suspend to ram working (and debug it when it isn't)
states.txt
@@ -38,7 +42,5 @@
- How to trick software suspend (to disk) into working when it isn't
userland-swsusp.txt
- Experimental implementation of software suspend in userspace
-video_extension.txt
- - ACPI video extensions
video.txt
- Video issues during resume from suspend
diff --git a/Documentation/ptp/testptp.c b/Documentation/ptp/testptp.c
index a74d0a8..f1ac2da 100644
--- a/Documentation/ptp/testptp.c
+++ b/Documentation/ptp/testptp.c
@@ -19,6 +19,7 @@
*/
#include <errno.h>
#include <fcntl.h>
+#include <inttypes.h>
#include <math.h>
#include <signal.h>
#include <stdio.h>
@@ -117,13 +118,22 @@
" -f val adjust the ptp clock frequency by 'val' ppb\n"
" -g get the ptp clock time\n"
" -h prints this message\n"
+ " -i val index for event/trigger\n"
" -k val measure the time offset between system and phc clock\n"
" for 'val' times (Maximum 25)\n"
+ " -l list the current pin configuration\n"
+ " -L pin,val configure pin index 'pin' with function 'val'\n"
+ " the channel index is taken from the '-i' option\n"
+ " 'val' specifies the auxiliary function:\n"
+ " 0 - none\n"
+ " 1 - external time stamp\n"
+ " 2 - periodic output\n"
" -p val enable output with a period of 'val' nanoseconds\n"
" -P val enable or disable (val=1|0) the system clock PPS\n"
" -s set the ptp clock time from the system time\n"
" -S set the system time from the ptp clock time\n"
- " -t val shift the ptp clock time by 'val' seconds\n",
+ " -t val shift the ptp clock time by 'val' seconds\n"
+ " -T val set the ptp clock time to 'val' seconds\n",
progname);
}
@@ -133,6 +143,7 @@
struct ptp_extts_event event;
struct ptp_extts_request extts_request;
struct ptp_perout_request perout_request;
+ struct ptp_pin_desc desc;
struct timespec ts;
struct timex tx;
@@ -154,12 +165,16 @@
int capabilities = 0;
int extts = 0;
int gettime = 0;
+ int index = 0;
+ int list_pins = 0;
int oneshot = 0;
int pct_offset = 0;
int n_samples = 0;
int periodic = 0;
int perout = -1;
+ int pin_index = -1, pin_func;
int pps = -1;
+ int seconds = 0;
int settime = 0;
int64_t t1, t2, tp;
@@ -167,7 +182,7 @@
progname = strrchr(argv[0], '/');
progname = progname ? 1+progname : argv[0];
- while (EOF != (c = getopt(argc, argv, "a:A:cd:e:f:ghk:p:P:sSt:v"))) {
+ while (EOF != (c = getopt(argc, argv, "a:A:cd:e:f:ghi:k:lL:p:P:sSt:T:v"))) {
switch (c) {
case 'a':
oneshot = atoi(optarg);
@@ -190,10 +205,23 @@
case 'g':
gettime = 1;
break;
+ case 'i':
+ index = atoi(optarg);
+ break;
case 'k':
pct_offset = 1;
n_samples = atoi(optarg);
break;
+ case 'l':
+ list_pins = 1;
+ break;
+ case 'L':
+ cnt = sscanf(optarg, "%d,%d", &pin_index, &pin_func);
+ if (cnt != 2) {
+ usage(progname);
+ return -1;
+ }
+ break;
case 'p':
perout = atoi(optarg);
break;
@@ -209,6 +237,10 @@
case 't':
adjtime = atoi(optarg);
break;
+ case 'T':
+ settime = 3;
+ seconds = atoi(optarg);
+ break;
case 'h':
usage(progname);
return 0;
@@ -240,12 +272,14 @@
" %d programmable alarms\n"
" %d external time stamp channels\n"
" %d programmable periodic signals\n"
- " %d pulse per second\n",
+ " %d pulse per second\n"
+ " %d programmable pins\n",
caps.max_adj,
caps.n_alarm,
caps.n_ext_ts,
caps.n_per_out,
- caps.pps);
+ caps.pps,
+ caps.n_pins);
}
}
@@ -299,9 +333,19 @@
}
}
+ if (settime == 3) {
+ ts.tv_sec = seconds;
+ ts.tv_nsec = 0;
+ if (clock_settime(clkid, &ts)) {
+ perror("clock_settime");
+ } else {
+ puts("set time okay");
+ }
+ }
+
if (extts) {
memset(&extts_request, 0, sizeof(extts_request));
- extts_request.index = 0;
+ extts_request.index = index;
extts_request.flags = PTP_ENABLE_FEATURE;
if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) {
perror("PTP_EXTTS_REQUEST");
@@ -326,6 +370,24 @@
}
}
+ if (list_pins) {
+ int n_pins = 0;
+ if (ioctl(fd, PTP_CLOCK_GETCAPS, &caps)) {
+ perror("PTP_CLOCK_GETCAPS");
+ } else {
+ n_pins = caps.n_pins;
+ }
+ for (i = 0; i < n_pins; i++) {
+ desc.index = i;
+ if (ioctl(fd, PTP_PIN_GETFUNC, &desc)) {
+ perror("PTP_PIN_GETFUNC");
+ break;
+ }
+ printf("name %s index %u func %u chan %u\n",
+ desc.name, desc.index, desc.func, desc.chan);
+ }
+ }
+
if (oneshot) {
install_handler(SIGALRM, handle_alarm);
/* Create a timer. */
@@ -375,7 +437,7 @@
return -1;
}
memset(&perout_request, 0, sizeof(perout_request));
- perout_request.index = 0;
+ perout_request.index = index;
perout_request.start.sec = ts.tv_sec + 2;
perout_request.start.nsec = 0;
perout_request.period.sec = 0;
@@ -387,6 +449,18 @@
}
}
+ if (pin_index >= 0) {
+ memset(&desc, 0, sizeof(desc));
+ desc.index = pin_index;
+ desc.func = pin_func;
+ desc.chan = index;
+ if (ioctl(fd, PTP_PIN_SETFUNC, &desc)) {
+ perror("PTP_PIN_SETFUNC");
+ } else {
+ puts("set pin function okay");
+ }
+ }
+
if (pps != -1) {
int enable = pps ? 1 : 0;
if (ioctl(fd, PTP_ENABLE_PPS, enable)) {
@@ -423,14 +497,14 @@
interval = t2 - t1;
offset = (t2 + t1) / 2 - tp;
- printf("system time: %ld.%ld\n",
+ printf("system time: %" PRId64 ".%u\n",
(pct+2*i)->sec, (pct+2*i)->nsec);
- printf("phc time: %ld.%ld\n",
+ printf("phc time: %" PRId64 ".%u\n",
(pct+2*i+1)->sec, (pct+2*i+1)->nsec);
- printf("system time: %ld.%ld\n",
+ printf("system time: %" PRId64 ".%u\n",
(pct+2*i+2)->sec, (pct+2*i+2)->nsec);
- printf("system/phc clock time offset is %ld ns\n"
- "system clock time delay is %ld ns\n",
+ printf("system/phc clock time offset is %" PRId64 " ns\n"
+ "system clock time delay is %" PRId64 " ns\n",
offset, interval);
}
diff --git a/Documentation/s390/00-INDEX b/Documentation/s390/00-INDEX
index 3a2b963..10c874e 100644
--- a/Documentation/s390/00-INDEX
+++ b/Documentation/s390/00-INDEX
@@ -16,11 +16,13 @@
- hints for debugging on s390 systems.
driver-model.txt
- information on s390 devices and the driver model.
+kvm.txt
+ - ioctl calls to /dev/kvm on s390.
monreader.txt
- information on accessing the z/VM monitor stream from Linux.
+qeth.txt
+ - HiperSockets Bridge Port Support.
s390dbf.txt
- information on using the s390 debug feature.
-TAPE
- - information on the driver for channel-attached tapes.
-zfcpdump
+zfcpdump.txt
- information on the s390 SCSI dump tool.
diff --git a/Documentation/scheduler/00-INDEX b/Documentation/scheduler/00-INDEX
index 46702e4..eccf7ad 100644
--- a/Documentation/scheduler/00-INDEX
+++ b/Documentation/scheduler/00-INDEX
@@ -2,6 +2,8 @@
- this file.
sched-arch.txt
- CPU Scheduler implementation hints for architecture specific code.
+sched-bwc.txt
+ - CFS bandwidth control overview.
sched-design-CFS.txt
- goals, design and implementation of the Completely Fair Scheduler.
sched-domains.txt
diff --git a/Documentation/scsi/00-INDEX b/Documentation/scsi/00-INDEX
index 2044be5..c4b978a 100644
--- a/Documentation/scsi/00-INDEX
+++ b/Documentation/scsi/00-INDEX
@@ -36,6 +36,8 @@
- info on WorkBiT NinjaSCSI-32/32Bi driver
aacraid.txt
- Driver supporting Adaptec RAID controllers
+advansys.txt
+ - List of Advansys Host Adapters
aha152x.txt
- info on driver for Adaptec AHA152x based adapters
aic79xx.txt
@@ -44,6 +46,12 @@
- info on driver for Adaptec controllers
arcmsr_spec.txt
- ARECA FIRMWARE SPEC (for IOP331 adapter)
+bfa.txt
+ - Brocade FC/FCOE adapter driver.
+bnx2fc.txt
+ - FCoE hardware offload for Broadcom network interfaces.
+cxgb3i.txt
+ - Chelsio iSCSI Linux Driver
dc395x.txt
- README file for the dc395x SCSI driver
dpti.txt
@@ -52,18 +60,24 @@
- info on driver for DTC 2x80 based adapters
g_NCR5380.txt
- info on driver for NCR5380 and NCR53c400 based adapters
+hpsa.txt
+ - HP Smart Array Controller SCSI driver.
hptiop.txt
- HIGHPOINT ROCKETRAID 3xxx RAID DRIVER
in2000.txt
- info on in2000 driver
libsas.txt
- Serial Attached SCSI management layer.
+link_power_management_policy.txt
+ - Link power management options.
lpfc.txt
- LPFC driver release notes
megaraid.txt
- Common Management Module, shared code handling ioctls for LSI drivers
ncr53c8xx.txt
- info on driver for NCR53c8xx based adapters
+osd.txt
+ Object-Based Storage Device, command set introduction.
osst.txt
- info on driver for OnStream SC-x0 SCSI tape
ppa.txt
@@ -74,6 +88,8 @@
- README for the SCSI media changer driver
scsi-generic.txt
- info on the sg driver for generic (non-disk/CD/tape) SCSI devices.
+scsi-parameters.txt
+ - List of SCSI-parameters to pass to the kernel at module load-time.
scsi.txt
- short blurb on using SCSI support as a module.
scsi_mid_low_api.txt
diff --git a/Documentation/serial/00-INDEX b/Documentation/serial/00-INDEX
index 1f1b22f..f9c6b5e 100644
--- a/Documentation/serial/00-INDEX
+++ b/Documentation/serial/00-INDEX
@@ -4,10 +4,12 @@
- info on Cyclades-Z firmware loading.
digiepca.txt
- info on Digi Intl. {PC,PCI,EISA}Xx and Xem series cards.
-hayes-esp.txt
- - info on using the Hayes ESP serial driver.
+driver
+ - intro to the low level serial driver.
moxa-smartio
- file with info on installing/using Moxa multiport serial driver.
+n_gsm.txt
+ - GSM 0710 tty multiplexer howto.
riscom8.txt
- notes on using the RISCom/8 multi-port serial driver.
rocket.txt
diff --git a/Documentation/spi/00-INDEX b/Documentation/spi/00-INDEX
new file mode 100644
index 0000000..a128fa8
--- /dev/null
+++ b/Documentation/spi/00-INDEX
@@ -0,0 +1,22 @@
+00-INDEX
+ - this file.
+Makefile
+ - Makefile for the example sourcefiles.
+butterfly
+ - AVR Butterfly SPI driver overview and pin configuration.
+ep93xx_spi
+ - Basic EP93xx SPI driver configuration.
+pxa2xx
+ - PXA2xx SPI master controller build by spi_message fifo wq
+spidev
+ - Intro to the userspace API for spi devices
+spidev_fdx.c
+ - spidev example file
+spi-lm70llp
+ - Connecting an LM70-LLP sensor to the kernel via the SPI subsys.
+spi-sc18is602
+ - NXP SC18IS602/603 I2C-bus to SPI bridge
+spi-summary
+ - (Linux) SPI overview. If unsure about SPI or SPI in Linux, start here.
+spidev_test.c
+ - SPI testing utility.
diff --git a/Documentation/spi/spi-summary b/Documentation/spi/spi-summary
index f72e0d1..7982bcc 100644
--- a/Documentation/spi/spi-summary
+++ b/Documentation/spi/spi-summary
@@ -543,7 +543,22 @@
queuing transfers that arrive in the meantime. When the driver is
finished with this message, it must call
spi_finalize_current_message() so the subsystem can issue the next
- transfer. This may sleep.
+ message. This may sleep.
+
+ master->transfer_one(struct spi_master *master, struct spi_device *spi,
+ struct spi_transfer *transfer)
+ The subsystem calls the driver to transfer a single transfer while
+ queuing transfers that arrive in the meantime. When the driver is
+ finished with this transfer, it must call
+ spi_finalize_current_transfer() so the subsystem can issue the next
+ transfer. This may sleep. Note: transfer_one and transfer_one_message
+ are mutually exclusive; when both are set, the generic subsystem does
+ not call your transfer_one callback.
+
+ Return values:
+ negative errno: error
+ 0: transfer is finished
+ 1: transfer is still in progress
DEPRECATED METHODS
diff --git a/Documentation/timers/00-INDEX b/Documentation/timers/00-INDEX
index ef2ccbf..6d042dc 100644
--- a/Documentation/timers/00-INDEX
+++ b/Documentation/timers/00-INDEX
@@ -8,6 +8,8 @@
- sample hpet timer test program
hrtimers.txt
- subsystem for high-resolution kernel timers
+Makefile
+ - Build and link hpet_example
NO_HZ.txt
- Summary of the different methods for the scheduler clock-interrupts management.
timers-howto.txt
diff --git a/Documentation/virtual/kvm/00-INDEX b/Documentation/virtual/kvm/00-INDEX
index 641ec92..fee9f2b 100644
--- a/Documentation/virtual/kvm/00-INDEX
+++ b/Documentation/virtual/kvm/00-INDEX
@@ -20,5 +20,7 @@
- the paravirtualization interface on PowerPC.
review-checklist.txt
- review checklist for KVM patches.
+s390-diag.txt
+ - Diagnose hypercall description (for IBM S/390)
timekeeping.txt
- timekeeping virtualization for x86-based architectures.
diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX
index a39d066..081c497 100644
--- a/Documentation/vm/00-INDEX
+++ b/Documentation/vm/00-INDEX
@@ -16,8 +16,6 @@
- explains what hwpoison is
ksm.txt
- how to use the Kernel Samepage Merging feature.
-locking
- - info on how locking and synchronization is done in the Linux vm code.
numa
- information about NUMA specific code in the Linux vm.
numa_memory_policy.txt
@@ -32,6 +30,8 @@
- a short users guide for SLUB.
soft-dirty.txt
- short explanation for soft-dirty PTEs
+split_page_table_lock
+ - Separate per-table lock to improve scalability of the old page_table_lock.
transhuge.txt
- Transparent Hugepage Support, alternative way of using hugepages.
unevictable-lru.txt
diff --git a/Documentation/w1/masters/00-INDEX b/Documentation/w1/masters/00-INDEX
index d63fa02..8330cf9 100644
--- a/Documentation/w1/masters/00-INDEX
+++ b/Documentation/w1/masters/00-INDEX
@@ -4,7 +4,9 @@
- The Maxim/Dallas Semiconductor DS2482 provides 1-wire busses.
ds2490
- The Maxim/Dallas Semiconductor DS2490 builds USB <-> W1 bridges.
-mxc_w1
+mxc-w1
- W1 master controller driver found on Freescale MX2/MX3 SoCs
+omap-hdq
+ - HDQ/1-wire module of TI OMAP 2430/3430.
w1-gpio
- GPIO 1-wire bus master driver.
diff --git a/Documentation/w1/slaves/00-INDEX b/Documentation/w1/slaves/00-INDEX
index 75613c9..6e18c70 100644
--- a/Documentation/w1/slaves/00-INDEX
+++ b/Documentation/w1/slaves/00-INDEX
@@ -4,3 +4,5 @@
- The Maxim/Dallas Semiconductor ds18*20 temperature sensor.
w1_ds2423
- The Maxim/Dallas Semiconductor ds2423 counter device.
+w1_ds28e04
+ - The Maxim/Dallas Semiconductor ds28e04 eeprom.
diff --git a/Documentation/x86/00-INDEX b/Documentation/x86/00-INDEX
index f37b46d..6922644 100644
--- a/Documentation/x86/00-INDEX
+++ b/Documentation/x86/00-INDEX
@@ -1,6 +1,20 @@
00-INDEX
- this file
-mtrr.txt
- - how to use x86 Memory Type Range Registers to increase performance
+boot.txt
+ - List of boot protocol versions
+early-microcode.txt
+ - How to load microcode from an initrd-CPIO archive early to fix CPU issues.
+earlyprintk.txt
+ - Using earlyprintk with a USB2 debug port key.
+entry_64.txt
+ - Describe (some of the) kernel entry points for x86.
exception-tables.txt
- why and how Linux kernel uses exception tables on x86
+mtrr.txt
+ - how to use x86 Memory Type Range Registers to increase performance
+pat.txt
+ - Page Attribute Table intro and API
+usb-legacy-support.txt
+ - how to fix/avoid quirks when using emulated PS/2 mouse/keyboard.
+zero-page.txt
+ - layout of the first page of memory.
diff --git a/Documentation/zh_CN/arm64/booting.txt b/Documentation/zh_CN/arm64/booting.txt
index 28fa325..6f6d956 100644
--- a/Documentation/zh_CN/arm64/booting.txt
+++ b/Documentation/zh_CN/arm64/booting.txt
@@ -7,7 +7,7 @@
or if there is a problem with the translation.
Maintainer: Will Deacon <will.deacon@arm.com>
-Chinese maintainer: Fu Wei <tekkamanninja@gmail.com>
+Chinese maintainer: Fu Wei <wefu@redhat.com>
---------------------------------------------------------------------
Documentation/arm64/booting.txt 的中文翻译
@@ -16,9 +16,9 @@
译存在问题，请联系中文版维护者。
英文版维护者： Will Deacon <will.deacon@arm.com>
-中文版维护者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
-中文版翻译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
-中文版校译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
+中文版维护者： 傅炜 Fu Wei <wefu@redhat.com>
+中文版翻译者： 傅炜 Fu Wei <wefu@redhat.com>
+中文版校译者： 傅炜 Fu Wei <wefu@redhat.com>
以下为正文
---------------------------------------------------------------------
@@ -64,8 +64,8 @@
必要性: 强制
-设备树数据块（dtb）大小必须不大于 2 MB，且位于从内核映像起始算起第一个
-512MB 内的 2MB 边界上。这使得内核可以通过初始页表中的单个节描述符来
+设备树数据块（dtb）必须 8 字节对齐，并位于从内核映像起始算起第一个 512MB
+内，且不得跨越 2MB 对齐边界。这使得内核可以通过初始页表中的单个节描述符来
映射此数据块。
@@ -84,13 +84,23 @@
必要性: 强制
-已解压的内核映像包含一个 32 字节的头，内容如下：
+已解压的内核映像包含一个 64 字节的头，内容如下：
- u32 magic = 0x14000008; /* 跳转到 stext, 小端 */
- u32 res0 = 0; /* 保留 */
+ u32 code0; /* 可执行代码 */
+ u32 code1; /* 可执行代码 */
u64 text_offset; /* 映像装载偏移 */
+ u64 res0 = 0; /* 保留 */
u64 res1 = 0; /* 保留 */
u64 res2 = 0; /* 保留 */
+ u64 res3 = 0; /* 保留 */
+ u64 res4 = 0; /* 保留 */
+ u32 magic = 0x644d5241; /* 魔数, 小端, "ARM\x64" */
+ u32 res5 = 0; /* 保留 */
+
+
+映像头注释：
+
+- code0/code1 负责跳转到 stext.
映像必须位于系统 RAM 起始处的特定偏移（当前是 0x80000）。系统 RAM
的起始地址必须是以 2MB 对齐的。
@@ -118,9 +128,9 @@
外部高速缓存（如果存在）必须配置并禁用。
- 架构计时器
- CNTFRQ 必须设定为计时器的频率。
- 如果在 EL1 模式下进入内核，则 CNTHCTL_EL2 中的 EL1PCTEN (bit 0)
- 必须置位。
+ CNTFRQ 必须设定为计时器的频率，且 CNTVOFF 必须设定为对所有 CPU
+ 都一致的值。如果在 EL1 模式下进入内核，则 CNTHCTL_EL2 中的
+ EL1PCTEN (bit 0) 必须置位。
- 一致性
通过内核启动的所有 CPU 在内核入口地址上必须处于相同的一致性域中。
@@ -131,23 +141,40 @@
在进入内核映像的异常级中，所有构架中可写的系统寄存器必须通过软件
在一个更高的异常级别下初始化，以防止在 未知 状态下运行。
+以上对于 CPU 模式、高速缓存、MMU、架构计时器、一致性、系统寄存器的
+必要条件描述适用于所有 CPU。所有 CPU 必须在同一异常级别跳入内核。
+
引导装载程序必须在每个 CPU 处于以下状态时跳入内核入口：
- 主 CPU 必须直接跳入内核映像的第一条指令。通过此 CPU 传递的设备树
- 数据块必须在每个 CPU 节点中包含以下内容：
-
- 1、‘enable-method’属性。目前，此字段支持的值仅为字符串“spin-table”。
-
- 2、‘cpu-release-addr’标识一个 64-bit、初始化为零的内存位置。
+ 数据块必须在每个 CPU 节点中包含一个 ‘enable-method’ 属性，所
+ 支持的 enable-method 请见下文。
引导装载程序必须生成这些设备树属性，并在跳入内核入口之前将其插入
数据块。
-- 任何辅助 CPU 必须在内存保留区（通过设备树中的 /memreserve/ 域传递
+- enable-method 为 “spin-table” 的 CPU 必须在它们的 CPU
+ 节点中包含一个 ‘cpu-release-addr’ 属性。这个属性标识了一个
+ 64 位自然对齐且初始化为零的内存位置。
+
+ 这些 CPU 必须在内存保留区（通过设备树中的 /memreserve/ 域传递
给内核）中自旋于内核之外，轮询它们的 cpu-release-addr 位置（必须
包含在保留区中）。可通过插入 wfe 指令来降低忙循环开销，而主 CPU 将
发出 sev 指令。当对 cpu-release-addr 所指位置的读取操作返回非零值
- 时，CPU 必须直接跳入此值所指向的地址。
+ 时，CPU 必须跳入此值所指向的地址。此值为一个单独的 64 位小端值，
+ 因此 CPU 须在跳转前将所读取的值转换为其本身的端模式。
+
+- enable-method 为 “psci” 的 CPU 保持在内核外（比如，在
+ memory 节点中描述为内核空间的内存区外，或在通过设备树 /memreserve/
+ 域中描述为内核保留区的空间中）。内核将会发起在 ARM 文档（编号
+ ARM DEN 0022A：用于 ARM 上的电源状态协调接口系统软件）中描述的
+ CPU_ON 调用来将 CPU 带入内核。
+
+ *译者注:到文档翻译时，此文档已更新为 ARM DEN 0022B。
+
+ 设备树必须包含一个 ‘psci’ 节点，请参考以下文档：
+ Documentation/devicetree/bindings/arm/psci.txt
+
- 辅助 CPU 通用寄存器设置
x0 = 0 (保留，将来可能使用)
diff --git a/Documentation/zh_CN/arm64/memory.txt b/Documentation/zh_CN/arm64/memory.txt
index a5f6283..a782704 100644
--- a/Documentation/zh_CN/arm64/memory.txt
+++ b/Documentation/zh_CN/arm64/memory.txt
@@ -7,7 +7,7 @@
or if there is a problem with the translation.
Maintainer: Catalin Marinas <catalin.marinas@arm.com>
-Chinese maintainer: Fu Wei <tekkamanninja@gmail.com>
+Chinese maintainer: Fu Wei <wefu@redhat.com>
---------------------------------------------------------------------
Documentation/arm64/memory.txt 的中文翻译
@@ -16,9 +16,9 @@
译存在问题，请联系中文版维护者。
英文版维护者： Catalin Marinas <catalin.marinas@arm.com>
-中文版维护者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
-中文版翻译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
-中文版校译者： 傅炜 Fu Wei <tekkamanninja@gmail.com>
+中文版维护者： 傅炜 Fu Wei <wefu@redhat.com>
+中文版翻译者： 傅炜 Fu Wei <wefu@redhat.com>
+中文版校译者： 傅炜 Fu Wei <wefu@redhat.com>
以下为正文
---------------------------------------------------------------------
@@ -41,7 +41,7 @@
TTBR1 中，且从不写入 TTBR0。
-AArch64 Linux 内存布局：
+AArch64 Linux 在页大小为 4KB 时的内存布局：
起始地址 结束地址 大小 用途
-----------------------------------------------------------------------
@@ -55,15 +55,42 @@
ffffffbe00000000 ffffffbffbbfffff ~8GB [防护页，未来用于 vmmemap]
+ffffffbffbc00000 ffffffbffbdfffff 2MB earlyprintk 设备
+
ffffffbffbe00000 ffffffbffbe0ffff 64KB PCI I/O 空间
-ffffffbbffff0000 ffffffbcffffffff ~2MB [防护页]
+ffffffbffbe10000 ffffffbcffffffff ~2MB [防护页]
ffffffbffc000000 ffffffbfffffffff 64MB 模块
ffffffc000000000 ffffffffffffffff 256GB 内核逻辑内存映射
+AArch64 Linux 在页大小为 64KB 时的内存布局：
+
+起始地址 结束地址 大小 用途
+-----------------------------------------------------------------------
+0000000000000000 000003ffffffffff 4TB 用户空间
+
+fffffc0000000000 fffffdfbfffeffff ~2TB vmalloc
+
+fffffdfbffff0000 fffffdfbffffffff 64KB [防护页]
+
+fffffdfc00000000 fffffdfdffffffff 8GB vmemmap
+
+fffffdfe00000000 fffffdfffbbfffff ~8GB [防护页，未来用于 vmmemap]
+
+fffffdfffbc00000 fffffdfffbdfffff 2MB earlyprintk 设备
+
+fffffdfffbe00000 fffffdfffbe0ffff 64KB PCI I/O 空间
+
+fffffdfffbe10000 fffffdfffbffffff ~2MB [防护页]
+
+fffffdfffc000000 fffffdffffffffff 64MB 模块
+
+fffffe0000000000 ffffffffffffffff 2TB 内核逻辑内存映射
+
+
4KB 页大小的转换表查找：
+--------+--------+--------+--------+--------+--------+--------+--------+
@@ -91,3 +118,10 @@
| | +--------------------------> [41:29] L2 索引 (仅使用 38:29 )
| +-------------------------------> [47:42] L1 索引 (未使用)
+-------------------------------------------------> [63] TTBR0/1
+
+当使用 KVM 时, 管理程序（hypervisor）在 EL2 中通过相对内核虚拟地址的
+一个固定偏移来映射内核页（内核虚拟地址的高 24 位设为零）:
+
+起始地址 结束地址 大小 用途
+-----------------------------------------------------------------------
+0000004000000000 0000007fffffffff 256GB 在 HYP 中映射的内核对象
diff --git a/Documentation/zh_CN/arm64/tagged-pointers.txt b/Documentation/zh_CN/arm64/tagged-pointers.txt
new file mode 100644
index 0000000..2664d1b
--- /dev/null
+++ b/Documentation/zh_CN/arm64/tagged-pointers.txt
@@ -0,0 +1,52 @@
+Chinese translated version of Documentation/arm64/tagged-pointers.txt
+
+If you have any comment or update to the content, please contact the
+original document maintainer directly. However, if you have a problem
+communicating in English you can also ask the Chinese maintainer for
+help. Contact the Chinese maintainer if this translation is outdated
+or if there is a problem with the translation.
+
+Maintainer: Will Deacon <will.deacon@arm.com>
+Chinese maintainer: Fu Wei <wefu@redhat.com>
+---------------------------------------------------------------------
+Documentation/arm64/tagged-pointers.txt 的中文翻译
+
+如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文
+交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻
+译存在问题，请联系中文版维护者。
+
+英文版维护者： Will Deacon <will.deacon@arm.com>
+中文版维护者： 傅炜 Fu Wei <wefu@redhat.com>
+中文版翻译者： 傅炜 Fu Wei <wefu@redhat.com>
+中文版校译者： 傅炜 Fu Wei <wefu@redhat.com>
+
+以下为正文
+---------------------------------------------------------------------
+ Linux 在 AArch64 中带标记的虚拟地址
+ =================================
+
+作者: Will Deacon <will.deacon@arm.com>
+日期: 2013 年 06 月 12 日
+
+本文档简述了在 AArch64 地址转换系统中提供的带标记的虚拟地址及其在
+AArch64 Linux 中的潜在用途。
+
+内核提供的地址转换表配置使通过 TTBR0 完成的虚拟地址转换（即用户空间
+映射），其虚拟地址的最高 8 位（63:56）会被转换硬件所忽略。这种机制
+让这些位可供应用程序自由使用，其注意事项如下：
+
+ (1) 内核要求所有传递到 EL1 的用户空间地址带有 0x00 标记。
+ 这意味着任何携带用户空间虚拟地址的系统调用（syscall）
+ 参数 *必须* 在陷入内核前使它们的最高字节被清零。
+
+ (2) 非零标记在传递信号时不被保存。这意味着在应用程序中利用了
+ 标记的信号处理函数无法依赖 siginfo_t 的用户空间虚拟
+ 地址所携带的包含其内部域信息的标记。此规则的一个例外是
+ 当信号是在调试观察点的异常处理程序中产生的，此时标记的
+ 信息将被保存。
+
+ (3) 当使用带标记的指针时需特别留心，因为仅对两个虚拟地址
+ 的高字节，C 编译器很可能无法判断它们是不同的。
+
+此构架会阻止对带标记的 PC 指针的利用，因此在异常返回时，其高字节
+将被设置成一个为 “55” 的扩展符。
diff --git a/MAINTAINERS b/MAINTAINERS
index ec12265..162b0fe 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -73,7 +73,8 @@
L: Mailing list that is relevant to this area
W: Web-page with status/info
Q: Patchwork web based patch tracking system site
- T: SCM tree type and location. Type is one of: git, hg, quilt, stgit, topgit.
+ T: SCM tree type and location.
+ Type is one of: git, hg, quilt, stgit, topgit
S: Status, one of the following:
Supported: Someone is actually paid to look after this.
Maintained: Someone actually looks after it.
@@ -473,7 +474,7 @@
AGPGART DRIVER
M: David Airlie <airlied@linux.ie>
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6.git
+T: git git://people.freedesktop.org/~airlied/linux (part of drm maint)
S: Maintained
F: drivers/char/agp/
F: include/linux/agp*
@@ -535,10 +536,17 @@
L: linux-alpha@vger.kernel.org
F: arch/alpha/
+ALTERA TRIPLE SPEED ETHERNET DRIVER
+M: Vince Bridgers <vbridgers2013@gmail.com
+L: netdev@vger.kernel.org
+L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers)
+S: Maintained
+F: drivers/net/ethernet/altera/
+
ALTERA UART/JTAG UART SERIAL DRIVERS
M: Tobias Klauser <tklauser@distanz.ch>
L: linux-serial@vger.kernel.org
-L: nios2-dev@sopc.et.ntust.edu.tw (moderated for non-subscribers)
+L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers)
S: Maintained
F: drivers/tty/serial/altera_uart.c
F: drivers/tty/serial/altera_jtaguart.c
@@ -910,11 +918,11 @@
F: arch/arm/mach-footbridge/
ARM/FREESCALE IMX / MXC ARM ARCHITECTURE
-M: Shawn Guo <shawn.guo@linaro.org>
+M: Shawn Guo <shawn.guo@freescale.com>
M: Sascha Hauer <kernel@pengutronix.de>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
-T: git git://git.linaro.org/people/shawnguo/linux-2.6.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
F: arch/arm/mach-imx/
F: arch/arm/boot/dts/imx*
F: arch/arm/configs/imx*_defconfig
@@ -1612,11 +1620,11 @@
F: drivers/net/wireless/atmel*
ATTO EXPRESSSAS SAS/SATA RAID SCSI DRIVER
-M: Bradley Grove <linuxdrivers@attotech.com>
-L: linux-scsi@vger.kernel.org
-W: http://www.attotech.com
-S: Supported
-F: drivers/scsi/esas2r
+M: Bradley Grove <linuxdrivers@attotech.com>
+L: linux-scsi@vger.kernel.org
+W: http://www.attotech.com
+S: Supported
+F: drivers/scsi/esas2r
AUDIT SUBSYSTEM
M: Eric Paris <eparis@redhat.com>
@@ -1737,6 +1745,7 @@
BLACKFIN ARCHITECTURE
M: Steven Miao <realmz6@gmail.com>
L: adi-buildroot-devel@lists.sourceforge.net
+T: git git://git.code.sf.net/p/adi-linux/code
W: http://blackfin.uclinux.org
S: Supported
F: arch/blackfin/
@@ -1830,8 +1839,8 @@
F: include/net/bluetooth/
BONDING DRIVER
-M: Jay Vosburgh <fubar@us.ibm.com>
-M: Veaceslav Falico <vfalico@redhat.com>
+M: Jay Vosburgh <j.vosburgh@gmail.com>
+M: Veaceslav Falico <vfalico@gmail.com>
M: Andy Gospodarek <andy@greyhouse.net>
L: netdev@vger.kernel.org
W: http://sourceforge.net/projects/bonding/
@@ -1845,6 +1854,12 @@
S: Supported
F: drivers/net/ethernet/broadcom/b44.*
+BROADCOM GENET ETHERNET DRIVER
+M: Florian Fainelli <f.fainelli@gmail.com>
+L: netdev@vger.kernel.org
+S: Supported
+F: drivers/net/ethernet/broadcom/genet/
+
BROADCOM BNX2 GIGABIT ETHERNET DRIVER
M: Michael Chan <mchan@broadcom.com>
L: netdev@vger.kernel.org
@@ -1860,6 +1875,7 @@
BROADCOM BCM281XX/BCM11XXX ARM ARCHITECTURE
M: Christian Daudt <bcm@fixthebug.org>
+M: Matt Porter <mporter@linaro.org>
L: bcm-kernel-feedback-list@broadcom.com
T: git git://git.github.com/broadcom/bcm11351
S: Maintained
@@ -2158,7 +2174,7 @@
CHIPIDEA USB HIGH SPEED DUAL ROLE CONTROLLER
M: Peter Chen <Peter.Chen@freescale.com>
-T: git://github.com/hzpeterchen/linux-usb.git
+T: git git://github.com/hzpeterchen/linux-usb.git
L: linux-usb@vger.kernel.org
S: Maintained
F: drivers/usb/chipidea/
@@ -2178,9 +2194,9 @@
F: drivers/net/ethernet/cisco/enic/
CISCO VIC LOW LATENCY NIC DRIVER
-M: Upinder Malhi <umalhi@cisco.com>
-S: Supported
-F: drivers/infiniband/hw/usnic
+M: Upinder Malhi <umalhi@cisco.com>
+S: Supported
+F: drivers/infiniband/hw/usnic
CIRRUS LOGIC EP93XX ETHERNET DRIVER
M: Hartley Sweeten <hsweeten@visionengravers.com>
@@ -2367,7 +2383,7 @@
CPU FREQUENCY DRIVERS - ARM BIG LITTLE
M: Viresh Kumar <viresh.kumar@linaro.org>
-M: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
+M: Sudeep Holla <sudeep.holla@arm.com>
L: cpufreq@vger.kernel.org
L: linux-pm@vger.kernel.org
W: http://www.arm.com/products/processors/technologies/biglittleprocessing.php
@@ -2377,20 +2393,20 @@
F: drivers/cpufreq/arm_big_little_dt.c
CPUIDLE DRIVER - ARM BIG LITTLE
-M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
-M: Daniel Lezcano <daniel.lezcano@linaro.org>
-L: linux-pm@vger.kernel.org
-L: linux-arm-kernel@lists.infradead.org
-T: git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
-S: Maintained
-F: drivers/cpuidle/cpuidle-big_little.c
+M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+M: Daniel Lezcano <daniel.lezcano@linaro.org>
+L: linux-pm@vger.kernel.org
+L: linux-arm-kernel@lists.infradead.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
+S: Maintained
+F: drivers/cpuidle/cpuidle-big_little.c
CPUIDLE DRIVERS
M: Rafael J. Wysocki <rjw@rjwysocki.net>
M: Daniel Lezcano <daniel.lezcano@linaro.org>
L: linux-pm@vger.kernel.org
S: Maintained
-T: git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
F: drivers/cpuidle/*
F: include/linux/cpuidle.h
@@ -2408,8 +2424,10 @@
CPUSETS
M: Li Zefan <lizefan@huawei.com>
+L: cgroups@vger.kernel.org
W: http://www.bullopensource.org/cpuset/
W: http://oss.sgi.com/projects/cpusets/
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git
S: Maintained
F: Documentation/cgroups/cpusets.txt
F: include/linux/cpuset.h
@@ -2455,9 +2473,9 @@
F: sound/pci/cs5535audio/
CW1200 WLAN driver
-M: Solomon Peachy <pizza@shaftnet.org>
-S: Maintained
-F: drivers/net/wireless/cw1200/
+M: Solomon Peachy <pizza@shaftnet.org>
+S: Maintained
+F: drivers/net/wireless/cw1200/
CX18 VIDEO4LINUX DRIVER
M: Andy Walls <awalls@md.metrocast.net>
@@ -2608,9 +2626,9 @@
M: Oliver Neukum <oliver@neukum.org>
M: Ali Akcaagac <aliakc@web.de>
M: Jamie Lenehan <lenehan@twibble.org>
-W: http://twibble.org/dist/dc395x/
L: dc395x@twibble.org
-L: http://lists.twibble.org/mailman/listinfo/dc395x/
+W: http://twibble.org/dist/dc395x/
+W: http://lists.twibble.org/mailman/listinfo/dc395x/
S: Maintained
F: Documentation/scsi/dc395x.txt
F: drivers/scsi/dc395x.*
@@ -2845,19 +2863,29 @@
DRM DRIVERS
M: David Airlie <airlied@linux.ie>
L: dri-devel@lists.freedesktop.org
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6.git
+T: git git://people.freedesktop.org/~airlied/linux
S: Maintained
F: drivers/gpu/drm/
F: include/drm/
F: include/uapi/drm/
+RADEON DRM DRIVERS
+M: Alex Deucher <alexander.deucher@amd.com>
+M: Christian König <christian.koenig@amd.com>
+L: dri-devel@lists.freedesktop.org
+T: git git://people.freedesktop.org/~agd5f/linux
+S: Supported
+F: drivers/gpu/drm/radeon/
+F: include/drm/radeon*
+F: include/uapi/drm/radeon*
+
INTEL DRM DRIVERS (excluding Poulsbo, Moorestown and derivative chipsets)
M: Daniel Vetter <daniel.vetter@ffwll.ch>
M: Jani Nikula <jani.nikula@linux.intel.com>
L: intel-gfx@lists.freedesktop.org
L: dri-devel@lists.freedesktop.org
Q: http://patchwork.freedesktop.org/project/intel-gfx/
-T: git git://people.freedesktop.org/~danvet/drm-intel
+T: git git://anongit.freedesktop.org/drm-intel
S: Supported
F: drivers/gpu/drm/i915/
F: include/drm/i915*
@@ -3082,6 +3110,8 @@
EDAC-CORE
M: Doug Thompson <dougthompson@xmission.com>
+M: Borislav Petkov <bp@alien8.de>
+M: Mauro Carvalho Chehab <m.chehab@samsung.com>
L: linux-edac@vger.kernel.org
W: bluesmoke.sourceforge.net
S: Supported
@@ -3324,6 +3354,17 @@
F: include/linux/netfilter_bridge/
F: net/bridge/
+ETHERNET PHY LIBRARY
+M: Florian Fainelli <f.fainelli@gmail.com>
+L: netdev@vger.kernel.org
+S: Maintained
+F: include/linux/phy.h
+F: include/linux/phy_fixed.h
+F: drivers/net/phy/
+F: Documentation/networking/phy.txt
+F: drivers/of/of_mdio.c
+F: drivers/of/of_net.c
+
EXT2 FILE SYSTEM
M: Jan Kara <jack@suse.cz>
L: linux-ext4@vger.kernel.org
@@ -4517,6 +4558,7 @@
M: Alex Duyck <alexander.h.duyck@intel.com>
M: John Ronciak <john.ronciak@intel.com>
M: Mitch Williams <mitch.a.williams@intel.com>
+M: Linux NICS <linux.nics@intel.com>
L: e1000-devel@lists.sourceforge.net
W: http://www.intel.com/support/feedback.htm
W: http://e1000.sourceforge.net/
@@ -4534,6 +4576,7 @@
F: Documentation/networking/i40e.txt
F: Documentation/networking/i40evf.txt
F: drivers/net/ethernet/intel/
+F: drivers/net/ethernet/intel/*/
INTEL-MID GPIO DRIVER
M: David Cohen <david.a.cohen@linux.intel.com>
@@ -4890,7 +4933,7 @@
KCONFIG
M: "Yann E. MORIN" <yann.morin.1998@free.fr>
L: linux-kbuild@vger.kernel.org
-T: git://gitorious.org/linux-kconfig/linux-kconfig
+T: git git://gitorious.org/linux-kconfig/linux-kconfig
S: Maintained
F: Documentation/kbuild/kconfig-language.txt
F: scripts/kconfig/
@@ -5447,11 +5490,11 @@
F: drivers/media/tuners/m88ts2022*
MA901 MASTERKIT USB FM RADIO DRIVER
-M: Alexey Klimov <klimov.linux@gmail.com>
-L: linux-media@vger.kernel.org
-T: git git://linuxtv.org/media_tree.git
-S: Maintained
-F: drivers/media/radio/radio-ma901.c
+M: Alexey Klimov <klimov.linux@gmail.com>
+L: linux-media@vger.kernel.org
+T: git git://linuxtv.org/media_tree.git
+S: Maintained
+F: drivers/media/radio/radio-ma901.c
MAC80211
M: Johannes Berg <johannes@sipsolutions.net>
@@ -5487,6 +5530,11 @@
L: linux-man@vger.kernel.org
S: Maintained
+MARVELL ARMADA DRM SUPPORT
+M: Russell King <rmk+kernel@arm.linux.org.uk>
+S: Maintained
+F: drivers/gpu/drm/armada/
+
MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2)
M: Mirko Lindner <mlindner@marvell.com>
M: Stephen Hemminger <stephen@networkplumber.org>
@@ -5607,7 +5655,7 @@
MELLANOX ETHERNET DRIVER (mlx4_en)
M: Amir Vadai <amirv@mellanox.com>
-L: netdev@vger.kernel.org
+L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
Q: http://patchwork.ozlabs.org/project/netdev/list/
@@ -5648,7 +5696,7 @@
F: include/uapi/mtd/
MEN A21 WATCHDOG DRIVER
-M: Johannes Thumshirn <johannes.thumshirn@men.de>
+M: Johannes Thumshirn <johannes.thumshirn@men.de>
L: linux-watchdog@vger.kernel.org
S: Supported
F: drivers/watchdog/mena21_wdt.c
@@ -5704,20 +5752,20 @@
W: http://www.mellanox.com
Q: http://patchwork.ozlabs.org/project/netdev/list/
Q: http://patchwork.kernel.org/project/linux-rdma/list/
-T: git://openfabrics.org/~eli/connect-ib.git
+T: git git://openfabrics.org/~eli/connect-ib.git
S: Supported
F: drivers/net/ethernet/mellanox/mlx5/core/
F: include/linux/mlx5/
Mellanox MLX5 IB driver
-M: Eli Cohen <eli@mellanox.com>
-L: linux-rdma@vger.kernel.org
-W: http://www.mellanox.com
-Q: http://patchwork.kernel.org/project/linux-rdma/list/
-T: git://openfabrics.org/~eli/connect-ib.git
-S: Supported
-F: include/linux/mlx5/
-F: drivers/infiniband/hw/mlx5/
+M: Eli Cohen <eli@mellanox.com>
+L: linux-rdma@vger.kernel.org
+W: http://www.mellanox.com
+Q: http://patchwork.kernel.org/project/linux-rdma/list/
+T: git git://openfabrics.org/~eli/connect-ib.git
+S: Supported
+F: include/linux/mlx5/
+F: drivers/infiniband/hw/mlx5/
MODULE SUPPORT
M: Rusty Russell <rusty@rustcorp.com.au>
@@ -5969,6 +6017,9 @@
F: include/uapi/linux/in.h
F: include/uapi/linux/net.h
F: include/uapi/linux/netdevice.h
+F: tools/net/
+F: tools/testing/selftests/net/
+F: lib/random32.c
NETWORKING [IPv4/IPv6]
M: "David S. Miller" <davem@davemloft.net>
@@ -5992,6 +6043,7 @@
T: git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.git
S: Maintained
+F: net/core/flow.c
F: net/xfrm/
F: net/key/
F: net/ipv4/xfrm*
@@ -6143,6 +6195,12 @@
F: drivers/block/nvme*
F: include/linux/nvme.h
+NXP TDA998X DRM DRIVER
+M: Russell King <rmk+kernel@arm.linux.org.uk>
+S: Supported
+F: drivers/gpu/drm/i2c/tda998x_drv.c
+F: include/drm/i2c/tda998x.h
+
OMAP SUPPORT
M: Tony Lindgren <tony@atomide.com>
L: linux-omap@vger.kernel.org
@@ -7021,13 +7079,8 @@
F: drivers/net/ethernet/qlogic/qla3xxx.*
QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER
-M: Himanshu Madhani <himanshu.madhani@qlogic.com>
-M: Rajesh Borundia <rajesh.borundia@qlogic.com>
M: Shahed Shaikh <shahed.shaikh@qlogic.com>
-M: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com>
-M: Sony Chacko <sony.chacko@qlogic.com>
-M: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com>
-M: linux-driver@qlogic.com
+M: Dept-HSGLinuxNICDev@qlogic.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/qlogic/qlcnic/
@@ -7197,7 +7250,7 @@
F: drivers/net/ethernet/rdc/r6040.c
RDS - RELIABLE DATAGRAM SOCKETS
-M: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
+M: Chien Yen <chien.yen@oracle.com>
L: rds-devel@oss.oracle.com (moderated for non-subscribers)
S: Supported
F: net/rds/
@@ -7498,6 +7551,15 @@
L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
F: drivers/clk/samsung/
+SAMSUNG SXGBE DRIVERS
+M: Byungho An <bh74.an@samsung.com>
+M: Girish K S <ks.giri@samsung.com>
+M: Siva Reddy Kallam <siva.kallam@samsung.com>
+M: Vipul Pandya <vipul.pandya@samsung.com>
+S: Supported
+L: netdev@vger.kernel.org
+F: drivers/net/ethernet/samsung/sxgbe/
+
SERIAL DRIVERS
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
L: linux-serial@vger.kernel.org
@@ -8430,8 +8492,8 @@
M: Nicholas A. Bellinger <nab@linux-iscsi.org>
L: linux-scsi@vger.kernel.org
L: target-devel@vger.kernel.org
-L: http://groups.google.com/group/linux-iscsi-target-dev
W: http://www.linux-iscsi.org
+W: http://groups.google.com/group/linux-iscsi-target-dev
T: git git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending.git master
S: Supported
F: drivers/target/
@@ -8672,17 +8734,17 @@
F: drivers/media/radio/radio-raremono.c
THERMAL
-M: Zhang Rui <rui.zhang@intel.com>
-M: Eduardo Valentin <eduardo.valentin@ti.com>
-L: linux-pm@vger.kernel.org
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal.git
-Q: https://patchwork.kernel.org/project/linux-pm/list/
-S: Supported
-F: drivers/thermal/
-F: include/linux/thermal.h
-F: include/linux/cpu_cooling.h
-F: Documentation/devicetree/bindings/thermal/
+M: Zhang Rui <rui.zhang@intel.com>
+M: Eduardo Valentin <eduardo.valentin@ti.com>
+L: linux-pm@vger.kernel.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal.git
+Q: https://patchwork.kernel.org/project/linux-pm/list/
+S: Supported
+F: drivers/thermal/
+F: include/linux/thermal.h
+F: include/linux/cpu_cooling.h
+F: Documentation/devicetree/bindings/thermal/
THINGM BLINK(1) USB RGB LED DRIVER
M: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
@@ -9716,7 +9778,6 @@
XFS FILESYSTEM
P: Silicon Graphics Inc
M: Dave Chinner <david@fromorbit.com>
-M: Ben Myers <bpm@sgi.com>
M: xfs@oss.sgi.com
L: xfs@oss.sgi.com
W: http://oss.sgi.com/projects/xfs
@@ -9785,7 +9846,7 @@
L: mjpeg-users@lists.sourceforge.net
L: linux-media@vger.kernel.org
W: http://mjpeg.sourceforge.net/driver-zoran/
-T: Mercurial http://linuxtv.org/hg/v4l-dvb
+T: hg http://linuxtv.org/hg/v4l-dvb
S: Odd Fixes
F: drivers/media/pci/zoran/
diff --git a/Makefile b/Makefile
index 933e1de..c10b734 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 3
PATCHLEVEL = 14
SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc8
NAME = Shuffling Zombie Juror
# *DOCUMENTATION*
@@ -605,10 +605,11 @@
ifdef CONFIG_CC_STACKPROTECTOR_REGULAR
stackp-flag := -fstack-protector
ifeq ($(call cc-option, $(stackp-flag)),)
- $(warning Cannot use CONFIG_CC_STACKPROTECTOR: \
- -fstack-protector not supported by compiler))
+ $(warning Cannot use CONFIG_CC_STACKPROTECTOR_REGULAR: \
+ -fstack-protector not supported by compiler)
endif
-else ifdef CONFIG_CC_STACKPROTECTOR_STRONG
+else
+ifdef CONFIG_CC_STACKPROTECTOR_STRONG
stackp-flag := -fstack-protector-strong
ifeq ($(call cc-option, $(stackp-flag)),)
$(warning Cannot use CONFIG_CC_STACKPROTECTOR_STRONG: \
@@ -618,6 +619,7 @@
# Force off for distro compilers that enable stack protector by default.
stackp-flag := $(call cc-option, -fno-stack-protector)
endif
+endif
KBUILD_CFLAGS += $(stackp-flag)
# This warning generated too much noise in a regular build.
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index 6b58c1d..400c663 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -282,7 +282,7 @@
#else
/* if V-P const for loop, PTAG can be written once outside loop */
if (full_page_op)
- write_aux_reg(ARC_REG_DC_PTAG, paddr);
+ write_aux_reg(aux_tag, paddr);
#endif
while (num_lines-- > 0) {
@@ -296,7 +296,7 @@
write_aux_reg(aux_cmd, vaddr);
vaddr += L1_CACHE_BYTES;
#else
- write_aux_reg(aux, paddr);
+ write_aux_reg(aux_cmd, paddr);
paddr += L1_CACHE_BYTES;
#endif
}
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e254198..1594945 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1578,6 +1578,7 @@
choice
prompt "Memory split"
+ depends on MMU
default VMSPLIT_3G
help
Select the desired split between kernel and user memory.
@@ -1595,6 +1596,7 @@
config PAGE_OFFSET
hex
+ default PHYS_OFFSET if !MMU
default 0x40000000 if VMSPLIT_1G
default 0x80000000 if VMSPLIT_2G
default 0xC0000000
@@ -1903,6 +1905,7 @@
depends on ARM && AEABI && OF
depends on CPU_V7 && !CPU_V6
depends on !GENERIC_ATOMIC64
+ depends on MMU
select ARM_PSCI
select SWIOTLB_XEN
select ARCH_DMA_ADDR_T_64BIT
diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore
index 47279aa..0714e03 100644
--- a/arch/arm/boot/compressed/.gitignore
+++ b/arch/arm/boot/compressed/.gitignore
@@ -1,4 +1,5 @@
ashldi3.S
+bswapsdi2.S
font.c
lib1funcs.S
hyp-stub.S
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index b9d6a8b..0320303 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -38,6 +38,7 @@
dtb-$(CONFIG_ARCH_AT91) += at91sam9x25ek.dtb
dtb-$(CONFIG_ARCH_AT91) += at91sam9x35ek.dtb
# sama5d3
+dtb-$(CONFIG_ARCH_AT91) += at91-sama5d3_xplained.dtb
dtb-$(CONFIG_ARCH_AT91) += sama5d31ek.dtb
dtb-$(CONFIG_ARCH_AT91) += sama5d33ek.dtb
dtb-$(CONFIG_ARCH_AT91) += sama5d34ek.dtb
@@ -208,7 +209,8 @@
omap3-n900.dtb \
omap3-n9.dtb \
omap3-n950.dtb \
- omap3-tobi.dtb \
+ omap3-overo-tobi.dtb \
+ omap3-overo-storm-tobi.dtb \
omap3-gta04.dtb \
omap3-igep0020.dtb \
omap3-igep0030.dtb \
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 4718ec4..486880b 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -121,7 +121,7 @@
ti,model = "AM335x-EVMSK";
ti,audio-codec = <&tlv320aic3106>;
ti,mcasp-controller = <&mcasp1>;
- ti,codec-clock-rate = <24576000>;
+ ti,codec-clock-rate = <24000000>;
ti,audio-routing =
"Headphone Jack", "HPLOUT",
"Headphone Jack", "HPROUT";
@@ -256,6 +256,12 @@
>;
};
+ mmc1_pins: pinmux_mmc1_pins {
+ pinctrl-single,pins = <
+ 0x160 (PIN_INPUT | MUX_MODE7) /* spi0_cs1.gpio0_6 */
+ >;
+ };
+
mcasp1_pins: mcasp1_pins {
pinctrl-single,pins = <
0x10c (PIN_INPUT_PULLDOWN | MUX_MODE4) /* mii1_crs.mcasp1_aclkx */
@@ -456,6 +462,9 @@
status = "okay";
vmmc-supply = <&vmmc_reg>;
bus-width = <4>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&mmc1_pins>;
+ cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>;
};
&sham {
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index 6660968..9480cf8 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -23,6 +23,7 @@
gpio0 = &gpio0;
gpio1 = &gpio1;
gpio2 = &gpio2;
+ eth3 = ð3;
};
cpus {
@@ -291,7 +292,7 @@
interrupts = <91>;
};
- ethernet@34000 {
+ eth3: ethernet@34000 {
compatible = "marvell,armada-370-neta";
reg = <0x34000 0x4000>;
interrupts = <14>;
diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
new file mode 100644
index 0000000..ce13755
--- /dev/null
+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -0,0 +1,229 @@
+/*
+ * at91-sama5d3_xplained.dts - Device Tree file for the SAMA5D3 Xplained board
+ *
+ * Copyright (C) 2014 Atmel,
+ * 2014 Nicolas Ferre <nicolas.ferre@atmel.com>
+ *
+ * Licensed under GPLv2 or later.
+ */
+/dts-v1/;
+#include "sama5d36.dtsi"
+
+/ {
+ model = "SAMA5D3 Xplained";
+ compatible = "atmel,sama5d3-xplained", "atmel,sama5d3", "atmel,sama5";
+
+ chosen {
+ bootargs = "console=ttyS0,115200";
+ };
+
+ memory {
+ reg = <0x20000000 0x10000000>;
+ };
+
+ ahb {
+ apb {
+ mmc0: mmc@f0000000 {
+ pinctrl-0 = <&pinctrl_mmc0_clk_cmd_dat0 &pinctrl_mmc0_dat1_3 &pinctrl_mmc0_dat4_7 &pinctrl_mmc0_cd>;
+ status = "okay";
+ slot@0 {
+ reg = <0>;
+ bus-width = <8>;
+ cd-gpios = <&pioE 0 GPIO_ACTIVE_LOW>;
+ };
+ };
+
+ spi0: spi@f0004000 {
+ cs-gpios = <&pioD 13 0>;
+ status = "okay";
+ };
+
+ can0: can@f000c000 {
+ status = "okay";
+ };
+
+ i2c0: i2c@f0014000 {
+ status = "okay";
+ };
+
+ i2c1: i2c@f0018000 {
+ status = "okay";
+ };
+
+ macb0: ethernet@f0028000 {
+ phy-mode = "rgmii";
+ status = "okay";
+ };
+
+ usart0: serial@f001c000 {
+ status = "okay";
+ };
+
+ usart1: serial@f0020000 {
+ pinctrl-0 = <&pinctrl_usart1 &pinctrl_usart1_rts_cts>;
+ status = "okay";
+ };
+
+ uart0: serial@f0024000 {
+ status = "okay";
+ };
+
+ mmc1: mmc@f8000000 {
+ pinctrl-0 = <&pinctrl_mmc1_clk_cmd_dat0 &pinctrl_mmc1_dat1_3 &pinctrl_mmc1_cd>;
+ status = "okay";
+ slot@0 {
+ reg = <0>;
+ bus-width = <4>;
+ cd-gpios = <&pioE 1 GPIO_ACTIVE_HIGH>;
+ };
+ };
+
+ spi1: spi@f8008000 {
+ cs-gpios = <&pioC 25 0>, <0>, <0>, <&pioD 16 0>;
+ status = "okay";
+ };
+
+ adc0: adc@f8018000 {
+ pinctrl-0 = <
+ &pinctrl_adc0_adtrg
+ &pinctrl_adc0_ad0
+ &pinctrl_adc0_ad1
+ &pinctrl_adc0_ad2
+ &pinctrl_adc0_ad3
+ &pinctrl_adc0_ad4
+ &pinctrl_adc0_ad5
+ &pinctrl_adc0_ad6
+ &pinctrl_adc0_ad7
+ &pinctrl_adc0_ad8
+ &pinctrl_adc0_ad9
+ >;
+ status = "okay";
+ };
+
+ i2c2: i2c@f801c000 {
+ dmas = <0>, <0>; /* Do not use DMA for i2c2 */
+ status = "okay";
+ };
+
+ macb1: ethernet@f802c000 {
+ phy-mode = "rmii";
+ status = "okay";
+ };
+
+ dbgu: serial@ffffee00 {
+ status = "okay";
+ };
+
+ pinctrl@fffff200 {
+ board {
+ pinctrl_mmc0_cd: mmc0_cd {
+ atmel,pins =
+ <AT91_PIOE 0 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+ };
+
+ pinctrl_mmc1_cd: mmc1_cd {
+ atmel,pins =
+ <AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>;
+ };
+
+ pinctrl_usba_vbus: usba_vbus {
+ atmel,pins =
+ <AT91_PIOE 9 AT91_PERIPH_GPIO AT91_PINCTRL_DEGLITCH>; /* PE9, conflicts with A9 */
+ };
+ };
+ };
+
+ pmc: pmc@fffffc00 {
+ main: mainck {
+ clock-frequency = <12000000>;
+ };
+ };
+ };
+
+ nand0: nand@60000000 {
+ nand-bus-width = <8>;
+ nand-ecc-mode = "hw";
+ atmel,has-pmecc;
+ atmel,pmecc-cap = <4>;
+ atmel,pmecc-sector-size = <512>;
+ nand-on-flash-bbt;
+ status = "okay";
+
+ at91bootstrap@0 {
+ label = "at91bootstrap";
+ reg = <0x0 0x40000>;
+ };
+
+ bootloader@40000 {
+ label = "bootloader";
+ reg = <0x40000 0x80000>;
+ };
+
+ bootloaderenv@c0000 {
+ label = "bootloader env";
+ reg = <0xc0000 0xc0000>;
+ };
+
+ dtb@180000 {
+ label = "device tree";
+ reg = <0x180000 0x80000>;
+ };
+
+ kernel@200000 {
+ label = "kernel";
+ reg = <0x200000 0x600000>;
+ };
+
+ rootfs@800000 {
+ label = "rootfs";
+ reg = <0x800000 0x0f800000>;
+ };
+ };
+
+ usb0: gadget@00500000 {
+ atmel,vbus-gpio = <&pioE 9 GPIO_ACTIVE_HIGH>; /* PE9, conflicts with A9 */
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_usba_vbus>;
+ status = "okay";
+ };
+
+ usb1: ohci@00600000 {
+ num-ports = <3>;
+ atmel,vbus-gpio = <0
+ &pioE 3 GPIO_ACTIVE_LOW
+ &pioE 4 GPIO_ACTIVE_LOW
+ >;
+ status = "okay";
+ };
+
+ usb2: ehci@00700000 {
+ status = "okay";
+ };
+ };
+
+ gpio_keys {
+ compatible = "gpio-keys";
+
+ bp3 {
+ label = "PB_USER";
+ gpios = <&pioE 29 GPIO_ACTIVE_LOW>;
+ linux,code = <0x104>;
+ gpio-key,wakeup;
+ };
+ };
+
+ leds {
+ compatible = "gpio-leds";
+
+ d2 {
+ label = "d2";
+ gpios = <&pioE 23 GPIO_ACTIVE_LOW>; /* PE23, conflicts with A23, CTS2 */
+ linux,default-trigger = "heartbeat";
+ };
+
+ d3 {
+ label = "d3";
+ gpios = <&pioE 24 GPIO_ACTIVE_HIGH>;
+ };
+ };
+};
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index 0042f73..fece866 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -523,7 +523,7 @@
};
i2c0: i2c@fff88000 {
- compatible = "atmel,at91sam9263-i2c";
+ compatible = "atmel,at91sam9260-i2c";
reg = <0xfff88000 0x100>;
interrupts = <13 IRQ_TYPE_LEVEL_HIGH 6>;
#address-cells = <1>;
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index e9487f6..924a6a6 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -124,6 +124,10 @@
nand-on-flash-bbt;
status = "okay";
};
+
+ usb0: ohci@00500000 {
+ status = "okay";
+ };
};
leds {
diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi
index e491b82..792fde1 100644
--- a/arch/arm/boot/dts/bcm11351.dtsi
+++ b/arch/arm/boot/dts/bcm11351.dtsi
@@ -147,7 +147,7 @@
};
pinctrl@35004800 {
- compatible = "brcm,capri-pinctrl";
+ compatible = "brcm,bcm11351-pinctrl";
reg = <0x35004800 0x430>;
};
diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi
index 2b76524..187fd46 100644
--- a/arch/arm/boot/dts/dove.dtsi
+++ b/arch/arm/boot/dts/dove.dtsi
@@ -379,15 +379,6 @@
#clock-cells = <1>;
};
- pmu_intc: pmu-interrupt-ctrl@d0050 {
- compatible = "marvell,dove-pmu-intc";
- interrupt-controller;
- #interrupt-cells = <1>;
- reg = <0xd0050 0x8>;
- interrupts = <33>;
- marvell,#interrupts = <7>;
- };
-
pinctrl: pin-ctrl@d0200 {
compatible = "marvell,dove-pinctrl";
reg = <0xd0200 0x10>;
@@ -610,8 +601,6 @@
rtc: real-time-clock@d8500 {
compatible = "marvell,orion-rtc";
reg = <0xd8500 0x20>;
- interrupt-parent = <&pmu_intc>;
- interrupts = <5>;
};
gpio2: gpio-ctrl@e8400 {
diff --git a/arch/arm/boot/dts/imx6dl-hummingboard.dts b/arch/arm/boot/dts/imx6dl-hummingboard.dts
index fd8fc7c..5bfae54 100644
--- a/arch/arm/boot/dts/imx6dl-hummingboard.dts
+++ b/arch/arm/boot/dts/imx6dl-hummingboard.dts
@@ -52,12 +52,6 @@
};
};
- codec: spdif-transmitter {
- compatible = "linux,spdif-dit";
- pinctrl-names = "default";
- pinctrl-0 = <&pinctrl_hummingboard_spdif>;
- };
-
sound-spdif {
compatible = "fsl,imx-audio-spdif";
model = "imx-spdif";
@@ -111,7 +105,7 @@
};
pinctrl_hummingboard_spdif: hummingboard-spdif {
- fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x1b0b0>;
+ fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x13091>;
};
pinctrl_hummingboard_usbh1_vbus: hummingboard-usbh1-vbus {
@@ -142,6 +136,8 @@
};
&spdif {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_hummingboard_spdif>;
status = "okay";
};
diff --git a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
index 64daa3b..c2a2488 100644
--- a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
@@ -46,12 +46,6 @@
};
};
- codec: spdif-transmitter {
- compatible = "linux,spdif-dit";
- pinctrl-names = "default";
- pinctrl-0 = <&pinctrl_cubox_i_spdif>;
- };
-
sound-spdif {
compatible = "fsl,imx-audio-spdif";
model = "imx-spdif";
@@ -89,7 +83,7 @@
};
pinctrl_cubox_i_spdif: cubox-i-spdif {
- fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x1b0b0>;
+ fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x13091>;
};
pinctrl_cubox_i_usbh1_vbus: cubox-i-usbh1-vbus {
@@ -121,6 +115,8 @@
};
&spdif {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_cubox_i_spdif>;
status = "okay";
};
diff --git a/arch/arm/boot/dts/keystone-clocks.dtsi b/arch/arm/boot/dts/keystone-clocks.dtsi
index 2363593..ef58d1c 100644
--- a/arch/arm/boot/dts/keystone-clocks.dtsi
+++ b/arch/arm/boot/dts/keystone-clocks.dtsi
@@ -612,7 +612,7 @@
compatible = "ti,keystone,psc-clock";
clocks = <&chipclk13>;
clock-output-names = "vcp-3";
- reg = <0x0235000a8 0xb00>, <0x02350060 0x400>;
+ reg = <0x023500a8 0xb00>, <0x02350060 0x400>;
reg-names = "control", "domain";
domain-id = <24>;
};
diff --git a/arch/arm/boot/dts/omap3-gta04.dts b/arch/arm/boot/dts/omap3-gta04.dts
index b9b55c9..d3b253b 100644
--- a/arch/arm/boot/dts/omap3-gta04.dts
+++ b/arch/arm/boot/dts/omap3-gta04.dts
@@ -13,7 +13,7 @@
/ {
model = "OMAP3 GTA04";
- compatible = "ti,omap3-gta04", "ti,omap3";
+ compatible = "ti,omap3-gta04", "ti,omap36xx", "ti,omap3";
cpus {
cpu@0 {
@@ -32,7 +32,7 @@
aux-button {
label = "aux";
linux,code = <169>;
- gpios = <&gpio1 7 GPIO_ACTIVE_LOW>;
+ gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
gpio-key,wakeup;
};
};
@@ -92,6 +92,8 @@
bmp085@77 {
compatible = "bosch,bmp085";
reg = <0x77>;
+ interrupt-parent = <&gpio4>;
+ interrupts = <17 IRQ_TYPE_EDGE_RISING>;
};
/* leds */
@@ -141,8 +143,8 @@
pinctrl-names = "default";
pinctrl-0 = <&mmc1_pins>;
vmmc-supply = <&vmmc1>;
- vmmc_aux-supply = <&vsim>;
bus-width = <4>;
+ ti,non-removable;
};
&mmc2 {
diff --git a/arch/arm/boot/dts/omap3-igep0020.dts b/arch/arm/boot/dts/omap3-igep0020.dts
index 25a2b5f..f2779ac 100644
--- a/arch/arm/boot/dts/omap3-igep0020.dts
+++ b/arch/arm/boot/dts/omap3-igep0020.dts
@@ -14,7 +14,7 @@
/ {
model = "IGEPv2 (TI OMAP AM/DM37x)";
- compatible = "isee,omap3-igep0020", "ti,omap3";
+ compatible = "isee,omap3-igep0020", "ti,omap36xx", "ti,omap3";
leds {
pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/omap3-igep0030.dts b/arch/arm/boot/dts/omap3-igep0030.dts
index 145c58c..2793749 100644
--- a/arch/arm/boot/dts/omap3-igep0030.dts
+++ b/arch/arm/boot/dts/omap3-igep0030.dts
@@ -13,7 +13,7 @@
/ {
model = "IGEP COM MODULE (TI OMAP AM/DM37x)";
- compatible = "isee,omap3-igep0030", "ti,omap3";
+ compatible = "isee,omap3-igep0030", "ti,omap36xx", "ti,omap3";
leds {
pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/omap3-n9.dts b/arch/arm/boot/dts/omap3-n9.dts
index 39828ce..9938b5d 100644
--- a/arch/arm/boot/dts/omap3-n9.dts
+++ b/arch/arm/boot/dts/omap3-n9.dts
@@ -14,5 +14,5 @@
/ {
model = "Nokia N9";
- compatible = "nokia,omap3-n9", "ti,omap3";
+ compatible = "nokia,omap3-n9", "ti,omap36xx", "ti,omap3";
};
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 6fc85f9..0bf40c9 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -1,6 +1,6 @@
/*
* Copyright (C) 2013 Pavel Machek <pavel@ucw.cz>
- * Copyright 2013 Aaro Koskinen <aaro.koskinen@iki.fi>
+ * Copyright (C) 2013-2014 Aaro Koskinen <aaro.koskinen@iki.fi>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 (or later) as
@@ -13,7 +13,7 @@
/ {
model = "Nokia N900";
- compatible = "nokia,omap3-n900", "ti,omap3";
+ compatible = "nokia,omap3-n900", "ti,omap3430", "ti,omap3";
cpus {
cpu@0 {
diff --git a/arch/arm/boot/dts/omap3-n950.dts b/arch/arm/boot/dts/omap3-n950.dts
index b076a52..261c558 100644
--- a/arch/arm/boot/dts/omap3-n950.dts
+++ b/arch/arm/boot/dts/omap3-n950.dts
@@ -14,5 +14,5 @@
/ {
model = "Nokia N950";
- compatible = "nokia,omap3-n950", "ti,omap3";
+ compatible = "nokia,omap3-n950", "ti,omap36xx", "ti,omap3";
};
diff --git a/arch/arm/boot/dts/omap3-overo-storm-tobi.dts b/arch/arm/boot/dts/omap3-overo-storm-tobi.dts
new file mode 100644
index 0000000..966b5c9
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-storm-tobi.dts
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2012 Florian Vaussard, EPFL Mobots group
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Tobi expansion board is manufactured by Gumstix Inc.
+ */
+
+/dts-v1/;
+
+#include "omap36xx.dtsi"
+#include "omap3-overo-tobi-common.dtsi"
+
+/ {
+ model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on Tobi";
+ compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3";
+};
+
diff --git a/arch/arm/boot/dts/omap3-tobi.dts b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
similarity index 93%
rename from arch/arm/boot/dts/omap3-tobi.dts
rename to arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
index 7e4ad2a..4edc013 100644
--- a/arch/arm/boot/dts/omap3-tobi.dts
+++ b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
@@ -13,9 +13,6 @@
#include "omap3-overo.dtsi"
/ {
- model = "TI OMAP3 Gumstix Overo on Tobi";
- compatible = "ti,omap3-tobi", "ti,omap3-overo", "ti,omap3";
-
leds {
compatible = "gpio-leds";
heartbeat {
diff --git a/arch/arm/boot/dts/omap3-overo-tobi.dts b/arch/arm/boot/dts/omap3-overo-tobi.dts
new file mode 100644
index 0000000..de5653e
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-tobi.dts
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2012 Florian Vaussard, EPFL Mobots group
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Tobi expansion board is manufactured by Gumstix Inc.
+ */
+
+/dts-v1/;
+
+#include "omap34xx.dtsi"
+#include "omap3-overo-tobi-common.dtsi"
+
+/ {
+ model = "OMAP35xx Gumstix Overo on Tobi";
+ compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap3430", "ti,omap3";
+};
+
diff --git a/arch/arm/boot/dts/omap3-overo.dtsi b/arch/arm/boot/dts/omap3-overo.dtsi
index a461d2f..5970999 100644
--- a/arch/arm/boot/dts/omap3-overo.dtsi
+++ b/arch/arm/boot/dts/omap3-overo.dtsi
@@ -9,9 +9,6 @@
/*
* The Gumstix Overo must be combined with an expansion board.
*/
-/dts-v1/;
-
-#include "omap34xx.dtsi"
/ {
pwmleds {
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 52447c1..3d5faf8 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -1228,7 +1228,7 @@
compatible = "atmel,at91rm9200-ohci", "usb-ohci";
reg = <0x00600000 0x100000>;
interrupts = <32 IRQ_TYPE_LEVEL_HIGH 2>;
- clocks = <&usb>, <&uhphs_clk>, <&udphs_clk>,
+ clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>,
<&uhpck>;
clock-names = "usb_clk", "ohci_clk", "hclk", "uhpck";
status = "disabled";
diff --git a/arch/arm/boot/dts/sama5d36.dtsi b/arch/arm/boot/dts/sama5d36.dtsi
index 6c31c26..db58cad 100644
--- a/arch/arm/boot/dts/sama5d36.dtsi
+++ b/arch/arm/boot/dts/sama5d36.dtsi
@@ -8,8 +8,8 @@
*/
#include "sama5d3.dtsi"
#include "sama5d3_can.dtsi"
-#include "sama5d3_emac.dtsi"
#include "sama5d3_gmac.dtsi"
+#include "sama5d3_emac.dtsi"
#include "sama5d3_lcd.dtsi"
#include "sama5d3_mci2.dtsi"
#include "sama5d3_tcb1.dtsi"
diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index 0c1e8d8..6cb9b68 100644
--- a/arch/arm/boot/dts/ste-href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -188,7 +188,6 @@
msp2: msp@80117000 {
pinctrl-names = "default";
pinctrl-0 = <&msp2_default_mode>;
- status = "okay";
};
msp3: msp@80125000 {
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 040bb0e..d4d2763 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -315,7 +315,7 @@
ranges;
emac: ethernet@01c0b000 {
- compatible = "allwinner,sun4i-emac";
+ compatible = "allwinner,sun4i-a10-emac";
reg = <0x01c0b000 0x1000>;
interrupts = <55>;
clocks = <&ahb_gates 17>;
@@ -323,7 +323,7 @@
};
mdio@01c0b080 {
- compatible = "allwinner,sun4i-mdio";
+ compatible = "allwinner,sun4i-a10-mdio";
reg = <0x01c0b080 0x14>;
status = "disabled";
#address-cells = <1>;
@@ -426,7 +426,7 @@
};
rtp: rtp@01c25000 {
- compatible = "allwinner,sun4i-ts";
+ compatible = "allwinner,sun4i-a10-ts";
reg = <0x01c25000 0x100>;
interrupts = <29>;
};
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index ea16054..79fd412 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -278,7 +278,7 @@
ranges;
emac: ethernet@01c0b000 {
- compatible = "allwinner,sun4i-emac";
+ compatible = "allwinner,sun4i-a10-emac";
reg = <0x01c0b000 0x1000>;
interrupts = <55>;
clocks = <&ahb_gates 17>;
@@ -286,7 +286,7 @@
};
mdio@01c0b080 {
- compatible = "allwinner,sun4i-mdio";
+ compatible = "allwinner,sun4i-a10-mdio";
reg = <0x01c0b080 0x14>;
status = "disabled";
#address-cells = <1>;
@@ -383,7 +383,7 @@
};
rtp: rtp@01c25000 {
- compatible = "allwinner,sun4i-ts";
+ compatible = "allwinner,sun4i-a10-ts";
reg = <0x01c25000 0x100>;
interrupts = <29>;
};
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index 320335a..c463fd7 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -346,7 +346,7 @@
};
rtp: rtp@01c25000 {
- compatible = "allwinner,sun4i-ts";
+ compatible = "allwinner,sun4i-a10-ts";
reg = <0x01c25000 0x100>;
interrupts = <29>;
};
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 119f066..6f25cf5 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -340,7 +340,7 @@
ranges;
emac: ethernet@01c0b000 {
- compatible = "allwinner,sun4i-emac";
+ compatible = "allwinner,sun4i-a10-emac";
reg = <0x01c0b000 0x1000>;
interrupts = <0 55 4>;
clocks = <&ahb_gates 17>;
@@ -348,7 +348,7 @@
};
mdio@01c0b080 {
- compatible = "allwinner,sun4i-mdio";
+ compatible = "allwinner,sun4i-a10-mdio";
reg = <0x01c0b080 0x14>;
status = "disabled";
#address-cells = <1>;
@@ -454,7 +454,7 @@
rtc: rtc@01c20d00 {
compatible = "allwinner,sun7i-a20-rtc";
reg = <0x01c20d00 0x20>;
- interrupts = <0 24 1>;
+ interrupts = <0 24 4>;
};
sid: eeprom@01c23800 {
@@ -463,7 +463,7 @@
};
rtp: rtp@01c25000 {
- compatible = "allwinner,sun4i-ts";
+ compatible = "allwinner,sun4i-a10-ts";
reg = <0x01c25000 0x100>;
interrupts = <0 29 4>;
};
@@ -596,10 +596,10 @@
hstimer@01c60000 {
compatible = "allwinner,sun7i-a20-hstimer";
reg = <0x01c60000 0x1000>;
- interrupts = <0 81 1>,
- <0 82 1>,
- <0 83 1>,
- <0 84 1>;
+ interrupts = <0 81 4>,
+ <0 82 4>,
+ <0 83 4>,
+ <0 84 4>;
clocks = <&ahb_gates 28>;
};
diff --git a/arch/arm/boot/dts/tegra114.dtsi b/arch/arm/boot/dts/tegra114.dtsi
index 389e987..44ec401 100644
--- a/arch/arm/boot/dts/tegra114.dtsi
+++ b/arch/arm/boot/dts/tegra114.dtsi
@@ -57,6 +57,8 @@
resets = <&tegra_car 27>;
reset-names = "dc";
+ nvidia,head = <0>;
+
rgb {
status = "disabled";
};
@@ -72,6 +74,8 @@
resets = <&tegra_car 26>;
reset-names = "dc";
+ nvidia,head = <1>;
+
rgb {
status = "disabled";
};
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index 480ecda..48d2a7f 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -94,6 +94,8 @@
resets = <&tegra_car 27>;
reset-names = "dc";
+ nvidia,head = <0>;
+
rgb {
status = "disabled";
};
@@ -109,6 +111,8 @@
resets = <&tegra_car 26>;
reset-names = "dc";
+ nvidia,head = <1>;
+
rgb {
status = "disabled";
};
diff --git a/arch/arm/boot/dts/tegra30-cardhu.dtsi b/arch/arm/boot/dts/tegra30-cardhu.dtsi
index 9104224..1e156d9 100644
--- a/arch/arm/boot/dts/tegra30-cardhu.dtsi
+++ b/arch/arm/boot/dts/tegra30-cardhu.dtsi
@@ -28,7 +28,7 @@
compatible = "nvidia,cardhu", "nvidia,tegra30";
aliases {
- rtc0 = "/i2c@7000d000/tps6586x@34";
+ rtc0 = "/i2c@7000d000/tps65911@2d";
rtc1 = "/rtc@7000e000";
};
diff --git a/arch/arm/boot/dts/tegra30.dtsi b/arch/arm/boot/dts/tegra30.dtsi
index ed8e770..19a84e9 100644
--- a/arch/arm/boot/dts/tegra30.dtsi
+++ b/arch/arm/boot/dts/tegra30.dtsi
@@ -170,6 +170,8 @@
resets = <&tegra_car 27>;
reset-names = "dc";
+ nvidia,head = <0>;
+
rgb {
status = "disabled";
};
@@ -185,6 +187,8 @@
resets = <&tegra_car 26>;
reset-names = "dc";
+ nvidia,head = <1>;
+
rgb {
status = "disabled";
};
diff --git a/arch/arm/boot/dts/testcases/tests.dtsi b/arch/arm/boot/dts/testcases/tests.dtsi
deleted file mode 100644
index 3f123ec..0000000
--- a/arch/arm/boot/dts/testcases/tests.dtsi
+++ /dev/null
@@ -1,2 +0,0 @@
-/include/ "tests-phandle.dtsi"
-/include/ "tests-interrupts.dtsi"
diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts
index f43907c..65f6577 100644
--- a/arch/arm/boot/dts/versatile-pb.dts
+++ b/arch/arm/boot/dts/versatile-pb.dts
@@ -1,4 +1,4 @@
-/include/ "versatile-ab.dts"
+#include <versatile-ab.dts>
/ {
model = "ARM Versatile PB";
@@ -47,4 +47,4 @@
};
};
-/include/ "testcases/tests.dtsi"
+#include <testcases.dtsi>
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 845bc74..ee69829 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -29,6 +29,7 @@
CONFIG_ARCH_OMAP4=y
CONFIG_SOC_OMAP5=y
CONFIG_SOC_AM33XX=y
+CONFIG_SOC_DRA7XX=y
CONFIG_SOC_AM43XX=y
CONFIG_ARCH_ROCKCHIP=y
CONFIG_ARCH_SOCFPGA=y
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index 00fe9e9..27d69b55 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -204,7 +204,10 @@
CONFIG_MMC_SDHCI=y
CONFIG_MMC_SDHCI_PLTFM=y
CONFIG_MMC_SDHCI_TEGRA=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
CONFIG_LEDS_TRIGGER_ONESHOT=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index e9a49fe..8b8b616 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -212,6 +212,7 @@
static inline void __flush_icache_all(void)
{
__flush_icache_preferred();
+ dsb();
}
/*
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 8756e4b..4afb376 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -30,14 +30,15 @@
*/
#define UL(x) _AC(x, UL)
+/* PAGE_OFFSET - the virtual address of the start of the kernel image */
+#define PAGE_OFFSET UL(CONFIG_PAGE_OFFSET)
+
#ifdef CONFIG_MMU
/*
- * PAGE_OFFSET - the virtual address of the start of the kernel image
* TASK_SIZE - the maximum size of a user space task.
* TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area
*/
-#define PAGE_OFFSET UL(CONFIG_PAGE_OFFSET)
#define TASK_SIZE (UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M))
#define TASK_UNMAPPED_BASE ALIGN(TASK_SIZE / 3, SZ_16M)
@@ -104,10 +105,6 @@
#define END_MEM (UL(CONFIG_DRAM_BASE) + CONFIG_DRAM_SIZE)
#endif
-#ifndef PAGE_OFFSET
-#define PAGE_OFFSET PLAT_PHYS_OFFSET
-#endif
-
/*
* The module can be at any place in ram in nommu mode.
*/
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 03243f7..85c60ad 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -120,13 +120,16 @@
/*
* 2nd stage PTE definitions for LPAE.
*/
-#define L_PTE_S2_MT_UNCACHED (_AT(pteval_t, 0x5) << 2) /* MemAttr[3:0] */
-#define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */
-#define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */
-#define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */
-#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */
+#define L_PTE_S2_MT_UNCACHED (_AT(pteval_t, 0x0) << 2) /* strongly ordered */
+#define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* normal inner write-through */
+#define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* normal inner write-back */
+#define L_PTE_S2_MT_DEV_SHARED (_AT(pteval_t, 0x1) << 2) /* device */
+#define L_PTE_S2_MT_MASK (_AT(pteval_t, 0xf) << 2)
-#define L_PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */
+#define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */
+#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */
+
+#define L_PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */
/*
* Hyp-mode PL2 PTE definitions for LPAE.
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index ef3c607..ac4bfae 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -37,18 +37,9 @@
static inline void dsb_sev(void)
{
-#if __LINUX_ARM_ARCH__ >= 7
- __asm__ __volatile__ (
- "dsb ishst\n"
- SEV
- );
-#else
- __asm__ __volatile__ (
- "mcr p15, 0, %0, c7, c10, 4\n"
- SEV
- : : "r" (0)
- );
-#endif
+
+ dsb(ishst);
+ __asm__(SEV);
}
/*
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 47cd974..c96ecac 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -177,6 +177,18 @@
.long __proc_info_end
.size __lookup_processor_type_data, . - __lookup_processor_type_data
+__error_lpae:
+#ifdef CONFIG_DEBUG_LL
+ adr r0, str_lpae
+ bl printascii
+ b __error
+str_lpae: .asciz "\nError: Kernel with LPAE support, but CPU does not support LPAE.\n"
+#else
+ b __error
+#endif
+ .align
+ENDPROC(__error_lpae)
+
__error_p:
#ifdef CONFIG_DEBUG_LL
adr r0, str_p1
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 914616e..f5f381d 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -102,7 +102,7 @@
and r3, r3, #0xf @ extract VMSA support
cmp r3, #5 @ long-descriptor translation table format?
THUMB( it lo ) @ force fixup-able long branch encoding
- blo __error_p @ only classic page table format
+ blo __error_lpae @ only classic page table format
#endif
#ifndef CONFIG_XIP_KERNEL
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index b0df976..1e8b030 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -731,7 +731,7 @@
kernel_data.end = virt_to_phys(_end - 1);
for_each_memblock(memory, region) {
- res = memblock_virt_alloc_low(sizeof(*res), 0);
+ res = memblock_virt_alloc(sizeof(*res), 0);
res->name = "System RAM";
res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 1d8248e..bd18bb8 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -878,7 +878,8 @@
unsigned long cmd,
void *v)
{
- if (cmd == CPU_PM_EXIT) {
+ if (cmd == CPU_PM_EXIT &&
+ __hyp_get_vectors() == hyp_default_vectors) {
cpu_init_hyp_mode(NULL);
return NOTIFY_OK;
}
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index ddc1553..0d68d40 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -220,6 +220,10 @@
* in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are
* passed in r0 and r1.
*
+ * A function pointer with a value of 0xffffffff has a special meaning,
+ * and is used to implement __hyp_get_vectors in the same way as in
+ * arch/arm/kernel/hyp_stub.S.
+ *
* The calling convention follows the standard AAPCS:
* r0 - r3: caller save
* r12: caller save
@@ -363,6 +367,11 @@
host_switch_to_hyp:
pop {r0, r1, r2}
+ /* Check for __hyp_get_vectors */
+ cmp r0, #-1
+ mrceq p15, 4, r0, c12, c0, 0 @ get HVBAR
+ beq 1f
+
push {lr}
mrs lr, SPSR
push {lr}
@@ -378,7 +387,7 @@
pop {lr}
msr SPSR_csxf, lr
pop {lr}
- eret
+1: eret
guest_trap:
load_vcpu @ Load VCPU pointer to r0
diff --git a/arch/arm/mach-hisi/Kconfig b/arch/arm/mach-hisi/Kconfig
index 8f4649b..1abae5f 100644
--- a/arch/arm/mach-hisi/Kconfig
+++ b/arch/arm/mach-hisi/Kconfig
@@ -8,7 +8,7 @@
select CLKSRC_OF
select GENERIC_CLOCKEVENTS
select HAVE_ARM_SCU
- select HAVE_ARM_TWD
+ select HAVE_ARM_TWD if SMP
select HAVE_SMP
select PINCTRL
select PINCTRL_SINGLE
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index befcaf5..ec41964 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -101,11 +101,9 @@
obj-$(CONFIG_SOC_IMX6Q) += clk-imx6q.o mach-imx6q.o
obj-$(CONFIG_SOC_IMX6SL) += clk-imx6sl.o mach-imx6sl.o
-ifeq ($(CONFIG_PM),y)
obj-$(CONFIG_SOC_IMX6Q) += pm-imx6q.o headsmp.o
# i.MX6SL reuses i.MX6Q code
obj-$(CONFIG_SOC_IMX6SL) += pm-imx6q.o headsmp.o
-endif
# i.MX5 based machines
obj-$(CONFIG_MACH_MX51_BABBAGE) += mach-mx51_babbage.o
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index af2e582..4d677f4 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -482,6 +482,9 @@
if (IS_ENABLED(CONFIG_PCI_IMX6))
clk_set_parent(clk[lvds1_sel], clk[sata_ref]);
+ /* Set initial power mode */
+ imx6q_set_lpm(WAIT_CLOCKED);
+
np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpt");
base = of_iomap(np, 0);
WARN_ON(!base);
diff --git a/arch/arm/mach-imx/clk-imx6sl.c b/arch/arm/mach-imx/clk-imx6sl.c
index 3781a18..4c86f30 100644
--- a/arch/arm/mach-imx/clk-imx6sl.c
+++ b/arch/arm/mach-imx/clk-imx6sl.c
@@ -266,6 +266,9 @@
/* Audio-related clocks configuration */
clk_set_parent(clks[IMX6SL_CLK_SPDIF0_SEL], clks[IMX6SL_CLK_PLL3_PFD3]);
+ /* Set initial power mode */
+ imx6q_set_lpm(WAIT_CLOCKED);
+
np = of_find_compatible_node(NULL, NULL, "fsl,imx6sl-gpt");
base = of_iomap(np, 0);
WARN_ON(!base);
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index 59c3b9b..baf439d 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -144,13 +144,11 @@
void imx_cpu_die(unsigned int cpu);
int imx_cpu_kill(unsigned int cpu);
-#ifdef CONFIG_PM
void imx6q_pm_init(void);
void imx6q_pm_set_ccm_base(void __iomem *base);
+#ifdef CONFIG_PM
void imx5_pm_init(void);
#else
-static inline void imx6q_pm_init(void) {}
-static inline void imx6q_pm_set_ccm_base(void __iomem *base) {}
static inline void imx5_pm_init(void) {}
#endif
diff --git a/arch/arm/mach-imx/pm-imx6q.c b/arch/arm/mach-imx/pm-imx6q.c
index 9d47adc..7a9b985 100644
--- a/arch/arm/mach-imx/pm-imx6q.c
+++ b/arch/arm/mach-imx/pm-imx6q.c
@@ -236,8 +236,6 @@
regmap_update_bits(gpr, IOMUXC_GPR1, IMX6Q_GPR1_GINT,
IMX6Q_GPR1_GINT);
- /* Set initial power mode */
- imx6q_set_lpm(WAIT_CLOCKED);
suspend_set_ops(&imx6q_pm_ops);
}
diff --git a/arch/arm/mach-moxart/Kconfig b/arch/arm/mach-moxart/Kconfig
index ba470d6..3795ae2 100644
--- a/arch/arm/mach-moxart/Kconfig
+++ b/arch/arm/mach-moxart/Kconfig
@@ -2,7 +2,6 @@
bool "MOXA ART SoC" if ARCH_MULTI_V4T
select CPU_FA526
select ARM_DMA_MEM_BUFFERABLE
- select DMA_OF
select USE_OF
select CLKSRC_OF
select CLKSRC_MMIO
diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c
index 91449c5..85089d8 100644
--- a/arch/arm/mach-omap1/board-nokia770.c
+++ b/arch/arm/mach-omap1/board-nokia770.c
@@ -156,6 +156,7 @@
.register_dev = 1,
.hmc_mode = 16,
.pins[0] = 6,
+ .extcon = "tahvo-usb",
};
#if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE)
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 653b489..0af7ca0 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -50,11 +50,12 @@
bool "TI OMAP5"
depends on ARCH_MULTI_V7
select ARCH_OMAP2PLUS
+ select ARCH_HAS_OPP
select ARM_CPU_SUSPEND if PM
select ARM_GIC
select CPU_V7
select HAVE_ARM_SCU if SMP
- select HAVE_ARM_TWD if LOCAL_TIMERS
+ select HAVE_ARM_TWD if SMP
select HAVE_SMP
select HAVE_ARM_ARCH_TIMER
select ARM_ERRATA_798181 if SMP
@@ -63,6 +64,7 @@
bool "TI AM33XX"
depends on ARCH_MULTI_V7
select ARCH_OMAP2PLUS
+ select ARCH_HAS_OPP
select ARM_CPU_SUSPEND if PM
select CPU_V7
select MULTI_IRQ_HANDLER
@@ -72,6 +74,7 @@
depends on ARCH_MULTI_V7
select CPU_V7
select ARCH_OMAP2PLUS
+ select ARCH_HAS_OPP
select MULTI_IRQ_HANDLER
select ARM_GIC
select MACH_OMAP_GENERIC
@@ -80,6 +83,7 @@
bool "TI DRA7XX"
depends on ARCH_MULTI_V7
select ARCH_OMAP2PLUS
+ select ARCH_HAS_OPP
select ARM_CPU_SUSPEND if PM
select ARM_GIC
select CPU_V7
@@ -268,9 +272,6 @@
default y
select OMAP_PACKAGE_CBB
-config MACH_NOKIA_N800
- bool
-
config MACH_NOKIA_N810
bool
@@ -281,7 +282,6 @@
bool "Nokia N800/N810"
depends on SOC_OMAP2420
default y
- select MACH_NOKIA_N800
select MACH_NOKIA_N810
select MACH_NOKIA_N810_WIMAX
select OMAP_PACKAGE_ZAC
diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c
index 3b05aea..11ed915 100644
--- a/arch/arm/mach-omap2/cclock3xxx_data.c
+++ b/arch/arm/mach-omap2/cclock3xxx_data.c
@@ -433,7 +433,9 @@
.enable = &omap2_dflt_clk_enable,
.disable = &omap2_dflt_clk_disable,
.is_enabled = &omap2_dflt_clk_is_enabled,
+ .set_rate = &omap3_clkoutx2_set_rate,
.recalc_rate = &omap3_clkoutx2_recalc,
+ .round_rate = &omap3_clkoutx2_round_rate,
};
static const struct clk_ops dpll4_m5x2_ck_3630_ops = {
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index 4c158c8..01fc710 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -23,6 +23,8 @@
#include "prm.h"
#include "clockdomain.h"
+#define MAX_CPUS 2
+
/* Machine specific information */
struct idle_statedata {
u32 cpu_state;
@@ -48,11 +50,11 @@
},
};
-static struct powerdomain *mpu_pd, *cpu_pd[NR_CPUS];
-static struct clockdomain *cpu_clkdm[NR_CPUS];
+static struct powerdomain *mpu_pd, *cpu_pd[MAX_CPUS];
+static struct clockdomain *cpu_clkdm[MAX_CPUS];
static atomic_t abort_barrier;
-static bool cpu_done[NR_CPUS];
+static bool cpu_done[MAX_CPUS];
static struct idle_statedata *state_ptr = &omap4_idle_data[0];
/* Private functions */
diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c
index 3185ced..3c418ea 100644
--- a/arch/arm/mach-omap2/dpll3xxx.c
+++ b/arch/arm/mach-omap2/dpll3xxx.c
@@ -623,25 +623,12 @@
/* Clock control for DPLL outputs */
-/**
- * omap3_clkoutx2_recalc - recalculate DPLL X2 output virtual clock rate
- * @clk: DPLL output struct clk
- *
- * Using parent clock DPLL data, look up DPLL state. If locked, set our
- * rate to the dpll_clk * 2; otherwise, just use dpll_clk.
- */
-unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
- unsigned long parent_rate)
+/* Find the parent DPLL for the given clkoutx2 clock */
+static struct clk_hw_omap *omap3_find_clkoutx2_dpll(struct clk_hw *hw)
{
- const struct dpll_data *dd;
- unsigned long rate;
- u32 v;
struct clk_hw_omap *pclk = NULL;
struct clk *parent;
- if (!parent_rate)
- return 0;
-
/* Walk up the parents of clk, looking for a DPLL */
do {
do {
@@ -656,9 +643,35 @@
/* clk does not have a DPLL as a parent? error in the clock data */
if (!pclk) {
WARN_ON(1);
- return 0;
+ return NULL;
}
+ return pclk;
+}
+
+/**
+ * omap3_clkoutx2_recalc - recalculate DPLL X2 output virtual clock rate
+ * @clk: DPLL output struct clk
+ *
+ * Using parent clock DPLL data, look up DPLL state. If locked, set our
+ * rate to the dpll_clk * 2; otherwise, just use dpll_clk.
+ */
+unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
+ unsigned long parent_rate)
+{
+ const struct dpll_data *dd;
+ unsigned long rate;
+ u32 v;
+ struct clk_hw_omap *pclk = NULL;
+
+ if (!parent_rate)
+ return 0;
+
+ pclk = omap3_find_clkoutx2_dpll(hw);
+
+ if (!pclk)
+ return 0;
+
dd = pclk->dpll_data;
WARN_ON(!dd->enable_mask);
@@ -672,6 +685,55 @@
return rate;
}
+int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate,
+ unsigned long parent_rate)
+{
+ return 0;
+}
+
+long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate,
+ unsigned long *prate)
+{
+ const struct dpll_data *dd;
+ u32 v;
+ struct clk_hw_omap *pclk = NULL;
+
+ if (!*prate)
+ return 0;
+
+ pclk = omap3_find_clkoutx2_dpll(hw);
+
+ if (!pclk)
+ return 0;
+
+ dd = pclk->dpll_data;
+
+ /* TYPE J does not have a clkoutx2 */
+ if (dd->flags & DPLL_J_TYPE) {
+ *prate = __clk_round_rate(__clk_get_parent(pclk->hw.clk), rate);
+ return *prate;
+ }
+
+ WARN_ON(!dd->enable_mask);
+
+ v = omap2_clk_readl(pclk, dd->control_reg) & dd->enable_mask;
+ v >>= __ffs(dd->enable_mask);
+
+ /* If in bypass, the rate is fixed to the bypass rate*/
+ if (v != OMAP3XXX_EN_DPLL_LOCKED)
+ return *prate;
+
+ if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) {
+ unsigned long best_parent;
+
+ best_parent = (rate / 2);
+ *prate = __clk_round_rate(__clk_get_parent(hw->clk),
+ best_parent);
+ }
+
+ return *prate * 2;
+}
+
/* OMAP3/4 non-CORE DPLL clkops */
const struct clk_hw_omap_ops clkhwops_omap3_dpll = {
.allow_idle = omap3_dpll_allow_idle,
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index d24926e..ab43755 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -1339,7 +1339,7 @@
of_property_read_bool(np, "gpmc,time-para-granularity");
}
-#ifdef CONFIG_MTD_NAND
+#if IS_ENABLED(CONFIG_MTD_NAND)
static const char * const nand_xfer_types[] = {
[NAND_OMAP_PREFETCH_POLLED] = "prefetch-polled",
@@ -1429,7 +1429,7 @@
}
#endif
-#ifdef CONFIG_MTD_ONENAND
+#if IS_ENABLED(CONFIG_MTD_ONENAND)
static int gpmc_probe_onenand_child(struct platform_device *pdev,
struct device_node *child)
{
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index d408b15..af432b1 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -179,15 +179,6 @@
.length = L4_EMU_34XX_SIZE,
.type = MT_DEVICE
},
-#if defined(CONFIG_DEBUG_LL) && \
- (defined(CONFIG_MACH_OMAP_ZOOM2) || defined(CONFIG_MACH_OMAP_ZOOM3))
- {
- .virtual = ZOOM_UART_VIRT,
- .pfn = __phys_to_pfn(ZOOM_UART_BASE),
- .length = SZ_1M,
- .type = MT_DEVICE
- },
-#endif
};
#endif
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 42d8188..1f33f5d 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1947,29 +1947,31 @@
goto dis_opt_clks;
_write_sysconfig(v, oh);
+
+ if (oh->class->sysc->srst_udelay)
+ udelay(oh->class->sysc->srst_udelay);
+
+ c = _wait_softreset_complete(oh);
+ if (c == MAX_MODULE_SOFTRESET_WAIT) {
+ pr_warning("omap_hwmod: %s: softreset failed (waited %d usec)\n",
+ oh->name, MAX_MODULE_SOFTRESET_WAIT);
+ ret = -ETIMEDOUT;
+ goto dis_opt_clks;
+ } else {
+ pr_debug("omap_hwmod: %s: softreset in %d usec\n", oh->name, c);
+ }
+
ret = _clear_softreset(oh, &v);
if (ret)
goto dis_opt_clks;
_write_sysconfig(v, oh);
- if (oh->class->sysc->srst_udelay)
- udelay(oh->class->sysc->srst_udelay);
-
- c = _wait_softreset_complete(oh);
- if (c == MAX_MODULE_SOFTRESET_WAIT)
- pr_warning("omap_hwmod: %s: softreset failed (waited %d usec)\n",
- oh->name, MAX_MODULE_SOFTRESET_WAIT);
- else
- pr_debug("omap_hwmod: %s: softreset in %d usec\n", oh->name, c);
-
/*
* XXX add _HWMOD_STATE_WEDGED for modules that don't come back from
* _wait_target_ready() or _reset()
*/
- ret = (c == MAX_MODULE_SOFTRESET_WAIT) ? -ETIMEDOUT : 0;
-
dis_opt_clks:
if (oh->flags & HWMOD_CONTROL_OPT_CLKS_IN_RESET)
_disable_optional_clocks(oh);
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 18f333c..810c205 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1365,11 +1365,10 @@
.rev_offs = 0x0000,
.sysc_offs = 0x0010,
.syss_offs = 0x0014,
- .sysc_flags = (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
- SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE |
- SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
- .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
- SIDLE_SMART_WKUP),
+ .sysc_flags = (SYSC_HAS_AUTOIDLE | SYSC_HAS_ENAWAKEUP |
+ SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET |
+ SYSS_HAS_RESET_STATUS),
+ .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
.sysc_fields = &omap_hwmod_sysc_type1,
};
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 3d5b24d..c33e07e 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -22,6 +22,8 @@
#include "common-board-devices.h"
#include "dss-common.h"
#include "control.h"
+#include "omap-secure.h"
+#include "soc.h"
struct pdata_init {
const char *compatible;
@@ -169,6 +171,22 @@
omap_ctrl_writel(v, AM35XX_CONTROL_IP_SW_RESET);
omap_ctrl_readl(AM35XX_CONTROL_IP_SW_RESET); /* OCP barrier */
}
+
+static void __init nokia_n900_legacy_init(void)
+{
+ hsmmc2_internal_input_clk();
+
+ if (omap_type() == OMAP2_DEVICE_TYPE_SEC) {
+ if (IS_ENABLED(CONFIG_ARM_ERRATA_430973)) {
+ pr_info("RX-51: Enabling ARM errata 430973 workaround\n");
+ /* set IBE to 1 */
+ rx51_secure_update_aux_cr(BIT(6), 0);
+ } else {
+ pr_warning("RX-51: Not enabling ARM errata 430973 workaround\n");
+ pr_warning("Thumb binaries may crash randomly without this workaround\n");
+ }
+ }
+}
#endif /* CONFIG_ARCH_OMAP3 */
#ifdef CONFIG_ARCH_OMAP4
@@ -239,6 +257,7 @@
#endif
#ifdef CONFIG_ARCH_OMAP3
OF_DEV_AUXDATA("ti,omap3-padconf", 0x48002030, "48002030.pinmux", &pcs_pdata),
+ OF_DEV_AUXDATA("ti,omap3-padconf", 0x480025a0, "480025a0.pinmux", &pcs_pdata),
OF_DEV_AUXDATA("ti,omap3-padconf", 0x48002a00, "48002a00.pinmux", &pcs_pdata),
/* Only on am3517 */
OF_DEV_AUXDATA("ti,davinci_mdio", 0x5c030000, "davinci_mdio.0", NULL),
@@ -259,7 +278,7 @@
static struct pdata_init pdata_quirks[] __initdata = {
#ifdef CONFIG_ARCH_OMAP3
{ "compulab,omap3-sbc-t3730", omap3_sbc_t3730_legacy_init, },
- { "nokia,omap3-n900", hsmmc2_internal_input_clk, },
+ { "nokia,omap3-n900", nokia_n900_legacy_init, },
{ "nokia,omap3-n9", hsmmc2_internal_input_clk, },
{ "nokia,omap3-n950", hsmmc2_internal_input_clk, },
{ "isee,omap3-igep0020", omap3_igep0020_legacy_init, },
diff --git a/arch/arm/mach-omap2/prminst44xx.c b/arch/arm/mach-omap2/prminst44xx.c
index 6334b96..280f3c5 100644
--- a/arch/arm/mach-omap2/prminst44xx.c
+++ b/arch/arm/mach-omap2/prminst44xx.c
@@ -183,11 +183,11 @@
OMAP4_PRM_RSTCTRL_OFFSET);
v |= OMAP4430_RST_GLOBAL_WARM_SW_MASK;
omap4_prminst_write_inst_reg(v, OMAP4430_PRM_PARTITION,
- OMAP4430_PRM_DEVICE_INST,
+ dev_inst,
OMAP4_PRM_RSTCTRL_OFFSET);
/* OCP barrier */
v = omap4_prminst_read_inst_reg(OMAP4430_PRM_PARTITION,
- OMAP4430_PRM_DEVICE_INST,
+ dev_inst,
OMAP4_PRM_RSTCTRL_OFFSET);
}
diff --git a/arch/arm/mach-pxa/am300epd.c b/arch/arm/mach-pxa/am300epd.c
index c9f309a..8b90c4f 100644
--- a/arch/arm/mach-pxa/am300epd.c
+++ b/arch/arm/mach-pxa/am300epd.c
@@ -30,6 +30,7 @@
#include <mach/gumstix.h>
#include <mach/mfp-pxa25x.h>
+#include <mach/irqs.h>
#include <linux/platform_data/video-pxafb.h>
#include "generic.h"
diff --git a/arch/arm/mach-pxa/include/mach/balloon3.h b/arch/arm/mach-pxa/include/mach/balloon3.h
index 954641e..1b08259 100644
--- a/arch/arm/mach-pxa/include/mach/balloon3.h
+++ b/arch/arm/mach-pxa/include/mach/balloon3.h
@@ -14,6 +14,8 @@
#ifndef ASM_ARCH_BALLOON3_H
#define ASM_ARCH_BALLOON3_H
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
+
enum balloon3_features {
BALLOON3_FEATURE_OHCI,
BALLOON3_FEATURE_MMC,
diff --git a/arch/arm/mach-pxa/include/mach/corgi.h b/arch/arm/mach-pxa/include/mach/corgi.h
index f3c3493..c030d95 100644
--- a/arch/arm/mach-pxa/include/mach/corgi.h
+++ b/arch/arm/mach-pxa/include/mach/corgi.h
@@ -13,6 +13,7 @@
#ifndef __ASM_ARCH_CORGI_H
#define __ASM_ARCH_CORGI_H 1
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
/*
* Corgi (Non Standard) GPIO Definitions
diff --git a/arch/arm/mach-pxa/include/mach/csb726.h b/arch/arm/mach-pxa/include/mach/csb726.h
index 2628e7b..00cfbbb 100644
--- a/arch/arm/mach-pxa/include/mach/csb726.h
+++ b/arch/arm/mach-pxa/include/mach/csb726.h
@@ -11,6 +11,8 @@
#ifndef CSB726_H
#define CSB726_H
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
#define CSB726_GPIO_IRQ_LAN 52
#define CSB726_GPIO_IRQ_SM501 53
#define CSB726_GPIO_MMC_DETECT 100
diff --git a/arch/arm/mach-pxa/include/mach/gumstix.h b/arch/arm/mach-pxa/include/mach/gumstix.h
index dba14b6..f7df27b 100644
--- a/arch/arm/mach-pxa/include/mach/gumstix.h
+++ b/arch/arm/mach-pxa/include/mach/gumstix.h
@@ -6,6 +6,7 @@
* published by the Free Software Foundation.
*/
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
/* BTRESET - Reset line to Bluetooth module, active low signal. */
#define GPIO_GUMSTIX_BTRESET 7
diff --git a/arch/arm/mach-pxa/include/mach/idp.h b/arch/arm/mach-pxa/include/mach/idp.h
index 22a96f8..7e63f46 100644
--- a/arch/arm/mach-pxa/include/mach/idp.h
+++ b/arch/arm/mach-pxa/include/mach/idp.h
@@ -23,6 +23,7 @@
* IDP hardware.
*/
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
#define IDP_FLASH_PHYS (PXA_CS0_PHYS)
#define IDP_ALT_FLASH_PHYS (PXA_CS1_PHYS)
diff --git a/arch/arm/mach-pxa/include/mach/palmld.h b/arch/arm/mach-pxa/include/mach/palmld.h
index 2c447133..b184f29 100644
--- a/arch/arm/mach-pxa/include/mach/palmld.h
+++ b/arch/arm/mach-pxa/include/mach/palmld.h
@@ -13,6 +13,8 @@
#ifndef _INCLUDE_PALMLD_H_
#define _INCLUDE_PALMLD_H_
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
/** HERE ARE GPIOs **/
/* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/palmt5.h b/arch/arm/mach-pxa/include/mach/palmt5.h
index 0bd4f03..e342c59 100644
--- a/arch/arm/mach-pxa/include/mach/palmt5.h
+++ b/arch/arm/mach-pxa/include/mach/palmt5.h
@@ -15,6 +15,8 @@
#ifndef _INCLUDE_PALMT5_H_
#define _INCLUDE_PALMT5_H_
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
/** HERE ARE GPIOs **/
/* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/palmtc.h b/arch/arm/mach-pxa/include/mach/palmtc.h
index c383a21..81c727b 100644
--- a/arch/arm/mach-pxa/include/mach/palmtc.h
+++ b/arch/arm/mach-pxa/include/mach/palmtc.h
@@ -16,6 +16,8 @@
#ifndef _INCLUDE_PALMTC_H_
#define _INCLUDE_PALMTC_H_
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
/** HERE ARE GPIOs **/
/* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/palmtx.h b/arch/arm/mach-pxa/include/mach/palmtx.h
index f2e5303..92bc1f0 100644
--- a/arch/arm/mach-pxa/include/mach/palmtx.h
+++ b/arch/arm/mach-pxa/include/mach/palmtx.h
@@ -16,6 +16,8 @@
#ifndef _INCLUDE_PALMTX_H_
#define _INCLUDE_PALMTX_H_
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
/** HERE ARE GPIOs **/
/* GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/pcm027.h b/arch/arm/mach-pxa/include/mach/pcm027.h
index 6bf28de..86ebd7b 100644
--- a/arch/arm/mach-pxa/include/mach/pcm027.h
+++ b/arch/arm/mach-pxa/include/mach/pcm027.h
@@ -23,6 +23,8 @@
* Definitions of CPU card resources only
*/
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
/* phyCORE-PXA270 (PCM027) Interrupts */
#define PCM027_IRQ(x) (IRQ_BOARD_START + (x))
#define PCM027_BTDET_IRQ PCM027_IRQ(0)
diff --git a/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h b/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h
index 0260aaa..7e544c1 100644
--- a/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h
+++ b/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h
@@ -20,6 +20,7 @@
*/
#include <mach/pcm027.h>
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
/*
* definitions relevant only when the PCM-990
diff --git a/arch/arm/mach-pxa/include/mach/poodle.h b/arch/arm/mach-pxa/include/mach/poodle.h
index f32ff75..b56b193 100644
--- a/arch/arm/mach-pxa/include/mach/poodle.h
+++ b/arch/arm/mach-pxa/include/mach/poodle.h
@@ -15,6 +15,8 @@
#ifndef __ASM_ARCH_POODLE_H
#define __ASM_ARCH_POODLE_H 1
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
/*
* GPIOs
*/
diff --git a/arch/arm/mach-pxa/include/mach/spitz.h b/arch/arm/mach-pxa/include/mach/spitz.h
index 0bfe650..25c9f62 100644
--- a/arch/arm/mach-pxa/include/mach/spitz.h
+++ b/arch/arm/mach-pxa/include/mach/spitz.h
@@ -15,8 +15,8 @@
#define __ASM_ARCH_SPITZ_H 1
#endif
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO, PXA_GPIO_TO_IRQ */
#include <linux/fb.h>
-#include <linux/gpio.h>
/* Spitz/Akita GPIOs */
diff --git a/arch/arm/mach-pxa/include/mach/tosa.h b/arch/arm/mach-pxa/include/mach/tosa.h
index 2bb0e86..0497d95 100644
--- a/arch/arm/mach-pxa/include/mach/tosa.h
+++ b/arch/arm/mach-pxa/include/mach/tosa.h
@@ -13,6 +13,8 @@
#ifndef _ASM_ARCH_TOSA_H_
#define _ASM_ARCH_TOSA_H_ 1
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
+
/* TOSA Chip selects */
#define TOSA_LCDC_PHYS PXA_CS4_PHYS
/* Internel Scoop */
diff --git a/arch/arm/mach-pxa/include/mach/trizeps4.h b/arch/arm/mach-pxa/include/mach/trizeps4.h
index d2ca010..ae3ca01 100644
--- a/arch/arm/mach-pxa/include/mach/trizeps4.h
+++ b/arch/arm/mach-pxa/include/mach/trizeps4.h
@@ -10,6 +10,8 @@
#ifndef _TRIPEPS4_H_
#define _TRIPEPS4_H_
+#include "irqs.h" /* PXA_GPIO_TO_IRQ */
+
/* physical memory regions */
#define TRIZEPS4_FLASH_PHYS (PXA_CS0_PHYS) /* Flash region */
#define TRIZEPS4_DISK_PHYS (PXA_CS1_PHYS) /* Disk On Chip region */
diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
index f70583f..29997bd 100644
--- a/arch/arm/mach-pxa/mioa701.c
+++ b/arch/arm/mach-pxa/mioa701.c
@@ -38,6 +38,7 @@
#include <linux/mtd/physmap.h>
#include <linux/usb/gpio_vbus.h>
#include <linux/reboot.h>
+#include <linux/regulator/fixed.h>
#include <linux/regulator/max1586.h>
#include <linux/slab.h>
#include <linux/i2c/pxa-i2c.h>
@@ -714,6 +715,10 @@
{ GPIO56_MT9M111_nOE, GPIOF_OUT_INIT_LOW, "Camera nOE" },
};
+static struct regulator_consumer_supply fixed_5v0_consumers[] = {
+ REGULATOR_SUPPLY("power", "pwm-backlight"),
+};
+
static void __init mioa701_machine_init(void)
{
int rc;
@@ -753,6 +758,10 @@
pxa_set_i2c_info(&i2c_pdata);
pxa27x_set_i2c_power_info(NULL);
pxa_set_camera_info(&mioa701_pxacamera_platform_data);
+
+ regulator_register_always_on(0, "fixed-5.0V", fixed_5v0_consumers,
+ ARRAY_SIZE(fixed_5v0_consumers),
+ 5000000);
}
static void mioa701_machine_exit(void)
diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h
index f33679d..50e1d85 100644
--- a/arch/arm/mach-sa1100/include/mach/collie.h
+++ b/arch/arm/mach-sa1100/include/mach/collie.h
@@ -13,6 +13,8 @@
#ifndef __ASM_ARCH_COLLIE_H
#define __ASM_ARCH_COLLIE_H
+#include "hardware.h" /* Gives GPIO_MAX */
+
extern void locomolcd_power(int on);
#define COLLIE_SCOOP_GPIO_BASE (GPIO_MAX + 1)
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 3386406..05fa505 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -8,7 +8,7 @@
select CPU_V7
select GENERIC_CLOCKEVENTS
select HAVE_ARM_SCU if SMP
- select HAVE_ARM_TWD if LOCAL_TIMERS
+ select HAVE_ARM_TWD if SMP
select HAVE_SMP
select ARM_GIC
select MIGHT_HAVE_CACHE_L2X0
diff --git a/arch/arm/mach-tegra/pm.c b/arch/arm/mach-tegra/pm.c
index 4ae0286..f55b05a 100644
--- a/arch/arm/mach-tegra/pm.c
+++ b/arch/arm/mach-tegra/pm.c
@@ -24,6 +24,7 @@
#include <linux/cpu_pm.h>
#include <linux/suspend.h>
#include <linux/err.h>
+#include <linux/slab.h>
#include <linux/clk/tegra.h>
#include <asm/smp_plat.h>
diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c
index 303a285..6191603 100644
--- a/arch/arm/mach-tegra/tegra.c
+++ b/arch/arm/mach-tegra/tegra.c
@@ -73,10 +73,20 @@
static void __init tegra_init_cache(void)
{
#ifdef CONFIG_CACHE_L2X0
+ static const struct of_device_id pl310_ids[] __initconst = {
+ { .compatible = "arm,pl310-cache", },
+ {}
+ };
+
+ struct device_node *np;
int ret;
void __iomem *p = IO_ADDRESS(TEGRA_ARM_PERIF_BASE) + 0x3000;
u32 aux_ctrl, cache_type;
+ np = of_find_matching_node(NULL, pl310_ids);
+ if (!np)
+ return;
+
cache_type = readl(p + L2X0_CACHE_TYPE);
aux_ctrl = (cache_type & 0x700) << (17-8);
aux_ctrl |= 0x7C400001;
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index 1db2a5ca..8c09a83 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -25,6 +25,7 @@
#include <linux/of_irq.h>
#include <linux/of_platform.h>
#include <linux/of.h>
+#include <linux/memblock.h>
#include <linux/irqchip.h>
#include <linux/irqchip/arm-gic.h>
@@ -41,6 +42,18 @@
void __iomem *zynq_scu_base;
+/**
+ * zynq_memory_init - Initialize special memory
+ *
+ * We need to stop things allocating the low memory as DMA can't work in
+ * the 1st 512K of memory.
+ */
+static void __init zynq_memory_init(void)
+{
+ if (!__pa(PAGE_OFFSET))
+ memblock_reserve(__pa(PAGE_OFFSET), __pa(swapper_pg_dir));
+}
+
static struct platform_device zynq_cpuidle_device = {
.name = "cpuidle-zynq",
};
@@ -117,5 +130,6 @@
.init_machine = zynq_init_machine,
.init_time = zynq_timer_init,
.dt_compat = zynq_dt_match,
+ .reserve = zynq_memory_init,
.restart = zynq_system_reset,
MACHINE_END
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 1a77450..11b3914 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1358,7 +1358,7 @@
*handle = DMA_ERROR_CODE;
size = PAGE_ALIGN(size);
- if (gfp & GFP_ATOMIC)
+ if (!(gfp & __GFP_WAIT))
return __iommu_alloc_atomic(dev, size, handle);
/*
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 2b3a564..ef69152 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -264,6 +264,9 @@
note_page(st, addr, 3, pmd_val(*pmd));
else
walk_pte(st, pmd, addr);
+
+ if (SECTION_SIZE < PMD_SIZE && pmd_large(pmd[1]))
+ note_page(st, addr + SECTION_SIZE, 3, pmd_val(pmd[1]));
}
}
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index d5a982d..7ea641b 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -38,6 +38,7 @@
struct mem_type {
pteval_t prot_pte;
+ pteval_t prot_pte_s2;
pmdval_t prot_l1;
pmdval_t prot_sect;
unsigned int domain;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4f08c13..a623cb3 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -232,12 +232,16 @@
#endif /* ifdef CONFIG_CPU_CP15 / else */
#define PROT_PTE_DEVICE L_PTE_PRESENT|L_PTE_YOUNG|L_PTE_DIRTY|L_PTE_XN
+#define PROT_PTE_S2_DEVICE PROT_PTE_DEVICE
#define PROT_SECT_DEVICE PMD_TYPE_SECT|PMD_SECT_AP_WRITE
static struct mem_type mem_types[] = {
[MT_DEVICE] = { /* Strongly ordered / ARMv6 shared device */
.prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED |
L_PTE_SHARED,
+ .prot_pte_s2 = s2_policy(PROT_PTE_S2_DEVICE) |
+ s2_policy(L_PTE_S2_MT_DEV_SHARED) |
+ L_PTE_SHARED,
.prot_l1 = PMD_TYPE_TABLE,
.prot_sect = PROT_SECT_DEVICE | PMD_SECT_S,
.domain = DOMAIN_IO,
@@ -508,7 +512,8 @@
cp = &cache_policies[cachepolicy];
vecs_pgprot = kern_pgprot = user_pgprot = cp->pte;
s2_pgprot = cp->pte_s2;
- hyp_device_pgprot = s2_device_pgprot = mem_types[MT_DEVICE].prot_pte;
+ hyp_device_pgprot = mem_types[MT_DEVICE].prot_pte;
+ s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2;
/*
* ARMv6 and above have extended page tables.
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 45dc29f..32b3558 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -208,7 +208,6 @@
mcr p15, 0, r0, c7, c14, 0 @ clean+invalidate D cache
mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache
mcr p15, 0, r0, c7, c15, 0 @ clean+invalidate cache
- mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
#ifdef CONFIG_MMU
mcr p15, 0, r0, c8, c7, 0 @ invalidate I + D TLBs
mcr p15, 0, r0, c2, c0, 2 @ TTB control register
@@ -218,6 +217,8 @@
ALT_UP(orr r8, r8, #TTB_FLAGS_UP)
mcr p15, 0, r8, c2, c0, 1 @ load TTB1
#endif /* CONFIG_MMU */
+ mcr p15, 0, r0, c7, c10, 4 @ drain write buffer and
+ @ complete invalidations
adr r5, v6_crval
ldmia r5, {r5, r6}
ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index bd17819..74f6033 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -351,7 +351,6 @@
4: mov r10, #0
mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate
- dsb
#ifdef CONFIG_MMU
mcr p15, 0, r10, c8, c7, 0 @ invalidate I + D TLBs
v7_ttb_setup r10, r4, r8, r5 @ TTBCR, TTBRx setup
@@ -360,6 +359,7 @@
mcr p15, 0, r5, c10, c2, 0 @ write PRRR
mcr p15, 0, r6, c10, c2, 1 @ write NMRR
#endif
+ dsb @ Complete invalidations
#ifndef CONFIG_ARM_THUMBEE
mrc p15, 0, r0, c0, c1, 0 @ read ID_PFR0 for ThumbEE
and r0, r0, #(0xf << 12) @ ThumbEE enabled field
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 271b5e9..6f879c3 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -825,8 +825,8 @@
break;
case BPF_S_ANC_RXHASH:
ctx->seen |= SEEN_SKB;
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
- off = offsetof(struct sk_buff, rxhash);
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+ off = offsetof(struct sk_buff, hash);
emit(ARM_LDR_I(r_A, r_skb, off), ctx);
break;
case BPF_S_ANC_VLAN_TAG:
@@ -925,6 +925,7 @@
bpf_jit_dump(fp->len, alloc_size, 2, ctx.target);
fp->bpf_func = (void *)ctx.target;
+ fp->jited = 1;
out:
kfree(ctx.offsets);
return;
@@ -932,7 +933,7 @@
void bpf_jit_free(struct sk_filter *fp)
{
- if (fp->bpf_func != sk_run_filter)
+ if (fp->jited)
module_free(NULL, fp->bpf_func);
kfree(fp);
}
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 13fb0b3..453a179 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -16,6 +16,8 @@
#ifndef __ASM_PERCPU_H
#define __ASM_PERCPU_H
+#ifdef CONFIG_SMP
+
static inline void set_my_cpu_offset(unsigned long off)
{
asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory");
@@ -36,6 +38,12 @@
}
#define __my_cpu_offset __my_cpu_offset()
+#else /* !CONFIG_SMP */
+
+#define set_my_cpu_offset(x) do { } while (0)
+
+#endif /* CONFIG_SMP */
+
#include <asm-generic/percpu.h>
#endif /* __ASM_PERCPU_H */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b524dcd..aa3917c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -136,11 +136,11 @@
/*
* The following only work if pte_present(). Undefined behaviour otherwise.
*/
-#define pte_present(pte) (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))
-#define pte_dirty(pte) (pte_val(pte) & PTE_DIRTY)
-#define pte_young(pte) (pte_val(pte) & PTE_AF)
-#define pte_special(pte) (pte_val(pte) & PTE_SPECIAL)
-#define pte_write(pte) (pte_val(pte) & PTE_WRITE)
+#define pte_present(pte) (!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)))
+#define pte_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY))
+#define pte_young(pte) (!!(pte_val(pte) & PTE_AF))
+#define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL))
+#define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE))
#define pte_exec(pte) (!(pte_val(pte) & PTE_UXN))
#define pte_valid_user(pte) \
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 495ab6f..eaf54a3 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -148,6 +148,15 @@
#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2)
#define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2)
+/* Device Control API: ARM VGIC */
+#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
+#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
+#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2
+#define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32
+#define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0
+#define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+
/* KVM_IRQ_LINE irq field index values */
#define KVM_ARM_IRQ_TYPE_SHIFT 24
#define KVM_ARM_IRQ_TYPE_MASK 0xff
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index c3b6c63..38f0558 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -48,7 +48,11 @@
frame->sp = fp + 0x10;
frame->fp = *(unsigned long *)(fp);
- frame->pc = *(unsigned long *)(fp + 8);
+ /*
+ * -4 here because we care about the PC at time of bl,
+ * not where the return will go.
+ */
+ frame->pc = *(unsigned long *)(fp + 8) - 4;
return 0;
}
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 3b47c36..2c56012 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -694,6 +694,24 @@
.align 2
+/*
+ * u64 kvm_call_hyp(void *hypfn, ...);
+ *
+ * This is not really a variadic function in the classic C-way and care must
+ * be taken when calling this to ensure parameters are passed in registers
+ * only, since the stack will change between the caller and the callee.
+ *
+ * Call the function with the first argument containing a pointer to the
+ * function you wish to call in Hyp mode, and subsequent arguments will be
+ * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the
+ * function pointer can be passed). The function being called must be mapped
+ * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are
+ * passed in r0 and r1.
+ *
+ * A function pointer with a value of 0 has a special meaning, and is
+ * used to implement __hyp_get_vectors in the same way as in
+ * arch/arm64/kernel/hyp_stub.S.
+ */
ENTRY(kvm_call_hyp)
hvc #0
ret
@@ -737,7 +755,12 @@
pop x2, x3
pop x0, x1
- push lr, xzr
+ /* Check for __hyp_get_vectors */
+ cbnz x0, 1f
+ mrs x0, vbar_el2
+ b 2f
+
+1: push lr, xzr
/*
* Compute the function address in EL2, and shuffle the parameters.
@@ -750,7 +773,7 @@
blr lr
pop lr, xzr
- eret
+2: eret
el1_trap:
/*
diff --git a/arch/avr32/Makefile b/arch/avr32/Makefile
index 22fb665..dba48a5d 100644
--- a/arch/avr32/Makefile
+++ b/arch/avr32/Makefile
@@ -11,7 +11,7 @@
KBUILD_DEFCONFIG := atstk1002_defconfig
-KBUILD_CFLAGS += -pipe -fno-builtin -mno-pic
+KBUILD_CFLAGS += -pipe -fno-builtin -mno-pic -D__linux__
KBUILD_AFLAGS += -mrelax -mno-pic
KBUILD_CFLAGS_MODULE += -mno-relax
LDFLAGS_vmlinux += --relax
diff --git a/arch/avr32/boards/mimc200/fram.c b/arch/avr32/boards/mimc200/fram.c
index 9764a1a..c1466a8 100644
--- a/arch/avr32/boards/mimc200/fram.c
+++ b/arch/avr32/boards/mimc200/fram.c
@@ -11,6 +11,7 @@
#define FRAM_VERSION "1.0"
#include <linux/miscdevice.h>
+#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/mm.h>
#include <linux/io.h>
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index cfb9fe1..c7c64a6 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -17,5 +17,6 @@
generic-y += sections.h
generic-y += topology.h
generic-y += trace_clock.h
+generic-y += vga.h
generic-y += xor.h
generic-y += hash.h
diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h
index fc6483f..4f5ec2b 100644
--- a/arch/avr32/include/asm/io.h
+++ b/arch/avr32/include/asm/io.h
@@ -295,6 +295,8 @@
#define iounmap(addr) \
__iounmap(addr)
+#define ioremap_wc ioremap_nocache
+
#define cached(addr) P1SEGADDR(addr)
#define uncached(addr) P2SEGADDR(addr)
diff --git a/arch/c6x/include/asm/cache.h b/arch/c6x/include/asm/cache.h
index 09c5a0f..86648c0 100644
--- a/arch/c6x/include/asm/cache.h
+++ b/arch/c6x/include/asm/cache.h
@@ -12,6 +12,7 @@
#define _ASM_C6X_CACHE_H
#include <linux/irqflags.h>
+#include <linux/init.h>
/*
* Cache line size
diff --git a/arch/cris/include/asm/bitops.h b/arch/cris/include/asm/bitops.h
index 184066c..053c17b 100644
--- a/arch/cris/include/asm/bitops.h
+++ b/arch/cris/include/asm/bitops.h
@@ -144,7 +144,7 @@
* definition, which doesn't have the same semantics. We don't want to
* use -fno-builtin, so just hide the name ffs.
*/
-#define ffs kernel_ffs
+#define ffs(x) kernel_ffs(x)
#include <asm-generic/bitops/fls.h>
#include <asm-generic/bitops/__fls.h>
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index a96bcf8..20e8a9b 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -98,7 +98,7 @@
/* attempt to allocate a granule's worth of cached memory pages */
page = alloc_pages_exact_node(nid,
- GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
IA64_GRANULE_SHIFT-PAGE_SHIFT);
if (!page) {
mutex_unlock(&uc_pool->add_chunk_mutex);
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 7cc8c36..6fb9e81 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,4 +1,4 @@
-
+generic-y += barrier.h
generic-y += bitsperlong.h
generic-y += clkdev.h
generic-y += cputime.h
@@ -6,6 +6,7 @@
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += hash.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ipcbuf.h
@@ -18,6 +19,7 @@
generic-y += mman.h
generic-y += mutex.h
generic-y += percpu.h
+generic-y += preempt.h
generic-y += resource.h
generic-y += scatterlist.h
generic-y += sections.h
@@ -31,5 +33,3 @@
generic-y += types.h
generic-y += word-at-a-time.h
generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/m68k/include/asm/barrier.h b/arch/m68k/include/asm/barrier.h
deleted file mode 100644
index 15c5f77..0000000
--- a/arch/m68k/include/asm/barrier.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _M68K_BARRIER_H
-#define _M68K_BARRIER_H
-
-#define nop() do { asm volatile ("nop"); barrier(); } while (0)
-
-#include <asm-generic/barrier.h>
-
-#endif /* _M68K_BARRIER_H */
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 014f288..9d38b73 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
#include <uapi/asm/unistd.h>
-#define NR_syscalls 349
+#define NR_syscalls 351
#define __ARCH_WANT_OLD_READDIR
#define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 625f321..b932dd4 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -354,5 +354,7 @@
#define __NR_process_vm_writev 346
#define __NR_kcmp 347
#define __NR_finit_module 348
+#define __NR_sched_setattr 349
+#define __NR_sched_getattr 350
#endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 3f04ea0..b6223dc4 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -369,4 +369,6 @@
.long sys_process_vm_writev
.long sys_kcmp
.long sys_finit_module
+ .long sys_sched_setattr
+ .long sys_sched_getattr /* 350 */
diff --git a/arch/microblaze/include/asm/delay.h b/arch/microblaze/include/asm/delay.h
index 05b7d39..66fc24c 100644
--- a/arch/microblaze/include/asm/delay.h
+++ b/arch/microblaze/include/asm/delay.h
@@ -13,6 +13,8 @@
#ifndef _ASM_MICROBLAZE_DELAY_H
#define _ASM_MICROBLAZE_DELAY_H
+#include <linux/param.h>
+
extern inline void __delay(unsigned long loops)
{
asm volatile ("# __delay \n\t" \
diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h
index a2cea72..3fbb7f1 100644
--- a/arch/microblaze/include/asm/io.h
+++ b/arch/microblaze/include/asm/io.h
@@ -89,6 +89,11 @@
{
return le32_to_cpu(*(volatile unsigned int __force *)addr);
}
+#define readq readq
+static inline u64 readq(const volatile void __iomem *addr)
+{
+ return le64_to_cpu(__raw_readq(addr));
+}
static inline void writeb(unsigned char v, volatile void __iomem *addr)
{
*(volatile unsigned char __force *)addr = v;
@@ -101,6 +106,7 @@
{
*(volatile unsigned int __force *)addr = cpu_to_le32(v);
}
+#define writeq(b, addr) __raw_writeq(cpu_to_le64(b), addr)
/* ioread and iowrite variants. thease are for now same as __raw_
* variants of accessors. we might check for endianess in the feature
diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S
index b7fb043..17645b2 100644
--- a/arch/microblaze/kernel/head.S
+++ b/arch/microblaze/kernel/head.S
@@ -66,7 +66,7 @@
mts rmsr, r0
/* Disable stack protection from bootloader */
mts rslr, r0
- addi r8, r0, 0xFFFFFFF
+ addi r8, r0, 0xFFFFFFFF
mts rshr, r8
/*
* According to Xilinx, msrclr instruction behaves like 'mfs rX,rpc'
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index dcae3a7..95fa1f1 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1776,12 +1776,12 @@
config FORCE_MAX_ZONEORDER
int "Maximum zone order"
- range 14 64 if HUGETLB_PAGE && PAGE_SIZE_64KB
- default "14" if HUGETLB_PAGE && PAGE_SIZE_64KB
- range 13 64 if HUGETLB_PAGE && PAGE_SIZE_32KB
- default "13" if HUGETLB_PAGE && PAGE_SIZE_32KB
- range 12 64 if HUGETLB_PAGE && PAGE_SIZE_16KB
- default "12" if HUGETLB_PAGE && PAGE_SIZE_16KB
+ range 14 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
+ default "14" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
+ range 13 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB
+ default "13" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB
+ range 12 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB
+ default "12" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB
range 11 64
default "11"
help
@@ -2353,9 +2353,8 @@
If unsure, say Y. Only embedded should say N here.
config MIPS_O32_FP64_SUPPORT
- bool "Support for O32 binaries using 64-bit FP"
+ bool "Support for O32 binaries using 64-bit FP (EXPERIMENTAL)"
depends on 32BIT || MIPS32_O32
- default y
help
When this is enabled, the kernel will support use of 64-bit floating
point registers with binaries using the O32 ABI along with the
@@ -2367,7 +2366,14 @@
of your kernel & potentially improve FP emulation performance by
saying N here.
- If unsure, say Y.
+ Although binutils currently supports use of this flag the details
+ concerning its effect upon the O32 ABI in userland are still being
+ worked on. In order to avoid userland becoming dependant upon current
+ behaviour before the details have been finalised, this option should
+ be considered experimental and only enabled by those working upon
+ said details.
+
+ If unsure, say N.
config USE_OF
bool
diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c
index 9edc35f..acf9a2a 100644
--- a/arch/mips/alchemy/board-gpr.c
+++ b/arch/mips/alchemy/board-gpr.c
@@ -53,10 +53,8 @@
prom_init_cmdline();
memsize_str = prom_getenv("memsize");
- if (!memsize_str)
+ if (!memsize_str || kstrtoul(memsize_str, 0, &memsize))
memsize = 0x04000000;
- else
- strict_strtoul(memsize_str, 0, &memsize);
add_memory_region(0, memsize, BOOT_MEM_RAM);
}
diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c
index 9969dba..25a59a2 100644
--- a/arch/mips/alchemy/board-mtx1.c
+++ b/arch/mips/alchemy/board-mtx1.c
@@ -52,10 +52,8 @@
prom_init_cmdline();
memsize_str = prom_getenv("memsize");
- if (!memsize_str)
+ if (!memsize_str || kstrtoul(memsize_str, 0, &memsize))
memsize = 0x04000000;
- else
- strict_strtoul(memsize_str, 0, &memsize);
add_memory_region(0, memsize, BOOT_MEM_RAM);
}
diff --git a/arch/mips/bcm47xx/board.c b/arch/mips/bcm47xx/board.c
index 6d612e2..cdd8246 100644
--- a/arch/mips/bcm47xx/board.c
+++ b/arch/mips/bcm47xx/board.c
@@ -1,3 +1,4 @@
+#include <linux/errno.h>
#include <linux/export.h>
#include <linux/string.h>
#include <bcm47xx_board.h>
diff --git a/arch/mips/bcm47xx/nvram.c b/arch/mips/bcm47xx/nvram.c
index 6decb27..2bed73a 100644
--- a/arch/mips/bcm47xx/nvram.c
+++ b/arch/mips/bcm47xx/nvram.c
@@ -196,7 +196,7 @@
char nvram_var[10];
char buf[30];
- for (i = 0; i < 16; i++) {
+ for (i = 0; i < 32; i++) {
err = snprintf(nvram_var, sizeof(nvram_var), "gpio%i", i);
if (err <= 0)
continue;
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 25fbfae..c2bb4f8 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -975,10 +975,6 @@
if (ciu > 1 || bit > 63)
return -EINVAL;
- /* These are the GPIO lines */
- if (ciu == 0 && bit >= 16 && bit < 32)
- return -EINVAL;
-
*out_hwirq = (ciu << 6) | bit;
*out_type = 0;
@@ -1007,6 +1003,10 @@
if (!octeon_irq_virq_in_range(virq))
return -EINVAL;
+ /* Don't map irq if it is reserved for GPIO. */
+ if (line == 0 && bit >= 16 && bit <32)
+ return 0;
+
if (line > 1 || octeon_irq_ciu_to_irq[line][bit] != 0)
return -EINVAL;
@@ -1525,10 +1525,6 @@
ciu = intspec[0];
bit = intspec[1];
- /* Line 7 are the GPIO lines */
- if (ciu > 6 || bit > 63)
- return -EINVAL;
-
*out_hwirq = (ciu << 6) | bit;
*out_type = 0;
@@ -1570,8 +1566,14 @@
if (!octeon_irq_virq_in_range(virq))
return -EINVAL;
- /* Line 7 are the GPIO lines */
- if (line > 6 || octeon_irq_ciu_to_irq[line][bit] != 0)
+ /*
+ * Don't map irq if it is reserved for GPIO.
+ * (Line 7 are the GPIO lines.)
+ */
+ if (line == 7)
+ return 0;
+
+ if (line > 7 || octeon_irq_ciu_to_irq[line][bit] != 0)
return -EINVAL;
if (octeon_irq_ciu2_is_edge(line, bit))
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 3220c93..4225e99 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -9,6 +9,7 @@
#define _ASM_ASMMACRO_H
#include <asm/hazards.h>
+#include <asm/asm-offsets.h>
#ifdef CONFIG_32BIT
#include <asm/asmmacro-32.h>
@@ -54,11 +55,21 @@
.endm
.macro local_irq_disable reg=t0
+#ifdef CONFIG_PREEMPT
+ lw \reg, TI_PRE_COUNT($28)
+ addi \reg, \reg, 1
+ sw \reg, TI_PRE_COUNT($28)
+#endif
mfc0 \reg, CP0_STATUS
ori \reg, \reg, 1
xori \reg, \reg, 1
mtc0 \reg, CP0_STATUS
irq_disable_hazard
+#ifdef CONFIG_PREEMPT
+ lw \reg, TI_PRE_COUNT($28)
+ addi \reg, \reg, -1
+ sw \reg, TI_PRE_COUNT($28)
+#endif
.endm
#endif /* CONFIG_MIPS_MT_SMTC */
@@ -106,7 +117,7 @@
.endm
.macro fpu_save_double thread status tmp
-#if defined(CONFIG_MIPS64) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
sll \tmp, \status, 5
bgez \tmp, 10f
fpu_save_16odd \thread
@@ -159,7 +170,7 @@
.endm
.macro fpu_restore_double thread status tmp
-#if defined(CONFIG_MIPS64) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
sll \tmp, \status, 5
bgez \tmp, 10f # 16 register mode?
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 6b97495..58e50cb 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -57,7 +57,7 @@
return 0;
case FPU_64BIT:
-#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_MIPS64))
+#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_64BIT))
/* we only have a 32-bit FPU */
return SIGFPE;
#endif
diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
index ce35c9a..992aaba 100644
--- a/arch/mips/include/asm/ftrace.h
+++ b/arch/mips/include/asm/ftrace.h
@@ -22,12 +22,12 @@
#define safe_load(load, src, dst, error) \
do { \
asm volatile ( \
- "1: " load " %[" STR(dst) "], 0(%[" STR(src) "])\n"\
- " li %[" STR(error) "], 0\n" \
+ "1: " load " %[tmp_dst], 0(%[tmp_src])\n" \
+ " li %[tmp_err], 0\n" \
"2:\n" \
\
".section .fixup, \"ax\"\n" \
- "3: li %[" STR(error) "], 1\n" \
+ "3: li %[tmp_err], 1\n" \
" j 2b\n" \
".previous\n" \
\
@@ -35,8 +35,8 @@
STR(PTR) "\t1b, 3b\n\t" \
".previous\n" \
\
- : [dst] "=&r" (dst), [error] "=r" (error)\
- : [src] "r" (src) \
+ : [tmp_dst] "=&r" (dst), [tmp_err] "=r" (error)\
+ : [tmp_src] "r" (src) \
: "memory" \
); \
} while (0)
@@ -44,12 +44,12 @@
#define safe_store(store, src, dst, error) \
do { \
asm volatile ( \
- "1: " store " %[" STR(src) "], 0(%[" STR(dst) "])\n"\
- " li %[" STR(error) "], 0\n" \
+ "1: " store " %[tmp_src], 0(%[tmp_dst])\n"\
+ " li %[tmp_err], 0\n" \
"2:\n" \
\
".section .fixup, \"ax\"\n" \
- "3: li %[" STR(error) "], 1\n" \
+ "3: li %[tmp_err], 1\n" \
" j 2b\n" \
".previous\n" \
\
@@ -57,8 +57,8 @@
STR(PTR) "\t1b, 3b\n\t" \
".previous\n" \
\
- : [error] "=r" (error) \
- : [dst] "r" (dst), [src] "r" (src)\
+ : [tmp_err] "=r" (error) \
+ : [tmp_dst] "r" (dst), [tmp_src] "r" (src)\
: "memory" \
); \
} while (0)
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 33e8dbf..f35b131 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -13,6 +13,7 @@
#ifndef __ASM_MIPS_SYSCALL_H
#define __ASM_MIPS_SYSCALL_H
+#include <linux/compiler.h>
#include <linux/audit.h>
#include <linux/elf-em.h>
#include <linux/kernel.h>
@@ -39,14 +40,14 @@
#ifdef CONFIG_32BIT
case 4: case 5: case 6: case 7:
- return get_user(*arg, (int *)usp + 4 * n);
+ return get_user(*arg, (int *)usp + n);
#endif
#ifdef CONFIG_64BIT
case 4: case 5: case 6: case 7:
#ifdef CONFIG_MIPS32_O32
if (test_thread_flag(TIF_32BIT_REGS))
- return get_user(*arg, (int *)usp + 4 * n);
+ return get_user(*arg, (int *)usp + n);
else
#endif
*arg = regs->regs[4 + n];
@@ -57,6 +58,8 @@
default:
BUG();
}
+
+ unreachable();
}
static inline long syscall_get_return_value(struct task_struct *task,
@@ -83,11 +86,10 @@
unsigned int i, unsigned int n,
unsigned long *args)
{
- unsigned long arg;
int ret;
while (n--)
- ret |= mips_get_syscall_arg(&arg, task, regs, i++);
+ ret |= mips_get_syscall_arg(args++, task, regs, i++);
/*
* No way to communicate an error because this is a void function.
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index b39ba25..f25181b 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -163,8 +163,8 @@
*/
enum cop1x_func {
lwxc1_op = 0x00, ldxc1_op = 0x01,
- pfetch_op = 0x07, swxc1_op = 0x08,
- sdxc1_op = 0x09, madd_s_op = 0x20,
+ swxc1_op = 0x08, sdxc1_op = 0x09,
+ pfetch_op = 0x0f, madd_s_op = 0x20,
madd_d_op = 0x21, madd_e_op = 0x22,
msub_s_op = 0x28, msub_d_op = 0x29,
msub_e_op = 0x2a, nmadd_s_op = 0x30,
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 185ba25..374ed74 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -111,11 +111,10 @@
safe_store_code(new_code1, ip, faulted);
if (unlikely(faulted))
return -EFAULT;
- ip += 4;
- safe_store_code(new_code2, ip, faulted);
+ safe_store_code(new_code2, ip + 4, faulted);
if (unlikely(faulted))
return -EFAULT;
- flush_icache_range(ip, ip + 8); /* original ip + 12 */
+ flush_icache_range(ip, ip + 8);
return 0;
}
#endif
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index 253b2fb..73b0ddf 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -35,9 +35,9 @@
LEAF(_save_fp_context)
cfc1 t1, fcr31
-#if defined(CONFIG_64BIT) || defined(CONFIG_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
.set push
-#ifdef CONFIG_MIPS32_R2
+#ifdef CONFIG_CPU_MIPS32_R2
.set mips64r2
mfc0 t0, CP0_STATUS
sll t0, t0, 5
@@ -146,11 +146,11 @@
* - cp1 status/control register
*/
LEAF(_restore_fp_context)
- EX lw t0, SC_FPC_CSR(a0)
+ EX lw t1, SC_FPC_CSR(a0)
-#if defined(CONFIG_64BIT) || defined(CONFIG_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
.set push
-#ifdef CONFIG_MIPS32_R2
+#ifdef CONFIG_CPU_MIPS32_R2
.set mips64r2
mfc0 t0, CP0_STATUS
sll t0, t0, 5
@@ -191,7 +191,7 @@
EX ldc1 $f26, SC_FPREGS+208(a0)
EX ldc1 $f28, SC_FPREGS+224(a0)
EX ldc1 $f30, SC_FPREGS+240(a0)
- ctc1 t0, fcr31
+ ctc1 t1, fcr31
jr ra
li v0, 0 # success
END(_restore_fp_context)
@@ -199,7 +199,7 @@
#ifdef CONFIG_MIPS32_COMPAT
LEAF(_restore_fp_context32)
/* Restore an o32 sigcontext. */
- EX lw t0, SC32_FPC_CSR(a0)
+ EX lw t1, SC32_FPC_CSR(a0)
mfc0 t0, CP0_STATUS
sll t0, t0, 5
@@ -239,7 +239,7 @@
EX ldc1 $f26, SC32_FPREGS+208(a0)
EX ldc1 $f28, SC32_FPREGS+224(a0)
EX ldc1 $f30, SC32_FPREGS+240(a0)
- ctc1 t0, fcr31
+ ctc1 t1, fcr31
jr ra
li v0, 0 # success
END(_restore_fp_context32)
diff --git a/arch/mips/kernel/rtlx-cmp.c b/arch/mips/kernel/rtlx-cmp.c
index 56dc696..758fb3c 100644
--- a/arch/mips/kernel/rtlx-cmp.c
+++ b/arch/mips/kernel/rtlx-cmp.c
@@ -112,5 +112,8 @@
for (i = 0; i < RTLX_CHANNELS; i++)
device_destroy(mt_class, MKDEV(major, i));
+
unregister_chrdev(major, RTLX_MODULE_NAME);
+
+ aprp_hook = NULL;
}
diff --git a/arch/mips/kernel/rtlx-mt.c b/arch/mips/kernel/rtlx-mt.c
index 91d61ba..9c1aca0 100644
--- a/arch/mips/kernel/rtlx-mt.c
+++ b/arch/mips/kernel/rtlx-mt.c
@@ -144,5 +144,8 @@
for (i = 0; i < RTLX_CHANNELS; i++)
device_destroy(mt_class, MKDEV(major, i));
+
unregister_chrdev(major, RTLX_MODULE_NAME);
+
+ aprp_hook = NULL;
}
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 506925b..0b4e2e3 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -1538,10 +1538,10 @@
break;
}
- case 0x7: /* 7 */
- if (MIPSInst_FUNC(ir) != pfetch_op) {
+ case 0x3:
+ if (MIPSInst_FUNC(ir) != pfetch_op)
return SIGILL;
- }
+
/* ignore prefx operation */
break;
diff --git a/arch/mips/mti-malta/malta-amon.c b/arch/mips/mti-malta/malta-amon.c
index 592ac04..84ac523 100644
--- a/arch/mips/mti-malta/malta-amon.c
+++ b/arch/mips/mti-malta/malta-amon.c
@@ -72,7 +72,7 @@
return 0;
}
-#ifdef CONFIG_MIPS_VPE_LOADER
+#ifdef CONFIG_MIPS_VPE_LOADER_CMP
int vpe_run(struct vpe *v)
{
struct vpe_notifications *n;
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index ca3e3a4..2242181 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -119,7 +119,7 @@
do_IRQ(MALTA_INT_BASE + irq);
-#ifdef MIPS_VPE_APSP_API
+#ifdef CONFIG_MIPS_VPE_APSP_API_MT
if (aprp_hook)
aprp_hook();
#endif
@@ -310,7 +310,7 @@
static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
{
-#ifdef MIPS_VPE_APSP_API
+#ifdef CONFIG_MIPS_VPE_APSP_API_CMP
if (aprp_hook)
aprp_hook();
#endif
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index d37be36..2b91b0e 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -150,6 +150,7 @@
msg.address_lo =
((128ul << 20) + CVMX_PCI_MSI_RCV) & 0xffffffff;
msg.address_hi = ((128ul << 20) + CVMX_PCI_MSI_RCV) >> 32;
+ break;
case OCTEON_DMA_BAR_TYPE_BIG:
/* When using big bar, Bar 0 is based at 0 */
msg.address_lo = (0 + CVMX_PCI_MSI_RCV) & 0xffffffff;
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index 637fe03..60d5d17 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -32,17 +32,6 @@
void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
struct page *pg);
-/* #define CONFIG_PARISC_TMPALIAS */
-
-#ifdef CONFIG_PARISC_TMPALIAS
-void clear_user_highpage(struct page *page, unsigned long vaddr);
-#define clear_user_highpage clear_user_highpage
-struct vm_area_struct;
-void copy_user_highpage(struct page *to, struct page *from,
- unsigned long vaddr, struct vm_area_struct *vma);
-#define __HAVE_ARCH_COPY_USER_HIGHPAGE
-#endif
-
/*
* These are used to make use of C type-checking..
*/
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index 3516e0b..64f2992 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -191,8 +191,4 @@
#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-#define arch_spin_relax(lock) cpu_relax()
-#define arch_read_relax(lock) cpu_relax()
-#define arch_write_relax(lock) cpu_relax()
-
#endif /* __ASM_SPINLOCK_H */
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 4270679..265ae51 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -828,13 +828,13 @@
#define __NR_finit_module (__NR_Linux + 333)
#define __NR_sched_setattr (__NR_Linux + 334)
#define __NR_sched_getattr (__NR_Linux + 335)
+#define __NR_utimes (__NR_Linux + 336)
-#define __NR_Linux_syscalls (__NR_sched_getattr + 1)
+#define __NR_Linux_syscalls (__NR_utimes + 1)
#define __IGNORE_select /* newselect */
#define __IGNORE_fadvise64 /* fadvise64_64 */
-#define __IGNORE_utimes /* utime */
#define HPUX_GATEWAY_ADDR 0xC0000004
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index ac87a40..a6ffc77 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -581,67 +581,3 @@
__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
}
}
-
-#ifdef CONFIG_PARISC_TMPALIAS
-
-void clear_user_highpage(struct page *page, unsigned long vaddr)
-{
- void *vto;
- unsigned long flags;
-
- /* Clear using TMPALIAS region. The page doesn't need to
- be flushed but the kernel mapping needs to be purged. */
-
- vto = kmap_atomic(page);
-
- /* The PA-RISC 2.0 Architecture book states on page F-6:
- "Before a write-capable translation is enabled, *all*
- non-equivalently-aliased translations must be removed
- from the page table and purged from the TLB. (Note
- that the caches are not required to be flushed at this
- time.) Before any non-equivalent aliased translation
- is re-enabled, the virtual address range for the writeable
- page (the entire page) must be flushed from the cache,
- and the write-capable translation removed from the page
- table and purged from the TLB." */
-
- purge_kernel_dcache_page_asm((unsigned long)vto);
- purge_tlb_start(flags);
- pdtlb_kernel(vto);
- purge_tlb_end(flags);
- preempt_disable();
- clear_user_page_asm(vto, vaddr);
- preempt_enable();
-
- pagefault_enable(); /* kunmap_atomic(addr, KM_USER0); */
-}
-
-void copy_user_highpage(struct page *to, struct page *from,
- unsigned long vaddr, struct vm_area_struct *vma)
-{
- void *vfrom, *vto;
- unsigned long flags;
-
- /* Copy using TMPALIAS region. This has the advantage
- that the `from' page doesn't need to be flushed. However,
- the `to' page must be flushed in copy_user_page_asm since
- it can be used to bring in executable code. */
-
- vfrom = kmap_atomic(from);
- vto = kmap_atomic(to);
-
- purge_kernel_dcache_page_asm((unsigned long)vto);
- purge_tlb_start(flags);
- pdtlb_kernel(vto);
- pdtlb_kernel(vfrom);
- purge_tlb_end(flags);
- preempt_disable();
- copy_user_page_asm(vto, vfrom, vaddr);
- flush_dcache_page_asm(__pa(vto), vaddr);
- preempt_enable();
-
- pagefault_enable(); /* kunmap_atomic(addr, KM_USER1); */
- pagefault_enable(); /* kunmap_atomic(addr, KM_USER0); */
-}
-
-#endif /* CONFIG_PARISC_TMPALIAS */
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 8fa3fbb..80e5dd2 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -431,6 +431,7 @@
ENTRY_SAME(finit_module)
ENTRY_SAME(sched_setattr)
ENTRY_SAME(sched_getattr) /* 335 */
+ ENTRY_COMP(utimes)
/* Nothing yet */
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 84fdf68..a613d2c 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -200,10 +200,11 @@
/*
* We can't access below the stack pointer in the 32bit ABI and
- * can access 288 bytes in the 64bit ABI
+ * can access 288 bytes in the 64bit big-endian ABI,
+ * or 512 bytes with the new ELFv2 little-endian ABI.
*/
if (!is_32bit_task())
- usp -= 288;
+ usp -= USER_REDZONE_SIZE;
return (void __user *) (usp - len);
}
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index e27e9ad..150866b 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -134,6 +134,7 @@
}
extern int dma_set_mask(struct device *dev, u64 dma_mask);
+extern int __dma_set_mask(struct device *dev, u64 dma_mask);
#define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL)
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 9e39ceb..d4dd41f 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -172,10 +172,20 @@
};
extern struct eeh_ops *eeh_ops;
-extern int eeh_subsystem_enabled;
+extern bool eeh_subsystem_enabled;
extern raw_spinlock_t confirm_error_lock;
extern int eeh_probe_mode;
+static inline bool eeh_enabled(void)
+{
+ return eeh_subsystem_enabled;
+}
+
+static inline void eeh_set_enable(bool mode)
+{
+ eeh_subsystem_enabled = mode;
+}
+
#define EEH_PROBE_MODE_DEV (1<<0) /* From PCI device */
#define EEH_PROBE_MODE_DEVTREE (1<<1) /* From device tree */
@@ -246,7 +256,7 @@
* If this macro yields TRUE, the caller relays to eeh_check_failure()
* which does further tests out of line.
*/
-#define EEH_POSSIBLE_ERROR(val, type) ((val) == (type)~0 && eeh_subsystem_enabled)
+#define EEH_POSSIBLE_ERROR(val, type) ((val) == (type)~0 && eeh_enabled())
/*
* Reads from a device which has been isolated by EEH will return
@@ -257,6 +267,13 @@
#else /* !CONFIG_EEH */
+static inline bool eeh_enabled(void)
+{
+ return false;
+}
+
+static inline void eeh_set_enable(bool mode) { }
+
static inline int eeh_init(void)
{
return 0;
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index d750336..623f297 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -127,7 +127,7 @@
unsigned long addr, pte_t *ptep)
{
#ifdef CONFIG_PPC64
- return __pte(pte_update(mm, addr, ptep, ~0UL, 1));
+ return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
#else
return __pte(pte_update(ptep, ~0UL, 0));
#endif
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index f7a8036..42632c7 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -77,6 +77,7 @@
#ifdef CONFIG_IOMMU_API
struct iommu_group *it_group;
#endif
+ void (*set_bypass)(struct iommu_table *tbl, bool enable);
};
/* Pure 2^n version of get_order */
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 40157e2..ed82142 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -816,8 +816,8 @@
int64_t opal_pci_poll(uint64_t phb_id);
int64_t opal_return_cpu(void);
-int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val);
-int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val);
+int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val);
+int64_t opal_xscom_write(uint32_t gcid, uint64_t pcb_addr, uint64_t val);
int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
uint32_t addr, uint32_t data, uint32_t sz);
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index bc141c9..eb92610 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -195,6 +195,7 @@
static inline unsigned long pte_update(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep, unsigned long clr,
+ unsigned long set,
int huge)
{
#ifdef PTE_ATOMIC_UPDATES
@@ -205,14 +206,15 @@
andi. %1,%0,%6\n\
bne- 1b \n\
andc %1,%0,%4 \n\
+ or %1,%1,%7\n\
stdcx. %1,0,%3 \n\
bne- 1b"
: "=&r" (old), "=&r" (tmp), "=m" (*ptep)
- : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY)
+ : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set)
: "cc" );
#else
unsigned long old = pte_val(*ptep);
- *ptep = __pte(old & ~clr);
+ *ptep = __pte((old & ~clr) | set);
#endif
/* huge pages use the old page table lock */
if (!huge)
@@ -231,9 +233,9 @@
{
unsigned long old;
- if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
+ if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
return 0;
- old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0);
+ old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
return (old & _PAGE_ACCESSED) != 0;
}
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
@@ -252,7 +254,7 @@
if ((pte_val(*ptep) & _PAGE_RW) == 0)
return;
- pte_update(mm, addr, ptep, _PAGE_RW, 0);
+ pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
}
static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
@@ -261,7 +263,7 @@
if ((pte_val(*ptep) & _PAGE_RW) == 0)
return;
- pte_update(mm, addr, ptep, _PAGE_RW, 1);
+ pte_update(mm, addr, ptep, _PAGE_RW, 0, 1);
}
/*
@@ -284,14 +286,14 @@
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0);
+ unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0);
return __pte(old);
}
static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t * ptep)
{
- pte_update(mm, addr, ptep, ~0UL, 0);
+ pte_update(mm, addr, ptep, ~0UL, 0, 0);
}
@@ -506,7 +508,9 @@
extern unsigned long pmd_hugepage_update(struct mm_struct *mm,
unsigned long addr,
- pmd_t *pmdp, unsigned long clr);
+ pmd_t *pmdp,
+ unsigned long clr,
+ unsigned long set);
static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
unsigned long addr, pmd_t *pmdp)
@@ -515,7 +519,7 @@
if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
return 0;
- old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED);
+ old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0);
return ((old & _PAGE_ACCESSED) != 0);
}
@@ -542,7 +546,7 @@
if ((pmd_val(*pmdp) & _PAGE_RW) == 0)
return;
- pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW);
+ pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0);
}
#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index f83b6f3..3ebb188 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -75,12 +75,34 @@
return pte;
}
+#define ptep_set_numa ptep_set_numa
+static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep)
+{
+ if ((pte_val(*ptep) & _PAGE_PRESENT) == 0)
+ VM_BUG_ON(1);
+
+ pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0);
+ return;
+}
+
#define pmd_numa pmd_numa
static inline int pmd_numa(pmd_t pmd)
{
return pte_numa(pmd_pte(pmd));
}
+#define pmdp_set_numa pmdp_set_numa
+static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp)
+{
+ if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0)
+ VM_BUG_ON(1);
+
+ pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA);
+ return;
+}
+
#define pmd_mknonnuma pmd_mknonnuma
static inline pmd_t pmd_mknonnuma(pmd_t pmd)
{
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index becc08e..279b80f 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -28,11 +28,23 @@
#ifdef __powerpc64__
+/*
+ * Size of redzone that userspace is allowed to use below the stack
+ * pointer. This is 288 in the 64-bit big-endian ELF ABI, and 512 in
+ * the new ELFv2 little-endian ABI, so we allow the larger amount.
+ *
+ * For kernel code we allow a 288-byte redzone, in order to conserve
+ * kernel stack space; gcc currently only uses 288 bytes, and will
+ * hopefully allow explicit control of the redzone size in future.
+ */
+#define USER_REDZONE_SIZE 512
+#define KERNEL_REDZONE_SIZE 288
+
#define STACK_FRAME_OVERHEAD 112 /* size of minimum stack frame */
#define STACK_FRAME_LR_SAVE 2 /* Location of LR in stack frame */
#define STACK_FRAME_REGS_MARKER ASM_CONST(0x7265677368657265)
#define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + \
- STACK_FRAME_OVERHEAD + 288)
+ STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE)
#define STACK_FRAME_MARKER 12
/* Size of dummy stack frame allocated when calling signal handler. */
@@ -41,6 +53,8 @@
#else /* __powerpc64__ */
+#define USER_REDZONE_SIZE 0
+#define KERNEL_REDZONE_SIZE 0
#define STACK_FRAME_OVERHEAD 16 /* size of minimum stack frame */
#define STACK_FRAME_LR_SAVE 1 /* Location of LR in stack frame */
#define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773)
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 4ee06fe..d0e784e 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -8,6 +8,7 @@
#ifdef __powerpc64__
+extern char __start_interrupts[];
extern char __end_interrupts[];
extern char __prom_init_toc_start[];
@@ -21,6 +22,17 @@
return 0;
}
+static inline int overlaps_interrupt_vector_text(unsigned long start,
+ unsigned long end)
+{
+ unsigned long real_start, real_end;
+ real_start = __start_interrupts - _stext;
+ real_end = __end_interrupts - _stext;
+
+ return start < (unsigned long)__va(real_end) &&
+ (unsigned long)__va(real_start) < end;
+}
+
static inline int overlaps_kernel_text(unsigned long start, unsigned long end)
{
return start < (unsigned long)__init_end &&
diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h
index 0d9cecd..c53f5f6 100644
--- a/arch/powerpc/include/asm/vdso.h
+++ b/arch/powerpc/include/asm/vdso.h
@@ -4,11 +4,11 @@
#ifdef __KERNEL__
/* Default link addresses for the vDSOs */
-#define VDSO32_LBASE 0x100000
-#define VDSO64_LBASE 0x100000
+#define VDSO32_LBASE 0x0
+#define VDSO64_LBASE 0x0
/* Default map addresses for 32bit vDSO */
-#define VDSO32_MBASE VDSO32_LBASE
+#define VDSO32_MBASE 0x100000
#define VDSO_VERSION_STRING LINUX_2.6.15
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 11c1d06..7a13f37 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -98,17 +98,19 @@
size_t csize, unsigned long offset, int userbuf)
{
void *vaddr;
+ phys_addr_t paddr;
if (!csize)
return 0;
csize = min_t(size_t, csize, PAGE_SIZE);
+ paddr = pfn << PAGE_SHIFT;
- if ((min_low_pfn < pfn) && (pfn < max_pfn)) {
- vaddr = __va(pfn << PAGE_SHIFT);
+ if (memblock_is_region_memory(paddr, csize)) {
+ vaddr = __va(paddr);
csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
} else {
- vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0);
+ vaddr = __ioremap(paddr, PAGE_SIZE, 0);
csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
iounmap(vaddr);
}
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 8032b97..ee78f6e 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -191,12 +191,10 @@
#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
-int dma_set_mask(struct device *dev, u64 dma_mask)
+int __dma_set_mask(struct device *dev, u64 dma_mask)
{
struct dma_map_ops *dma_ops = get_dma_ops(dev);
- if (ppc_md.dma_set_mask)
- return ppc_md.dma_set_mask(dev, dma_mask);
if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL))
return dma_ops->set_dma_mask(dev, dma_mask);
if (!dev->dma_mask || !dma_supported(dev, dma_mask))
@@ -204,6 +202,12 @@
*dev->dma_mask = dma_mask;
return 0;
}
+int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+ if (ppc_md.dma_set_mask)
+ return ppc_md.dma_set_mask(dev, dma_mask);
+ return __dma_set_mask(dev, dma_mask);
+}
EXPORT_SYMBOL(dma_set_mask);
u64 dma_get_required_mask(struct device *dev)
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 148db72..e7b76a6 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -28,6 +28,7 @@
#include <linux/pci.h>
#include <linux/proc_fs.h>
#include <linux/rbtree.h>
+#include <linux/reboot.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
#include <linux/export.h>
@@ -89,7 +90,7 @@
/* Platform dependent EEH operations */
struct eeh_ops *eeh_ops = NULL;
-int eeh_subsystem_enabled;
+bool eeh_subsystem_enabled = false;
EXPORT_SYMBOL(eeh_subsystem_enabled);
/*
@@ -364,7 +365,7 @@
eeh_stats.total_mmio_ffs++;
- if (!eeh_subsystem_enabled)
+ if (!eeh_enabled())
return 0;
if (!edev) {
@@ -747,6 +748,17 @@
return -EEXIST;
}
+static int eeh_reboot_notifier(struct notifier_block *nb,
+ unsigned long action, void *unused)
+{
+ eeh_set_enable(false);
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block eeh_reboot_nb = {
+ .notifier_call = eeh_reboot_notifier,
+};
+
/**
* eeh_init - EEH initialization
*
@@ -778,6 +790,14 @@
if (machine_is(powernv) && cnt++ <= 0)
return ret;
+ /* Register reboot notifier */
+ ret = register_reboot_notifier(&eeh_reboot_nb);
+ if (ret) {
+ pr_warn("%s: Failed to register notifier (%d)\n",
+ __func__, ret);
+ return ret;
+ }
+
/* call platform initialization function */
if (!eeh_ops) {
pr_warning("%s: Platform EEH operation not found\n",
@@ -822,7 +842,7 @@
return ret;
}
- if (eeh_subsystem_enabled)
+ if (eeh_enabled())
pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
else
pr_warning("EEH: No capable adapters found\n");
@@ -897,7 +917,7 @@
struct device_node *dn;
struct eeh_dev *edev;
- if (!dev || !eeh_subsystem_enabled)
+ if (!dev || !eeh_enabled())
return;
pr_debug("EEH: Adding device %s\n", pci_name(dev));
@@ -1005,7 +1025,7 @@
{
struct eeh_dev *edev;
- if (!dev || !eeh_subsystem_enabled)
+ if (!dev || !eeh_enabled())
return;
edev = pci_dev_to_eeh_dev(dev);
@@ -1045,7 +1065,7 @@
static int proc_eeh_show(struct seq_file *m, void *v)
{
- if (0 == eeh_subsystem_enabled) {
+ if (!eeh_enabled()) {
seq_printf(m, "EEH Subsystem is globally disabled\n");
seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs);
} else {
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 7bb30dc..fdc679d 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -362,9 +362,13 @@
*/
if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE))
return NULL;
+
driver = eeh_pcid_get(dev);
- if (driver && driver->err_handler)
- return NULL;
+ if (driver) {
+ eeh_pcid_put(dev);
+ if (driver->err_handler)
+ return NULL;
+ }
/* Remove it from PCI subsystem */
pr_debug("EEH: Removing %s without EEH sensitive driver\n",
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 9b27b29..b0ded97 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -74,6 +74,7 @@
*/
static int test_24bit_addr(unsigned long ip, unsigned long addr)
{
+ addr = ppc_function_entry((void *)addr);
/* use the create_branch to verify that this offset can be branched */
return create_branch((unsigned int *)ip, addr, 0);
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index d773dd4..88e3ec6 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1088,6 +1088,14 @@
memset(tbl->it_map, 0xff, sz);
iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
+ /*
+ * Disable iommu bypass, otherwise the user can DMA to all of
+ * our physical memory via the bypass window instead of just
+ * the pages that has been explicitly mapped into the iommu
+ */
+ if (tbl->set_bypass)
+ tbl->set_bypass(tbl, false);
+
return 0;
}
EXPORT_SYMBOL_GPL(iommu_take_ownership);
@@ -1102,6 +1110,10 @@
/* Restore bit#0 set by iommu_init_table() */
if (tbl->it_offset == 0)
set_bit(0, tbl->it_map);
+
+ /* The kernel owns the device now, we can restore the iommu bypass */
+ if (tbl->set_bypass)
+ tbl->set_bypass(tbl, true);
}
EXPORT_SYMBOL_GPL(iommu_release_ownership);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 9729b23..1d0848b 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -559,8 +559,13 @@
#ifdef CONFIG_PPC64
cpu_nr = i;
#else
+#ifdef CONFIG_SMP
cpu_nr = get_hard_smp_processor_id(i);
+#else
+ cpu_nr = 0;
#endif
+#endif
+
memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE);
tp = critirq_ctx[cpu_nr];
tp->cpu = cpu_nr;
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index 75d4f73..015ae55 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -196,7 +196,9 @@
/* Values we need to export to the second kernel via the device tree. */
static phys_addr_t kernel_end;
+static phys_addr_t crashk_base;
static phys_addr_t crashk_size;
+static unsigned long long mem_limit;
static struct property kernel_end_prop = {
.name = "linux,kernel-end",
@@ -207,7 +209,7 @@
static struct property crashk_base_prop = {
.name = "linux,crashkernel-base",
.length = sizeof(phys_addr_t),
- .value = &crashk_res.start,
+ .value = &crashk_base
};
static struct property crashk_size_prop = {
@@ -219,9 +221,11 @@
static struct property memory_limit_prop = {
.name = "linux,memory-limit",
.length = sizeof(unsigned long long),
- .value = &memory_limit,
+ .value = &mem_limit,
};
+#define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG)
+
static void __init export_crashk_values(struct device_node *node)
{
struct property *prop;
@@ -237,8 +241,9 @@
of_remove_property(node, prop);
if (crashk_res.start != 0) {
+ crashk_base = cpu_to_be_ulong(crashk_res.start),
of_add_property(node, &crashk_base_prop);
- crashk_size = resource_size(&crashk_res);
+ crashk_size = cpu_to_be_ulong(resource_size(&crashk_res));
of_add_property(node, &crashk_size_prop);
}
@@ -246,6 +251,7 @@
* memory_limit is required by the kexec-tools to limit the
* crash regions to the actual memory used.
*/
+ mem_limit = cpu_to_be_ulong(memory_limit);
of_update_property(node, &memory_limit_prop);
}
@@ -264,7 +270,7 @@
of_remove_property(node, prop);
/* information needed by userspace when using default_machine_kexec */
- kernel_end = __pa(_end);
+ kernel_end = cpu_to_be_ulong(__pa(_end));
of_add_property(node, &kernel_end_prop);
export_crashk_values(node);
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index be4e6d6..59d229a 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -369,6 +369,7 @@
/* Values we need to export to the second kernel via the device tree. */
static unsigned long htab_base;
+static unsigned long htab_size;
static struct property htab_base_prop = {
.name = "linux,htab-base",
@@ -379,7 +380,7 @@
static struct property htab_size_prop = {
.name = "linux,htab-size",
.length = sizeof(unsigned long),
- .value = &htab_size_bytes,
+ .value = &htab_size,
};
static int __init export_htab_values(void)
@@ -403,8 +404,9 @@
if (prop)
of_remove_property(node, prop);
- htab_base = __pa(htab_address);
+ htab_base = cpu_to_be64(__pa(htab_address));
of_add_property(node, &htab_base_prop);
+ htab_size = cpu_to_be64(htab_size_bytes);
of_add_property(node, &htab_size_prop);
of_node_put(node);
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 879f096..7c6bb4b 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -57,11 +57,14 @@
mtlr r0
blr
+/*
+ * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
+ */
_GLOBAL(call_do_irq)
mflr r0
stw r0,4(r1)
lwz r10,THREAD+KSP_LIMIT(r2)
- addi r11,r3,THREAD_INFO_GAP
+ addi r11,r4,THREAD_INFO_GAP
stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
mr r1,r4
stw r10,8(r1)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8d4c247f1..af064d2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1048,6 +1048,15 @@
flush_altivec_to_thread(src);
flush_vsx_to_thread(src);
flush_spe_to_thread(src);
+ /*
+ * Flush TM state out so we can copy it. __switch_to_tm() does this
+ * flush but it removes the checkpointed state from the current CPU and
+ * transitions the CPU out of TM mode. Hence we need to call
+ * tm_recheckpoint_new_task() (on the same task) to restore the
+ * checkpointed state back and the TM mode.
+ */
+ __switch_to_tm(src);
+ tm_recheckpoint_new_task(src);
*dst = *src;
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index b47a0e1..d88736f 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -69,8 +69,8 @@
* R_PPC64_RELATIVE ones.
*/
mtctr r8
-5: lwz r0,12(9) /* ELF64_R_TYPE(reloc->r_info) */
- cmpwi r0,R_PPC64_RELATIVE
+5: ld r0,8(9) /* ELF64_R_TYPE(reloc->r_info) */
+ cmpdi r0,R_PPC64_RELATIVE
bne 6f
ld r6,0(r9) /* reloc->r_offset */
ld r0,16(r9) /* reloc->r_addend */
@@ -81,6 +81,7 @@
6: blr
+.balign 8
p_dyn: .llong __dynamic_start - 0b
p_rela: .llong __rela_dyn_start - 0b
p_st: .llong _stext - 0b
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 2b0da27..04cc4fc 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -247,7 +247,12 @@
/* interrupt stacks must be in lowmem, we get that for free on ppc32
* as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */
for_each_possible_cpu(i) {
+#ifdef CONFIG_SMP
hw_cpu = get_hard_smp_processor_id(i);
+#else
+ hw_cpu = 0;
+#endif
+
critirq_ctx[hw_cpu] = (struct thread_info *)
__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
#ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index e35bf77..8d253c2 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -65,8 +65,8 @@
struct siginfo __user *pinfo;
void __user *puc;
struct siginfo info;
- /* 64 bit ABI allows for 288 bytes below sp before decrementing it. */
- char abigap[288];
+ /* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */
+ char abigap[USER_REDZONE_SIZE];
} __attribute__ ((aligned (16)));
static const char fmt32[] = KERN_INFO \
diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S
index 79683d0..6ac107a 100644
--- a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S
+++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S
@@ -6,7 +6,7 @@
.globl vdso32_start, vdso32_end
.balign PAGE_SIZE
vdso32_start:
- .incbin "arch/powerpc/kernel/vdso32/vdso32.so"
+ .incbin "arch/powerpc/kernel/vdso32/vdso32.so.dbg"
.balign PAGE_SIZE
vdso32_end:
diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S
index 8df9e24..df60fca 100644
--- a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S
+++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S
@@ -6,7 +6,7 @@
.globl vdso64_start, vdso64_end
.balign PAGE_SIZE
vdso64_start:
- .incbin "arch/powerpc/kernel/vdso64/vdso64.so"
+ .incbin "arch/powerpc/kernel/vdso64/vdso64.so.dbg"
.balign PAGE_SIZE
vdso64_end:
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index e66d4ec..818dce3 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1504,73 +1504,6 @@
1: addi r8,r8,16
.endr
- /* Save DEC */
- mfspr r5,SPRN_DEC
- mftb r6
- extsw r5,r5
- add r5,r5,r6
- std r5,VCPU_DEC_EXPIRES(r9)
-
-BEGIN_FTR_SECTION
- b 8f
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
- /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
- mfmsr r8
- li r0, 1
- rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG
- mtmsrd r8
-
- /* Save POWER8-specific registers */
- mfspr r5, SPRN_IAMR
- mfspr r6, SPRN_PSPB
- mfspr r7, SPRN_FSCR
- std r5, VCPU_IAMR(r9)
- stw r6, VCPU_PSPB(r9)
- std r7, VCPU_FSCR(r9)
- mfspr r5, SPRN_IC
- mfspr r6, SPRN_VTB
- mfspr r7, SPRN_TAR
- std r5, VCPU_IC(r9)
- std r6, VCPU_VTB(r9)
- std r7, VCPU_TAR(r9)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
- mfspr r5, SPRN_TFHAR
- mfspr r6, SPRN_TFIAR
- mfspr r7, SPRN_TEXASR
- std r5, VCPU_TFHAR(r9)
- std r6, VCPU_TFIAR(r9)
- std r7, VCPU_TEXASR(r9)
-#endif
- mfspr r8, SPRN_EBBHR
- std r8, VCPU_EBBHR(r9)
- mfspr r5, SPRN_EBBRR
- mfspr r6, SPRN_BESCR
- mfspr r7, SPRN_CSIGR
- mfspr r8, SPRN_TACR
- std r5, VCPU_EBBRR(r9)
- std r6, VCPU_BESCR(r9)
- std r7, VCPU_CSIGR(r9)
- std r8, VCPU_TACR(r9)
- mfspr r5, SPRN_TCSCR
- mfspr r6, SPRN_ACOP
- mfspr r7, SPRN_PID
- mfspr r8, SPRN_WORT
- std r5, VCPU_TCSCR(r9)
- std r6, VCPU_ACOP(r9)
- stw r7, VCPU_GUEST_PID(r9)
- std r8, VCPU_WORT(r9)
-8:
-
- /* Save and reset AMR and UAMOR before turning on the MMU */
-BEGIN_FTR_SECTION
- mfspr r5,SPRN_AMR
- mfspr r6,SPRN_UAMOR
- std r5,VCPU_AMR(r9)
- std r6,VCPU_UAMOR(r9)
- li r6,0
- mtspr SPRN_AMR,r6
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
/* Unset guest mode */
li r0, KVM_GUEST_MODE_NONE
stb r0, HSTATE_IN_GUEST(r13)
@@ -2203,7 +2136,7 @@
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
mfspr r6,SPRN_VRSAVE
- stw r6,VCPU_VRSAVE(r3)
+ stw r6,VCPU_VRSAVE(r31)
mtlr r30
mtmsrd r5
isync
@@ -2240,7 +2173,7 @@
bl .load_vr_state
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
- lwz r7,VCPU_VRSAVE(r4)
+ lwz r7,VCPU_VRSAVE(r31)
mtspr SPRN_VRSAVE,r7
mtlr r30
mr r4,r31
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index de68812..d766d6e 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -207,6 +207,20 @@
if (overlaps_kernel_text(vaddr, vaddr + step))
tprot &= ~HPTE_R_N;
+ /*
+ * If relocatable, check if it overlaps interrupt vectors that
+ * are copied down to real 0. For relocatable kernel
+ * (e.g. kdump case) we copy interrupt vectors down to real
+ * address 0. Mark that region as executable. This is
+ * because on p8 system with relocation on exception feature
+ * enabled, exceptions are raised with MMU (IR=DR=1) ON. Hence
+ * in order to execute the interrupt handlers in virtual
+ * mode the vector region need to be marked as executable.
+ */
+ if ((PHYSICAL_START > MEMORY_START) &&
+ overlaps_interrupt_vector_text(vaddr, vaddr + step))
+ tprot &= ~HPTE_R_N;
+
hash = hpt_hash(vpn, shift, ssize);
hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 65b7b65..62bf5e8 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -510,7 +510,8 @@
}
unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
- pmd_t *pmdp, unsigned long clr)
+ pmd_t *pmdp, unsigned long clr,
+ unsigned long set)
{
unsigned long old, tmp;
@@ -526,14 +527,15 @@
andi. %1,%0,%6\n\
bne- 1b \n\
andc %1,%0,%4 \n\
+ or %1,%1,%7\n\
stdcx. %1,0,%3 \n\
bne- 1b"
: "=&r" (old), "=&r" (tmp), "=m" (*pmdp)
- : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY)
+ : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY), "r" (set)
: "cc" );
#else
old = pmd_val(*pmdp);
- *pmdp = __pmd(old & ~clr);
+ *pmdp = __pmd((old & ~clr) | set);
#endif
if (old & _PAGE_HASHPTE)
hpte_do_hugepage_flush(mm, addr, pmdp);
@@ -708,7 +710,7 @@
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
- pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT);
+ pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
}
/*
@@ -835,7 +837,7 @@
unsigned long old;
pgtable_t *pgtable_slot;
- old = pmd_hugepage_update(mm, addr, pmdp, ~0UL);
+ old = pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0);
old_pmd = __pmd(old);
/*
* We have pmd == none and we are holding page_table_lock.
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index a770df2d..6c0b1f5 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -78,7 +78,7 @@
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
arch_enter_lazy_mmu_mode();
for (; npages > 0; --npages) {
- pte_update(mm, addr, pte, 0, 0);
+ pte_update(mm, addr, pte, 0, 0, 0);
addr += PAGE_SIZE;
++pte;
}
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 555034f..808ce1c 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -390,9 +390,9 @@
mark));
break;
case BPF_S_ANC_RXHASH:
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
- rxhash));
+ hash));
break;
case BPF_S_ANC_VLAN_TAG:
case BPF_S_ANC_VLAN_TAG_PRESENT:
@@ -689,6 +689,7 @@
((u64 *)image)[0] = (u64)code_base;
((u64 *)image)[1] = local_paca->kernel_toc;
fp->bpf_func = (void *)image;
+ fp->jited = 1;
}
out:
kfree(addrs);
@@ -697,7 +698,7 @@
void bpf_jit_free(struct sk_filter *fp)
{
- if (fp->bpf_func != sk_run_filter)
+ if (fp->jited)
module_free(NULL, fp->bpf_func);
kfree(fp);
}
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 29b89e8..67cf220 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1147,6 +1147,9 @@
mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
mb();
+ if (cpuhw->bhrb_users)
+ ppmu->config_bhrb(cpuhw->bhrb_filter);
+
write_mmcr0(cpuhw, mmcr0);
/*
@@ -1158,8 +1161,6 @@
}
out:
- if (cpuhw->bhrb_users)
- ppmu->config_bhrb(cpuhw->bhrb_filter);
local_irq_restore(flags);
}
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index a3f7abd..96cee20 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -25,6 +25,37 @@
#define PM_BRU_FIN 0x10068
#define PM_BR_MPRED_CMPL 0x400f6
+/* All L1 D cache load references counted at finish, gated by reject */
+#define PM_LD_REF_L1 0x100ee
+/* Load Missed L1 */
+#define PM_LD_MISS_L1 0x3e054
+/* Store Missed L1 */
+#define PM_ST_MISS_L1 0x300f0
+/* L1 cache data prefetches */
+#define PM_L1_PREF 0x0d8b8
+/* Instruction fetches from L1 */
+#define PM_INST_FROM_L1 0x04080
+/* Demand iCache Miss */
+#define PM_L1_ICACHE_MISS 0x200fd
+/* Instruction Demand sectors wriittent into IL1 */
+#define PM_L1_DEMAND_WRITE 0x0408c
+/* Instruction prefetch written into IL1 */
+#define PM_IC_PREF_WRITE 0x0408e
+/* The data cache was reloaded from local core's L3 due to a demand load */
+#define PM_DATA_FROM_L3 0x4c042
+/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */
+#define PM_DATA_FROM_L3MISS 0x300fe
+/* All successful D-side store dispatches for this thread */
+#define PM_L2_ST 0x17080
+/* All successful D-side store dispatches for this thread that were L2 Miss */
+#define PM_L2_ST_MISS 0x17082
+/* Total HW L3 prefetches(Load+store) */
+#define PM_L3_PREF_ALL 0x4e052
+/* Data PTEG reload */
+#define PM_DTLB_MISS 0x300fc
+/* ITLB Reloaded */
+#define PM_ITLB_MISS 0x400fc
+
/*
* Raw event encoding for POWER8:
@@ -557,6 +588,8 @@
[PERF_COUNT_HW_INSTRUCTIONS] = PM_INST_CMPL,
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BRU_FIN,
[PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1,
+ [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1,
};
static u64 power8_bhrb_filter_map(u64 branch_sample_type)
@@ -596,6 +629,116 @@
mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter));
}
+#define C(x) PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+ [ C(L1D) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = PM_LD_REF_L1,
+ [ C(RESULT_MISS) ] = PM_LD_MISS_L1,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = PM_ST_MISS_L1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = PM_L1_PREF,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(L1I) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = PM_INST_FROM_L1,
+ [ C(RESULT_MISS) ] = PM_L1_ICACHE_MISS,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = PM_L1_DEMAND_WRITE,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = PM_IC_PREF_WRITE,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(LL) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = PM_DATA_FROM_L3,
+ [ C(RESULT_MISS) ] = PM_DATA_FROM_L3MISS,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = PM_L2_ST,
+ [ C(RESULT_MISS) ] = PM_L2_ST_MISS,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = PM_DTLB_MISS,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = PM_ITLB_MISS,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = PM_BRU_FIN,
+ [ C(RESULT_MISS) ] = PM_BR_MPRED_CMPL,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
+#undef C
+
static struct power_pmu power8_pmu = {
.name = "POWER8",
.n_counter = 6,
@@ -611,6 +754,7 @@
.flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB,
.n_generic = ARRAY_SIZE(power8_generic_events),
.generic_events = power8_generic_events,
+ .cache_events = &power8_cache_events,
.attr_groups = power8_pmu_attr_groups,
.bhrb_nr = 32,
};
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 5ec1e47..e865d74 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -123,7 +123,8 @@
area->nid = nid;
area->order = order;
- area->pages = alloc_pages_exact_node(area->nid, GFP_KERNEL|GFP_THISNODE,
+ area->pages = alloc_pages_exact_node(area->nid,
+ GFP_KERNEL|__GFP_THISNODE,
area->order);
if (!area->pages) {
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index e1e7161..253fefe 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -44,7 +44,8 @@
/* We simply send special EEH event */
if ((changed_evts & OPAL_EVENT_PCI_ERROR) &&
- (events & OPAL_EVENT_PCI_ERROR))
+ (events & OPAL_EVENT_PCI_ERROR) &&
+ eeh_enabled())
eeh_send_failure_event(NULL);
return 0;
@@ -113,6 +114,7 @@
ioda_eeh_inbB_dbgfs_set, "0x%llx\n");
#endif /* CONFIG_DEBUG_FS */
+
/**
* ioda_eeh_post_init - Chip dependent post initialization
* @hose: PCI controller
@@ -220,6 +222,22 @@
return ret;
}
+static void ioda_eeh_phb_diag(struct pci_controller *hose)
+{
+ struct pnv_phb *phb = hose->private_data;
+ long rc;
+
+ rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+ PNV_PCI_DIAG_BUF_SIZE);
+ if (rc != OPAL_SUCCESS) {
+ pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
+ __func__, hose->global_number, rc);
+ return;
+ }
+
+ pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
+}
+
/**
* ioda_eeh_get_state - Retrieve the state of PE
* @pe: EEH PE
@@ -271,6 +289,9 @@
result |= EEH_STATE_DMA_ACTIVE;
result |= EEH_STATE_MMIO_ENABLED;
result |= EEH_STATE_DMA_ENABLED;
+ } else if (!(pe->state & EEH_PE_ISOLATED)) {
+ eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+ ioda_eeh_phb_diag(hose);
}
return result;
@@ -314,6 +335,15 @@
__func__, fstate, hose->global_number, pe_no);
}
+ /* Dump PHB diag-data for frozen PE */
+ if (result != EEH_STATE_NOT_SUPPORT &&
+ (result & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) !=
+ (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) &&
+ !(pe->state & EEH_PE_ISOLATED)) {
+ eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+ ioda_eeh_phb_diag(hose);
+ }
+
return result;
}
@@ -489,8 +519,7 @@
static int ioda_eeh_reset(struct eeh_pe *pe, int option)
{
struct pci_controller *hose = pe->phb;
- struct eeh_dev *edev;
- struct pci_dev *dev;
+ struct pci_bus *bus;
int ret;
/*
@@ -519,73 +548,17 @@
if (pe->type & EEH_PE_PHB) {
ret = ioda_eeh_phb_reset(hose, option);
} else {
- if (pe->type & EEH_PE_DEVICE) {
- /*
- * If it's device PE, we didn't refer to the parent
- * PCI bus yet. So we have to figure it out indirectly.
- */
- edev = list_first_entry(&pe->edevs,
- struct eeh_dev, list);
- dev = eeh_dev_to_pci_dev(edev);
- dev = dev->bus->self;
- } else {
- /*
- * If it's bus PE, the parent PCI bus is already there
- * and just pick it up.
- */
- dev = pe->bus->self;
- }
-
- /*
- * Do reset based on the fact that the direct upstream bridge
- * is root bridge (port) or not.
- */
- if (dev->bus->number == 0)
+ bus = eeh_pe_bus_get(pe);
+ if (pci_is_root_bus(bus))
ret = ioda_eeh_root_reset(hose, option);
else
- ret = ioda_eeh_bridge_reset(hose, dev, option);
+ ret = ioda_eeh_bridge_reset(hose, bus->self, option);
}
return ret;
}
/**
- * ioda_eeh_get_log - Retrieve error log
- * @pe: EEH PE
- * @severity: Severity level of the log
- * @drv_log: buffer to store the log
- * @len: space of the log buffer
- *
- * The function is used to retrieve error log from P7IOC.
- */
-static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
- char *drv_log, unsigned long len)
-{
- s64 ret;
- unsigned long flags;
- struct pci_controller *hose = pe->phb;
- struct pnv_phb *phb = hose->private_data;
-
- spin_lock_irqsave(&phb->lock, flags);
-
- ret = opal_pci_get_phb_diag_data2(phb->opal_id,
- phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
- if (ret) {
- spin_unlock_irqrestore(&phb->lock, flags);
- pr_warning("%s: Can't get log for PHB#%x-PE#%x (%lld)\n",
- __func__, hose->global_number, pe->addr, ret);
- return -EIO;
- }
-
- /* The PHB diag-data is always indicative */
- pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-
- spin_unlock_irqrestore(&phb->lock, flags);
-
- return 0;
-}
-
-/**
* ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE
* @pe: EEH PE
*
@@ -666,22 +639,6 @@
}
}
-static void ioda_eeh_phb_diag(struct pci_controller *hose)
-{
- struct pnv_phb *phb = hose->private_data;
- long rc;
-
- rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
- PNV_PCI_DIAG_BUF_SIZE);
- if (rc != OPAL_SUCCESS) {
- pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
- __func__, hose->global_number, rc);
- return;
- }
-
- pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-}
-
static int ioda_eeh_get_phb_pe(struct pci_controller *hose,
struct eeh_pe **pe)
{
@@ -855,6 +812,20 @@
}
/*
+ * EEH core will try recover from fenced PHB or
+ * frozen PE. In the time for frozen PE, EEH core
+ * enable IO path for that before collecting logs,
+ * but it ruins the site. So we have to dump the
+ * log in advance here.
+ */
+ if ((ret == EEH_NEXT_ERR_FROZEN_PE ||
+ ret == EEH_NEXT_ERR_FENCED_PHB) &&
+ !((*pe)->state & EEH_PE_ISOLATED)) {
+ eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
+ ioda_eeh_phb_diag(hose);
+ }
+
+ /*
* If we have no errors on the specific PHB or only
* informative error there, we continue poking it.
* Otherwise, we need actions to be taken by upper
@@ -872,7 +843,6 @@
.set_option = ioda_eeh_set_option,
.get_state = ioda_eeh_get_state,
.reset = ioda_eeh_reset,
- .get_log = ioda_eeh_get_log,
.configure_bridge = ioda_eeh_configure_bridge,
.next_error = ioda_eeh_next_error
};
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index a79fddc..a59788e 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -145,7 +145,7 @@
* Enable EEH explicitly so that we will do EEH check
* while accessing I/O stuff
*/
- eeh_subsystem_enabled = 1;
+ eeh_set_enable(true);
/* Save memory bars */
eeh_save_bars(edev);
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 4fbf276..4cd2ea6 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -71,11 +71,11 @@
}
}
-static u64 opal_scom_unmangle(u64 reg)
+static u64 opal_scom_unmangle(u64 addr)
{
/*
* XSCOM indirect addresses have the top bit set. Additionally
- * the reset of the top 3 nibbles is always 0.
+ * the rest of the top 3 nibbles is always 0.
*
* Because the debugfs interface uses signed offsets and shifts
* the address left by 3, we basically cannot use the top 4 bits
@@ -86,10 +86,13 @@
* conversion here. To leave room for further xscom address
* expansion, we only clear out the top byte
*
+ * For in-kernel use, we also support the real indirect bit, so
+ * we test for any of the top 5 bits
+ *
*/
- if (reg & (1ull << 59))
- reg = (reg & ~(0xffull << 56)) | (1ull << 63);
- return reg;
+ if (addr & (0x1full << 59))
+ addr = (addr & ~(0xffull << 56)) | (1ull << 63);
+ return addr;
}
static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
@@ -98,8 +101,8 @@
int64_t rc;
__be64 v;
- reg = opal_scom_unmangle(reg);
- rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v));
+ reg = opal_scom_unmangle(m->addr + reg);
+ rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v));
*value = be64_to_cpu(v);
return opal_xscom_err_xlate(rc);
}
@@ -109,8 +112,8 @@
struct opal_scom_map *m = map;
int64_t rc;
- reg = opal_scom_unmangle(reg);
- rc = opal_xscom_write(m->chip, m->addr + reg, value);
+ reg = opal_scom_unmangle(m->addr + reg);
+ rc = opal_xscom_write(m->chip, reg, value);
return opal_xscom_err_xlate(rc);
}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 7d6dcc6..3b2b4fb 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -21,6 +21,7 @@
#include <linux/irq.h>
#include <linux/io.h>
#include <linux/msi.h>
+#include <linux/memblock.h>
#include <asm/sections.h>
#include <asm/io.h>
@@ -460,9 +461,39 @@
return;
pe = &phb->ioda.pe_array[pdn->pe_number];
+ WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
}
+static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
+ struct pci_dev *pdev, u64 dma_mask)
+{
+ struct pci_dn *pdn = pci_get_pdn(pdev);
+ struct pnv_ioda_pe *pe;
+ uint64_t top;
+ bool bypass = false;
+
+ if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
+ return -ENODEV;;
+
+ pe = &phb->ioda.pe_array[pdn->pe_number];
+ if (pe->tce_bypass_enabled) {
+ top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1;
+ bypass = (dma_mask >= top);
+ }
+
+ if (bypass) {
+ dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n");
+ set_dma_ops(&pdev->dev, &dma_direct_ops);
+ set_dma_offset(&pdev->dev, pe->tce_bypass_base);
+ } else {
+ dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
+ set_dma_ops(&pdev->dev, &dma_iommu_ops);
+ set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+ }
+ return 0;
+}
+
static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
{
struct pci_dev *dev;
@@ -657,6 +688,56 @@
__free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs));
}
+static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
+{
+ struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
+ tce32_table);
+ uint16_t window_id = (pe->pe_number << 1 ) + 1;
+ int64_t rc;
+
+ pe_info(pe, "%sabling 64-bit DMA bypass\n", enable ? "En" : "Dis");
+ if (enable) {
+ phys_addr_t top = memblock_end_of_DRAM();
+
+ top = roundup_pow_of_two(top);
+ rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+ pe->pe_number,
+ window_id,
+ pe->tce_bypass_base,
+ top);
+ } else {
+ rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+ pe->pe_number,
+ window_id,
+ pe->tce_bypass_base,
+ 0);
+
+ /*
+ * We might want to reset the DMA ops of all devices on
+ * this PE. However in theory, that shouldn't be necessary
+ * as this is used for VFIO/KVM pass-through and the device
+ * hasn't yet been returned to its kernel driver
+ */
+ }
+ if (rc)
+ pe_err(pe, "OPAL error %lld configuring bypass window\n", rc);
+ else
+ pe->tce_bypass_enabled = enable;
+}
+
+static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
+ struct pnv_ioda_pe *pe)
+{
+ /* TVE #1 is selected by PCI address bit 59 */
+ pe->tce_bypass_base = 1ull << 59;
+
+ /* Install set_bypass callback for VFIO */
+ pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass;
+
+ /* Enable bypass by default */
+ pnv_pci_ioda2_set_bypass(&pe->tce32_table, true);
+}
+
static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
struct pnv_ioda_pe *pe)
{
@@ -727,6 +808,8 @@
else
pnv_ioda_setup_bus_dma(pe, pe->pbus);
+ /* Also create a bypass window */
+ pnv_pci_ioda2_setup_bypass_pe(phb, pe);
return;
fail:
if (pe->tce32_seg >= 0)
@@ -1286,6 +1369,7 @@
/* Setup TCEs */
phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
+ phb->dma_set_mask = pnv_pci_ioda_dma_set_mask;
/* Setup shutdown function for kexec */
phb->shutdown = pnv_pci_ioda_shutdown;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index b555ebc..8518817 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -134,57 +134,72 @@
pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n",
hose->global_number, common->version);
- pr_info(" brdgCtl: %08x\n", data->brdgCtl);
-
- pr_info(" portStatusReg: %08x\n", data->portStatusReg);
- pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus);
- pr_info(" busAgentStatus: %08x\n", data->busAgentStatus);
-
- pr_info(" deviceStatus: %08x\n", data->deviceStatus);
- pr_info(" slotStatus: %08x\n", data->slotStatus);
- pr_info(" linkStatus: %08x\n", data->linkStatus);
- pr_info(" devCmdStatus: %08x\n", data->devCmdStatus);
- pr_info(" devSecStatus: %08x\n", data->devSecStatus);
-
- pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus);
- pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus);
- pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus);
- pr_info(" tlpHdr1: %08x\n", data->tlpHdr1);
- pr_info(" tlpHdr2: %08x\n", data->tlpHdr2);
- pr_info(" tlpHdr3: %08x\n", data->tlpHdr3);
- pr_info(" tlpHdr4: %08x\n", data->tlpHdr4);
- pr_info(" sourceId: %08x\n", data->sourceId);
- pr_info(" errorClass: %016llx\n", data->errorClass);
- pr_info(" correlator: %016llx\n", data->correlator);
- pr_info(" p7iocPlssr: %016llx\n", data->p7iocPlssr);
- pr_info(" p7iocCsr: %016llx\n", data->p7iocCsr);
- pr_info(" lemFir: %016llx\n", data->lemFir);
- pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask);
- pr_info(" lemWOF: %016llx\n", data->lemWOF);
- pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus);
- pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus);
- pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0);
- pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1);
- pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus);
- pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
- pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0);
- pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1);
- pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus);
- pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
- pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0);
- pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1);
- pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus);
- pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
- pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0);
- pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1);
+ if (data->brdgCtl)
+ pr_info(" brdgCtl: %08x\n",
+ data->brdgCtl);
+ if (data->portStatusReg || data->rootCmplxStatus ||
+ data->busAgentStatus)
+ pr_info(" UtlSts: %08x %08x %08x\n",
+ data->portStatusReg, data->rootCmplxStatus,
+ data->busAgentStatus);
+ if (data->deviceStatus || data->slotStatus ||
+ data->linkStatus || data->devCmdStatus ||
+ data->devSecStatus)
+ pr_info(" RootSts: %08x %08x %08x %08x %08x\n",
+ data->deviceStatus, data->slotStatus,
+ data->linkStatus, data->devCmdStatus,
+ data->devSecStatus);
+ if (data->rootErrorStatus || data->uncorrErrorStatus ||
+ data->corrErrorStatus)
+ pr_info(" RootErrSts: %08x %08x %08x\n",
+ data->rootErrorStatus, data->uncorrErrorStatus,
+ data->corrErrorStatus);
+ if (data->tlpHdr1 || data->tlpHdr2 ||
+ data->tlpHdr3 || data->tlpHdr4)
+ pr_info(" RootErrLog: %08x %08x %08x %08x\n",
+ data->tlpHdr1, data->tlpHdr2,
+ data->tlpHdr3, data->tlpHdr4);
+ if (data->sourceId || data->errorClass ||
+ data->correlator)
+ pr_info(" RootErrLog1: %08x %016llx %016llx\n",
+ data->sourceId, data->errorClass,
+ data->correlator);
+ if (data->p7iocPlssr || data->p7iocCsr)
+ pr_info(" PhbSts: %016llx %016llx\n",
+ data->p7iocPlssr, data->p7iocCsr);
+ if (data->lemFir || data->lemErrorMask ||
+ data->lemWOF)
+ pr_info(" Lem: %016llx %016llx %016llx\n",
+ data->lemFir, data->lemErrorMask,
+ data->lemWOF);
+ if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+ data->phbErrorLog0 || data->phbErrorLog1)
+ pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n",
+ data->phbErrorStatus, data->phbFirstErrorStatus,
+ data->phbErrorLog0, data->phbErrorLog1);
+ if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+ data->mmioErrorLog0 || data->mmioErrorLog1)
+ pr_info(" OutErr: %016llx %016llx %016llx %016llx\n",
+ data->mmioErrorStatus, data->mmioFirstErrorStatus,
+ data->mmioErrorLog0, data->mmioErrorLog1);
+ if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+ data->dma0ErrorLog0 || data->dma0ErrorLog1)
+ pr_info(" InAErr: %016llx %016llx %016llx %016llx\n",
+ data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+ data->dma0ErrorLog0, data->dma0ErrorLog1);
+ if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+ data->dma1ErrorLog0 || data->dma1ErrorLog1)
+ pr_info(" InBErr: %016llx %016llx %016llx %016llx\n",
+ data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+ data->dma1ErrorLog0, data->dma1ErrorLog1);
for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
if ((data->pestA[i] >> 63) == 0 &&
(data->pestB[i] >> 63) == 0)
continue;
- pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]);
- pr_info(" PESTB: %016llx\n", data->pestB[i]);
+ pr_info(" PE[%3d] A/B: %016llx %016llx\n",
+ i, data->pestA[i], data->pestB[i]);
}
}
@@ -197,62 +212,77 @@
data = (struct OpalIoPhb3ErrorData*)common;
pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n",
hose->global_number, common->version);
-
- pr_info(" brdgCtl: %08x\n", data->brdgCtl);
-
- pr_info(" portStatusReg: %08x\n", data->portStatusReg);
- pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus);
- pr_info(" busAgentStatus: %08x\n", data->busAgentStatus);
-
- pr_info(" deviceStatus: %08x\n", data->deviceStatus);
- pr_info(" slotStatus: %08x\n", data->slotStatus);
- pr_info(" linkStatus: %08x\n", data->linkStatus);
- pr_info(" devCmdStatus: %08x\n", data->devCmdStatus);
- pr_info(" devSecStatus: %08x\n", data->devSecStatus);
-
- pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus);
- pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus);
- pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus);
- pr_info(" tlpHdr1: %08x\n", data->tlpHdr1);
- pr_info(" tlpHdr2: %08x\n", data->tlpHdr2);
- pr_info(" tlpHdr3: %08x\n", data->tlpHdr3);
- pr_info(" tlpHdr4: %08x\n", data->tlpHdr4);
- pr_info(" sourceId: %08x\n", data->sourceId);
- pr_info(" errorClass: %016llx\n", data->errorClass);
- pr_info(" correlator: %016llx\n", data->correlator);
-
- pr_info(" nFir: %016llx\n", data->nFir);
- pr_info(" nFirMask: %016llx\n", data->nFirMask);
- pr_info(" nFirWOF: %016llx\n", data->nFirWOF);
- pr_info(" PhbPlssr: %016llx\n", data->phbPlssr);
- pr_info(" PhbCsr: %016llx\n", data->phbCsr);
- pr_info(" lemFir: %016llx\n", data->lemFir);
- pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask);
- pr_info(" lemWOF: %016llx\n", data->lemWOF);
- pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus);
- pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus);
- pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0);
- pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1);
- pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus);
- pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
- pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0);
- pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1);
- pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus);
- pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
- pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0);
- pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1);
- pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus);
- pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
- pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0);
- pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1);
+ if (data->brdgCtl)
+ pr_info(" brdgCtl: %08x\n",
+ data->brdgCtl);
+ if (data->portStatusReg || data->rootCmplxStatus ||
+ data->busAgentStatus)
+ pr_info(" UtlSts: %08x %08x %08x\n",
+ data->portStatusReg, data->rootCmplxStatus,
+ data->busAgentStatus);
+ if (data->deviceStatus || data->slotStatus ||
+ data->linkStatus || data->devCmdStatus ||
+ data->devSecStatus)
+ pr_info(" RootSts: %08x %08x %08x %08x %08x\n",
+ data->deviceStatus, data->slotStatus,
+ data->linkStatus, data->devCmdStatus,
+ data->devSecStatus);
+ if (data->rootErrorStatus || data->uncorrErrorStatus ||
+ data->corrErrorStatus)
+ pr_info(" RootErrSts: %08x %08x %08x\n",
+ data->rootErrorStatus, data->uncorrErrorStatus,
+ data->corrErrorStatus);
+ if (data->tlpHdr1 || data->tlpHdr2 ||
+ data->tlpHdr3 || data->tlpHdr4)
+ pr_info(" RootErrLog: %08x %08x %08x %08x\n",
+ data->tlpHdr1, data->tlpHdr2,
+ data->tlpHdr3, data->tlpHdr4);
+ if (data->sourceId || data->errorClass ||
+ data->correlator)
+ pr_info(" RootErrLog1: %08x %016llx %016llx\n",
+ data->sourceId, data->errorClass,
+ data->correlator);
+ if (data->nFir || data->nFirMask ||
+ data->nFirWOF)
+ pr_info(" nFir: %016llx %016llx %016llx\n",
+ data->nFir, data->nFirMask,
+ data->nFirWOF);
+ if (data->phbPlssr || data->phbCsr)
+ pr_info(" PhbSts: %016llx %016llx\n",
+ data->phbPlssr, data->phbCsr);
+ if (data->lemFir || data->lemErrorMask ||
+ data->lemWOF)
+ pr_info(" Lem: %016llx %016llx %016llx\n",
+ data->lemFir, data->lemErrorMask,
+ data->lemWOF);
+ if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+ data->phbErrorLog0 || data->phbErrorLog1)
+ pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n",
+ data->phbErrorStatus, data->phbFirstErrorStatus,
+ data->phbErrorLog0, data->phbErrorLog1);
+ if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+ data->mmioErrorLog0 || data->mmioErrorLog1)
+ pr_info(" OutErr: %016llx %016llx %016llx %016llx\n",
+ data->mmioErrorStatus, data->mmioFirstErrorStatus,
+ data->mmioErrorLog0, data->mmioErrorLog1);
+ if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+ data->dma0ErrorLog0 || data->dma0ErrorLog1)
+ pr_info(" InAErr: %016llx %016llx %016llx %016llx\n",
+ data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+ data->dma0ErrorLog0, data->dma0ErrorLog1);
+ if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+ data->dma1ErrorLog0 || data->dma1ErrorLog1)
+ pr_info(" InBErr: %016llx %016llx %016llx %016llx\n",
+ data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+ data->dma1ErrorLog0, data->dma1ErrorLog1);
for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
if ((data->pestA[i] >> 63) == 0 &&
(data->pestB[i] >> 63) == 0)
continue;
- pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]);
- pr_info(" PESTB: %016llx\n", data->pestB[i]);
+ pr_info(" PE[%3d] A/B: %016llx %016llx\n",
+ i, data->pestA[i], data->pestB[i]);
}
}
@@ -634,6 +664,16 @@
pnv_pci_dma_fallback_setup(hose, pdev);
}
+int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+ struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+ struct pnv_phb *phb = hose->private_data;
+
+ if (phb && phb->dma_set_mask)
+ return phb->dma_set_mask(phb, pdev, dma_mask);
+ return __dma_set_mask(&pdev->dev, dma_mask);
+}
+
void pnv_pci_shutdown(void)
{
struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 13f1942..cde1694 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -54,7 +54,9 @@
struct iommu_table tce32_table;
phys_addr_t tce_inval_reg_phys;
- /* XXX TODO: Add support for additional 64-bit iommus */
+ /* 64-bit TCE bypass region */
+ bool tce_bypass_enabled;
+ uint64_t tce_bypass_base;
/* MSIs. MVE index is identical for for 32 and 64 bit MSI
* and -1 if not supported. (It's actually identical to the
@@ -113,6 +115,8 @@
unsigned int hwirq, unsigned int virq,
unsigned int is_64, struct msi_msg *msg);
void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
+ int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev,
+ u64 dma_mask);
void (*fixup_phb)(struct pci_controller *hose);
u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
void (*shutdown)(struct pnv_phb *phb);
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index de6819b..0051e10 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -7,12 +7,20 @@
static inline void pnv_smp_init(void) { }
#endif
+struct pci_dev;
+
#ifdef CONFIG_PCI
extern void pnv_pci_init(void);
extern void pnv_pci_shutdown(void);
+extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask);
#else
static inline void pnv_pci_init(void) { }
static inline void pnv_pci_shutdown(void) { }
+
+static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+ return -ENODEV;
+}
#endif
extern void pnv_lpc_init(void);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 21166f6..110f4fb 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -27,6 +27,7 @@
#include <linux/interrupt.h>
#include <linux/bug.h>
#include <linux/cpuidle.h>
+#include <linux/pci.h>
#include <asm/machdep.h>
#include <asm/firmware.h>
@@ -141,6 +142,13 @@
{
}
+static int pnv_dma_set_mask(struct device *dev, u64 dma_mask)
+{
+ if (dev_is_pci(dev))
+ return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask);
+ return __dma_set_mask(dev, dma_mask);
+}
+
static void pnv_shutdown(void)
{
/* Let the PCI code clear up IODA tables */
@@ -238,6 +246,7 @@
.machine_shutdown = pnv_shutdown,
.power_save = powernv_idle,
.calibrate_decr = generic_calibrate_decr,
+ .dma_set_mask = pnv_dma_set_mask,
#ifdef CONFIG_KEXEC
.kexec_cpu_down = pnv_kexec_cpu_down,
#endif
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 37300f6..80b1d57 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -20,6 +20,7 @@
select PPC_DOORBELL
select HAVE_CONTEXT_TRACKING
select HOTPLUG_CPU if SMP
+ select ARCH_RANDOM
default y
config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 9ef3cc8..8a8f047 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -265,7 +265,7 @@
enable = 1;
if (enable) {
- eeh_subsystem_enabled = 1;
+ eeh_set_enable(true);
eeh_add_to_parent_pe(edev);
pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n",
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 82789e7..0ea99e3 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -35,12 +35,7 @@
#include "offline_states.h"
/* This version can't take the spinlock, because it never returns */
-static struct rtas_args rtas_stop_self_args = {
- .token = RTAS_UNKNOWN_SERVICE,
- .nargs = 0,
- .nret = 1,
- .rets = &rtas_stop_self_args.args[0],
-};
+static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE;
static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) =
CPU_STATE_OFFLINE;
@@ -93,15 +88,20 @@
static void rtas_stop_self(void)
{
- struct rtas_args *args = &rtas_stop_self_args;
+ struct rtas_args args = {
+ .token = cpu_to_be32(rtas_stop_self_token),
+ .nargs = 0,
+ .nret = 1,
+ .rets = &args.args[0],
+ };
local_irq_disable();
- BUG_ON(args->token == RTAS_UNKNOWN_SERVICE);
+ BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE);
printk("cpu %u (hwid %u) Ready to die...\n",
smp_processor_id(), hard_smp_processor_id());
- enter_rtas(__pa(args));
+ enter_rtas(__pa(&args));
panic("Alas, I survived.\n");
}
@@ -392,10 +392,10 @@
}
}
- rtas_stop_self_args.token = rtas_token("stop-self");
+ rtas_stop_self_token = rtas_token("stop-self");
qcss_tok = rtas_token("query-cpu-stopped-state");
- if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE ||
+ if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE ||
qcss_tok == RTAS_UNKNOWN_SERVICE) {
printk(KERN_INFO "CPU Hotplug not supported by firmware "
"- disabling.\n");
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 70670a2..c413ec1 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -113,7 +113,8 @@
{
struct device_node *dn, *pdn;
struct pci_bus *bus;
- const __be32 *pcie_link_speed_stats;
+ u32 pcie_link_speed_stats[2];
+ int rc;
bus = bridge->bus;
@@ -122,38 +123,45 @@
return 0;
for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) {
- pcie_link_speed_stats = of_get_property(pdn,
- "ibm,pcie-link-speed-stats", NULL);
- if (pcie_link_speed_stats)
+ rc = of_property_read_u32_array(pdn,
+ "ibm,pcie-link-speed-stats",
+ &pcie_link_speed_stats[0], 2);
+ if (!rc)
break;
}
of_node_put(pdn);
- if (!pcie_link_speed_stats) {
+ if (rc) {
pr_err("no ibm,pcie-link-speed-stats property\n");
return 0;
}
- switch (be32_to_cpup(pcie_link_speed_stats)) {
+ switch (pcie_link_speed_stats[0]) {
case 0x01:
bus->max_bus_speed = PCIE_SPEED_2_5GT;
break;
case 0x02:
bus->max_bus_speed = PCIE_SPEED_5_0GT;
break;
+ case 0x04:
+ bus->max_bus_speed = PCIE_SPEED_8_0GT;
+ break;
default:
bus->max_bus_speed = PCI_SPEED_UNKNOWN;
break;
}
- switch (be32_to_cpup(pcie_link_speed_stats)) {
+ switch (pcie_link_speed_stats[1]) {
case 0x01:
bus->cur_bus_speed = PCIE_SPEED_2_5GT;
break;
case 0x02:
bus->cur_bus_speed = PCIE_SPEED_5_0GT;
break;
+ case 0x04:
+ bus->cur_bus_speed = PCIE_SPEED_8_0GT;
+ break;
default:
bus->cur_bus_speed = PCI_SPEED_UNKNOWN;
break;
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 8e639d7..972df0ff 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -430,8 +430,7 @@
{
long rc;
- if (firmware_has_feature(FW_FEATURE_SET_MODE) &&
- (image->type != KEXEC_TYPE_CRASH)) {
+ if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
rc = pSeries_disable_reloc_on_exc();
if (rc != H_SUCCESS)
pr_warning("Warning: Failed to disable relocation on "
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 0e166ed..8209744 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -886,25 +886,25 @@
/* Default: read HW settings */
if (flow_type == IRQ_TYPE_DEFAULT) {
- switch(vold & (MPIC_INFO(VECPRI_POLARITY_MASK) |
- MPIC_INFO(VECPRI_SENSE_MASK))) {
- case MPIC_INFO(VECPRI_SENSE_EDGE) |
- MPIC_INFO(VECPRI_POLARITY_POSITIVE):
- flow_type = IRQ_TYPE_EDGE_RISING;
- break;
- case MPIC_INFO(VECPRI_SENSE_EDGE) |
- MPIC_INFO(VECPRI_POLARITY_NEGATIVE):
- flow_type = IRQ_TYPE_EDGE_FALLING;
- break;
- case MPIC_INFO(VECPRI_SENSE_LEVEL) |
- MPIC_INFO(VECPRI_POLARITY_POSITIVE):
- flow_type = IRQ_TYPE_LEVEL_HIGH;
- break;
- case MPIC_INFO(VECPRI_SENSE_LEVEL) |
- MPIC_INFO(VECPRI_POLARITY_NEGATIVE):
- flow_type = IRQ_TYPE_LEVEL_LOW;
- break;
- }
+ int vold_ps;
+
+ vold_ps = vold & (MPIC_INFO(VECPRI_POLARITY_MASK) |
+ MPIC_INFO(VECPRI_SENSE_MASK));
+
+ if (vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) |
+ MPIC_INFO(VECPRI_POLARITY_POSITIVE)))
+ flow_type = IRQ_TYPE_EDGE_RISING;
+ else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) |
+ MPIC_INFO(VECPRI_POLARITY_NEGATIVE)))
+ flow_type = IRQ_TYPE_EDGE_FALLING;
+ else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) |
+ MPIC_INFO(VECPRI_POLARITY_POSITIVE)))
+ flow_type = IRQ_TYPE_LEVEL_HIGH;
+ else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) |
+ MPIC_INFO(VECPRI_POLARITY_NEGATIVE)))
+ flow_type = IRQ_TYPE_LEVEL_LOW;
+ else
+ WARN_ONCE(1, "mpic: unknown IRQ type %d\n", vold);
}
/* Apply to irq desc */
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index a90731b..b079098 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -309,16 +309,23 @@
if (xmon_speaker == me)
return;
+
for (;;) {
- if (xmon_speaker == 0) {
- last_speaker = cmpxchg(&xmon_speaker, 0, me);
- if (last_speaker == 0)
- return;
- }
- timeout = 10000000;
+ last_speaker = cmpxchg(&xmon_speaker, 0, me);
+ if (last_speaker == 0)
+ return;
+
+ /*
+ * Wait a full second for the lock, we might be on a slow
+ * console, but check every 100us.
+ */
+ timeout = 10000;
while (xmon_speaker == last_speaker) {
- if (--timeout > 0)
+ if (--timeout > 0) {
+ udelay(100);
continue;
+ }
+
/* hostile takeover */
prev = cmpxchg(&xmon_speaker, last_speaker, me);
if (prev == last_speaker)
@@ -397,7 +404,6 @@
}
xmon_fault_jmp[cpu] = recurse_jmp;
- cpumask_set_cpu(cpu, &cpus_in_xmon);
bp = NULL;
if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT))
@@ -419,6 +425,8 @@
release_output_lock();
}
+ cpumask_set_cpu(cpu, &cpus_in_xmon);
+
waiting:
secondary = 1;
while (secondary && !xmon_gate) {
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 4c4a1ce..47c8630 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -529,6 +529,7 @@
{
int rc;
+ init_virt_timer(&appldata_timer);
appldata_timer.function = appldata_timer_function;
appldata_timer.data = (unsigned long) &appldata_work;
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 59c8efc..0248949 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -1421,5 +1421,5 @@
ENTRY(sys_sched_getattr_wrapper)
lgfr %r2,%r2 # pid_t
llgtr %r3,%r3 # const char __user *
- llgfr %r3,%r3 # unsigned int
+ llgfr %r4,%r4 # unsigned int
jg sys_sched_getattr
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index b9e25ae..d7c0050 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -59,7 +59,7 @@
.quad 0 # cr12: tracing off
.quad 0 # cr13: home space segment table
.quad 0xc0000000 # cr14: machine check handling off
- .quad 0 # cr15: linkage stack operations
+ .quad .Llinkage_stack # cr15: linkage stack operations
.Lpcmsk:.quad 0x0000000180000000
.L4malign:.quad 0xffffffffffc00000
.Lscan2g:.quad 0x80000000 + 0x20000 - 8 # 2GB + 128K - 8
@@ -67,12 +67,15 @@
.Lparmaddr:
.quad PARMAREA
.align 64
-.Lduct: .long 0,0,0,0,.Lduald,0,0,0
+.Lduct: .long 0,.Laste,.Laste,0,.Lduald,0,0,0
.long 0,0,0,0,0,0,0,0
+.Laste: .quad 0,0xffffffffffffffff,0,0,0,0,0,0
.align 128
.Lduald:.rept 8
.long 0x80000000,0,0,0 # invalid access-list entries
.endr
+.Llinkage_stack:
+ .long 0,0,0x89000000,0,0,0,0x8a000000,0
ENTRY(_ehead)
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index a90d45e..27c50f4 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -12,6 +12,8 @@
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/init.h>
+#include <asm/setup.h>
+#include <asm/ipl.h>
#define ESSA_SET_STABLE 1
#define ESSA_SET_UNUSED 2
@@ -41,6 +43,14 @@
if (!cmma_flag)
return;
+ /*
+ * Disable CMM for dump, otherwise the tprot based memory
+ * detection can fail because of unstable pages.
+ */
+ if (OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP) {
+ cmma_flag = 0;
+ return;
+ }
asm volatile(
" .insn rrf,0xb9ab0000,%1,%1,0,0\n"
"0: la %0,0\n"
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 708d60e..9c36dc3 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -737,10 +737,10 @@
/* icm %r5,3,<d(type)>(%r1) */
EMIT4_DISP(0xbf531000, offsetof(struct net_device, type));
break;
- case BPF_S_ANC_RXHASH: /* A = skb->rxhash */
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
- /* l %r5,<d(rxhash)>(%r2) */
- EMIT4_DISP(0x58502000, offsetof(struct sk_buff, rxhash));
+ case BPF_S_ANC_RXHASH: /* A = skb->hash */
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+ /* l %r5,<d(hash)>(%r2) */
+ EMIT4_DISP(0x58502000, offsetof(struct sk_buff, hash));
break;
case BPF_S_ANC_VLAN_TAG:
case BPF_S_ANC_VLAN_TAG_PRESENT:
@@ -877,6 +877,7 @@
if (jit.start) {
set_memory_ro((unsigned long)header, header->pages);
fp->bpf_func = (void *) jit.start;
+ fp->jited = 1;
}
out:
kfree(addrs);
@@ -887,10 +888,12 @@
unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
struct bpf_binary_header *header = (void *)addr;
- if (fp->bpf_func == sk_run_filter)
+ if (!fp->jited)
goto free_filter;
+
set_memory_rw(addr, header->pages);
module_free(NULL, header);
+
free_filter:
kfree(fp);
}
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 60c11a6..f91c031 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -206,11 +206,13 @@
zdev->dma_table = NULL;
}
-static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev, unsigned long start,
- int size)
+static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev,
+ unsigned long start, int size)
{
- unsigned long boundary_size = 0x1000000;
+ unsigned long boundary_size;
+ boundary_size = ALIGN(dma_get_seg_boundary(&zdev->pdev->dev) + 1,
+ PAGE_SIZE) >> PAGE_SHIFT;
return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
start, size, 0, boundary_size, 0);
}
diff --git a/arch/sh/include/cpu-sh2/cpu/cache.h b/arch/sh/include/cpu-sh2/cpu/cache.h
index 673515b..aa1b2b9 100644
--- a/arch/sh/include/cpu-sh2/cpu/cache.h
+++ b/arch/sh/include/cpu-sh2/cpu/cache.h
@@ -18,7 +18,7 @@
#define SH_CACHE_ASSOC 8
#if defined(CONFIG_CPU_SUBTYPE_SH7619)
-#define CCR 0xffffffec
+#define SH_CCR 0xffffffec
#define CCR_CACHE_CE 0x01 /* Cache enable */
#define CCR_CACHE_WT 0x02 /* CCR[bit1=1,bit2=1] */
diff --git a/arch/sh/include/cpu-sh2a/cpu/cache.h b/arch/sh/include/cpu-sh2a/cpu/cache.h
index defb0ba..b27ce92 100644
--- a/arch/sh/include/cpu-sh2a/cpu/cache.h
+++ b/arch/sh/include/cpu-sh2a/cpu/cache.h
@@ -17,8 +17,8 @@
#define SH_CACHE_COMBINED 4
#define SH_CACHE_ASSOC 8
-#define CCR 0xfffc1000 /* CCR1 */
-#define CCR2 0xfffc1004
+#define SH_CCR 0xfffc1000 /* CCR1 */
+#define SH_CCR2 0xfffc1004
/*
* Most of the SH-2A CCR1 definitions resemble the SH-4 ones. All others not
diff --git a/arch/sh/include/cpu-sh3/cpu/cache.h b/arch/sh/include/cpu-sh3/cpu/cache.h
index bee2d81..29700fd 100644
--- a/arch/sh/include/cpu-sh3/cpu/cache.h
+++ b/arch/sh/include/cpu-sh3/cpu/cache.h
@@ -17,7 +17,7 @@
#define SH_CACHE_COMBINED 4
#define SH_CACHE_ASSOC 8
-#define CCR 0xffffffec /* Address of Cache Control Register */
+#define SH_CCR 0xffffffec /* Address of Cache Control Register */
#define CCR_CACHE_CE 0x01 /* Cache Enable */
#define CCR_CACHE_WT 0x02 /* Write-Through (for P0,U0,P3) (else writeback) */
diff --git a/arch/sh/include/cpu-sh4/cpu/cache.h b/arch/sh/include/cpu-sh4/cpu/cache.h
index 7bfb9e8..92c4cd1 100644
--- a/arch/sh/include/cpu-sh4/cpu/cache.h
+++ b/arch/sh/include/cpu-sh4/cpu/cache.h
@@ -17,7 +17,7 @@
#define SH_CACHE_COMBINED 4
#define SH_CACHE_ASSOC 8
-#define CCR 0xff00001c /* Address of Cache Control Register */
+#define SH_CCR 0xff00001c /* Address of Cache Control Register */
#define CCR_CACHE_OCE 0x0001 /* Operand Cache Enable */
#define CCR_CACHE_WT 0x0002 /* Write-Through (for P0,U0,P3) (else writeback)*/
#define CCR_CACHE_CB 0x0004 /* Copy-Back (for P1) (else writethrough) */
diff --git a/arch/sh/kernel/cpu/init.c b/arch/sh/kernel/cpu/init.c
index ecf83cd..0d7360d 100644
--- a/arch/sh/kernel/cpu/init.c
+++ b/arch/sh/kernel/cpu/init.c
@@ -112,7 +112,7 @@
unsigned long ccr, flags;
jump_to_uncached();
- ccr = __raw_readl(CCR);
+ ccr = __raw_readl(SH_CCR);
/*
* At this point we don't know whether the cache is enabled or not - a
@@ -189,7 +189,7 @@
l2_cache_init();
- __raw_writel(flags, CCR);
+ __raw_writel(flags, SH_CCR);
back_to_cached();
}
#else
diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c
index 1157251..777e50f 100644
--- a/arch/sh/mm/cache-debugfs.c
+++ b/arch/sh/mm/cache-debugfs.c
@@ -36,7 +36,7 @@
*/
jump_to_uncached();
- ccr = __raw_readl(CCR);
+ ccr = __raw_readl(SH_CCR);
if ((ccr & CCR_CACHE_ENABLE) == 0) {
back_to_cached();
diff --git a/arch/sh/mm/cache-sh2.c b/arch/sh/mm/cache-sh2.c
index defcf71..a74259f 100644
--- a/arch/sh/mm/cache-sh2.c
+++ b/arch/sh/mm/cache-sh2.c
@@ -63,9 +63,9 @@
local_irq_save(flags);
jump_to_uncached();
- ccr = __raw_readl(CCR);
+ ccr = __raw_readl(SH_CCR);
ccr |= CCR_CACHE_INVALIDATE;
- __raw_writel(ccr, CCR);
+ __raw_writel(ccr, SH_CCR);
back_to_cached();
local_irq_restore(flags);
diff --git a/arch/sh/mm/cache-sh2a.c b/arch/sh/mm/cache-sh2a.c
index 949e2d3..ee87d08 100644
--- a/arch/sh/mm/cache-sh2a.c
+++ b/arch/sh/mm/cache-sh2a.c
@@ -134,7 +134,8 @@
/* If there are too many pages then just blow the cache */
if (((end - begin) >> PAGE_SHIFT) >= MAX_OCACHE_PAGES) {
- __raw_writel(__raw_readl(CCR) | CCR_OCACHE_INVALIDATE, CCR);
+ __raw_writel(__raw_readl(SH_CCR) | CCR_OCACHE_INVALIDATE,
+ SH_CCR);
} else {
for (v = begin; v < end; v += L1_CACHE_BYTES)
sh2a_invalidate_line(CACHE_OC_ADDRESS_ARRAY, v);
@@ -167,7 +168,8 @@
/* I-Cache invalidate */
/* If there are too many pages then just blow the cache */
if (((end - start) >> PAGE_SHIFT) >= MAX_ICACHE_PAGES) {
- __raw_writel(__raw_readl(CCR) | CCR_ICACHE_INVALIDATE, CCR);
+ __raw_writel(__raw_readl(SH_CCR) | CCR_ICACHE_INVALIDATE,
+ SH_CCR);
} else {
for (v = start; v < end; v += L1_CACHE_BYTES)
sh2a_invalidate_line(CACHE_IC_ADDRESS_ARRAY, v);
diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c
index 0e52928..51d8f7f 100644
--- a/arch/sh/mm/cache-sh4.c
+++ b/arch/sh/mm/cache-sh4.c
@@ -133,9 +133,9 @@
jump_to_uncached();
/* Flush I-cache */
- ccr = __raw_readl(CCR);
+ ccr = __raw_readl(SH_CCR);
ccr |= CCR_CACHE_ICI;
- __raw_writel(ccr, CCR);
+ __raw_writel(ccr, SH_CCR);
/*
* back_to_cached() will take care of the barrier for us, don't add
diff --git a/arch/sh/mm/cache-shx3.c b/arch/sh/mm/cache-shx3.c
index c0adbee..24c58b7 100644
--- a/arch/sh/mm/cache-shx3.c
+++ b/arch/sh/mm/cache-shx3.c
@@ -19,7 +19,7 @@
{
unsigned int ccr;
- ccr = __raw_readl(CCR);
+ ccr = __raw_readl(SH_CCR);
/*
* If we've got cache aliases, resolve them in hardware.
@@ -40,5 +40,5 @@
ccr |= CCR_CACHE_IBE;
#endif
- writel_uncached(ccr, CCR);
+ writel_uncached(ccr, SH_CCR);
}
diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c
index 616966a..097c2cd 100644
--- a/arch/sh/mm/cache.c
+++ b/arch/sh/mm/cache.c
@@ -285,8 +285,8 @@
{
unsigned int cache_disabled = 0;
-#ifdef CCR
- cache_disabled = !(__raw_readl(CCR) & CCR_CACHE_ENABLE);
+#ifdef SH_CCR
+ cache_disabled = !(__raw_readl(SH_CCR) & CCR_CACHE_ENABLE);
#endif
compute_alias(&boot_cpu_data.icache);
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index c51efdc..7d8b7e9 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -27,7 +27,7 @@
select RTC_DRV_M48T59
select HAVE_DMA_ATTRS
select HAVE_DMA_API_DEBUG
- select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_JUMP_LABEL if SPARC64
select GENERIC_IRQ_SHOW
select ARCH_WANT_IPC_PARSE_VERSION
select GENERIC_PCI_IOMAP
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 32a280e..d7b4967 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -58,9 +58,12 @@
{
if (tlb_type != hypervisor) {
touch_nmi_watchdog();
+ local_irq_enable();
} else {
unsigned long pstate;
+ local_irq_enable();
+
/* The sun4v sleeping code requires that we have PSTATE.IE cleared over
* the cpu sleep hypervisor call.
*/
@@ -82,7 +85,6 @@
: "=&r" (pstate)
: "i" (PSTATE_IE));
}
- local_irq_enable();
}
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index 87729ff..33a17e7 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -189,7 +189,8 @@
mov %i0, %l5 ! IEU1
5: call %l7 ! CTI Group brk forced
srl %i5, 0, %o5 ! IEU1
- ba,a,pt %xcc, 3f
+ ba,pt %xcc, 3f
+ sra %o0, 0, %o0
/* Linux native system calls enter here... */
.align 32
@@ -217,7 +218,6 @@
3: stx %o0, [%sp + PTREGS_OFF + PT_V9_I0]
ret_sys_call:
ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %g3
- sra %o0, 0, %o0
mov %ulo(TSTATE_XCARRY | TSTATE_ICARRY), %g2
sllx %g2, 32, %g2
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index 869023a..cfbe53c 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -14,6 +14,7 @@
#include <linux/pagemap.h>
#include <linux/vmalloc.h>
#include <linux/kdebug.h>
+#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/log2.h>
@@ -62,6 +63,7 @@
static pgd_t *srmmu_swapper_pg_dir;
const struct sparc32_cachetlb_ops *sparc32_cachetlb_ops;
+EXPORT_SYMBOL(sparc32_cachetlb_ops);
#ifdef CONFIG_SMP
const struct sparc32_cachetlb_ops *local_ops;
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 3b3a360..f5d506f 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -273,7 +273,7 @@
prom_halt();
}
- for (i = 0; i < 8; i++) {
+ for (i = 0; i < ARRAY_SIZE(tsb_cache_names); i++) {
unsigned long size = 8192 << i;
const char *name = tsb_cache_names[i];
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index 01fe994..a82c6b2 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -618,7 +618,7 @@
emit_load16(r_A, struct net_device, type, r_A);
break;
case BPF_S_ANC_RXHASH:
- emit_skb_load32(rxhash, r_A);
+ emit_skb_load32(hash, r_A);
break;
case BPF_S_ANC_VLAN_TAG:
case BPF_S_ANC_VLAN_TAG_PRESENT:
@@ -809,6 +809,7 @@
if (image) {
bpf_flush_icache(image, image + proglen);
fp->bpf_func = (void *)image;
+ fp->jited = 1;
}
out:
kfree(addrs);
@@ -817,7 +818,7 @@
void bpf_jit_free(struct sk_filter *fp)
{
- if (fp->bpf_func != sk_run_filter)
+ if (fp->jited)
module_free(NULL, fp->bpf_func);
kfree(fp);
}
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 39f1862..7d26d9c 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -240,7 +240,7 @@
spin_unlock_irqrestore(&lp->lock, flags);
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index c026cca..f3aaf23 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -341,10 +341,6 @@
def_bool y
depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
-config X86_OOSTORE
- def_bool y
- depends on (MWINCHIP3D || MWINCHIPC6) && MTRR
-
#
# P6_NOPs are a relatively minor optimization that require a family >=
# 6 processor, except that it is broken on certain VIA chips.
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 90a21f4..4dbf967 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -111,7 +111,7 @@
};
#define MEM_AVOID_MAX 5
-struct mem_vector mem_avoid[MEM_AVOID_MAX];
+static struct mem_vector mem_avoid[MEM_AVOID_MAX];
static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
{
@@ -180,7 +180,7 @@
}
/* Does this memory vector overlap a known avoided area? */
-bool mem_avoid_overlap(struct mem_vector *img)
+static bool mem_avoid_overlap(struct mem_vector *img)
{
int i;
@@ -192,8 +192,9 @@
return false;
}
-unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / CONFIG_PHYSICAL_ALIGN];
-unsigned long slot_max = 0;
+static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+ CONFIG_PHYSICAL_ALIGN];
+static unsigned long slot_max;
static void slots_append(unsigned long addr)
{
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 04a4890..69bbb48 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -85,11 +85,7 @@
#else
# define smp_rmb() barrier()
#endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() wmb()
-#else
-# define smp_wmb() barrier()
-#endif
+#define smp_wmb() barrier()
#define smp_read_barrier_depends() read_barrier_depends()
#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
#else /* !SMP */
@@ -100,7 +96,7 @@
#define set_mb(var, value) do { var = value; barrier(); } while (0)
#endif /* SMP */
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+#if defined(CONFIG_X86_PPRO_FENCE)
/*
* For either of these options x86 doesn't have a strong TSO memory
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3b978c4..acd86c8 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -132,6 +132,9 @@
extern void efi_sync_low_kernel_mappings(void);
extern void efi_setup_page_tables(void);
extern void __init old_map_region(efi_memory_desc_t *md);
+extern void __init runtime_code_page_mkexec(void);
+extern void __init efi_runtime_mkexec(void);
+extern void __init efi_apply_memmap_quirks(void);
struct efi_setup_data {
u64 fw_vendor;
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 34f69cb..91d9c69 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -237,7 +237,7 @@
static inline void flush_write_buffers(void)
{
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+#if defined(CONFIG_X86_PPRO_FENCE)
asm volatile("lock; addl $0,0(%%esp)": : :"memory");
#endif
}
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index bf156de..0f62f54 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -26,10 +26,9 @@
# define LOCK_PTR_REG "D"
#endif
-#if defined(CONFIG_X86_32) && \
- (defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE))
+#if defined(CONFIG_X86_32) && (defined(CONFIG_X86_PPRO_FENCE))
/*
- * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
+ * On PPro SMP, we use a locked operation to unlock
* (PPro errata 66, 92)
*/
# define UNLOCK_LOCK_PREFIX LOCK_PREFIX
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index d35f24e..1306d11 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -119,9 +119,10 @@
extern const struct cpumask *cpu_coregroup_mask(int cpu);
-#ifdef ENABLE_TOPO_DEFINES
#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id)
#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
+
+#ifdef ENABLE_TOPO_DEFINES
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
#endif
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 57ae63c..94605c0 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -66,6 +66,6 @@
extern void tsc_restore_sched_clock_state(void);
/* MSR based TSC calibration for Intel Atom SoC platforms */
-int try_msr_calibrate_tsc(unsigned long *fast_calibrate);
+unsigned long try_msr_calibrate_tsc(void);
#endif /* _ASM_X86_TSC_H */
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index fd972a3..9fa8aa0 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -18,7 +18,6 @@
#include <linux/pci_ids.h>
#include <linux/pci.h>
#include <linux/bitops.h>
-#include <linux/ioport.h>
#include <linux/suspend.h>
#include <asm/e820.h>
#include <asm/io.h>
@@ -54,18 +53,6 @@
int fix_aperture __initdata = 1;
-static struct resource gart_resource = {
- .name = "GART",
- .flags = IORESOURCE_MEM,
-};
-
-static void __init insert_aperture_resource(u32 aper_base, u32 aper_size)
-{
- gart_resource.start = aper_base;
- gart_resource.end = aper_base + aper_size - 1;
- insert_resource(&iomem_resource, &gart_resource);
-}
-
/* This code runs before the PCI subsystem is initialized, so just
access the northbridge directly. */
@@ -96,7 +83,6 @@
memblock_reserve(addr, aper_size);
printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
aper_size >> 10, addr);
- insert_aperture_resource((u32)addr, aper_size);
register_nosave_region(addr >> PAGE_SHIFT,
(addr+aper_size) >> PAGE_SHIFT);
@@ -444,12 +430,8 @@
out:
if (!fix && !fallback_aper_force) {
- if (last_aper_base) {
- unsigned long n = (32 * 1024 * 1024) << last_aper_order;
-
- insert_aperture_resource((u32)last_aper_base, n);
+ if (last_aper_base)
return 1;
- }
return 0;
}
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 8779eda..d8fba5c 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -8,236 +8,6 @@
#include "cpu.h"
-#ifdef CONFIG_X86_OOSTORE
-
-static u32 power2(u32 x)
-{
- u32 s = 1;
-
- while (s <= x)
- s <<= 1;
-
- return s >>= 1;
-}
-
-
-/*
- * Set up an actual MCR
- */
-static void centaur_mcr_insert(int reg, u32 base, u32 size, int key)
-{
- u32 lo, hi;
-
- hi = base & ~0xFFF;
- lo = ~(size-1); /* Size is a power of 2 so this makes a mask */
- lo &= ~0xFFF; /* Remove the ctrl value bits */
- lo |= key; /* Attribute we wish to set */
- wrmsr(reg+MSR_IDT_MCR0, lo, hi);
- mtrr_centaur_report_mcr(reg, lo, hi); /* Tell the mtrr driver */
-}
-
-/*
- * Figure what we can cover with MCR's
- *
- * Shortcut: We know you can't put 4Gig of RAM on a winchip
- */
-static u32 ramtop(void)
-{
- u32 clip = 0xFFFFFFFFUL;
- u32 top = 0;
- int i;
-
- for (i = 0; i < e820.nr_map; i++) {
- unsigned long start, end;
-
- if (e820.map[i].addr > 0xFFFFFFFFUL)
- continue;
- /*
- * Don't MCR over reserved space. Ignore the ISA hole
- * we frob around that catastrophe already
- */
- if (e820.map[i].type == E820_RESERVED) {
- if (e820.map[i].addr >= 0x100000UL &&
- e820.map[i].addr < clip)
- clip = e820.map[i].addr;
- continue;
- }
- start = e820.map[i].addr;
- end = e820.map[i].addr + e820.map[i].size;
- if (start >= end)
- continue;
- if (end > top)
- top = end;
- }
- /*
- * Everything below 'top' should be RAM except for the ISA hole.
- * Because of the limited MCR's we want to map NV/ACPI into our
- * MCR range for gunk in RAM
- *
- * Clip might cause us to MCR insufficient RAM but that is an
- * acceptable failure mode and should only bite obscure boxes with
- * a VESA hole at 15Mb
- *
- * The second case Clip sometimes kicks in is when the EBDA is marked
- * as reserved. Again we fail safe with reasonable results
- */
- if (top > clip)
- top = clip;
-
- return top;
-}
-
-/*
- * Compute a set of MCR's to give maximum coverage
- */
-static int centaur_mcr_compute(int nr, int key)
-{
- u32 mem = ramtop();
- u32 root = power2(mem);
- u32 base = root;
- u32 top = root;
- u32 floor = 0;
- int ct = 0;
-
- while (ct < nr) {
- u32 fspace = 0;
- u32 high;
- u32 low;
-
- /*
- * Find the largest block we will fill going upwards
- */
- high = power2(mem-top);
-
- /*
- * Find the largest block we will fill going downwards
- */
- low = base/2;
-
- /*
- * Don't fill below 1Mb going downwards as there
- * is an ISA hole in the way.
- */
- if (base <= 1024*1024)
- low = 0;
-
- /*
- * See how much space we could cover by filling below
- * the ISA hole
- */
-
- if (floor == 0)
- fspace = 512*1024;
- else if (floor == 512*1024)
- fspace = 128*1024;
-
- /* And forget ROM space */
-
- /*
- * Now install the largest coverage we get
- */
- if (fspace > high && fspace > low) {
- centaur_mcr_insert(ct, floor, fspace, key);
- floor += fspace;
- } else if (high > low) {
- centaur_mcr_insert(ct, top, high, key);
- top += high;
- } else if (low > 0) {
- base -= low;
- centaur_mcr_insert(ct, base, low, key);
- } else
- break;
- ct++;
- }
- /*
- * We loaded ct values. We now need to set the mask. The caller
- * must do this bit.
- */
- return ct;
-}
-
-static void centaur_create_optimal_mcr(void)
-{
- int used;
- int i;
-
- /*
- * Allocate up to 6 mcrs to mark as much of ram as possible
- * as write combining and weak write ordered.
- *
- * To experiment with: Linux never uses stack operations for
- * mmio spaces so we could globally enable stack operation wc
- *
- * Load the registers with type 31 - full write combining, all
- * writes weakly ordered.
- */
- used = centaur_mcr_compute(6, 31);
-
- /*
- * Wipe unused MCRs
- */
- for (i = used; i < 8; i++)
- wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-static void winchip2_create_optimal_mcr(void)
-{
- u32 lo, hi;
- int used;
- int i;
-
- /*
- * Allocate up to 6 mcrs to mark as much of ram as possible
- * as write combining, weak store ordered.
- *
- * Load the registers with type 25
- * 8 - weak write ordering
- * 16 - weak read ordering
- * 1 - write combining
- */
- used = centaur_mcr_compute(6, 25);
-
- /*
- * Mark the registers we are using.
- */
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- for (i = 0; i < used; i++)
- lo |= 1<<(9+i);
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-
- /*
- * Wipe unused MCRs
- */
-
- for (i = used; i < 8; i++)
- wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-/*
- * Handle the MCR key on the Winchip 2.
- */
-static void winchip2_unprotect_mcr(void)
-{
- u32 lo, hi;
- u32 key;
-
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- lo &= ~0x1C0; /* blank bits 8-6 */
- key = (lo>>17) & 7;
- lo |= key<<6; /* replace with unlock key */
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-
-static void winchip2_protect_mcr(void)
-{
- u32 lo, hi;
-
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- lo &= ~0x1C0; /* blank bits 8-6 */
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-#endif /* CONFIG_X86_OOSTORE */
-
#define ACE_PRESENT (1 << 6)
#define ACE_ENABLED (1 << 7)
#define ACE_FCR (1 << 28) /* MSR_VIA_FCR */
@@ -362,20 +132,6 @@
fcr_clr = DPDC;
printk(KERN_NOTICE "Disabling bugged TSC.\n");
clear_cpu_cap(c, X86_FEATURE_TSC);
-#ifdef CONFIG_X86_OOSTORE
- centaur_create_optimal_mcr();
- /*
- * Enable:
- * write combining on non-stack, non-string
- * write combining on string, all types
- * weak write ordering
- *
- * The C6 original lacks weak read order
- *
- * Note 0x120 is write only on Winchip 1
- */
- wrmsr(MSR_IDT_MCR_CTRL, 0x01F0001F, 0);
-#endif
break;
case 8:
switch (c->x86_mask) {
@@ -392,40 +148,12 @@
fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
E2MMX|EAMD3D;
fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
- winchip2_unprotect_mcr();
- winchip2_create_optimal_mcr();
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- /*
- * Enable:
- * write combining on non-stack, non-string
- * write combining on string, all types
- * weak write ordering
- */
- lo |= 31;
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
- winchip2_protect_mcr();
-#endif
break;
case 9:
name = "3";
fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
E2MMX|EAMD3D;
fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
- winchip2_unprotect_mcr();
- winchip2_create_optimal_mcr();
- rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
- /*
- * Enable:
- * write combining on non-stack, non-string
- * write combining on string, all types
- * weak write ordering
- */
- lo |= 31;
- wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
- winchip2_protect_mcr();
-#endif
break;
default:
name = "??";
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 24b6fd1..8e28bf2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -284,8 +284,13 @@
raw_local_save_flags(eflags);
BUG_ON(eflags & X86_EFLAGS_AC);
- if (cpu_has(c, X86_FEATURE_SMAP))
+ if (cpu_has(c, X86_FEATURE_SMAP)) {
+#ifdef CONFIG_X86_SMAP
set_in_cr4(X86_CR4_SMAP);
+#else
+ clear_in_cr4(X86_CR4_SMAP);
+#endif
+ }
}
/*
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index b886451..79f9f84 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1192,6 +1192,9 @@
for (i = 0; i < cpuc->n_events; i++) {
if (event == cpuc->event_list[i]) {
+ if (i >= cpuc->n_events - cpuc->n_added)
+ --cpuc->n_added;
+
if (x86_pmu.put_event_constraints)
x86_pmu.put_event_constraints(cpuc, event);
@@ -1521,6 +1524,8 @@
pr_cont("%s PMU driver.\n", x86_pmu.name);
+ x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
+
for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next)
quirk->func();
@@ -1534,7 +1539,6 @@
__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
0, x86_pmu.num_counters, 0, 0);
- x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
if (x86_pmu.event_attrs)
@@ -1820,9 +1824,12 @@
if (ret)
return ret;
+ if (x86_pmu.attr_rdpmc_broken)
+ return -ENOTSUPP;
+
if (!!val != !!x86_pmu.attr_rdpmc) {
x86_pmu.attr_rdpmc = !!val;
- smp_call_function(change_rdpmc, (void *)val, 1);
+ on_each_cpu(change_rdpmc, (void *)val, 1);
}
return count;
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index c1a8618..4972c24 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -409,6 +409,7 @@
/*
* sysfs attrs
*/
+ int attr_rdpmc_broken;
int attr_rdpmc;
struct attribute **format_attrs;
struct attribute **event_attrs;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 0fa4f24..aa333d9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1361,10 +1361,8 @@
intel_pmu_disable_all();
handled = intel_pmu_drain_bts_buffer();
status = intel_pmu_get_status();
- if (!status) {
- intel_pmu_enable_all(0);
- return handled;
- }
+ if (!status)
+ goto done;
loops = 0;
again:
@@ -2310,10 +2308,7 @@
if (version > 1)
x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3);
- /*
- * v2 and above have a perf capabilities MSR
- */
- if (version > 1) {
+ if (boot_cpu_has(X86_FEATURE_PDCM)) {
u64 capabilities;
rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 29c2487..047f540 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -501,8 +501,11 @@
SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6),
SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6),
SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6),
SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
@@ -1178,10 +1181,15 @@
SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc),
SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10),
SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
@@ -3326,6 +3334,8 @@
if (!pmus)
return -ENOMEM;
+ type->pmus = pmus;
+
type->unconstrainted = (struct event_constraint)
__EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
0, type->num_counters, 0, 0);
@@ -3361,7 +3371,6 @@
}
type->pmu_group = &uncore_pmu_attr_group;
- type->pmus = pmus;
return 0;
fail:
uncore_type_exit(type);
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index b1e2fe1..7c1a0c0 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -231,31 +231,49 @@
};
+static __init void p6_pmu_rdpmc_quirk(void)
+{
+ if (boot_cpu_data.x86_mask < 9) {
+ /*
+ * PPro erratum 26; fixed in stepping 9 and above.
+ */
+ pr_warn("Userspace RDPMC support disabled due to a CPU erratum\n");
+ x86_pmu.attr_rdpmc_broken = 1;
+ x86_pmu.attr_rdpmc = 0;
+ }
+}
+
__init int p6_pmu_init(void)
{
+ x86_pmu = p6_pmu;
+
switch (boot_cpu_data.x86_model) {
- case 1:
- case 3: /* Pentium Pro */
- case 5:
- case 6: /* Pentium II */
- case 7:
- case 8:
- case 11: /* Pentium III */
- case 9:
- case 13:
- /* Pentium M */
+ case 1: /* Pentium Pro */
+ x86_add_quirk(p6_pmu_rdpmc_quirk);
break;
+
+ case 3: /* Pentium II - Klamath */
+ case 5: /* Pentium II - Deschutes */
+ case 6: /* Pentium II - Mendocino */
+ break;
+
+ case 7: /* Pentium III - Katmai */
+ case 8: /* Pentium III - Coppermine */
+ case 10: /* Pentium III Xeon */
+ case 11: /* Pentium III - Tualatin */
+ break;
+
+ case 9: /* Pentium M - Banias */
+ case 13: /* Pentium M - Dothan */
+ break;
+
default:
- pr_cont("unsupported p6 CPU model %d ",
- boot_cpu_data.x86_model);
+ pr_cont("unsupported p6 CPU model %d ", boot_cpu_data.x86_model);
return -ENODEV;
}
- x86_pmu = p6_pmu;
-
memcpy(hw_cache_event_ids, p6_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
-
return 0;
}
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index d4bdd25..e625319 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -77,8 +77,7 @@
return addr >= start && addr < end;
}
-static int
-do_ftrace_mod_code(unsigned long ip, const void *new_code)
+static unsigned long text_ip_addr(unsigned long ip)
{
/*
* On x86_64, kernel text mappings are mapped read-only with
@@ -91,7 +90,7 @@
if (within(ip, (unsigned long)_text, (unsigned long)_etext))
ip = (unsigned long)__va(__pa_symbol(ip));
- return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE);
+ return ip;
}
static const unsigned char *ftrace_nop_replace(void)
@@ -123,8 +122,10 @@
if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
return -EINVAL;
+ ip = text_ip_addr(ip);
+
/* replace the text with the new text */
- if (do_ftrace_mod_code(ip, new_code))
+ if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
return -EPERM;
sync_core();
@@ -221,37 +222,51 @@
return -EINVAL;
}
-int ftrace_update_ftrace_func(ftrace_func_t func)
+static unsigned long ftrace_update_func;
+
+static int update_ftrace_func(unsigned long ip, void *new)
{
- unsigned long ip = (unsigned long)(&ftrace_call);
- unsigned char old[MCOUNT_INSN_SIZE], *new;
+ unsigned char old[MCOUNT_INSN_SIZE];
int ret;
- memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
- new = ftrace_call_replace(ip, (unsigned long)func);
+ memcpy(old, (void *)ip, MCOUNT_INSN_SIZE);
+
+ ftrace_update_func = ip;
+ /* Make sure the breakpoints see the ftrace_update_func update */
+ smp_wmb();
/* See comment above by declaration of modifying_ftrace_code */
atomic_inc(&modifying_ftrace_code);
ret = ftrace_modify_code(ip, old, new);
+ atomic_dec(&modifying_ftrace_code);
+
+ return ret;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+ unsigned long ip = (unsigned long)(&ftrace_call);
+ unsigned char *new;
+ int ret;
+
+ new = ftrace_call_replace(ip, (unsigned long)func);
+ ret = update_ftrace_func(ip, new);
+
/* Also update the regs callback function */
if (!ret) {
ip = (unsigned long)(&ftrace_regs_call);
- memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE);
new = ftrace_call_replace(ip, (unsigned long)func);
- ret = ftrace_modify_code(ip, old, new);
+ ret = update_ftrace_func(ip, new);
}
- atomic_dec(&modifying_ftrace_code);
-
return ret;
}
static int is_ftrace_caller(unsigned long ip)
{
- if (ip == (unsigned long)(&ftrace_call) ||
- ip == (unsigned long)(&ftrace_regs_call))
+ if (ip == ftrace_update_func)
return 1;
return 0;
@@ -677,45 +692,41 @@
#ifdef CONFIG_DYNAMIC_FTRACE
extern void ftrace_graph_call(void);
-static int ftrace_mod_jmp(unsigned long ip,
- int old_offset, int new_offset)
+static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
{
- unsigned char code[MCOUNT_INSN_SIZE];
+ static union ftrace_code_union calc;
- if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
- return -EFAULT;
+ /* Jmp not a call (ignore the .e8) */
+ calc.e8 = 0xe9;
+ calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
- if (code[0] != 0xe9 || old_offset != *(int *)(&code[1]))
- return -EINVAL;
+ /*
+ * ftrace external locks synchronize the access to the static variable.
+ */
+ return calc.code;
+}
- *(int *)(&code[1]) = new_offset;
+static int ftrace_mod_jmp(unsigned long ip, void *func)
+{
+ unsigned char *new;
- if (do_ftrace_mod_code(ip, &code))
- return -EPERM;
+ new = ftrace_jmp_replace(ip, (unsigned long)func);
- return 0;
+ return update_ftrace_func(ip, new);
}
int ftrace_enable_ftrace_graph_caller(void)
{
unsigned long ip = (unsigned long)(&ftrace_graph_call);
- int old_offset, new_offset;
- old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
- new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
-
- return ftrace_mod_jmp(ip, old_offset, new_offset);
+ return ftrace_mod_jmp(ip, &ftrace_graph_caller);
}
int ftrace_disable_ftrace_graph_caller(void)
{
unsigned long ip = (unsigned long)(&ftrace_graph_call);
- int old_offset, new_offset;
- old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
- new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
-
- return ftrace_mod_jmp(ip, old_offset, new_offset);
+ return ftrace_mod_jmp(ip, &ftrace_stub);
}
#endif /* !CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 81ba276..f36bd42 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -544,6 +544,10 @@
/* This is global to keep gas from relaxing the jumps */
ENTRY(early_idt_handler)
cld
+
+ cmpl $2,(%esp) # X86_TRAP_NMI
+ je is_nmi # Ignore NMI
+
cmpl $2,%ss:early_recursion_flag
je hlt_loop
incl %ss:early_recursion_flag
@@ -594,8 +598,9 @@
pop %edx
pop %ecx
pop %eax
- addl $8,%esp /* drop vector number and error code */
decl %ss:early_recursion_flag
+is_nmi:
+ addl $8,%esp /* drop vector number and error code */
iret
ENDPROC(early_idt_handler)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e1aabdb..a468c0a 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -343,6 +343,9 @@
ENTRY(early_idt_handler)
cld
+ cmpl $2,(%rsp) # X86_TRAP_NMI
+ je is_nmi # Ignore NMI
+
cmpl $2,early_recursion_flag(%rip)
jz 1f
incl early_recursion_flag(%rip)
@@ -405,8 +408,9 @@
popq %rdx
popq %rcx
popq %rax
- addq $16,%rsp # drop vector number and error code
decl early_recursion_flag(%rip)
+is_nmi:
+ addq $16,%rsp # drop vector number and error code
INTERRUPT_RETURN
ENDPROC(early_idt_handler)
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e8368c6..d5dd808 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -86,10 +86,19 @@
void __kernel_fpu_end(void)
{
- if (use_eager_fpu())
- math_state_restore();
- else
+ if (use_eager_fpu()) {
+ /*
+ * For eager fpu, most the time, tsk_used_math() is true.
+ * Restore the user math as we are done with the kernel usage.
+ * At few instances during thread exit, signal handling etc,
+ * tsk_used_math() is false. Those few places will take proper
+ * actions, so we don't need to restore the math here.
+ */
+ if (likely(tsk_used_math(current)))
+ math_state_restore();
+ } else {
stts();
+ }
}
EXPORT_SYMBOL(__kernel_fpu_end);
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 4eabc16..679cef0 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -279,5 +279,7 @@
VMCOREINFO_SYMBOL(node_data);
VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
#endif
+ vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
+ (unsigned long)&_text - __START_KERNEL);
}
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 872079a..f7d0672 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -100,8 +100,10 @@
flag |= __GFP_ZERO;
again:
page = NULL;
- if (!(flag & GFP_ATOMIC))
+ /* CMA can be used only in the context which permits sleeping */
+ if (flag & __GFP_WAIT)
page = dma_alloc_from_contiguous(dev, count, get_order(size));
+ /* fallback */
if (!page)
page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
if (!page)
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 7c6acd4..ff898bb 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -529,7 +529,7 @@
return;
pci_read_config_dword(nb_ht, 0x60, &val);
- node = val & 7;
+ node = pcibus_to_node(dev->bus) | (val & 7);
/*
* Some hardware may return an invalid node ID,
* so check it first:
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 06853e6..ce72964 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1239,14 +1239,8 @@
register_refined_jiffies(CLOCK_TICK_RATE);
#ifdef CONFIG_EFI
- /* Once setup is done above, unmap the EFI memory map on
- * mismatched firmware/kernel archtectures since there is no
- * support for runtime services.
- */
- if (efi_enabled(EFI_BOOT) && !efi_is_native()) {
- pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
- efi_unmap_memmap();
- }
+ if (efi_enabled(EFI_BOOT))
+ efi_apply_memmap_quirks();
#endif
}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 19e5adb..cfbe99f 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -209,7 +209,7 @@
* dance when its actually needed.
*/
- preempt_disable();
+ preempt_disable_notrace();
data = this_cpu_read(cyc2ns.head);
tail = this_cpu_read(cyc2ns.tail);
@@ -229,7 +229,7 @@
if (!--data->__count)
this_cpu_write(cyc2ns.tail, data);
}
- preempt_enable();
+ preempt_enable_notrace();
return ns;
}
@@ -653,13 +653,10 @@
/* Calibrate TSC using MSR for Intel Atom SoCs */
local_irq_save(flags);
- i = try_msr_calibrate_tsc(&fast_calibrate);
+ fast_calibrate = try_msr_calibrate_tsc();
local_irq_restore(flags);
- if (i >= 0) {
- if (i == 0)
- pr_warn("Fast TSC calibration using MSR failed\n");
+ if (fast_calibrate)
return fast_calibrate;
- }
local_irq_save(flags);
fast_calibrate = quick_pit_calibrate();
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 8b5434f..92ae6ac 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -53,7 +53,7 @@
/* TNG */
{ 6, 0x4a, 1, { 0, FREQ_100, FREQ_133, 0, 0, 0, 0, 0 } },
/* VLV2 */
- { 6, 0x37, 1, { 0, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } },
+ { 6, 0x37, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } },
/* ANN */
{ 6, 0x5a, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_100, 0, 0, 0, 0 } },
};
@@ -77,21 +77,18 @@
/*
* Do MSR calibration only for known/supported CPUs.
- * Return values:
- * -1: CPU is unknown/unsupported for MSR based calibration
- * 0: CPU is known/supported, but calibration failed
- * 1: CPU is known/supported, and calibration succeeded
+ *
+ * Returns the calibration value or 0 if MSR calibration failed.
*/
-int try_msr_calibrate_tsc(unsigned long *fast_calibrate)
+unsigned long try_msr_calibrate_tsc(void)
{
- int cpu_index;
u32 lo, hi, ratio, freq_id, freq;
+ unsigned long res;
+ int cpu_index;
cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model);
if (cpu_index < 0)
- return -1;
-
- *fast_calibrate = 0;
+ return 0;
if (freq_desc_tables[cpu_index].msr_plat) {
rdmsr(MSR_PLATFORM_INFO, lo, hi);
@@ -103,7 +100,7 @@
pr_info("Maximum core-clock to bus-clock ratio: 0x%x\n", ratio);
if (!ratio)
- return 0;
+ goto fail;
/* Get FSB FREQ ID */
rdmsr(MSR_FSB_FREQ, lo, hi);
@@ -112,16 +109,19 @@
pr_info("Resolved frequency ID: %u, frequency: %u KHz\n",
freq_id, freq);
if (!freq)
- return 0;
+ goto fail;
/* TSC frequency = maximum resolved freq * maximum resolved bus ratio */
- *fast_calibrate = freq * ratio;
- pr_info("TSC runs at %lu KHz\n", *fast_calibrate);
+ res = freq * ratio;
+ pr_info("TSC runs at %lu KHz\n", res);
#ifdef CONFIG_X86_LOCAL_APIC
lapic_timer_frequency = (freq * 1000) / HZ;
pr_info("lapic_timer_frequency = %d\n", lapic_timer_frequency);
#endif
+ return res;
- return 1;
+fail:
+ pr_warn("Fast TSC calibration using MSR failed\n");
+ return 0;
}
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e50425d..9b53135 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2672,6 +2672,7 @@
break;
}
+ drop_large_spte(vcpu, iterator.sptep);
if (!is_shadow_present_pte(*iterator.sptep)) {
u64 base_addr = iterator.addr;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e81df8f..2de1bc0 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3002,10 +3002,8 @@
u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
/* instruction emulation calls kvm_set_cr8() */
r = cr_interception(svm);
- if (irqchip_in_kernel(svm->vcpu.kvm)) {
- clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+ if (irqchip_in_kernel(svm->vcpu.kvm))
return r;
- }
if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
return r;
kvm_run->exit_reason = KVM_EXIT_SET_TPR;
@@ -3567,6 +3565,8 @@
if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK))
return;
+ clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+
if (irr == -1)
return;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a06f101..3927528 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6688,7 +6688,7 @@
else if (is_page_fault(intr_info))
return enable_ept;
else if (is_no_device(intr_info) &&
- !(nested_read_cr0(vmcs12) & X86_CR0_TS))
+ !(vmcs12->guest_cr0 & X86_CR0_TS))
return 0;
return vmcs12->exception_bitmap &
(1u << (intr_info & INTR_INFO_VECTOR_MASK));
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 39c28f09..2b85784 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6186,7 +6186,7 @@
frag->len -= len;
}
- if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+ if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
vcpu->mmio_needed = 0;
/* FIXME: return into emulator if single-stepping. */
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9d591c8..a10c8c7 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1001,6 +1001,12 @@
static inline bool smap_violation(int error_code, struct pt_regs *regs)
{
+ if (!IS_ENABLED(CONFIG_X86_SMAP))
+ return false;
+
+ if (!static_cpu_has(X86_FEATURE_SMAP))
+ return false;
+
if (error_code & PF_USER)
return false;
@@ -1014,13 +1020,17 @@
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
+ *
+ * This function must have noinline because both callers
+ * {,trace_}do_page_fault() have notrace on. Having this an actual function
+ * guarantees there's a function trace entry.
*/
-static void __kprobes
-__do_page_fault(struct pt_regs *regs, unsigned long error_code)
+static void __kprobes noinline
+__do_page_fault(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
- unsigned long address;
struct mm_struct *mm;
int fault;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -1028,9 +1038,6 @@
tsk = current;
mm = tsk->mm;
- /* Get the faulting address: */
- address = read_cr2();
-
/*
* Detect and handle instructions that would cause a page fault for
* both a tracked kernel page and a userspace page.
@@ -1087,11 +1094,9 @@
if (unlikely(error_code & PF_RSVD))
pgtable_bad(regs, error_code, address);
- if (static_cpu_has(X86_FEATURE_SMAP)) {
- if (unlikely(smap_violation(error_code, regs))) {
- bad_area_nosemaphore(regs, error_code, address);
- return;
- }
+ if (unlikely(smap_violation(error_code, regs))) {
+ bad_area_nosemaphore(regs, error_code, address);
+ return;
}
/*
@@ -1244,32 +1249,50 @@
up_read(&mm->mmap_sem);
}
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
+ unsigned long address = read_cr2(); /* Get the faulting address */
enum ctx_state prev_state;
+ /*
+ * We must have this function tagged with __kprobes, notrace and call
+ * read_cr2() before calling anything else. To avoid calling any kind
+ * of tracing machinery before we've observed the CR2 value.
+ *
+ * exception_{enter,exit}() contain all sorts of tracepoints.
+ */
+
prev_state = exception_enter();
- __do_page_fault(regs, error_code);
+ __do_page_fault(regs, error_code, address);
exception_exit(prev_state);
}
-static void trace_page_fault_entries(struct pt_regs *regs,
+#ifdef CONFIG_TRACING
+static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs,
unsigned long error_code)
{
if (user_mode(regs))
- trace_page_fault_user(read_cr2(), regs, error_code);
+ trace_page_fault_user(address, regs, error_code);
else
- trace_page_fault_kernel(read_cr2(), regs, error_code);
+ trace_page_fault_kernel(address, regs, error_code);
}
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
trace_do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
+ /*
+ * The exception_enter and tracepoint processing could
+ * trigger another page faults (user space callchain
+ * reading) and destroy the original cr2 value, so read
+ * the faulting address now.
+ */
+ unsigned long address = read_cr2();
enum ctx_state prev_state;
prev_state = exception_enter();
- trace_page_fault_entries(regs, error_code);
- __do_page_fault(regs, error_code);
+ trace_page_fault_entries(address, regs, error_code);
+ __do_page_fault(regs, error_code, address);
exception_exit(prev_state);
}
+#endif /* CONFIG_TRACING */
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 877b9a1..0149575 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -140,7 +140,7 @@
push %r9; \
push SKBDATA; \
/* rsi already has offset */ \
- mov $SIZE,%ecx; /* size */ \
+ mov $SIZE,%edx; /* size */ \
call bpf_internal_load_pointer_neg_helper; \
test %rax,%rax; \
pop SKBDATA; \
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 4ed75dd..dc01773 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -553,13 +553,13 @@
}
break;
case BPF_S_ANC_RXHASH:
- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
- if (is_imm8(offsetof(struct sk_buff, rxhash))) {
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+ if (is_imm8(offsetof(struct sk_buff, hash))) {
/* mov off8(%rdi),%eax */
- EMIT3(0x8b, 0x47, offsetof(struct sk_buff, rxhash));
+ EMIT3(0x8b, 0x47, offsetof(struct sk_buff, hash));
} else {
EMIT2(0x8b, 0x87);
- EMIT(offsetof(struct sk_buff, rxhash), 4);
+ EMIT(offsetof(struct sk_buff, hash), 4);
}
break;
case BPF_S_ANC_QUEUE:
@@ -772,6 +772,7 @@
bpf_flush_icache(header, image + proglen);
set_memory_ro((unsigned long)header, header->pages);
fp->bpf_func = (void *)image;
+ fp->jited = 1;
}
out:
kfree(addrs);
@@ -791,7 +792,7 @@
void bpf_jit_free(struct sk_filter *fp)
{
- if (fp->bpf_func != sk_run_filter) {
+ if (fp->jited) {
INIT_WORK(&fp->work, bpf_jit_free_deferred);
schedule_work(&fp->work);
} else {
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index 4df9591..f15103d 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -42,7 +42,7 @@
if (bgrt_tab->header.length < sizeof(*bgrt_tab))
return;
- if (bgrt_tab->version != 1)
+ if (bgrt_tab->version != 1 || bgrt_tab->status != 1)
return;
if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address)
return;
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index d62ec87..b97acec 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -52,6 +52,7 @@
#include <asm/tlbflush.h>
#include <asm/x86_init.h>
#include <asm/rtc.h>
+#include <asm/uv/uv.h>
#define EFI_DEBUG
@@ -792,7 +793,7 @@
set_memory_nx(addr, npages);
}
-static void __init runtime_code_page_mkexec(void)
+void __init runtime_code_page_mkexec(void)
{
efi_memory_desc_t *md;
void *p;
@@ -1069,8 +1070,7 @@
efi.update_capsule = virt_efi_update_capsule;
efi.query_capsule_caps = virt_efi_query_capsule_caps;
- if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX))
- runtime_code_page_mkexec();
+ efi_runtime_mkexec();
kfree(new_memmap);
@@ -1211,3 +1211,22 @@
return 0;
}
early_param("efi", parse_efi_cmdline);
+
+void __init efi_apply_memmap_quirks(void)
+{
+ /*
+ * Once setup is done earlier, unmap the EFI memory map on mismatched
+ * firmware/kernel architectures since there is no support for runtime
+ * services.
+ */
+ if (!efi_is_native()) {
+ pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+ efi_unmap_memmap();
+ }
+
+ /*
+ * UV doesn't support the new EFI pagetable mapping yet.
+ */
+ if (is_uv_system())
+ set_bit(EFI_OLD_MEMMAP, &x86_efi_facility);
+}
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 249b183..0b74cdf 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -77,3 +77,9 @@
local_irq_restore(efi_rt_eflags);
}
+
+void __init efi_runtime_mkexec(void)
+{
+ if (__supported_pte_mask & _PAGE_NX)
+ runtime_code_page_mkexec();
+}
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 6284f15..0c2a234 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -233,3 +233,12 @@
{
efi_setup = phys_addr + sizeof(struct setup_data);
}
+
+void __init efi_runtime_mkexec(void)
+{
+ if (!efi_enabled(EFI_OLD_MEMMAP))
+ return;
+
+ if (__supported_pte_mask & _PAGE_NX)
+ runtime_code_page_mkexec();
+}
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 7d01b8c..cc04e67 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -40,11 +40,7 @@
#define smp_rmb() barrier()
#endif /* CONFIG_X86_PPRO_FENCE */
-#ifdef CONFIG_X86_OOSTORE
-#define smp_wmb() wmb()
-#else /* CONFIG_X86_OOSTORE */
#define smp_wmb() barrier()
-#endif /* CONFIG_X86_OOSTORE */
#define smp_read_barrier_depends() read_barrier_depends()
#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index ba56e11..c87ae7c 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -20,6 +20,7 @@
select HAVE_FUNCTION_TRACER
select HAVE_IRQ_TIME_ACCOUNTING
select HAVE_PERF_EVENTS
+ select COMMON_CLK
help
Xtensa processors are 32-bit RISC machines designed by Tensilica
primarily for embedded systems. These processors are both
@@ -80,7 +81,6 @@
config XTENSA_VARIANT_FSF
bool "fsf - default (not generic) configuration"
select MMU
- select HAVE_XTENSA_GPIO32
config XTENSA_VARIANT_DC232B
bool "dc232b - Diamond 232L Standard Core Rev.B (LE)"
@@ -135,7 +135,6 @@
config SMP
bool "Enable Symmetric multi-processing support"
depends on HAVE_SMP
- select USE_GENERIC_SMP_HELPERS
select GENERIC_SMP_IDLE_THREAD
help
Enabled SMP Software; allows more than one CPU/CORE
diff --git a/arch/xtensa/boot/dts/xtfpga.dtsi b/arch/xtensa/boot/dts/xtfpga.dtsi
index 46b4f5e..e7370b1 100644
--- a/arch/xtensa/boot/dts/xtfpga.dtsi
+++ b/arch/xtensa/boot/dts/xtfpga.dtsi
@@ -35,6 +35,13 @@
interrupt-controller;
};
+ clocks {
+ osc: main-oscillator {
+ #clock-cells = <0>;
+ compatible = "fixed-clock";
+ };
+ };
+
serial0: serial@fd050020 {
device_type = "serial";
compatible = "ns16550a";
@@ -42,9 +49,7 @@
reg = <0xfd050020 0x20>;
reg-shift = <2>;
interrupts = <0 1>; /* external irq 0 */
- /* Filled in by platform_setup from FPGA register
- * clock-frequency = <100000000>;
- */
+ clocks = <&osc>;
};
enet0: ethoc@fd030000 {
@@ -52,5 +57,6 @@
reg = <0xfd030000 0x4000 0xfd800000 0x4000>;
interrupts = <1 1>; /* external irq 1 */
local-mac-address = [00 50 c2 13 6f 00];
+ clocks = <&osc>;
};
};
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index 2a042d4..7494420 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -25,7 +25,7 @@
#ifdef CONFIG_MMU
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
extern unsigned long xtensa_kio_paddr;
static inline unsigned long xtensa_get_kio_paddr(void)
diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h
index 8c194f6..677bfcf 100644
--- a/arch/xtensa/include/asm/traps.h
+++ b/arch/xtensa/include/asm/traps.h
@@ -23,25 +23,37 @@
static inline void spill_registers(void)
{
-
+#if XCHAL_NUM_AREGS > 16
__asm__ __volatile__ (
- "movi a14, "__stringify((1 << PS_EXCM_BIT) | LOCKLEVEL)"\n\t"
- "mov a12, a0\n\t"
- "rsr a13, sar\n\t"
- "xsr a14, ps\n\t"
- "movi a0, _spill_registers\n\t"
- "rsync\n\t"
- "callx0 a0\n\t"
- "mov a0, a12\n\t"
- "wsr a13, sar\n\t"
- "wsr a14, ps\n\t"
- : :
-#if defined(CONFIG_FRAME_POINTER)
- : "a2", "a3", "a4", "a11", "a12", "a13", "a14", "a15",
-#else
- : "a2", "a3", "a4", "a7", "a11", "a12", "a13", "a14", "a15",
+ " call12 1f\n"
+ " _j 2f\n"
+ " retw\n"
+ " .align 4\n"
+ "1:\n"
+ " _entry a1, 48\n"
+ " addi a12, a0, 3\n"
+#if XCHAL_NUM_AREGS > 32
+ " .rept (" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n"
+ " _entry a1, 48\n"
+ " mov a12, a0\n"
+ " .endr\n"
#endif
- "memory");
+ " _entry a1, 48\n"
+#if XCHAL_NUM_AREGS % 12 == 0
+ " mov a8, a8\n"
+#elif XCHAL_NUM_AREGS % 12 == 4
+ " mov a12, a12\n"
+#elif XCHAL_NUM_AREGS % 12 == 8
+ " mov a4, a4\n"
+#endif
+ " retw\n"
+ "2:\n"
+ : : : "a12", "a13", "memory");
+#else
+ __asm__ __volatile__ (
+ " mov a12, a12\n"
+ : : : "memory");
+#endif
}
#endif /* _XTENSA_TRAPS_H */
diff --git a/arch/xtensa/include/asm/vectors.h b/arch/xtensa/include/asm/vectors.h
index 5791b45..f74ddfb 100644
--- a/arch/xtensa/include/asm/vectors.h
+++ b/arch/xtensa/include/asm/vectors.h
@@ -25,7 +25,7 @@
#define XCHAL_KIO_DEFAULT_PADDR 0xf0000000
#define XCHAL_KIO_SIZE 0x10000000
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
#define XCHAL_KIO_PADDR xtensa_get_kio_paddr()
#else
#define XCHAL_KIO_PADDR XCHAL_KIO_DEFAULT_PADDR
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index 51940fe..b939552 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -734,7 +734,12 @@
#define __NR_accept4 333
__SYSCALL(333, sys_accept4, 4)
-#define __NR_syscall_count 334
+#define __NR_sched_setattr 334
+__SYSCALL(334, sys_sched_setattr, 2)
+#define __NR_sched_getattr 335
+__SYSCALL(335, sys_sched_getattr, 3)
+
+#define __NR_syscall_count 336
/*
* sysxtensa syscall handler
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 21dbe6b..ef7f499 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1081,34 +1081,202 @@
rsr a0, sar
s32i a3, a2, PT_AREG3
+ s32i a0, a2, PT_SAR
+
+ /* The spill routine might clobber a4, a7, a8, a11, a12, and a15. */
+
s32i a4, a2, PT_AREG4
- s32i a0, a2, PT_AREG5 # store SAR to PT_AREG5
-
- /* The spill routine might clobber a7, a11, and a15. */
-
s32i a7, a2, PT_AREG7
+ s32i a8, a2, PT_AREG8
s32i a11, a2, PT_AREG11
+ s32i a12, a2, PT_AREG12
s32i a15, a2, PT_AREG15
- call0 _spill_registers # destroys a3, a4, and SAR
+ /*
+ * Rotate ws so that the current windowbase is at bit 0.
+ * Assume ws = xxxwww1yy (www1 current window frame).
+ * Rotate ws right so that a4 = yyxxxwww1.
+ */
+
+ rsr a0, windowbase
+ rsr a3, windowstart # a3 = xxxwww1yy
+ ssr a0 # holds WB
+ slli a0, a3, WSBITS
+ or a3, a3, a0 # a3 = xxxwww1yyxxxwww1yy
+ srl a3, a3 # a3 = 00xxxwww1yyxxxwww1
+
+ /* We are done if there are no more than the current register frame. */
+
+ extui a3, a3, 1, WSBITS-1 # a3 = 0yyxxxwww
+ movi a0, (1 << (WSBITS-1))
+ _beqz a3, .Lnospill # only one active frame? jump
+
+ /* We want 1 at the top, so that we return to the current windowbase */
+
+ or a3, a3, a0 # 1yyxxxwww
+
+ /* Skip empty frames - get 'oldest' WINDOWSTART-bit. */
+
+ wsr a3, windowstart # save shifted windowstart
+ neg a0, a3
+ and a3, a0, a3 # first bit set from right: 000010000
+
+ ffs_ws a0, a3 # a0: shifts to skip empty frames
+ movi a3, WSBITS
+ sub a0, a3, a0 # WSBITS-a0:number of 0-bits from right
+ ssr a0 # save in SAR for later.
+
+ rsr a3, windowbase
+ add a3, a3, a0
+ wsr a3, windowbase
+ rsync
+
+ rsr a3, windowstart
+ srl a3, a3 # shift windowstart
+
+ /* WB is now just one frame below the oldest frame in the register
+ window. WS is shifted so the oldest frame is in bit 0, thus, WB
+ and WS differ by one 4-register frame. */
+
+ /* Save frames. Depending what call was used (call4, call8, call12),
+ * we have to save 4,8. or 12 registers.
+ */
+
+
+.Lloop: _bbsi.l a3, 1, .Lc4
+ _bbci.l a3, 2, .Lc12
+
+.Lc8: s32e a4, a13, -16
+ l32e a4, a5, -12
+ s32e a8, a4, -32
+ s32e a5, a13, -12
+ s32e a6, a13, -8
+ s32e a7, a13, -4
+ s32e a9, a4, -28
+ s32e a10, a4, -24
+ s32e a11, a4, -20
+ srli a11, a3, 2 # shift windowbase by 2
+ rotw 2
+ _bnei a3, 1, .Lloop
+ j .Lexit
+
+.Lc4: s32e a4, a9, -16
+ s32e a5, a9, -12
+ s32e a6, a9, -8
+ s32e a7, a9, -4
+
+ srli a7, a3, 1
+ rotw 1
+ _bnei a3, 1, .Lloop
+ j .Lexit
+
+.Lc12: _bbci.l a3, 3, .Linvalid_mask # bit 2 shouldn't be zero!
+
+ /* 12-register frame (call12) */
+
+ l32e a0, a5, -12
+ s32e a8, a0, -48
+ mov a8, a0
+
+ s32e a9, a8, -44
+ s32e a10, a8, -40
+ s32e a11, a8, -36
+ s32e a12, a8, -32
+ s32e a13, a8, -28
+ s32e a14, a8, -24
+ s32e a15, a8, -20
+ srli a15, a3, 3
+
+ /* The stack pointer for a4..a7 is out of reach, so we rotate the
+ * window, grab the stackpointer, and rotate back.
+ * Alternatively, we could also use the following approach, but that
+ * makes the fixup routine much more complicated:
+ * rotw 1
+ * s32e a0, a13, -16
+ * ...
+ * rotw 2
+ */
+
+ rotw 1
+ mov a4, a13
+ rotw -1
+
+ s32e a4, a8, -16
+ s32e a5, a8, -12
+ s32e a6, a8, -8
+ s32e a7, a8, -4
+
+ rotw 3
+
+ _beqi a3, 1, .Lexit
+ j .Lloop
+
+.Lexit:
+
+ /* Done. Do the final rotation and set WS */
+
+ rotw 1
+ rsr a3, windowbase
+ ssl a3
+ movi a3, 1
+ sll a3, a3
+ wsr a3, windowstart
+.Lnospill:
/* Advance PC, restore registers and SAR, and return from exception. */
- l32i a3, a2, PT_AREG5
- l32i a4, a2, PT_AREG4
+ l32i a3, a2, PT_SAR
l32i a0, a2, PT_AREG0
wsr a3, sar
l32i a3, a2, PT_AREG3
/* Restore clobbered registers. */
+ l32i a4, a2, PT_AREG4
l32i a7, a2, PT_AREG7
+ l32i a8, a2, PT_AREG8
l32i a11, a2, PT_AREG11
+ l32i a12, a2, PT_AREG12
l32i a15, a2, PT_AREG15
movi a2, 0
rfe
+.Linvalid_mask:
+
+ /* We get here because of an unrecoverable error in the window
+ * registers, so set up a dummy frame and kill the user application.
+ * Note: We assume EXC_TABLE_KSTK contains a valid stack pointer.
+ */
+
+ movi a0, 1
+ movi a1, 0
+
+ wsr a0, windowstart
+ wsr a1, windowbase
+ rsync
+
+ movi a0, 0
+
+ rsr a3, excsave1
+ l32i a1, a3, EXC_TABLE_KSTK
+
+ movi a4, (1 << PS_WOE_BIT) | LOCKLEVEL
+ wsr a4, ps
+ rsync
+
+ movi a6, SIGSEGV
+ movi a4, do_exit
+ callx4 a4
+
+ /* shouldn't return, so panic */
+
+ wsr a0, excsave1
+ movi a0, unrecoverable_exception
+ callx0 a0 # should not return
+1: j 1b
+
+
ENDPROC(fast_syscall_spill_registers)
/* Fixup handler.
@@ -1117,6 +1285,13 @@
* We basically restore WINDOWBASE and WINDOWSTART to the condition when
* we entered the spill routine and jump to the user exception handler.
*
+ * Note that we only need to restore the bits in windowstart that have not
+ * been spilled yet by the _spill_register routine. Luckily, a3 contains a
+ * rotated windowstart with only those bits set for frames that haven't been
+ * spilled yet. Because a3 is rotated such that bit 0 represents the register
+ * frame for the current windowbase - 1, we need to rotate a3 left by the
+ * value of the current windowbase + 1 and move it to windowstart.
+ *
* a0: value of depc, original value in depc
* a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE
* a3: exctable, original value in excsave1
@@ -1131,10 +1306,15 @@
/* We need to make sure the current registers (a0-a3) are preserved.
* To do this, we simply set the bit for the current window frame
* in WS, so that the exception handlers save them to the task stack.
+ *
+ * Note: we use a3 to set the windowbase, so we take a special care
+ * of it, saving it in the original _spill_registers frame across
+ * the exception handler call.
*/
xsr a3, excsave1 # get spill-mask
slli a3, a3, 1 # shift left by one
+ addi a3, a3, 1 # set the bit for the current window frame
slli a2, a3, 32-WSBITS
src a2, a3, a2 # a2 = xxwww1yyxxxwww1yy......
@@ -1220,209 +1400,6 @@
ENDPROC(fast_syscall_spill_registers_fixup_return)
-/*
- * spill all registers.
- *
- * This is not a real function. The following conditions must be met:
- *
- * - must be called with call0.
- * - uses a3, a4 and SAR.
- * - the last 'valid' register of each frame are clobbered.
- * - the caller must have registered a fixup handler
- * (or be inside a critical section)
- * - PS_EXCM must be set (PS_WOE cleared?)
- */
-
-ENTRY(_spill_registers)
-
- /*
- * Rotate ws so that the current windowbase is at bit 0.
- * Assume ws = xxxwww1yy (www1 current window frame).
- * Rotate ws right so that a4 = yyxxxwww1.
- */
-
- rsr a4, windowbase
- rsr a3, windowstart # a3 = xxxwww1yy
- ssr a4 # holds WB
- slli a4, a3, WSBITS
- or a3, a3, a4 # a3 = xxxwww1yyxxxwww1yy
- srl a3, a3 # a3 = 00xxxwww1yyxxxwww1
-
- /* We are done if there are no more than the current register frame. */
-
- extui a3, a3, 1, WSBITS-1 # a3 = 0yyxxxwww
- movi a4, (1 << (WSBITS-1))
- _beqz a3, .Lnospill # only one active frame? jump
-
- /* We want 1 at the top, so that we return to the current windowbase */
-
- or a3, a3, a4 # 1yyxxxwww
-
- /* Skip empty frames - get 'oldest' WINDOWSTART-bit. */
-
- wsr a3, windowstart # save shifted windowstart
- neg a4, a3
- and a3, a4, a3 # first bit set from right: 000010000
-
- ffs_ws a4, a3 # a4: shifts to skip empty frames
- movi a3, WSBITS
- sub a4, a3, a4 # WSBITS-a4:number of 0-bits from right
- ssr a4 # save in SAR for later.
-
- rsr a3, windowbase
- add a3, a3, a4
- wsr a3, windowbase
- rsync
-
- rsr a3, windowstart
- srl a3, a3 # shift windowstart
-
- /* WB is now just one frame below the oldest frame in the register
- window. WS is shifted so the oldest frame is in bit 0, thus, WB
- and WS differ by one 4-register frame. */
-
- /* Save frames. Depending what call was used (call4, call8, call12),
- * we have to save 4,8. or 12 registers.
- */
-
- _bbsi.l a3, 1, .Lc4
- _bbsi.l a3, 2, .Lc8
-
- /* Special case: we have a call12-frame starting at a4. */
-
- _bbci.l a3, 3, .Lc12 # bit 3 shouldn't be zero! (Jump to Lc12 first)
-
- s32e a4, a1, -16 # a1 is valid with an empty spill area
- l32e a4, a5, -12
- s32e a8, a4, -48
- mov a8, a4
- l32e a4, a1, -16
- j .Lc12c
-
-.Lnospill:
- ret
-
-.Lloop: _bbsi.l a3, 1, .Lc4
- _bbci.l a3, 2, .Lc12
-
-.Lc8: s32e a4, a13, -16
- l32e a4, a5, -12
- s32e a8, a4, -32
- s32e a5, a13, -12
- s32e a6, a13, -8
- s32e a7, a13, -4
- s32e a9, a4, -28
- s32e a10, a4, -24
- s32e a11, a4, -20
-
- srli a11, a3, 2 # shift windowbase by 2
- rotw 2
- _bnei a3, 1, .Lloop
-
-.Lexit: /* Done. Do the final rotation, set WS, and return. */
-
- rotw 1
- rsr a3, windowbase
- ssl a3
- movi a3, 1
- sll a3, a3
- wsr a3, windowstart
- ret
-
-.Lc4: s32e a4, a9, -16
- s32e a5, a9, -12
- s32e a6, a9, -8
- s32e a7, a9, -4
-
- srli a7, a3, 1
- rotw 1
- _bnei a3, 1, .Lloop
- j .Lexit
-
-.Lc12: _bbci.l a3, 3, .Linvalid_mask # bit 2 shouldn't be zero!
-
- /* 12-register frame (call12) */
-
- l32e a2, a5, -12
- s32e a8, a2, -48
- mov a8, a2
-
-.Lc12c: s32e a9, a8, -44
- s32e a10, a8, -40
- s32e a11, a8, -36
- s32e a12, a8, -32
- s32e a13, a8, -28
- s32e a14, a8, -24
- s32e a15, a8, -20
- srli a15, a3, 3
-
- /* The stack pointer for a4..a7 is out of reach, so we rotate the
- * window, grab the stackpointer, and rotate back.
- * Alternatively, we could also use the following approach, but that
- * makes the fixup routine much more complicated:
- * rotw 1
- * s32e a0, a13, -16
- * ...
- * rotw 2
- */
-
- rotw 1
- mov a5, a13
- rotw -1
-
- s32e a4, a9, -16
- s32e a5, a9, -12
- s32e a6, a9, -8
- s32e a7, a9, -4
-
- rotw 3
-
- _beqi a3, 1, .Lexit
- j .Lloop
-
-.Linvalid_mask:
-
- /* We get here because of an unrecoverable error in the window
- * registers. If we are in user space, we kill the application,
- * however, this condition is unrecoverable in kernel space.
- */
-
- rsr a0, ps
- _bbci.l a0, PS_UM_BIT, 1f
-
- /* User space: Setup a dummy frame and kill application.
- * Note: We assume EXC_TABLE_KSTK contains a valid stack pointer.
- */
-
- movi a0, 1
- movi a1, 0
-
- wsr a0, windowstart
- wsr a1, windowbase
- rsync
-
- movi a0, 0
-
- rsr a3, excsave1
- l32i a1, a3, EXC_TABLE_KSTK
-
- movi a4, (1 << PS_WOE_BIT) | LOCKLEVEL
- wsr a4, ps
- rsync
-
- movi a6, SIGSEGV
- movi a4, do_exit
- callx4 a4
-
-1: /* Kernel space: PANIC! */
-
- wsr a0, excsave1
- movi a0, unrecoverable_exception
- callx0 a0 # should not return
-1: j 1b
-
-ENDPROC(_spill_registers)
-
#ifdef CONFIG_MMU
/*
* We should never get here. Bail out!
@@ -1794,6 +1771,43 @@
ENDPROC(system_call)
+/*
+ * Spill live registers on the kernel stack macro.
+ *
+ * Entry condition: ps.woe is set, ps.excm is cleared
+ * Exit condition: windowstart has single bit set
+ * May clobber: a12, a13
+ */
+ .macro spill_registers_kernel
+
+#if XCHAL_NUM_AREGS > 16
+ call12 1f
+ _j 2f
+ retw
+ .align 4
+1:
+ _entry a1, 48
+ addi a12, a0, 3
+#if XCHAL_NUM_AREGS > 32
+ .rept (XCHAL_NUM_AREGS - 32) / 12
+ _entry a1, 48
+ mov a12, a0
+ .endr
+#endif
+ _entry a1, 48
+#if XCHAL_NUM_AREGS % 12 == 0
+ mov a8, a8
+#elif XCHAL_NUM_AREGS % 12 == 4
+ mov a12, a12
+#elif XCHAL_NUM_AREGS % 12 == 8
+ mov a4, a4
+#endif
+ retw
+2:
+#else
+ mov a12, a12
+#endif
+ .endm
/*
* Task switch.
@@ -1806,21 +1820,20 @@
entry a1, 16
- mov a12, a2 # preserve 'prev' (a2)
- mov a13, a3 # and 'next' (a3)
+ mov a10, a2 # preserve 'prev' (a2)
+ mov a11, a3 # and 'next' (a3)
l32i a4, a2, TASK_THREAD_INFO
l32i a5, a3, TASK_THREAD_INFO
- save_xtregs_user a4 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+ save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
- s32i a0, a12, THREAD_RA # save return address
- s32i a1, a12, THREAD_SP # save stack pointer
+ s32i a0, a10, THREAD_RA # save return address
+ s32i a1, a10, THREAD_SP # save stack pointer
/* Disable ints while we manipulate the stack pointer. */
- movi a14, (1 << PS_EXCM_BIT) | LOCKLEVEL
- xsr a14, ps
+ rsil a14, LOCKLEVEL
rsr a3, excsave1
rsync
s32i a3, a3, EXC_TABLE_FIXUP /* enter critical section */
@@ -1835,7 +1848,7 @@
/* Flush register file. */
- call0 _spill_registers # destroys a3, a4, and SAR
+ spill_registers_kernel
/* Set kernel stack (and leave critical section)
* Note: It's save to set it here. The stack will not be overwritten
@@ -1851,13 +1864,13 @@
/* restore context of the task 'next' */
- l32i a0, a13, THREAD_RA # restore return address
- l32i a1, a13, THREAD_SP # restore stack pointer
+ l32i a0, a11, THREAD_RA # restore return address
+ l32i a1, a11, THREAD_SP # restore stack pointer
- load_xtregs_user a5 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+ load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
wsr a14, ps
- mov a2, a12 # return 'prev'
+ mov a2, a10 # return 'prev'
rsync
retw
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 7d12af1..84fe931 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -22,6 +22,7 @@
#include <linux/bootmem.h>
#include <linux/kernel.h>
#include <linux/percpu.h>
+#include <linux/clk-provider.h>
#include <linux/cpu.h>
#include <linux/of_fdt.h>
#include <linux/of_platform.h>
@@ -276,6 +277,7 @@
static int __init xtensa_device_probe(void)
{
+ of_clk_init(NULL);
of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
return 0;
}
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 08b769d..2a1823d 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -30,6 +30,7 @@
#include <asm/platform.h>
unsigned long ccount_freq; /* ccount Hz */
+EXPORT_SYMBOL(ccount_freq);
static cycle_t ccount_read(struct clocksource *cs)
{
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index cb8fd44..f9e1ec3 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -235,7 +235,7 @@
/* Check for overflow/underflow exception, jump if overflow. */
- _bbci.l a0, 6, _DoubleExceptionVector_WindowOverflow
+ bbci.l a0, 6, _DoubleExceptionVector_WindowOverflow
/*
* Restart window underflow exception.
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 74a60c7..80b33ed 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -122,9 +122,7 @@
EXPORT_SYMBOL(insl);
extern long common_exception_return;
-extern long _spill_registers;
EXPORT_SYMBOL(common_exception_return);
-EXPORT_SYMBOL(_spill_registers);
#ifdef CONFIG_FUNCTION_TRACER
EXPORT_SYMBOL(_mcount);
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 479d753..aff108d 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -90,7 +90,7 @@
/*
- * Initialize the bootmem system and give it all the memory we have available.
+ * Initialize the bootmem system and give it all low memory we have available.
*/
void __init bootmem_init(void)
@@ -142,9 +142,14 @@
/* Add all remaining memory pieces into the bootmem map */
- for (i=0; i<sysmem.nr_banks; i++)
- free_bootmem(sysmem.bank[i].start,
- sysmem.bank[i].end - sysmem.bank[i].start);
+ for (i = 0; i < sysmem.nr_banks; i++) {
+ if (sysmem.bank[i].start >> PAGE_SHIFT < max_low_pfn) {
+ unsigned long end = min(max_low_pfn << PAGE_SHIFT,
+ sysmem.bank[i].end);
+ free_bootmem(sysmem.bank[i].start,
+ end - sysmem.bank[i].start);
+ }
+ }
}
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
index 36ec171..861203e 100644
--- a/arch/xtensa/mm/mmu.c
+++ b/arch/xtensa/mm/mmu.c
@@ -39,7 +39,7 @@
set_itlbcfg_register(0);
set_dtlbcfg_register(0);
#endif
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
/*
* Update the IO area mapping in case xtensa_kio_paddr has changed
*/
diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c
index 8002278..57fd08b 100644
--- a/arch/xtensa/platforms/xtfpga/setup.c
+++ b/arch/xtensa/platforms/xtfpga/setup.c
@@ -135,11 +135,11 @@
static int __init machine_setup(void)
{
- struct device_node *serial;
+ struct device_node *clock;
struct device_node *eth = NULL;
- for_each_compatible_node(serial, NULL, "ns16550a")
- update_clock_frequency(serial);
+ for_each_node_by_name(clock, "main-oscillator")
+ update_clock_frequency(clock);
if ((eth = of_find_compatible_node(eth, NULL, "opencores,ethoc")))
update_local_mac(eth);
@@ -290,6 +290,7 @@
* knows whether they set it correctly on the DIP switches.
*/
pr_info("XTFPGA: Ethernet MAC %pM\n", ethoc_pdata.hwaddr);
+ ethoc_pdata.eth_clkfreq = *(long *)XTFPGA_CLKFRQ_VADDR;
return 0;
}
diff --git a/arch/xtensa/variants/fsf/include/variant/tie.h b/arch/xtensa/variants/fsf/include/variant/tie.h
index bf40201..244cdea 100644
--- a/arch/xtensa/variants/fsf/include/variant/tie.h
+++ b/arch/xtensa/variants/fsf/include/variant/tie.h
@@ -18,13 +18,6 @@
#define XCHAL_CP_MASK 0x00 /* bitmask of all CPs by ID */
#define XCHAL_CP_PORT_MASK 0x00 /* bitmask of only port CPs */
-/* Basic parameters of each coprocessor: */
-#define XCHAL_CP7_NAME "XTIOP"
-#define XCHAL_CP7_IDENT XTIOP
-#define XCHAL_CP7_SA_SIZE 0 /* size of state save area */
-#define XCHAL_CP7_SA_ALIGN 1 /* min alignment of save area */
-#define XCHAL_CP_ID_XTIOP 7 /* coprocessor ID (0..7) */
-
/* Filler info for unassigned coprocessors, to simplify arrays etc: */
#define XCHAL_NCP_SA_SIZE 0
#define XCHAL_NCP_SA_ALIGN 1
@@ -42,6 +35,8 @@
#define XCHAL_CP5_SA_ALIGN 1
#define XCHAL_CP6_SA_SIZE 0
#define XCHAL_CP6_SA_ALIGN 1
+#define XCHAL_CP7_SA_SIZE 0
+#define XCHAL_CP7_SA_ALIGN 1
/* Save area for non-coprocessor optional and custom (TIE) state: */
#define XCHAL_NCP_SA_SIZE 0
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 86154ea..604f6d9 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -435,9 +435,9 @@
uint64_t v;
do {
- start = u64_stats_fetch_begin_bh(&stat->syncp);
+ start = u64_stats_fetch_begin_irq(&stat->syncp);
v = stat->cnt;
- } while (u64_stats_fetch_retry_bh(&stat->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&stat->syncp, start));
return v;
}
@@ -508,9 +508,9 @@
struct blkg_rwstat tmp;
do {
- start = u64_stats_fetch_begin_bh(&rwstat->syncp);
+ start = u64_stats_fetch_begin_irq(&rwstat->syncp);
tmp = *rwstat;
- } while (u64_stats_fetch_retry_bh(&rwstat->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&rwstat->syncp, start));
return tmp;
}
diff --git a/block/blk-core.c b/block/blk-core.c
index c00e0bd..bfe16d5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -708,9 +708,13 @@
if (!q)
return NULL;
- if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+ q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
+ if (!q->flush_rq)
return NULL;
+ if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+ goto fail;
+
q->request_fn = rfn;
q->prep_rq_fn = NULL;
q->unprep_rq_fn = NULL;
@@ -733,12 +737,16 @@
/* init elevator */
if (elevator_init(q, NULL)) {
mutex_unlock(&q->sysfs_lock);
- return NULL;
+ goto fail;
}
mutex_unlock(&q->sysfs_lock);
return q;
+
+fail:
+ kfree(q->flush_rq);
+ return NULL;
}
EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -1127,7 +1135,7 @@
struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
{
if (q->mq_ops)
- return blk_mq_alloc_request(q, rw, gfp_mask, false);
+ return blk_mq_alloc_request(q, rw, gfp_mask);
else
return blk_old_get_request(q, rw, gfp_mask);
}
@@ -1278,6 +1286,11 @@
if (unlikely(!q))
return;
+ if (q->mq_ops) {
+ blk_mq_free_request(req);
+ return;
+ }
+
blk_pm_put_request(req);
elv_completed_request(q, req);
diff --git a/block/blk-exec.c b/block/blk-exec.c
index bbfc072..dbf4502 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -65,7 +65,7 @@
* be resued after dying flag is set
*/
if (q->mq_ops) {
- blk_mq_insert_request(q, rq, true);
+ blk_mq_insert_request(rq, at_head, true, false);
return;
}
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 9288aaf..43e6b47 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -130,20 +130,29 @@
blk_clear_rq_complete(rq);
}
-static void mq_flush_data_run(struct work_struct *work)
+static void mq_flush_run(struct work_struct *work)
{
struct request *rq;
- rq = container_of(work, struct request, mq_flush_data);
+ rq = container_of(work, struct request, mq_flush_work);
memset(&rq->csd, 0, sizeof(rq->csd));
- blk_mq_run_request(rq, true, false);
+ blk_mq_insert_request(rq, false, true, false);
}
-static void blk_mq_flush_data_insert(struct request *rq)
+static bool blk_flush_queue_rq(struct request *rq, bool add_front)
{
- INIT_WORK(&rq->mq_flush_data, mq_flush_data_run);
- kblockd_schedule_work(rq->q, &rq->mq_flush_data);
+ if (rq->q->mq_ops) {
+ INIT_WORK(&rq->mq_flush_work, mq_flush_run);
+ kblockd_schedule_work(rq->q, &rq->mq_flush_work);
+ return false;
+ } else {
+ if (add_front)
+ list_add(&rq->queuelist, &rq->q->queue_head);
+ else
+ list_add_tail(&rq->queuelist, &rq->q->queue_head);
+ return true;
+ }
}
/**
@@ -187,12 +196,7 @@
case REQ_FSEQ_DATA:
list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
- if (q->mq_ops)
- blk_mq_flush_data_insert(rq);
- else {
- list_add(&rq->queuelist, &q->queue_head);
- queued = true;
- }
+ queued = blk_flush_queue_rq(rq, true);
break;
case REQ_FSEQ_DONE:
@@ -216,9 +220,6 @@
}
kicked = blk_kick_flush(q);
- /* blk_mq_run_flush will run queue */
- if (q->mq_ops)
- return queued;
return kicked | queued;
}
@@ -230,10 +231,9 @@
struct request *rq, *n;
unsigned long flags = 0;
- if (q->mq_ops) {
- blk_mq_free_request(flush_rq);
+ if (q->mq_ops)
spin_lock_irqsave(&q->mq_flush_lock, flags);
- }
+
running = &q->flush_queue[q->flush_running_idx];
BUG_ON(q->flush_pending_idx == q->flush_running_idx);
@@ -263,49 +263,14 @@
* kblockd.
*/
if (queued || q->flush_queue_delayed) {
- if (!q->mq_ops)
- blk_run_queue_async(q);
- else
- /*
- * This can be optimized to only run queues with requests
- * queued if necessary.
- */
- blk_mq_run_queues(q, true);
+ WARN_ON(q->mq_ops);
+ blk_run_queue_async(q);
}
q->flush_queue_delayed = 0;
if (q->mq_ops)
spin_unlock_irqrestore(&q->mq_flush_lock, flags);
}
-static void mq_flush_work(struct work_struct *work)
-{
- struct request_queue *q;
- struct request *rq;
-
- q = container_of(work, struct request_queue, mq_flush_work);
-
- /* We don't need set REQ_FLUSH_SEQ, it's for consistency */
- rq = blk_mq_alloc_request(q, WRITE_FLUSH|REQ_FLUSH_SEQ,
- __GFP_WAIT|GFP_ATOMIC, true);
- rq->cmd_type = REQ_TYPE_FS;
- rq->end_io = flush_end_io;
-
- blk_mq_run_request(rq, true, false);
-}
-
-/*
- * We can't directly use q->flush_rq, because it doesn't have tag and is not in
- * hctx->rqs[]. so we must allocate a new request, since we can't sleep here,
- * so offload the work to workqueue.
- *
- * Note: we assume a flush request finished in any hardware queue will flush
- * the whole disk cache.
- */
-static void mq_run_flush(struct request_queue *q)
-{
- kblockd_schedule_work(q, &q->mq_flush_work);
-}
-
/**
* blk_kick_flush - consider issuing flush request
* @q: request_queue being kicked
@@ -340,19 +305,31 @@
* different from running_idx, which means flush is in flight.
*/
q->flush_pending_idx ^= 1;
+
if (q->mq_ops) {
- mq_run_flush(q);
- return true;
+ struct blk_mq_ctx *ctx = first_rq->mq_ctx;
+ struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+ blk_mq_rq_init(hctx, q->flush_rq);
+ q->flush_rq->mq_ctx = ctx;
+
+ /*
+ * Reuse the tag value from the fist waiting request,
+ * with blk-mq the tag is generated during request
+ * allocation and drivers can rely on it being inside
+ * the range they asked for.
+ */
+ q->flush_rq->tag = first_rq->tag;
+ } else {
+ blk_rq_init(q, q->flush_rq);
}
- blk_rq_init(q, &q->flush_rq);
- q->flush_rq.cmd_type = REQ_TYPE_FS;
- q->flush_rq.cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
- q->flush_rq.rq_disk = first_rq->rq_disk;
- q->flush_rq.end_io = flush_end_io;
+ q->flush_rq->cmd_type = REQ_TYPE_FS;
+ q->flush_rq->cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
+ q->flush_rq->rq_disk = first_rq->rq_disk;
+ q->flush_rq->end_io = flush_end_io;
- list_add_tail(&q->flush_rq.queuelist, &q->queue_head);
- return true;
+ return blk_flush_queue_rq(q->flush_rq, false);
}
static void flush_data_end_io(struct request *rq, int error)
@@ -437,7 +414,7 @@
if ((policy & REQ_FSEQ_DATA) &&
!(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
if (q->mq_ops) {
- blk_mq_run_request(rq, false, true);
+ blk_mq_insert_request(rq, false, false, true);
} else
list_add_tail(&rq->queuelist, &q->queue_head);
return;
@@ -558,5 +535,4 @@
void blk_mq_init_flush(struct request_queue *q)
{
spin_lock_init(&q->mq_flush_lock);
- INIT_WORK(&q->mq_flush_work, mq_flush_work);
}
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 2da76c9..97a733c 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -119,6 +119,14 @@
atomic_inc(&bb.done);
submit_bio(type, bio);
+
+ /*
+ * We can loop for a long time in here, if someone does
+ * full device discards (like mkfs). Be nice and allow
+ * us to schedule out to avoid softlocking if preempt
+ * is disabled.
+ */
+ cond_resched();
}
blk_finish_plug(&plug);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 8f8adaa..6c583f9 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -21,6 +21,16 @@
if (!bio)
return 0;
+ /*
+ * This should probably be returning 0, but blk_add_request_payload()
+ * (Christoph!!!!)
+ */
+ if (bio->bi_rw & REQ_DISCARD)
+ return 1;
+
+ if (bio->bi_rw & REQ_WRITE_SAME)
+ return 1;
+
fbio = bio;
cluster = blk_queue_cluster(q);
seg_size = 0;
@@ -161,6 +171,48 @@
*bvprv = *bvec;
}
+static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
+ struct scatterlist *sglist,
+ struct scatterlist **sg)
+{
+ struct bio_vec bvec, bvprv = { NULL };
+ struct bvec_iter iter;
+ int nsegs, cluster;
+
+ nsegs = 0;
+ cluster = blk_queue_cluster(q);
+
+ if (bio->bi_rw & REQ_DISCARD) {
+ /*
+ * This is a hack - drivers should be neither modifying the
+ * biovec, nor relying on bi_vcnt - but because of
+ * blk_add_request_payload(), a discard bio may or may not have
+ * a payload we need to set up here (thank you Christoph) and
+ * bi_vcnt is really the only way of telling if we need to.
+ */
+
+ if (bio->bi_vcnt)
+ goto single_segment;
+
+ return 0;
+ }
+
+ if (bio->bi_rw & REQ_WRITE_SAME) {
+single_segment:
+ *sg = sglist;
+ bvec = bio_iovec(bio);
+ sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
+ return 1;
+ }
+
+ for_each_bio(bio)
+ bio_for_each_segment(bvec, bio, iter)
+ __blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
+ &nsegs, &cluster);
+
+ return nsegs;
+}
+
/*
* map a request to scatterlist, return number of sg entries setup. Caller
* must make sure sg can hold rq->nr_phys_segments entries
@@ -168,23 +220,11 @@
int blk_rq_map_sg(struct request_queue *q, struct request *rq,
struct scatterlist *sglist)
{
- struct bio_vec bvec, bvprv = { NULL };
- struct req_iterator iter;
- struct scatterlist *sg;
- int nsegs, cluster;
+ struct scatterlist *sg = NULL;
+ int nsegs = 0;
- nsegs = 0;
- cluster = blk_queue_cluster(q);
-
- /*
- * for each bio in rq
- */
- sg = NULL;
- rq_for_each_segment(bvec, rq, iter) {
- __blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg,
- &nsegs, &cluster);
- } /* segments in rq */
-
+ if (rq->bio)
+ nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg);
if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
(blk_rq_bytes(rq) & q->dma_pad_mask)) {
@@ -230,20 +270,13 @@
int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
struct scatterlist *sglist)
{
- struct bio_vec bvec, bvprv = { NULL };
- struct scatterlist *sg;
- int nsegs, cluster;
- struct bvec_iter iter;
+ struct scatterlist *sg = NULL;
+ int nsegs;
+ struct bio *next = bio->bi_next;
+ bio->bi_next = NULL;
- nsegs = 0;
- cluster = blk_queue_cluster(q);
-
- sg = NULL;
- bio_for_each_segment(bvec, bio, iter) {
- __blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg,
- &nsegs, &cluster);
- } /* segments in bio */
-
+ nsegs = __blk_bios_map_sg(q, bio, sglist, &sg);
+ bio->bi_next = next;
if (sg)
sg_mark_end(sg);
diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c
index 3146bef..136ef86 100644
--- a/block/blk-mq-cpu.c
+++ b/block/blk-mq-cpu.c
@@ -11,7 +11,7 @@
#include "blk-mq.h"
static LIST_HEAD(blk_mq_cpu_notify_list);
-static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock);
+static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock);
static int blk_mq_main_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
@@ -19,12 +19,12 @@
unsigned int cpu = (unsigned long) hcpu;
struct blk_mq_cpu_notifier *notify;
- spin_lock(&blk_mq_cpu_notify_lock);
+ raw_spin_lock(&blk_mq_cpu_notify_lock);
list_for_each_entry(notify, &blk_mq_cpu_notify_list, list)
notify->notify(notify->data, action, cpu);
- spin_unlock(&blk_mq_cpu_notify_lock);
+ raw_spin_unlock(&blk_mq_cpu_notify_lock);
return NOTIFY_OK;
}
@@ -32,16 +32,16 @@
{
BUG_ON(!notifier->notify);
- spin_lock(&blk_mq_cpu_notify_lock);
+ raw_spin_lock(&blk_mq_cpu_notify_lock);
list_add_tail(¬ifier->list, &blk_mq_cpu_notify_list);
- spin_unlock(&blk_mq_cpu_notify_lock);
+ raw_spin_unlock(&blk_mq_cpu_notify_lock);
}
void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
{
- spin_lock(&blk_mq_cpu_notify_lock);
+ raw_spin_lock(&blk_mq_cpu_notify_lock);
list_del(¬ifier->list);
- spin_unlock(&blk_mq_cpu_notify_lock);
+ raw_spin_unlock(&blk_mq_cpu_notify_lock);
}
void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 5d70edc..83ae96c 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -184,7 +184,7 @@
ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page)
{
char *orig_page = page;
- int cpu;
+ unsigned int cpu;
if (!tags)
return 0;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 57039fc..883f720 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -73,8 +73,8 @@
set_bit(ctx->index_hw, hctx->ctx_map);
}
-static struct request *blk_mq_alloc_rq(struct blk_mq_hw_ctx *hctx, gfp_t gfp,
- bool reserved)
+static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
+ gfp_t gfp, bool reserved)
{
struct request *rq;
unsigned int tag;
@@ -193,12 +193,6 @@
ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
}
-static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
- gfp_t gfp, bool reserved)
-{
- return blk_mq_alloc_rq(hctx, gfp, reserved);
-}
-
static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
int rw, gfp_t gfp,
bool reserved)
@@ -226,15 +220,14 @@
return rq;
}
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
- gfp_t gfp, bool reserved)
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp)
{
struct request *rq;
if (blk_mq_queue_enter(q))
return NULL;
- rq = blk_mq_alloc_request_pinned(q, rw, gfp, reserved);
+ rq = blk_mq_alloc_request_pinned(q, rw, gfp, false);
if (rq)
blk_mq_put_ctx(rq->mq_ctx);
return rq;
@@ -258,7 +251,7 @@
/*
* Re-init and set pdu, if we have it
*/
-static void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq)
+void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq)
{
blk_rq_init(hctx->queue, rq);
@@ -290,38 +283,10 @@
__blk_mq_free_request(hctx, ctx, rq);
}
-static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error)
+bool blk_mq_end_io_partial(struct request *rq, int error, unsigned int nr_bytes)
{
- if (error)
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
- else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
- error = -EIO;
-
- if (unlikely(rq->cmd_flags & REQ_QUIET))
- set_bit(BIO_QUIET, &bio->bi_flags);
-
- /* don't actually finish bio if it's part of flush sequence */
- if (!(rq->cmd_flags & REQ_FLUSH_SEQ))
- bio_endio(bio, error);
-}
-
-void blk_mq_complete_request(struct request *rq, int error)
-{
- struct bio *bio = rq->bio;
- unsigned int bytes = 0;
-
- trace_block_rq_complete(rq->q, rq);
-
- while (bio) {
- struct bio *next = bio->bi_next;
-
- bio->bi_next = NULL;
- bytes += bio->bi_iter.bi_size;
- blk_mq_bio_endio(rq, bio, error);
- bio = next;
- }
-
- blk_account_io_completion(rq, bytes);
+ if (blk_update_request(rq, error, blk_rq_bytes(rq)))
+ return true;
blk_account_io_done(rq);
@@ -329,49 +294,57 @@
rq->end_io(rq, error);
else
blk_mq_free_request(rq);
+ return false;
}
+EXPORT_SYMBOL(blk_mq_end_io_partial);
-void __blk_mq_end_io(struct request *rq, int error)
-{
- if (!blk_mark_rq_complete(rq))
- blk_mq_complete_request(rq, error);
-}
-
-static void blk_mq_end_io_remote(void *data)
+static void __blk_mq_complete_request_remote(void *data)
{
struct request *rq = data;
- __blk_mq_end_io(rq, rq->errors);
+ rq->q->softirq_done_fn(rq);
}
-/*
- * End IO on this request on a multiqueue enabled driver. We'll either do
- * it directly inline, or punt to a local IPI handler on the matching
- * remote CPU.
- */
-void blk_mq_end_io(struct request *rq, int error)
+void __blk_mq_complete_request(struct request *rq)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
int cpu;
- if (!ctx->ipi_redirect)
- return __blk_mq_end_io(rq, error);
+ if (!ctx->ipi_redirect) {
+ rq->q->softirq_done_fn(rq);
+ return;
+ }
cpu = get_cpu();
if (cpu != ctx->cpu && cpu_online(ctx->cpu)) {
- rq->errors = error;
- rq->csd.func = blk_mq_end_io_remote;
+ rq->csd.func = __blk_mq_complete_request_remote;
rq->csd.info = rq;
rq->csd.flags = 0;
__smp_call_function_single(ctx->cpu, &rq->csd, 0);
} else {
- __blk_mq_end_io(rq, error);
+ rq->q->softirq_done_fn(rq);
}
put_cpu();
}
-EXPORT_SYMBOL(blk_mq_end_io);
-static void blk_mq_start_request(struct request *rq)
+/**
+ * blk_mq_complete_request - end I/O on a request
+ * @rq: the request being processed
+ *
+ * Description:
+ * Ends all I/O on a request. It does not handle partial completions.
+ * The actual completion happens out-of-order, through a IPI handler.
+ **/
+void blk_mq_complete_request(struct request *rq)
+{
+ if (unlikely(blk_should_fake_timeout(rq->q)))
+ return;
+ if (!blk_mark_rq_complete(rq))
+ __blk_mq_complete_request(rq);
+}
+EXPORT_SYMBOL(blk_mq_complete_request);
+
+static void blk_mq_start_request(struct request *rq, bool last)
{
struct request_queue *q = rq->q;
@@ -384,6 +357,25 @@
*/
rq->deadline = jiffies + q->rq_timeout;
set_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+
+ if (q->dma_drain_size && blk_rq_bytes(rq)) {
+ /*
+ * Make sure space for the drain appears. We know we can do
+ * this because max_hw_segments has been adjusted to be one
+ * fewer than the device can handle.
+ */
+ rq->nr_phys_segments++;
+ }
+
+ /*
+ * Flag the last request in the series so that drivers know when IO
+ * should be kicked off, if they don't do it on a per-request basis.
+ *
+ * Note: the flag isn't the only condition drivers should do kick off.
+ * If drive is busy, the last request might not have the bit set.
+ */
+ if (last)
+ rq->cmd_flags |= REQ_END;
}
static void blk_mq_requeue_request(struct request *rq)
@@ -392,6 +384,11 @@
trace_block_rq_requeue(q, rq);
clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+
+ rq->cmd_flags &= ~REQ_END;
+
+ if (q->dma_drain_size && blk_rq_bytes(rq))
+ rq->nr_phys_segments--;
}
struct blk_mq_timeout_data {
@@ -559,19 +556,8 @@
rq = list_first_entry(&rq_list, struct request, queuelist);
list_del_init(&rq->queuelist);
- blk_mq_start_request(rq);
- /*
- * Last request in the series. Flag it as such, this
- * enables drivers to know when IO should be kicked off,
- * if they don't do it on a per-request basis.
- *
- * Note: the flag isn't the only condition drivers
- * should do kick off. If drive is busy, the last
- * request might not have the bit set.
- */
- if (list_empty(&rq_list))
- rq->cmd_flags |= REQ_END;
+ blk_mq_start_request(rq, list_empty(&rq_list));
ret = q->mq_ops->queue_rq(hctx, rq);
switch (ret) {
@@ -589,8 +575,8 @@
break;
default:
pr_err("blk-mq: bad return on queue: %d\n", ret);
- rq->errors = -EIO;
case BLK_MQ_RQ_QUEUE_ERROR:
+ rq->errors = -EIO;
blk_mq_end_io(rq, rq->errors);
break;
}
@@ -693,13 +679,16 @@
}
static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
- struct request *rq)
+ struct request *rq, bool at_head)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
trace_block_rq_insert(hctx->queue, rq);
- list_add_tail(&rq->queuelist, &ctx->rq_list);
+ if (at_head)
+ list_add(&rq->queuelist, &ctx->rq_list);
+ else
+ list_add_tail(&rq->queuelist, &ctx->rq_list);
blk_mq_hctx_mark_pending(hctx, ctx);
/*
@@ -708,60 +697,27 @@
blk_mq_add_timer(rq);
}
-void blk_mq_insert_request(struct request_queue *q, struct request *rq,
- bool run_queue)
-{
- struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *ctx, *current_ctx;
-
- ctx = rq->mq_ctx;
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
- if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
- blk_insert_flush(rq);
- } else {
- current_ctx = blk_mq_get_ctx(q);
-
- if (!cpu_online(ctx->cpu)) {
- ctx = current_ctx;
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
- rq->mq_ctx = ctx;
- }
- spin_lock(&ctx->lock);
- __blk_mq_insert_request(hctx, rq);
- spin_unlock(&ctx->lock);
-
- blk_mq_put_ctx(current_ctx);
- }
-
- if (run_queue)
- __blk_mq_run_hw_queue(hctx);
-}
-EXPORT_SYMBOL(blk_mq_insert_request);
-
-/*
- * This is a special version of blk_mq_insert_request to bypass FLUSH request
- * check. Should only be used internally.
- */
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async)
+void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
+ bool async)
{
struct request_queue *q = rq->q;
struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *ctx, *current_ctx;
+ struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx;
current_ctx = blk_mq_get_ctx(q);
+ if (!cpu_online(ctx->cpu))
+ rq->mq_ctx = ctx = current_ctx;
- ctx = rq->mq_ctx;
- if (!cpu_online(ctx->cpu)) {
- ctx = current_ctx;
- rq->mq_ctx = ctx;
- }
hctx = q->mq_ops->map_queue(q, ctx->cpu);
- /* ctx->cpu might be offline */
- spin_lock(&ctx->lock);
- __blk_mq_insert_request(hctx, rq);
- spin_unlock(&ctx->lock);
+ if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA) &&
+ !(rq->cmd_flags & (REQ_FLUSH_SEQ))) {
+ blk_insert_flush(rq);
+ } else {
+ spin_lock(&ctx->lock);
+ __blk_mq_insert_request(hctx, rq, at_head);
+ spin_unlock(&ctx->lock);
+ }
blk_mq_put_ctx(current_ctx);
@@ -798,7 +754,7 @@
rq = list_first_entry(list, struct request, queuelist);
list_del_init(&rq->queuelist);
rq->mq_ctx = ctx;
- __blk_mq_insert_request(hctx, rq);
+ __blk_mq_insert_request(hctx, rq, false);
}
spin_unlock(&ctx->lock);
@@ -888,6 +844,11 @@
blk_queue_bounce(q, &bio);
+ if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
+ bio_endio(bio, -EIO);
+ return;
+ }
+
if (use_plug && blk_attempt_plug_merge(q, bio, &request_count))
return;
@@ -899,6 +860,8 @@
ctx = blk_mq_get_ctx(q);
hctx = q->mq_ops->map_queue(q, ctx->cpu);
+ if (is_sync)
+ rw |= REQ_SYNC;
trace_block_getrq(q, bio, rw);
rq = __blk_mq_alloc_request(hctx, GFP_ATOMIC, false);
if (likely(rq))
@@ -950,7 +913,7 @@
__blk_mq_free_request(hctx, ctx, rq);
else {
blk_mq_bio_to_request(rq, bio);
- __blk_mq_insert_request(hctx, rq);
+ __blk_mq_insert_request(hctx, rq, false);
}
spin_unlock(&ctx->lock);
@@ -1309,15 +1272,6 @@
reg->queue_depth = BLK_MQ_MAX_DEPTH;
}
- /*
- * Set aside a tag for flush requests. It will only be used while
- * another flush request is in progress but outside the driver.
- *
- * TODO: only allocate if flushes are supported
- */
- reg->queue_depth++;
- reg->reserved_tags++;
-
if (reg->queue_depth < (reg->reserved_tags + BLK_MQ_TAG_MIN))
return ERR_PTR(-EINVAL);
@@ -1360,17 +1314,27 @@
q->mq_ops = reg->ops;
q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
+ q->sg_reserved_size = INT_MAX;
+
blk_queue_make_request(q, blk_mq_make_request);
blk_queue_rq_timed_out(q, reg->ops->timeout);
if (reg->timeout)
blk_queue_rq_timeout(q, reg->timeout);
+ if (reg->ops->complete)
+ blk_queue_softirq_done(q, reg->ops->complete);
+
blk_mq_init_flush(q);
blk_mq_init_cpu_queues(q, reg->nr_hw_queues);
- if (blk_mq_init_hw_queues(q, reg, driver_data))
+ q->flush_rq = kzalloc(round_up(sizeof(struct request) + reg->cmd_size,
+ cache_line_size()), GFP_KERNEL);
+ if (!q->flush_rq)
goto err_hw;
+ if (blk_mq_init_hw_queues(q, reg, driver_data))
+ goto err_flush_rq;
+
blk_mq_map_swqueue(q);
mutex_lock(&all_q_mutex);
@@ -1378,6 +1342,9 @@
mutex_unlock(&all_q_mutex);
return q;
+
+err_flush_rq:
+ kfree(q->flush_rq);
err_hw:
kfree(q->mq_map);
err_map:
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 5c39179..72beba1 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -22,13 +22,12 @@
struct kobject kobj;
};
-void __blk_mq_end_io(struct request *rq, int error);
-void blk_mq_complete_request(struct request *rq, int error);
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async);
+void __blk_mq_complete_request(struct request *rq);
void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_init_flush(struct request_queue *q);
void blk_mq_drain_queue(struct request_queue *q);
void blk_mq_free_queue(struct request_queue *q);
+void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq);
/*
* CPU hotplug helpers
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 8095c4a..7500f87 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -549,6 +549,8 @@
if (q->mq_ops)
blk_mq_free_queue(q);
+ kfree(q->flush_rq);
+
blk_trace_shutdown(q);
bdi_destroy(&q->backing_dev_info);
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index bba81c9..d96f7061 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -91,7 +91,7 @@
case BLK_EH_HANDLED:
/* Can we use req->errors here? */
if (q->mq_ops)
- blk_mq_complete_request(req, req->errors);
+ __blk_mq_complete_request(req);
else
__blk_complete_request(req);
break;
diff --git a/block/blk.h b/block/blk.h
index c90e1d8..d23b415 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -113,7 +113,7 @@
q->flush_queue_delayed = 1;
return NULL;
}
- if (unlikely(blk_queue_dying(q)) ||
+ if (unlikely(blk_queue_bypass(q)) ||
!q->elevator->type->ops.elevator_dispatch_fn(q, 0))
return NULL;
}
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index e7515aa..6f190bc 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -243,6 +243,8 @@
kobject_uevent(&ac->charger.dev->kobj, KOBJ_CHANGE);
return 0;
}
+#else
+#define acpi_ac_resume NULL
#endif
static SIMPLE_DEV_PM_OPS(acpi_ac_pm_ops, NULL, acpi_ac_resume);
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 018a428..797a693 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -841,6 +841,8 @@
acpi_battery_update(battery);
return 0;
}
+#else
+#define acpi_battery_resume NULL
#endif
static SIMPLE_DEV_PM_OPS(acpi_battery_pm, NULL, acpi_battery_resume);
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index 10e4964..afec452 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -260,14 +260,6 @@
},
{
.callback = dmi_disable_osi_win8,
- .ident = "Dell Inspiron 15R SE",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7520"),
- },
- },
- {
- .callback = dmi_disable_osi_win8,
.ident = "ThinkPad Edge E530",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
@@ -322,56 +314,6 @@
DMI_MATCH(DMI_PRODUCT_VERSION, "2349D15"),
},
},
- {
- .callback = dmi_disable_osi_win8,
- .ident = "HP ProBook 2013 models",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook "),
- DMI_MATCH(DMI_PRODUCT_NAME, " G1"),
- },
- },
- {
- .callback = dmi_disable_osi_win8,
- .ident = "HP EliteBook 2013 models",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook "),
- DMI_MATCH(DMI_PRODUCT_NAME, " G1"),
- },
- },
- {
- .callback = dmi_disable_osi_win8,
- .ident = "HP ZBook 14",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 14"),
- },
- },
- {
- .callback = dmi_disable_osi_win8,
- .ident = "HP ZBook 15",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 15"),
- },
- },
- {
- .callback = dmi_disable_osi_win8,
- .ident = "HP ZBook 17",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 17"),
- },
- },
- {
- .callback = dmi_disable_osi_win8,
- .ident = "HP EliteBook 8780w",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 8780w"),
- },
- },
/*
* BIOS invocation of _OSI(Linux) is almost always a BIOS bug.
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 11c11f6..714e957 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -80,6 +80,8 @@
#ifdef CONFIG_PM_SLEEP
static int acpi_button_resume(struct device *dev);
+#else
+#define acpi_button_resume NULL
#endif
static SIMPLE_DEV_PM_OPS(acpi_button_pm, NULL, acpi_button_resume);
diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c
index 0b6ae6e..368f9dd 100644
--- a/drivers/acpi/container.c
+++ b/drivers/acpi/container.c
@@ -79,9 +79,10 @@
ACPI_COMPANION_SET(dev, adev);
dev->release = acpi_container_release;
ret = device_register(dev);
- if (ret)
+ if (ret) {
+ put_device(dev);
return ret;
-
+ }
adev->driver_data = dev;
return 1;
}
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index c431c88..5bfd769 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -609,7 +609,7 @@
static void dock_notify(struct dock_station *ds, u32 event)
{
acpi_handle handle = ds->handle;
- struct acpi_device *ad;
+ struct acpi_device *adev = NULL;
int surprise_removal = 0;
/*
@@ -632,7 +632,8 @@
switch (event) {
case ACPI_NOTIFY_BUS_CHECK:
case ACPI_NOTIFY_DEVICE_CHECK:
- if (!dock_in_progress(ds) && acpi_bus_get_device(handle, &ad)) {
+ acpi_bus_get_device(handle, &adev);
+ if (!dock_in_progress(ds) && !acpi_device_enumerated(adev)) {
begin_dock(ds);
dock(ds);
if (!dock_present(ds)) {
@@ -712,13 +713,11 @@
static ssize_t show_docked(struct device *dev,
struct device_attribute *attr, char *buf)
{
- struct acpi_device *tmp;
-
struct dock_station *dock_station = dev->platform_data;
+ struct acpi_device *adev = NULL;
- if (!acpi_bus_get_device(dock_station->handle, &tmp))
- return snprintf(buf, PAGE_SIZE, "1\n");
- return snprintf(buf, PAGE_SIZE, "0\n");
+ acpi_bus_get_device(dock_station->handle, &adev);
+ return snprintf(buf, PAGE_SIZE, "%u\n", acpi_device_enumerated(adev));
}
static DEVICE_ATTR(docked, S_IRUGO, show_docked, NULL);
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 959d41a..d7d32c2 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -67,6 +67,8 @@
#define ACPI_EC_DELAY 500 /* Wait 500ms max. during EC ops */
#define ACPI_EC_UDELAY_GLK 1000 /* Wait 1ms max. to get global lock */
#define ACPI_EC_MSI_UDELAY 550 /* Wait 550us for MSI EC */
+#define ACPI_EC_CLEAR_MAX 100 /* Maximum number of events to query
+ * when trying to clear the EC */
enum {
EC_FLAGS_QUERY_PENDING, /* Query is pending */
@@ -116,6 +118,7 @@
static int EC_FLAGS_MSI; /* Out-of-spec MSI controller */
static int EC_FLAGS_VALIDATE_ECDT; /* ASUStec ECDTs need to be validated */
static int EC_FLAGS_SKIP_DSDT_SCAN; /* Not all BIOS survive early DSDT scan */
+static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */
/* --------------------------------------------------------------------------
Transaction Management
@@ -440,6 +443,29 @@
EXPORT_SYMBOL(ec_get_handle);
+static int acpi_ec_query_unlocked(struct acpi_ec *ec, u8 *data);
+
+/*
+ * Clears stale _Q events that might have accumulated in the EC.
+ * Run with locked ec mutex.
+ */
+static void acpi_ec_clear(struct acpi_ec *ec)
+{
+ int i, status;
+ u8 value = 0;
+
+ for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) {
+ status = acpi_ec_query_unlocked(ec, &value);
+ if (status || !value)
+ break;
+ }
+
+ if (unlikely(i == ACPI_EC_CLEAR_MAX))
+ pr_warn("Warning: Maximum of %d stale EC events cleared\n", i);
+ else
+ pr_info("%d stale EC events cleared\n", i);
+}
+
void acpi_ec_block_transactions(void)
{
struct acpi_ec *ec = first_ec;
@@ -463,6 +489,10 @@
mutex_lock(&ec->mutex);
/* Allow transactions to be carried out again */
clear_bit(EC_FLAGS_BLOCKED, &ec->flags);
+
+ if (EC_FLAGS_CLEAR_ON_RESUME)
+ acpi_ec_clear(ec);
+
mutex_unlock(&ec->mutex);
}
@@ -821,6 +851,13 @@
/* EC is fully operational, allow queries */
clear_bit(EC_FLAGS_QUERY_PENDING, &ec->flags);
+
+ /* Clear stale _Q events if hardware might require that */
+ if (EC_FLAGS_CLEAR_ON_RESUME) {
+ mutex_lock(&ec->mutex);
+ acpi_ec_clear(ec);
+ mutex_unlock(&ec->mutex);
+ }
return ret;
}
@@ -922,6 +959,30 @@
return 0;
}
+/*
+ * On some hardware it is necessary to clear events accumulated by the EC during
+ * sleep. These ECs stop reporting GPEs until they are manually polled, if too
+ * many events are accumulated. (e.g. Samsung Series 5/9 notebooks)
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=44161
+ *
+ * Ideally, the EC should also be instructed NOT to accumulate events during
+ * sleep (which Windows seems to do somehow), but the interface to control this
+ * behaviour is not known at this time.
+ *
+ * Models known to be affected are Samsung 530Uxx/535Uxx/540Uxx/550Pxx/900Xxx,
+ * however it is very likely that other Samsung models are affected.
+ *
+ * On systems which don't accumulate _Q events during sleep, this extra check
+ * should be harmless.
+ */
+static int ec_clear_on_resume(const struct dmi_system_id *id)
+{
+ pr_debug("Detected system needing EC poll on resume.\n");
+ EC_FLAGS_CLEAR_ON_RESUME = 1;
+ return 0;
+}
+
static struct dmi_system_id ec_dmi_table[] __initdata = {
{
ec_skip_dsdt_scan, "Compal JFL92", {
@@ -965,6 +1026,9 @@
ec_validate_ecdt, "ASUS hardware", {
DMI_MATCH(DMI_SYS_VENDOR, "ASUSTek Computer Inc."),
DMI_MATCH(DMI_PRODUCT_NAME, "L4R"),}, NULL},
+ {
+ ec_clear_on_resume, "Samsung hardware", {
+ DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD.")}, NULL},
{},
};
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index 1fb6290..09e423f 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -55,6 +55,9 @@
#ifdef CONFIG_PM_SLEEP
static int acpi_fan_suspend(struct device *dev);
static int acpi_fan_resume(struct device *dev);
+#else
+#define acpi_fan_suspend NULL
+#define acpi_fan_resume NULL
#endif
static SIMPLE_DEV_PM_OPS(acpi_fan_pm, acpi_fan_suspend, acpi_fan_resume);
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 52d45ea..361b40c 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -430,6 +430,7 @@
pin_name(pin));
}
+ kfree(entry);
return 0;
}
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index 28baa05..84243c3 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -56,6 +56,12 @@
int target_state; /* target T-state */
};
+struct acpi_processor_throttling_arg {
+ struct acpi_processor *pr;
+ int target_state;
+ bool force;
+};
+
#define THROTTLING_PRECHANGE (1)
#define THROTTLING_POSTCHANGE (2)
@@ -1060,16 +1066,24 @@
return 0;
}
+static long acpi_processor_throttling_fn(void *data)
+{
+ struct acpi_processor_throttling_arg *arg = data;
+ struct acpi_processor *pr = arg->pr;
+
+ return pr->throttling.acpi_processor_set_throttling(pr,
+ arg->target_state, arg->force);
+}
+
int acpi_processor_set_throttling(struct acpi_processor *pr,
int state, bool force)
{
- cpumask_var_t saved_mask;
int ret = 0;
unsigned int i;
struct acpi_processor *match_pr;
struct acpi_processor_throttling *p_throttling;
+ struct acpi_processor_throttling_arg arg;
struct throttling_tstate t_state;
- cpumask_var_t online_throttling_cpus;
if (!pr)
return -EINVAL;
@@ -1080,14 +1094,6 @@
if ((state < 0) || (state > (pr->throttling.state_count - 1)))
return -EINVAL;
- if (!alloc_cpumask_var(&saved_mask, GFP_KERNEL))
- return -ENOMEM;
-
- if (!alloc_cpumask_var(&online_throttling_cpus, GFP_KERNEL)) {
- free_cpumask_var(saved_mask);
- return -ENOMEM;
- }
-
if (cpu_is_offline(pr->id)) {
/*
* the cpu pointed by pr->id is offline. Unnecessary to change
@@ -1096,17 +1102,15 @@
return -ENODEV;
}
- cpumask_copy(saved_mask, ¤t->cpus_allowed);
t_state.target_state = state;
p_throttling = &(pr->throttling);
- cpumask_and(online_throttling_cpus, cpu_online_mask,
- p_throttling->shared_cpu_map);
+
/*
* The throttling notifier will be called for every
* affected cpu in order to get one proper T-state.
* The notifier event is THROTTLING_PRECHANGE.
*/
- for_each_cpu(i, online_throttling_cpus) {
+ for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) {
t_state.cpu = i;
acpi_processor_throttling_notifier(THROTTLING_PRECHANGE,
&t_state);
@@ -1118,21 +1122,18 @@
* it can be called only for the cpu pointed by pr.
*/
if (p_throttling->shared_type == DOMAIN_COORD_TYPE_SW_ANY) {
- /* FIXME: use work_on_cpu() */
- if (set_cpus_allowed_ptr(current, cpumask_of(pr->id))) {
- /* Can't migrate to the pr->id CPU. Exit */
- ret = -ENODEV;
- goto exit;
- }
- ret = p_throttling->acpi_processor_set_throttling(pr,
- t_state.target_state, force);
+ arg.pr = pr;
+ arg.target_state = state;
+ arg.force = force;
+ ret = work_on_cpu(pr->id, acpi_processor_throttling_fn, &arg);
} else {
/*
* When the T-state coordination is SW_ALL or HW_ALL,
* it is necessary to set T-state for every affected
* cpus.
*/
- for_each_cpu(i, online_throttling_cpus) {
+ for_each_cpu_and(i, cpu_online_mask,
+ p_throttling->shared_cpu_map) {
match_pr = per_cpu(processors, i);
/*
* If the pointer is invalid, we will report the
@@ -1153,13 +1154,12 @@
"on CPU %d\n", i));
continue;
}
- t_state.cpu = i;
- /* FIXME: use work_on_cpu() */
- if (set_cpus_allowed_ptr(current, cpumask_of(i)))
- continue;
- ret = match_pr->throttling.
- acpi_processor_set_throttling(
- match_pr, t_state.target_state, force);
+
+ arg.pr = match_pr;
+ arg.target_state = state;
+ arg.force = force;
+ ret = work_on_cpu(pr->id, acpi_processor_throttling_fn,
+ &arg);
}
}
/*
@@ -1168,17 +1168,12 @@
* affected cpu to update the T-states.
* The notifier event is THROTTLING_POSTCHANGE
*/
- for_each_cpu(i, online_throttling_cpus) {
+ for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) {
t_state.cpu = i;
acpi_processor_throttling_notifier(THROTTLING_POSTCHANGE,
&t_state);
}
- /* restore the previous state */
- /* FIXME: use work_on_cpu() */
- set_cpus_allowed_ptr(current, saved_mask);
-exit:
- free_cpumask_var(online_throttling_cpus);
- free_cpumask_var(saved_mask);
+
return ret;
}
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index b7201fc..0bdacc5 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -77,18 +77,24 @@
switch (ares->type) {
case ACPI_RESOURCE_TYPE_MEMORY24:
memory24 = &ares->data.memory24;
+ if (!memory24->address_length)
+ return false;
acpi_dev_get_memresource(res, memory24->minimum,
memory24->address_length,
memory24->write_protect);
break;
case ACPI_RESOURCE_TYPE_MEMORY32:
memory32 = &ares->data.memory32;
+ if (!memory32->address_length)
+ return false;
acpi_dev_get_memresource(res, memory32->minimum,
memory32->address_length,
memory32->write_protect);
break;
case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
fixed_memory32 = &ares->data.fixed_memory32;
+ if (!fixed_memory32->address_length)
+ return false;
acpi_dev_get_memresource(res, fixed_memory32->address,
fixed_memory32->address_length,
fixed_memory32->write_protect);
@@ -144,12 +150,16 @@
switch (ares->type) {
case ACPI_RESOURCE_TYPE_IO:
io = &ares->data.io;
+ if (!io->address_length)
+ return false;
acpi_dev_get_ioresource(res, io->minimum,
io->address_length,
io->io_decode);
break;
case ACPI_RESOURCE_TYPE_FIXED_IO:
fixed_io = &ares->data.fixed_io;
+ if (!fixed_io->address_length)
+ return false;
acpi_dev_get_ioresource(res, fixed_io->address,
fixed_io->address_length,
ACPI_DECODE_10);
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index d465ae6..dbd4849 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -450,7 +450,7 @@
{
unsigned long x;
struct acpi_battery *battery = to_acpi_battery(dev_get_drvdata(dev));
- if (sscanf(buf, "%ld\n", &x) == 1)
+ if (sscanf(buf, "%lu\n", &x) == 1)
battery->alarm_capacity = x /
(1000 * acpi_battery_scale(battery));
if (battery->present)
@@ -668,6 +668,8 @@
acpi_sbs_callback(sbs);
return 0;
}
+#else
+#define acpi_sbs_resume NULL
#endif
static SIMPLE_DEV_PM_OPS(acpi_sbs_pm, NULL, acpi_sbs_resume);
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index b718806..c40fb2e 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -71,6 +71,17 @@
return 0;
}
+static bool acpi_sleep_state_supported(u8 sleep_state)
+{
+ acpi_status status;
+ u8 type_a, type_b;
+
+ status = acpi_get_sleep_type_data(sleep_state, &type_a, &type_b);
+ return ACPI_SUCCESS(status) && (!acpi_gbl_reduced_hardware
+ || (acpi_gbl_FADT.sleep_control.address
+ && acpi_gbl_FADT.sleep_status.address));
+}
+
#ifdef CONFIG_ACPI_SLEEP
static u32 acpi_target_sleep_state = ACPI_STATE_S0;
@@ -604,15 +615,9 @@
{
int i;
- for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++) {
- acpi_status status;
- u8 type_a, type_b;
-
- status = acpi_get_sleep_type_data(i, &type_a, &type_b);
- if (ACPI_SUCCESS(status)) {
+ for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++)
+ if (acpi_sleep_state_supported(i))
sleep_states[i] = 1;
- }
- }
suspend_set_ops(old_suspend_ordering ?
&acpi_suspend_ops_old : &acpi_suspend_ops);
@@ -740,11 +745,7 @@
static void acpi_sleep_hibernate_setup(void)
{
- acpi_status status;
- u8 type_a, type_b;
-
- status = acpi_get_sleep_type_data(ACPI_STATE_S4, &type_a, &type_b);
- if (ACPI_FAILURE(status))
+ if (!acpi_sleep_state_supported(ACPI_STATE_S4))
return;
hibernation_set_ops(old_suspend_ordering ?
@@ -793,8 +794,6 @@
int __init acpi_sleep_init(void)
{
- acpi_status status;
- u8 type_a, type_b;
char supported[ACPI_S_STATE_COUNT * 3 + 1];
char *pos = supported;
int i;
@@ -806,8 +805,7 @@
acpi_sleep_suspend_setup();
acpi_sleep_hibernate_setup();
- status = acpi_get_sleep_type_data(ACPI_STATE_S5, &type_a, &type_b);
- if (ACPI_SUCCESS(status)) {
+ if (acpi_sleep_state_supported(ACPI_STATE_S5)) {
sleep_states[ACPI_STATE_S5] = 1;
pm_power_off_prepare = acpi_power_off_prepare;
pm_power_off = acpi_power_off;
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 8349a55..08626c8 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -102,6 +102,8 @@
#ifdef CONFIG_PM_SLEEP
static int acpi_thermal_resume(struct device *dev);
+#else
+#define acpi_thermal_resume NULL
#endif
static SIMPLE_DEV_PM_OPS(acpi_thermal_pm, NULL, acpi_thermal_resume);
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index b727d10..b6ba88e 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -81,11 +81,12 @@
module_param(allow_duplicates, bool, 0644);
/*
- * For Windows 8 systems: if set ture and the GPU driver has
- * registered a backlight interface, skip registering ACPI video's.
+ * For Windows 8 systems: used to decide if video module
+ * should skip registering backlight interface of its own.
*/
-static bool use_native_backlight = false;
-module_param(use_native_backlight, bool, 0644);
+static int use_native_backlight_param = -1;
+module_param_named(use_native_backlight, use_native_backlight_param, int, 0444);
+static bool use_native_backlight_dmi = false;
static int register_count;
static struct mutex video_list_lock;
@@ -231,9 +232,17 @@
static int acpi_video_switch_brightness(struct acpi_video_device *device,
int event);
+static bool acpi_video_use_native_backlight(void)
+{
+ if (use_native_backlight_param != -1)
+ return use_native_backlight_param;
+ else
+ return use_native_backlight_dmi;
+}
+
static bool acpi_video_verify_backlight_support(void)
{
- if (acpi_osi_is_win8() && use_native_backlight &&
+ if (acpi_osi_is_win8() && acpi_video_use_native_backlight() &&
backlight_device_registered(BACKLIGHT_RAW))
return false;
return acpi_video_backlight_support();
@@ -398,6 +407,12 @@
return 0;
}
+static int __init video_set_use_native_backlight(const struct dmi_system_id *d)
+{
+ use_native_backlight_dmi = true;
+ return 0;
+}
+
static struct dmi_system_id video_dmi_table[] __initdata = {
/*
* Broken _BQC workaround http://bugzilla.kernel.org/show_bug.cgi?id=13121
@@ -442,6 +457,120 @@
DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7720"),
},
},
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "ThinkPad T430s",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430s"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "ThinkPad X230",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X230"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "ThinkPad X1 Carbon",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X1 Carbon"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "Lenovo Yoga 13",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo IdeaPad Yoga 13"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "Dell Inspiron 7520",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "Inspiron 7520"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "Acer Aspire 5733Z",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5733Z"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "Acer Aspire V5-431",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Aspire V5-431"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "HP ProBook 4340s",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "HP ProBook 4340s"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "HP ProBook 2013 models",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook "),
+ DMI_MATCH(DMI_PRODUCT_NAME, " G1"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "HP EliteBook 2013 models",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook "),
+ DMI_MATCH(DMI_PRODUCT_NAME, " G1"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "HP ZBook 14",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 14"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "HP ZBook 15",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 15"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "HP ZBook 17",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 17"),
+ },
+ },
+ {
+ .callback = video_set_use_native_backlight,
+ .ident = "HP EliteBook 8780w",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 8780w"),
+ },
+ },
{}
};
@@ -685,6 +814,7 @@
union acpi_object *o;
struct acpi_video_device_brightness *br = NULL;
int result = -EINVAL;
+ u32 value;
if (!ACPI_SUCCESS(acpi_video_device_lcd_query_levels(device, &obj))) {
ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Could not query available "
@@ -715,7 +845,12 @@
printk(KERN_ERR PREFIX "Invalid data\n");
continue;
}
- br->levels[count] = (u32) o->integer.value;
+ value = (u32) o->integer.value;
+ /* Skip duplicate entries */
+ if (count > 2 && br->levels[count - 1] == value)
+ continue;
+
+ br->levels[count] = value;
if (br->levels[count] > max_level)
max_level = br->levels[count];
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index a697b77..19080c8 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -168,22 +168,6 @@
DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"),
},
},
- {
- .callback = video_detect_force_vendor,
- .ident = "HP EliteBook Revolve 810",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook Revolve 810 G1"),
- },
- },
- {
- .callback = video_detect_force_vendor,
- .ident = "Lenovo Yoga 13",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
- DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo IdeaPad Yoga 13"),
- },
- },
{ },
};
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 4e73772..868429a 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -247,6 +247,7 @@
config SATA_MV
tristate "Marvell SATA support"
+ select GENERIC_PHY
help
This option enables support for the Marvell Serial ATA family.
Currently supports 88SX[56]0[48][01] PCI(-X) chips,
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index dc2756f..c81d809 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -61,6 +61,7 @@
/* board IDs by feature in alphabetical order */
board_ahci,
board_ahci_ign_iferr,
+ board_ahci_noncq,
board_ahci_nosntf,
board_ahci_yes_fbs,
@@ -121,6 +122,13 @@
.udma_mask = ATA_UDMA6,
.port_ops = &ahci_ops,
},
+ [board_ahci_noncq] = {
+ AHCI_HFLAGS (AHCI_HFLAG_NO_NCQ),
+ .flags = AHCI_FLAG_COMMON,
+ .pio_mask = ATA_PIO4,
+ .udma_mask = ATA_UDMA6,
+ .port_ops = &ahci_ops,
+ },
[board_ahci_nosntf] = {
AHCI_HFLAGS (AHCI_HFLAG_NO_SNTF),
.flags = AHCI_FLAG_COMMON,
@@ -452,6 +460,12 @@
{ PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci }, /* ASM1061 */
{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci }, /* ASM1062 */
+ /*
+ * Samsung SSDs found on some macbooks. NCQ times out.
+ * https://bugzilla.kernel.org/show_bug.cgi?id=60731
+ */
+ { PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_noncq },
+
/* Enmotus */
{ PCI_DEVICE(0x1c44, 0x8000), board_ahci },
@@ -1170,8 +1184,10 @@
nvec = rc;
rc = pci_enable_msi_block(pdev, nvec);
- if (rc)
+ if (rc < 0)
goto intx;
+ else if (rc > 0)
+ goto single_msi;
return nvec;
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 1a3dbd1..8cb2522 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4175,6 +4175,7 @@
/* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */
{ "ST1000LM024 HN-M101MBB", "2AR10001", ATA_HORKAGE_BROKEN_FPDMA_AA },
+ { "ST1000LM024 HN-M101MBB", "2BA30001", ATA_HORKAGE_BROKEN_FPDMA_AA },
/* Blacklist entries taken from Silicon Image 3124/3132
Windows driver .inf file - also several Linux problem reports */
@@ -4224,7 +4225,7 @@
/* devices that don't properly handle queued TRIM commands */
{ "Micron_M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, },
- { "Crucial_CT???M500SSD1", NULL, ATA_HORKAGE_NO_NCQ_TRIM, },
+ { "Crucial_CT???M500SSD*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, },
/*
* Some WD SATA-I drives spin up and down erratically when the link
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index 20fd337..7ccc084 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -447,8 +447,11 @@
* otherwise. Don't try hard to recover it.
*/
ap->pmp_link[ap->nr_pmp_links - 1].flags |= ATA_LFLAG_NO_RETRY;
- } else if (vendor == 0x197b && devid == 0x2352) {
- /* chip found in Thermaltake BlackX Duet, jmicron JMB350? */
+ } else if (vendor == 0x197b && (devid == 0x2352 || devid == 0x0325)) {
+ /*
+ * 0x2352: found in Thermaltake BlackX Duet, jmicron JMB350?
+ * 0x0325: jmicron JMB394.
+ */
ata_for_each_link(link, ap, EDGE) {
/* SRST breaks detection and disks get misclassified
* LPM disabled to avoid potential problems
diff --git a/drivers/ata/pata_imx.c b/drivers/ata/pata_imx.c
index 26386f0..b0b18ec 100644
--- a/drivers/ata/pata_imx.c
+++ b/drivers/ata/pata_imx.c
@@ -119,7 +119,9 @@
return PTR_ERR(priv->clk);
}
- clk_prepare_enable(priv->clk);
+ ret = clk_prepare_enable(priv->clk);
+ if (ret)
+ return ret;
host = ata_host_alloc(&pdev->dev, 1);
if (!host) {
@@ -212,7 +214,9 @@
struct ata_host *host = dev_get_drvdata(dev);
struct pata_imx_priv *priv = host->private_data;
- clk_prepare_enable(priv->clk);
+ int ret = clk_prepare_enable(priv->clk);
+ if (ret)
+ return ret;
__raw_writel(priv->ata_ctl, priv->host_regs + PATA_IMX_ATA_CONTROL);
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 20a7517..05c8a44 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -4104,7 +4104,6 @@
if (!hpriv->port_phys)
return -ENOMEM;
host->private_data = hpriv;
- hpriv->n_ports = n_ports;
hpriv->board_idx = chip_soc;
host->iomap = NULL;
@@ -4126,17 +4125,24 @@
clk_prepare_enable(hpriv->port_clks[port]);
sprintf(port_number, "port%d", port);
- hpriv->port_phys[port] = devm_phy_get(&pdev->dev, port_number);
+ hpriv->port_phys[port] = devm_phy_optional_get(&pdev->dev,
+ port_number);
if (IS_ERR(hpriv->port_phys[port])) {
rc = PTR_ERR(hpriv->port_phys[port]);
hpriv->port_phys[port] = NULL;
- if ((rc != -EPROBE_DEFER) && (rc != -ENODEV))
- dev_warn(&pdev->dev, "error getting phy");
+ if (rc != -EPROBE_DEFER)
+ dev_warn(&pdev->dev, "error getting phy %d", rc);
+
+ /* Cleanup only the initialized ports */
+ hpriv->n_ports = port;
goto err;
} else
phy_power_on(hpriv->port_phys[port]);
}
+ /* All the ports have been initialized */
+ hpriv->n_ports = n_ports;
+
/*
* (Re-)program MBUS remapping windows if we are asked to.
*/
@@ -4174,7 +4180,7 @@
clk_disable_unprepare(hpriv->clk);
clk_put(hpriv->clk);
}
- for (port = 0; port < n_ports; port++) {
+ for (port = 0; port < hpriv->n_ports; port++) {
if (!IS_ERR(hpriv->port_clks[port])) {
clk_disable_unprepare(hpriv->port_clks[port]);
clk_put(hpriv->port_clks[port]);
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index d67fc35..b7695e8 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -157,6 +157,7 @@
{ "ST380011ASL", SIL_QUIRK_MOD15WRITE },
{ "ST3120022ASL", SIL_QUIRK_MOD15WRITE },
{ "ST3160021ASL", SIL_QUIRK_MOD15WRITE },
+ { "TOSHIBA MK2561GSYN", SIL_QUIRK_MOD15WRITE },
{ "Maxtor 4D060H3", SIL_QUIRK_UDMA5MAX },
{ }
};
diff --git a/drivers/atm/ambassador.c b/drivers/atm/ambassador.c
index 62a7607..f1a9198 100644
--- a/drivers/atm/ambassador.c
+++ b/drivers/atm/ambassador.c
@@ -1925,7 +1925,7 @@
const struct firmware *fw;
unsigned long start_address;
const struct ihex_binrec *rec;
- const char *errmsg = 0;
+ const char *errmsg = NULL;
int res;
res = request_ihex_firmware(&fw, "atmsar11.fw", &dev->pci_dev->dev);
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index b41c948..82f2ae0 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -736,8 +736,8 @@
skb = td->skb;
if (skb == FS_VCC (ATM_SKB(skb)->vcc)->last_skb) {
- wake_up_interruptible (& FS_VCC (ATM_SKB(skb)->vcc)->close_wait);
FS_VCC (ATM_SKB(skb)->vcc)->last_skb = NULL;
+ wake_up_interruptible (& FS_VCC (ATM_SKB(skb)->vcc)->close_wait);
}
td->dev->ntxpckts--;
@@ -1123,7 +1123,7 @@
this sleep_on, we'll lose any reference to these packets. Memory leak!
On the other hand, it's awfully convenient that we can abort a "close" that
is taking too long. Maybe just use non-interruptible sleep on? -- REW */
- interruptible_sleep_on (& vcc->close_wait);
+ wait_event_interruptible(vcc->close_wait, !vcc->last_skb);
}
txtp = &atm_vcc->qos.txtp;
@@ -2000,7 +2000,7 @@
fs_dprintk (FS_DEBUG_CLEANUP, "Freeing irq%d.\n", dev->irq);
free_irq (dev->irq, dev);
- del_timer (&dev->timer);
+ del_timer_sync (&dev->timer);
atm_dev_deregister(dev->atm_dev);
free_queue (dev, &dev->hp_txq);
diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c
index 45d5063..909c95b 100644
--- a/drivers/atm/idt77105.c
+++ b/drivers/atm/idt77105.c
@@ -368,9 +368,9 @@
static void __exit idt77105_exit(void)
{
- /* turn off timers */
- del_timer(&stats_timer);
- del_timer(&restart_timer);
+ /* turn off timers */
+ del_timer_sync(&stats_timer);
+ del_timer_sync(&restart_timer);
}
module_exit(idt77105_exit);
diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c
index 9587e95..9988ac9 100644
--- a/drivers/atm/nicstar.c
+++ b/drivers/atm/nicstar.c
@@ -639,9 +639,9 @@
card->hbnr.init = NUM_HB;
card->hbnr.max = MAX_HB;
- card->sm_handle = 0x00000000;
+ card->sm_handle = NULL;
card->sm_addr = 0x00000000;
- card->lg_handle = 0x00000000;
+ card->lg_handle = NULL;
card->lg_addr = 0x00000000;
card->efbie = 1; /* To prevent push_rxbufs from enabling the interrupt */
@@ -979,7 +979,7 @@
addr2 = card->sm_addr;
handle2 = card->sm_handle;
card->sm_addr = 0x00000000;
- card->sm_handle = 0x00000000;
+ card->sm_handle = NULL;
} else { /* (!sm_addr) */
card->sm_addr = addr1;
@@ -993,7 +993,7 @@
addr2 = card->lg_addr;
handle2 = card->lg_handle;
card->lg_addr = 0x00000000;
- card->lg_handle = 0x00000000;
+ card->lg_handle = NULL;
} else { /* (!lg_addr) */
card->lg_addr = addr1;
@@ -1739,10 +1739,10 @@
}
scq->full = 1;
- spin_unlock_irqrestore(&scq->lock, flags);
- interruptible_sleep_on_timeout(&scq->scqfull_waitq,
- SCQFULL_TIMEOUT);
- spin_lock_irqsave(&scq->lock, flags);
+ wait_event_interruptible_lock_irq_timeout(scq->scqfull_waitq,
+ scq->tail != scq->next,
+ scq->lock,
+ SCQFULL_TIMEOUT);
if (scq->full) {
spin_unlock_irqrestore(&scq->lock, flags);
@@ -1789,10 +1789,10 @@
scq->full = 1;
if (has_run++)
break;
- spin_unlock_irqrestore(&scq->lock, flags);
- interruptible_sleep_on_timeout(&scq->scqfull_waitq,
- SCQFULL_TIMEOUT);
- spin_lock_irqsave(&scq->lock, flags);
+ wait_event_interruptible_lock_irq_timeout(scq->scqfull_waitq,
+ scq->tail != scq->next,
+ scq->lock,
+ SCQFULL_TIMEOUT);
}
if (!scq->full) {
diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c
index e3fb496..943cf0d 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -760,7 +760,7 @@
return IRQ_RETVAL(handled);
}
-void solos_bh(unsigned long card_arg)
+static void solos_bh(unsigned long card_arg)
{
struct solos_card *card = (void *)card_arg;
uint32_t card_flags;
diff --git a/drivers/base/component.c b/drivers/base/component.c
index c53efe6..c477899 100644
--- a/drivers/base/component.c
+++ b/drivers/base/component.c
@@ -133,9 +133,16 @@
goto out;
}
+ if (!devres_open_group(master->dev, NULL, GFP_KERNEL)) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
/* Found all components */
ret = master->ops->bind(master->dev);
if (ret < 0) {
+ devres_release_group(master->dev, NULL);
+ dev_info(master->dev, "master bind failed: %d\n", ret);
master_remove_components(master);
goto out;
}
@@ -166,6 +173,7 @@
{
if (master->bound) {
master->ops->unbind(master->dev);
+ devres_release_group(master->dev, NULL);
master->bound = false;
}
diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c
index 1e16cbd..61d6d62 100644
--- a/drivers/base/dma-buf.c
+++ b/drivers/base/dma-buf.c
@@ -616,36 +616,35 @@
if (ret)
return ret;
- seq_printf(s, "\nDma-buf Objects:\n");
- seq_printf(s, "\texp_name\tsize\tflags\tmode\tcount\n");
+ seq_puts(s, "\nDma-buf Objects:\n");
+ seq_puts(s, "size\tflags\tmode\tcount\texp_name\n");
list_for_each_entry(buf_obj, &db_list.head, list_node) {
ret = mutex_lock_interruptible(&buf_obj->lock);
if (ret) {
- seq_printf(s,
- "\tERROR locking buffer object: skipping\n");
+ seq_puts(s,
+ "\tERROR locking buffer object: skipping\n");
continue;
}
- seq_printf(s, "\t");
-
- seq_printf(s, "\t%s\t%08zu\t%08x\t%08x\t%08ld\n",
- buf_obj->exp_name, buf_obj->size,
+ seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\n",
+ buf_obj->size,
buf_obj->file->f_flags, buf_obj->file->f_mode,
- (long)(buf_obj->file->f_count.counter));
+ (long)(buf_obj->file->f_count.counter),
+ buf_obj->exp_name);
- seq_printf(s, "\t\tAttached Devices:\n");
+ seq_puts(s, "\tAttached Devices:\n");
attach_count = 0;
list_for_each_entry(attach_obj, &buf_obj->attachments, node) {
- seq_printf(s, "\t\t");
+ seq_puts(s, "\t");
- seq_printf(s, "%s\n", attach_obj->dev->init_name);
+ seq_printf(s, "%s\n", dev_name(attach_obj->dev));
attach_count++;
}
- seq_printf(s, "\n\t\tTotal %d devices attached\n",
+ seq_printf(s, "Total %d devices attached\n\n",
attach_count);
count++;
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 8a97ddf..c30df50e 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -1580,6 +1580,7 @@
switch (mode) {
case PM_HIBERNATION_PREPARE:
case PM_SUSPEND_PREPARE:
+ case PM_RESTORE_PREPARE:
kill_requests_without_uevent();
device_cache_fw_images();
break;
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 8184451..422b7d8 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -874,7 +874,7 @@
/* Non-zero page count for non-head members of
* compound pages is no longer allowed by the kernel.
*/
- page = compound_trans_head(bv.bv_page);
+ page = compound_head(bv.bv_page);
atomic_inc(&page->_count);
}
}
@@ -887,7 +887,7 @@
struct bvec_iter iter;
bio_for_each_segment(bv, bio, iter) {
- page = compound_trans_head(bv.bv_page);
+ page = compound_head(bv.bv_page);
atomic_dec(&page->_count);
}
}
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 5160269..d777bb7 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -4498,7 +4498,7 @@
}
dev_info(&pdev->dev, "NUMA node %d (closest: %d,%d, probe on %d:%d)\n",
my_node, pcibus_to_node(pdev->bus), dev_to_node(&pdev->dev),
- cpu_to_node(smp_processor_id()), smp_processor_id());
+ cpu_to_node(raw_smp_processor_id()), raw_smp_processor_id());
dd = kzalloc_node(sizeof(struct driver_data), GFP_KERNEL, my_node);
if (dd == NULL) {
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index b52e9a6..54174cb 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -53,7 +53,7 @@
#define MTIP_FTL_REBUILD_TIMEOUT_MS 2400000
/* unaligned IO handling */
-#define MTIP_MAX_UNALIGNED_SLOTS 8
+#define MTIP_MAX_UNALIGNED_SLOTS 2
/* Macro to extract the tag bit number from a tag value. */
#define MTIP_TAG_BIT(tag) (tag & 0x1F)
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 3107282..091b9ea 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -60,7 +60,9 @@
NULL_IRQ_NONE = 0,
NULL_IRQ_SOFTIRQ = 1,
NULL_IRQ_TIMER = 2,
+};
+enum {
NULL_Q_BIO = 0,
NULL_Q_RQ = 1,
NULL_Q_MQ = 2,
@@ -172,18 +174,20 @@
static void end_cmd(struct nullb_cmd *cmd)
{
- if (cmd->rq) {
- if (queue_mode == NULL_Q_MQ)
- blk_mq_end_io(cmd->rq, 0);
- else {
- INIT_LIST_HEAD(&cmd->rq->queuelist);
- blk_end_request_all(cmd->rq, 0);
- }
- } else if (cmd->bio)
+ switch (queue_mode) {
+ case NULL_Q_MQ:
+ blk_mq_end_io(cmd->rq, 0);
+ return;
+ case NULL_Q_RQ:
+ INIT_LIST_HEAD(&cmd->rq->queuelist);
+ blk_end_request_all(cmd->rq, 0);
+ break;
+ case NULL_Q_BIO:
bio_endio(cmd->bio, 0);
+ break;
+ }
- if (queue_mode != NULL_Q_MQ)
- free_cmd(cmd);
+ free_cmd(cmd);
}
static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
@@ -195,6 +199,7 @@
cq = &per_cpu(completion_queues, smp_processor_id());
while ((entry = llist_del_all(&cq->list)) != NULL) {
+ entry = llist_reverse_order(entry);
do {
cmd = container_of(entry, struct nullb_cmd, ll_list);
end_cmd(cmd);
@@ -221,62 +226,32 @@
static void null_softirq_done_fn(struct request *rq)
{
- blk_end_request_all(rq, 0);
+ end_cmd(rq->special);
}
-#ifdef CONFIG_SMP
-
-static void null_ipi_cmd_end_io(void *data)
-{
- struct completion_queue *cq;
- struct llist_node *entry, *next;
- struct nullb_cmd *cmd;
-
- cq = &per_cpu(completion_queues, smp_processor_id());
-
- entry = llist_del_all(&cq->list);
-
- while (entry) {
- next = entry->next;
- cmd = llist_entry(entry, struct nullb_cmd, ll_list);
- end_cmd(cmd);
- entry = next;
- }
-}
-
-static void null_cmd_end_ipi(struct nullb_cmd *cmd)
-{
- struct call_single_data *data = &cmd->csd;
- int cpu = get_cpu();
- struct completion_queue *cq = &per_cpu(completion_queues, cpu);
-
- cmd->ll_list.next = NULL;
-
- if (llist_add(&cmd->ll_list, &cq->list)) {
- data->func = null_ipi_cmd_end_io;
- data->flags = 0;
- __smp_call_function_single(cpu, data, 0);
- }
-
- put_cpu();
-}
-
-#endif /* CONFIG_SMP */
-
static inline void null_handle_cmd(struct nullb_cmd *cmd)
{
/* Complete IO by inline, softirq or timer */
switch (irqmode) {
+ case NULL_IRQ_SOFTIRQ:
+ switch (queue_mode) {
+ case NULL_Q_MQ:
+ blk_mq_complete_request(cmd->rq);
+ break;
+ case NULL_Q_RQ:
+ blk_complete_request(cmd->rq);
+ break;
+ case NULL_Q_BIO:
+ /*
+ * XXX: no proper submitting cpu information available.
+ */
+ end_cmd(cmd);
+ break;
+ }
+ break;
case NULL_IRQ_NONE:
end_cmd(cmd);
break;
- case NULL_IRQ_SOFTIRQ:
-#ifdef CONFIG_SMP
- null_cmd_end_ipi(cmd);
-#else
- end_cmd(cmd);
-#endif
- break;
case NULL_IRQ_TIMER:
null_cmd_end_timer(cmd);
break;
@@ -411,6 +386,7 @@
.queue_rq = null_queue_rq,
.map_queue = blk_mq_map_queue,
.init_hctx = null_init_hctx,
+ .complete = null_softirq_done_fn,
};
static struct blk_mq_reg null_mq_reg = {
@@ -609,13 +585,6 @@
{
unsigned int i;
-#if !defined(CONFIG_SMP)
- if (irqmode == NULL_IRQ_SOFTIRQ) {
- pr_warn("null_blk: softirq completions not available.\n");
- pr_warn("null_blk: using direct completions.\n");
- irqmode = NULL_IRQ_NONE;
- }
-#endif
if (bs > PAGE_SIZE) {
pr_warn("null_blk: invalid block size\n");
pr_warn("null_blk: defaults block size to %lu\n", PAGE_SIZE);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 6a680d4..b1cb3f4 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -110,9 +110,9 @@
return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
}
-static inline void virtblk_request_done(struct virtblk_req *vbr)
+static inline void virtblk_request_done(struct request *req)
{
- struct request *req = vbr->req;
+ struct virtblk_req *vbr = req->special;
int error = virtblk_result(vbr);
if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
@@ -138,7 +138,7 @@
do {
virtqueue_disable_cb(vq);
while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) {
- virtblk_request_done(vbr);
+ blk_mq_complete_request(vbr->req);
req_done = true;
}
if (unlikely(virtqueue_is_broken(vq)))
@@ -479,6 +479,7 @@
.map_queue = blk_mq_map_queue,
.alloc_hctx = blk_mq_alloc_single_hw_queue,
.free_hctx = blk_mq_free_single_hw_queue,
+ .complete = virtblk_request_done,
};
static struct blk_mq_reg virtio_mq_reg = {
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 4b97b86..64c60ed 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -299,7 +299,7 @@
BUG_ON(num != 0);
}
-static void unmap_purged_grants(struct work_struct *work)
+void xen_blkbk_unmap_purged_grants(struct work_struct *work)
{
struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
@@ -375,7 +375,7 @@
pr_debug(DRV_PFX "Going to purge %u persistent grants\n", num_clean);
- INIT_LIST_HEAD(&blkif->persistent_purge_list);
+ BUG_ON(!list_empty(&blkif->persistent_purge_list));
root = &blkif->persistent_gnts;
purge_list:
foreach_grant_safe(persistent_gnt, n, root, node) {
@@ -420,7 +420,6 @@
blkif->vbd.overflow_max_grants = 0;
/* We can defer this work */
- INIT_WORK(&blkif->persistent_purge_work, unmap_purged_grants);
schedule_work(&blkif->persistent_purge_work);
pr_debug(DRV_PFX "Purged %u/%u\n", (total - num_clean), total);
return;
@@ -625,16 +624,8 @@
print_stats(blkif);
}
- /* Since we are shutting down remove all pages from the buffer */
- shrink_free_pagepool(blkif, 0 /* All */);
-
- /* Free all persistent grant pages */
- if (!RB_EMPTY_ROOT(&blkif->persistent_gnts))
- free_persistent_gnts(blkif, &blkif->persistent_gnts,
- blkif->persistent_gnt_c);
-
- BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
- blkif->persistent_gnt_c = 0;
+ /* Drain pending purge work */
+ flush_work(&blkif->persistent_purge_work);
if (log_stats)
print_stats(blkif);
@@ -646,6 +637,23 @@
}
/*
+ * Remove persistent grants and empty the pool of free pages
+ */
+void xen_blkbk_free_caches(struct xen_blkif *blkif)
+{
+ /* Free all persistent grant pages */
+ if (!RB_EMPTY_ROOT(&blkif->persistent_gnts))
+ free_persistent_gnts(blkif, &blkif->persistent_gnts,
+ blkif->persistent_gnt_c);
+
+ BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
+ blkif->persistent_gnt_c = 0;
+
+ /* Since we are shutting down remove all pages from the buffer */
+ shrink_free_pagepool(blkif, 0 /* All */);
+}
+
+/*
* Unmap the grant references, and also remove the M2P over-rides
* used in the 'pending_req'.
*/
@@ -838,7 +846,7 @@
struct grant_page **pages = pending_req->indirect_pages;
struct xen_blkif *blkif = pending_req->blkif;
int indirect_grefs, rc, n, nseg, i;
- struct blkif_request_segment_aligned *segments = NULL;
+ struct blkif_request_segment *segments = NULL;
nseg = pending_req->nr_pages;
indirect_grefs = INDIRECT_PAGES(nseg);
@@ -934,9 +942,7 @@
{
atomic_set(&blkif->drain, 1);
do {
- /* The initial value is one, and one refcnt taken at the
- * start of the xen_blkif_schedule thread. */
- if (atomic_read(&blkif->refcnt) <= 2)
+ if (atomic_read(&blkif->inflight) == 0)
break;
wait_for_completion_interruptible_timeout(
&blkif->drain_complete, HZ);
@@ -976,17 +982,30 @@
* the proper response on the ring.
*/
if (atomic_dec_and_test(&pending_req->pendcnt)) {
- xen_blkbk_unmap(pending_req->blkif,
+ struct xen_blkif *blkif = pending_req->blkif;
+
+ xen_blkbk_unmap(blkif,
pending_req->segments,
pending_req->nr_pages);
- make_response(pending_req->blkif, pending_req->id,
+ make_response(blkif, pending_req->id,
pending_req->operation, pending_req->status);
- xen_blkif_put(pending_req->blkif);
- if (atomic_read(&pending_req->blkif->refcnt) <= 2) {
- if (atomic_read(&pending_req->blkif->drain))
- complete(&pending_req->blkif->drain_complete);
+ free_req(blkif, pending_req);
+ /*
+ * Make sure the request is freed before releasing blkif,
+ * or there could be a race between free_req and the
+ * cleanup done in xen_blkif_free during shutdown.
+ *
+ * NB: The fact that we might try to wake up pending_free_wq
+ * before drain_complete (in case there's a drain going on)
+ * it's not a problem with our current implementation
+ * because we can assure there's no thread waiting on
+ * pending_free_wq if there's a drain going on, but it has
+ * to be taken into account if the current model is changed.
+ */
+ if (atomic_dec_and_test(&blkif->inflight) && atomic_read(&blkif->drain)) {
+ complete(&blkif->drain_complete);
}
- free_req(pending_req->blkif, pending_req);
+ xen_blkif_put(blkif);
}
}
@@ -1240,6 +1259,7 @@
* below (in "!bio") if we are handling a BLKIF_OP_DISCARD.
*/
xen_blkif_get(blkif);
+ atomic_inc(&blkif->inflight);
for (i = 0; i < nseg; i++) {
while ((bio == NULL) ||
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 8d88075..be05277 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -57,7 +57,7 @@
#define MAX_INDIRECT_SEGMENTS 256
#define SEGS_PER_INDIRECT_FRAME \
- (PAGE_SIZE/sizeof(struct blkif_request_segment_aligned))
+ (PAGE_SIZE/sizeof(struct blkif_request_segment))
#define MAX_INDIRECT_PAGES \
((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
#define INDIRECT_PAGES(_segs) \
@@ -278,6 +278,7 @@
/* for barrier (drain) requests */
struct completion drain_complete;
atomic_t drain;
+ atomic_t inflight;
/* One thread per one blkif. */
struct task_struct *xenblkd;
unsigned int waiting_reqs;
@@ -376,6 +377,7 @@
irqreturn_t xen_blkif_be_int(int irq, void *dev_id);
int xen_blkif_schedule(void *arg);
int xen_blkif_purge_persistent(void *arg);
+void xen_blkbk_free_caches(struct xen_blkif *blkif);
int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
struct backend_info *be, int state);
@@ -383,6 +385,7 @@
int xen_blkbk_barrier(struct xenbus_transaction xbt,
struct backend_info *be, int state);
struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be);
+void xen_blkbk_unmap_purged_grants(struct work_struct *work);
static inline void blkif_get_x86_32_req(struct blkif_request *dst,
struct blkif_x86_32_request *src)
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index c2014a0..9a547e6 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -125,8 +125,11 @@
blkif->persistent_gnts.rb_node = NULL;
spin_lock_init(&blkif->free_pages_lock);
INIT_LIST_HEAD(&blkif->free_pages);
+ INIT_LIST_HEAD(&blkif->persistent_purge_list);
blkif->free_pages_num = 0;
atomic_set(&blkif->persistent_gnt_in_use, 0);
+ atomic_set(&blkif->inflight, 0);
+ INIT_WORK(&blkif->persistent_purge_work, xen_blkbk_unmap_purged_grants);
INIT_LIST_HEAD(&blkif->pending_free);
@@ -259,6 +262,17 @@
if (!atomic_dec_and_test(&blkif->refcnt))
BUG();
+ /* Remove all persistent grants and the cache of ballooned pages. */
+ xen_blkbk_free_caches(blkif);
+
+ /* Make sure everything is drained before shutting down */
+ BUG_ON(blkif->persistent_gnt_c != 0);
+ BUG_ON(atomic_read(&blkif->persistent_gnt_in_use) != 0);
+ BUG_ON(blkif->free_pages_num != 0);
+ BUG_ON(!list_empty(&blkif->persistent_purge_list));
+ BUG_ON(!list_empty(&blkif->free_pages));
+ BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
+
/* Check that there is no request in use */
list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
list_del(&req->free_list);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 8dcfb54..efe1b47 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -162,7 +162,7 @@
#define DEV_NAME "xvd" /* name in /dev */
#define SEGS_PER_INDIRECT_FRAME \
- (PAGE_SIZE/sizeof(struct blkif_request_segment_aligned))
+ (PAGE_SIZE/sizeof(struct blkif_request_segment))
#define INDIRECT_GREFS(_segs) \
((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
@@ -393,7 +393,7 @@
unsigned long id;
unsigned int fsect, lsect;
int i, ref, n;
- struct blkif_request_segment_aligned *segments = NULL;
+ struct blkif_request_segment *segments = NULL;
/*
* Used to store if we are able to queue the request by just using
@@ -550,7 +550,7 @@
} else {
n = i % SEGS_PER_INDIRECT_FRAME;
segments[n] =
- (struct blkif_request_segment_aligned) {
+ (struct blkif_request_segment) {
.gref = ref,
.first_sect = fsect,
.last_sect = lsect };
@@ -1904,13 +1904,16 @@
case XenbusStateReconfiguring:
case XenbusStateReconfigured:
case XenbusStateUnknown:
- case XenbusStateClosed:
break;
case XenbusStateConnected:
blkfront_connect(info);
break;
+ case XenbusStateClosed:
+ if (dev->state == XenbusStateClosed)
+ break;
+ /* Missed the backend's Closing state -- fallthrough */
case XenbusStateClosing:
blkfront_closing(info);
break;
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 011e55d..51c557c 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -612,6 +612,8 @@
disksize = PAGE_ALIGN(disksize);
meta = zram_meta_alloc(disksize);
+ if (!meta)
+ return -ENOMEM;
down_write(&zram->init_lock);
if (zram->init_done) {
up_write(&zram->init_lock);
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index fa3243d..1386749 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -499,6 +499,7 @@
config MAX_RAW_DEVS
int "Maximum number of RAW devices to support (1-65536)"
depends on RAW_DRIVER
+ range 1 65536
default "256"
help
The maximum number of RAW devices that are supported.
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index f3223aa..6e8d65e 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -190,7 +190,7 @@
struct raw_device_data *rawdev;
struct block_device *bdev;
- if (number <= 0 || number >= MAX_RAW_MINORS)
+ if (number <= 0 || number >= max_raw_minors)
return -EINVAL;
rawdev = &raw_devices[number];
diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
index bd313f7..c1af80b 100644
--- a/drivers/clk/at91/clk-master.c
+++ b/drivers/clk/at91/clk-master.c
@@ -242,7 +242,7 @@
irq = irq_of_parse_and_map(np, 0);
if (!irq)
- return;
+ goto out_free_characteristics;
clk = at91_clk_register_master(pmc, irq, name, num_parents,
parent_names, layout,
diff --git a/drivers/clk/clk-nomadik.c b/drivers/clk/clk-nomadik.c
index 6a934a5..05e04ce 100644
--- a/drivers/clk/clk-nomadik.c
+++ b/drivers/clk/clk-nomadik.c
@@ -494,6 +494,9 @@
static int __init nomadik_src_clk_init_debugfs(void)
{
+ /* Vital for multiplatform */
+ if (!src_base)
+ return -ENODEV;
src_pcksr0_boot = readl(src_base + SRC_PCKSR0);
src_pcksr1_boot = readl(src_base + SRC_PCKSR1);
debugfs_create_file("nomadik-src-clk", S_IFREG | S_IRUGO,
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 5517944..c42e608 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -2226,24 +2226,25 @@
*/
int __clk_get(struct clk *clk)
{
- if (clk && !try_module_get(clk->owner))
- return 0;
+ if (clk) {
+ if (!try_module_get(clk->owner))
+ return 0;
- kref_get(&clk->ref);
+ kref_get(&clk->ref);
+ }
return 1;
}
void __clk_put(struct clk *clk)
{
- if (WARN_ON_ONCE(IS_ERR(clk)))
+ if (!clk || WARN_ON_ONCE(IS_ERR(clk)))
return;
clk_prepare_lock();
kref_put(&clk->ref, __clk_release);
clk_prepare_unlock();
- if (clk)
- module_put(clk->owner);
+ module_put(clk->owner);
}
/*** clk rate change notifiers ***/
diff --git a/drivers/clk/keystone/gate.c b/drivers/clk/keystone/gate.c
index 17a5983..86f1e36 100644
--- a/drivers/clk/keystone/gate.c
+++ b/drivers/clk/keystone/gate.c
@@ -179,6 +179,7 @@
init.name = name;
init.ops = &clk_psc_ops;
+ init.flags = 0;
init.parent_names = (parent_name ? &parent_name : NULL);
init.num_parents = (parent_name ? 1 : 0);
diff --git a/drivers/clk/mvebu/armada-370.c b/drivers/clk/mvebu/armada-370.c
index 81a202d..bef198a 100644
--- a/drivers/clk/mvebu/armada-370.c
+++ b/drivers/clk/mvebu/armada-370.c
@@ -141,13 +141,6 @@
.num_ratios = ARRAY_SIZE(a370_coreclk_ratios),
};
-static void __init a370_coreclk_init(struct device_node *np)
-{
- mvebu_coreclk_setup(np, &a370_coreclks);
-}
-CLK_OF_DECLARE(a370_core_clk, "marvell,armada-370-core-clock",
- a370_coreclk_init);
-
/*
* Clock Gating Control
*/
@@ -168,9 +161,15 @@
{ }
};
-static void __init a370_clk_gating_init(struct device_node *np)
+static void __init a370_clk_init(struct device_node *np)
{
- mvebu_clk_gating_setup(np, a370_gating_desc);
+ struct device_node *cgnp =
+ of_find_compatible_node(NULL, NULL, "marvell,armada-370-gating-clock");
+
+ mvebu_coreclk_setup(np, &a370_coreclks);
+
+ if (cgnp)
+ mvebu_clk_gating_setup(cgnp, a370_gating_desc);
}
-CLK_OF_DECLARE(a370_clk_gating, "marvell,armada-370-gating-clock",
- a370_clk_gating_init);
+CLK_OF_DECLARE(a370_clk, "marvell,armada-370-core-clock", a370_clk_init);
+
diff --git a/drivers/clk/mvebu/armada-xp.c b/drivers/clk/mvebu/armada-xp.c
index 9922c44..b309431 100644
--- a/drivers/clk/mvebu/armada-xp.c
+++ b/drivers/clk/mvebu/armada-xp.c
@@ -158,13 +158,6 @@
.num_ratios = ARRAY_SIZE(axp_coreclk_ratios),
};
-static void __init axp_coreclk_init(struct device_node *np)
-{
- mvebu_coreclk_setup(np, &axp_coreclks);
-}
-CLK_OF_DECLARE(axp_core_clk, "marvell,armada-xp-core-clock",
- axp_coreclk_init);
-
/*
* Clock Gating Control
*/
@@ -202,9 +195,14 @@
{ }
};
-static void __init axp_clk_gating_init(struct device_node *np)
+static void __init axp_clk_init(struct device_node *np)
{
- mvebu_clk_gating_setup(np, axp_gating_desc);
+ struct device_node *cgnp =
+ of_find_compatible_node(NULL, NULL, "marvell,armada-xp-gating-clock");
+
+ mvebu_coreclk_setup(np, &axp_coreclks);
+
+ if (cgnp)
+ mvebu_clk_gating_setup(cgnp, axp_gating_desc);
}
-CLK_OF_DECLARE(axp_clk_gating, "marvell,armada-xp-gating-clock",
- axp_clk_gating_init);
+CLK_OF_DECLARE(axp_clk, "marvell,armada-xp-core-clock", axp_clk_init);
diff --git a/drivers/clk/mvebu/dove.c b/drivers/clk/mvebu/dove.c
index 38aee1e..b8c2424 100644
--- a/drivers/clk/mvebu/dove.c
+++ b/drivers/clk/mvebu/dove.c
@@ -154,12 +154,6 @@
.num_ratios = ARRAY_SIZE(dove_coreclk_ratios),
};
-static void __init dove_coreclk_init(struct device_node *np)
-{
- mvebu_coreclk_setup(np, &dove_coreclks);
-}
-CLK_OF_DECLARE(dove_core_clk, "marvell,dove-core-clock", dove_coreclk_init);
-
/*
* Clock Gating Control
*/
@@ -186,9 +180,14 @@
{ }
};
-static void __init dove_clk_gating_init(struct device_node *np)
+static void __init dove_clk_init(struct device_node *np)
{
- mvebu_clk_gating_setup(np, dove_gating_desc);
+ struct device_node *cgnp =
+ of_find_compatible_node(NULL, NULL, "marvell,dove-gating-clock");
+
+ mvebu_coreclk_setup(np, &dove_coreclks);
+
+ if (cgnp)
+ mvebu_clk_gating_setup(cgnp, dove_gating_desc);
}
-CLK_OF_DECLARE(dove_clk_gating, "marvell,dove-gating-clock",
- dove_clk_gating_init);
+CLK_OF_DECLARE(dove_clk, "marvell,dove-core-clock", dove_clk_init);
diff --git a/drivers/clk/mvebu/kirkwood.c b/drivers/clk/mvebu/kirkwood.c
index 2636a55..ddb666a 100644
--- a/drivers/clk/mvebu/kirkwood.c
+++ b/drivers/clk/mvebu/kirkwood.c
@@ -193,13 +193,6 @@
.num_ratios = ARRAY_SIZE(kirkwood_coreclk_ratios),
};
-static void __init kirkwood_coreclk_init(struct device_node *np)
-{
- mvebu_coreclk_setup(np, &kirkwood_coreclks);
-}
-CLK_OF_DECLARE(kirkwood_core_clk, "marvell,kirkwood-core-clock",
- kirkwood_coreclk_init);
-
static const struct coreclk_soc_desc mv88f6180_coreclks = {
.get_tclk_freq = kirkwood_get_tclk_freq,
.get_cpu_freq = mv88f6180_get_cpu_freq,
@@ -208,13 +201,6 @@
.num_ratios = ARRAY_SIZE(kirkwood_coreclk_ratios),
};
-static void __init mv88f6180_coreclk_init(struct device_node *np)
-{
- mvebu_coreclk_setup(np, &mv88f6180_coreclks);
-}
-CLK_OF_DECLARE(mv88f6180_core_clk, "marvell,mv88f6180-core-clock",
- mv88f6180_coreclk_init);
-
/*
* Clock Gating Control
*/
@@ -239,9 +225,21 @@
{ }
};
-static void __init kirkwood_clk_gating_init(struct device_node *np)
+static void __init kirkwood_clk_init(struct device_node *np)
{
- mvebu_clk_gating_setup(np, kirkwood_gating_desc);
+ struct device_node *cgnp =
+ of_find_compatible_node(NULL, NULL, "marvell,kirkwood-gating-clock");
+
+
+ if (of_device_is_compatible(np, "marvell,mv88f6180-core-clock"))
+ mvebu_coreclk_setup(np, &mv88f6180_coreclks);
+ else
+ mvebu_coreclk_setup(np, &kirkwood_coreclks);
+
+ if (cgnp)
+ mvebu_clk_gating_setup(cgnp, kirkwood_gating_desc);
}
-CLK_OF_DECLARE(kirkwood_clk_gating, "marvell,kirkwood-gating-clock",
- kirkwood_clk_gating_init);
+CLK_OF_DECLARE(kirkwood_clk, "marvell,kirkwood-core-clock",
+ kirkwood_clk_init);
+CLK_OF_DECLARE(mv88f6180_clk, "marvell,mv88f6180-core-clock",
+ kirkwood_clk_init);
diff --git a/drivers/clk/shmobile/clk-rcar-gen2.c b/drivers/clk/shmobile/clk-rcar-gen2.c
index a59ec21..99c27b1 100644
--- a/drivers/clk/shmobile/clk-rcar-gen2.c
+++ b/drivers/clk/shmobile/clk-rcar-gen2.c
@@ -26,6 +26,8 @@
void __iomem *reg;
};
+#define CPG_FRQCRB 0x00000004
+#define CPG_FRQCRB_KICK BIT(31)
#define CPG_SDCKCR 0x00000074
#define CPG_PLL0CR 0x000000d8
#define CPG_FRQCRC 0x000000e0
@@ -45,6 +47,7 @@
struct cpg_z_clk {
struct clk_hw hw;
void __iomem *reg;
+ void __iomem *kick_reg;
};
#define to_z_clk(_hw) container_of(_hw, struct cpg_z_clk, hw)
@@ -83,17 +86,45 @@
{
struct cpg_z_clk *zclk = to_z_clk(hw);
unsigned int mult;
- u32 val;
+ u32 val, kick;
+ unsigned int i;
mult = div_u64((u64)rate * 32, parent_rate);
mult = clamp(mult, 1U, 32U);
+ if (clk_readl(zclk->kick_reg) & CPG_FRQCRB_KICK)
+ return -EBUSY;
+
val = clk_readl(zclk->reg);
val &= ~CPG_FRQCRC_ZFC_MASK;
val |= (32 - mult) << CPG_FRQCRC_ZFC_SHIFT;
clk_writel(val, zclk->reg);
- return 0;
+ /*
+ * Set KICK bit in FRQCRB to update hardware setting and wait for
+ * clock change completion.
+ */
+ kick = clk_readl(zclk->kick_reg);
+ kick |= CPG_FRQCRB_KICK;
+ clk_writel(kick, zclk->kick_reg);
+
+ /*
+ * Note: There is no HW information about the worst case latency.
+ *
+ * Using experimental measurements, it seems that no more than
+ * ~10 iterations are needed, independently of the CPU rate.
+ * Since this value might be dependant of external xtal rate, pll1
+ * rate or even the other emulation clocks rate, use 1000 as a
+ * "super" safe value.
+ */
+ for (i = 1000; i; i--) {
+ if (!(clk_readl(zclk->kick_reg) & CPG_FRQCRB_KICK))
+ return 0;
+
+ cpu_relax();
+ }
+
+ return -ETIMEDOUT;
}
static const struct clk_ops cpg_z_clk_ops = {
@@ -120,6 +151,7 @@
init.num_parents = 1;
zclk->reg = cpg->reg + CPG_FRQCRC;
+ zclk->kick_reg = cpg->reg + CPG_FRQCRB;
zclk->hw.init = &init;
clk = clk_register(NULL, &zclk->hw);
@@ -186,7 +218,7 @@
const char *name)
{
const struct clk_div_table *table = NULL;
- const char *parent_name = "main";
+ const char *parent_name;
unsigned int shift;
unsigned int mult = 1;
unsigned int div = 1;
@@ -201,23 +233,31 @@
* the multiplier value.
*/
u32 value = clk_readl(cpg->reg + CPG_PLL0CR);
+ parent_name = "main";
mult = ((value >> 24) & ((1 << 7) - 1)) + 1;
} else if (!strcmp(name, "pll1")) {
+ parent_name = "main";
mult = config->pll1_mult / 2;
} else if (!strcmp(name, "pll3")) {
+ parent_name = "main";
mult = config->pll3_mult;
} else if (!strcmp(name, "lb")) {
+ parent_name = "pll1_div2";
div = cpg_mode & BIT(18) ? 36 : 24;
} else if (!strcmp(name, "qspi")) {
+ parent_name = "pll1_div2";
div = (cpg_mode & (BIT(3) | BIT(2) | BIT(1))) == BIT(2)
- ? 16 : 20;
+ ? 8 : 10;
} else if (!strcmp(name, "sdh")) {
+ parent_name = "pll1_div2";
table = cpg_sdh_div_table;
shift = 8;
} else if (!strcmp(name, "sd0")) {
+ parent_name = "pll1_div2";
table = cpg_sd01_div_table;
shift = 4;
} else if (!strcmp(name, "sd1")) {
+ parent_name = "pll1_div2";
table = cpg_sd01_div_table;
shift = 0;
} else if (!strcmp(name, "z")) {
diff --git a/drivers/clk/tegra/clk-divider.c b/drivers/clk/tegra/clk-divider.c
index 4d75b1f..290f9c1 100644
--- a/drivers/clk/tegra/clk-divider.c
+++ b/drivers/clk/tegra/clk-divider.c
@@ -59,7 +59,7 @@
return 0;
if (divider_ux1 > get_max_div(divider))
- return -EINVAL;
+ return get_max_div(divider);
return divider_ux1;
}
diff --git a/drivers/clk/tegra/clk-id.h b/drivers/clk/tegra/clk-id.h
index cf0c323..c39613c 100644
--- a/drivers/clk/tegra/clk-id.h
+++ b/drivers/clk/tegra/clk-id.h
@@ -180,9 +180,13 @@
tegra_clk_sbc6_8,
tegra_clk_sclk,
tegra_clk_sdmmc1,
+ tegra_clk_sdmmc1_8,
tegra_clk_sdmmc2,
+ tegra_clk_sdmmc2_8,
tegra_clk_sdmmc3,
+ tegra_clk_sdmmc3_8,
tegra_clk_sdmmc4,
+ tegra_clk_sdmmc4_8,
tegra_clk_se,
tegra_clk_soc_therm,
tegra_clk_sor0,
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index 5c35885..1fa5c3f 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -371,9 +371,7 @@
static const char *mux_pllm_pllc_pllp_plla_pllc2_c3_clkm[] = {
"pll_m", "pll_c", "pll_p", "pll_a", "pll_c2", "pll_c3", "clk_m"
};
-static u32 mux_pllm_pllc_pllp_plla_pllc2_c3_clkm_idx[] = {
- [0] = 0, [1] = 1, [2] = 2, [3] = 3, [4] = 4, [5] = 6,
-};
+#define mux_pllm_pllc_pllp_plla_pllc2_c3_clkm_idx NULL
static const char *mux_pllm_pllc2_c_c3_pllp_plla_pllc4[] = {
"pll_m", "pll_c2", "pll_c", "pll_c3", "pll_p", "pll_a_out0", "pll_c4",
@@ -465,6 +463,10 @@
MUX("adx1", mux_plla_pllc_pllp_clkm, CLK_SOURCE_ADX1, 180, TEGRA_PERIPH_ON_APB, tegra_clk_adx1),
MUX("amx1", mux_plla_pllc_pllp_clkm, CLK_SOURCE_AMX1, 185, TEGRA_PERIPH_ON_APB, tegra_clk_amx1),
MUX("vi_sensor2", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_VI_SENSOR2, 20, TEGRA_PERIPH_NO_RESET, tegra_clk_vi_sensor2),
+ MUX8("sdmmc1", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC1, 14, 0, tegra_clk_sdmmc1_8),
+ MUX8("sdmmc2", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC2, 9, 0, tegra_clk_sdmmc2_8),
+ MUX8("sdmmc3", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC3, 69, 0, tegra_clk_sdmmc3_8),
+ MUX8("sdmmc4", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC4, 15, 0, tegra_clk_sdmmc4_8),
MUX8("sbc1", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC1, 41, TEGRA_PERIPH_ON_APB, tegra_clk_sbc1_8),
MUX8("sbc2", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC2, 44, TEGRA_PERIPH_ON_APB, tegra_clk_sbc2_8),
MUX8("sbc3", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC3, 46, TEGRA_PERIPH_ON_APB, tegra_clk_sbc3_8),
@@ -492,7 +494,7 @@
UART("uartb", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTB, 7, tegra_clk_uartb),
UART("uartc", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTC, 55, tegra_clk_uartc),
UART("uartd", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTD, 65, tegra_clk_uartd),
- UART("uarte", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTE, 65, tegra_clk_uarte),
+ UART("uarte", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTE, 66, tegra_clk_uarte),
XUSB("xusb_host_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_HOST_SRC, 143, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_host_src),
XUSB("xusb_falcon_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_FALCON_SRC, 143, TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_falcon_src),
XUSB("xusb_fs_src", mux_clkm_48M_pllp_480M, CLK_SOURCE_XUSB_FS_SRC, 143, TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_fs_src),
diff --git a/drivers/clk/tegra/clk-tegra-super-gen4.c b/drivers/clk/tegra/clk-tegra-super-gen4.c
index 05dce4a..feb3201 100644
--- a/drivers/clk/tegra/clk-tegra-super-gen4.c
+++ b/drivers/clk/tegra/clk-tegra-super-gen4.c
@@ -120,7 +120,7 @@
ARRAY_SIZE(cclk_lp_parents),
CLK_SET_RATE_PARENT,
clk_base + CCLKLP_BURST_POLICY,
- 0, 4, 8, 9, NULL);
+ TEGRA_DIVIDER_2, 4, 8, 9, NULL);
*dt_clk = clk;
}
diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c
index 90d9d25..80431f0 100644
--- a/drivers/clk/tegra/clk-tegra114.c
+++ b/drivers/clk/tegra/clk-tegra114.c
@@ -682,12 +682,12 @@
[tegra_clk_timer] = { .dt_id = TEGRA114_CLK_TIMER, .present = true },
[tegra_clk_uarta] = { .dt_id = TEGRA114_CLK_UARTA, .present = true },
[tegra_clk_uartd] = { .dt_id = TEGRA114_CLK_UARTD, .present = true },
- [tegra_clk_sdmmc2] = { .dt_id = TEGRA114_CLK_SDMMC2, .present = true },
+ [tegra_clk_sdmmc2_8] = { .dt_id = TEGRA114_CLK_SDMMC2, .present = true },
[tegra_clk_i2s1] = { .dt_id = TEGRA114_CLK_I2S1, .present = true },
[tegra_clk_i2c1] = { .dt_id = TEGRA114_CLK_I2C1, .present = true },
[tegra_clk_ndflash] = { .dt_id = TEGRA114_CLK_NDFLASH, .present = true },
- [tegra_clk_sdmmc1] = { .dt_id = TEGRA114_CLK_SDMMC1, .present = true },
- [tegra_clk_sdmmc4] = { .dt_id = TEGRA114_CLK_SDMMC4, .present = true },
+ [tegra_clk_sdmmc1_8] = { .dt_id = TEGRA114_CLK_SDMMC1, .present = true },
+ [tegra_clk_sdmmc4_8] = { .dt_id = TEGRA114_CLK_SDMMC4, .present = true },
[tegra_clk_pwm] = { .dt_id = TEGRA114_CLK_PWM, .present = true },
[tegra_clk_i2s0] = { .dt_id = TEGRA114_CLK_I2S0, .present = true },
[tegra_clk_i2s2] = { .dt_id = TEGRA114_CLK_I2S2, .present = true },
@@ -723,7 +723,7 @@
[tegra_clk_bsev] = { .dt_id = TEGRA114_CLK_BSEV, .present = true },
[tegra_clk_i2c3] = { .dt_id = TEGRA114_CLK_I2C3, .present = true },
[tegra_clk_sbc4_8] = { .dt_id = TEGRA114_CLK_SBC4, .present = true },
- [tegra_clk_sdmmc3] = { .dt_id = TEGRA114_CLK_SDMMC3, .present = true },
+ [tegra_clk_sdmmc3_8] = { .dt_id = TEGRA114_CLK_SDMMC3, .present = true },
[tegra_clk_owr] = { .dt_id = TEGRA114_CLK_OWR, .present = true },
[tegra_clk_csite] = { .dt_id = TEGRA114_CLK_CSITE, .present = true },
[tegra_clk_la] = { .dt_id = TEGRA114_CLK_LA, .present = true },
diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index aff86b5..166e02f 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -516,11 +516,11 @@
};
static struct tegra_clk_pll_freq_table pll_p_freq_table[] = {
- {12000000, 216000000, 432, 12, 1, 8},
- {13000000, 216000000, 432, 13, 1, 8},
- {16800000, 216000000, 360, 14, 1, 8},
- {19200000, 216000000, 360, 16, 1, 8},
- {26000000, 216000000, 432, 26, 1, 8},
+ {12000000, 408000000, 408, 12, 0, 8},
+ {13000000, 408000000, 408, 13, 0, 8},
+ {16800000, 408000000, 340, 14, 0, 8},
+ {19200000, 408000000, 340, 16, 0, 8},
+ {26000000, 408000000, 408, 26, 0, 8},
{0, 0, 0, 0, 0, 0},
};
@@ -570,6 +570,15 @@
.flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_USE_LOCK,
};
+static struct div_nmp plld_nmp = {
+ .divm_shift = 0,
+ .divm_width = 5,
+ .divn_shift = 8,
+ .divn_width = 11,
+ .divp_shift = 20,
+ .divp_width = 3,
+};
+
static struct tegra_clk_pll_freq_table pll_d_freq_table[] = {
{12000000, 216000000, 864, 12, 4, 12},
{13000000, 216000000, 864, 13, 4, 12},
@@ -603,19 +612,18 @@
.lock_mask = PLL_BASE_LOCK,
.lock_enable_bit_idx = PLLDU_MISC_LOCK_ENABLE,
.lock_delay = 1000,
- .div_nmp = &pllp_nmp,
+ .div_nmp = &plld_nmp,
.freq_table = pll_d_freq_table,
.flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_SET_LFCON |
TEGRA_PLL_USE_LOCK,
};
static struct tegra_clk_pll_freq_table tegra124_pll_d2_freq_table[] = {
- { 12000000, 148500000, 99, 1, 8},
- { 12000000, 594000000, 99, 1, 1},
- { 13000000, 594000000, 91, 1, 1}, /* actual: 591.5 MHz */
- { 16800000, 594000000, 71, 1, 1}, /* actual: 596.4 MHz */
- { 19200000, 594000000, 62, 1, 1}, /* actual: 595.2 MHz */
- { 26000000, 594000000, 91, 2, 1}, /* actual: 591.5 MHz */
+ { 12000000, 594000000, 99, 1, 2},
+ { 13000000, 594000000, 91, 1, 2}, /* actual: 591.5 MHz */
+ { 16800000, 594000000, 71, 1, 2}, /* actual: 596.4 MHz */
+ { 19200000, 594000000, 62, 1, 2}, /* actual: 595.2 MHz */
+ { 26000000, 594000000, 91, 2, 2}, /* actual: 591.5 MHz */
{ 0, 0, 0, 0, 0, 0 },
};
@@ -753,21 +761,19 @@
[tegra_clk_rtc] = { .dt_id = TEGRA124_CLK_RTC, .present = true },
[tegra_clk_timer] = { .dt_id = TEGRA124_CLK_TIMER, .present = true },
[tegra_clk_uarta] = { .dt_id = TEGRA124_CLK_UARTA, .present = true },
- [tegra_clk_sdmmc2] = { .dt_id = TEGRA124_CLK_SDMMC2, .present = true },
+ [tegra_clk_sdmmc2_8] = { .dt_id = TEGRA124_CLK_SDMMC2, .present = true },
[tegra_clk_i2s1] = { .dt_id = TEGRA124_CLK_I2S1, .present = true },
[tegra_clk_i2c1] = { .dt_id = TEGRA124_CLK_I2C1, .present = true },
[tegra_clk_ndflash] = { .dt_id = TEGRA124_CLK_NDFLASH, .present = true },
- [tegra_clk_sdmmc1] = { .dt_id = TEGRA124_CLK_SDMMC1, .present = true },
- [tegra_clk_sdmmc4] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true },
+ [tegra_clk_sdmmc1_8] = { .dt_id = TEGRA124_CLK_SDMMC1, .present = true },
+ [tegra_clk_sdmmc4_8] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true },
[tegra_clk_pwm] = { .dt_id = TEGRA124_CLK_PWM, .present = true },
[tegra_clk_i2s2] = { .dt_id = TEGRA124_CLK_I2S2, .present = true },
- [tegra_clk_gr2d] = { .dt_id = TEGRA124_CLK_GR_2D, .present = true },
[tegra_clk_usbd] = { .dt_id = TEGRA124_CLK_USBD, .present = true },
[tegra_clk_isp_8] = { .dt_id = TEGRA124_CLK_ISP, .present = true },
- [tegra_clk_gr3d] = { .dt_id = TEGRA124_CLK_GR_3D, .present = true },
[tegra_clk_disp2] = { .dt_id = TEGRA124_CLK_DISP2, .present = true },
[tegra_clk_disp1] = { .dt_id = TEGRA124_CLK_DISP1, .present = true },
- [tegra_clk_host1x] = { .dt_id = TEGRA124_CLK_HOST1X, .present = true },
+ [tegra_clk_host1x_8] = { .dt_id = TEGRA124_CLK_HOST1X, .present = true },
[tegra_clk_vcp] = { .dt_id = TEGRA124_CLK_VCP, .present = true },
[tegra_clk_i2s0] = { .dt_id = TEGRA124_CLK_I2S0, .present = true },
[tegra_clk_apbdma] = { .dt_id = TEGRA124_CLK_APBDMA, .present = true },
@@ -794,7 +800,7 @@
[tegra_clk_uartd] = { .dt_id = TEGRA124_CLK_UARTD, .present = true },
[tegra_clk_i2c3] = { .dt_id = TEGRA124_CLK_I2C3, .present = true },
[tegra_clk_sbc4] = { .dt_id = TEGRA124_CLK_SBC4, .present = true },
- [tegra_clk_sdmmc3] = { .dt_id = TEGRA124_CLK_SDMMC3, .present = true },
+ [tegra_clk_sdmmc3_8] = { .dt_id = TEGRA124_CLK_SDMMC3, .present = true },
[tegra_clk_pcie] = { .dt_id = TEGRA124_CLK_PCIE, .present = true },
[tegra_clk_owr] = { .dt_id = TEGRA124_CLK_OWR, .present = true },
[tegra_clk_afi] = { .dt_id = TEGRA124_CLK_AFI, .present = true },
@@ -1286,9 +1292,9 @@
clk_register_clkdev(clk, "pll_d2", NULL);
clks[TEGRA124_CLK_PLL_D2] = clk;
- /* PLLD2_OUT0 ?? */
+ /* PLLD2_OUT0 */
clk = clk_register_fixed_factor(NULL, "pll_d2_out0", "pll_d2",
- CLK_SET_RATE_PARENT, 1, 2);
+ CLK_SET_RATE_PARENT, 1, 1);
clk_register_clkdev(clk, "pll_d2_out0", NULL);
clks[TEGRA124_CLK_PLL_D2_OUT0] = clk;
diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c
index dbace15..dace2b1 100644
--- a/drivers/clk/tegra/clk-tegra20.c
+++ b/drivers/clk/tegra/clk-tegra20.c
@@ -574,6 +574,8 @@
[tegra_clk_tvdac] = { .dt_id = TEGRA20_CLK_TVDAC, .present = true },
[tegra_clk_vi_sensor] = { .dt_id = TEGRA20_CLK_VI_SENSOR, .present = true },
[tegra_clk_afi] = { .dt_id = TEGRA20_CLK_AFI, .present = true },
+ [tegra_clk_fuse] = { .dt_id = TEGRA20_CLK_FUSE, .present = true },
+ [tegra_clk_kfuse] = { .dt_id = TEGRA20_CLK_KFUSE, .present = true },
};
static unsigned long tegra20_clk_measure_input_freq(void)
diff --git a/drivers/clocksource/bcm_kona_timer.c b/drivers/clocksource/bcm_kona_timer.c
index 974b2db..0595dc6 100644
--- a/drivers/clocksource/bcm_kona_timer.c
+++ b/drivers/clocksource/bcm_kona_timer.c
@@ -99,31 +99,6 @@
return;
}
-static void __init kona_timers_init(struct device_node *node)
-{
- u32 freq;
- struct clk *external_clk;
-
- external_clk = of_clk_get_by_name(node, NULL);
-
- if (!IS_ERR(external_clk)) {
- arch_timer_rate = clk_get_rate(external_clk);
- clk_prepare_enable(external_clk);
- } else if (!of_property_read_u32(node, "clock-frequency", &freq)) {
- arch_timer_rate = freq;
- } else {
- panic("unable to determine clock-frequency");
- }
-
- /* Setup IRQ numbers */
- timers.tmr_irq = irq_of_parse_and_map(node, 0);
-
- /* Setup IO addresses */
- timers.tmr_regs = of_iomap(node, 0);
-
- kona_timer_disable_and_clear(timers.tmr_regs);
-}
-
static int kona_timer_set_next_event(unsigned long clc,
struct clock_event_device *unused)
{
@@ -198,7 +173,34 @@
static void __init kona_timer_init(struct device_node *node)
{
- kona_timers_init(node);
+ u32 freq;
+ struct clk *external_clk;
+
+ if (!of_device_is_available(node)) {
+ pr_info("Kona Timer v1 marked as disabled in device tree\n");
+ return;
+ }
+
+ external_clk = of_clk_get_by_name(node, NULL);
+
+ if (!IS_ERR(external_clk)) {
+ arch_timer_rate = clk_get_rate(external_clk);
+ clk_prepare_enable(external_clk);
+ } else if (!of_property_read_u32(node, "clock-frequency", &freq)) {
+ arch_timer_rate = freq;
+ } else {
+ pr_err("Kona Timer v1 unable to determine clock-frequency");
+ return;
+ }
+
+ /* Setup IRQ numbers */
+ timers.tmr_irq = irq_of_parse_and_map(node, 0);
+
+ /* Setup IO addresses */
+ timers.tmr_regs = of_iomap(node, 0);
+
+ kona_timer_disable_and_clear(timers.tmr_regs);
+
kona_timer_clockevents_init();
setup_irq(timers.tmr_irq, &kona_timer_irq);
kona_timer_set_next_event((arch_timer_rate / HZ), NULL);
diff --git a/drivers/clocksource/vf_pit_timer.c b/drivers/clocksource/vf_pit_timer.c
index 02821b0..a918bc4 100644
--- a/drivers/clocksource/vf_pit_timer.c
+++ b/drivers/clocksource/vf_pit_timer.c
@@ -54,7 +54,7 @@
static u64 pit_read_sched_clock(void)
{
- return __raw_readl(clksrc_base + PITCVAL);
+ return ~__raw_readl(clksrc_base + PITCVAL);
}
static int __init pit_clocksource_init(unsigned long rate)
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index a36749f..9b0ea0a 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -139,7 +139,6 @@
spin_unlock_bh(&dev->cbdev->queue_lock);
if (cbq != NULL) {
- err = 0;
cbq->callback(msg, nsp);
kfree_skb(skb);
cn_queue_release_callback(cbq);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 08ca8c9..199b52b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1109,12 +1109,27 @@
goto err_set_policy_cpu;
}
+ /* related cpus should atleast have policy->cpus */
+ cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
+
+ /*
+ * affected cpus must always be the one, which are online. We aren't
+ * managing offline cpus here.
+ */
+ cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
+
+ if (!frozen) {
+ policy->user_policy.min = policy->min;
+ policy->user_policy.max = policy->max;
+ }
+
+ down_write(&policy->rwsem);
write_lock_irqsave(&cpufreq_driver_lock, flags);
for_each_cpu(j, policy->cpus)
per_cpu(cpufreq_cpu_data, j) = policy;
write_unlock_irqrestore(&cpufreq_driver_lock, flags);
- if (cpufreq_driver->get) {
+ if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
policy->cur = cpufreq_driver->get(policy->cpu);
if (!policy->cur) {
pr_err("%s: ->get() failed\n", __func__);
@@ -1162,20 +1177,6 @@
}
}
- /* related cpus should atleast have policy->cpus */
- cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
-
- /*
- * affected cpus must always be the one, which are online. We aren't
- * managing offline cpus here.
- */
- cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
-
- if (!frozen) {
- policy->user_policy.min = policy->min;
- policy->user_policy.max = policy->max;
- }
-
blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
CPUFREQ_START, policy);
@@ -1206,6 +1207,7 @@
policy->user_policy.policy = policy->policy;
policy->user_policy.governor = policy->governor;
}
+ up_write(&policy->rwsem);
kobject_uevent(&policy->kobj, KOBJ_ADD);
up_read(&cpufreq_rwsem);
@@ -1323,8 +1325,7 @@
up_read(&policy->rwsem);
if (cpu != policy->cpu) {
- if (!frozen)
- sysfs_remove_link(&dev->kobj, "cpufreq");
+ sysfs_remove_link(&dev->kobj, "cpufreq");
} else if (cpus > 1) {
new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu);
if (new_cpu >= 0) {
@@ -1547,23 +1548,16 @@
*/
unsigned int cpufreq_get(unsigned int cpu)
{
- struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
+ struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
unsigned int ret_freq = 0;
- if (cpufreq_disabled() || !cpufreq_driver)
- return -ENOENT;
+ if (policy) {
+ down_read(&policy->rwsem);
+ ret_freq = __cpufreq_get(cpu);
+ up_read(&policy->rwsem);
- BUG_ON(!policy);
-
- if (!down_read_trylock(&cpufreq_rwsem))
- return 0;
-
- down_read(&policy->rwsem);
-
- ret_freq = __cpufreq_get(cpu);
-
- up_read(&policy->rwsem);
- up_read(&cpufreq_rwsem);
+ cpufreq_cpu_put(policy);
+ }
return ret_freq;
}
@@ -2149,7 +2143,7 @@
* BIOS might change freq behind our back
* -> ask driver for current freq and notify governors about a change
*/
- if (cpufreq_driver->get) {
+ if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
new_policy.cur = cpufreq_driver->get(cpu);
if (!policy->cur) {
pr_debug("Driver did not initialize current freq");
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 79606f473..2cd36b9 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -34,12 +34,15 @@
#define SAMPLE_COUNT 3
-#define BYT_RATIOS 0x66a
-#define BYT_VIDS 0x66b
+#define BYT_RATIOS 0x66a
+#define BYT_VIDS 0x66b
+#define BYT_TURBO_RATIOS 0x66c
-#define FRAC_BITS 8
+
+#define FRAC_BITS 6
#define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
#define fp_toint(X) ((X) >> FRAC_BITS)
+#define FP_ROUNDUP(X) ((X) += 1 << FRAC_BITS)
static inline int32_t mul_fp(int32_t x, int32_t y)
{
@@ -51,8 +54,6 @@
return div_s64((int64_t)x << FRAC_BITS, (int64_t)y);
}
-static u64 energy_divisor;
-
struct sample {
int32_t core_pct_busy;
u64 aperf;
@@ -359,7 +360,7 @@
{
u64 value;
rdmsrl(BYT_RATIOS, value);
- return value & 0xFF;
+ return (value >> 8) & 0xFF;
}
static int byt_get_max_pstate(void)
@@ -369,6 +370,13 @@
return (value >> 16) & 0xFF;
}
+static int byt_get_turbo_pstate(void)
+{
+ u64 value;
+ rdmsrl(BYT_TURBO_RATIOS, value);
+ return value & 0x3F;
+}
+
static void byt_set_pstate(struct cpudata *cpudata, int pstate)
{
u64 val;
@@ -471,7 +479,7 @@
.funcs = {
.get_max = byt_get_max_pstate,
.get_min = byt_get_min_pstate,
- .get_turbo = byt_get_max_pstate,
+ .get_turbo = byt_get_turbo_pstate,
.set = byt_set_pstate,
.get_vid = byt_get_vid,
},
@@ -549,18 +557,20 @@
static inline void intel_pstate_calc_busy(struct cpudata *cpu,
struct sample *sample)
{
- u64 core_pct;
- u64 c0_pct;
+ int32_t core_pct;
+ int32_t c0_pct;
- core_pct = div64_u64(sample->aperf * 100, sample->mperf);
+ core_pct = div_fp(int_tofp((sample->aperf)),
+ int_tofp((sample->mperf)));
+ core_pct = mul_fp(core_pct, int_tofp(100));
+ FP_ROUNDUP(core_pct);
- c0_pct = div64_u64(sample->mperf * 100, sample->tsc);
+ c0_pct = div_fp(int_tofp(sample->mperf), int_tofp(sample->tsc));
+
sample->freq = fp_toint(
- mul_fp(int_tofp(cpu->pstate.max_pstate),
- int_tofp(core_pct * 1000)));
+ mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct));
- sample->core_pct_busy = mul_fp(int_tofp(core_pct),
- div_fp(int_tofp(c0_pct + 1), int_tofp(100)));
+ sample->core_pct_busy = mul_fp(core_pct, c0_pct);
}
static inline void intel_pstate_sample(struct cpudata *cpu)
@@ -572,6 +582,10 @@
rdmsrl(MSR_IA32_MPERF, mperf);
tsc = native_read_tsc();
+ aperf = aperf >> FRAC_BITS;
+ mperf = mperf >> FRAC_BITS;
+ tsc = tsc >> FRAC_BITS;
+
cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
cpu->samples[cpu->sample_ptr].aperf = aperf;
cpu->samples[cpu->sample_ptr].mperf = mperf;
@@ -603,7 +617,8 @@
core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy;
max_pstate = int_tofp(cpu->pstate.max_pstate);
current_pstate = int_tofp(cpu->pstate.current_pstate);
- return mul_fp(core_busy, div_fp(max_pstate, current_pstate));
+ core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
+ return FP_ROUNDUP(core_busy);
}
static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
@@ -630,12 +645,10 @@
{
struct cpudata *cpu = (struct cpudata *) __data;
struct sample *sample;
- u64 energy;
intel_pstate_sample(cpu);
sample = &cpu->samples[cpu->sample_ptr];
- rdmsrl(MSR_PKG_ENERGY_STATUS, energy);
intel_pstate_adjust_busy_pstate(cpu);
@@ -644,7 +657,6 @@
cpu->pstate.current_pstate,
sample->mperf,
sample->aperf,
- div64_u64(energy, energy_divisor),
sample->freq);
intel_pstate_set_sample_time(cpu);
@@ -926,7 +938,6 @@
int cpu, rc = 0;
const struct x86_cpu_id *id;
struct cpu_defaults *cpu_info;
- u64 units;
if (no_load)
return -ENODEV;
@@ -960,9 +971,6 @@
if (rc)
goto out;
- rdmsrl(MSR_RAPL_POWER_UNIT, units);
- energy_divisor = 1 << ((units >> 8) & 0x1f); /* bits{12:8} */
-
intel_pstate_debug_expose_params();
intel_pstate_sysfs_expose_params();
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index e10b646..6684e03 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1076,7 +1076,7 @@
{
struct powernow_k8_data *data;
struct init_on_cpu init_on_cpu;
- int rc;
+ int rc, cpu;
smp_call_function_single(pol->cpu, check_supported_cpu, &rc, 1);
if (rc)
@@ -1140,7 +1140,9 @@
pr_debug("cpu_init done, current fid 0x%x, vid 0x%x\n",
data->currfid, data->currvid);
- per_cpu(powernow_data, pol->cpu) = data;
+ /* Point all the CPUs in this policy to the same data */
+ for_each_cpu(cpu, pol->cpus)
+ per_cpu(powernow_data, cpu) = data;
return 0;
@@ -1155,6 +1157,7 @@
static int powernowk8_cpu_exit(struct cpufreq_policy *pol)
{
struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
+ int cpu;
if (!data)
return -EINVAL;
@@ -1165,7 +1168,8 @@
kfree(data->powernow_table);
kfree(data);
- per_cpu(powernow_data, pol->cpu) = NULL;
+ for_each_cpu(cpu, pol->cpus)
+ per_cpu(powernow_data, cpu) = NULL;
return 0;
}
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index 6c4c000..1e5481d 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -158,6 +158,15 @@
return sl->entry_nr * sizeof(struct nx842_slentry);
}
+static inline unsigned long nx842_get_pa(void *addr)
+{
+ if (is_vmalloc_addr(addr))
+ return page_to_phys(vmalloc_to_page(addr))
+ + offset_in_page(addr);
+ else
+ return __pa(addr);
+}
+
static int nx842_build_scatterlist(unsigned long buf, int len,
struct nx842_scatterlist *sl)
{
@@ -168,7 +177,7 @@
entry = sl->entries;
while (len) {
- entry->ptr = __pa(buf);
+ entry->ptr = nx842_get_pa((void *)buf);
nextpage = ALIGN(buf + 1, NX842_HW_PAGE_SIZE);
if (nextpage < buf + len) {
/* we aren't at the end yet */
@@ -370,8 +379,8 @@
op.flags = NX842_OP_COMPRESS;
csbcpb = &workmem->csbcpb;
memset(csbcpb, 0, sizeof(*csbcpb));
- op.csbcpb = __pa(csbcpb);
- op.out = __pa(slout.entries);
+ op.csbcpb = nx842_get_pa(csbcpb);
+ op.out = nx842_get_pa(slout.entries);
for (i = 0; i < hdr->blocks_nr; i++) {
/*
@@ -401,13 +410,13 @@
*/
if (likely(max_sync_size == NX842_HW_PAGE_SIZE)) {
/* Create direct DDE */
- op.in = __pa(inbuf);
+ op.in = nx842_get_pa((void *)inbuf);
op.inlen = max_sync_size;
} else {
/* Create indirect DDE (scatterlist) */
nx842_build_scatterlist(inbuf, max_sync_size, &slin);
- op.in = __pa(slin.entries);
+ op.in = nx842_get_pa(slin.entries);
op.inlen = -nx842_get_scatterlist_size(&slin);
}
@@ -565,7 +574,7 @@
op.flags = NX842_OP_DECOMPRESS;
csbcpb = &workmem->csbcpb;
memset(csbcpb, 0, sizeof(*csbcpb));
- op.csbcpb = __pa(csbcpb);
+ op.csbcpb = nx842_get_pa(csbcpb);
/*
* max_sync_size may have changed since compression,
@@ -597,12 +606,12 @@
if (likely((inbuf & NX842_HW_PAGE_MASK) ==
((inbuf + hdr->sizes[i] - 1) & NX842_HW_PAGE_MASK))) {
/* Create direct DDE */
- op.in = __pa(inbuf);
+ op.in = nx842_get_pa((void *)inbuf);
op.inlen = hdr->sizes[i];
} else {
/* Create indirect DDE (scatterlist) */
nx842_build_scatterlist(inbuf, hdr->sizes[i] , &slin);
- op.in = __pa(slin.entries);
+ op.in = nx842_get_pa(slin.entries);
op.inlen = -nx842_get_scatterlist_size(&slin);
}
@@ -613,12 +622,12 @@
*/
if (likely(max_sync_size == NX842_HW_PAGE_SIZE)) {
/* Create direct DDE */
- op.out = __pa(outbuf);
+ op.out = nx842_get_pa((void *)outbuf);
op.outlen = max_sync_size;
} else {
/* Create indirect DDE (scatterlist) */
nx842_build_scatterlist(outbuf, max_sync_size, &slout);
- op.out = __pa(slout.entries);
+ op.out = nx842_get_pa(slout.entries);
op.outlen = -nx842_get_scatterlist_size(&slout);
}
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 9bed1a2..605b016 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -346,6 +346,7 @@
tristate "MOXART DMA support"
depends on ARCH_MOXART
select DMA_ENGINE
+ select DMA_OF
select DMA_VIRTUAL_CHANNELS
help
Enable support for the MOXA ART SoC DMA controller.
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 4e79183..19041ce 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -449,6 +449,7 @@
{ .compatible = "fsl,imx51-sdma", .data = &sdma_imx51, },
{ .compatible = "fsl,imx35-sdma", .data = &sdma_imx35, },
{ .compatible = "fsl,imx31-sdma", .data = &sdma_imx31, },
+ { .compatible = "fsl,imx25-sdma", .data = &sdma_imx25, },
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, sdma_dt_ids);
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 8752918..4e3549a 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -77,7 +77,8 @@
attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET);
for_each_set_bit(bit, &attnstatus, BITS_PER_LONG) {
chan = ioat_chan_by_index(instance, bit);
- tasklet_schedule(&chan->cleanup_task);
+ if (test_bit(IOAT_RUN, &chan->state))
+ tasklet_schedule(&chan->cleanup_task);
}
writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET);
@@ -93,7 +94,8 @@
{
struct ioat_chan_common *chan = data;
- tasklet_schedule(&chan->cleanup_task);
+ if (test_bit(IOAT_RUN, &chan->state))
+ tasklet_schedule(&chan->cleanup_task);
return IRQ_HANDLED;
}
@@ -116,7 +118,6 @@
chan->timer.function = device->timer_fn;
chan->timer.data = data;
tasklet_init(&chan->cleanup_task, device->cleanup_fn, data);
- tasklet_disable(&chan->cleanup_task);
}
/**
@@ -354,13 +355,49 @@
writel(((u64) chan->completion_dma) >> 32,
chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
- tasklet_enable(&chan->cleanup_task);
+ set_bit(IOAT_RUN, &chan->state);
ioat1_dma_start_null_desc(ioat); /* give chain to dma device */
dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n",
__func__, ioat->desccount);
return ioat->desccount;
}
+void ioat_stop(struct ioat_chan_common *chan)
+{
+ struct ioatdma_device *device = chan->device;
+ struct pci_dev *pdev = device->pdev;
+ int chan_id = chan_num(chan);
+ struct msix_entry *msix;
+
+ /* 1/ stop irq from firing tasklets
+ * 2/ stop the tasklet from re-arming irqs
+ */
+ clear_bit(IOAT_RUN, &chan->state);
+
+ /* flush inflight interrupts */
+ switch (device->irq_mode) {
+ case IOAT_MSIX:
+ msix = &device->msix_entries[chan_id];
+ synchronize_irq(msix->vector);
+ break;
+ case IOAT_MSI:
+ case IOAT_INTX:
+ synchronize_irq(pdev->irq);
+ break;
+ default:
+ break;
+ }
+
+ /* flush inflight timers */
+ del_timer_sync(&chan->timer);
+
+ /* flush inflight tasklet runs */
+ tasklet_kill(&chan->cleanup_task);
+
+ /* final cleanup now that everything is quiesced and can't re-arm */
+ device->cleanup_fn((unsigned long) &chan->common);
+}
+
/**
* ioat1_dma_free_chan_resources - release all the descriptors
* @chan: the channel to be cleaned
@@ -379,9 +416,7 @@
if (ioat->desccount == 0)
return;
- tasklet_disable(&chan->cleanup_task);
- del_timer_sync(&chan->timer);
- ioat1_cleanup(ioat);
+ ioat_stop(chan);
/* Delay 100ms after reset to allow internal DMA logic to quiesce
* before removing DMA descriptor resources.
@@ -526,8 +561,11 @@
static void ioat1_cleanup_event(unsigned long data)
{
struct ioat_dma_chan *ioat = to_ioat_chan((void *) data);
+ struct ioat_chan_common *chan = &ioat->base;
ioat1_cleanup(ioat);
+ if (!test_bit(IOAT_RUN, &chan->state))
+ return;
writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
}
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 11fb877..e982f00 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -356,6 +356,7 @@
void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type);
void ioat_kobject_del(struct ioatdma_device *device);
int ioat_dma_setup_interrupts(struct ioatdma_device *device);
+void ioat_stop(struct ioat_chan_common *chan);
extern const struct sysfs_ops ioat_sysfs_ops;
extern struct ioat_sysfs_entry ioat_version_attr;
extern struct ioat_sysfs_entry ioat_cap_attr;
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index 5d3affe..8d10580 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -190,8 +190,11 @@
void ioat2_cleanup_event(unsigned long data)
{
struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+ struct ioat_chan_common *chan = &ioat->base;
ioat2_cleanup(ioat);
+ if (!test_bit(IOAT_RUN, &chan->state))
+ return;
writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
}
@@ -553,10 +556,10 @@
ioat->issued = 0;
ioat->tail = 0;
ioat->alloc_order = order;
+ set_bit(IOAT_RUN, &chan->state);
spin_unlock_bh(&ioat->prep_lock);
spin_unlock_bh(&chan->cleanup_lock);
- tasklet_enable(&chan->cleanup_task);
ioat2_start_null_desc(ioat);
/* check that we got off the ground */
@@ -566,7 +569,6 @@
} while (i++ < 20 && !is_ioat_active(status) && !is_ioat_idle(status));
if (is_ioat_active(status) || is_ioat_idle(status)) {
- set_bit(IOAT_RUN, &chan->state);
return 1 << ioat->alloc_order;
} else {
u32 chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
@@ -809,11 +811,8 @@
if (!ioat->ring)
return;
- tasklet_disable(&chan->cleanup_task);
- del_timer_sync(&chan->timer);
- device->cleanup_fn((unsigned long) c);
+ ioat_stop(chan);
device->reset_hw(chan);
- clear_bit(IOAT_RUN, &chan->state);
spin_lock_bh(&chan->cleanup_lock);
spin_lock_bh(&ioat->prep_lock);
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index 820817e9..b9b38a1 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -464,8 +464,11 @@
static void ioat3_cleanup_event(unsigned long data)
{
struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+ struct ioat_chan_common *chan = &ioat->base;
ioat3_cleanup(ioat);
+ if (!test_bit(IOAT_RUN, &chan->state))
+ return;
writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
}
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 53fb0c8..766b68e 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -497,8 +497,8 @@
if (!mv_can_chain(grp_start))
goto submit_done;
- dev_dbg(mv_chan_to_devp(mv_chan), "Append to last desc %x\n",
- old_chain_tail->async_tx.phys);
+ dev_dbg(mv_chan_to_devp(mv_chan), "Append to last desc %pa\n",
+ &old_chain_tail->async_tx.phys);
/* fix up the hardware chain */
mv_desc_set_next_desc(old_chain_tail, grp_start->async_tx.phys);
@@ -527,7 +527,8 @@
/* returns the number of allocated descriptors */
static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
{
- char *hw_desc;
+ void *virt_desc;
+ dma_addr_t dma_desc;
int idx;
struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
struct mv_xor_desc_slot *slot = NULL;
@@ -542,17 +543,16 @@
" %d descriptor slots", idx);
break;
}
- hw_desc = (char *) mv_chan->dma_desc_pool_virt;
- slot->hw_desc = (void *) &hw_desc[idx * MV_XOR_SLOT_SIZE];
+ virt_desc = mv_chan->dma_desc_pool_virt;
+ slot->hw_desc = virt_desc + idx * MV_XOR_SLOT_SIZE;
dma_async_tx_descriptor_init(&slot->async_tx, chan);
slot->async_tx.tx_submit = mv_xor_tx_submit;
INIT_LIST_HEAD(&slot->chain_node);
INIT_LIST_HEAD(&slot->slot_node);
INIT_LIST_HEAD(&slot->tx_list);
- hw_desc = (char *) mv_chan->dma_desc_pool;
- slot->async_tx.phys =
- (dma_addr_t) &hw_desc[idx * MV_XOR_SLOT_SIZE];
+ dma_desc = mv_chan->dma_desc_pool;
+ slot->async_tx.phys = dma_desc + idx * MV_XOR_SLOT_SIZE;
slot->idx = idx++;
spin_lock_bh(&mv_chan->lock);
@@ -582,8 +582,8 @@
int slot_cnt;
dev_dbg(mv_chan_to_devp(mv_chan),
- "%s dest: %x src %x len: %u flags: %ld\n",
- __func__, dest, src, len, flags);
+ "%s dest: %pad src %pad len: %u flags: %ld\n",
+ __func__, &dest, &src, len, flags);
if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
return NULL;
@@ -626,8 +626,8 @@
BUG_ON(len > MV_XOR_MAX_BYTE_COUNT);
dev_dbg(mv_chan_to_devp(mv_chan),
- "%s src_cnt: %d len: dest %x %u flags: %ld\n",
- __func__, src_cnt, len, dest, flags);
+ "%s src_cnt: %d len: %u dest %pad flags: %ld\n",
+ __func__, src_cnt, len, &dest, flags);
spin_lock_bh(&mv_chan->lock);
slot_cnt = mv_chan_xor_slot_count(len, src_cnt);
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 00a2de9..bf18c78 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -1641,6 +1641,7 @@
struct d40_chan *d40c = (struct d40_chan *) data;
struct d40_desc *d40d;
unsigned long flags;
+ bool callback_active;
dma_async_tx_callback callback;
void *callback_param;
@@ -1668,6 +1669,7 @@
}
/* Callback to client */
+ callback_active = !!(d40d->txd.flags & DMA_PREP_INTERRUPT);
callback = d40d->txd.callback;
callback_param = d40d->txd.callback_param;
@@ -1690,7 +1692,7 @@
spin_unlock_irqrestore(&d40c->lock, flags);
- if (callback && (d40d->txd.flags & DMA_PREP_INTERRUPT))
+ if (callback_active && callback)
callback(callback_param);
return;
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index e8c9ef0..33edd67 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -559,7 +559,8 @@
*
* called with the mem_ctls_mutex held
*/
-static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec)
+static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec,
+ bool init)
{
edac_dbg(0, "\n");
@@ -567,7 +568,9 @@
if (mci->op_state != OP_RUNNING_POLL)
return;
- INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function);
+ if (init)
+ INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function);
+
mod_delayed_work(edac_workqueue, &mci->work, msecs_to_jiffies(msec));
}
@@ -601,7 +604,7 @@
* user space has updated our poll period value, need to
* reset our workq delays
*/
-void edac_mc_reset_delay_period(int value)
+void edac_mc_reset_delay_period(unsigned long value)
{
struct mem_ctl_info *mci;
struct list_head *item;
@@ -611,7 +614,7 @@
list_for_each(item, &mc_devices) {
mci = list_entry(item, struct mem_ctl_info, link);
- edac_mc_workq_setup(mci, (unsigned long) value);
+ edac_mc_workq_setup(mci, value, false);
}
mutex_unlock(&mem_ctls_mutex);
@@ -782,7 +785,7 @@
/* This instance is NOW RUNNING */
mci->op_state = OP_RUNNING_POLL;
- edac_mc_workq_setup(mci, edac_mc_get_poll_msec());
+ edac_mc_workq_setup(mci, edac_mc_get_poll_msec(), true);
} else {
mci->op_state = OP_RUNNING_INTERRUPT;
}
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 51c0362..b335c6a 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -52,18 +52,20 @@
static int edac_set_poll_msec(const char *val, struct kernel_param *kp)
{
- long l;
+ unsigned long l;
int ret;
if (!val)
return -EINVAL;
- ret = kstrtol(val, 0, &l);
+ ret = kstrtoul(val, 0, &l);
if (ret)
return ret;
- if ((int)l != l)
+
+ if (l < 1000)
return -EINVAL;
- *((int *)kp->arg) = l;
+
+ *((unsigned long *)kp->arg) = l;
/* notify edac_mc engine to reset the poll period */
edac_mc_reset_delay_period(l);
diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h
index 3d139c6..f2118bf 100644
--- a/drivers/edac/edac_module.h
+++ b/drivers/edac/edac_module.h
@@ -52,7 +52,7 @@
extern void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev);
extern void edac_device_reset_delay_period(struct edac_device_ctl_info
*edac_dev, unsigned long value);
-extern void edac_mc_reset_delay_period(int value);
+extern void edac_mc_reset_delay_period(unsigned long value);
extern void *edac_align_ptr(void **p, unsigned size, int n_elems);
diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c
index d63f479..57e96a3 100644
--- a/drivers/edac/i7300_edac.c
+++ b/drivers/edac/i7300_edac.c
@@ -943,33 +943,35 @@
/* Attempt to 'get' the MCH register we want */
pdev = NULL;
- while (!pvt->pci_dev_16_1_fsb_addr_map ||
- !pvt->pci_dev_16_2_fsb_err_regs) {
- pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
- PCI_DEVICE_ID_INTEL_I7300_MCH_ERR, pdev);
- if (!pdev) {
- /* End of list, leave */
- i7300_printk(KERN_ERR,
- "'system address,Process Bus' "
- "device not found:"
- "vendor 0x%x device 0x%x ERR funcs "
- "(broken BIOS?)\n",
- PCI_VENDOR_ID_INTEL,
- PCI_DEVICE_ID_INTEL_I7300_MCH_ERR);
- goto error;
- }
-
+ while ((pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
+ PCI_DEVICE_ID_INTEL_I7300_MCH_ERR,
+ pdev))) {
/* Store device 16 funcs 1 and 2 */
switch (PCI_FUNC(pdev->devfn)) {
case 1:
- pvt->pci_dev_16_1_fsb_addr_map = pdev;
+ if (!pvt->pci_dev_16_1_fsb_addr_map)
+ pvt->pci_dev_16_1_fsb_addr_map =
+ pci_dev_get(pdev);
break;
case 2:
- pvt->pci_dev_16_2_fsb_err_regs = pdev;
+ if (!pvt->pci_dev_16_2_fsb_err_regs)
+ pvt->pci_dev_16_2_fsb_err_regs =
+ pci_dev_get(pdev);
break;
}
}
+ if (!pvt->pci_dev_16_1_fsb_addr_map ||
+ !pvt->pci_dev_16_2_fsb_err_regs) {
+ /* At least one device was not found */
+ i7300_printk(KERN_ERR,
+ "'system address,Process Bus' device not found:"
+ "vendor 0x%x device 0x%x ERR funcs (broken BIOS?)\n",
+ PCI_VENDOR_ID_INTEL,
+ PCI_DEVICE_ID_INTEL_I7300_MCH_ERR);
+ goto error;
+ }
+
edac_dbg(1, "System Address, processor bus- PCI Bus ID: %s %x:%x\n",
pci_name(pvt->pci_dev_16_0_fsb_ctlr),
pvt->pci_dev_16_0_fsb_ctlr->vendor,
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 87533ca..d871275 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1334,14 +1334,19 @@
* is at addr 8086:2c40, instead of 8086:2c41. So, we need
* to probe for the alternate address in case of failure
*/
- if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev)
+ if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev) {
+ pci_dev_get(*prev); /* pci_get_device will put it */
pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
PCI_DEVICE_ID_INTEL_I7_NONCORE_ALT, *prev);
+ }
- if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE && !pdev)
+ if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE &&
+ !pdev) {
+ pci_dev_get(*prev); /* pci_get_device will put it */
pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE_ALT,
*prev);
+ }
if (!pdev) {
if (*prev) {
diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c
index c20602f..98a14f6 100644
--- a/drivers/extcon/extcon-arizona.c
+++ b/drivers/extcon/extcon-arizona.c
@@ -222,27 +222,19 @@
struct snd_soc_dapm_context *dapm = arizona->dapm;
int ret;
- mutex_lock(&dapm->card->dapm_mutex);
-
ret = snd_soc_dapm_force_enable_pin(dapm, widget);
if (ret != 0)
dev_warn(arizona->dev, "Failed to enable %s: %d\n",
widget, ret);
- mutex_unlock(&dapm->card->dapm_mutex);
-
snd_soc_dapm_sync(dapm);
if (!arizona->pdata.micd_force_micbias) {
- mutex_lock(&dapm->card->dapm_mutex);
-
ret = snd_soc_dapm_disable_pin(arizona->dapm, widget);
if (ret != 0)
dev_warn(arizona->dev, "Failed to disable %s: %d\n",
widget, ret);
- mutex_unlock(&dapm->card->dapm_mutex);
-
snd_soc_dapm_sync(dapm);
}
}
@@ -304,16 +296,12 @@
ARIZONA_MICD_ENA, 0,
&change);
- mutex_lock(&dapm->card->dapm_mutex);
-
ret = snd_soc_dapm_disable_pin(dapm, widget);
if (ret != 0)
dev_warn(arizona->dev,
"Failed to disable %s: %d\n",
widget, ret);
- mutex_unlock(&dapm->card->dapm_mutex);
-
snd_soc_dapm_sync(dapm);
if (info->micd_reva) {
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index de4aa40..2c6d5e1 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -916,7 +916,7 @@
old->config_rom_retries = 0;
fw_notice(card, "rediscovered device %s\n", dev_name(dev));
- PREPARE_DELAYED_WORK(&old->work, fw_device_update);
+ old->workfn = fw_device_update;
fw_schedule_device_work(old, 0);
if (current_node == card->root_node)
@@ -1075,7 +1075,7 @@
if (atomic_cmpxchg(&device->state,
FW_DEVICE_INITIALIZING,
FW_DEVICE_RUNNING) == FW_DEVICE_GONE) {
- PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+ device->workfn = fw_device_shutdown;
fw_schedule_device_work(device, SHUTDOWN_DELAY);
} else {
fw_notice(card, "created device %s: GUID %08x%08x, S%d00\n",
@@ -1196,13 +1196,20 @@
dev_name(&device->device), fw_rcode_string(ret));
gone:
atomic_set(&device->state, FW_DEVICE_GONE);
- PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+ device->workfn = fw_device_shutdown;
fw_schedule_device_work(device, SHUTDOWN_DELAY);
out:
if (node_id == card->root_node->node_id)
fw_schedule_bm_work(card, 0);
}
+static void fw_device_workfn(struct work_struct *work)
+{
+ struct fw_device *device = container_of(to_delayed_work(work),
+ struct fw_device, work);
+ device->workfn(work);
+}
+
void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
{
struct fw_device *device;
@@ -1252,7 +1259,8 @@
* power-up after getting plugged in. We schedule the
* first config rom scan half a second after bus reset.
*/
- INIT_DELAYED_WORK(&device->work, fw_device_init);
+ device->workfn = fw_device_init;
+ INIT_DELAYED_WORK(&device->work, fw_device_workfn);
fw_schedule_device_work(device, INITIAL_DELAY);
break;
@@ -1268,7 +1276,7 @@
if (atomic_cmpxchg(&device->state,
FW_DEVICE_RUNNING,
FW_DEVICE_INITIALIZING) == FW_DEVICE_RUNNING) {
- PREPARE_DELAYED_WORK(&device->work, fw_device_refresh);
+ device->workfn = fw_device_refresh;
fw_schedule_device_work(device,
device->is_local ? 0 : INITIAL_DELAY);
}
@@ -1283,7 +1291,7 @@
smp_wmb(); /* update node_id before generation */
device->generation = card->generation;
if (atomic_read(&device->state) == FW_DEVICE_RUNNING) {
- PREPARE_DELAYED_WORK(&device->work, fw_device_update);
+ device->workfn = fw_device_update;
fw_schedule_device_work(device, 0);
}
break;
@@ -1308,7 +1316,7 @@
device = node->data;
if (atomic_xchg(&device->state,
FW_DEVICE_GONE) == FW_DEVICE_RUNNING) {
- PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+ device->workfn = fw_device_shutdown;
fw_schedule_device_work(device,
list_empty(&card->link) ? 0 : SHUTDOWN_DELAY);
}
diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c
index 6b89598..4af0a7b 100644
--- a/drivers/firewire/net.c
+++ b/drivers/firewire/net.c
@@ -929,8 +929,6 @@
if (rcode == RCODE_COMPLETE) {
fwnet_transmit_packet_done(ptask);
} else {
- fwnet_transmit_packet_failed(ptask);
-
if (printk_timed_ratelimit(&j, 1000) || rcode != last_rcode) {
dev_err(&ptask->dev->netdev->dev,
"fwnet_write_complete failed: %x (skipped %d)\n",
@@ -938,8 +936,10 @@
errors_skipped = 0;
last_rcode = rcode;
- } else
+ } else {
errors_skipped++;
+ }
+ fwnet_transmit_packet_failed(ptask);
}
}
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 6f74d8d..8db6632 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -290,7 +290,6 @@
#define QUIRK_NO_MSI 0x10
#define QUIRK_TI_SLLZ059 0x20
#define QUIRK_IR_WAKE 0x40
-#define QUIRK_PHY_LCTRL_TIMEOUT 0x80
/* In case of multiple matches in ohci_quirks[], only the first one is used. */
static const struct {
@@ -303,10 +302,7 @@
QUIRK_BE_HEADERS},
{PCI_VENDOR_ID_ATT, PCI_DEVICE_ID_AGERE_FW643, 6,
- QUIRK_PHY_LCTRL_TIMEOUT | QUIRK_NO_MSI},
-
- {PCI_VENDOR_ID_ATT, PCI_ANY_ID, PCI_ANY_ID,
- QUIRK_PHY_LCTRL_TIMEOUT},
+ QUIRK_NO_MSI},
{PCI_VENDOR_ID_CREATIVE, PCI_DEVICE_ID_CREATIVE_SB1394, PCI_ANY_ID,
QUIRK_RESET_PACKET},
@@ -353,7 +349,6 @@
", disable MSI = " __stringify(QUIRK_NO_MSI)
", TI SLLZ059 erratum = " __stringify(QUIRK_TI_SLLZ059)
", IR wake unreliable = " __stringify(QUIRK_IR_WAKE)
- ", phy LCtrl timeout = " __stringify(QUIRK_PHY_LCTRL_TIMEOUT)
")");
#define OHCI_PARAM_DEBUG_AT_AR 1
@@ -2299,9 +2294,6 @@
* TI TSB82AA2 + TSB81BA3(A) cards signal LPS enabled early but
* cannot actually use the phy at that time. These need tens of
* millisecods pause between LPS write and first phy access too.
- *
- * But do not wait for 50msec on Agere/LSI cards. Their phy
- * arbitration state machine may time out during such a long wait.
*/
reg_write(ohci, OHCI1394_HCControlSet,
@@ -2309,11 +2301,8 @@
OHCI1394_HCControl_postedWriteEnable);
flush_writes(ohci);
- if (!(ohci->quirks & QUIRK_PHY_LCTRL_TIMEOUT))
+ for (lps = 0, i = 0; !lps && i < 3; i++) {
msleep(50);
-
- for (lps = 0, i = 0; !lps && i < 150; i++) {
- msleep(1);
lps = reg_read(ohci, OHCI1394_HCControlSet) &
OHCI1394_HCControl_LPS;
}
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index 281029d..7aef911 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -146,6 +146,7 @@
*/
int generation;
int retries;
+ work_func_t workfn;
struct delayed_work work;
bool has_sdev;
bool blocked;
@@ -864,7 +865,7 @@
/* set appropriate retry limit(s) in BUSY_TIMEOUT register */
sbp2_set_busy_timeout(lu);
- PREPARE_DELAYED_WORK(&lu->work, sbp2_reconnect);
+ lu->workfn = sbp2_reconnect;
sbp2_agent_reset(lu);
/* This was a re-login. */
@@ -918,7 +919,7 @@
* If a bus reset happened, sbp2_update will have requeued
* lu->work already. Reset the work from reconnect to login.
*/
- PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
+ lu->workfn = sbp2_login;
}
static void sbp2_reconnect(struct work_struct *work)
@@ -952,7 +953,7 @@
lu->retries++ >= 5) {
dev_err(tgt_dev(tgt), "failed to reconnect\n");
lu->retries = 0;
- PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
+ lu->workfn = sbp2_login;
}
sbp2_queue_work(lu, DIV_ROUND_UP(HZ, 5));
@@ -972,6 +973,13 @@
sbp2_conditionally_unblock(lu);
}
+static void sbp2_lu_workfn(struct work_struct *work)
+{
+ struct sbp2_logical_unit *lu = container_of(to_delayed_work(work),
+ struct sbp2_logical_unit, work);
+ lu->workfn(work);
+}
+
static int sbp2_add_logical_unit(struct sbp2_target *tgt, int lun_entry)
{
struct sbp2_logical_unit *lu;
@@ -998,7 +1006,8 @@
lu->blocked = false;
++tgt->dont_block;
INIT_LIST_HEAD(&lu->orb_list);
- INIT_DELAYED_WORK(&lu->work, sbp2_login);
+ lu->workfn = sbp2_login;
+ INIT_DELAYED_WORK(&lu->work, sbp2_lu_workfn);
list_add_tail(&lu->link, &tgt->lu_list);
return 0;
diff --git a/drivers/fmc/fmc-write-eeprom.c b/drivers/fmc/fmc-write-eeprom.c
index ee5b479..9bb2cbd 100644
--- a/drivers/fmc/fmc-write-eeprom.c
+++ b/drivers/fmc/fmc-write-eeprom.c
@@ -27,7 +27,7 @@
/* The "file=" is like the generic "gateware=" used elsewhere */
static char *fwe_file[FMC_MAX_CARDS];
static int fwe_file_n;
-module_param_array_named(file, fwe_file, charp, &fwe_file_n, 444);
+module_param_array_named(file, fwe_file, charp, &fwe_file_n, 0444);
static int fwe_run_tlv(struct fmc_device *fmc, const struct firmware *fw,
int write)
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 6973387..903f24d 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -403,6 +403,7 @@
config GPIO_TB10X
bool
+ select GENERIC_IRQ_CHIP
select OF_GPIO
comment "I2C GPIO expanders:"
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 233d088..f32357e 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2012-2013 Broadcom Corporation
+ * Copyright (C) 2012-2014 Broadcom Corporation
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
@@ -657,6 +657,6 @@
module_platform_driver(bcm_kona_gpio_driver);
-MODULE_AUTHOR("Broadcom");
+MODULE_AUTHOR("Broadcom Corporation <bcm-kernel-feedback-list@broadcom.com>");
MODULE_DESCRIPTION("Broadcom Kona GPIO Driver");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-clps711x.c b/drivers/gpio/gpio-clps711x.c
index d355027..3c2ba2ad 100644
--- a/drivers/gpio/gpio-clps711x.c
+++ b/drivers/gpio/gpio-clps711x.c
@@ -97,3 +97,4 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Alexander Shiyan <shc_work@mail.ru>");
MODULE_DESCRIPTION("CLPS711X GPIO driver");
+MODULE_ALIAS("platform:clps711x-gpio");
diff --git a/drivers/gpio/gpio-intel-mid.c b/drivers/gpio/gpio-intel-mid.c
index d1b50ef..e585163 100644
--- a/drivers/gpio/gpio-intel-mid.c
+++ b/drivers/gpio/gpio-intel-mid.c
@@ -394,8 +394,8 @@
static int intel_gpio_runtime_idle(struct device *dev)
{
- pm_schedule_suspend(dev, 500);
- return -EBUSY;
+ int err = pm_schedule_suspend(dev, 500);
+ return err ?: -EBUSY;
}
static const struct dev_pm_ops intel_gpio_pm_ops = {
diff --git a/drivers/gpio/gpio-xtensa.c b/drivers/gpio/gpio-xtensa.c
index 1d136ec..7081304 100644
--- a/drivers/gpio/gpio-xtensa.c
+++ b/drivers/gpio/gpio-xtensa.c
@@ -40,6 +40,8 @@
#error GPIO32 option is not enabled for your xtensa core variant
#endif
+#if XCHAL_HAVE_CP
+
static inline unsigned long enable_cp(unsigned long *cpenable)
{
unsigned long flags;
@@ -57,6 +59,20 @@
local_irq_restore(flags);
}
+#else
+
+static inline unsigned long enable_cp(unsigned long *cpenable)
+{
+ *cpenable = 0; /* avoid uninitialized value warning */
+ return 0;
+}
+
+static inline void disable_cp(unsigned long flags, unsigned long cpenable)
+{
+}
+
+#endif /* XCHAL_HAVE_CP */
+
static int xtensa_impwire_get_direction(struct gpio_chip *gc, unsigned offset)
{
return 1; /* input only */
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index acf3a36..32982da 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -68,15 +68,7 @@
{
struct armada_private *priv = dev->dev_private;
- /*
- * Yes, we really must jump through these hoops just to store a
- * _pointer_ to something into the kfifo. This is utterly insane
- * and idiotic, because it kfifo requires the _data_ pointed to by
- * the pointer const, not the pointer itself. Not only that, but
- * you have to pass a pointer _to_ the pointer you want stored.
- */
- const struct drm_framebuffer *silly_api_alert = fb;
- WARN_ON(!kfifo_put(&priv->fb_unref, &silly_api_alert));
+ WARN_ON(!kfifo_put(&priv->fb_unref, fb));
schedule_work(&priv->fb_unref_work);
}
diff --git a/drivers/gpu/drm/bochs/Kconfig b/drivers/gpu/drm/bochs/Kconfig
index c8fcf12..5f8b0c2 100644
--- a/drivers/gpu/drm/bochs/Kconfig
+++ b/drivers/gpu/drm/bochs/Kconfig
@@ -2,6 +2,7 @@
tristate "DRM Support for bochs dispi vga interface (qemu stdvga)"
depends on DRM && PCI
select DRM_KMS_HELPER
+ select DRM_KMS_FB_HELPER
select FB_SYS_FILLRECT
select FB_SYS_COPYAREA
select FB_SYS_IMAGEBLIT
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index dffc836..f4dc9b7 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -296,6 +296,18 @@
case DRM_CAP_ASYNC_PAGE_FLIP:
req->value = dev->mode_config.async_page_flip;
break;
+ case DRM_CAP_CURSOR_WIDTH:
+ if (dev->mode_config.cursor_width)
+ req->value = dev->mode_config.cursor_width;
+ else
+ req->value = 64;
+ break;
+ case DRM_CAP_CURSOR_HEIGHT:
+ if (dev->mode_config.cursor_height)
+ req->value = dev->mode_config.cursor_height;
+ else
+ req->value = 64;
+ break;
default:
return -EINVAL;
}
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 5736aaa..f7af69b 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -468,8 +468,8 @@
} else {
list_for_each_entry_safe(dev, tmp, &driver->legacy_dev_list,
legacy_dev_list) {
- drm_put_dev(dev);
list_del(&dev->legacy_dev_list);
+ drm_put_dev(dev);
}
}
DRM_INFO("Module unloaded\n");
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index f227f54..6e1a1a2 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -51,7 +51,7 @@
config DRM_EXYNOS_IPP
bool "Exynos DRM IPP"
- depends on DRM_EXYNOS && !ARCH_MULTIPLATFORM
+ depends on DRM_EXYNOS
help
Choose this option if you want to use IPP feature for DRM.
@@ -69,6 +69,6 @@
config DRM_EXYNOS_GSC
bool "Exynos DRM GSC"
- depends on DRM_EXYNOS_IPP && ARCH_EXYNOS5
+ depends on DRM_EXYNOS_IPP && ARCH_EXYNOS5 && !ARCH_MULTIPLATFORM
help
Choose this option if you want to use Exynos GSC for DRM.
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 9d096a0..c204b4e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -171,22 +171,28 @@
file->driver_priv = file_priv;
ret = exynos_drm_subdrv_open(dev, file);
- if (ret) {
- kfree(file_priv);
- file->driver_priv = NULL;
- }
+ if (ret)
+ goto err_file_priv_free;
anon_filp = anon_inode_getfile("exynos_gem", &exynos_drm_gem_fops,
NULL, 0);
if (IS_ERR(anon_filp)) {
- kfree(file_priv);
- return PTR_ERR(anon_filp);
+ ret = PTR_ERR(anon_filp);
+ goto err_subdrv_close;
}
anon_filp->f_mode = FMODE_READ | FMODE_WRITE;
file_priv->anon_filp = anon_filp;
return ret;
+
+err_subdrv_close:
+ exynos_drm_subdrv_close(dev, file);
+
+err_file_priv_free:
+ kfree(file_priv);
+ file->driver_priv = NULL;
+ return ret;
}
static void exynos_drm_preclose(struct drm_device *dev,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 380aec2..6c1885e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -607,7 +607,7 @@
reg_type = REG_TYPE_NONE;
DRM_ERROR("Unknown register offset![%d]\n", reg_offset);
break;
- };
+ }
return reg_type;
}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index d519a4e..09312b8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -16,7 +16,6 @@
#include <linux/types.h>
#include <linux/clk.h>
#include <linux/pm_runtime.h>
-#include <plat/map-base.h>
#include <drm/drmP.h>
#include <drm/exynos_drm.h>
@@ -826,7 +825,7 @@
DRM_DEBUG_KMS("count[%d]e[0x%x]\n", count++, (int)e);
/*
- * quf == NULL condition means all event deletion.
+ * qbuf == NULL condition means all event deletion.
* stop operations want to delete all event list.
* another case delete only same buf id.
*/
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index a0e10ae..c021ddc 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -34,6 +34,7 @@
#include <linux/io.h>
#include <linux/of.h>
#include <linux/of_gpio.h>
+#include <linux/hdmi.h>
#include <drm/exynos_drm.h>
@@ -59,19 +60,6 @@
#define HDMI_AUI_VERSION 0x01
#define HDMI_AUI_LENGTH 0x0A
-/* HDMI infoframe to configure HDMI out packet header, AUI and AVI */
-enum HDMI_PACKET_TYPE {
- /* refer to Table 5-8 Packet Type in HDMI specification v1.4a */
- /* InfoFrame packet type */
- HDMI_PACKET_TYPE_INFOFRAME = 0x80,
- /* Vendor-Specific InfoFrame */
- HDMI_PACKET_TYPE_VSI = HDMI_PACKET_TYPE_INFOFRAME + 1,
- /* Auxiliary Video information InfoFrame */
- HDMI_PACKET_TYPE_AVI = HDMI_PACKET_TYPE_INFOFRAME + 2,
- /* Audio information InfoFrame */
- HDMI_PACKET_TYPE_AUI = HDMI_PACKET_TYPE_INFOFRAME + 4
-};
-
enum hdmi_type {
HDMI_TYPE13,
HDMI_TYPE14,
@@ -379,12 +367,6 @@
},
};
-struct hdmi_infoframe {
- enum HDMI_PACKET_TYPE type;
- u8 ver;
- u8 len;
-};
-
static inline u32 hdmi_reg_read(struct hdmi_context *hdata, u32 reg_id)
{
return readl(hdata->regs + reg_id);
@@ -682,7 +664,7 @@
}
static void hdmi_reg_infoframe(struct hdmi_context *hdata,
- struct hdmi_infoframe *infoframe)
+ union hdmi_infoframe *infoframe)
{
u32 hdr_sum;
u8 chksum;
@@ -700,13 +682,15 @@
return;
}
- switch (infoframe->type) {
- case HDMI_PACKET_TYPE_AVI:
+ switch (infoframe->any.type) {
+ case HDMI_INFOFRAME_TYPE_AVI:
hdmi_reg_writeb(hdata, HDMI_AVI_CON, HDMI_AVI_CON_EVERY_VSYNC);
- hdmi_reg_writeb(hdata, HDMI_AVI_HEADER0, infoframe->type);
- hdmi_reg_writeb(hdata, HDMI_AVI_HEADER1, infoframe->ver);
- hdmi_reg_writeb(hdata, HDMI_AVI_HEADER2, infoframe->len);
- hdr_sum = infoframe->type + infoframe->ver + infoframe->len;
+ hdmi_reg_writeb(hdata, HDMI_AVI_HEADER0, infoframe->any.type);
+ hdmi_reg_writeb(hdata, HDMI_AVI_HEADER1,
+ infoframe->any.version);
+ hdmi_reg_writeb(hdata, HDMI_AVI_HEADER2, infoframe->any.length);
+ hdr_sum = infoframe->any.type + infoframe->any.version +
+ infoframe->any.length;
/* Output format zero hardcoded ,RGB YBCR selection */
hdmi_reg_writeb(hdata, HDMI_AVI_BYTE(1), 0 << 5 |
@@ -722,18 +706,20 @@
hdmi_reg_writeb(hdata, HDMI_AVI_BYTE(4), vic);
chksum = hdmi_chksum(hdata, HDMI_AVI_BYTE(1),
- infoframe->len, hdr_sum);
+ infoframe->any.length, hdr_sum);
DRM_DEBUG_KMS("AVI checksum = 0x%x\n", chksum);
hdmi_reg_writeb(hdata, HDMI_AVI_CHECK_SUM, chksum);
break;
- case HDMI_PACKET_TYPE_AUI:
+ case HDMI_INFOFRAME_TYPE_AUDIO:
hdmi_reg_writeb(hdata, HDMI_AUI_CON, 0x02);
- hdmi_reg_writeb(hdata, HDMI_AUI_HEADER0, infoframe->type);
- hdmi_reg_writeb(hdata, HDMI_AUI_HEADER1, infoframe->ver);
- hdmi_reg_writeb(hdata, HDMI_AUI_HEADER2, infoframe->len);
- hdr_sum = infoframe->type + infoframe->ver + infoframe->len;
+ hdmi_reg_writeb(hdata, HDMI_AUI_HEADER0, infoframe->any.type);
+ hdmi_reg_writeb(hdata, HDMI_AUI_HEADER1,
+ infoframe->any.version);
+ hdmi_reg_writeb(hdata, HDMI_AUI_HEADER2, infoframe->any.length);
+ hdr_sum = infoframe->any.type + infoframe->any.version +
+ infoframe->any.length;
chksum = hdmi_chksum(hdata, HDMI_AUI_BYTE(1),
- infoframe->len, hdr_sum);
+ infoframe->any.length, hdr_sum);
DRM_DEBUG_KMS("AUI checksum = 0x%x\n", chksum);
hdmi_reg_writeb(hdata, HDMI_AUI_CHECK_SUM, chksum);
break;
@@ -985,7 +971,7 @@
static void hdmi_conf_init(struct hdmi_context *hdata)
{
- struct hdmi_infoframe infoframe;
+ union hdmi_infoframe infoframe;
/* disable HPD interrupts from HDMI IP block, use GPIO instead */
hdmi_reg_writemask(hdata, HDMI_INTC_CON, 0, HDMI_INTC_EN_GLOBAL |
@@ -1021,14 +1007,14 @@
hdmi_reg_writeb(hdata, HDMI_V13_AUI_CON, 0x02);
hdmi_reg_writeb(hdata, HDMI_V13_ACR_CON, 0x04);
} else {
- infoframe.type = HDMI_PACKET_TYPE_AVI;
- infoframe.ver = HDMI_AVI_VERSION;
- infoframe.len = HDMI_AVI_LENGTH;
+ infoframe.any.type = HDMI_INFOFRAME_TYPE_AVI;
+ infoframe.any.version = HDMI_AVI_VERSION;
+ infoframe.any.length = HDMI_AVI_LENGTH;
hdmi_reg_infoframe(hdata, &infoframe);
- infoframe.type = HDMI_PACKET_TYPE_AUI;
- infoframe.ver = HDMI_AUI_VERSION;
- infoframe.len = HDMI_AUI_LENGTH;
+ infoframe.any.type = HDMI_INFOFRAME_TYPE_AUDIO;
+ infoframe.any.version = HDMI_AUI_VERSION;
+ infoframe.any.length = HDMI_AUI_LENGTH;
hdmi_reg_infoframe(hdata, &infoframe);
/* enable AVI packet every vsync, fixes purple line problem */
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 400b0c4..faa77f5 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -208,7 +208,7 @@
# define PLL_SERIAL_1_SRL_IZ(x) (((x) & 3) << 1)
# define PLL_SERIAL_1_SRL_MAN_IZ (1 << 6)
#define REG_PLL_SERIAL_2 REG(0x02, 0x01) /* read/write */
-# define PLL_SERIAL_2_SRL_NOSC(x) (((x) & 3) << 0)
+# define PLL_SERIAL_2_SRL_NOSC(x) ((x) << 0)
# define PLL_SERIAL_2_SRL_PR(x) (((x) & 0xf) << 4)
#define REG_PLL_SERIAL_3 REG(0x02, 0x02) /* read/write */
# define PLL_SERIAL_3_SRL_CCIR (1 << 0)
@@ -528,10 +528,10 @@
{
uint8_t buf[PB(5) + 1];
+ memset(buf, 0, sizeof(buf));
buf[HB(0)] = 0x84;
buf[HB(1)] = 0x01;
buf[HB(2)] = 10;
- buf[PB(0)] = 0;
buf[PB(1)] = p->audio_frame[1] & 0x07; /* CC */
buf[PB(2)] = p->audio_frame[2] & 0x1c; /* SF */
buf[PB(4)] = p->audio_frame[4];
@@ -824,6 +824,11 @@
}
div = 148500 / mode->clock;
+ if (div != 0) {
+ div--;
+ if (div > 3)
+ div = 3;
+ }
/* mute the audio FIFO: */
reg_set(encoder, REG_AIP_CNTRL_0, AIP_CNTRL_0_RST_FIFO);
@@ -913,7 +918,7 @@
if (priv->rev == TDA19988) {
/* let incoming pixels fill the active space (if any) */
- reg_write(encoder, REG_ENABLE_SPACE, 0x01);
+ reg_write(encoder, REG_ENABLE_SPACE, 0x00);
}
/* must be last register set: */
@@ -1094,6 +1099,8 @@
{
struct tda998x_priv *priv = to_tda998x_priv(encoder);
drm_i2c_encoder_destroy(encoder);
+ if (priv->cec)
+ i2c_unregister_device(priv->cec);
kfree(priv);
}
@@ -1142,8 +1149,12 @@
priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(0) | VIP_CNTRL_1_SWAP_D(1);
priv->vip_cntrl_2 = VIP_CNTRL_2_SWAP_E(4) | VIP_CNTRL_2_SWAP_F(5);
- priv->current_page = 0;
+ priv->current_page = 0xff;
priv->cec = i2c_new_dummy(client->adapter, 0x34);
+ if (!priv->cec) {
+ kfree(priv);
+ return -ENODEV;
+ }
priv->dpms = DRM_MODE_DPMS_OFF;
encoder_slave->slave_priv = priv;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 04f1f02..ec7bb0f 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -403,7 +403,7 @@
void intel_detect_pch(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- struct pci_dev *pch;
+ struct pci_dev *pch = NULL;
/* In all current cases, num_pipes is equivalent to the PCH_NOP setting
* (which really amounts to a PCH but no South Display).
@@ -424,12 +424,9 @@
* all the ISA bridge devices and check for the first match, instead
* of only checking the first one.
*/
- pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL);
- while (pch) {
- struct pci_dev *curr = pch;
+ while ((pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, pch))) {
if (pch->vendor == PCI_VENDOR_ID_INTEL) {
- unsigned short id;
- id = pch->device & INTEL_PCH_DEVICE_ID_MASK;
+ unsigned short id = pch->device & INTEL_PCH_DEVICE_ID_MASK;
dev_priv->pch_id = id;
if (id == INTEL_PCH_IBX_DEVICE_ID_TYPE) {
@@ -461,18 +458,16 @@
DRM_DEBUG_KMS("Found LynxPoint LP PCH\n");
WARN_ON(!IS_HASWELL(dev));
WARN_ON(!IS_ULT(dev));
- } else {
- goto check_next;
- }
- pci_dev_put(pch);
+ } else
+ continue;
+
break;
}
-check_next:
- pch = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, curr);
- pci_dev_put(curr);
}
if (!pch)
- DRM_DEBUG_KMS("No PCH found?\n");
+ DRM_DEBUG_KMS("No PCH found.\n");
+
+ pci_dev_put(pch);
}
bool i915_semaphore_is_enabled(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4a2bf8e..df77e20 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1831,6 +1831,14 @@
/* Early gen2 have a totally busted CS tlb and require pinned batches. */
#define HAS_BROKEN_CS_TLB(dev) (IS_I830(dev) || IS_845G(dev))
+/*
+ * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts
+ * even when in MSI mode. This results in spurious interrupt warnings if the
+ * legacy irq no. is shared with another device. The kernel then disables that
+ * interrupt source and so prevents the other device from working properly.
+ */
+#define HAS_AUX_IRQ(dev) (INTEL_INFO(dev)->gen >= 5)
+#define HAS_GMBUS_IRQ(dev) (INTEL_INFO(dev)->gen >= 5)
/* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte
* rows, which changed the alignment requirements and fence programming.
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 40a2b36..d278be1 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -842,7 +842,7 @@
dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
dev_priv->gtt.base.start / PAGE_SIZE,
dev_priv->gtt.base.total / PAGE_SIZE,
- false);
+ true);
}
void i915_gem_restore_gtt_mappings(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 1a24e84..28d24ca 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -82,9 +82,22 @@
r = devm_request_mem_region(dev->dev, base, dev_priv->gtt.stolen_size,
"Graphics Stolen Memory");
if (r == NULL) {
- DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n",
- base, base + (uint32_t)dev_priv->gtt.stolen_size);
- base = 0;
+ /*
+ * One more attempt but this time requesting region from
+ * base + 1, as we have seen that this resolves the region
+ * conflict with the PCI Bus.
+ * This is a BIOS w/a: Some BIOS wrap stolen in the root
+ * PCI bus, but have an off-by-one error. Hence retry the
+ * reservation starting from 1 instead of 0.
+ */
+ r = devm_request_mem_region(dev->dev, base + 1,
+ dev_priv->gtt.stolen_size - 1,
+ "Graphics Stolen Memory");
+ if (r == NULL) {
+ DRM_ERROR("conflict detected with stolen region: [0x%08x - 0x%08x]\n",
+ base, base + (uint32_t)dev_priv->gtt.stolen_size);
+ base = 0;
+ }
}
return base;
@@ -201,6 +214,13 @@
struct drm_i915_private *dev_priv = dev->dev_private;
int bios_reserved = 0;
+#ifdef CONFIG_INTEL_IOMMU
+ if (intel_iommu_gfx_mapped) {
+ DRM_INFO("DMAR active, disabling use of stolen memory\n");
+ return 0;
+ }
+#endif
+
if (dev_priv->gtt.stolen_size == 0)
return 0;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index d7fd2fd2..990cf8f 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -146,7 +146,10 @@
va_list tmp;
va_copy(tmp, args);
- if (!__i915_error_seek(e, vsnprintf(NULL, 0, f, tmp)))
+ len = vsnprintf(NULL, 0, f, tmp);
+ va_end(tmp);
+
+ if (!__i915_error_seek(e, len))
return;
}
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 17d8fcb..d554169 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -567,8 +567,7 @@
vbl_start = mode->crtc_vblank_start * mode->crtc_htotal;
} else {
- enum transcoder cpu_transcoder =
- intel_pipe_to_cpu_transcoder(dev_priv, pipe);
+ enum transcoder cpu_transcoder = (enum transcoder) pipe;
u32 htotal;
htotal = ((I915_READ(HTOTAL(cpu_transcoder)) >> 16) & 0x1fff) + 1;
@@ -619,33 +618,25 @@
/* raw reads, only for fast reads of display block, no need for forcewake etc. */
#define __raw_i915_read32(dev_priv__, reg__) readl((dev_priv__)->regs + (reg__))
-#define __raw_i915_read16(dev_priv__, reg__) readw((dev_priv__)->regs + (reg__))
static bool ilk_pipe_in_vblank_locked(struct drm_device *dev, enum pipe pipe)
{
struct drm_i915_private *dev_priv = dev->dev_private;
uint32_t status;
+ int reg;
- if (INTEL_INFO(dev)->gen < 7) {
- status = pipe == PIPE_A ?
- DE_PIPEA_VBLANK :
- DE_PIPEB_VBLANK;
+ if (INTEL_INFO(dev)->gen >= 8) {
+ status = GEN8_PIPE_VBLANK;
+ reg = GEN8_DE_PIPE_ISR(pipe);
+ } else if (INTEL_INFO(dev)->gen >= 7) {
+ status = DE_PIPE_VBLANK_IVB(pipe);
+ reg = DEISR;
} else {
- switch (pipe) {
- default:
- case PIPE_A:
- status = DE_PIPEA_VBLANK_IVB;
- break;
- case PIPE_B:
- status = DE_PIPEB_VBLANK_IVB;
- break;
- case PIPE_C:
- status = DE_PIPEC_VBLANK_IVB;
- break;
- }
+ status = DE_PIPE_VBLANK(pipe);
+ reg = DEISR;
}
- return __raw_i915_read32(dev_priv, DEISR) & status;
+ return __raw_i915_read32(dev_priv, reg) & status;
}
static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
@@ -703,7 +694,28 @@
else
position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
- if (HAS_PCH_SPLIT(dev)) {
+ if (HAS_DDI(dev)) {
+ /*
+ * On HSW HDMI outputs there seems to be a 2 line
+ * difference, whereas eDP has the normal 1 line
+ * difference that earlier platforms have. External
+ * DP is unknown. For now just check for the 2 line
+ * difference case on all output types on HSW+.
+ *
+ * This might misinterpret the scanline counter being
+ * one line too far along on eDP, but that's less
+ * dangerous than the alternative since that would lead
+ * the vblank timestamp code astray when it sees a
+ * scanline count before vblank_start during a vblank
+ * interrupt.
+ */
+ in_vbl = ilk_pipe_in_vblank_locked(dev, pipe);
+ if ((in_vbl && (position == vbl_start - 2 ||
+ position == vbl_start - 1)) ||
+ (!in_vbl && (position == vbl_end - 2 ||
+ position == vbl_end - 1)))
+ position = (position + 2) % vtotal;
+ } else if (HAS_PCH_SPLIT(dev)) {
/*
* The scanline counter increments at the leading edge
* of hsync, ie. it completely misses the active portion
@@ -2770,10 +2782,9 @@
return;
if (HAS_PCH_IBX(dev)) {
- mask = SDE_GMBUS | SDE_AUX_MASK | SDE_TRANSB_FIFO_UNDER |
- SDE_TRANSA_FIFO_UNDER | SDE_POISON;
+ mask = SDE_GMBUS | SDE_AUX_MASK | SDE_POISON;
} else {
- mask = SDE_GMBUS_CPT | SDE_AUX_MASK_CPT | SDE_ERROR_CPT;
+ mask = SDE_GMBUS_CPT | SDE_AUX_MASK_CPT;
I915_WRITE(SERR_INT, I915_READ(SERR_INT));
}
@@ -2833,20 +2844,19 @@
display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE_IVB |
DE_PCH_EVENT_IVB | DE_PLANEC_FLIP_DONE_IVB |
DE_PLANEB_FLIP_DONE_IVB |
- DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB |
- DE_ERR_INT_IVB);
+ DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB);
extra_mask = (DE_PIPEC_VBLANK_IVB | DE_PIPEB_VBLANK_IVB |
- DE_PIPEA_VBLANK_IVB);
+ DE_PIPEA_VBLANK_IVB | DE_ERR_INT_IVB);
I915_WRITE(GEN7_ERR_INT, I915_READ(GEN7_ERR_INT));
} else {
display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE | DE_PCH_EVENT |
DE_PLANEA_FLIP_DONE | DE_PLANEB_FLIP_DONE |
DE_AUX_CHANNEL_A |
- DE_PIPEB_FIFO_UNDERRUN | DE_PIPEA_FIFO_UNDERRUN |
DE_PIPEB_CRC_DONE | DE_PIPEA_CRC_DONE |
DE_POISON);
- extra_mask = DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT;
+ extra_mask = DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT |
+ DE_PIPEB_FIFO_UNDERRUN | DE_PIPEA_FIFO_UNDERRUN;
}
dev_priv->irq_mask = ~display_mask;
@@ -2962,9 +2972,9 @@
struct drm_device *dev = dev_priv->dev;
uint32_t de_pipe_masked = GEN8_PIPE_FLIP_DONE |
GEN8_PIPE_CDCLK_CRC_DONE |
- GEN8_PIPE_FIFO_UNDERRUN |
GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
- uint32_t de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK;
+ uint32_t de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK |
+ GEN8_PIPE_FIFO_UNDERRUN;
int pipe;
dev_priv->de_irq_mask[PIPE_A] = ~de_pipe_masked;
dev_priv->de_irq_mask[PIPE_B] = ~de_pipe_masked;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index e06b9e0..234ac5f 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1244,6 +1244,7 @@
if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
+ ironlake_edp_panel_vdd_on(intel_dp);
ironlake_edp_panel_off(intel_dp);
}
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 9fa2434..9b8a7c7 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1092,12 +1092,12 @@
struct drm_device *dev = dev_priv->dev;
bool cur_state;
- if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
- cur_state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE;
- else if (IS_845G(dev) || IS_I865G(dev))
+ if (IS_845G(dev) || IS_I865G(dev))
cur_state = I915_READ(_CURACNTR) & CURSOR_ENABLE;
- else
+ else if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev))
cur_state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE;
+ else
+ cur_state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE;
WARN(cur_state != state,
"cursor on pipe %c assertion failure (expected %s, current %s)\n",
@@ -8586,6 +8586,20 @@
if (ring->id == RCS)
len += 6;
+ /*
+ * BSpec MI_DISPLAY_FLIP for IVB:
+ * "The full packet must be contained within the same cache line."
+ *
+ * Currently the LRI+SRM+MI_DISPLAY_FLIP all fit within the same
+ * cacheline, if we ever start emitting more commands before
+ * the MI_DISPLAY_FLIP we may need to first emit everything else,
+ * then do the cacheline alignment, and finally emit the
+ * MI_DISPLAY_FLIP.
+ */
+ ret = intel_ring_cacheline_align(ring);
+ if (ret)
+ goto err_unpin;
+
ret = intel_ring_begin(ring, len);
if (ret)
goto err_unpin;
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 5ede4e8..2688f6d 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -404,7 +404,7 @@
int i, ret, recv_bytes;
uint32_t status;
int try, precharge, clock = 0;
- bool has_aux_irq = true;
+ bool has_aux_irq = HAS_AUX_IRQ(dev);
uint32_t timeout;
/* dp aux is extremely sensitive to irq latency, hence request the
@@ -537,6 +537,7 @@
uint8_t msg[20];
int msg_bytes;
uint8_t ack;
+ int retry;
if (WARN_ON(send_bytes > 16))
return -E2BIG;
@@ -548,19 +549,21 @@
msg[3] = send_bytes - 1;
memcpy(&msg[4], send, send_bytes);
msg_bytes = send_bytes + 4;
- for (;;) {
+ for (retry = 0; retry < 7; retry++) {
ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes, &ack, 1);
if (ret < 0)
return ret;
ack >>= 4;
if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_ACK)
- break;
+ return send_bytes;
else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER)
- udelay(100);
+ usleep_range(400, 500);
else
return -EIO;
}
- return send_bytes;
+
+ DRM_ERROR("too many retries, giving up\n");
+ return -EIO;
}
/* Write a single byte to the aux channel in native mode */
@@ -582,6 +585,7 @@
int reply_bytes;
uint8_t ack;
int ret;
+ int retry;
if (WARN_ON(recv_bytes > 19))
return -E2BIG;
@@ -595,7 +599,7 @@
msg_bytes = 4;
reply_bytes = recv_bytes + 1;
- for (;;) {
+ for (retry = 0; retry < 7; retry++) {
ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes,
reply, reply_bytes);
if (ret == 0)
@@ -608,10 +612,13 @@
return ret - 1;
}
else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER)
- udelay(100);
+ usleep_range(400, 500);
else
return -EIO;
}
+
+ DRM_ERROR("too many retries, giving up\n");
+ return -EIO;
}
static int
@@ -1242,17 +1249,24 @@
DRM_DEBUG_KMS("Turn eDP power off\n");
+ WARN(!intel_dp->want_panel_vdd, "Need VDD to turn off panel\n");
+
pp = ironlake_get_pp_control(intel_dp);
/* We need to switch off panel power _and_ force vdd, for otherwise some
* panels get very unhappy and cease to work. */
- pp &= ~(POWER_TARGET_ON | PANEL_POWER_RESET | EDP_BLC_ENABLE);
+ pp &= ~(POWER_TARGET_ON | EDP_FORCE_VDD | PANEL_POWER_RESET | EDP_BLC_ENABLE);
pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
I915_WRITE(pp_ctrl_reg, pp);
POSTING_READ(pp_ctrl_reg);
+ intel_dp->want_panel_vdd = false;
+
ironlake_wait_panel_off(intel_dp);
+
+ /* We got a reference when we enabled the VDD. */
+ intel_runtime_pm_put(dev_priv);
}
void ironlake_edp_backlight_on(struct intel_dp *intel_dp)
@@ -1632,7 +1646,7 @@
val |= EDP_PSR_LINK_DISABLE;
I915_WRITE(EDP_PSR_CTL(dev), val |
- IS_BROADWELL(dev) ? 0 : link_entry_time |
+ (IS_BROADWELL(dev) ? 0 : link_entry_time) |
max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT |
idle_frames << EDP_PSR_IDLE_FRAME_SHIFT |
EDP_PSR_ENABLE);
@@ -1777,6 +1791,7 @@
/* Make sure the panel is off before trying to change the mode. But also
* ensure that we have vdd while we switch off the panel. */
+ ironlake_edp_panel_vdd_on(intel_dp);
ironlake_edp_backlight_off(intel_dp);
intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
ironlake_edp_panel_off(intel_dp);
@@ -1869,10 +1884,12 @@
mutex_unlock(&dev_priv->dpio_lock);
- /* init power sequencer on this pipe and port */
- intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
- intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
- &power_seq);
+ if (is_edp(intel_dp)) {
+ /* init power sequencer on this pipe and port */
+ intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
+ intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
+ &power_seq);
+ }
intel_enable_dp(encoder);
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 6db0d9d..ee3181e 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -845,7 +845,7 @@
{
struct drm_device *dev = intel_hdmi_to_dev(hdmi);
- if (IS_G4X(dev))
+ if (!hdmi->has_hdmi_sink || IS_G4X(dev))
return 165000;
else if (IS_HASWELL(dev) || INTEL_INFO(dev)->gen >= 8)
return 300000;
@@ -899,8 +899,8 @@
* outputs. We also need to check that the higher clock still fits
* within limits.
*/
- if (pipe_config->pipe_bpp > 8*3 && clock_12bpc <= portclock_limit
- && HAS_PCH_SPLIT(dev)) {
+ if (pipe_config->pipe_bpp > 8*3 && intel_hdmi->has_hdmi_sink &&
+ clock_12bpc <= portclock_limit && HAS_PCH_SPLIT(dev)) {
DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n");
desired_bpp = 12*3;
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index b1dc33f..d33b61d 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -258,13 +258,6 @@
algo->data = bus;
}
-/*
- * gmbus on gen4 seems to be able to generate legacy interrupts even when in MSI
- * mode. This results in spurious interrupt warnings if the legacy irq no. is
- * shared with another device. The kernel then disables that interrupt source
- * and so prevents the other device from working properly.
- */
-#define HAS_GMBUS_IRQ(dev) (INTEL_INFO(dev)->gen >= 5)
static int
gmbus_wait_hw_status(struct drm_i915_private *dev_priv,
u32 gmbus2_status,
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index 4e960ec..acde294 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -226,6 +226,8 @@
#define ACPI_DIGITAL_OUTPUT (3<<8)
#define ACPI_LVDS_OUTPUT (4<<8)
+#define MAX_DSLP 1500
+
#ifdef CONFIG_ACPI
static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out)
{
@@ -260,10 +262,11 @@
/* The spec says 2ms should be the default, but it's too small
* for some machines. */
dslp = 50;
- } else if (dslp > 500) {
+ } else if (dslp > MAX_DSLP) {
/* Hey bios, trust must be earned. */
- WARN_ONCE(1, "excessive driver sleep timeout (DSPL) %u\n", dslp);
- dslp = 500;
+ DRM_INFO_ONCE("ACPI BIOS requests an excessive sleep of %u ms, "
+ "using %u ms instead\n", dslp, MAX_DSLP);
+ dslp = MAX_DSLP;
}
/* The spec tells us to do this, but we are the only user... */
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 350de35..079ea38 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -698,7 +698,7 @@
freq /= 0xff;
ctl = freq << 17;
- if (IS_GEN2(dev) && panel->backlight.combination_mode)
+ if (panel->backlight.combination_mode)
ctl |= BLM_LEGACY_MODE;
if (IS_PINEVIEW(dev) && panel->backlight.active_low_pwm)
ctl |= BLM_POLARITY_PNV;
@@ -979,7 +979,7 @@
ctl = I915_READ(BLC_PWM_CTL);
- if (IS_GEN2(dev))
+ if (IS_GEN2(dev) || IS_I915GM(dev) || IS_I945GM(dev))
panel->backlight.combination_mode = ctl & BLM_LEGACY_MODE;
if (IS_PINEVIEW(dev))
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d77cc81..e1fc35a 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3493,6 +3493,8 @@
u32 pcbr;
int pctx_size = 24*1024;
+ WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
pcbr = I915_READ(VLV_PCBR);
if (pcbr) {
/* BIOS set it up already, grab the pre-alloc'd space */
@@ -3542,8 +3544,6 @@
I915_WRITE(GTFIFODBG, gtfifodbg);
}
- valleyview_setup_pctx(dev);
-
/* If VLV, Forcewake all wells, else re-direct to regular path */
gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
@@ -4395,6 +4395,8 @@
ironlake_enable_rc6(dev);
intel_init_emon(dev);
} else if (IS_GEN6(dev) || IS_GEN7(dev)) {
+ if (IS_VALLEYVIEW(dev))
+ valleyview_setup_pctx(dev);
/*
* PCU communication is slow and this doesn't need to be
* done at any specific time, so do this out of our fast path
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index b7f1742..31b36c5 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1653,6 +1653,27 @@
return 0;
}
+/* Align the ring tail to a cacheline boundary */
+int intel_ring_cacheline_align(struct intel_ring_buffer *ring)
+{
+ int num_dwords = (64 - (ring->tail & 63)) / sizeof(uint32_t);
+ int ret;
+
+ if (num_dwords == 0)
+ return 0;
+
+ ret = intel_ring_begin(ring, num_dwords);
+ if (ret)
+ return ret;
+
+ while (num_dwords--)
+ intel_ring_emit(ring, MI_NOOP);
+
+ intel_ring_advance(ring);
+
+ return 0;
+}
+
void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
{
struct drm_i915_private *dev_priv = ring->dev->dev_private;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 71a73f4..0b243ce 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -233,6 +233,7 @@
void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring);
int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n);
+int __must_check intel_ring_cacheline_align(struct intel_ring_buffer *ring);
static inline void intel_ring_emit(struct intel_ring_buffer *ring,
u32 data)
{
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
index 1964f4f..84c5b13 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
@@ -39,6 +39,7 @@
spinlock_t lock;
bool stale;
uint32_t width, height;
+ uint32_t x, y;
/* next cursor to scan-out: */
uint32_t next_iova;
@@ -57,9 +58,16 @@
#define PENDING_FLIP 0x2
atomic_t pending;
- /* the fb that we currently hold a scanout ref to: */
+ /* the fb that we logically (from PoV of KMS API) hold a ref
+ * to. Which we may not yet be scanning out (we may still
+ * be scanning out previous in case of page_flip while waiting
+ * for gpu rendering to complete:
+ */
struct drm_framebuffer *fb;
+ /* the fb that we currently hold a scanout ref to: */
+ struct drm_framebuffer *scanout_fb;
+
/* for unref'ing framebuffers after scanout completes: */
struct drm_flip_work unref_fb_work;
@@ -77,24 +85,73 @@
return to_mdp4_kms(to_mdp_kms(priv->kms));
}
-static void update_fb(struct drm_crtc *crtc, bool async,
- struct drm_framebuffer *new_fb)
+static void request_pending(struct drm_crtc *crtc, uint32_t pending)
+{
+ struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+
+ atomic_or(pending, &mdp4_crtc->pending);
+ mdp_irq_register(&get_kms(crtc)->base, &mdp4_crtc->vblank);
+}
+
+static void crtc_flush(struct drm_crtc *crtc)
+{
+ struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+ struct mdp4_kms *mdp4_kms = get_kms(crtc);
+ uint32_t i, flush = 0;
+
+ for (i = 0; i < ARRAY_SIZE(mdp4_crtc->planes); i++) {
+ struct drm_plane *plane = mdp4_crtc->planes[i];
+ if (plane) {
+ enum mdp4_pipe pipe_id = mdp4_plane_pipe(plane);
+ flush |= pipe2flush(pipe_id);
+ }
+ }
+ flush |= ovlp2flush(mdp4_crtc->ovlp);
+
+ DBG("%s: flush=%08x", mdp4_crtc->name, flush);
+
+ mdp4_write(mdp4_kms, REG_MDP4_OVERLAY_FLUSH, flush);
+}
+
+static void update_fb(struct drm_crtc *crtc, struct drm_framebuffer *new_fb)
{
struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
struct drm_framebuffer *old_fb = mdp4_crtc->fb;
- if (old_fb)
- drm_flip_work_queue(&mdp4_crtc->unref_fb_work, old_fb);
-
/* grab reference to incoming scanout fb: */
drm_framebuffer_reference(new_fb);
mdp4_crtc->base.fb = new_fb;
mdp4_crtc->fb = new_fb;
- if (!async) {
- /* enable vblank to pick up the old_fb */
- mdp_irq_register(&get_kms(crtc)->base, &mdp4_crtc->vblank);
- }
+ if (old_fb)
+ drm_flip_work_queue(&mdp4_crtc->unref_fb_work, old_fb);
+}
+
+/* unlike update_fb(), take a ref to the new scanout fb *before* updating
+ * plane, then call this. Needed to ensure we don't unref the buffer that
+ * is actually still being scanned out.
+ *
+ * Note that this whole thing goes away with atomic.. since we can defer
+ * calling into driver until rendering is done.
+ */
+static void update_scanout(struct drm_crtc *crtc, struct drm_framebuffer *fb)
+{
+ struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+
+ /* flush updates, to make sure hw is updated to new scanout fb,
+ * so that we can safely queue unref to current fb (ie. next
+ * vblank we know hw is done w/ previous scanout_fb).
+ */
+ crtc_flush(crtc);
+
+ if (mdp4_crtc->scanout_fb)
+ drm_flip_work_queue(&mdp4_crtc->unref_fb_work,
+ mdp4_crtc->scanout_fb);
+
+ mdp4_crtc->scanout_fb = fb;
+
+ /* enable vblank to complete flip: */
+ request_pending(crtc, PENDING_FLIP);
}
/* if file!=NULL, this is preclose potential cancel-flip path */
@@ -120,34 +177,6 @@
spin_unlock_irqrestore(&dev->event_lock, flags);
}
-static void crtc_flush(struct drm_crtc *crtc)
-{
- struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
- struct mdp4_kms *mdp4_kms = get_kms(crtc);
- uint32_t i, flush = 0;
-
- for (i = 0; i < ARRAY_SIZE(mdp4_crtc->planes); i++) {
- struct drm_plane *plane = mdp4_crtc->planes[i];
- if (plane) {
- enum mdp4_pipe pipe_id = mdp4_plane_pipe(plane);
- flush |= pipe2flush(pipe_id);
- }
- }
- flush |= ovlp2flush(mdp4_crtc->ovlp);
-
- DBG("%s: flush=%08x", mdp4_crtc->name, flush);
-
- mdp4_write(mdp4_kms, REG_MDP4_OVERLAY_FLUSH, flush);
-}
-
-static void request_pending(struct drm_crtc *crtc, uint32_t pending)
-{
- struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
-
- atomic_or(pending, &mdp4_crtc->pending);
- mdp_irq_register(&get_kms(crtc)->base, &mdp4_crtc->vblank);
-}
-
static void pageflip_cb(struct msm_fence_cb *cb)
{
struct mdp4_crtc *mdp4_crtc =
@@ -158,11 +187,9 @@
if (!fb)
return;
+ drm_framebuffer_reference(fb);
mdp4_plane_set_scanout(mdp4_crtc->plane, fb);
- crtc_flush(crtc);
-
- /* enable vblank to complete flip: */
- request_pending(crtc, PENDING_FLIP);
+ update_scanout(crtc, fb);
}
static void unref_fb_worker(struct drm_flip_work *work, void *val)
@@ -320,6 +347,20 @@
mode->vsync_end, mode->vtotal,
mode->type, mode->flags);
+ /* grab extra ref for update_scanout() */
+ drm_framebuffer_reference(crtc->fb);
+
+ ret = mdp4_plane_mode_set(mdp4_crtc->plane, crtc, crtc->fb,
+ 0, 0, mode->hdisplay, mode->vdisplay,
+ x << 16, y << 16,
+ mode->hdisplay << 16, mode->vdisplay << 16);
+ if (ret) {
+ drm_framebuffer_unreference(crtc->fb);
+ dev_err(crtc->dev->dev, "%s: failed to set mode on plane: %d\n",
+ mdp4_crtc->name, ret);
+ return ret;
+ }
+
mdp4_write(mdp4_kms, REG_MDP4_DMA_SRC_SIZE(dma),
MDP4_DMA_SRC_SIZE_WIDTH(mode->hdisplay) |
MDP4_DMA_SRC_SIZE_HEIGHT(mode->vdisplay));
@@ -341,24 +382,15 @@
mdp4_write(mdp4_kms, REG_MDP4_OVLP_CFG(ovlp), 1);
- update_fb(crtc, false, crtc->fb);
-
- ret = mdp4_plane_mode_set(mdp4_crtc->plane, crtc, crtc->fb,
- 0, 0, mode->hdisplay, mode->vdisplay,
- x << 16, y << 16,
- mode->hdisplay << 16, mode->vdisplay << 16);
- if (ret) {
- dev_err(crtc->dev->dev, "%s: failed to set mode on plane: %d\n",
- mdp4_crtc->name, ret);
- return ret;
- }
-
if (dma == DMA_E) {
mdp4_write(mdp4_kms, REG_MDP4_DMA_E_QUANT(0), 0x00ff0000);
mdp4_write(mdp4_kms, REG_MDP4_DMA_E_QUANT(1), 0x00ff0000);
mdp4_write(mdp4_kms, REG_MDP4_DMA_E_QUANT(2), 0x00ff0000);
}
+ update_fb(crtc, crtc->fb);
+ update_scanout(crtc, crtc->fb);
+
return 0;
}
@@ -385,13 +417,24 @@
struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
struct drm_plane *plane = mdp4_crtc->plane;
struct drm_display_mode *mode = &crtc->mode;
+ int ret;
- update_fb(crtc, false, crtc->fb);
+ /* grab extra ref for update_scanout() */
+ drm_framebuffer_reference(crtc->fb);
- return mdp4_plane_mode_set(plane, crtc, crtc->fb,
+ ret = mdp4_plane_mode_set(plane, crtc, crtc->fb,
0, 0, mode->hdisplay, mode->vdisplay,
x << 16, y << 16,
mode->hdisplay << 16, mode->vdisplay << 16);
+ if (ret) {
+ drm_framebuffer_unreference(crtc->fb);
+ return ret;
+ }
+
+ update_fb(crtc, crtc->fb);
+ update_scanout(crtc, crtc->fb);
+
+ return 0;
}
static void mdp4_crtc_load_lut(struct drm_crtc *crtc)
@@ -419,7 +462,7 @@
mdp4_crtc->event = event;
spin_unlock_irqrestore(&dev->event_lock, flags);
- update_fb(crtc, true, new_fb);
+ update_fb(crtc, new_fb);
return msm_gem_queue_inactive_cb(obj, &mdp4_crtc->pageflip_cb);
}
@@ -442,12 +485,12 @@
static void update_cursor(struct drm_crtc *crtc)
{
struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
+ struct mdp4_kms *mdp4_kms = get_kms(crtc);
enum mdp4_dma dma = mdp4_crtc->dma;
unsigned long flags;
spin_lock_irqsave(&mdp4_crtc->cursor.lock, flags);
if (mdp4_crtc->cursor.stale) {
- struct mdp4_kms *mdp4_kms = get_kms(crtc);
struct drm_gem_object *next_bo = mdp4_crtc->cursor.next_bo;
struct drm_gem_object *prev_bo = mdp4_crtc->cursor.scanout_bo;
uint32_t iova = mdp4_crtc->cursor.next_iova;
@@ -479,6 +522,11 @@
mdp4_crtc->cursor.scanout_bo = next_bo;
mdp4_crtc->cursor.stale = false;
}
+
+ mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_POS(dma),
+ MDP4_DMA_CURSOR_POS_X(mdp4_crtc->cursor.x) |
+ MDP4_DMA_CURSOR_POS_Y(mdp4_crtc->cursor.y));
+
spin_unlock_irqrestore(&mdp4_crtc->cursor.lock, flags);
}
@@ -530,6 +578,7 @@
drm_gem_object_unreference_unlocked(old_bo);
}
+ crtc_flush(crtc);
request_pending(crtc, PENDING_CURSOR);
return 0;
@@ -542,12 +591,15 @@
static int mdp4_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
{
struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
- struct mdp4_kms *mdp4_kms = get_kms(crtc);
- enum mdp4_dma dma = mdp4_crtc->dma;
+ unsigned long flags;
- mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_POS(dma),
- MDP4_DMA_CURSOR_POS_X(x) |
- MDP4_DMA_CURSOR_POS_Y(y));
+ spin_lock_irqsave(&mdp4_crtc->cursor.lock, flags);
+ mdp4_crtc->cursor.x = x;
+ mdp4_crtc->cursor.y = y;
+ spin_unlock_irqrestore(&mdp4_crtc->cursor.lock, flags);
+
+ crtc_flush(crtc);
+ request_pending(crtc, PENDING_CURSOR);
return 0;
}
@@ -713,6 +765,7 @@
crtc = &mdp4_crtc->base;
mdp4_crtc->plane = plane;
+ mdp4_crtc->id = id;
mdp4_crtc->ovlp = ovlp_id;
mdp4_crtc->dma = dma_id;
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
index 2406027..1e893dd 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
@@ -170,8 +170,8 @@
MDP4_PIPE_DST_SIZE_HEIGHT(crtc_h));
mdp4_write(mdp4_kms, REG_MDP4_PIPE_DST_XY(pipe),
- MDP4_PIPE_SRC_XY_X(crtc_x) |
- MDP4_PIPE_SRC_XY_Y(crtc_y));
+ MDP4_PIPE_DST_XY_X(crtc_x) |
+ MDP4_PIPE_DST_XY_Y(crtc_y));
mdp4_plane_set_scanout(plane, fb);
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
index 71a3b23..f279402 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
@@ -296,6 +296,7 @@
x << 16, y << 16,
mode->hdisplay << 16, mode->vdisplay << 16);
if (ret) {
+ drm_framebuffer_unreference(crtc->fb);
dev_err(crtc->dev->dev, "%s: failed to set mode on plane: %d\n",
mdp5_crtc->name, ret);
return ret;
@@ -343,11 +344,15 @@
0, 0, mode->hdisplay, mode->vdisplay,
x << 16, y << 16,
mode->hdisplay << 16, mode->vdisplay << 16);
+ if (ret) {
+ drm_framebuffer_unreference(crtc->fb);
+ return ret;
+ }
update_fb(crtc, crtc->fb);
update_scanout(crtc, crtc->fb);
- return ret;
+ return 0;
}
static void mdp5_crtc_load_lut(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index d8d60c9..3da8264 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -644,7 +644,7 @@
fail:
if (obj)
- drm_gem_object_unreference_unlocked(obj);
+ drm_gem_object_unreference(obj);
return ERR_PTR(ret);
}
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 5281d4b..5423e91 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -163,7 +163,7 @@
/* if locking succeeded, pin bo: */
- ret = msm_gem_get_iova(&msm_obj->base,
+ ret = msm_gem_get_iova_locked(&msm_obj->base,
submit->gpu->id, &iova);
/* this would break the logic in the fail path.. there is no
@@ -247,7 +247,7 @@
/* For now, just map the entire thing. Eventually we probably
* to do it page-by-page, w/ kmap() if not vmap()d..
*/
- ptr = msm_gem_vaddr(&obj->base);
+ ptr = msm_gem_vaddr_locked(&obj->base);
if (IS_ERR(ptr)) {
ret = PTR_ERR(ptr);
@@ -307,14 +307,12 @@
{
unsigned i;
- mutex_lock(&submit->dev->struct_mutex);
for (i = 0; i < submit->nr_bos; i++) {
struct msm_gem_object *msm_obj = submit->bos[i].obj;
submit_unlock_unpin_bo(submit, i);
list_del_init(&msm_obj->submit_entry);
drm_gem_object_unreference(&msm_obj->base);
}
- mutex_unlock(&submit->dev->struct_mutex);
ww_acquire_fini(&submit->ticket);
kfree(submit);
@@ -342,6 +340,8 @@
if (args->nr_cmds > MAX_CMDS)
return -EINVAL;
+ mutex_lock(&dev->struct_mutex);
+
submit = submit_create(dev, gpu, args->nr_bos);
if (!submit) {
ret = -ENOMEM;
@@ -410,5 +410,6 @@
out:
if (submit)
submit_cleanup(submit, !!ret);
+ mutex_unlock(&dev->struct_mutex);
return ret;
}
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 4ebce8b..0cfe3f4 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -298,8 +298,6 @@
struct msm_drm_private *priv = dev->dev_private;
int i, ret;
- mutex_lock(&dev->struct_mutex);
-
submit->fence = ++priv->next_fence;
gpu->submitted_fence = submit->fence;
@@ -331,7 +329,6 @@
msm_gem_move_to_active(&msm_obj->base, gpu, true, submit->fence);
}
hangcheck_timer_reset(gpu);
- mutex_unlock(&dev->struct_mutex);
return ret;
}
diff --git a/drivers/gpu/drm/nouveau/Makefile b/drivers/gpu/drm/nouveau/Makefile
index e88145b..d310c19 100644
--- a/drivers/gpu/drm/nouveau/Makefile
+++ b/drivers/gpu/drm/nouveau/Makefile
@@ -141,6 +141,7 @@
nouveau-y += core/subdev/mc/nv04.o
nouveau-y += core/subdev/mc/nv40.o
nouveau-y += core/subdev/mc/nv44.o
+nouveau-y += core/subdev/mc/nv4c.o
nouveau-y += core/subdev/mc/nv50.o
nouveau-y += core/subdev/mc/nv94.o
nouveau-y += core/subdev/mc/nv98.o
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nv40.c b/drivers/gpu/drm/nouveau/core/engine/device/nv40.c
index 1b653dd..08b8859 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nv40.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nv40.c
@@ -311,7 +311,7 @@
device->oclass[NVDEV_SUBDEV_CLOCK ] = &nv40_clock_oclass;
device->oclass[NVDEV_SUBDEV_THERM ] = &nv40_therm_oclass;
device->oclass[NVDEV_SUBDEV_DEVINIT] = nv1a_devinit_oclass;
- device->oclass[NVDEV_SUBDEV_MC ] = nv44_mc_oclass;
+ device->oclass[NVDEV_SUBDEV_MC ] = nv4c_mc_oclass;
device->oclass[NVDEV_SUBDEV_BUS ] = nv31_bus_oclass;
device->oclass[NVDEV_SUBDEV_TIMER ] = &nv04_timer_oclass;
device->oclass[NVDEV_SUBDEV_FB ] = nv46_fb_oclass;
@@ -334,7 +334,7 @@
device->oclass[NVDEV_SUBDEV_CLOCK ] = &nv40_clock_oclass;
device->oclass[NVDEV_SUBDEV_THERM ] = &nv40_therm_oclass;
device->oclass[NVDEV_SUBDEV_DEVINIT] = nv1a_devinit_oclass;
- device->oclass[NVDEV_SUBDEV_MC ] = nv44_mc_oclass;
+ device->oclass[NVDEV_SUBDEV_MC ] = nv4c_mc_oclass;
device->oclass[NVDEV_SUBDEV_BUS ] = nv31_bus_oclass;
device->oclass[NVDEV_SUBDEV_TIMER ] = &nv04_timer_oclass;
device->oclass[NVDEV_SUBDEV_FB ] = nv4e_fb_oclass;
@@ -357,7 +357,7 @@
device->oclass[NVDEV_SUBDEV_CLOCK ] = &nv40_clock_oclass;
device->oclass[NVDEV_SUBDEV_THERM ] = &nv40_therm_oclass;
device->oclass[NVDEV_SUBDEV_DEVINIT] = nv1a_devinit_oclass;
- device->oclass[NVDEV_SUBDEV_MC ] = nv44_mc_oclass;
+ device->oclass[NVDEV_SUBDEV_MC ] = nv4c_mc_oclass;
device->oclass[NVDEV_SUBDEV_BUS ] = nv31_bus_oclass;
device->oclass[NVDEV_SUBDEV_TIMER ] = &nv04_timer_oclass;
device->oclass[NVDEV_SUBDEV_FB ] = nv46_fb_oclass;
@@ -380,7 +380,7 @@
device->oclass[NVDEV_SUBDEV_CLOCK ] = &nv40_clock_oclass;
device->oclass[NVDEV_SUBDEV_THERM ] = &nv40_therm_oclass;
device->oclass[NVDEV_SUBDEV_DEVINIT] = nv1a_devinit_oclass;
- device->oclass[NVDEV_SUBDEV_MC ] = nv44_mc_oclass;
+ device->oclass[NVDEV_SUBDEV_MC ] = nv4c_mc_oclass;
device->oclass[NVDEV_SUBDEV_BUS ] = nv31_bus_oclass;
device->oclass[NVDEV_SUBDEV_TIMER ] = &nv04_timer_oclass;
device->oclass[NVDEV_SUBDEV_FB ] = nv46_fb_oclass;
@@ -403,7 +403,7 @@
device->oclass[NVDEV_SUBDEV_CLOCK ] = &nv40_clock_oclass;
device->oclass[NVDEV_SUBDEV_THERM ] = &nv40_therm_oclass;
device->oclass[NVDEV_SUBDEV_DEVINIT] = nv1a_devinit_oclass;
- device->oclass[NVDEV_SUBDEV_MC ] = nv44_mc_oclass;
+ device->oclass[NVDEV_SUBDEV_MC ] = nv4c_mc_oclass;
device->oclass[NVDEV_SUBDEV_BUS ] = nv31_bus_oclass;
device->oclass[NVDEV_SUBDEV_TIMER ] = &nv04_timer_oclass;
device->oclass[NVDEV_SUBDEV_FB ] = nv46_fb_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
index 940eaa5..9ad722e 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
@@ -1142,7 +1142,7 @@
if (conf != ~0) {
if (outp.location == 0 && outp.type == DCB_OUTPUT_DP) {
u32 soff = (ffs(outp.or) - 1) * 0x08;
- u32 ctrl = nv_rd32(priv, 0x610798 + soff);
+ u32 ctrl = nv_rd32(priv, 0x610794 + soff);
u32 datarate;
switch ((ctrl & 0x000f0000) >> 16) {
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
index 9a850fe..54c1b5b 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
@@ -112,7 +112,7 @@
nv_wr32(priv, 0x002270, cur->addr >> 12);
nv_wr32(priv, 0x002274, (engine << 20) | (p >> 3));
- if (!nv_wait(priv, 0x002284 + (engine * 4), 0x00100000, 0x00000000))
+ if (!nv_wait(priv, 0x002284 + (engine * 8), 0x00100000, 0x00000000))
nv_error(priv, "runlist %d update timeout\n", engine);
mutex_unlock(&nv_subdev(priv)->mutex);
}
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c b/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
index 30ed19c..7a367c4 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
@@ -539,7 +539,7 @@
ustatus &= ~0x04030000;
}
if (ustatus && display) {
- nv_error("%s - TP%d:", name, i);
+ nv_error(priv, "%s - TP%d:", name, i);
nouveau_bitfield_print(nv50_mpc_traps, ustatus);
pr_cont("\n");
ustatus = 0;
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
index adc88b7..3c6738e 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
@@ -47,6 +47,7 @@
extern struct nouveau_oclass *nv04_mc_oclass;
extern struct nouveau_oclass *nv40_mc_oclass;
extern struct nouveau_oclass *nv44_mc_oclass;
+extern struct nouveau_oclass *nv4c_mc_oclass;
extern struct nouveau_oclass *nv50_mc_oclass;
extern struct nouveau_oclass *nv94_mc_oclass;
extern struct nouveau_oclass *nv98_mc_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/base.c b/drivers/gpu/drm/nouveau/core/subdev/bios/base.c
index aa0fbbe..ef0c9c4 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/base.c
@@ -130,6 +130,10 @@
u16 pcir;
int i;
+ /* there is no prom on nv4x IGP's */
+ if (device->card_type == NV_40 && device->chipset >= 0x4c)
+ return;
+
/* enable access to rom */
if (device->card_type >= NV_50)
pcireg = 0x088050;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/nv1a.c b/drivers/gpu/drm/nouveau/core/subdev/fb/nv1a.c
index 9159a5c..265d125 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/nv1a.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/nv1a.c
@@ -36,7 +36,7 @@
.fini = _nouveau_fb_fini,
},
.base.memtype = nv04_fb_memtype_valid,
- .base.ram = &nv10_ram_oclass,
+ .base.ram = &nv1a_ram_oclass,
.tile.regions = 8,
.tile.init = nv10_fb_tile_init,
.tile.fini = nv10_fb_tile_fini,
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.h b/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.h
index b0d5c31..81a408e 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.h
@@ -14,6 +14,7 @@
extern const struct nouveau_mc_intr nv04_mc_intr[];
int nv04_mc_init(struct nouveau_object *);
void nv40_mc_msi_rearm(struct nouveau_mc *);
+int nv44_mc_init(struct nouveau_object *object);
int nv50_mc_init(struct nouveau_object *);
extern const struct nouveau_mc_intr nv50_mc_intr[];
extern const struct nouveau_mc_intr nvc0_mc_intr[];
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c
index 3bfee5c..cc4d0d2 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c
@@ -24,7 +24,7 @@
#include "nv04.h"
-static int
+int
nv44_mc_init(struct nouveau_object *object)
{
struct nv04_mc_priv *priv = (void *)object;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
new file mode 100644
index 0000000..a75c35c
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2014 Ilia Mirkin
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ilia Mirkin
+ */
+
+#include "nv04.h"
+
+static void
+nv4c_mc_msi_rearm(struct nouveau_mc *pmc)
+{
+ struct nv04_mc_priv *priv = (void *)pmc;
+ nv_wr08(priv, 0x088050, 0xff);
+}
+
+struct nouveau_oclass *
+nv4c_mc_oclass = &(struct nouveau_mc_oclass) {
+ .base.handle = NV_SUBDEV(MC, 0x4c),
+ .base.ofuncs = &(struct nouveau_ofuncs) {
+ .ctor = nv04_mc_ctor,
+ .dtor = _nouveau_mc_dtor,
+ .init = nv44_mc_init,
+ .fini = _nouveau_mc_fini,
+ },
+ .intr = nv04_mc_intr,
+ .msi_rearm = nv4c_mc_msi_rearm,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 4ef83df..83face3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -106,6 +106,29 @@
return 0;
}
+/*
+ * On some platforms, _DSM(nouveau_op_dsm_muid, func0) has special
+ * requirements on the fourth parameter, so a private implementation
+ * instead of using acpi_check_dsm().
+ */
+static int nouveau_check_optimus_dsm(acpi_handle handle)
+{
+ int result;
+
+ /*
+ * Function 0 returns a Buffer containing available functions.
+ * The args parameter is ignored for function 0, so just put 0 in it
+ */
+ if (nouveau_optimus_dsm(handle, 0, 0, &result))
+ return 0;
+
+ /*
+ * ACPI Spec v4 9.14.1: if bit 0 is zero, no function is supported.
+ * If the n-th bit is enabled, function n is supported
+ */
+ return result & 1 && result & (1 << NOUVEAU_DSM_OPTIMUS_CAPS);
+}
+
static int nouveau_dsm(acpi_handle handle, int func, int arg)
{
int ret = 0;
@@ -207,8 +230,7 @@
1 << NOUVEAU_DSM_POWER))
retval |= NOUVEAU_DSM_HAS_MUX;
- if (acpi_check_dsm(dhandle, nouveau_op_dsm_muid, 0x00000100,
- 1 << NOUVEAU_DSM_OPTIMUS_CAPS))
+ if (nouveau_check_optimus_dsm(dhandle))
retval |= NOUVEAU_DSM_HAS_OPT;
if (retval & NOUVEAU_DSM_HAS_OPT) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 488686d..4aed171 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1249,7 +1249,7 @@
mem->bus.is_iomem = !dev->agp->cant_use_aperture;
}
#endif
- if (!node->memtype)
+ if (nv_device(drm->device)->card_type < NV_50 || !node->memtype)
/* untiled */
break;
/* fallthrough, tiled memory */
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 78c8e71..4ee702a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -376,6 +376,8 @@
if (ret)
goto fail_device;
+ dev->irq_enabled = true;
+
/* workaround an odd issue on nvc1 by disabling the device's
* nosnoop capability. hopefully won't cause issues until a
* better fix is found - assuming there is one...
@@ -475,6 +477,7 @@
struct nouveau_drm *drm = nouveau_drm(dev);
struct nouveau_object *device;
+ dev->irq_enabled = false;
device = drm->client.base.device;
drm_put_dev(dev);
@@ -863,13 +866,16 @@
struct drm_device *drm_dev = pci_get_drvdata(pdev);
int ret;
- if (nouveau_runtime_pm == 0)
- return -EINVAL;
+ if (nouveau_runtime_pm == 0) {
+ pm_runtime_forbid(dev);
+ return -EBUSY;
+ }
/* are we optimus enabled? */
if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
- return -EINVAL;
+ pm_runtime_forbid(dev);
+ return -EBUSY;
}
nv_debug_level(SILENT);
@@ -920,12 +926,15 @@
struct nouveau_drm *drm = nouveau_drm(drm_dev);
struct drm_crtc *crtc;
- if (nouveau_runtime_pm == 0)
+ if (nouveau_runtime_pm == 0) {
+ pm_runtime_forbid(dev);
return -EBUSY;
+ }
/* are we optimus enabled? */
if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
+ pm_runtime_forbid(dev);
return -EBUSY;
}
diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c
index 81638d7..471347e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vga.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vga.c
@@ -14,7 +14,9 @@
{
struct nouveau_device *device = nouveau_dev(priv);
- if (device->chipset >= 0x40)
+ if (device->card_type == NV_40 && device->chipset >= 0x4c)
+ nv_wr32(device, 0x088060, state);
+ else if (device->chipset >= 0x40)
nv_wr32(device, 0x088054, state);
else
nv_wr32(device, 0x001854, state);
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index a9338c8..daa4dd3 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -559,7 +559,7 @@
u32 adjusted_clock = mode->clock;
int encoder_mode = atombios_get_encoder_mode(encoder);
u32 dp_clock = mode->clock;
- int bpc = radeon_get_monitor_bpc(connector);
+ int bpc = radeon_crtc->bpc;
bool is_duallink = radeon_dig_monitor_is_duallink(encoder, mode->clock);
/* reset the pll flags */
@@ -1176,7 +1176,7 @@
evergreen_tiling_fields(tiling_flags, &bankw, &bankh, &mtaspect, &tile_split);
/* Set NUM_BANKS. */
- if (rdev->family >= CHIP_BONAIRE) {
+ if (rdev->family >= CHIP_TAHITI) {
unsigned tileb, index, num_banks, tile_split_bytes;
/* Calculate the macrotile mode index. */
@@ -1194,13 +1194,14 @@
return -EINVAL;
}
- num_banks = (rdev->config.cik.macrotile_mode_array[index] >> 6) & 0x3;
+ if (rdev->family >= CHIP_BONAIRE)
+ num_banks = (rdev->config.cik.macrotile_mode_array[index] >> 6) & 0x3;
+ else
+ num_banks = (rdev->config.si.tile_mode_array[index] >> 20) & 0x3;
fb_format |= EVERGREEN_GRPH_NUM_BANKS(num_banks);
} else {
- /* SI and older. */
- if (rdev->family >= CHIP_TAHITI)
- tmp = rdev->config.si.tile_config;
- else if (rdev->family >= CHIP_CAYMAN)
+ /* NI and older. */
+ if (rdev->family >= CHIP_CAYMAN)
tmp = rdev->config.cayman.tile_config;
else
tmp = rdev->config.evergreen.tile_config;
@@ -1773,6 +1774,20 @@
return ATOM_PPLL1;
DRM_ERROR("unable to allocate a PPLL\n");
return ATOM_PPLL_INVALID;
+ } else if (ASIC_IS_DCE41(rdev)) {
+ /* Don't share PLLs on DCE4.1 chips */
+ if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(radeon_crtc->encoder))) {
+ if (rdev->clock.dp_extclk)
+ /* skip PPLL programming if using ext clock */
+ return ATOM_PPLL_INVALID;
+ }
+ pll_in_use = radeon_get_pll_use_mask(crtc);
+ if (!(pll_in_use & (1 << ATOM_PPLL1)))
+ return ATOM_PPLL1;
+ if (!(pll_in_use & (1 << ATOM_PPLL2)))
+ return ATOM_PPLL2;
+ DRM_ERROR("unable to allocate a PPLL\n");
+ return ATOM_PPLL_INVALID;
} else if (ASIC_IS_DCE4(rdev)) {
/* in DP mode, the DP ref clock can come from PPLL, DCPLL, or ext clock,
* depending on the asic:
@@ -1800,7 +1815,7 @@
if (pll != ATOM_PPLL_INVALID)
return pll;
}
- } else if (!ASIC_IS_DCE41(rdev)) { /* Don't share PLLs on DCE4.1 chips */
+ } else {
/* use the same PPLL for all monitors with the same clock */
pll = radeon_get_shared_nondp_ppll(crtc);
if (pll != ATOM_PPLL_INVALID)
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index a42d615..607dc14 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -464,11 +464,12 @@
static u8 radeon_atom_get_bpc(struct drm_encoder *encoder)
{
- struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
int bpc = 8;
- if (connector)
- bpc = radeon_get_monitor_bpc(connector);
+ if (encoder->crtc) {
+ struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
+ bpc = radeon_crtc->bpc;
+ }
switch (bpc) {
case 0:
@@ -1313,7 +1314,7 @@
}
if (is_dp)
args.v5.ucLaneNum = dp_lane_count;
- else if (radeon_encoder->pixel_clock > 165000)
+ else if (radeon_dig_monitor_is_duallink(encoder, radeon_encoder->pixel_clock))
args.v5.ucLaneNum = 8;
else
args.v5.ucLaneNum = 4;
diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c
index 0fbd36f..ea103cc 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.c
+++ b/drivers/gpu/drm/radeon/btc_dpm.c
@@ -29,6 +29,7 @@
#include "cypress_dpm.h"
#include "btc_dpm.h"
#include "atom.h"
+#include <linux/seq_file.h>
#define MC_CG_ARB_FREQ_F0 0x0a
#define MC_CG_ARB_FREQ_F1 0x0b
@@ -2756,6 +2757,37 @@
r600_free_extended_power_table(rdev);
}
+void btc_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
+ struct seq_file *m)
+{
+ struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
+ struct radeon_ps *rps = &eg_pi->current_rps;
+ struct rv7xx_ps *ps = rv770_get_ps(rps);
+ struct rv7xx_pl *pl;
+ u32 current_index =
+ (RREG32(TARGET_AND_CURRENT_PROFILE_INDEX) & CURRENT_PROFILE_INDEX_MASK) >>
+ CURRENT_PROFILE_INDEX_SHIFT;
+
+ if (current_index > 2) {
+ seq_printf(m, "invalid dpm profile %d\n", current_index);
+ } else {
+ if (current_index == 0)
+ pl = &ps->low;
+ else if (current_index == 1)
+ pl = &ps->medium;
+ else /* current_index == 2 */
+ pl = &ps->high;
+ seq_printf(m, "uvd vclk: %d dclk: %d\n", rps->vclk, rps->dclk);
+ if (rdev->family >= CHIP_CEDAR) {
+ seq_printf(m, "power level %d sclk: %u mclk: %u vddc: %u vddci: %u\n",
+ current_index, pl->sclk, pl->mclk, pl->vddc, pl->vddci);
+ } else {
+ seq_printf(m, "power level %d sclk: %u mclk: %u vddc: %u\n",
+ current_index, pl->sclk, pl->mclk, pl->vddc);
+ }
+ }
+}
+
u32 btc_dpm_get_sclk(struct radeon_device *rdev, bool low)
{
struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
diff --git a/drivers/gpu/drm/radeon/btcd.h b/drivers/gpu/drm/radeon/btcd.h
index 29e32de..9c65be2 100644
--- a/drivers/gpu/drm/radeon/btcd.h
+++ b/drivers/gpu/drm/radeon/btcd.h
@@ -44,6 +44,10 @@
# define DYN_SPREAD_SPECTRUM_EN (1 << 23)
# define AC_DC_SW (1 << 24)
+#define TARGET_AND_CURRENT_PROFILE_INDEX 0x66c
+# define CURRENT_PROFILE_INDEX_MASK (0xf << 4)
+# define CURRENT_PROFILE_INDEX_SHIFT 4
+
#define CG_BIF_REQ_AND_RSP 0x7f4
#define CG_CLIENT_REQ(x) ((x) << 0)
#define CG_CLIENT_REQ_MASK (0xff << 0)
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index e6419ca..bbb1784 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3046,7 +3046,7 @@
}
/**
- * cik_select_se_sh - select which SE, SH to address
+ * cik_get_rb_disabled - computes the mask of disabled RBs
*
* @rdev: radeon_device pointer
* @max_rb_num: max RBs (render backends) for the asic
@@ -4134,8 +4134,11 @@
{
if (enable)
WREG32(CP_MEC_CNTL, 0);
- else
+ else {
WREG32(CP_MEC_CNTL, (MEC_ME1_HALT | MEC_ME2_HALT));
+ rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX].ready = false;
+ rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX].ready = false;
+ }
udelay(50);
}
@@ -7902,7 +7905,8 @@
/* init golden registers */
cik_init_golden_registers(rdev);
- radeon_pm_resume(rdev);
+ if (rdev->pm.pm_method == PM_METHOD_DPM)
+ radeon_pm_resume(rdev);
rdev->accel_working = true;
r = cik_startup(rdev);
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index 1ecb3f1..94626ea 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -264,6 +264,8 @@
WREG32(SDMA0_GFX_RB_CNTL + reg_offset, rb_cntl);
WREG32(SDMA0_GFX_IB_CNTL + reg_offset, 0);
}
+ rdev->ring[R600_RING_TYPE_DMA_INDEX].ready = false;
+ rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX].ready = false;
}
/**
@@ -291,6 +293,11 @@
u32 me_cntl, reg_offset;
int i;
+ if (enable == false) {
+ cik_sdma_gfx_stop(rdev);
+ cik_sdma_rlc_stop(rdev);
+ }
+
for (i = 0; i < 2; i++) {
if (i == 0)
reg_offset = SDMA0_REGISTER_OFFSET;
@@ -420,10 +427,6 @@
if (!rdev->sdma_fw)
return -EINVAL;
- /* stop the gfx rings and rlc compute queues */
- cik_sdma_gfx_stop(rdev);
- cik_sdma_rlc_stop(rdev);
-
/* halt the MEs */
cik_sdma_enable(rdev, false);
@@ -492,9 +495,6 @@
*/
void cik_sdma_fini(struct radeon_device *rdev)
{
- /* stop the gfx rings and rlc compute queues */
- cik_sdma_gfx_stop(rdev);
- cik_sdma_rlc_stop(rdev);
/* halt the MEs */
cik_sdma_enable(rdev, false);
radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_DMA_INDEX]);
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index 713a5d3..94e8587 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -278,13 +278,15 @@
return !ASIC_IS_NODCE(rdev);
}
-static void dce6_audio_enable(struct radeon_device *rdev,
- struct r600_audio_pin *pin,
- bool enable)
+void dce6_audio_enable(struct radeon_device *rdev,
+ struct r600_audio_pin *pin,
+ bool enable)
{
+ if (!pin)
+ return;
+
WREG32_ENDPOINT(pin->offset, AZ_F0_CODEC_PIN_CONTROL_HOTPLUG_CONTROL,
- AUDIO_ENABLED);
- DRM_INFO("%s audio %d support\n", enable ? "Enabling" : "Disabling", pin->id);
+ enable ? AUDIO_ENABLED : 0);
}
static const u32 pin_offsets[7] =
@@ -323,7 +325,8 @@
rdev->audio.pin[i].connected = false;
rdev->audio.pin[i].offset = pin_offsets[i];
rdev->audio.pin[i].id = i;
- dce6_audio_enable(rdev, &rdev->audio.pin[i], true);
+ /* disable audio. it will be set up later */
+ dce6_audio_enable(rdev, &rdev->audio.pin[i], false);
}
return 0;
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index f2b9e21..27b0ff1 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1680,7 +1680,7 @@
case RADEON_HPD_6:
if (RREG32(DC_HPD6_INT_STATUS) & DC_HPDx_SENSE)
connected = true;
- break;
+ break;
default:
break;
}
@@ -5299,7 +5299,8 @@
/* init golden registers */
evergreen_init_golden_registers(rdev);
- radeon_pm_resume(rdev);
+ if (rdev->pm.pm_method == PM_METHOD_DPM)
+ radeon_pm_resume(rdev);
rdev->accel_working = true;
r = evergreen_startup(rdev);
@@ -5475,9 +5476,9 @@
radeon_wb_fini(rdev);
radeon_ib_pool_fini(rdev);
radeon_irq_kms_fini(rdev);
- evergreen_pcie_gart_fini(rdev);
uvd_v1_0_fini(rdev);
radeon_uvd_fini(rdev);
+ evergreen_pcie_gart_fini(rdev);
r600_vram_scratch_fini(rdev);
radeon_gem_fini(rdev);
radeon_fence_driver_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index 0c6d5ce..05b0c95 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -306,6 +306,15 @@
return;
offset = dig->afmt->offset;
+ /* disable audio prior to setting up hw */
+ if (ASIC_IS_DCE6(rdev)) {
+ dig->afmt->pin = dce6_audio_get_pin(rdev);
+ dce6_audio_enable(rdev, dig->afmt->pin, false);
+ } else {
+ dig->afmt->pin = r600_audio_get_pin(rdev);
+ r600_audio_enable(rdev, dig->afmt->pin, false);
+ }
+
evergreen_audio_set_dto(encoder, mode->clock);
WREG32(HDMI_VBI_PACKET_CONTROL + offset,
@@ -409,12 +418,16 @@
WREG32(AFMT_RAMP_CONTROL1 + offset, 0x007FFFFF);
WREG32(AFMT_RAMP_CONTROL2 + offset, 0x00000001);
WREG32(AFMT_RAMP_CONTROL3 + offset, 0x00000001);
+
+ /* enable audio after to setting up hw */
+ if (ASIC_IS_DCE6(rdev))
+ dce6_audio_enable(rdev, dig->afmt->pin, true);
+ else
+ r600_audio_enable(rdev, dig->afmt->pin, true);
}
void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable)
{
- struct drm_device *dev = encoder->dev;
- struct radeon_device *rdev = dev->dev_private;
struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
@@ -427,15 +440,6 @@
if (!enable && !dig->afmt->enabled)
return;
- if (enable) {
- if (ASIC_IS_DCE6(rdev))
- dig->afmt->pin = dce6_audio_get_pin(rdev);
- else
- dig->afmt->pin = r600_audio_get_pin(rdev);
- } else {
- dig->afmt->pin = NULL;
- }
-
dig->afmt->enabled = enable;
DRM_DEBUG("%sabling HDMI interface @ 0x%04X for encoder 0x%x\n",
diff --git a/drivers/gpu/drm/radeon/evergreen_smc.h b/drivers/gpu/drm/radeon/evergreen_smc.h
index 76ada8c..3a03ba3 100644
--- a/drivers/gpu/drm/radeon/evergreen_smc.h
+++ b/drivers/gpu/drm/radeon/evergreen_smc.h
@@ -57,7 +57,7 @@
#define EVERGREEN_SMC_FIRMWARE_HEADER_LOCATION 0x100
-#define EVERGREEN_SMC_FIRMWARE_HEADER_softRegisters 0x0
+#define EVERGREEN_SMC_FIRMWARE_HEADER_softRegisters 0x8
#define EVERGREEN_SMC_FIRMWARE_HEADER_stateTable 0xC
#define EVERGREEN_SMC_FIRMWARE_HEADER_mcRegisterTable 0x20
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index b6e01d5..351db36 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -1223,7 +1223,7 @@
int kv_dpm_late_enable(struct radeon_device *rdev)
{
- int ret;
+ int ret = 0;
if (rdev->irq.installed &&
r600_is_internal_thermal_sensor(rdev->pm.int_thermal_type)) {
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index ea932ac..bf6300c 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -2105,7 +2105,8 @@
/* init golden registers */
ni_init_golden_registers(rdev);
- radeon_pm_resume(rdev);
+ if (rdev->pm.pm_method == PM_METHOD_DPM)
+ radeon_pm_resume(rdev);
rdev->accel_working = true;
r = cayman_startup(rdev);
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index c351226..ca81427 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -2588,7 +2588,7 @@
if (NISLANDS_DPM2_SQ_RAMP_STI_SIZE > (STI_SIZE_MASK >> STI_SIZE_SHIFT))
enable_sq_ramping = false;
- if (NISLANDS_DPM2_SQ_RAMP_LTI_RATIO <= (LTI_RATIO_MASK >> LTI_RATIO_SHIFT))
+ if (NISLANDS_DPM2_SQ_RAMP_LTI_RATIO > (LTI_RATIO_MASK >> LTI_RATIO_SHIFT))
enable_sq_ramping = false;
for (i = 0; i < state->performance_level_count; i++) {
@@ -3945,7 +3945,6 @@
struct rv7xx_power_info *pi = rv770_get_pi(rdev);
struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
struct ni_ps *ps = ni_get_ps(rps);
- u16 vddc;
struct rv7xx_pl *pl = &ps->performance_levels[index];
ps->performance_level_count = index + 1;
@@ -3961,8 +3960,8 @@
/* patch up vddc if necessary */
if (pl->vddc == 0xff01) {
- if (radeon_atom_get_max_vddc(rdev, 0, 0, &vddc) == 0)
- pl->vddc = vddc;
+ if (pi->max_vddc)
+ pl->vddc = pi->max_vddc;
}
if (rps->class & ATOM_PPLIB_CLASSIFICATION_ACPI) {
@@ -4322,7 +4321,8 @@
void ni_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
struct seq_file *m)
{
- struct radeon_ps *rps = rdev->pm.dpm.current_ps;
+ struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
+ struct radeon_ps *rps = &eg_pi->current_rps;
struct ni_ps *ps = ni_get_ps(rps);
struct rv7xx_pl *pl;
u32 current_index =
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index ef024ce..3cc78bb 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -3942,8 +3942,6 @@
/* Initialize surface registers */
radeon_surface_init(rdev);
- radeon_pm_resume(rdev);
-
rdev->accel_working = true;
r = r100_startup(rdev);
if (r) {
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 7c63ef8..0b658b3 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -1430,8 +1430,6 @@
/* Initialize surface registers */
radeon_surface_init(rdev);
- radeon_pm_resume(rdev);
-
rdev->accel_working = true;
r = r300_startup(rdev);
if (r) {
diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c
index 3768aab..802b192 100644
--- a/drivers/gpu/drm/radeon/r420.c
+++ b/drivers/gpu/drm/radeon/r420.c
@@ -325,8 +325,6 @@
/* Initialize surface registers */
radeon_surface_init(rdev);
- radeon_pm_resume(rdev);
-
rdev->accel_working = true;
r = r420_startup(rdev);
if (r) {
diff --git a/drivers/gpu/drm/radeon/r520.c b/drivers/gpu/drm/radeon/r520.c
index e209eb7..98d6053 100644
--- a/drivers/gpu/drm/radeon/r520.c
+++ b/drivers/gpu/drm/radeon/r520.c
@@ -240,8 +240,6 @@
/* Initialize surface registers */
radeon_surface_init(rdev);
- radeon_pm_resume(rdev);
-
rdev->accel_working = true;
r = r520_startup(rdev);
if (r) {
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 56140b4..647ef40 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2968,7 +2968,8 @@
/* post card */
atom_asic_init(rdev->mode_info.atom_context);
- radeon_pm_resume(rdev);
+ if (rdev->pm.pm_method == PM_METHOD_DPM)
+ radeon_pm_resume(rdev);
rdev->accel_working = true;
r = r600_startup(rdev);
@@ -3991,6 +3992,10 @@
break;
}
break;
+ case 124: /* UVD */
+ DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data);
+ radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX);
+ break;
case 176: /* CP_INT in ring buffer */
case 177: /* CP_INT in IB1 */
case 178: /* CP_INT in IB2 */
diff --git a/drivers/gpu/drm/radeon/r600_audio.c b/drivers/gpu/drm/radeon/r600_audio.c
index 47fc2b8..bffac10 100644
--- a/drivers/gpu/drm/radeon/r600_audio.c
+++ b/drivers/gpu/drm/radeon/r600_audio.c
@@ -142,12 +142,15 @@
}
/* enable the audio stream */
-static void r600_audio_enable(struct radeon_device *rdev,
- struct r600_audio_pin *pin,
- bool enable)
+void r600_audio_enable(struct radeon_device *rdev,
+ struct r600_audio_pin *pin,
+ bool enable)
{
u32 value = 0;
+ if (!pin)
+ return;
+
if (ASIC_IS_DCE4(rdev)) {
if (enable) {
value |= 0x81000000; /* Required to enable audio */
@@ -158,7 +161,6 @@
WREG32_P(R600_AUDIO_ENABLE,
enable ? 0x81000000 : 0x0, ~0x81000000);
}
- DRM_INFO("%s audio %d support\n", enable ? "Enabling" : "Disabling", pin->id);
}
/*
@@ -178,8 +180,8 @@
rdev->audio.pin[0].status_bits = 0;
rdev->audio.pin[0].category_code = 0;
rdev->audio.pin[0].id = 0;
-
- r600_audio_enable(rdev, &rdev->audio.pin[0], true);
+ /* disable audio. it will be set up later */
+ r600_audio_enable(rdev, &rdev->audio.pin[0], false);
return 0;
}
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index 3016fc1..85a2bb2 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -329,9 +329,6 @@
u8 *sadb;
int sad_count;
- /* XXX: setting this register causes hangs on some asics */
- return;
-
list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
if (connector->encoder == encoder) {
radeon_connector = to_radeon_connector(connector);
@@ -460,6 +457,10 @@
return;
offset = dig->afmt->offset;
+ /* disable audio prior to setting up hw */
+ dig->afmt->pin = r600_audio_get_pin(rdev);
+ r600_audio_enable(rdev, dig->afmt->pin, false);
+
r600_audio_set_dto(encoder, mode->clock);
WREG32(HDMI0_VBI_PACKET_CONTROL + offset,
@@ -531,6 +532,9 @@
WREG32(HDMI0_RAMP_CONTROL3 + offset, 0x00000001);
r600_hdmi_audio_workaround(encoder);
+
+ /* enable audio after to setting up hw */
+ r600_audio_enable(rdev, dig->afmt->pin, true);
}
/*
@@ -651,11 +655,6 @@
if (!enable && !dig->afmt->enabled)
return;
- if (enable)
- dig->afmt->pin = r600_audio_get_pin(rdev);
- else
- dig->afmt->pin = NULL;
-
/* Older chipsets require setting HDMI and routing manually */
if (!ASIC_IS_DCE3(rdev)) {
if (enable)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 4a8ac1c..e887d02 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -135,6 +135,9 @@
/* R600+ */
#define R600_RING_TYPE_UVD_INDEX 5
+/* number of hw syncs before falling back on blocking */
+#define RADEON_NUM_SYNCS 4
+
/* hardcode those limit for now */
#define RADEON_VA_IB_OFFSET (1 << 20)
#define RADEON_VA_RESERVED_SIZE (8 << 20)
@@ -554,7 +557,6 @@
/*
* Semaphores.
*/
-/* everything here is constant */
struct radeon_semaphore {
struct radeon_sa_bo *sa_bo;
signed waiters;
@@ -2745,6 +2747,12 @@
void r600_audio_update_hdmi(struct work_struct *work);
struct r600_audio_pin *r600_audio_get_pin(struct radeon_device *rdev);
struct r600_audio_pin *dce6_audio_get_pin(struct radeon_device *rdev);
+void r600_audio_enable(struct radeon_device *rdev,
+ struct r600_audio_pin *pin,
+ bool enable);
+void dce6_audio_enable(struct radeon_device *rdev,
+ struct r600_audio_pin *pin,
+ bool enable);
/*
* R600 vram scratch functions
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index f74db43..dda02bf 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1555,7 +1555,7 @@
.get_sclk = &btc_dpm_get_sclk,
.get_mclk = &btc_dpm_get_mclk,
.print_power_state = &rv770_dpm_print_power_state,
- .debugfs_print_current_performance_level = &rv770_dpm_debugfs_print_current_performance_level,
+ .debugfs_print_current_performance_level = &btc_dpm_debugfs_print_current_performance_level,
.force_performance_level = &rv770_dpm_force_performance_level,
.vblank_too_short = &btc_dpm_vblank_too_short,
},
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index b3bc433..ae637cf 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -551,6 +551,8 @@
u32 btc_dpm_get_sclk(struct radeon_device *rdev, bool low);
u32 btc_dpm_get_mclk(struct radeon_device *rdev, bool low);
bool btc_dpm_vblank_too_short(struct radeon_device *rdev);
+void btc_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
+ struct seq_file *m);
int sumo_dpm_init(struct radeon_device *rdev);
int sumo_dpm_enable(struct radeon_device *rdev);
int sumo_dpm_late_enable(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 485848f..fa9a9c0 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -219,7 +219,8 @@
memcpy(&output, info->buffer.pointer, size);
/* TODO: check version? */
- printk("ATPX version %u\n", output.version);
+ printk("ATPX version %u, functions 0x%08x\n",
+ output.version, output.function_bits);
radeon_atpx_parse_functions(&atpx->functions, output.function_bits);
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index b012cbb..044bc98 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1521,13 +1521,16 @@
if (r)
DRM_ERROR("ib ring test failed (%d).\n", r);
- if (rdev->pm.dpm_enabled) {
+ if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) {
/* do dpm late init */
r = radeon_pm_late_init(rdev);
if (r) {
rdev->pm.dpm_enabled = false;
DRM_ERROR("radeon_pm_late_init failed, disabling dpm\n");
}
+ } else {
+ /* resume old pm late */
+ radeon_pm_resume(rdev);
}
radeon_restore_bios_scratch_regs(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index d680608..fbd8b93 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -571,6 +571,8 @@
radeon_crtc->max_cursor_width = CURSOR_WIDTH;
radeon_crtc->max_cursor_height = CURSOR_HEIGHT;
}
+ dev->mode_config.cursor_width = radeon_crtc->max_cursor_width;
+ dev->mode_config.cursor_height = radeon_crtc->max_cursor_height;
#if 0
radeon_crtc->mode_set.crtc = &radeon_crtc->base;
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 84a1bbb7..f633c27 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -403,11 +403,15 @@
struct drm_device *drm_dev = pci_get_drvdata(pdev);
int ret;
- if (radeon_runtime_pm == 0)
- return -EINVAL;
+ if (radeon_runtime_pm == 0) {
+ pm_runtime_forbid(dev);
+ return -EBUSY;
+ }
- if (radeon_runtime_pm == -1 && !radeon_is_px())
- return -EINVAL;
+ if (radeon_runtime_pm == -1 && !radeon_is_px()) {
+ pm_runtime_forbid(dev);
+ return -EBUSY;
+ }
drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
drm_kms_helper_poll_disable(drm_dev);
@@ -456,12 +460,15 @@
struct drm_device *drm_dev = pci_get_drvdata(pdev);
struct drm_crtc *crtc;
- if (radeon_runtime_pm == 0)
+ if (radeon_runtime_pm == 0) {
+ pm_runtime_forbid(dev);
return -EBUSY;
+ }
/* are we PX enabled? */
if (radeon_runtime_pm == -1 && !radeon_is_px()) {
DRM_DEBUG_DRIVER("failing to power off - not px\n");
+ pm_runtime_forbid(dev);
return -EBUSY;
}
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 114d167..66ed3ea 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -33,6 +33,13 @@
#include <linux/vga_switcheroo.h>
#include <linux/slab.h>
#include <linux/pm_runtime.h>
+
+#if defined(CONFIG_VGA_SWITCHEROO)
+bool radeon_is_px(void);
+#else
+static inline bool radeon_is_px(void) { return false; }
+#endif
+
/**
* radeon_driver_unload_kms - Main unload function for KMS.
*
@@ -130,7 +137,8 @@
"Error during ACPI methods call\n");
}
- if (radeon_runtime_pm != 0) {
+ if ((radeon_runtime_pm == 1) ||
+ ((radeon_runtime_pm == -1) && radeon_is_px())) {
pm_runtime_use_autosuspend(dev->dev);
pm_runtime_set_autosuspend_delay(dev->dev, 5000);
pm_runtime_set_active(dev->dev);
@@ -537,6 +545,10 @@
radeon_vm_init(rdev, &fpriv->vm);
+ r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
+ if (r)
+ return r;
+
/* map the ib pool buffer read only into
* virtual address space */
bo_va = radeon_vm_bo_add(rdev, &fpriv->vm,
@@ -544,6 +556,8 @@
r = radeon_vm_bo_set_addr(rdev, bo_va, RADEON_VA_IB_OFFSET,
RADEON_VM_PAGE_READABLE |
RADEON_VM_PAGE_SNOOPED);
+
+ radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
if (r) {
radeon_vm_fini(rdev, &fpriv->vm);
kfree(fpriv);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 1b783f0..15e44a7 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -139,7 +139,7 @@
}
/* 64 dwords should be enough for fence too */
- r = radeon_ring_lock(rdev, ring, 64 + RADEON_NUM_RINGS * 8);
+ r = radeon_ring_lock(rdev, ring, 64 + RADEON_NUM_SYNCS * 8);
if (r) {
dev_err(rdev->dev, "scheduling IB failed (%d).\n", r);
return r;
diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c
index 2b42aa1..9006b32 100644
--- a/drivers/gpu/drm/radeon/radeon_semaphore.c
+++ b/drivers/gpu/drm/radeon/radeon_semaphore.c
@@ -34,14 +34,15 @@
int radeon_semaphore_create(struct radeon_device *rdev,
struct radeon_semaphore **semaphore)
{
+ uint32_t *cpu_addr;
int i, r;
*semaphore = kmalloc(sizeof(struct radeon_semaphore), GFP_KERNEL);
if (*semaphore == NULL) {
return -ENOMEM;
}
- r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo,
- &(*semaphore)->sa_bo, 8, 8, true);
+ r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &(*semaphore)->sa_bo,
+ 8 * RADEON_NUM_SYNCS, 8, true);
if (r) {
kfree(*semaphore);
*semaphore = NULL;
@@ -49,7 +50,10 @@
}
(*semaphore)->waiters = 0;
(*semaphore)->gpu_addr = radeon_sa_bo_gpu_addr((*semaphore)->sa_bo);
- *((uint64_t*)radeon_sa_bo_cpu_addr((*semaphore)->sa_bo)) = 0;
+
+ cpu_addr = radeon_sa_bo_cpu_addr((*semaphore)->sa_bo);
+ for (i = 0; i < RADEON_NUM_SYNCS; ++i)
+ cpu_addr[i] = 0;
for (i = 0; i < RADEON_NUM_RINGS; ++i)
(*semaphore)->sync_to[i] = NULL;
@@ -125,6 +129,7 @@
struct radeon_semaphore *semaphore,
int ring)
{
+ unsigned count = 0;
int i, r;
for (i = 0; i < RADEON_NUM_RINGS; ++i) {
@@ -140,6 +145,12 @@
return -EINVAL;
}
+ if (++count > RADEON_NUM_SYNCS) {
+ /* not enough room, wait manually */
+ radeon_fence_wait_locked(fence);
+ continue;
+ }
+
/* allocate enough space for sync command */
r = radeon_ring_alloc(rdev, &rdev->ring[i], 16);
if (r) {
@@ -164,6 +175,8 @@
radeon_ring_commit(rdev, &rdev->ring[i]);
radeon_fence_note_sync(fence, ring);
+
+ semaphore->gpu_addr += 8;
}
return 0;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 77f5b0c..040a2a1 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -714,6 +714,9 @@
DRM_ERROR("Failed initializing VRAM heap.\n");
return r;
}
+ /* Change the size here instead of the init above so only lpfn is affected */
+ radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
+
r = radeon_bo_create(rdev, 256 * 1024, PAGE_SIZE, true,
RADEON_GEM_DOMAIN_VRAM,
NULL, &rdev->stollen_vga_memory);
@@ -935,7 +938,7 @@
while (size) {
loff_t p = *pos / PAGE_SIZE;
unsigned off = *pos & ~PAGE_MASK;
- ssize_t cur_size = min(size, PAGE_SIZE - off);
+ size_t cur_size = min_t(size_t, size, PAGE_SIZE - off);
struct page *page;
void *ptr;
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 6781fee..3e6804b 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -171,6 +171,8 @@
radeon_bo_unref(&rdev->uvd.vcpu_bo);
+ radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_UVD_INDEX]);
+
release_firmware(rdev->uvd_fw);
}
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index b5c2369..130d5cc 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -474,8 +474,6 @@
/* Initialize surface registers */
radeon_surface_init(rdev);
- radeon_pm_resume(rdev);
-
rdev->accel_working = true;
r = rs400_startup(rdev);
if (r) {
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index fdcde76..72d3616 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -1048,8 +1048,6 @@
/* Initialize surface registers */
radeon_surface_init(rdev);
- radeon_pm_resume(rdev);
-
rdev->accel_working = true;
r = rs600_startup(rdev);
if (r) {
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 3595073..3462b64 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -756,8 +756,6 @@
/* Initialize surface registers */
radeon_surface_init(rdev);
- radeon_pm_resume(rdev);
-
rdev->accel_working = true;
r = rs690_startup(rdev);
if (r) {
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 98e8138..237dd29 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -586,8 +586,6 @@
/* Initialize surface registers */
radeon_surface_init(rdev);
- radeon_pm_resume(rdev);
-
rdev->accel_working = true;
r = rv515_startup(rdev);
if (r) {
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 6c772e5..fef3107 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -1811,7 +1811,8 @@
/* init golden registers */
rv770_init_golden_registers(rdev);
- radeon_pm_resume(rdev);
+ if (rdev->pm.pm_method == PM_METHOD_DPM)
+ radeon_pm_resume(rdev);
rdev->accel_working = true;
r = rv770_startup(rdev);
@@ -1955,9 +1956,9 @@
radeon_wb_fini(rdev);
radeon_ib_pool_fini(rdev);
radeon_irq_kms_fini(rdev);
- rv770_pcie_gart_fini(rdev);
uvd_v1_0_fini(rdev);
radeon_uvd_fini(rdev);
+ rv770_pcie_gart_fini(rdev);
r600_vram_scratch_fini(rdev);
radeon_gem_fini(rdev);
radeon_fence_driver_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index 80c595a..b5f63f5 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -2174,7 +2174,6 @@
struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
struct rv7xx_ps *ps = rv770_get_ps(rps);
u32 sclk, mclk;
- u16 vddc;
struct rv7xx_pl *pl;
switch (index) {
@@ -2214,8 +2213,8 @@
/* patch up vddc if necessary */
if (pl->vddc == 0xff01) {
- if (radeon_atom_get_max_vddc(rdev, 0, 0, &vddc) == 0)
- pl->vddc = vddc;
+ if (pi->max_vddc)
+ pl->vddc = pi->max_vddc;
}
if (rps->class & ATOM_PPLIB_CLASSIFICATION_ACPI) {
@@ -2527,14 +2526,7 @@
bool rv770_dpm_vblank_too_short(struct radeon_device *rdev)
{
u32 vblank_time = r600_dpm_get_vblank_time(rdev);
- u32 switch_limit = 300;
-
- /* quirks */
- /* ASUS K70AF */
- if ((rdev->pdev->device == 0x9553) &&
- (rdev->pdev->subsystem_vendor == 0x1043) &&
- (rdev->pdev->subsystem_device == 0x1c42))
- switch_limit = 200;
+ u32 switch_limit = 200; /* 300 */
/* RV770 */
/* mclk switching doesn't seem to work reliably on desktop RV770s */
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 09ec4f6..9a124d0 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -6338,6 +6338,10 @@
break;
}
break;
+ case 124: /* UVD */
+ DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data);
+ radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX);
+ break;
case 146:
case 147:
addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR);
@@ -6614,7 +6618,8 @@
/* init golden registers */
si_init_golden_registers(rdev);
- radeon_pm_resume(rdev);
+ if (rdev->pm.pm_method == PM_METHOD_DPM)
+ radeon_pm_resume(rdev);
rdev->accel_working = true;
r = si_startup(rdev);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 0471501..0a2f5b4 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2395,7 +2395,7 @@
if (SISLANDS_DPM2_SQ_RAMP_STI_SIZE > (STI_SIZE_MASK >> STI_SIZE_SHIFT))
enable_sq_ramping = false;
- if (SISLANDS_DPM2_SQ_RAMP_LTI_RATIO <= (LTI_RATIO_MASK >> LTI_RATIO_SHIFT))
+ if (SISLANDS_DPM2_SQ_RAMP_LTI_RATIO > (LTI_RATIO_MASK >> LTI_RATIO_SHIFT))
enable_sq_ramping = false;
for (i = 0; i < state->performance_level_count; i++) {
@@ -6472,7 +6472,8 @@
void si_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
struct seq_file *m)
{
- struct radeon_ps *rps = rdev->pm.dpm.current_ps;
+ struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev);
+ struct radeon_ps *rps = &eg_pi->current_rps;
struct ni_ps *ps = ni_get_ps(rps);
struct rv7xx_pl *pl;
u32 current_index =
diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c
index f121efe..8b47b3cd 100644
--- a/drivers/gpu/drm/radeon/sumo_dpm.c
+++ b/drivers/gpu/drm/radeon/sumo_dpm.c
@@ -1807,7 +1807,7 @@
struct seq_file *m)
{
struct sumo_power_info *pi = sumo_get_pi(rdev);
- struct radeon_ps *rps = rdev->pm.dpm.current_ps;
+ struct radeon_ps *rps = &pi->current_rps;
struct sumo_ps *ps = sumo_get_ps(rps);
struct sumo_pl *pl;
u32 current_index =
diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c
index 2d44719..2da0e17 100644
--- a/drivers/gpu/drm/radeon/trinity_dpm.c
+++ b/drivers/gpu/drm/radeon/trinity_dpm.c
@@ -1926,7 +1926,8 @@
void trinity_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
struct seq_file *m)
{
- struct radeon_ps *rps = rdev->pm.dpm.current_ps;
+ struct trinity_power_info *pi = trinity_get_pi(rdev);
+ struct radeon_ps *rps = &pi->current_rps;
struct trinity_ps *ps = trinity_get_ps(rps);
struct trinity_pl *pl;
u32 current_index =
diff --git a/drivers/gpu/drm/radeon/uvd_v2_2.c b/drivers/gpu/drm/radeon/uvd_v2_2.c
index 824550d..d177100 100644
--- a/drivers/gpu/drm/radeon/uvd_v2_2.c
+++ b/drivers/gpu/drm/radeon/uvd_v2_2.c
@@ -57,7 +57,6 @@
radeon_ring_write(ring, 0);
radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_CMD, 0));
radeon_ring_write(ring, 2);
- return;
}
/**
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 88a5290..c715947 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -104,7 +104,7 @@
static void tegra_drm_lastclose(struct drm_device *drm)
{
-#ifdef CONFIG_TEGRA_DRM_FBDEV
+#ifdef CONFIG_DRM_TEGRA_FBDEV
struct tegra_drm *tegra = drm->dev_private;
tegra_fbdev_restore_mode(tegra->fbdev);
diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c
index 338f7f6..0266fb4 100644
--- a/drivers/gpu/drm/tegra/rgb.c
+++ b/drivers/gpu/drm/tegra/rgb.c
@@ -15,6 +15,7 @@
struct tegra_rgb {
struct tegra_output output;
struct tegra_dc *dc;
+ bool enabled;
struct clk *clk_parent;
struct clk *clk;
@@ -89,6 +90,9 @@
struct tegra_rgb *rgb = to_rgb(output);
unsigned long value;
+ if (rgb->enabled)
+ return 0;
+
tegra_dc_write_regs(rgb->dc, rgb_enable, ARRAY_SIZE(rgb_enable));
value = DE_SELECT_ACTIVE | DE_CONTROL_NORMAL;
@@ -122,6 +126,8 @@
tegra_dc_writel(rgb->dc, GENERAL_ACT_REQ << 8, DC_CMD_STATE_CONTROL);
tegra_dc_writel(rgb->dc, GENERAL_ACT_REQ, DC_CMD_STATE_CONTROL);
+ rgb->enabled = true;
+
return 0;
}
@@ -130,6 +136,9 @@
struct tegra_rgb *rgb = to_rgb(output);
unsigned long value;
+ if (!rgb->enabled)
+ return 0;
+
value = tegra_dc_readl(rgb->dc, DC_CMD_DISPLAY_POWER_CONTROL);
value &= ~(PW0_ENABLE | PW1_ENABLE | PW2_ENABLE | PW3_ENABLE |
PW4_ENABLE | PM0_ENABLE | PM1_ENABLE);
@@ -144,6 +153,8 @@
tegra_dc_write_regs(rgb->dc, rgb_disable, ARRAY_SIZE(rgb_disable));
+ rgb->enabled = false;
+
return 0;
}
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index 3302f99e..764be36 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -126,6 +126,7 @@
agp_be->ttm.func = &ttm_agp_func;
if (ttm_tt_init(&agp_be->ttm, bdev, size, page_flags, dummy_read_page)) {
+ kfree(agp_be);
return NULL;
}
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index a066513..214b799 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -351,9 +351,11 @@
moved:
if (bo->evicted) {
- ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement);
- if (ret)
- pr_err("Can not flush read caches\n");
+ if (bdev->driver->invalidate_caches) {
+ ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement);
+ if (ret)
+ pr_err("Can not flush read caches\n");
+ }
bo->evicted = false;
}
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 801231c..0ce48e5 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -339,11 +339,13 @@
vma->vm_private_data = bo;
/*
- * PFNMAP is faster than MIXEDMAP due to reduced page
- * administration. So use MIXEDMAP only if private VMA, where
- * we need to support COW.
+ * We'd like to use VM_PFNMAP on shared mappings, where
+ * (vma->vm_flags & VM_SHARED) != 0, for performance reasons,
+ * but for some reason VM_PFNMAP + x86 PAT + write-combine is very
+ * bad for performance. Until that has been sorted out, use
+ * VM_MIXEDMAP on all mappings. See freedesktop.org bug #75719
*/
- vma->vm_flags |= (vma->vm_flags & VM_SHARED) ? VM_PFNMAP : VM_MIXEDMAP;
+ vma->vm_flags |= VM_MIXEDMAP;
vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
return 0;
out_unref:
@@ -359,7 +361,7 @@
vma->vm_ops = &ttm_bo_vm_ops;
vma->vm_private_data = ttm_bo_reference(bo);
- vma->vm_flags |= (vma->vm_flags & VM_SHARED) ? VM_PFNMAP : VM_MIXEDMAP;
+ vma->vm_flags |= VM_MIXEDMAP;
vma->vm_flags |= VM_IO | VM_DONTEXPAND;
return 0;
}
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 8d67b94..0394811 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -177,8 +177,10 @@
if (obj->vmapping)
udl_gem_vunmap(obj);
- if (gem_obj->import_attach)
+ if (gem_obj->import_attach) {
drm_prime_gem_destroy(gem_obj, obj->sg);
+ put_device(gem_obj->dev->dev);
+ }
if (obj->pages)
udl_gem_put_pages(obj);
@@ -256,9 +258,12 @@
int ret;
/* need to attach */
+ get_device(dev->dev);
attach = dma_buf_attach(dma_buf, dev->dev);
- if (IS_ERR(attach))
+ if (IS_ERR(attach)) {
+ put_device(dev->dev);
return ERR_CAST(attach);
+ }
get_dma_buf(dma_buf);
@@ -282,6 +287,6 @@
fail_detach:
dma_buf_detach(dma_buf, attach);
dma_buf_put(dma_buf);
-
+ put_device(dev->dev);
return ERR_PTR(ret);
}
diff --git a/drivers/gpu/drm/vmwgfx/svga3d_reg.h b/drivers/gpu/drm/vmwgfx/svga3d_reg.h
index b645647..f58dc7d 100644
--- a/drivers/gpu/drm/vmwgfx/svga3d_reg.h
+++ b/drivers/gpu/drm/vmwgfx/svga3d_reg.h
@@ -261,12 +261,7 @@
/* Planar video formats. */
SVGA3D_YV12 = 121,
- /* Shader constant formats. */
- SVGA3D_SURFACE_SHADERCONST_FLOAT = 122,
- SVGA3D_SURFACE_SHADERCONST_INT = 123,
- SVGA3D_SURFACE_SHADERCONST_BOOL = 124,
-
- SVGA3D_FORMAT_MAX = 125,
+ SVGA3D_FORMAT_MAX = 122,
} SVGA3dSurfaceFormat;
typedef uint32 SVGA3dColor; /* a, r, g, b */
@@ -1223,9 +1218,19 @@
#define SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL 1129
#define SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE 1130
-
+#define SVGA_3D_CMD_GB_SCREEN_DMA 1131
+#define SVGA_3D_CMD_BIND_GB_SURFACE_WITH_PITCH 1132
+#define SVGA_3D_CMD_GB_MOB_FENCE 1133
+#define SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 1134
#define SVGA_3D_CMD_DEFINE_GB_MOB64 1135
#define SVGA_3D_CMD_REDEFINE_GB_MOB64 1136
+#define SVGA_3D_CMD_NOP_ERROR 1137
+
+#define SVGA_3D_CMD_RESERVED1 1138
+#define SVGA_3D_CMD_RESERVED2 1139
+#define SVGA_3D_CMD_RESERVED3 1140
+#define SVGA_3D_CMD_RESERVED4 1141
+#define SVGA_3D_CMD_RESERVED5 1142
#define SVGA_3D_CMD_MAX 1142
#define SVGA_3D_CMD_FUTURE_MAX 3000
@@ -1973,8 +1978,7 @@
uint32 sizeInBytes;
uint32 validSizeInBytes;
SVGAMobFormat ptDepth;
-}
-__attribute__((__packed__))
+} __packed
SVGA3dCmdSetOTableBase; /* SVGA_3D_CMD_SET_OTABLE_BASE */
typedef
@@ -1984,15 +1988,13 @@
uint32 sizeInBytes;
uint32 validSizeInBytes;
SVGAMobFormat ptDepth;
-}
-__attribute__((__packed__))
+} __packed
SVGA3dCmdSetOTableBase64; /* SVGA_3D_CMD_SET_OTABLE_BASE64 */
typedef
struct {
SVGAOTableType type;
-}
-__attribute__((__packed__))
+} __packed
SVGA3dCmdReadbackOTable; /* SVGA_3D_CMD_READBACK_OTABLE */
/*
@@ -2005,8 +2007,7 @@
SVGAMobFormat ptDepth;
PPN base;
uint32 sizeInBytes;
-}
-__attribute__((__packed__))
+} __packed
SVGA3dCmdDefineGBMob; /* SVGA_3D_CMD_DEFINE_GB_MOB */
@@ -2017,8 +2018,7 @@
typedef
struct SVGA3dCmdDestroyGBMob {
SVGAMobId mobid;
-}
-__attribute__((__packed__))
+} __packed
SVGA3dCmdDestroyGBMob; /* SVGA_3D_CMD_DESTROY_GB_MOB */
/*
@@ -2031,8 +2031,7 @@
SVGAMobFormat ptDepth;
PPN base;
uint32 sizeInBytes;
-}
-__attribute__((__packed__))
+} __packed
SVGA3dCmdRedefineGBMob; /* SVGA_3D_CMD_REDEFINE_GB_MOB */
/*
@@ -2045,8 +2044,7 @@
SVGAMobFormat ptDepth;
PPN64 base;
uint32 sizeInBytes;
-}
-__attribute__((__packed__))
+} __packed
SVGA3dCmdDefineGBMob64; /* SVGA_3D_CMD_DEFINE_GB_MOB64 */
/*
@@ -2059,8 +2057,7 @@
SVGAMobFormat ptDepth;
PPN64 base;
uint32 sizeInBytes;
-}
-__attribute__((__packed__))
+} __packed
SVGA3dCmdRedefineGBMob64; /* SVGA_3D_CMD_REDEFINE_GB_MOB64 */
/*
@@ -2070,8 +2067,7 @@
typedef
struct SVGA3dCmdUpdateGBMobMapping {
SVGAMobId mobid;
-}
-__attribute__((__packed__))
+} __packed
SVGA3dCmdUpdateGBMobMapping; /* SVGA_3D_CMD_UPDATE_GB_MOB_MAPPING */
/*
@@ -2087,7 +2083,8 @@
uint32 multisampleCount;
SVGA3dTextureFilter autogenFilter;
SVGA3dSize size;
-} SVGA3dCmdDefineGBSurface; /* SVGA_3D_CMD_DEFINE_GB_SURFACE */
+} __packed
+SVGA3dCmdDefineGBSurface; /* SVGA_3D_CMD_DEFINE_GB_SURFACE */
/*
* Destroy a guest-backed surface.
@@ -2096,7 +2093,8 @@
typedef
struct SVGA3dCmdDestroyGBSurface {
uint32 sid;
-} SVGA3dCmdDestroyGBSurface; /* SVGA_3D_CMD_DESTROY_GB_SURFACE */
+} __packed
+SVGA3dCmdDestroyGBSurface; /* SVGA_3D_CMD_DESTROY_GB_SURFACE */
/*
* Bind a guest-backed surface to an object.
@@ -2106,7 +2104,8 @@
struct SVGA3dCmdBindGBSurface {
uint32 sid;
SVGAMobId mobid;
-} SVGA3dCmdBindGBSurface; /* SVGA_3D_CMD_BIND_GB_SURFACE */
+} __packed
+SVGA3dCmdBindGBSurface; /* SVGA_3D_CMD_BIND_GB_SURFACE */
/*
* Conditionally bind a mob to a guest backed surface if testMobid
@@ -2123,7 +2122,7 @@
SVGAMobId testMobid;
SVGAMobId mobid;
uint32 flags;
-}
+} __packed
SVGA3dCmdCondBindGBSurface; /* SVGA_3D_CMD_COND_BIND_GB_SURFACE */
/*
@@ -2135,7 +2134,8 @@
struct SVGA3dCmdUpdateGBImage {
SVGA3dSurfaceImageId image;
SVGA3dBox box;
-} SVGA3dCmdUpdateGBImage; /* SVGA_3D_CMD_UPDATE_GB_IMAGE */
+} __packed
+SVGA3dCmdUpdateGBImage; /* SVGA_3D_CMD_UPDATE_GB_IMAGE */
/*
* Update an entire guest-backed surface.
@@ -2145,7 +2145,8 @@
typedef
struct SVGA3dCmdUpdateGBSurface {
uint32 sid;
-} SVGA3dCmdUpdateGBSurface; /* SVGA_3D_CMD_UPDATE_GB_SURFACE */
+} __packed
+SVGA3dCmdUpdateGBSurface; /* SVGA_3D_CMD_UPDATE_GB_SURFACE */
/*
* Readback an image in a guest-backed surface.
@@ -2155,7 +2156,8 @@
typedef
struct SVGA3dCmdReadbackGBImage {
SVGA3dSurfaceImageId image;
-} SVGA3dCmdReadbackGBImage; /* SVGA_3D_CMD_READBACK_GB_IMAGE*/
+} __packed
+SVGA3dCmdReadbackGBImage; /* SVGA_3D_CMD_READBACK_GB_IMAGE*/
/*
* Readback an entire guest-backed surface.
@@ -2165,7 +2167,8 @@
typedef
struct SVGA3dCmdReadbackGBSurface {
uint32 sid;
-} SVGA3dCmdReadbackGBSurface; /* SVGA_3D_CMD_READBACK_GB_SURFACE */
+} __packed
+SVGA3dCmdReadbackGBSurface; /* SVGA_3D_CMD_READBACK_GB_SURFACE */
/*
* Readback a sub rect of an image in a guest-backed surface. After
@@ -2179,7 +2182,7 @@
SVGA3dSurfaceImageId image;
SVGA3dBox box;
uint32 invertBox;
-}
+} __packed
SVGA3dCmdReadbackGBImagePartial; /* SVGA_3D_CMD_READBACK_GB_IMAGE_PARTIAL */
/*
@@ -2190,7 +2193,8 @@
typedef
struct SVGA3dCmdInvalidateGBImage {
SVGA3dSurfaceImageId image;
-} SVGA3dCmdInvalidateGBImage; /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE */
+} __packed
+SVGA3dCmdInvalidateGBImage; /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE */
/*
* Invalidate an entire guest-backed surface.
@@ -2200,7 +2204,8 @@
typedef
struct SVGA3dCmdInvalidateGBSurface {
uint32 sid;
-} SVGA3dCmdInvalidateGBSurface; /* SVGA_3D_CMD_INVALIDATE_GB_SURFACE */
+} __packed
+SVGA3dCmdInvalidateGBSurface; /* SVGA_3D_CMD_INVALIDATE_GB_SURFACE */
/*
* Invalidate a sub rect of an image in a guest-backed surface. After
@@ -2214,7 +2219,7 @@
SVGA3dSurfaceImageId image;
SVGA3dBox box;
uint32 invertBox;
-}
+} __packed
SVGA3dCmdInvalidateGBImagePartial; /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL */
/*
@@ -2224,7 +2229,8 @@
typedef
struct SVGA3dCmdDefineGBContext {
uint32 cid;
-} SVGA3dCmdDefineGBContext; /* SVGA_3D_CMD_DEFINE_GB_CONTEXT */
+} __packed
+SVGA3dCmdDefineGBContext; /* SVGA_3D_CMD_DEFINE_GB_CONTEXT */
/*
* Destroy a guest-backed context.
@@ -2233,7 +2239,8 @@
typedef
struct SVGA3dCmdDestroyGBContext {
uint32 cid;
-} SVGA3dCmdDestroyGBContext; /* SVGA_3D_CMD_DESTROY_GB_CONTEXT */
+} __packed
+SVGA3dCmdDestroyGBContext; /* SVGA_3D_CMD_DESTROY_GB_CONTEXT */
/*
* Bind a guest-backed context.
@@ -2252,7 +2259,8 @@
uint32 cid;
SVGAMobId mobid;
uint32 validContents;
-} SVGA3dCmdBindGBContext; /* SVGA_3D_CMD_BIND_GB_CONTEXT */
+} __packed
+SVGA3dCmdBindGBContext; /* SVGA_3D_CMD_BIND_GB_CONTEXT */
/*
* Readback a guest-backed context.
@@ -2262,7 +2270,8 @@
typedef
struct SVGA3dCmdReadbackGBContext {
uint32 cid;
-} SVGA3dCmdReadbackGBContext; /* SVGA_3D_CMD_READBACK_GB_CONTEXT */
+} __packed
+SVGA3dCmdReadbackGBContext; /* SVGA_3D_CMD_READBACK_GB_CONTEXT */
/*
* Invalidate a guest-backed context.
@@ -2270,7 +2279,8 @@
typedef
struct SVGA3dCmdInvalidateGBContext {
uint32 cid;
-} SVGA3dCmdInvalidateGBContext; /* SVGA_3D_CMD_INVALIDATE_GB_CONTEXT */
+} __packed
+SVGA3dCmdInvalidateGBContext; /* SVGA_3D_CMD_INVALIDATE_GB_CONTEXT */
/*
* Define a guest-backed shader.
@@ -2281,7 +2291,8 @@
uint32 shid;
SVGA3dShaderType type;
uint32 sizeInBytes;
-} SVGA3dCmdDefineGBShader; /* SVGA_3D_CMD_DEFINE_GB_SHADER */
+} __packed
+SVGA3dCmdDefineGBShader; /* SVGA_3D_CMD_DEFINE_GB_SHADER */
/*
* Bind a guest-backed shader.
@@ -2291,7 +2302,8 @@
uint32 shid;
SVGAMobId mobid;
uint32 offsetInBytes;
-} SVGA3dCmdBindGBShader; /* SVGA_3D_CMD_BIND_GB_SHADER */
+} __packed
+SVGA3dCmdBindGBShader; /* SVGA_3D_CMD_BIND_GB_SHADER */
/*
* Destroy a guest-backed shader.
@@ -2299,7 +2311,8 @@
typedef struct SVGA3dCmdDestroyGBShader {
uint32 shid;
-} SVGA3dCmdDestroyGBShader; /* SVGA_3D_CMD_DESTROY_GB_SHADER */
+} __packed
+SVGA3dCmdDestroyGBShader; /* SVGA_3D_CMD_DESTROY_GB_SHADER */
typedef
struct {
@@ -2314,14 +2327,16 @@
* Note that FLOAT and INT constants are 4-dwords in length, while
* BOOL constants are 1-dword in length.
*/
-} SVGA3dCmdSetGBShaderConstInline;
+} __packed
+SVGA3dCmdSetGBShaderConstInline;
/* SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE */
typedef
struct {
uint32 cid;
SVGA3dQueryType type;
-} SVGA3dCmdBeginGBQuery; /* SVGA_3D_CMD_BEGIN_GB_QUERY */
+} __packed
+SVGA3dCmdBeginGBQuery; /* SVGA_3D_CMD_BEGIN_GB_QUERY */
typedef
struct {
@@ -2329,7 +2344,8 @@
SVGA3dQueryType type;
SVGAMobId mobid;
uint32 offset;
-} SVGA3dCmdEndGBQuery; /* SVGA_3D_CMD_END_GB_QUERY */
+} __packed
+SVGA3dCmdEndGBQuery; /* SVGA_3D_CMD_END_GB_QUERY */
/*
@@ -2346,21 +2362,22 @@
SVGA3dQueryType type;
SVGAMobId mobid;
uint32 offset;
-} SVGA3dCmdWaitForGBQuery; /* SVGA_3D_CMD_WAIT_FOR_GB_QUERY */
+} __packed
+SVGA3dCmdWaitForGBQuery; /* SVGA_3D_CMD_WAIT_FOR_GB_QUERY */
typedef
struct {
SVGAMobId mobid;
uint32 fbOffset;
uint32 initalized;
-}
+} __packed
SVGA3dCmdEnableGart; /* SVGA_3D_CMD_ENABLE_GART */
typedef
struct {
SVGAMobId mobid;
uint32 gartOffset;
-}
+} __packed
SVGA3dCmdMapMobIntoGart; /* SVGA_3D_CMD_MAP_MOB_INTO_GART */
@@ -2368,7 +2385,7 @@
struct {
uint32 gartOffset;
uint32 numPages;
-}
+} __packed
SVGA3dCmdUnmapGartRange; /* SVGA_3D_CMD_UNMAP_GART_RANGE */
@@ -2385,27 +2402,27 @@
int32 xRoot;
int32 yRoot;
uint32 flags;
-}
+} __packed
SVGA3dCmdDefineGBScreenTarget; /* SVGA_3D_CMD_DEFINE_GB_SCREENTARGET */
typedef
struct {
uint32 stid;
-}
+} __packed
SVGA3dCmdDestroyGBScreenTarget; /* SVGA_3D_CMD_DESTROY_GB_SCREENTARGET */
typedef
struct {
uint32 stid;
SVGA3dSurfaceImageId image;
-}
+} __packed
SVGA3dCmdBindGBScreenTarget; /* SVGA_3D_CMD_BIND_GB_SCREENTARGET */
typedef
struct {
uint32 stid;
SVGA3dBox box;
-}
+} __packed
SVGA3dCmdUpdateGBScreenTarget; /* SVGA_3D_CMD_UPDATE_GB_SCREENTARGET */
/*
diff --git a/drivers/gpu/drm/vmwgfx/svga3d_surfacedefs.h b/drivers/gpu/drm/vmwgfx/svga3d_surfacedefs.h
index 8369c3b..ef33850 100644
--- a/drivers/gpu/drm/vmwgfx/svga3d_surfacedefs.h
+++ b/drivers/gpu/drm/vmwgfx/svga3d_surfacedefs.h
@@ -38,8 +38,11 @@
#define DIV_ROUND_UP(x, y) (((x) + (y) - 1) / (y))
#define max_t(type, x, y) ((x) > (y) ? (x) : (y))
+#define min_t(type, x, y) ((x) < (y) ? (x) : (y))
#define surf_size_struct SVGA3dSize
#define u32 uint32
+#define u64 uint64_t
+#define U32_MAX ((u32)~0U)
#endif /* __KERNEL__ */
@@ -704,8 +707,8 @@
static inline u32 clamped_umul32(u32 a, u32 b)
{
- uint64_t tmp = (uint64_t) a*b;
- return (tmp > (uint64_t) ((u32) -1)) ? (u32) -1 : tmp;
+ u64 tmp = (u64) a*b;
+ return (tmp > (u64) U32_MAX) ? U32_MAX : tmp;
}
static inline const struct svga3d_surface_desc *
@@ -834,7 +837,7 @@
bool cubemap)
{
const struct svga3d_surface_desc *desc = svga3dsurface_get_desc(format);
- u32 total_size = 0;
+ u64 total_size = 0;
u32 mip;
for (mip = 0; mip < num_mip_levels; mip++) {
@@ -847,7 +850,7 @@
if (cubemap)
total_size *= SVGA3D_MAX_SURFACE_FACES;
- return total_size;
+ return (u32) min_t(u64, total_size, (u64) U32_MAX);
}
diff --git a/drivers/gpu/drm/vmwgfx/svga_reg.h b/drivers/gpu/drm/vmwgfx/svga_reg.h
index 71defa4..11323dd 100644
--- a/drivers/gpu/drm/vmwgfx/svga_reg.h
+++ b/drivers/gpu/drm/vmwgfx/svga_reg.h
@@ -169,10 +169,17 @@
SVGA_REG_TRACES = 45, /* Enable trace-based updates even when FIFO is on */
SVGA_REG_GMRS_MAX_PAGES = 46, /* Maximum number of 4KB pages for all GMRs */
SVGA_REG_MEMORY_SIZE = 47, /* Total dedicated device memory excluding FIFO */
+ SVGA_REG_COMMAND_LOW = 48, /* Lower 32 bits and submits commands */
+ SVGA_REG_COMMAND_HIGH = 49, /* Upper 32 bits of command buffer PA */
SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM = 50, /* Max primary memory */
SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB = 51, /* Suggested limit on mob mem */
SVGA_REG_DEV_CAP = 52, /* Write dev cap index, read value */
- SVGA_REG_TOP = 53, /* Must be 1 more than the last register */
+ SVGA_REG_CMD_PREPEND_LOW = 53,
+ SVGA_REG_CMD_PREPEND_HIGH = 54,
+ SVGA_REG_SCREENTARGET_MAX_WIDTH = 55,
+ SVGA_REG_SCREENTARGET_MAX_HEIGHT = 56,
+ SVGA_REG_MOB_MAX_SIZE = 57,
+ SVGA_REG_TOP = 58, /* Must be 1 more than the last register */
SVGA_PALETTE_BASE = 1024, /* Base of SVGA color map */
/* Next 768 (== 256*3) registers exist for colormap */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
index 9426c53..1e80152 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
@@ -551,8 +551,7 @@
cmd->header.size = sizeof(cmd->body);
cmd->body.cid = bi->ctx->id;
cmd->body.type = bi->i1.shader_type;
- cmd->body.shid =
- cpu_to_le32((rebind) ? bi->res->id : SVGA3D_INVALID_ID);
+ cmd->body.shid = ((rebind) ? bi->res->id : SVGA3D_INVALID_ID);
vmw_fifo_commit(dev_priv, sizeof(*cmd));
return 0;
@@ -585,8 +584,7 @@
cmd->header.size = sizeof(cmd->body);
cmd->body.cid = bi->ctx->id;
cmd->body.type = bi->i1.rt_type;
- cmd->body.target.sid =
- cpu_to_le32((rebind) ? bi->res->id : SVGA3D_INVALID_ID);
+ cmd->body.target.sid = ((rebind) ? bi->res->id : SVGA3D_INVALID_ID);
cmd->body.target.face = 0;
cmd->body.target.mipmap = 0;
vmw_fifo_commit(dev_priv, sizeof(*cmd));
@@ -628,8 +626,7 @@
cmd->body.c.cid = bi->ctx->id;
cmd->body.s1.stage = bi->i1.texture_stage;
cmd->body.s1.name = SVGA3D_TS_BIND_TEXTURE;
- cmd->body.s1.value =
- cpu_to_le32((rebind) ? bi->res->id : SVGA3D_INVALID_ID);
+ cmd->body.s1.value = ((rebind) ? bi->res->id : SVGA3D_INVALID_ID);
vmw_fifo_commit(dev_priv, sizeof(*cmd));
return 0;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 3bdc0ad..0083cbf 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -667,6 +667,7 @@
dev_priv->memory_size = 512*1024*1024;
}
dev_priv->max_mob_pages = 0;
+ dev_priv->max_mob_size = 0;
if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) {
uint64_t mem_size =
vmw_read(dev_priv,
@@ -676,6 +677,8 @@
dev_priv->prim_bb_mem =
vmw_read(dev_priv,
SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM);
+ dev_priv->max_mob_size =
+ vmw_read(dev_priv, SVGA_REG_MOB_MAX_SIZE);
} else
dev_priv->prim_bb_mem = dev_priv->vram_size;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index ecaa302..0783155 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -40,7 +40,7 @@
#include <drm/ttm/ttm_module.h>
#include "vmwgfx_fence.h"
-#define VMWGFX_DRIVER_DATE "20121114"
+#define VMWGFX_DRIVER_DATE "20140228"
#define VMWGFX_DRIVER_MAJOR 2
#define VMWGFX_DRIVER_MINOR 5
#define VMWGFX_DRIVER_PATCHLEVEL 0
@@ -386,6 +386,7 @@
uint32_t max_gmr_ids;
uint32_t max_gmr_pages;
uint32_t max_mob_pages;
+ uint32_t max_mob_size;
uint32_t memory_size;
bool has_gmr;
bool has_mob;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 269b85c..efb575a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -602,7 +602,7 @@
{
struct vmw_cid_cmd {
SVGA3dCmdHeader header;
- __le32 cid;
+ uint32_t cid;
} *cmd;
cmd = container_of(header, struct vmw_cid_cmd, header);
@@ -1835,7 +1835,7 @@
return 0;
}
-static const struct vmw_cmd_entry const vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
+static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
VMW_CMD_DEF(SVGA_3D_CMD_SURFACE_DEFINE, &vmw_cmd_invalid,
false, false, false),
VMW_CMD_DEF(SVGA_3D_CMD_SURFACE_DESTROY, &vmw_cmd_invalid,
@@ -2032,6 +2032,9 @@
goto out_invalid;
entry = &vmw_cmd_entries[cmd_id];
+ if (unlikely(!entry->func))
+ goto out_invalid;
+
if (unlikely(!entry->user_allow && !sw_context->kernel))
goto out_privileged;
@@ -2469,7 +2472,7 @@
if (dev_priv->has_mob) {
ret = vmw_rebind_contexts(sw_context);
if (unlikely(ret != 0))
- goto out_err;
+ goto out_unlock_binding;
}
cmd = vmw_fifo_reserve(dev_priv, command_size);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index f9881f9..47b7094 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -102,6 +102,9 @@
vmw_fp->gb_aware = true;
param->value = dev_priv->max_mob_pages * PAGE_SIZE;
break;
+ case DRM_VMW_PARAM_MAX_MOB_SIZE:
+ param->value = dev_priv->max_mob_size;
+ break;
default:
DRM_ERROR("Illegal vmwgfx get param request: %d\n",
param->param);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
index d4a5a19..04a64b8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
@@ -188,18 +188,20 @@
bo = otable->page_table->pt_bo;
cmd = vmw_fifo_reserve(dev_priv, sizeof(*cmd));
- if (unlikely(cmd == NULL))
- DRM_ERROR("Failed reserving FIFO space for OTable setup.\n");
-
- memset(cmd, 0, sizeof(*cmd));
- cmd->header.id = SVGA_3D_CMD_SET_OTABLE_BASE;
- cmd->header.size = sizeof(cmd->body);
- cmd->body.type = type;
- cmd->body.baseAddress = 0;
- cmd->body.sizeInBytes = 0;
- cmd->body.validSizeInBytes = 0;
- cmd->body.ptDepth = SVGA3D_MOBFMT_INVALID;
- vmw_fifo_commit(dev_priv, sizeof(*cmd));
+ if (unlikely(cmd == NULL)) {
+ DRM_ERROR("Failed reserving FIFO space for OTable "
+ "takedown.\n");
+ } else {
+ memset(cmd, 0, sizeof(*cmd));
+ cmd->header.id = SVGA_3D_CMD_SET_OTABLE_BASE;
+ cmd->header.size = sizeof(cmd->body);
+ cmd->body.type = type;
+ cmd->body.baseAddress = 0;
+ cmd->body.sizeInBytes = 0;
+ cmd->body.validSizeInBytes = 0;
+ cmd->body.ptDepth = SVGA3D_MOBFMT_INVALID;
+ vmw_fifo_commit(dev_priv, sizeof(*cmd));
+ }
if (bo) {
int ret;
@@ -562,11 +564,12 @@
if (unlikely(cmd == NULL)) {
DRM_ERROR("Failed reserving FIFO space for Memory "
"Object unbinding.\n");
+ } else {
+ cmd->header.id = SVGA_3D_CMD_DESTROY_GB_MOB;
+ cmd->header.size = sizeof(cmd->body);
+ cmd->body.mobid = mob->id;
+ vmw_fifo_commit(dev_priv, sizeof(*cmd));
}
- cmd->header.id = SVGA_3D_CMD_DESTROY_GB_MOB;
- cmd->header.size = sizeof(cmd->body);
- cmd->body.mobid = mob->id;
- vmw_fifo_commit(dev_priv, sizeof(*cmd));
if (bo) {
vmw_fence_single_bo(bo, NULL);
ttm_bo_unreserve(bo);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 2aa4bc6..9757b57 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -427,8 +427,7 @@
INIT_LIST_HEAD(&vmw_bo->res_list);
ret = ttm_bo_init(bdev, &vmw_bo->base, size,
- (user) ? ttm_bo_type_device :
- ttm_bo_type_kernel, placement,
+ ttm_bo_type_device, placement,
0, interruptible,
NULL, acc_size, NULL, bo_free);
return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
index 217d941..ee38565 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -371,13 +371,13 @@
TTM_REF_USAGE);
}
-int vmw_shader_alloc(struct vmw_private *dev_priv,
- struct vmw_dma_buffer *buffer,
- size_t shader_size,
- size_t offset,
- SVGA3dShaderType shader_type,
- struct ttm_object_file *tfile,
- u32 *handle)
+static int vmw_shader_alloc(struct vmw_private *dev_priv,
+ struct vmw_dma_buffer *buffer,
+ size_t shader_size,
+ size_t offset,
+ SVGA3dShaderType shader_type,
+ struct ttm_object_file *tfile,
+ u32 *handle)
{
struct vmw_user_shader *ushader;
struct vmw_resource *res, *tmp;
@@ -779,6 +779,8 @@
int ret;
man = kzalloc(sizeof(*man), GFP_KERNEL);
+ if (man == NULL)
+ return ERR_PTR(-ENOMEM);
man->dev_priv = dev_priv;
INIT_LIST_HEAD(&man->list);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 82468d9..e7af580 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -830,6 +830,24 @@
if (unlikely(ret != 0))
goto out_unlock;
+ /*
+ * A gb-aware client referencing a shared surface will
+ * expect a backup buffer to be present.
+ */
+ if (dev_priv->has_mob && req->shareable) {
+ uint32_t backup_handle;
+
+ ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
+ res->backup_size,
+ true,
+ &backup_handle,
+ &res->backup);
+ if (unlikely(ret != 0)) {
+ vmw_resource_unreference(&res);
+ goto out_unlock;
+ }
+ }
+
tmp = vmw_resource_reference(&srf->res);
ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime,
req->shareable, VMW_RES_SURFACE,
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index 1146e3b..112f27e 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -538,7 +538,7 @@
g->base = job->gather_addr_phys[i];
- for (j = 0; j < job->num_gathers; j++)
+ for (j = i + 1; j < job->num_gathers; j++)
if (job->gathers[j].bo == g->bo)
job->gathers[j].handled = true;
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 4975581..f822fd2 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -469,6 +469,9 @@
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI),
.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
+ USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS),
+ .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_JIS),
.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING_ANSI),
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 3bfac3a..cc32a6f 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1679,6 +1679,7 @@
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO) },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
{ HID_USB_DEVICE(USB_VENDOR_ID_AUREAL, USB_DEVICE_ID_AUREAL_W01RN) },
@@ -1779,6 +1780,8 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_USB) },
{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K) },
{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_WIRELESS_OPTICAL_DESKTOP_3_0) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2) },
{ HID_USB_DEVICE(USB_VENDOR_ID_MONTEREY, USB_DEVICE_ID_GENIUS_KB29E) },
{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN) },
{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_1) },
diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c
index 8fae6d1..c24908f 100644
--- a/drivers/hid/hid-hyperv.c
+++ b/drivers/hid/hid-hyperv.c
@@ -157,6 +157,7 @@
u32 report_desc_size;
struct hv_input_dev_info hid_dev_info;
struct hid_device *hid_device;
+ u8 input_buf[HID_MAX_BUFFER_SIZE];
};
@@ -256,6 +257,7 @@
struct synthhid_msg *hid_msg;
struct mousevsc_dev *input_dev = hv_get_drvdata(device);
struct synthhid_input_report *input_report;
+ size_t len;
pipe_msg = (struct pipe_prt_msg *)((unsigned long)packet +
(packet->offset8 << 3));
@@ -300,9 +302,12 @@
(struct synthhid_input_report *)pipe_msg->data;
if (!input_dev->init_complete)
break;
- hid_input_report(input_dev->hid_device,
- HID_INPUT_REPORT, input_report->buffer,
- input_report->header.size, 1);
+
+ len = min(input_report->header.size,
+ (u32)sizeof(input_dev->input_buf));
+ memcpy(input_dev->input_buf, input_report->buffer, len);
+ hid_input_report(input_dev->hid_device, HID_INPUT_REPORT,
+ input_dev->input_buf, len, 1);
break;
default:
pr_err("unsupported hid msg type - type %d len %d",
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 5a5248f..22f28d6 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -135,6 +135,7 @@
#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS 0x023b
#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI 0x0255
#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO 0x0256
+#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS 0x0257
#define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI 0x0290
#define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO 0x0291
#define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS 0x0292
@@ -240,6 +241,7 @@
#define USB_VENDOR_ID_CYGNAL 0x10c4
#define USB_DEVICE_ID_CYGNAL_RADIO_SI470X 0x818a
+#define USB_DEVICE_ID_FOCALTECH_FTXXXX_MULTITOUCH 0x81b9
#define USB_DEVICE_ID_CYGNAL_RADIO_SI4713 0x8244
@@ -451,6 +453,9 @@
#define USB_VENDOR_ID_INTEL_1 0x8087
#define USB_DEVICE_ID_INTEL_HID_SENSOR 0x09fa
+#define USB_VENDOR_ID_STM_0 0x0483
+#define USB_DEVICE_ID_STM_HID_SENSOR 0x91d1
+
#define USB_VENDOR_ID_ION 0x15e4
#define USB_DEVICE_ID_ICADE 0x0132
@@ -619,6 +624,8 @@
#define USB_DEVICE_ID_MS_PRESENTER_8K_USB 0x0713
#define USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K 0x0730
#define USB_DEVICE_ID_MS_COMFORT_MOUSE_4500 0x076c
+#define USB_DEVICE_ID_MS_TOUCH_COVER_2 0x07a7
+#define USB_DEVICE_ID_MS_TYPE_COVER_2 0x07a9
#define USB_VENDOR_ID_MOJO 0x8282
#define USB_DEVICE_ID_RETRO_ADAPTER 0x3201
@@ -644,6 +651,7 @@
#define USB_VENDOR_ID_NEXIO 0x1870
#define USB_DEVICE_ID_NEXIO_MULTITOUCH_420 0x010d
+#define USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750 0x0110
#define USB_VENDOR_ID_NEXTWINDOW 0x1926
#define USB_DEVICE_ID_NEXTWINDOW_TOUCHSCREEN 0x0003
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index d50e731..a713e62 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -1178,7 +1178,7 @@
/* fall back to generic raw-output-report */
len = ((report->size - 1) >> 3) + 1 + (report->id > 0);
- buf = kmalloc(len, GFP_KERNEL);
+ buf = hid_alloc_report_buf(report, GFP_KERNEL);
if (!buf)
return;
diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c
index befe0e3..24883b4 100644
--- a/drivers/hid/hid-lg4ff.c
+++ b/drivers/hid/hid-lg4ff.c
@@ -43,6 +43,7 @@
#define G25_REV_MIN 0x22
#define G27_REV_MAJ 0x12
#define G27_REV_MIN 0x38
+#define G27_2_REV_MIN 0x39
#define to_hid_device(pdev) container_of(pdev, struct hid_device, dev)
@@ -130,6 +131,7 @@
{DFP_REV_MAJ, DFP_REV_MIN, &native_dfp}, /* Driving Force Pro */
{G25_REV_MAJ, G25_REV_MIN, &native_g25}, /* G25 */
{G27_REV_MAJ, G27_REV_MIN, &native_g27}, /* G27 */
+ {G27_REV_MAJ, G27_2_REV_MIN, &native_g27}, /* G27 v2 */
};
/* Recalculates X axis value accordingly to currently selected range */
diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c
index c6ef6ee..404a3a8 100644
--- a/drivers/hid/hid-microsoft.c
+++ b/drivers/hid/hid-microsoft.c
@@ -208,6 +208,10 @@
.driver_data = MS_NOGET },
{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_COMFORT_MOUSE_4500),
.driver_data = MS_DUPLICATE_USAGES },
+ { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2),
+ .driver_data = 0 },
+ { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2),
+ .driver_data = 0 },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_BT),
.driver_data = MS_PRESENTER },
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index f134d73..221d503 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -1166,6 +1166,11 @@
MT_USB_DEVICE(USB_VENDOR_ID_FLATFROG,
USB_DEVICE_ID_MULTITOUCH_3200) },
+ /* FocalTech Panels */
+ { .driver_data = MT_CLS_SERIAL,
+ MT_USB_DEVICE(USB_VENDOR_ID_CYGNAL,
+ USB_DEVICE_ID_FOCALTECH_FTXXXX_MULTITOUCH) },
+
/* GeneralTouch panel */
{ .driver_data = MT_CLS_GENERALTOUCH_TWOFINGERS,
MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index 46f4480..9c22e14 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -665,6 +665,9 @@
{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, USB_VENDOR_ID_INTEL_1,
USB_DEVICE_ID_INTEL_HID_SENSOR),
.driver_data = HID_SENSOR_HUB_ENUM_QUIRK},
+ { HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, USB_VENDOR_ID_STM_0,
+ USB_DEVICE_ID_STM_HID_SENSOR),
+ .driver_data = HID_SENSOR_HUB_ENUM_QUIRK},
{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, HID_ANY_ID,
HID_ANY_ID) },
{ }
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 1235405..2f19b15 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -42,6 +42,7 @@
#define DUALSHOCK4_CONTROLLER_BT BIT(6)
#define SONY_LED_SUPPORT (SIXAXIS_CONTROLLER_USB | BUZZ_CONTROLLER | DUALSHOCK4_CONTROLLER_USB)
+#define SONY_FF_SUPPORT (SIXAXIS_CONTROLLER_USB | DUALSHOCK4_CONTROLLER_USB)
#define MAX_LEDS 4
@@ -499,6 +500,7 @@
__u8 right;
#endif
+ __u8 worker_initialized;
__u8 led_state[MAX_LEDS];
__u8 led_count;
};
@@ -993,22 +995,11 @@
return input_ff_create_memless(input_dev, NULL, sony_play_effect);
}
-static void sony_destroy_ff(struct hid_device *hdev)
-{
- struct sony_sc *sc = hid_get_drvdata(hdev);
-
- cancel_work_sync(&sc->state_worker);
-}
-
#else
static int sony_init_ff(struct hid_device *hdev)
{
return 0;
}
-
-static void sony_destroy_ff(struct hid_device *hdev)
-{
-}
#endif
static int sony_set_output_report(struct sony_sc *sc, int req_id, int req_size)
@@ -1077,6 +1068,8 @@
if (sc->quirks & SIXAXIS_CONTROLLER_USB) {
hdev->hid_output_raw_report = sixaxis_usb_output_raw_report;
ret = sixaxis_set_operational_usb(hdev);
+
+ sc->worker_initialized = 1;
INIT_WORK(&sc->state_worker, sixaxis_state_worker);
}
else if (sc->quirks & SIXAXIS_CONTROLLER_BT)
@@ -1087,6 +1080,7 @@
if (ret < 0)
goto err_stop;
+ sc->worker_initialized = 1;
INIT_WORK(&sc->state_worker, dualshock4_state_worker);
} else {
ret = 0;
@@ -1101,9 +1095,11 @@
goto err_stop;
}
- ret = sony_init_ff(hdev);
- if (ret < 0)
- goto err_stop;
+ if (sc->quirks & SONY_FF_SUPPORT) {
+ ret = sony_init_ff(hdev);
+ if (ret < 0)
+ goto err_stop;
+ }
return 0;
err_stop:
@@ -1120,7 +1116,8 @@
if (sc->quirks & SONY_LED_SUPPORT)
sony_leds_remove(hdev);
- sony_destroy_ff(hdev);
+ if (sc->worker_initialized)
+ cancel_work_sync(&sc->state_worker);
hid_hw_stop(hdev);
}
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index cb0137b..ab24ce2 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -320,13 +320,13 @@
hid_hw_close(hidraw->hid);
wake_up_interruptible(&hidraw->wait);
}
+ device_destroy(hidraw_class,
+ MKDEV(hidraw_major, hidraw->minor));
} else {
--hidraw->open;
}
if (!hidraw->open) {
if (!hidraw->exist) {
- device_destroy(hidraw_class,
- MKDEV(hidraw_major, hidraw->minor));
hidraw_table[hidraw->minor] = NULL;
kfree(hidraw);
} else {
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index d1f81f5..42eebd1 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -582,7 +582,7 @@
int ret;
int len = i2c_hid_get_report_length(rep) - 2;
- buf = kzalloc(len, GFP_KERNEL);
+ buf = hid_alloc_report_buf(rep, GFP_KERNEL);
if (!buf)
return;
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 175ec0a..dbd8387 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -74,6 +74,7 @@
{ USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GX680R_LED_PANEL, HID_QUIRK_NO_INIT_REPORTS },
+ { USB_VENDOR_ID_NEXIO, USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750, HID_QUIRK_NO_INIT_REPORTS },
{ USB_VENDOR_ID_NOVATEK, USB_DEVICE_ID_NOVATEK_MOUSE, HID_QUIRK_NO_INIT_REPORTS },
{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN, HID_QUIRK_NO_INIT_REPORTS },
{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN1, HID_QUIRK_NO_INIT_REPORTS },
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index af6edf9..f2d7bf9 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -67,7 +67,6 @@
int ret = 0;
struct vmbus_channel_initiate_contact *msg;
unsigned long flags;
- int t;
init_completion(&msginfo->waitevent);
@@ -78,6 +77,8 @@
msg->interrupt_page = virt_to_phys(vmbus_connection.int_page);
msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
+ if (version == VERSION_WIN8)
+ msg->target_vcpu = hv_context.vp_index[smp_processor_id()];
/*
* Add to list before we send the request since we may
@@ -100,15 +101,7 @@
}
/* Wait for the connection response */
- t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ);
- if (t == 0) {
- spin_lock_irqsave(&vmbus_connection.channelmsg_lock,
- flags);
- list_del(&msginfo->msglistentry);
- spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock,
- flags);
- return -ETIMEDOUT;
- }
+ wait_for_completion(&msginfo->waitevent);
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_del(&msginfo->msglistentry);
diff --git a/drivers/hwmon/max1668.c b/drivers/hwmon/max1668.c
index a762635..029b65e 100644
--- a/drivers/hwmon/max1668.c
+++ b/drivers/hwmon/max1668.c
@@ -243,7 +243,7 @@
data->temp_min[index] = clamp_val(temp/1000, -128, 127);
if (i2c_smbus_write_byte_data(client,
MAX1668_REG_LIML_WR(index),
- data->temp_max[index]))
+ data->temp_min[index]))
count = -EIO;
mutex_unlock(&data->update_lock);
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index 8c232039..8a17f01 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -145,7 +145,7 @@
static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata)
{
struct iio_channel *channel = pdata->chan;
- unsigned int result;
+ s64 result;
int val, ret;
ret = iio_read_channel_raw(channel, &val);
@@ -155,10 +155,10 @@
}
/* unit: mV */
- result = pdata->pullup_uv * val;
+ result = pdata->pullup_uv * (s64) val;
result >>= 12;
- return result;
+ return (int)result;
}
static const struct of_device_id ntc_match[] = {
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index f5ed031..de17c55 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -387,7 +387,7 @@
config I2C_CPM
tristate "Freescale CPM1 or CPM2 (MPC8xx/826x)"
- depends on (CPM1 || CPM2) && OF_I2C
+ depends on CPM1 || CPM2
help
This supports the use of the I2C interface on Freescale
processors with CPM1 or CPM2.
diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c
index be7f0a2..f3b89a4 100644
--- a/drivers/i2c/busses/i2c-cpm.c
+++ b/drivers/i2c/busses/i2c-cpm.c
@@ -39,7 +39,9 @@
#include <linux/i2c.h>
#include <linux/io.h>
#include <linux/dma-mapping.h>
+#include <linux/of_address.h>
#include <linux/of_device.h>
+#include <linux/of_irq.h>
#include <linux/of_platform.h>
#include <sysdev/fsl_soc.h>
#include <asm/cpm.h>
diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c
index b8c5187..d52d849 100644
--- a/drivers/i2c/busses/i2c-mv64xxx.c
+++ b/drivers/i2c/busses/i2c-mv64xxx.c
@@ -97,7 +97,6 @@
enum {
MV64XXX_I2C_ACTION_INVALID,
MV64XXX_I2C_ACTION_CONTINUE,
- MV64XXX_I2C_ACTION_OFFLOAD_SEND_START,
MV64XXX_I2C_ACTION_SEND_START,
MV64XXX_I2C_ACTION_SEND_RESTART,
MV64XXX_I2C_ACTION_OFFLOAD_RESTART,
@@ -204,6 +203,9 @@
unsigned long ctrl_reg;
struct i2c_msg *msg = drv_data->msgs;
+ if (!drv_data->offload_enabled)
+ return -EOPNOTSUPP;
+
drv_data->msg = msg;
drv_data->byte_posn = 0;
drv_data->bytes_left = msg->len;
@@ -433,8 +435,7 @@
drv_data->msgs++;
drv_data->num_msgs--;
- if (!(drv_data->offload_enabled &&
- mv64xxx_i2c_offload_msg(drv_data))) {
+ if (mv64xxx_i2c_offload_msg(drv_data) < 0) {
drv_data->cntl_bits |= MV64XXX_I2C_REG_CONTROL_START;
writel(drv_data->cntl_bits,
drv_data->reg_base + drv_data->reg_offsets.control);
@@ -458,15 +459,14 @@
drv_data->reg_base + drv_data->reg_offsets.control);
break;
- case MV64XXX_I2C_ACTION_OFFLOAD_SEND_START:
- if (!mv64xxx_i2c_offload_msg(drv_data))
- break;
- else
- drv_data->action = MV64XXX_I2C_ACTION_SEND_START;
- /* FALLTHRU */
case MV64XXX_I2C_ACTION_SEND_START:
- writel(drv_data->cntl_bits | MV64XXX_I2C_REG_CONTROL_START,
- drv_data->reg_base + drv_data->reg_offsets.control);
+ /* Can we offload this msg ? */
+ if (mv64xxx_i2c_offload_msg(drv_data) < 0) {
+ /* No, switch to standard path */
+ mv64xxx_i2c_prepare_for_io(drv_data, drv_data->msgs);
+ writel(drv_data->cntl_bits | MV64XXX_I2C_REG_CONTROL_START,
+ drv_data->reg_base + drv_data->reg_offsets.control);
+ }
break;
case MV64XXX_I2C_ACTION_SEND_ADDR_1:
@@ -625,15 +625,10 @@
unsigned long flags;
spin_lock_irqsave(&drv_data->lock, flags);
- if (drv_data->offload_enabled) {
- drv_data->action = MV64XXX_I2C_ACTION_OFFLOAD_SEND_START;
- drv_data->state = MV64XXX_I2C_STATE_WAITING_FOR_START_COND;
- } else {
- mv64xxx_i2c_prepare_for_io(drv_data, msg);
- drv_data->action = MV64XXX_I2C_ACTION_SEND_START;
- drv_data->state = MV64XXX_I2C_STATE_WAITING_FOR_START_COND;
- }
+ drv_data->action = MV64XXX_I2C_ACTION_SEND_START;
+ drv_data->state = MV64XXX_I2C_STATE_WAITING_FOR_START_COND;
+
drv_data->send_stop = is_last;
drv_data->block = 1;
mv64xxx_i2c_do_action(drv_data);
diff --git a/drivers/iio/accel/bma180.c b/drivers/iio/accel/bma180.c
index 3bec922..bfec313 100644
--- a/drivers/iio/accel/bma180.c
+++ b/drivers/iio/accel/bma180.c
@@ -447,14 +447,14 @@
{ },
};
-#define BMA180_CHANNEL(_index) { \
+#define BMA180_CHANNEL(_axis) { \
.type = IIO_ACCEL, \
- .indexed = 1, \
- .channel = (_index), \
+ .modified = 1, \
+ .channel2 = IIO_MOD_##_axis, \
.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \
BIT(IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY), \
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \
- .scan_index = (_index), \
+ .scan_index = AXIS_##_axis, \
.scan_type = { \
.sign = 's', \
.realbits = 14, \
@@ -465,10 +465,10 @@
}
static const struct iio_chan_spec bma180_channels[] = {
- BMA180_CHANNEL(AXIS_X),
- BMA180_CHANNEL(AXIS_Y),
- BMA180_CHANNEL(AXIS_Z),
- IIO_CHAN_SOFT_TIMESTAMP(4),
+ BMA180_CHANNEL(X),
+ BMA180_CHANNEL(Y),
+ BMA180_CHANNEL(Z),
+ IIO_CHAN_SOFT_TIMESTAMP(3),
};
static irqreturn_t bma180_trigger_handler(int irq, void *p)
diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c
index e283f2f..3602592 100644
--- a/drivers/iio/adc/max1363.c
+++ b/drivers/iio/adc/max1363.c
@@ -1560,7 +1560,7 @@
st->client = client;
st->vref_uv = st->chip_info->int_vref_mv * 1000;
- vref = devm_regulator_get(&client->dev, "vref");
+ vref = devm_regulator_get_optional(&client->dev, "vref");
if (!IS_ERR(vref)) {
int vref_uv;
diff --git a/drivers/iio/gyro/Kconfig b/drivers/iio/gyro/Kconfig
index 41c64a4..ac2d69e 100644
--- a/drivers/iio/gyro/Kconfig
+++ b/drivers/iio/gyro/Kconfig
@@ -70,7 +70,7 @@
select IIO_TRIGGERED_BUFFER if (IIO_BUFFER)
help
Say yes here to build support for STMicroelectronics gyroscopes:
- L3G4200D, LSM330DL, L3GD20, L3GD20H, LSM330DLC, L3G4IS, LSM330.
+ L3G4200D, LSM330DL, L3GD20, LSM330DLC, L3G4IS, LSM330.
This driver can also be built as a module. If so, these modules
will be created:
diff --git a/drivers/iio/gyro/st_gyro.h b/drivers/iio/gyro/st_gyro.h
index f8f2bf8..c197360 100644
--- a/drivers/iio/gyro/st_gyro.h
+++ b/drivers/iio/gyro/st_gyro.h
@@ -19,7 +19,6 @@
#define LSM330DL_GYRO_DEV_NAME "lsm330dl_gyro"
#define LSM330DLC_GYRO_DEV_NAME "lsm330dlc_gyro"
#define L3GD20_GYRO_DEV_NAME "l3gd20"
-#define L3GD20H_GYRO_DEV_NAME "l3gd20h"
#define L3G4IS_GYRO_DEV_NAME "l3g4is_ui"
#define LSM330_GYRO_DEV_NAME "lsm330_gyro"
diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c
index d53d91a..a8e174a 100644
--- a/drivers/iio/gyro/st_gyro_core.c
+++ b/drivers/iio/gyro/st_gyro_core.c
@@ -167,11 +167,10 @@
.wai = ST_GYRO_2_WAI_EXP,
.sensors_supported = {
[0] = L3GD20_GYRO_DEV_NAME,
- [1] = L3GD20H_GYRO_DEV_NAME,
- [2] = LSM330D_GYRO_DEV_NAME,
- [3] = LSM330DLC_GYRO_DEV_NAME,
- [4] = L3G4IS_GYRO_DEV_NAME,
- [5] = LSM330_GYRO_DEV_NAME,
+ [1] = LSM330D_GYRO_DEV_NAME,
+ [2] = LSM330DLC_GYRO_DEV_NAME,
+ [3] = L3G4IS_GYRO_DEV_NAME,
+ [4] = LSM330_GYRO_DEV_NAME,
},
.ch = (struct iio_chan_spec *)st_gyro_16bit_channels,
.odr = {
diff --git a/drivers/iio/gyro/st_gyro_i2c.c b/drivers/iio/gyro/st_gyro_i2c.c
index 16b8b8d..23c12f3 100644
--- a/drivers/iio/gyro/st_gyro_i2c.c
+++ b/drivers/iio/gyro/st_gyro_i2c.c
@@ -55,7 +55,6 @@
{ LSM330DL_GYRO_DEV_NAME },
{ LSM330DLC_GYRO_DEV_NAME },
{ L3GD20_GYRO_DEV_NAME },
- { L3GD20H_GYRO_DEV_NAME },
{ L3G4IS_GYRO_DEV_NAME },
{ LSM330_GYRO_DEV_NAME },
{},
diff --git a/drivers/iio/gyro/st_gyro_spi.c b/drivers/iio/gyro/st_gyro_spi.c
index 94763e2..b4ad3be 100644
--- a/drivers/iio/gyro/st_gyro_spi.c
+++ b/drivers/iio/gyro/st_gyro_spi.c
@@ -54,7 +54,6 @@
{ LSM330DL_GYRO_DEV_NAME },
{ LSM330DLC_GYRO_DEV_NAME },
{ L3GD20_GYRO_DEV_NAME },
- { L3GD20H_GYRO_DEV_NAME },
{ L3G4IS_GYRO_DEV_NAME },
{ LSM330_GYRO_DEV_NAME },
{},
diff --git a/drivers/iio/imu/adis16400.h b/drivers/iio/imu/adis16400.h
index 2f8f9d6..0916bf6 100644
--- a/drivers/iio/imu/adis16400.h
+++ b/drivers/iio/imu/adis16400.h
@@ -189,6 +189,7 @@
ADIS16300_SCAN_INCLI_X,
ADIS16300_SCAN_INCLI_Y,
ADIS16400_SCAN_ADC,
+ ADIS16400_SCAN_TIMESTAMP,
};
#ifdef CONFIG_IIO_BUFFER
diff --git a/drivers/iio/imu/adis16400_core.c b/drivers/iio/imu/adis16400_core.c
index 368660d..7c582f7 100644
--- a/drivers/iio/imu/adis16400_core.c
+++ b/drivers/iio/imu/adis16400_core.c
@@ -632,7 +632,7 @@
ADIS16400_MAGN_CHAN(Z, ADIS16400_ZMAGN_OUT, 14),
ADIS16400_TEMP_CHAN(ADIS16400_TEMP_OUT, 12),
ADIS16400_AUX_ADC_CHAN(ADIS16400_AUX_ADC, 12),
- IIO_CHAN_SOFT_TIMESTAMP(12)
+ IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
};
static const struct iio_chan_spec adis16448_channels[] = {
@@ -659,7 +659,7 @@
},
},
ADIS16400_TEMP_CHAN(ADIS16448_TEMP_OUT, 12),
- IIO_CHAN_SOFT_TIMESTAMP(11)
+ IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
};
static const struct iio_chan_spec adis16350_channels[] = {
@@ -677,7 +677,7 @@
ADIS16400_MOD_TEMP_CHAN(X, ADIS16350_XTEMP_OUT, 12),
ADIS16400_MOD_TEMP_CHAN(Y, ADIS16350_YTEMP_OUT, 12),
ADIS16400_MOD_TEMP_CHAN(Z, ADIS16350_ZTEMP_OUT, 12),
- IIO_CHAN_SOFT_TIMESTAMP(11)
+ IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
};
static const struct iio_chan_spec adis16300_channels[] = {
@@ -690,7 +690,7 @@
ADIS16400_AUX_ADC_CHAN(ADIS16300_AUX_ADC, 12),
ADIS16400_INCLI_CHAN(X, ADIS16300_PITCH_OUT, 13),
ADIS16400_INCLI_CHAN(Y, ADIS16300_ROLL_OUT, 13),
- IIO_CHAN_SOFT_TIMESTAMP(14)
+ IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
};
static const struct iio_chan_spec adis16334_channels[] = {
@@ -701,7 +701,7 @@
ADIS16400_ACCEL_CHAN(Y, ADIS16400_YACCL_OUT, 14),
ADIS16400_ACCEL_CHAN(Z, ADIS16400_ZACCL_OUT, 14),
ADIS16400_TEMP_CHAN(ADIS16350_XTEMP_OUT, 12),
- IIO_CHAN_SOFT_TIMESTAMP(8)
+ IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
};
static struct attribute *adis16400_attributes[] = {
diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c
index f17b4e6..47a6dba 100644
--- a/drivers/iio/light/cm32181.c
+++ b/drivers/iio/light/cm32181.c
@@ -103,13 +103,13 @@
/**
* cm32181_read_als_it() - Get sensor integration time (ms)
* @cm32181: pointer of struct cm32181
- * @val: pointer of int to load the als_it value.
+ * @val2: pointer of int to load the als_it value.
*
* Report the current integartion time by millisecond.
*
- * Return: IIO_VAL_INT for success, otherwise -EINVAL.
+ * Return: IIO_VAL_INT_PLUS_MICRO for success, otherwise -EINVAL.
*/
-static int cm32181_read_als_it(struct cm32181_chip *cm32181, int *val)
+static int cm32181_read_als_it(struct cm32181_chip *cm32181, int *val2)
{
u16 als_it;
int i;
@@ -119,8 +119,8 @@
als_it >>= CM32181_CMD_ALS_IT_SHIFT;
for (i = 0; i < ARRAY_SIZE(als_it_bits); i++) {
if (als_it == als_it_bits[i]) {
- *val = als_it_value[i];
- return IIO_VAL_INT;
+ *val2 = als_it_value[i];
+ return IIO_VAL_INT_PLUS_MICRO;
}
}
@@ -221,7 +221,7 @@
*val = cm32181->calibscale;
return IIO_VAL_INT;
case IIO_CHAN_INFO_INT_TIME:
- ret = cm32181_read_als_it(cm32181, val);
+ ret = cm32181_read_als_it(cm32181, val2);
return ret;
}
@@ -240,7 +240,7 @@
cm32181->calibscale = val;
return val;
case IIO_CHAN_INFO_INT_TIME:
- ret = cm32181_write_als_it(cm32181, val);
+ ret = cm32181_write_als_it(cm32181, val2);
return ret;
}
@@ -264,7 +264,7 @@
n = ARRAY_SIZE(als_it_value);
for (i = 0, len = 0; i < n; i++)
- len += sprintf(buf + len, "%d ", als_it_value[i]);
+ len += sprintf(buf + len, "0.%06u ", als_it_value[i]);
return len + sprintf(buf + len, "\n");
}
diff --git a/drivers/iio/light/cm36651.c b/drivers/iio/light/cm36651.c
index 0a142af..a45e074 100644
--- a/drivers/iio/light/cm36651.c
+++ b/drivers/iio/light/cm36651.c
@@ -50,10 +50,10 @@
#define CM36651_CS_CONF2_DEFAULT_BIT 0x08
/* CS_CONF3 channel integration time */
-#define CM36651_CS_IT1 0x00 /* Integration time 80000 usec */
-#define CM36651_CS_IT2 0x40 /* Integration time 160000 usec */
-#define CM36651_CS_IT3 0x80 /* Integration time 320000 usec */
-#define CM36651_CS_IT4 0xC0 /* Integration time 640000 usec */
+#define CM36651_CS_IT1 0x00 /* Integration time 80 msec */
+#define CM36651_CS_IT2 0x40 /* Integration time 160 msec */
+#define CM36651_CS_IT3 0x80 /* Integration time 320 msec */
+#define CM36651_CS_IT4 0xC0 /* Integration time 640 msec */
/* PS_CONF1 command code */
#define CM36651_PS_ENABLE 0x00
@@ -64,10 +64,10 @@
#define CM36651_PS_PERS4 0x0C
/* PS_CONF1 command code: integration time */
-#define CM36651_PS_IT1 0x00 /* Integration time 320 usec */
-#define CM36651_PS_IT2 0x10 /* Integration time 420 usec */
-#define CM36651_PS_IT3 0x20 /* Integration time 520 usec */
-#define CM36651_PS_IT4 0x30 /* Integration time 640 usec */
+#define CM36651_PS_IT1 0x00 /* Integration time 0.32 msec */
+#define CM36651_PS_IT2 0x10 /* Integration time 0.42 msec */
+#define CM36651_PS_IT3 0x20 /* Integration time 0.52 msec */
+#define CM36651_PS_IT4 0x30 /* Integration time 0.64 msec */
/* PS_CONF1 command code: duty ratio */
#define CM36651_PS_DR1 0x00 /* Duty ratio 1/80 */
@@ -93,8 +93,8 @@
#define CM36651_CLOSE_PROXIMITY 0x32
#define CM36651_FAR_PROXIMITY 0x33
-#define CM36651_CS_INT_TIME_AVAIL "80000 160000 320000 640000"
-#define CM36651_PS_INT_TIME_AVAIL "320 420 520 640"
+#define CM36651_CS_INT_TIME_AVAIL "0.08 0.16 0.32 0.64"
+#define CM36651_PS_INT_TIME_AVAIL "0.000320 0.000420 0.000520 0.000640"
enum cm36651_operation_mode {
CM36651_LIGHT_EN,
@@ -356,30 +356,30 @@
}
static int cm36651_read_int_time(struct cm36651_data *cm36651,
- struct iio_chan_spec const *chan, int *val)
+ struct iio_chan_spec const *chan, int *val2)
{
switch (chan->type) {
case IIO_LIGHT:
if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT1)
- *val = 80000;
+ *val2 = 80000;
else if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT2)
- *val = 160000;
+ *val2 = 160000;
else if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT3)
- *val = 320000;
+ *val2 = 320000;
else if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT4)
- *val = 640000;
+ *val2 = 640000;
else
return -EINVAL;
break;
case IIO_PROXIMITY:
if (cm36651->ps_int_time == CM36651_PS_IT1)
- *val = 320;
+ *val2 = 320;
else if (cm36651->ps_int_time == CM36651_PS_IT2)
- *val = 420;
+ *val2 = 420;
else if (cm36651->ps_int_time == CM36651_PS_IT3)
- *val = 520;
+ *val2 = 520;
else if (cm36651->ps_int_time == CM36651_PS_IT4)
- *val = 640;
+ *val2 = 640;
else
return -EINVAL;
break;
@@ -387,7 +387,7 @@
return -EINVAL;
}
- return IIO_VAL_INT;
+ return IIO_VAL_INT_PLUS_MICRO;
}
static int cm36651_write_int_time(struct cm36651_data *cm36651,
@@ -459,7 +459,8 @@
ret = cm36651_read_channel(cm36651, chan, val);
break;
case IIO_CHAN_INFO_INT_TIME:
- ret = cm36651_read_int_time(cm36651, chan, val);
+ *val = 0;
+ ret = cm36651_read_int_time(cm36651, chan, val2);
break;
default:
ret = -EINVAL;
@@ -479,7 +480,7 @@
int ret = -EINVAL;
if (mask == IIO_CHAN_INFO_INT_TIME) {
- ret = cm36651_write_int_time(cm36651, chan, val);
+ ret = cm36651_write_int_time(cm36651, chan, val2);
if (ret < 0)
dev_err(&client->dev, "Integration time write failed\n");
}
diff --git a/drivers/iio/light/tsl2563.c b/drivers/iio/light/tsl2563.c
index 3d81101..94daa9f 100644
--- a/drivers/iio/light/tsl2563.c
+++ b/drivers/iio/light/tsl2563.c
@@ -460,10 +460,14 @@
{
struct tsl2563_chip *chip = iio_priv(indio_dev);
- if (chan->channel == IIO_MOD_LIGHT_BOTH)
+ if (mask != IIO_CHAN_INFO_CALIBSCALE)
+ return -EINVAL;
+ if (chan->channel2 == IIO_MOD_LIGHT_BOTH)
chip->calib0 = calib_from_sysfs(val);
- else
+ else if (chan->channel2 == IIO_MOD_LIGHT_IR)
chip->calib1 = calib_from_sysfs(val);
+ else
+ return -EINVAL;
return 0;
}
@@ -472,14 +476,14 @@
struct iio_chan_spec const *chan,
int *val,
int *val2,
- long m)
+ long mask)
{
int ret = -EINVAL;
u32 calib0, calib1;
struct tsl2563_chip *chip = iio_priv(indio_dev);
mutex_lock(&chip->lock);
- switch (m) {
+ switch (mask) {
case IIO_CHAN_INFO_RAW:
case IIO_CHAN_INFO_PROCESSED:
switch (chan->type) {
@@ -498,7 +502,7 @@
ret = tsl2563_get_adc(chip);
if (ret)
goto error_ret;
- if (chan->channel == 0)
+ if (chan->channel2 == IIO_MOD_LIGHT_BOTH)
*val = chip->data0;
else
*val = chip->data1;
@@ -510,7 +514,7 @@
break;
case IIO_CHAN_INFO_CALIBSCALE:
- if (chan->channel == 0)
+ if (chan->channel2 == IIO_MOD_LIGHT_BOTH)
*val = calib_to_sysfs(chip->calib0);
else
*val = calib_to_sysfs(chip->calib1);
diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index ff284e5..0542354 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -85,6 +85,7 @@
#define AK8975_MAX_CONVERSION_TIMEOUT 500
#define AK8975_CONVERSION_DONE_POLL_TIME 10
#define AK8975_DATA_READY_TIMEOUT ((100*HZ)/1000)
+#define RAW_TO_GAUSS(asa) ((((asa) + 128) * 3000) / 256)
/*
* Per-instance context data for the device.
@@ -265,15 +266,15 @@
*
* Since 1uT = 0.01 gauss, our final scale factor becomes:
*
- * Hadj = H * ((ASA + 128) / 256) * 3/10 * 100
- * Hadj = H * ((ASA + 128) * 30 / 256
+ * Hadj = H * ((ASA + 128) / 256) * 3/10 * 1/100
+ * Hadj = H * ((ASA + 128) * 0.003) / 256
*
* Since ASA doesn't change, we cache the resultant scale factor into the
* device context in ak8975_setup().
*/
- data->raw_to_gauss[0] = ((data->asa[0] + 128) * 30) >> 8;
- data->raw_to_gauss[1] = ((data->asa[1] + 128) * 30) >> 8;
- data->raw_to_gauss[2] = ((data->asa[2] + 128) * 30) >> 8;
+ data->raw_to_gauss[0] = RAW_TO_GAUSS(data->asa[0]);
+ data->raw_to_gauss[1] = RAW_TO_GAUSS(data->asa[1]);
+ data->raw_to_gauss[2] = RAW_TO_GAUSS(data->asa[2]);
return 0;
}
@@ -428,8 +429,9 @@
case IIO_CHAN_INFO_RAW:
return ak8975_read_axis(indio_dev, chan->address, val);
case IIO_CHAN_INFO_SCALE:
- *val = data->raw_to_gauss[chan->address];
- return IIO_VAL_INT;
+ *val = 0;
+ *val2 = data->raw_to_gauss[chan->address];
+ return IIO_VAL_INT_PLUS_MICRO;
}
return -EINVAL;
}
diff --git a/drivers/iio/magnetometer/mag3110.c b/drivers/iio/magnetometer/mag3110.c
index 4b65b6d..f66955f 100644
--- a/drivers/iio/magnetometer/mag3110.c
+++ b/drivers/iio/magnetometer/mag3110.c
@@ -106,7 +106,7 @@
while (n-- > 0)
len += scnprintf(buf + len, PAGE_SIZE - len,
- "%d.%d ", vals[n][0], vals[n][1]);
+ "%d.%06d ", vals[n][0], vals[n][1]);
/* replace trailing space by newline */
buf[len - 1] = '\n';
@@ -154,6 +154,9 @@
switch (mask) {
case IIO_CHAN_INFO_RAW:
+ if (iio_buffer_enabled(indio_dev))
+ return -EBUSY;
+
switch (chan->type) {
case IIO_MAGN: /* in 0.1 uT / LSB */
ret = mag3110_read(data, buffer);
@@ -199,6 +202,9 @@
struct mag3110_data *data = iio_priv(indio_dev);
int rate;
+ if (iio_buffer_enabled(indio_dev))
+ return -EBUSY;
+
switch (mask) {
case IIO_CHAN_INFO_SAMP_FREQ:
rate = mag3110_get_samp_freq_index(data, val, val2);
diff --git a/drivers/infiniband/hw/amso1100/c2.c b/drivers/infiniband/hw/amso1100/c2.c
index d53cf51..00400c3 100644
--- a/drivers/infiniband/hw/amso1100/c2.c
+++ b/drivers/infiniband/hw/amso1100/c2.c
@@ -1082,6 +1082,7 @@
/* Initialize network device */
if ((netdev = c2_devinit(c2dev, mmio_regs)) == NULL) {
+ ret = -ENOMEM;
iounmap(mmio_regs);
goto bail4;
}
@@ -1151,7 +1152,8 @@
goto bail10;
}
- if (c2_register_device(c2dev))
+ ret = c2_register_device(c2dev);
+ if (ret)
goto bail10;
return 0;
diff --git a/drivers/infiniband/hw/amso1100/c2_rnic.c b/drivers/infiniband/hw/amso1100/c2_rnic.c
index b7c9869..d2a6d96 100644
--- a/drivers/infiniband/hw/amso1100/c2_rnic.c
+++ b/drivers/infiniband/hw/amso1100/c2_rnic.c
@@ -576,7 +576,8 @@
goto bail4;
/* Initialize cached the adapter limits */
- if (c2_rnic_query(c2dev, &c2dev->props))
+ err = c2_rnic_query(c2dev, &c2dev->props);
+ if (err)
goto bail5;
/* Initialize the PD pool */
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 4512687..7e98a58 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1647,6 +1647,15 @@
status != CPL_ERR_ARP_MISS;
}
+/* Returns whether a CPL status conveys negative advice.
+ */
+static int is_neg_adv(unsigned int status)
+{
+ return status == CPL_ERR_RTX_NEG_ADVICE ||
+ status == CPL_ERR_PERSIST_NEG_ADVICE ||
+ status == CPL_ERR_KEEPALV_NEG_ADVICE;
+}
+
#define ACT_OPEN_RETRY_COUNT 2
static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip,
@@ -1835,7 +1844,7 @@
PDBG("%s ep %p atid %u status %u errno %d\n", __func__, ep, atid,
status, status2errno(status));
- if (status == CPL_ERR_RTX_NEG_ADVICE) {
+ if (is_neg_adv(status)) {
printk(KERN_WARNING MOD "Connection problems for atid %u\n",
atid);
return 0;
@@ -2265,15 +2274,6 @@
return 0;
}
-/*
- * Returns whether an ABORT_REQ_RSS message is a negative advice.
- */
-static int is_neg_adv_abort(unsigned int status)
-{
- return status == CPL_ERR_RTX_NEG_ADVICE ||
- status == CPL_ERR_PERSIST_NEG_ADVICE;
-}
-
static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct cpl_abort_req_rss *req = cplhdr(skb);
@@ -2287,7 +2287,7 @@
unsigned int tid = GET_TID(req);
ep = lookup_tid(t, tid);
- if (is_neg_adv_abort(req->status)) {
+ if (is_neg_adv(req->status)) {
PDBG("%s neg_adv_abort ep %p tid %u\n", __func__, ep,
ep->hwtid);
return 0;
@@ -3352,6 +3352,7 @@
goto free_dst;
}
+ neigh_release(neigh);
step = dev->rdev.lldi.nrxq / dev->rdev.lldi.nchan;
rss_qid = dev->rdev.lldi.rxq_ids[pi->port_id * step];
window = (__force u16) htons((__force u16)tcph->window);
@@ -3569,7 +3570,7 @@
kfree_skb(skb);
return 0;
}
- if (is_neg_adv_abort(req->status)) {
+ if (is_neg_adv(req->status)) {
PDBG("%s neg_adv_abort ep %p tid %u\n", __func__, ep,
ep->hwtid);
kfree_skb(skb);
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 4a03385..ba7335f 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -64,6 +64,10 @@
static LIST_HEAD(uld_ctx_list);
static DEFINE_MUTEX(dev_mutex);
+#define DB_FC_RESUME_SIZE 64
+#define DB_FC_RESUME_DELAY 1
+#define DB_FC_DRAIN_THRESH 0
+
static struct dentry *c4iw_debugfs_root;
struct c4iw_debugfs_data {
@@ -282,7 +286,7 @@
.llseek = default_llseek,
};
-static char *db_state_str[] = {"NORMAL", "FLOW_CONTROL", "RECOVERY"};
+static char *db_state_str[] = {"NORMAL", "FLOW_CONTROL", "RECOVERY", "STOPPED"};
static int stats_show(struct seq_file *seq, void *v)
{
@@ -311,9 +315,10 @@
seq_printf(seq, " DB FULL: %10llu\n", dev->rdev.stats.db_full);
seq_printf(seq, " DB EMPTY: %10llu\n", dev->rdev.stats.db_empty);
seq_printf(seq, " DB DROP: %10llu\n", dev->rdev.stats.db_drop);
- seq_printf(seq, " DB State: %s Transitions %llu\n",
+ seq_printf(seq, " DB State: %s Transitions %llu FC Interruptions %llu\n",
db_state_str[dev->db_state],
- dev->rdev.stats.db_state_transitions);
+ dev->rdev.stats.db_state_transitions,
+ dev->rdev.stats.db_fc_interruptions);
seq_printf(seq, "TCAM_FULL: %10llu\n", dev->rdev.stats.tcam_full);
seq_printf(seq, "ACT_OFLD_CONN_FAILS: %10llu\n",
dev->rdev.stats.act_ofld_conn_fails);
@@ -643,6 +648,12 @@
printk(KERN_ERR MOD "error %d initializing ocqp pool\n", err);
goto err4;
}
+ rdev->status_page = (struct t4_dev_status_page *)
+ __get_free_page(GFP_KERNEL);
+ if (!rdev->status_page) {
+ pr_err(MOD "error allocating status page\n");
+ goto err4;
+ }
return 0;
err4:
c4iw_rqtpool_destroy(rdev);
@@ -656,6 +667,7 @@
static void c4iw_rdev_close(struct c4iw_rdev *rdev)
{
+ free_page((unsigned long)rdev->status_page);
c4iw_pblpool_destroy(rdev);
c4iw_rqtpool_destroy(rdev);
c4iw_destroy_resource(&rdev->resource);
@@ -703,18 +715,6 @@
pr_info("%s: On-Chip Queues not supported on this device.\n",
pci_name(infop->pdev));
- if (!is_t4(infop->adapter_type)) {
- if (!allow_db_fc_on_t5) {
- db_fc_threshold = 100000;
- pr_info("DB Flow Control Disabled.\n");
- }
-
- if (!allow_db_coalescing_on_t5) {
- db_coalescing_threshold = -1;
- pr_info("DB Coalescing Disabled.\n");
- }
- }
-
devp = (struct c4iw_dev *)ib_alloc_device(sizeof(*devp));
if (!devp) {
printk(KERN_ERR MOD "Cannot allocate ib device\n");
@@ -749,6 +749,7 @@
spin_lock_init(&devp->lock);
mutex_init(&devp->rdev.stats.lock);
mutex_init(&devp->db_mutex);
+ INIT_LIST_HEAD(&devp->db_fc_list);
if (c4iw_debugfs_root) {
devp->debugfs_root = debugfs_create_dir(
@@ -977,13 +978,16 @@
static void stop_queues(struct uld_ctx *ctx)
{
- spin_lock_irq(&ctx->dev->lock);
- if (ctx->dev->db_state == NORMAL) {
- ctx->dev->rdev.stats.db_state_transitions++;
- ctx->dev->db_state = FLOW_CONTROL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->dev->lock, flags);
+ ctx->dev->rdev.stats.db_state_transitions++;
+ ctx->dev->db_state = STOPPED;
+ if (ctx->dev->rdev.flags & T4_STATUS_PAGE_DISABLED)
idr_for_each(&ctx->dev->qpidr, disable_qp_db, NULL);
- }
- spin_unlock_irq(&ctx->dev->lock);
+ else
+ ctx->dev->rdev.status_page->db_off = 1;
+ spin_unlock_irqrestore(&ctx->dev->lock, flags);
}
static int enable_qp_db(int id, void *p, void *data)
@@ -994,15 +998,70 @@
return 0;
}
+static void resume_rc_qp(struct c4iw_qp *qp)
+{
+ spin_lock(&qp->lock);
+ t4_ring_sq_db(&qp->wq, qp->wq.sq.wq_pidx_inc);
+ qp->wq.sq.wq_pidx_inc = 0;
+ t4_ring_rq_db(&qp->wq, qp->wq.rq.wq_pidx_inc);
+ qp->wq.rq.wq_pidx_inc = 0;
+ spin_unlock(&qp->lock);
+}
+
+static void resume_a_chunk(struct uld_ctx *ctx)
+{
+ int i;
+ struct c4iw_qp *qp;
+
+ for (i = 0; i < DB_FC_RESUME_SIZE; i++) {
+ qp = list_first_entry(&ctx->dev->db_fc_list, struct c4iw_qp,
+ db_fc_entry);
+ list_del_init(&qp->db_fc_entry);
+ resume_rc_qp(qp);
+ if (list_empty(&ctx->dev->db_fc_list))
+ break;
+ }
+}
+
static void resume_queues(struct uld_ctx *ctx)
{
spin_lock_irq(&ctx->dev->lock);
- if (ctx->dev->qpcnt <= db_fc_threshold &&
- ctx->dev->db_state == FLOW_CONTROL) {
- ctx->dev->db_state = NORMAL;
- ctx->dev->rdev.stats.db_state_transitions++;
- idr_for_each(&ctx->dev->qpidr, enable_qp_db, NULL);
+ if (ctx->dev->db_state != STOPPED)
+ goto out;
+ ctx->dev->db_state = FLOW_CONTROL;
+ while (1) {
+ if (list_empty(&ctx->dev->db_fc_list)) {
+ WARN_ON(ctx->dev->db_state != FLOW_CONTROL);
+ ctx->dev->db_state = NORMAL;
+ ctx->dev->rdev.stats.db_state_transitions++;
+ if (ctx->dev->rdev.flags & T4_STATUS_PAGE_DISABLED) {
+ idr_for_each(&ctx->dev->qpidr, enable_qp_db,
+ NULL);
+ } else {
+ ctx->dev->rdev.status_page->db_off = 0;
+ }
+ break;
+ } else {
+ if (cxgb4_dbfifo_count(ctx->dev->rdev.lldi.ports[0], 1)
+ < (ctx->dev->rdev.lldi.dbfifo_int_thresh <<
+ DB_FC_DRAIN_THRESH)) {
+ resume_a_chunk(ctx);
+ }
+ if (!list_empty(&ctx->dev->db_fc_list)) {
+ spin_unlock_irq(&ctx->dev->lock);
+ if (DB_FC_RESUME_DELAY) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule_timeout(DB_FC_RESUME_DELAY);
+ }
+ spin_lock_irq(&ctx->dev->lock);
+ if (ctx->dev->db_state != FLOW_CONTROL)
+ break;
+ }
+ }
}
+out:
+ if (ctx->dev->db_state != NORMAL)
+ ctx->dev->rdev.stats.db_fc_interruptions++;
spin_unlock_irq(&ctx->dev->lock);
}
@@ -1028,12 +1087,12 @@
return 0;
}
-static void deref_qps(struct qp_list qp_list)
+static void deref_qps(struct qp_list *qp_list)
{
int idx;
- for (idx = 0; idx < qp_list.idx; idx++)
- c4iw_qp_rem_ref(&qp_list.qps[idx]->ibqp);
+ for (idx = 0; idx < qp_list->idx; idx++)
+ c4iw_qp_rem_ref(&qp_list->qps[idx]->ibqp);
}
static void recover_lost_dbs(struct uld_ctx *ctx, struct qp_list *qp_list)
@@ -1044,17 +1103,22 @@
for (idx = 0; idx < qp_list->idx; idx++) {
struct c4iw_qp *qp = qp_list->qps[idx];
+ spin_lock_irq(&qp->rhp->lock);
+ spin_lock(&qp->lock);
ret = cxgb4_sync_txq_pidx(qp->rhp->rdev.lldi.ports[0],
qp->wq.sq.qid,
t4_sq_host_wq_pidx(&qp->wq),
t4_sq_wq_size(&qp->wq));
if (ret) {
- printk(KERN_ERR MOD "%s: Fatal error - "
+ pr_err(KERN_ERR MOD "%s: Fatal error - "
"DB overflow recovery failed - "
"error syncing SQ qid %u\n",
pci_name(ctx->lldi.pdev), qp->wq.sq.qid);
+ spin_unlock(&qp->lock);
+ spin_unlock_irq(&qp->rhp->lock);
return;
}
+ qp->wq.sq.wq_pidx_inc = 0;
ret = cxgb4_sync_txq_pidx(qp->rhp->rdev.lldi.ports[0],
qp->wq.rq.qid,
@@ -1062,12 +1126,17 @@
t4_rq_wq_size(&qp->wq));
if (ret) {
- printk(KERN_ERR MOD "%s: Fatal error - "
+ pr_err(KERN_ERR MOD "%s: Fatal error - "
"DB overflow recovery failed - "
"error syncing RQ qid %u\n",
pci_name(ctx->lldi.pdev), qp->wq.rq.qid);
+ spin_unlock(&qp->lock);
+ spin_unlock_irq(&qp->rhp->lock);
return;
}
+ qp->wq.rq.wq_pidx_inc = 0;
+ spin_unlock(&qp->lock);
+ spin_unlock_irq(&qp->rhp->lock);
/* Wait for the dbfifo to drain */
while (cxgb4_dbfifo_count(qp->rhp->rdev.lldi.ports[0], 1) > 0) {
@@ -1083,36 +1152,22 @@
struct qp_list qp_list;
int ret;
- /* lock out kernel db ringers */
- mutex_lock(&ctx->dev->db_mutex);
-
- /* put all queues in to recovery mode */
- spin_lock_irq(&ctx->dev->lock);
- ctx->dev->db_state = RECOVERY;
- ctx->dev->rdev.stats.db_state_transitions++;
- idr_for_each(&ctx->dev->qpidr, disable_qp_db, NULL);
- spin_unlock_irq(&ctx->dev->lock);
-
/* slow everybody down */
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_timeout(usecs_to_jiffies(1000));
- /* Wait for the dbfifo to completely drain. */
- while (cxgb4_dbfifo_count(ctx->dev->rdev.lldi.ports[0], 1) > 0) {
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(usecs_to_jiffies(10));
- }
-
/* flush the SGE contexts */
ret = cxgb4_flush_eq_cache(ctx->dev->rdev.lldi.ports[0]);
if (ret) {
printk(KERN_ERR MOD "%s: Fatal error - DB overflow recovery failed\n",
pci_name(ctx->lldi.pdev));
- goto out;
+ return;
}
/* Count active queues so we can build a list of queues to recover */
spin_lock_irq(&ctx->dev->lock);
+ WARN_ON(ctx->dev->db_state != STOPPED);
+ ctx->dev->db_state = RECOVERY;
idr_for_each(&ctx->dev->qpidr, count_qps, &count);
qp_list.qps = kzalloc(count * sizeof *qp_list.qps, GFP_ATOMIC);
@@ -1120,7 +1175,7 @@
printk(KERN_ERR MOD "%s: Fatal error - DB overflow recovery failed\n",
pci_name(ctx->lldi.pdev));
spin_unlock_irq(&ctx->dev->lock);
- goto out;
+ return;
}
qp_list.idx = 0;
@@ -1133,29 +1188,13 @@
recover_lost_dbs(ctx, &qp_list);
/* we're almost done! deref the qps and clean up */
- deref_qps(qp_list);
+ deref_qps(&qp_list);
kfree(qp_list.qps);
- /* Wait for the dbfifo to completely drain again */
- while (cxgb4_dbfifo_count(ctx->dev->rdev.lldi.ports[0], 1) > 0) {
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(usecs_to_jiffies(10));
- }
-
- /* resume the queues */
spin_lock_irq(&ctx->dev->lock);
- if (ctx->dev->qpcnt > db_fc_threshold)
- ctx->dev->db_state = FLOW_CONTROL;
- else {
- ctx->dev->db_state = NORMAL;
- idr_for_each(&ctx->dev->qpidr, enable_qp_db, NULL);
- }
- ctx->dev->rdev.stats.db_state_transitions++;
+ WARN_ON(ctx->dev->db_state != RECOVERY);
+ ctx->dev->db_state = STOPPED;
spin_unlock_irq(&ctx->dev->lock);
-
-out:
- /* start up kernel db ringers again */
- mutex_unlock(&ctx->dev->db_mutex);
}
static int c4iw_uld_control(void *handle, enum cxgb4_control control, ...)
@@ -1165,9 +1204,7 @@
switch (control) {
case CXGB4_CONTROL_DB_FULL:
stop_queues(ctx);
- mutex_lock(&ctx->dev->rdev.stats.lock);
ctx->dev->rdev.stats.db_full++;
- mutex_unlock(&ctx->dev->rdev.stats.lock);
break;
case CXGB4_CONTROL_DB_EMPTY:
resume_queues(ctx);
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 23eaeab..eb18f9b 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -109,6 +109,7 @@
enum c4iw_rdev_flags {
T4_FATAL_ERROR = (1<<0),
+ T4_STATUS_PAGE_DISABLED = (1<<1),
};
struct c4iw_stat {
@@ -130,6 +131,7 @@
u64 db_empty;
u64 db_drop;
u64 db_state_transitions;
+ u64 db_fc_interruptions;
u64 tcam_full;
u64 act_ofld_conn_fails;
u64 pas_ofld_conn_fails;
@@ -150,6 +152,7 @@
unsigned long oc_mw_pa;
void __iomem *oc_mw_kva;
struct c4iw_stats stats;
+ struct t4_dev_status_page *status_page;
};
static inline int c4iw_fatal_error(struct c4iw_rdev *rdev)
@@ -211,7 +214,8 @@
enum db_state {
NORMAL = 0,
FLOW_CONTROL = 1,
- RECOVERY = 2
+ RECOVERY = 2,
+ STOPPED = 3
};
struct c4iw_dev {
@@ -225,10 +229,10 @@
struct mutex db_mutex;
struct dentry *debugfs_root;
enum db_state db_state;
- int qpcnt;
struct idr hwtid_idr;
struct idr atid_idr;
struct idr stid_idr;
+ struct list_head db_fc_list;
};
static inline struct c4iw_dev *to_c4iw_dev(struct ib_device *ibdev)
@@ -432,6 +436,7 @@
struct c4iw_qp {
struct ib_qp ibqp;
+ struct list_head db_fc_entry;
struct c4iw_dev *rhp;
struct c4iw_ep *ep;
struct c4iw_qp_attributes attr;
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 7e94c9a..7942925 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -106,15 +106,56 @@
{
struct c4iw_ucontext *context;
struct c4iw_dev *rhp = to_c4iw_dev(ibdev);
+ static int warned;
+ struct c4iw_alloc_ucontext_resp uresp;
+ int ret = 0;
+ struct c4iw_mm_entry *mm = NULL;
PDBG("%s ibdev %p\n", __func__, ibdev);
context = kzalloc(sizeof(*context), GFP_KERNEL);
- if (!context)
- return ERR_PTR(-ENOMEM);
+ if (!context) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
c4iw_init_dev_ucontext(&rhp->rdev, &context->uctx);
INIT_LIST_HEAD(&context->mmaps);
spin_lock_init(&context->mmap_lock);
+
+ if (udata->outlen < sizeof(uresp)) {
+ if (!warned++)
+ pr_err(MOD "Warning - downlevel libcxgb4 (non-fatal), device status page disabled.");
+ rhp->rdev.flags |= T4_STATUS_PAGE_DISABLED;
+ } else {
+ mm = kmalloc(sizeof(*mm), GFP_KERNEL);
+ if (!mm) {
+ ret = -ENOMEM;
+ goto err_free;
+ }
+
+ uresp.status_page_size = PAGE_SIZE;
+
+ spin_lock(&context->mmap_lock);
+ uresp.status_page_key = context->key;
+ context->key += PAGE_SIZE;
+ spin_unlock(&context->mmap_lock);
+
+ ret = ib_copy_to_udata(udata, &uresp, sizeof(uresp));
+ if (ret)
+ goto err_mm;
+
+ mm->key = uresp.status_page_key;
+ mm->addr = virt_to_phys(rhp->rdev.status_page);
+ mm->len = PAGE_SIZE;
+ insert_mmap(context, mm);
+ }
return &context->ibucontext;
+err_mm:
+ kfree(mm);
+err_free:
+ kfree(context);
+err:
+ return ERR_PTR(ret);
}
static int c4iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 5829367..3b62eb5 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -638,6 +638,46 @@
wake_up(&(to_c4iw_qp(qp)->wait));
}
+static void add_to_fc_list(struct list_head *head, struct list_head *entry)
+{
+ if (list_empty(entry))
+ list_add_tail(entry, head);
+}
+
+static int ring_kernel_sq_db(struct c4iw_qp *qhp, u16 inc)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&qhp->rhp->lock, flags);
+ spin_lock(&qhp->lock);
+ if (qhp->rhp->db_state == NORMAL) {
+ t4_ring_sq_db(&qhp->wq, inc);
+ } else {
+ add_to_fc_list(&qhp->rhp->db_fc_list, &qhp->db_fc_entry);
+ qhp->wq.sq.wq_pidx_inc += inc;
+ }
+ spin_unlock(&qhp->lock);
+ spin_unlock_irqrestore(&qhp->rhp->lock, flags);
+ return 0;
+}
+
+static int ring_kernel_rq_db(struct c4iw_qp *qhp, u16 inc)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&qhp->rhp->lock, flags);
+ spin_lock(&qhp->lock);
+ if (qhp->rhp->db_state == NORMAL) {
+ t4_ring_rq_db(&qhp->wq, inc);
+ } else {
+ add_to_fc_list(&qhp->rhp->db_fc_list, &qhp->db_fc_entry);
+ qhp->wq.rq.wq_pidx_inc += inc;
+ }
+ spin_unlock(&qhp->lock);
+ spin_unlock_irqrestore(&qhp->rhp->lock, flags);
+ return 0;
+}
+
int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
struct ib_send_wr **bad_wr)
{
@@ -750,9 +790,13 @@
t4_sq_produce(&qhp->wq, len16);
idx += DIV_ROUND_UP(len16*16, T4_EQ_ENTRY_SIZE);
}
- if (t4_wq_db_enabled(&qhp->wq))
+ if (!qhp->rhp->rdev.status_page->db_off) {
t4_ring_sq_db(&qhp->wq, idx);
- spin_unlock_irqrestore(&qhp->lock, flag);
+ spin_unlock_irqrestore(&qhp->lock, flag);
+ } else {
+ spin_unlock_irqrestore(&qhp->lock, flag);
+ ring_kernel_sq_db(qhp, idx);
+ }
return err;
}
@@ -812,9 +856,13 @@
wr = wr->next;
num_wrs--;
}
- if (t4_wq_db_enabled(&qhp->wq))
+ if (!qhp->rhp->rdev.status_page->db_off) {
t4_ring_rq_db(&qhp->wq, idx);
- spin_unlock_irqrestore(&qhp->lock, flag);
+ spin_unlock_irqrestore(&qhp->lock, flag);
+ } else {
+ spin_unlock_irqrestore(&qhp->lock, flag);
+ ring_kernel_rq_db(qhp, idx);
+ }
return err;
}
@@ -1200,35 +1248,6 @@
return ret;
}
-/*
- * Called by the library when the qp has user dbs disabled due to
- * a DB_FULL condition. This function will single-thread all user
- * DB rings to avoid overflowing the hw db-fifo.
- */
-static int ring_kernel_db(struct c4iw_qp *qhp, u32 qid, u16 inc)
-{
- int delay = db_delay_usecs;
-
- mutex_lock(&qhp->rhp->db_mutex);
- do {
-
- /*
- * The interrupt threshold is dbfifo_int_thresh << 6. So
- * make sure we don't cross that and generate an interrupt.
- */
- if (cxgb4_dbfifo_count(qhp->rhp->rdev.lldi.ports[0], 1) <
- (qhp->rhp->rdev.lldi.dbfifo_int_thresh << 5)) {
- writel(QID(qid) | PIDX(inc), qhp->wq.db);
- break;
- }
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(usecs_to_jiffies(delay));
- delay = min(delay << 1, 2000);
- } while (1);
- mutex_unlock(&qhp->rhp->db_mutex);
- return 0;
-}
-
int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
enum c4iw_qp_attr_mask mask,
struct c4iw_qp_attributes *attrs,
@@ -1278,11 +1297,11 @@
}
if (mask & C4IW_QP_ATTR_SQ_DB) {
- ret = ring_kernel_db(qhp, qhp->wq.sq.qid, attrs->sq_db_inc);
+ ret = ring_kernel_sq_db(qhp, attrs->sq_db_inc);
goto out;
}
if (mask & C4IW_QP_ATTR_RQ_DB) {
- ret = ring_kernel_db(qhp, qhp->wq.rq.qid, attrs->rq_db_inc);
+ ret = ring_kernel_rq_db(qhp, attrs->rq_db_inc);
goto out;
}
@@ -1465,14 +1484,6 @@
return ret;
}
-static int enable_qp_db(int id, void *p, void *data)
-{
- struct c4iw_qp *qp = p;
-
- t4_enable_wq_db(&qp->wq);
- return 0;
-}
-
int c4iw_destroy_qp(struct ib_qp *ib_qp)
{
struct c4iw_dev *rhp;
@@ -1490,22 +1501,15 @@
c4iw_modify_qp(rhp, qhp, C4IW_QP_ATTR_NEXT_STATE, &attrs, 0);
wait_event(qhp->wait, !qhp->ep);
- spin_lock_irq(&rhp->lock);
- remove_handle_nolock(rhp, &rhp->qpidr, qhp->wq.sq.qid);
- rhp->qpcnt--;
- BUG_ON(rhp->qpcnt < 0);
- if (rhp->qpcnt <= db_fc_threshold && rhp->db_state == FLOW_CONTROL) {
- rhp->rdev.stats.db_state_transitions++;
- rhp->db_state = NORMAL;
- idr_for_each(&rhp->qpidr, enable_qp_db, NULL);
- }
- if (db_coalescing_threshold >= 0)
- if (rhp->qpcnt <= db_coalescing_threshold)
- cxgb4_enable_db_coalescing(rhp->rdev.lldi.ports[0]);
- spin_unlock_irq(&rhp->lock);
+ remove_handle(rhp, &rhp->qpidr, qhp->wq.sq.qid);
atomic_dec(&qhp->refcnt);
wait_event(qhp->wait, !atomic_read(&qhp->refcnt));
+ spin_lock_irq(&rhp->lock);
+ if (!list_empty(&qhp->db_fc_entry))
+ list_del_init(&qhp->db_fc_entry);
+ spin_unlock_irq(&rhp->lock);
+
ucontext = ib_qp->uobject ?
to_c4iw_ucontext(ib_qp->uobject->context) : NULL;
destroy_qp(&rhp->rdev, &qhp->wq,
@@ -1516,14 +1520,6 @@
return 0;
}
-static int disable_qp_db(int id, void *p, void *data)
-{
- struct c4iw_qp *qp = p;
-
- t4_disable_wq_db(&qp->wq);
- return 0;
-}
-
struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
struct ib_udata *udata)
{
@@ -1610,20 +1606,7 @@
init_waitqueue_head(&qhp->wait);
atomic_set(&qhp->refcnt, 1);
- spin_lock_irq(&rhp->lock);
- if (rhp->db_state != NORMAL)
- t4_disable_wq_db(&qhp->wq);
- rhp->qpcnt++;
- if (rhp->qpcnt > db_fc_threshold && rhp->db_state == NORMAL) {
- rhp->rdev.stats.db_state_transitions++;
- rhp->db_state = FLOW_CONTROL;
- idr_for_each(&rhp->qpidr, disable_qp_db, NULL);
- }
- if (db_coalescing_threshold >= 0)
- if (rhp->qpcnt > db_coalescing_threshold)
- cxgb4_disable_db_coalescing(rhp->rdev.lldi.ports[0]);
- ret = insert_handle_nolock(rhp, &rhp->qpidr, qhp, qhp->wq.sq.qid);
- spin_unlock_irq(&rhp->lock);
+ ret = insert_handle(rhp, &rhp->qpidr, qhp, qhp->wq.sq.qid);
if (ret)
goto err2;
@@ -1709,6 +1692,7 @@
}
qhp->ibqp.qp_num = qhp->wq.sq.qid;
init_timer(&(qhp->timer));
+ INIT_LIST_HEAD(&qhp->db_fc_entry);
PDBG("%s qhp %p sq_num_entries %d, rq_num_entries %d qpid 0x%0x\n",
__func__, qhp, qhp->attr.sq_num_entries, qhp->attr.rq_num_entries,
qhp->wq.sq.qid);
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index e73ace7..eeca8b1 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -300,6 +300,7 @@
u16 cidx;
u16 pidx;
u16 wq_pidx;
+ u16 wq_pidx_inc;
u16 flags;
short flush_cidx;
};
@@ -324,6 +325,7 @@
u16 cidx;
u16 pidx;
u16 wq_pidx;
+ u16 wq_pidx_inc;
};
struct t4_wq {
@@ -609,3 +611,7 @@
((struct t4_status_page *)&cq->queue[cq->size])->qp_err = 1;
}
#endif
+
+struct t4_dev_status_page {
+ u8 db_off;
+};
diff --git a/drivers/infiniband/hw/cxgb4/user.h b/drivers/infiniband/hw/cxgb4/user.h
index 32b754c..11ccd27 100644
--- a/drivers/infiniband/hw/cxgb4/user.h
+++ b/drivers/infiniband/hw/cxgb4/user.h
@@ -70,4 +70,9 @@
__u32 qid_mask;
__u32 flags;
};
+
+struct c4iw_alloc_ucontext_resp {
+ __u64 status_page_key;
+ __u32 status_page_size;
+};
#endif
diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c
index 2f215b9..0eb141c 100644
--- a/drivers/infiniband/hw/mlx4/alias_GUID.c
+++ b/drivers/infiniband/hw/mlx4/alias_GUID.c
@@ -154,7 +154,7 @@
continue;
slave_id = (block_num * NUM_ALIAS_GUID_IN_REC) + i ;
- if (slave_id >= dev->dev->num_slaves)
+ if (slave_id >= dev->dev->num_vfs + 1)
return;
tmp_cur_ag = *(__be64 *)&p_data[i * GUID_REC_SIZE];
form_cache_ag = get_cached_alias_guid(dev, port_num,
diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c
index d1f5f1d..56a593e 100644
--- a/drivers/infiniband/hw/mlx4/cm.c
+++ b/drivers/infiniband/hw/mlx4/cm.c
@@ -61,6 +61,11 @@
__be32 remote_comm_id;
};
+struct cm_sidr_generic_msg {
+ struct ib_mad_hdr hdr;
+ __be32 request_id;
+};
+
struct cm_req_msg {
unsigned char unused[0x60];
union ib_gid primary_path_sgid;
@@ -69,28 +74,62 @@
static void set_local_comm_id(struct ib_mad *mad, u32 cm_id)
{
- struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
- msg->local_comm_id = cpu_to_be32(cm_id);
+ if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+ struct cm_sidr_generic_msg *msg =
+ (struct cm_sidr_generic_msg *)mad;
+ msg->request_id = cpu_to_be32(cm_id);
+ } else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+ pr_err("trying to set local_comm_id in SIDR_REP\n");
+ return;
+ } else {
+ struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
+ msg->local_comm_id = cpu_to_be32(cm_id);
+ }
}
static u32 get_local_comm_id(struct ib_mad *mad)
{
- struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
-
- return be32_to_cpu(msg->local_comm_id);
+ if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+ struct cm_sidr_generic_msg *msg =
+ (struct cm_sidr_generic_msg *)mad;
+ return be32_to_cpu(msg->request_id);
+ } else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+ pr_err("trying to set local_comm_id in SIDR_REP\n");
+ return -1;
+ } else {
+ struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
+ return be32_to_cpu(msg->local_comm_id);
+ }
}
static void set_remote_comm_id(struct ib_mad *mad, u32 cm_id)
{
- struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
- msg->remote_comm_id = cpu_to_be32(cm_id);
+ if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+ struct cm_sidr_generic_msg *msg =
+ (struct cm_sidr_generic_msg *)mad;
+ msg->request_id = cpu_to_be32(cm_id);
+ } else if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+ pr_err("trying to set remote_comm_id in SIDR_REQ\n");
+ return;
+ } else {
+ struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
+ msg->remote_comm_id = cpu_to_be32(cm_id);
+ }
}
static u32 get_remote_comm_id(struct ib_mad *mad)
{
- struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
-
- return be32_to_cpu(msg->remote_comm_id);
+ if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+ struct cm_sidr_generic_msg *msg =
+ (struct cm_sidr_generic_msg *)mad;
+ return be32_to_cpu(msg->request_id);
+ } else if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+ pr_err("trying to set remote_comm_id in SIDR_REQ\n");
+ return -1;
+ } else {
+ struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
+ return be32_to_cpu(msg->remote_comm_id);
+ }
}
static union ib_gid gid_from_req_msg(struct ib_device *ibdev, struct ib_mad *mad)
@@ -282,19 +321,21 @@
u32 sl_cm_id;
int pv_cm_id = -1;
- sl_cm_id = get_local_comm_id(mad);
-
if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID ||
- mad->mad_hdr.attr_id == CM_REP_ATTR_ID) {
+ mad->mad_hdr.attr_id == CM_REP_ATTR_ID ||
+ mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+ sl_cm_id = get_local_comm_id(mad);
id = id_map_alloc(ibdev, slave_id, sl_cm_id);
if (IS_ERR(id)) {
mlx4_ib_warn(ibdev, "%s: id{slave: %d, sl_cm_id: 0x%x} Failed to id_map_alloc\n",
__func__, slave_id, sl_cm_id);
return PTR_ERR(id);
}
- } else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID) {
+ } else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID ||
+ mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
return 0;
} else {
+ sl_cm_id = get_local_comm_id(mad);
id = id_map_get(ibdev, &pv_cm_id, slave_id, sl_cm_id);
}
@@ -315,14 +356,18 @@
}
int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
- struct ib_mad *mad)
+ struct ib_mad *mad)
{
u32 pv_cm_id;
struct id_map_entry *id;
- if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID) {
+ if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID ||
+ mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
union ib_gid gid;
+ if (!slave)
+ return 0;
+
gid = gid_from_req_msg(ibdev, mad);
*slave = mlx4_ib_find_real_gid(ibdev, port, gid.global.interface_id);
if (*slave < 0) {
@@ -341,7 +386,8 @@
return -ENOENT;
}
- *slave = id->slave_id;
+ if (slave)
+ *slave = id->slave_id;
set_remote_comm_id(mad, id->sl_cm_id);
if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID)
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index cc40f08..5f64081 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -564,7 +564,7 @@
}
static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc,
- unsigned tail, struct mlx4_cqe *cqe)
+ unsigned tail, struct mlx4_cqe *cqe, int is_eth)
{
struct mlx4_ib_proxy_sqp_hdr *hdr;
@@ -574,12 +574,20 @@
DMA_FROM_DEVICE);
hdr = (struct mlx4_ib_proxy_sqp_hdr *) (qp->sqp_proxy_rcv[tail].addr);
wc->pkey_index = be16_to_cpu(hdr->tun.pkey_index);
- wc->slid = be16_to_cpu(hdr->tun.slid_mac_47_32);
- wc->sl = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12);
wc->src_qp = be32_to_cpu(hdr->tun.flags_src_qp) & 0xFFFFFF;
wc->wc_flags |= (hdr->tun.g_ml_path & 0x80) ? (IB_WC_GRH) : 0;
wc->dlid_path_bits = 0;
+ if (is_eth) {
+ wc->vlan_id = be16_to_cpu(hdr->tun.sl_vid);
+ memcpy(&(wc->smac[0]), (char *)&hdr->tun.mac_31_0, 4);
+ memcpy(&(wc->smac[4]), (char *)&hdr->tun.slid_mac_47_32, 2);
+ wc->wc_flags |= (IB_WC_WITH_VLAN | IB_WC_WITH_SMAC);
+ } else {
+ wc->slid = be16_to_cpu(hdr->tun.slid_mac_47_32);
+ wc->sl = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12);
+ }
+
return 0;
}
@@ -594,6 +602,7 @@
struct mlx4_srq *msrq = NULL;
int is_send;
int is_error;
+ int is_eth;
u32 g_mlpath_rqpn;
u16 wqe_ctr;
unsigned tail = 0;
@@ -778,11 +787,15 @@
break;
}
+ is_eth = (rdma_port_get_link_layer(wc->qp->device,
+ (*cur_qp)->port) ==
+ IB_LINK_LAYER_ETHERNET);
if (mlx4_is_mfunc(to_mdev(cq->ibcq.device)->dev)) {
if ((*cur_qp)->mlx4_ib_qp_type &
(MLX4_IB_QPT_PROXY_SMI_OWNER |
MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI))
- return use_tunnel_data(*cur_qp, cq, wc, tail, cqe);
+ return use_tunnel_data(*cur_qp, cq, wc, tail,
+ cqe, is_eth);
}
wc->slid = be16_to_cpu(cqe->rlid);
@@ -793,20 +806,21 @@
wc->pkey_index = be32_to_cpu(cqe->immed_rss_invalid) & 0x7f;
wc->wc_flags |= mlx4_ib_ipoib_csum_ok(cqe->status,
cqe->checksum) ? IB_WC_IP_CSUM_OK : 0;
- if (rdma_port_get_link_layer(wc->qp->device,
- (*cur_qp)->port) == IB_LINK_LAYER_ETHERNET)
+ if (is_eth) {
wc->sl = be16_to_cpu(cqe->sl_vid) >> 13;
- else
- wc->sl = be16_to_cpu(cqe->sl_vid) >> 12;
- if (be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_VLAN_PRESENT_MASK) {
- wc->vlan_id = be16_to_cpu(cqe->sl_vid) &
- MLX4_CQE_VID_MASK;
+ if (be32_to_cpu(cqe->vlan_my_qpn) &
+ MLX4_CQE_VLAN_PRESENT_MASK) {
+ wc->vlan_id = be16_to_cpu(cqe->sl_vid) &
+ MLX4_CQE_VID_MASK;
+ } else {
+ wc->vlan_id = 0xffff;
+ }
+ memcpy(wc->smac, cqe->smac, ETH_ALEN);
+ wc->wc_flags |= (IB_WC_WITH_VLAN | IB_WC_WITH_SMAC);
} else {
+ wc->sl = be16_to_cpu(cqe->sl_vid) >> 12;
wc->vlan_id = 0xffff;
}
- wc->wc_flags |= IB_WC_WITH_VLAN;
- memcpy(wc->smac, cqe->smac, ETH_ALEN);
- wc->wc_flags |= IB_WC_WITH_SMAC;
}
return 0;
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index f2a3f48..fd36ec6 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -467,6 +467,7 @@
int ret = 0;
u16 tun_pkey_ix;
u16 cached_pkey;
+ u8 is_eth = dev->dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH;
if (dest_qpt > IB_QPT_GSI)
return -EINVAL;
@@ -509,6 +510,10 @@
* The driver will set the force loopback bit in post_send */
memset(&attr, 0, sizeof attr);
attr.port_num = port;
+ if (is_eth) {
+ memcpy(&attr.grh.dgid.raw[0], &grh->dgid.raw[0], 16);
+ attr.ah_flags = IB_AH_GRH;
+ }
ah = ib_create_ah(tun_ctx->pd, &attr);
if (IS_ERR(ah))
return -ENOMEM;
@@ -540,11 +545,36 @@
/* adjust tunnel data */
tun_mad->hdr.pkey_index = cpu_to_be16(tun_pkey_ix);
- tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12);
- tun_mad->hdr.slid_mac_47_32 = cpu_to_be16(wc->slid);
tun_mad->hdr.flags_src_qp = cpu_to_be32(wc->src_qp & 0xFFFFFF);
tun_mad->hdr.g_ml_path = (grh && (wc->wc_flags & IB_WC_GRH)) ? 0x80 : 0;
+ if (is_eth) {
+ u16 vlan = 0;
+ if (mlx4_get_slave_default_vlan(dev->dev, port, slave, &vlan,
+ NULL)) {
+ /* VST mode */
+ if (vlan != wc->vlan_id)
+ /* Packet vlan is not the VST-assigned vlan.
+ * Drop the packet.
+ */
+ goto out;
+ else
+ /* Remove the vlan tag before forwarding
+ * the packet to the VF.
+ */
+ vlan = 0xffff;
+ } else {
+ vlan = wc->vlan_id;
+ }
+
+ tun_mad->hdr.sl_vid = cpu_to_be16(vlan);
+ memcpy((char *)&tun_mad->hdr.mac_31_0, &(wc->smac[0]), 4);
+ memcpy((char *)&tun_mad->hdr.slid_mac_47_32, &(wc->smac[4]), 2);
+ } else {
+ tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12);
+ tun_mad->hdr.slid_mac_47_32 = cpu_to_be16(wc->slid);
+ }
+
ib_dma_sync_single_for_device(&dev->ib_dev,
tun_qp->tx_ring[tun_tx_ix].buf.map,
sizeof (struct mlx4_rcv_tunnel_mad),
@@ -580,6 +610,41 @@
int err;
int slave;
u8 *slave_id;
+ int is_eth = 0;
+
+ if (rdma_port_get_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND)
+ is_eth = 0;
+ else
+ is_eth = 1;
+
+ if (is_eth) {
+ if (!(wc->wc_flags & IB_WC_GRH)) {
+ mlx4_ib_warn(ibdev, "RoCE grh not present.\n");
+ return -EINVAL;
+ }
+ if (mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_CM) {
+ mlx4_ib_warn(ibdev, "RoCE mgmt class is not CM\n");
+ return -EINVAL;
+ }
+ if (mlx4_get_slave_from_roce_gid(dev->dev, port, grh->dgid.raw, &slave)) {
+ mlx4_ib_warn(ibdev, "failed matching grh\n");
+ return -ENOENT;
+ }
+ if (slave >= dev->dev->caps.sqp_demux) {
+ mlx4_ib_warn(ibdev, "slave id: %d is bigger than allowed:%d\n",
+ slave, dev->dev->caps.sqp_demux);
+ return -ENOENT;
+ }
+
+ if (mlx4_ib_demux_cm_handler(ibdev, port, NULL, mad))
+ return 0;
+
+ err = mlx4_ib_send_to_slave(dev, slave, port, wc->qp->qp_type, wc, grh, mad);
+ if (err)
+ pr_debug("failed sending to slave %d via tunnel qp (%d)\n",
+ slave, err);
+ return 0;
+ }
/* Initially assume that this mad is for us */
slave = mlx4_master_func_num(dev->dev);
@@ -1076,8 +1141,9 @@
int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
- enum ib_qp_type dest_qpt, u16 pkey_index, u32 remote_qpn,
- u32 qkey, struct ib_ah_attr *attr, struct ib_mad *mad)
+ enum ib_qp_type dest_qpt, u16 pkey_index,
+ u32 remote_qpn, u32 qkey, struct ib_ah_attr *attr,
+ u8 *s_mac, struct ib_mad *mad)
{
struct ib_sge list;
struct ib_send_wr wr, *bad_wr;
@@ -1166,6 +1232,9 @@
wr.num_sge = 1;
wr.opcode = IB_WR_SEND;
wr.send_flags = IB_SEND_SIGNALED;
+ if (s_mac)
+ memcpy(to_mah(ah)->av.eth.s_mac, s_mac, 6);
+
ret = ib_post_send(send_qp, &wr, &bad_wr);
out:
@@ -1174,6 +1243,22 @@
return ret;
}
+static int get_slave_base_gid_ix(struct mlx4_ib_dev *dev, int slave, int port)
+{
+ if (rdma_port_get_link_layer(&dev->ib_dev, port) == IB_LINK_LAYER_INFINIBAND)
+ return slave;
+ return mlx4_get_base_gid_ix(dev->dev, slave, port);
+}
+
+static void fill_in_real_sgid_index(struct mlx4_ib_dev *dev, int slave, int port,
+ struct ib_ah_attr *ah_attr)
+{
+ if (rdma_port_get_link_layer(&dev->ib_dev, port) == IB_LINK_LAYER_INFINIBAND)
+ ah_attr->grh.sgid_index = slave;
+ else
+ ah_attr->grh.sgid_index += get_slave_base_gid_ix(dev, slave, port);
+}
+
static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc *wc)
{
struct mlx4_ib_dev *dev = to_mdev(ctx->ib_dev);
@@ -1184,6 +1269,7 @@
struct ib_ah_attr ah_attr;
u8 *slave_id;
int slave;
+ int port;
/* Get slave that sent this packet */
if (wc->src_qp < dev->dev->phys_caps.base_proxy_sqpn ||
@@ -1260,12 +1346,18 @@
memcpy(&ah.av, &tunnel->hdr.av, sizeof (struct mlx4_av));
ah.ibah.device = ctx->ib_dev;
mlx4_ib_query_ah(&ah.ibah, &ah_attr);
- if ((ah_attr.ah_flags & IB_AH_GRH) &&
- (ah_attr.grh.sgid_index != slave)) {
- mlx4_ib_warn(ctx->ib_dev, "slave:%d accessed invalid sgid_index:%d\n",
- slave, ah_attr.grh.sgid_index);
+ if (ah_attr.ah_flags & IB_AH_GRH)
+ fill_in_real_sgid_index(dev, slave, ctx->port, &ah_attr);
+
+ port = mlx4_slave_convert_port(dev->dev, slave, ah_attr.port_num);
+ if (port < 0)
return;
- }
+ ah_attr.port_num = port;
+ memcpy(ah_attr.dmac, tunnel->hdr.mac, 6);
+ ah_attr.vlan_id = be16_to_cpu(tunnel->hdr.vlan);
+ /* if slave have default vlan use it */
+ mlx4_get_slave_default_vlan(dev->dev, ctx->port, slave,
+ &ah_attr.vlan_id, &ah_attr.sl);
mlx4_ib_send_to_wire(dev, slave, ctx->port,
is_proxy_qp0(dev, wc->src_qp, slave) ?
@@ -1273,7 +1365,7 @@
be16_to_cpu(tunnel->hdr.pkey_index),
be32_to_cpu(tunnel->hdr.remote_qpn),
be32_to_cpu(tunnel->hdr.qkey),
- &ah_attr, &tunnel->mad);
+ &ah_attr, wc->smac, &tunnel->mad);
}
static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx,
@@ -1850,7 +1942,15 @@
ctx->port = port;
ctx->ib_dev = &dev->ib_dev;
- for (i = 0; i < dev->dev->caps.sqp_demux; i++) {
+ for (i = 0;
+ i < min(dev->dev->caps.sqp_demux, (u16)(dev->dev->num_vfs + 1));
+ i++) {
+ struct mlx4_active_ports actv_ports =
+ mlx4_get_active_ports(dev->dev, i);
+
+ if (!test_bit(port - 1, actv_ports.ports))
+ continue;
+
ret = alloc_pv_object(dev, i, port, &ctx->tun[i]);
if (ret) {
ret = -ENOMEM;
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index c2702f5..6cb8546 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -53,8 +53,8 @@
#include "user.h"
#define DRV_NAME MLX4_IB_DRV_NAME
-#define DRV_VERSION "1.0"
-#define DRV_RELDATE "April 4, 2008"
+#define DRV_VERSION "2.2-1"
+#define DRV_RELDATE "Feb 2014"
#define MLX4_IB_FLOW_MAX_PRIO 0xFFF
#define MLX4_IB_FLOW_QPN_MASK 0xFFFFFF
@@ -347,7 +347,7 @@
props->active_width = (((u8 *)mailbox->buf)[5] == 0x40) ?
IB_WIDTH_4X : IB_WIDTH_1X;
props->active_speed = IB_SPEED_QDR;
- props->port_cap_flags = IB_PORT_CM_SUP;
+ props->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_IP_BASED_GIDS;
props->gid_tbl_len = mdev->dev->caps.gid_table_len[port];
props->max_msg_sz = mdev->dev->caps.max_msg_sz;
props->pkey_tbl_len = 1;
@@ -1357,6 +1357,21 @@
&dev_attr_board_id
};
+static void mlx4_addrconf_ifid_eui48(u8 *eui, u16 vlan_id,
+ struct net_device *dev)
+{
+ memcpy(eui, dev->dev_addr, 3);
+ memcpy(eui + 5, dev->dev_addr + 3, 3);
+ if (vlan_id < 0x1000) {
+ eui[3] = vlan_id >> 8;
+ eui[4] = vlan_id & 0xff;
+ } else {
+ eui[3] = 0xff;
+ eui[4] = 0xfe;
+ }
+ eui[0] ^= 2;
+}
+
static void update_gids_task(struct work_struct *work)
{
struct update_gid_work *gw = container_of(work, struct update_gid_work, work);
@@ -1393,7 +1408,6 @@
struct mlx4_cmd_mailbox *mailbox;
union ib_gid *gids;
int err;
- int i;
struct mlx4_dev *dev = gw->dev->dev;
mailbox = mlx4_alloc_cmd_mailbox(dev);
@@ -1405,18 +1419,16 @@
gids = mailbox->buf;
memcpy(gids, gw->gids, sizeof(gw->gids));
- for (i = 1; i < gw->dev->num_ports + 1; i++) {
- if (mlx4_ib_port_link_layer(&gw->dev->ib_dev, i) ==
- IB_LINK_LAYER_ETHERNET) {
- err = mlx4_cmd(dev, mailbox->dma,
- MLX4_SET_PORT_GID_TABLE << 8 | i,
- 1, MLX4_CMD_SET_PORT,
- MLX4_CMD_TIME_CLASS_B,
- MLX4_CMD_WRAPPED);
- if (err)
- pr_warn(KERN_WARNING
- "set port %d command failed\n", i);
- }
+ if (mlx4_ib_port_link_layer(&gw->dev->ib_dev, gw->port) ==
+ IB_LINK_LAYER_ETHERNET) {
+ err = mlx4_cmd(dev, mailbox->dma,
+ MLX4_SET_PORT_GID_TABLE << 8 | gw->port,
+ 1, MLX4_CMD_SET_PORT,
+ MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
+ if (err)
+ pr_warn(KERN_WARNING
+ "set port %d command failed\n", gw->port);
}
mlx4_free_cmd_mailbox(dev, mailbox);
@@ -1425,7 +1437,8 @@
}
static int update_gid_table(struct mlx4_ib_dev *dev, int port,
- union ib_gid *gid, int clear)
+ union ib_gid *gid, int clear,
+ int default_gid)
{
struct update_gid_work *work;
int i;
@@ -1434,26 +1447,31 @@
int found = -1;
int max_gids;
- max_gids = dev->dev->caps.gid_table_len[port];
- for (i = 0; i < max_gids; ++i) {
- if (!memcmp(&dev->iboe.gid_table[port - 1][i], gid,
- sizeof(*gid)))
- found = i;
-
- if (clear) {
- if (found >= 0) {
- need_update = 1;
- dev->iboe.gid_table[port - 1][found] = zgid;
- break;
- }
- } else {
- if (found >= 0)
- break;
-
- if (free < 0 &&
- !memcmp(&dev->iboe.gid_table[port - 1][i], &zgid,
+ if (default_gid) {
+ free = 0;
+ } else {
+ max_gids = dev->dev->caps.gid_table_len[port];
+ for (i = 1; i < max_gids; ++i) {
+ if (!memcmp(&dev->iboe.gid_table[port - 1][i], gid,
sizeof(*gid)))
- free = i;
+ found = i;
+
+ if (clear) {
+ if (found >= 0) {
+ need_update = 1;
+ dev->iboe.gid_table[port - 1][found] =
+ zgid;
+ break;
+ }
+ } else {
+ if (found >= 0)
+ break;
+
+ if (free < 0 &&
+ !memcmp(&dev->iboe.gid_table[port - 1][i],
+ &zgid, sizeof(*gid)))
+ free = i;
+ }
}
}
@@ -1478,18 +1496,26 @@
return 0;
}
-static int reset_gid_table(struct mlx4_ib_dev *dev)
+static void mlx4_make_default_gid(struct net_device *dev, union ib_gid *gid)
+{
+ gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
+ mlx4_addrconf_ifid_eui48(&gid->raw[8], 0xffff, dev);
+}
+
+
+static int reset_gid_table(struct mlx4_ib_dev *dev, u8 port)
{
struct update_gid_work *work;
-
work = kzalloc(sizeof(*work), GFP_ATOMIC);
if (!work)
return -ENOMEM;
- memset(dev->iboe.gid_table, 0, sizeof(dev->iboe.gid_table));
+
+ memset(dev->iboe.gid_table[port - 1], 0, sizeof(work->gids));
memset(work->gids, 0, sizeof(work->gids));
INIT_WORK(&work->work, reset_gids_task);
work->dev = dev;
+ work->port = port;
queue_work(wq, &work->work);
return 0;
}
@@ -1502,6 +1528,12 @@
struct net_device *real_dev = rdma_vlan_dev_real_dev(event_netdev) ?
rdma_vlan_dev_real_dev(event_netdev) :
event_netdev;
+ union ib_gid default_gid;
+
+ mlx4_make_default_gid(real_dev, &default_gid);
+
+ if (!memcmp(gid, &default_gid, sizeof(*gid)))
+ return 0;
if (event != NETDEV_DOWN && event != NETDEV_UP)
return 0;
@@ -1514,13 +1546,13 @@
iboe = &ibdev->iboe;
spin_lock(&iboe->lock);
- for (port = 1; port <= MLX4_MAX_PORTS; ++port)
+ for (port = 1; port <= ibdev->dev->caps.num_ports; ++port)
if ((netif_is_bond_master(real_dev) &&
(real_dev == iboe->masters[port - 1])) ||
(!netif_is_bond_master(real_dev) &&
(real_dev == iboe->netdevs[port - 1])))
update_gid_table(ibdev, port, gid,
- event == NETDEV_DOWN);
+ event == NETDEV_DOWN, 0);
spin_unlock(&iboe->lock);
return 0;
@@ -1536,18 +1568,15 @@
rdma_vlan_dev_real_dev(dev) : dev;
iboe = &ibdev->iboe;
- spin_lock(&iboe->lock);
- for (port = 1; port <= MLX4_MAX_PORTS; ++port)
+ for (port = 1; port <= ibdev->dev->caps.num_ports; ++port)
if ((netif_is_bond_master(real_dev) &&
(real_dev == iboe->masters[port - 1])) ||
(!netif_is_bond_master(real_dev) &&
(real_dev == iboe->netdevs[port - 1])))
break;
- spin_unlock(&iboe->lock);
-
- if ((port == 0) || (port > MLX4_MAX_PORTS))
+ if ((port == 0) || (port > ibdev->dev->caps.num_ports))
return 0;
else
return port;
@@ -1597,7 +1626,7 @@
union ib_gid gid;
- if ((port == 0) || (port > MLX4_MAX_PORTS))
+ if ((port == 0) || (port > ibdev->dev->caps.num_ports))
return;
/* IPv4 gids */
@@ -1607,7 +1636,7 @@
/*ifa->ifa_address;*/
ipv6_addr_set_v4mapped(ifa->ifa_address,
(struct in6_addr *)&gid);
- update_gid_table(ibdev, port, &gid, 0);
+ update_gid_table(ibdev, port, &gid, 0, 0);
}
endfor_ifa(in_dev);
in_dev_put(in_dev);
@@ -1619,7 +1648,7 @@
read_lock_bh(&in6_dev->lock);
list_for_each_entry(ifp, &in6_dev->addr_list, if_list) {
pgid = (union ib_gid *)&ifp->addr;
- update_gid_table(ibdev, port, pgid, 0);
+ update_gid_table(ibdev, port, pgid, 0, 0);
}
read_unlock_bh(&in6_dev->lock);
in6_dev_put(in6_dev);
@@ -1627,14 +1656,26 @@
#endif
}
+static void mlx4_ib_set_default_gid(struct mlx4_ib_dev *ibdev,
+ struct net_device *dev, u8 port)
+{
+ union ib_gid gid;
+ mlx4_make_default_gid(dev, &gid);
+ update_gid_table(ibdev, port, &gid, 0, 1);
+}
+
static int mlx4_ib_init_gid_table(struct mlx4_ib_dev *ibdev)
{
struct net_device *dev;
+ struct mlx4_ib_iboe *iboe = &ibdev->iboe;
+ int i;
- if (reset_gid_table(ibdev))
- return -1;
+ for (i = 1; i <= ibdev->num_ports; ++i)
+ if (reset_gid_table(ibdev, i))
+ return -1;
read_lock(&dev_base_lock);
+ spin_lock(&iboe->lock);
for_each_netdev(&init_net, dev) {
u8 port = mlx4_ib_get_dev_port(dev, ibdev);
@@ -1642,6 +1683,7 @@
mlx4_ib_get_dev_addr(dev, ibdev, port);
}
+ spin_unlock(&iboe->lock);
read_unlock(&dev_base_lock);
return 0;
@@ -1656,25 +1698,57 @@
spin_lock(&iboe->lock);
mlx4_foreach_ib_transport_port(port, ibdev->dev) {
+ enum ib_port_state port_state = IB_PORT_NOP;
struct net_device *old_master = iboe->masters[port - 1];
+ struct net_device *curr_netdev;
struct net_device *curr_master;
+
iboe->netdevs[port - 1] =
mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
+ if (iboe->netdevs[port - 1])
+ mlx4_ib_set_default_gid(ibdev,
+ iboe->netdevs[port - 1], port);
+ curr_netdev = iboe->netdevs[port - 1];
if (iboe->netdevs[port - 1] &&
netif_is_bond_slave(iboe->netdevs[port - 1])) {
- rtnl_lock();
iboe->masters[port - 1] = netdev_master_upper_dev_get(
iboe->netdevs[port - 1]);
- rtnl_unlock();
+ } else {
+ iboe->masters[port - 1] = NULL;
}
curr_master = iboe->masters[port - 1];
+ if (curr_netdev) {
+ port_state = (netif_running(curr_netdev) && netif_carrier_ok(curr_netdev)) ?
+ IB_PORT_ACTIVE : IB_PORT_DOWN;
+ mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
+ } else {
+ reset_gid_table(ibdev, port);
+ }
+ /* if using bonding/team and a slave port is down, we don't the bond IP
+ * based gids in the table since flows that select port by gid may get
+ * the down port.
+ */
+ if (curr_master && (port_state == IB_PORT_DOWN)) {
+ reset_gid_table(ibdev, port);
+ mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
+ }
/* if bonding is used it is possible that we add it to masters
- only after IP address is assigned to the net bonding
- interface */
- if (curr_master && (old_master != curr_master))
+ * only after IP address is assigned to the net bonding
+ * interface.
+ */
+ if (curr_master && (old_master != curr_master)) {
+ reset_gid_table(ibdev, port);
+ mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
mlx4_ib_get_dev_addr(curr_master, ibdev, port);
+ }
+
+ if (!curr_master && (old_master != curr_master)) {
+ reset_gid_table(ibdev, port);
+ mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
+ mlx4_ib_get_dev_addr(curr_netdev, ibdev, port);
+ }
}
spin_unlock(&iboe->lock);
@@ -1810,17 +1884,10 @@
int i, j;
int err;
struct mlx4_ib_iboe *iboe;
+ int ib_num_ports = 0;
pr_info_once("%s", mlx4_ib_version);
- mlx4_foreach_non_ib_transport_port(i, dev)
- num_ports++;
-
- if (mlx4_is_mfunc(dev) && num_ports) {
- dev_err(&dev->pdev->dev, "RoCE is not supported over SRIOV as yet\n");
- return NULL;
- }
-
num_ports = 0;
mlx4_foreach_ib_transport_port(i, dev)
num_ports++;
@@ -1985,10 +2052,14 @@
ibdev->counters[i] = -1;
}
+ mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
+ ib_num_ports++;
+
spin_lock_init(&ibdev->sm_lock);
mutex_init(&ibdev->cap_mask_mutex);
- if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) {
+ if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED &&
+ ib_num_ports) {
ibdev->steer_qpn_count = MLX4_IB_UC_MAX_NUM_QPS;
err = mlx4_qp_reserve_range(dev, ibdev->steer_qpn_count,
MLX4_IB_UC_STEER_QPN_ALIGN,
@@ -2051,7 +2122,11 @@
}
}
#endif
+ for (i = 1 ; i <= ibdev->num_ports ; ++i)
+ reset_gid_table(ibdev, i);
+ rtnl_lock();
mlx4_ib_scan_netdevs(ibdev);
+ rtnl_unlock();
mlx4_ib_init_gid_table(ibdev);
}
@@ -2248,17 +2323,24 @@
struct mlx4_dev *dev = ibdev->dev;
int i;
unsigned long flags;
+ struct mlx4_active_ports actv_ports;
+ unsigned int ports;
+ unsigned int first_port;
if (!mlx4_is_master(dev))
return;
- dm = kcalloc(dev->caps.num_ports, sizeof *dm, GFP_ATOMIC);
+ actv_ports = mlx4_get_active_ports(dev, slave);
+ ports = bitmap_weight(actv_ports.ports, dev->caps.num_ports);
+ first_port = find_first_bit(actv_ports.ports, dev->caps.num_ports);
+
+ dm = kcalloc(ports, sizeof(*dm), GFP_ATOMIC);
if (!dm) {
pr_err("failed to allocate memory for tunneling qp update\n");
goto out;
}
- for (i = 0; i < dev->caps.num_ports; i++) {
+ for (i = 0; i < ports; i++) {
dm[i] = kmalloc(sizeof (struct mlx4_ib_demux_work), GFP_ATOMIC);
if (!dm[i]) {
pr_err("failed to allocate memory for tunneling qp update work struct\n");
@@ -2270,9 +2352,9 @@
}
}
/* initialize or tear down tunnel QPs for the slave */
- for (i = 0; i < dev->caps.num_ports; i++) {
+ for (i = 0; i < ports; i++) {
INIT_WORK(&dm[i]->work, mlx4_ib_tunnels_update_work);
- dm[i]->port = i + 1;
+ dm[i]->port = first_port + i + 1;
dm[i]->slave = slave;
dm[i]->do_init = do_init;
dm[i]->dev = ibdev;
diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c
index 25b2cdf..ed327e6 100644
--- a/drivers/infiniband/hw/mlx4/mcg.c
+++ b/drivers/infiniband/hw/mlx4/mcg.c
@@ -215,8 +215,9 @@
}
mlx4_ib_query_ah(dev->sm_ah[ctx->port - 1], &ah_attr);
spin_unlock(&dev->sm_lock);
- return mlx4_ib_send_to_wire(dev, mlx4_master_func_num(dev->dev), ctx->port,
- IB_QPT_GSI, 0, 1, IB_QP1_QKEY, &ah_attr, mad);
+ return mlx4_ib_send_to_wire(dev, mlx4_master_func_num(dev->dev),
+ ctx->port, IB_QPT_GSI, 0, 1, IB_QP1_QKEY,
+ &ah_attr, NULL, mad);
}
static int send_mad_to_slave(int slave, struct mlx4_ib_demux_ctx *ctx,
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index a230683..f589522 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -241,6 +241,22 @@
struct mlx4_rcv_tunnel_hdr tun;
} __packed;
+struct mlx4_roce_smac_vlan_info {
+ u64 smac;
+ int smac_index;
+ int smac_port;
+ u64 candidate_smac;
+ int candidate_smac_index;
+ int candidate_smac_port;
+ u16 vid;
+ int vlan_index;
+ int vlan_port;
+ u16 candidate_vid;
+ int candidate_vlan_index;
+ int candidate_vlan_port;
+ int update_vid;
+};
+
struct mlx4_ib_qp {
struct ib_qp ibqp;
struct mlx4_qp mqp;
@@ -273,8 +289,9 @@
struct list_head gid_list;
struct list_head steering_rules;
struct mlx4_ib_buf *sqp_proxy_rcv;
+ struct mlx4_roce_smac_vlan_info pri;
+ struct mlx4_roce_smac_vlan_info alt;
u64 reg_id;
-
};
struct mlx4_ib_srq {
@@ -720,9 +737,12 @@
int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
enum ib_qp_type qpt, struct ib_wc *wc,
struct ib_grh *grh, struct ib_mad *mad);
+
int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
enum ib_qp_type dest_qpt, u16 pkey_index, u32 remote_qpn,
- u32 qkey, struct ib_ah_attr *attr, struct ib_mad *mad);
+ u32 qkey, struct ib_ah_attr *attr, u8 *s_mac,
+ struct ib_mad *mad);
+
__be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx);
int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index d8f4d1f..aadf7f8 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -662,10 +662,14 @@
if (!sqp)
return -ENOMEM;
qp = &sqp->qp;
+ qp->pri.vid = 0xFFFF;
+ qp->alt.vid = 0xFFFF;
} else {
qp = kzalloc(sizeof (struct mlx4_ib_qp), GFP_KERNEL);
if (!qp)
return -ENOMEM;
+ qp->pri.vid = 0xFFFF;
+ qp->alt.vid = 0xFFFF;
}
} else
qp = *caller_qp;
@@ -940,11 +944,32 @@
{
struct mlx4_ib_cq *send_cq, *recv_cq;
- if (qp->state != IB_QPS_RESET)
+ if (qp->state != IB_QPS_RESET) {
if (mlx4_qp_modify(dev->dev, NULL, to_mlx4_state(qp->state),
MLX4_QP_STATE_RST, NULL, 0, 0, &qp->mqp))
pr_warn("modify QP %06x to RESET failed.\n",
qp->mqp.qpn);
+ if (qp->pri.smac) {
+ mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac);
+ qp->pri.smac = 0;
+ }
+ if (qp->alt.smac) {
+ mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac);
+ qp->alt.smac = 0;
+ }
+ if (qp->pri.vid < 0x1000) {
+ mlx4_unregister_vlan(dev->dev, qp->pri.vlan_port, qp->pri.vid);
+ qp->pri.vid = 0xFFFF;
+ qp->pri.candidate_vid = 0xFFFF;
+ qp->pri.update_vid = 0;
+ }
+ if (qp->alt.vid < 0x1000) {
+ mlx4_unregister_vlan(dev->dev, qp->alt.vlan_port, qp->alt.vid);
+ qp->alt.vid = 0xFFFF;
+ qp->alt.candidate_vid = 0xFFFF;
+ qp->alt.update_vid = 0;
+ }
+ }
get_cqs(qp, &send_cq, &recv_cq);
@@ -1057,6 +1082,8 @@
qp = kzalloc(sizeof *qp, GFP_KERNEL);
if (!qp)
return ERR_PTR(-ENOMEM);
+ qp->pri.vid = 0xFFFF;
+ qp->alt.vid = 0xFFFF;
/* fall through */
case IB_QPT_UD:
{
@@ -1188,12 +1215,13 @@
static int _mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
u64 smac, u16 vlan_tag, struct mlx4_qp_path *path,
- u8 port)
+ struct mlx4_roce_smac_vlan_info *smac_info, u8 port)
{
int is_eth = rdma_port_get_link_layer(&dev->ib_dev, port) ==
IB_LINK_LAYER_ETHERNET;
int vidx;
int smac_index;
+ int err;
path->grh_mylmc = ah->src_path_bits & 0x7f;
@@ -1223,61 +1251,103 @@
}
if (is_eth) {
- path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
- ((port - 1) << 6) | ((ah->sl & 7) << 3);
-
if (!(ah->ah_flags & IB_AH_GRH))
return -1;
- memcpy(path->dmac, ah->dmac, ETH_ALEN);
- path->ackto = MLX4_IB_LINK_TYPE_ETH;
- /* find the index into MAC table for IBoE */
- if (!is_zero_ether_addr((const u8 *)&smac)) {
- if (mlx4_find_cached_mac(dev->dev, port, smac,
- &smac_index))
- return -ENOENT;
- } else {
- smac_index = 0;
- }
-
- path->grh_mylmc &= 0x80 | smac_index;
+ path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
+ ((port - 1) << 6) | ((ah->sl & 7) << 3);
path->feup |= MLX4_FEUP_FORCE_ETH_UP;
if (vlan_tag < 0x1000) {
- if (mlx4_find_cached_vlan(dev->dev, port, vlan_tag, &vidx))
- return -ENOENT;
-
- path->vlan_index = vidx;
- path->fl = 1 << 6;
+ if (smac_info->vid < 0x1000) {
+ /* both valid vlan ids */
+ if (smac_info->vid != vlan_tag) {
+ /* different VIDs. unreg old and reg new */
+ err = mlx4_register_vlan(dev->dev, port, vlan_tag, &vidx);
+ if (err)
+ return err;
+ smac_info->candidate_vid = vlan_tag;
+ smac_info->candidate_vlan_index = vidx;
+ smac_info->candidate_vlan_port = port;
+ smac_info->update_vid = 1;
+ path->vlan_index = vidx;
+ } else {
+ path->vlan_index = smac_info->vlan_index;
+ }
+ } else {
+ /* no current vlan tag in qp */
+ err = mlx4_register_vlan(dev->dev, port, vlan_tag, &vidx);
+ if (err)
+ return err;
+ smac_info->candidate_vid = vlan_tag;
+ smac_info->candidate_vlan_index = vidx;
+ smac_info->candidate_vlan_port = port;
+ smac_info->update_vid = 1;
+ path->vlan_index = vidx;
+ }
path->feup |= MLX4_FVL_FORCE_ETH_VLAN;
+ path->fl = 1 << 6;
+ } else {
+ /* have current vlan tag. unregister it at modify-qp success */
+ if (smac_info->vid < 0x1000) {
+ smac_info->candidate_vid = 0xFFFF;
+ smac_info->update_vid = 1;
+ }
}
- } else
+
+ /* get smac_index for RoCE use.
+ * If no smac was yet assigned, register one.
+ * If one was already assigned, but the new mac differs,
+ * unregister the old one and register the new one.
+ */
+ if (!smac_info->smac || smac_info->smac != smac) {
+ /* register candidate now, unreg if needed, after success */
+ smac_index = mlx4_register_mac(dev->dev, port, smac);
+ if (smac_index >= 0) {
+ smac_info->candidate_smac_index = smac_index;
+ smac_info->candidate_smac = smac;
+ smac_info->candidate_smac_port = port;
+ } else {
+ return -EINVAL;
+ }
+ } else {
+ smac_index = smac_info->smac_index;
+ }
+
+ memcpy(path->dmac, ah->dmac, 6);
+ path->ackto = MLX4_IB_LINK_TYPE_ETH;
+ /* put MAC table smac index for IBoE */
+ path->grh_mylmc = (u8) (smac_index) | 0x80;
+ } else {
path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
((port - 1) << 6) | ((ah->sl & 0xf) << 2);
+ }
return 0;
}
static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_qp_attr *qp,
enum ib_qp_attr_mask qp_attr_mask,
+ struct mlx4_ib_qp *mqp,
struct mlx4_qp_path *path, u8 port)
{
return _mlx4_set_path(dev, &qp->ah_attr,
mlx4_mac_to_u64((u8 *)qp->smac),
(qp_attr_mask & IB_QP_VID) ? qp->vlan_id : 0xffff,
- path, port);
+ path, &mqp->pri, port);
}
static int mlx4_set_alt_path(struct mlx4_ib_dev *dev,
const struct ib_qp_attr *qp,
enum ib_qp_attr_mask qp_attr_mask,
+ struct mlx4_ib_qp *mqp,
struct mlx4_qp_path *path, u8 port)
{
return _mlx4_set_path(dev, &qp->alt_ah_attr,
mlx4_mac_to_u64((u8 *)qp->alt_smac),
(qp_attr_mask & IB_QP_ALT_VID) ?
qp->alt_vlan_id : 0xffff,
- path, port);
+ path, &mqp->alt, port);
}
static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
@@ -1292,6 +1362,37 @@
}
}
+static int handle_eth_ud_smac_index(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, u8 *smac,
+ struct mlx4_qp_context *context)
+{
+ struct net_device *ndev;
+ u64 u64_mac;
+ int smac_index;
+
+
+ ndev = dev->iboe.netdevs[qp->port - 1];
+ if (ndev) {
+ smac = ndev->dev_addr;
+ u64_mac = mlx4_mac_to_u64(smac);
+ } else {
+ u64_mac = dev->dev->caps.def_mac[qp->port];
+ }
+
+ context->pri_path.sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE | ((qp->port - 1) << 6);
+ if (!qp->pri.smac) {
+ smac_index = mlx4_register_mac(dev->dev, qp->port, u64_mac);
+ if (smac_index >= 0) {
+ qp->pri.candidate_smac_index = smac_index;
+ qp->pri.candidate_smac = u64_mac;
+ qp->pri.candidate_smac_port = qp->port;
+ context->pri_path.grh_mylmc = 0x80 | (u8) smac_index;
+ } else {
+ return -ENOENT;
+ }
+ }
+ return 0;
+}
+
static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
const struct ib_qp_attr *attr, int attr_mask,
enum ib_qp_state cur_state, enum ib_qp_state new_state)
@@ -1403,7 +1504,7 @@
}
if (attr_mask & IB_QP_AV) {
- if (mlx4_set_path(dev, attr, attr_mask, &context->pri_path,
+ if (mlx4_set_path(dev, attr, attr_mask, qp, &context->pri_path,
attr_mask & IB_QP_PORT ?
attr->port_num : qp->port))
goto out;
@@ -1426,7 +1527,8 @@
dev->dev->caps.pkey_table_len[attr->alt_port_num])
goto out;
- if (mlx4_set_alt_path(dev, attr, attr_mask, &context->alt_path,
+ if (mlx4_set_alt_path(dev, attr, attr_mask, qp,
+ &context->alt_path,
attr->alt_port_num))
goto out;
@@ -1532,6 +1634,20 @@
context->pri_path.fl = 0x80;
context->pri_path.sched_queue |= MLX4_IB_DEFAULT_SCHED_QUEUE;
}
+ if (rdma_port_get_link_layer(&dev->ib_dev, qp->port) ==
+ IB_LINK_LAYER_ETHERNET) {
+ if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_TUN_GSI ||
+ qp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI)
+ context->pri_path.feup = 1 << 7; /* don't fsm */
+ /* handle smac_index */
+ if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_UD ||
+ qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI ||
+ qp->mlx4_ib_qp_type == MLX4_IB_QPT_TUN_GSI) {
+ err = handle_eth_ud_smac_index(dev, qp, (u8 *)attr->smac, context);
+ if (err)
+ return -EINVAL;
+ }
+ }
}
if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET)
@@ -1619,28 +1735,113 @@
* If we moved a kernel QP to RESET, clean up all old CQ
* entries and reinitialize the QP.
*/
- if (new_state == IB_QPS_RESET && !ibqp->uobject) {
- mlx4_ib_cq_clean(recv_cq, qp->mqp.qpn,
- ibqp->srq ? to_msrq(ibqp->srq): NULL);
- if (send_cq != recv_cq)
- mlx4_ib_cq_clean(send_cq, qp->mqp.qpn, NULL);
+ if (new_state == IB_QPS_RESET) {
+ if (!ibqp->uobject) {
+ mlx4_ib_cq_clean(recv_cq, qp->mqp.qpn,
+ ibqp->srq ? to_msrq(ibqp->srq) : NULL);
+ if (send_cq != recv_cq)
+ mlx4_ib_cq_clean(send_cq, qp->mqp.qpn, NULL);
- qp->rq.head = 0;
- qp->rq.tail = 0;
- qp->sq.head = 0;
- qp->sq.tail = 0;
- qp->sq_next_wqe = 0;
- if (qp->rq.wqe_cnt)
- *qp->db.db = 0;
+ qp->rq.head = 0;
+ qp->rq.tail = 0;
+ qp->sq.head = 0;
+ qp->sq.tail = 0;
+ qp->sq_next_wqe = 0;
+ if (qp->rq.wqe_cnt)
+ *qp->db.db = 0;
- if (qp->flags & MLX4_IB_QP_NETIF)
- mlx4_ib_steer_qp_reg(dev, qp, 0);
+ if (qp->flags & MLX4_IB_QP_NETIF)
+ mlx4_ib_steer_qp_reg(dev, qp, 0);
+ }
+ if (qp->pri.smac) {
+ mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac);
+ qp->pri.smac = 0;
+ }
+ if (qp->alt.smac) {
+ mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac);
+ qp->alt.smac = 0;
+ }
+ if (qp->pri.vid < 0x1000) {
+ mlx4_unregister_vlan(dev->dev, qp->pri.vlan_port, qp->pri.vid);
+ qp->pri.vid = 0xFFFF;
+ qp->pri.candidate_vid = 0xFFFF;
+ qp->pri.update_vid = 0;
+ }
+
+ if (qp->alt.vid < 0x1000) {
+ mlx4_unregister_vlan(dev->dev, qp->alt.vlan_port, qp->alt.vid);
+ qp->alt.vid = 0xFFFF;
+ qp->alt.candidate_vid = 0xFFFF;
+ qp->alt.update_vid = 0;
+ }
}
-
out:
if (err && steer_qp)
mlx4_ib_steer_qp_reg(dev, qp, 0);
kfree(context);
+ if (qp->pri.candidate_smac) {
+ if (err) {
+ mlx4_unregister_mac(dev->dev, qp->pri.candidate_smac_port, qp->pri.candidate_smac);
+ } else {
+ if (qp->pri.smac)
+ mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac);
+ qp->pri.smac = qp->pri.candidate_smac;
+ qp->pri.smac_index = qp->pri.candidate_smac_index;
+ qp->pri.smac_port = qp->pri.candidate_smac_port;
+ }
+ qp->pri.candidate_smac = 0;
+ qp->pri.candidate_smac_index = 0;
+ qp->pri.candidate_smac_port = 0;
+ }
+ if (qp->alt.candidate_smac) {
+ if (err) {
+ mlx4_unregister_mac(dev->dev, qp->alt.candidate_smac_port, qp->alt.candidate_smac);
+ } else {
+ if (qp->alt.smac)
+ mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac);
+ qp->alt.smac = qp->alt.candidate_smac;
+ qp->alt.smac_index = qp->alt.candidate_smac_index;
+ qp->alt.smac_port = qp->alt.candidate_smac_port;
+ }
+ qp->alt.candidate_smac = 0;
+ qp->alt.candidate_smac_index = 0;
+ qp->alt.candidate_smac_port = 0;
+ }
+
+ if (qp->pri.update_vid) {
+ if (err) {
+ if (qp->pri.candidate_vid < 0x1000)
+ mlx4_unregister_vlan(dev->dev, qp->pri.candidate_vlan_port,
+ qp->pri.candidate_vid);
+ } else {
+ if (qp->pri.vid < 0x1000)
+ mlx4_unregister_vlan(dev->dev, qp->pri.vlan_port,
+ qp->pri.vid);
+ qp->pri.vid = qp->pri.candidate_vid;
+ qp->pri.vlan_port = qp->pri.candidate_vlan_port;
+ qp->pri.vlan_index = qp->pri.candidate_vlan_index;
+ }
+ qp->pri.candidate_vid = 0xFFFF;
+ qp->pri.update_vid = 0;
+ }
+
+ if (qp->alt.update_vid) {
+ if (err) {
+ if (qp->alt.candidate_vid < 0x1000)
+ mlx4_unregister_vlan(dev->dev, qp->alt.candidate_vlan_port,
+ qp->alt.candidate_vid);
+ } else {
+ if (qp->alt.vid < 0x1000)
+ mlx4_unregister_vlan(dev->dev, qp->alt.vlan_port,
+ qp->alt.vid);
+ qp->alt.vid = qp->alt.candidate_vid;
+ qp->alt.vlan_port = qp->alt.candidate_vlan_port;
+ qp->alt.vlan_index = qp->alt.candidate_vlan_index;
+ }
+ qp->alt.candidate_vid = 0xFFFF;
+ qp->alt.update_vid = 0;
+ }
+
return err;
}
@@ -1842,9 +2043,9 @@
{
struct ib_device *ib_dev = sqp->qp.ibqp.device;
struct mlx4_wqe_mlx_seg *mlx = wqe;
+ struct mlx4_wqe_ctrl_seg *ctrl = wqe;
struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx;
struct mlx4_ib_ah *ah = to_mah(wr->wr.ud.ah);
- struct net_device *ndev;
union ib_gid sgid;
u16 pkey;
int send_size;
@@ -1868,12 +2069,11 @@
/* When multi-function is enabled, the ib_core gid
* indexes don't necessarily match the hw ones, so
* we must use our own cache */
- sgid.global.subnet_prefix =
- to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
- subnet_prefix;
- sgid.global.interface_id =
- to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
- guid_cache[ah->av.ib.gid_index];
+ err = mlx4_get_roce_gid_from_slave(to_mdev(ib_dev)->dev,
+ be32_to_cpu(ah->av.ib.port_pd) >> 24,
+ ah->av.ib.gid_index, &sgid.raw[0]);
+ if (err)
+ return err;
} else {
err = ib_get_cached_gid(ib_dev,
be32_to_cpu(ah->av.ib.port_pd) >> 24,
@@ -1902,6 +2102,9 @@
sqp->ud_header.grh.flow_label =
ah->av.ib.sl_tclass_flowlabel & cpu_to_be32(0xfffff);
sqp->ud_header.grh.hop_limit = ah->av.ib.hop_limit;
+ if (is_eth)
+ memcpy(sqp->ud_header.grh.source_gid.raw, sgid.raw, 16);
+ else {
if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
/* When multi-function is enabled, the ib_core gid
* indexes don't necessarily match the hw ones, so
@@ -1917,6 +2120,7 @@
be32_to_cpu(ah->av.ib.port_pd) >> 24,
ah->av.ib.gid_index,
&sqp->ud_header.grh.source_gid);
+ }
memcpy(sqp->ud_header.grh.destination_gid.raw,
ah->av.ib.dgid, 16);
}
@@ -1949,16 +2153,23 @@
if (is_eth) {
u8 *smac;
+ struct in6_addr in6;
+
u16 pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 29) << 13;
mlx->sched_prio = cpu_to_be16(pcp);
memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6);
/* FIXME: cache smac value? */
- ndev = to_mdev(sqp->qp.ibqp.device)->iboe.netdevs[sqp->qp.port - 1];
- if (!ndev)
- return -ENODEV;
- smac = ndev->dev_addr;
+ memcpy(&ctrl->srcrb_flags16[0], ah->av.eth.mac, 2);
+ memcpy(&ctrl->imm, ah->av.eth.mac + 2, 4);
+ memcpy(&in6, sgid.raw, sizeof(in6));
+
+ if (!mlx4_is_mfunc(to_mdev(ib_dev)->dev))
+ smac = to_mdev(sqp->qp.ibqp.device)->
+ iboe.netdevs[sqp->qp.port - 1]->dev_addr;
+ else /* use the src mac of the tunnel */
+ smac = ah->av.eth.s_mac;
memcpy(sqp->ud_header.eth.smac_h, smac, 6);
if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6))
mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK);
@@ -2190,6 +2401,8 @@
hdr.remote_qpn = cpu_to_be32(wr->wr.ud.remote_qpn);
hdr.pkey_index = cpu_to_be16(wr->wr.ud.pkey_index);
hdr.qkey = cpu_to_be32(wr->wr.ud.remote_qkey);
+ memcpy(hdr.mac, ah->av.eth.mac, 6);
+ hdr.vlan = ah->av.eth.vlan;
spc = MLX4_INLINE_ALIGN -
((unsigned long) (inl + 1) & (MLX4_INLINE_ALIGN - 1));
diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c
index db2ea31..5a38e43 100644
--- a/drivers/infiniband/hw/mlx4/sysfs.c
+++ b/drivers/infiniband/hw/mlx4/sysfs.c
@@ -627,6 +627,7 @@
int port;
struct kobject *p, *t;
struct mlx4_port *mport;
+ struct mlx4_active_ports actv_ports;
get_name(dev, name, slave, sizeof name);
@@ -649,7 +650,11 @@
goto err_ports;
}
+ actv_ports = mlx4_get_active_ports(dev->dev, slave);
+
for (port = 1; port <= dev->dev->caps.num_ports; ++port) {
+ if (!test_bit(port - 1, actv_ports.ports))
+ continue;
err = add_port(dev, port, slave);
if (err)
goto err_add;
diff --git a/drivers/infiniband/hw/mlx5/Kconfig b/drivers/infiniband/hw/mlx5/Kconfig
index 8e6aebf..10df386 100644
--- a/drivers/infiniband/hw/mlx5/Kconfig
+++ b/drivers/infiniband/hw/mlx5/Kconfig
@@ -1,6 +1,6 @@
config MLX5_INFINIBAND
tristate "Mellanox Connect-IB HCA support"
- depends on NETDEVICES && ETHERNET && PCI && X86
+ depends on NETDEVICES && ETHERNET && PCI
select NET_VENDOR_MELLANOX
select MLX5_CORE
---help---
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 9660d09..bf90057 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -46,8 +46,8 @@
#include "mlx5_ib.h"
#define DRIVER_NAME "mlx5_ib"
-#define DRIVER_VERSION "1.0"
-#define DRIVER_RELDATE "June 2013"
+#define DRIVER_VERSION "2.2-1"
+#define DRIVER_RELDATE "Feb 2014"
MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
MODULE_DESCRIPTION("Mellanox Connect-IB HCA IB driver");
@@ -261,8 +261,7 @@
props->device_cap_flags = IB_DEVICE_CHANGE_PHY_PORT |
IB_DEVICE_PORT_ACTIVE_EVENT |
IB_DEVICE_SYS_IMAGE_GUID |
- IB_DEVICE_RC_RNR_NAK_GEN |
- IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
+ IB_DEVICE_RC_RNR_NAK_GEN;
flags = dev->mdev.caps.flags;
if (flags & MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR)
props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR;
@@ -536,24 +535,38 @@
struct ib_udata *udata)
{
struct mlx5_ib_dev *dev = to_mdev(ibdev);
- struct mlx5_ib_alloc_ucontext_req req;
+ struct mlx5_ib_alloc_ucontext_req_v2 req;
struct mlx5_ib_alloc_ucontext_resp resp;
struct mlx5_ib_ucontext *context;
struct mlx5_uuar_info *uuari;
struct mlx5_uar *uars;
int gross_uuars;
int num_uars;
+ int ver;
int uuarn;
int err;
int i;
+ int reqlen;
if (!dev->ib_active)
return ERR_PTR(-EAGAIN);
- err = ib_copy_from_udata(&req, udata, sizeof(req));
+ memset(&req, 0, sizeof(req));
+ reqlen = udata->inlen - sizeof(struct ib_uverbs_cmd_hdr);
+ if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req))
+ ver = 0;
+ else if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req_v2))
+ ver = 2;
+ else
+ return ERR_PTR(-EINVAL);
+
+ err = ib_copy_from_udata(&req, udata, reqlen);
if (err)
return ERR_PTR(err);
+ if (req.flags || req.reserved)
+ return ERR_PTR(-EINVAL);
+
if (req.total_num_uuars > MLX5_MAX_UUARS)
return ERR_PTR(-ENOMEM);
@@ -626,6 +639,7 @@
if (err)
goto out_uars;
+ uuari->ver = ver;
uuari->num_low_latency_uuars = req.num_low_latency_uuars;
uuari->uars = uars;
uuari->num_uars = num_uars;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index ae37fb9..7dfe8a1 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -216,7 +216,9 @@
case IB_QPT_UC:
size += sizeof(struct mlx5_wqe_ctrl_seg) +
- sizeof(struct mlx5_wqe_raddr_seg);
+ sizeof(struct mlx5_wqe_raddr_seg) +
+ sizeof(struct mlx5_wqe_umr_ctrl_seg) +
+ sizeof(struct mlx5_mkey_seg);
break;
case IB_QPT_UD:
@@ -428,11 +430,17 @@
break;
case MLX5_IB_LATENCY_CLASS_MEDIUM:
- uuarn = alloc_med_class_uuar(uuari);
+ if (uuari->ver < 2)
+ uuarn = -ENOMEM;
+ else
+ uuarn = alloc_med_class_uuar(uuari);
break;
case MLX5_IB_LATENCY_CLASS_HIGH:
- uuarn = alloc_high_class_uuar(uuari);
+ if (uuari->ver < 2)
+ uuarn = -ENOMEM;
+ else
+ uuarn = alloc_high_class_uuar(uuari);
break;
case MLX5_IB_LATENCY_CLASS_FAST_PATH:
@@ -657,8 +665,8 @@
int err;
uuari = &dev->mdev.priv.uuari;
- if (init_attr->create_flags & IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK)
- qp->flags |= MLX5_IB_QP_BLOCK_MULTICAST_LOOPBACK;
+ if (init_attr->create_flags)
+ return -EINVAL;
if (init_attr->qp_type == MLX5_IB_QPT_REG_UMR)
lc = MLX5_IB_LATENCY_CLASS_FAST_PATH;
diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h
index 32a2a5d..0f4f8e4 100644
--- a/drivers/infiniband/hw/mlx5/user.h
+++ b/drivers/infiniband/hw/mlx5/user.h
@@ -62,6 +62,13 @@
__u32 num_low_latency_uuars;
};
+struct mlx5_ib_alloc_ucontext_req_v2 {
+ __u32 total_num_uuars;
+ __u32 num_low_latency_uuars;
+ __u32 flags;
+ __u32 reserved;
+};
+
struct mlx5_ib_alloc_ucontext_resp {
__u32 qp_tab_size;
__u32 bf_reg_size;
diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c
index 4291410..353c7b0 100644
--- a/drivers/infiniband/hw/nes/nes.c
+++ b/drivers/infiniband/hw/nes/nes.c
@@ -675,8 +675,11 @@
INIT_DELAYED_WORK(&nesdev->work, nes_recheck_link_status);
/* Initialize network devices */
- if ((netdev = nes_netdev_init(nesdev, mmio_regs)) == NULL)
+ netdev = nes_netdev_init(nesdev, mmio_regs);
+ if (netdev == NULL) {
+ ret = -ENOMEM;
goto bail7;
+ }
/* Register network device */
ret = register_netdev(netdev);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 2ca86ca..1a8a945 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -127,7 +127,7 @@
is_vlan = netdev->priv_flags & IFF_802_1Q_VLAN;
if (is_vlan)
- netdev = vlan_dev_real_dev(netdev);
+ netdev = rdma_vlan_dev_real_dev(netdev);
rcu_read_lock();
list_for_each_entry_rcu(dev, &ocrdma_dev_list, entry) {
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index aa92f40..e0cc201 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -176,7 +176,7 @@
props->port_cap_flags =
IB_PORT_CM_SUP |
IB_PORT_REINIT_SUP |
- IB_PORT_DEVICE_MGMT_SUP | IB_PORT_VENDOR_CLASS_SUP;
+ IB_PORT_DEVICE_MGMT_SUP | IB_PORT_VENDOR_CLASS_SUP | IB_PORT_IP_BASED_GIDS;
props->gid_tbl_len = OCRDMA_MAX_SGID;
props->pkey_tbl_len = 1;
props->bad_pkey_cntr = 0;
@@ -1416,7 +1416,7 @@
OCRDMA_QP_PARAMS_HOP_LMT_MASK) >>
OCRDMA_QP_PARAMS_HOP_LMT_SHIFT;
qp_attr->ah_attr.grh.traffic_class = (params.tclass_sq_psn &
- OCRDMA_QP_PARAMS_SQ_PSN_MASK) >>
+ OCRDMA_QP_PARAMS_TCLASS_MASK) >>
OCRDMA_QP_PARAMS_TCLASS_SHIFT;
qp_attr->ah_attr.ah_flags = IB_AH_GRH;
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 5bfc02f..d1bd213 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -2395,6 +2395,11 @@
qib_write_kreg_port(ppd, krp_ibcctrl_a, ppd->cpspec->ibcctrl_a);
qib_write_kreg(dd, kr_scratch, 0ULL);
+ /* ensure previous Tx parameters are not still forced */
+ qib_write_kreg_port(ppd, krp_tx_deemph_override,
+ SYM_MASK(IBSD_TX_DEEMPHASIS_OVERRIDE_0,
+ reset_tx_deemphasis_override));
+
if (qib_compat_ddr_negotiate) {
ppd->cpspec->ibdeltainprog = 1;
ppd->cpspec->ibsymsnap = read_7322_creg32_port(ppd,
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c
index 7ecc606..f8dfd76 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c
@@ -629,6 +629,7 @@
{
enum usnic_transport_type trans_type = qp_flow->trans_type;
int err;
+ uint16_t port_num = 0;
switch (trans_type) {
case USNIC_TRANSPORT_ROCE_CUSTOM:
@@ -637,9 +638,15 @@
case USNIC_TRANSPORT_IPV4_UDP:
err = usnic_transport_sock_get_addr(qp_flow->udp.sock,
NULL, NULL,
- (uint16_t *) id);
+ &port_num);
if (err)
return err;
+ /*
+ * Copy port_num to stack first and then to *id,
+ * so that the short to int cast works for little
+ * and big endian systems.
+ */
+ *id = port_num;
break;
default:
usnic_err("Unsupported transport %u\n", trans_type);
diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c
index 5388226..334f34b 100644
--- a/drivers/infiniband/ulp/iser/iser_initiator.c
+++ b/drivers/infiniband/ulp/iser/iser_initiator.c
@@ -610,11 +610,12 @@
ib_dma_unmap_single(device->ib_device, tx_desc->dma_addr,
ISER_HEADERS_LEN, DMA_TO_DEVICE);
kmem_cache_free(ig.desc_cache, tx_desc);
+ tx_desc = NULL;
}
atomic_dec(&ib_conn->post_send_buf_count);
- if (tx_desc->type == ISCSI_TX_CONTROL) {
+ if (tx_desc && tx_desc->type == ISCSI_TX_CONTROL) {
/* this arithmetic is legal by libiscsi dd_data allocation */
task = (void *) ((long)(void *)tx_desc -
sizeof(struct iscsi_task));
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index afe9567..ca37ede 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -652,9 +652,13 @@
/* getting here when the state is UP means that the conn is being *
* terminated asynchronously from the iSCSI layer's perspective. */
if (iser_conn_state_comp_exch(ib_conn, ISER_CONN_UP,
- ISER_CONN_TERMINATING))
- iscsi_conn_failure(ib_conn->iser_conn->iscsi_conn,
- ISCSI_ERR_CONN_FAILED);
+ ISER_CONN_TERMINATING)){
+ if (ib_conn->iser_conn)
+ iscsi_conn_failure(ib_conn->iser_conn->iscsi_conn,
+ ISCSI_ERR_CONN_FAILED);
+ else
+ iser_err("iscsi_iser connection isn't bound\n");
+ }
/* Complete the termination process if no posts are pending */
if (ib_conn->post_recv_buf_count == 0 &&
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 2b161be..8ee228e 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -453,6 +453,7 @@
if (ret) {
pr_err("Failed to create fastreg descriptor err=%d\n",
ret);
+ kfree(fr_desc);
goto err;
}
@@ -491,12 +492,11 @@
isert_conn->state = ISER_CONN_INIT;
INIT_LIST_HEAD(&isert_conn->conn_accept_node);
init_completion(&isert_conn->conn_login_comp);
- init_waitqueue_head(&isert_conn->conn_wait);
- init_waitqueue_head(&isert_conn->conn_wait_comp_err);
+ init_completion(&isert_conn->conn_wait);
+ init_completion(&isert_conn->conn_wait_comp_err);
kref_init(&isert_conn->conn_kref);
kref_get(&isert_conn->conn_kref);
mutex_init(&isert_conn->conn_mutex);
- mutex_init(&isert_conn->conn_comp_mutex);
spin_lock_init(&isert_conn->conn_lock);
cma_id->context = isert_conn;
@@ -687,11 +687,11 @@
pr_debug("isert_disconnect_work(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
mutex_lock(&isert_conn->conn_mutex);
- isert_conn->state = ISER_CONN_DOWN;
+ if (isert_conn->state == ISER_CONN_UP)
+ isert_conn->state = ISER_CONN_TERMINATING;
if (isert_conn->post_recv_buf_count == 0 &&
atomic_read(&isert_conn->post_send_buf_count) == 0) {
- pr_debug("Calling wake_up(&isert_conn->conn_wait);\n");
mutex_unlock(&isert_conn->conn_mutex);
goto wake_up;
}
@@ -711,7 +711,7 @@
mutex_unlock(&isert_conn->conn_mutex);
wake_up:
- wake_up(&isert_conn->conn_wait);
+ complete(&isert_conn->conn_wait);
isert_put_conn(isert_conn);
}
@@ -887,16 +887,17 @@
* Coalesce send completion interrupts by only setting IB_SEND_SIGNALED
* bit for every ISERT_COMP_BATCH_COUNT number of ib_post_send() calls.
*/
- mutex_lock(&isert_conn->conn_comp_mutex);
- if (coalesce &&
+ mutex_lock(&isert_conn->conn_mutex);
+ if (coalesce && isert_conn->state == ISER_CONN_UP &&
++isert_conn->conn_comp_batch < ISERT_COMP_BATCH_COUNT) {
+ tx_desc->llnode_active = true;
llist_add(&tx_desc->comp_llnode, &isert_conn->conn_comp_llist);
- mutex_unlock(&isert_conn->conn_comp_mutex);
+ mutex_unlock(&isert_conn->conn_mutex);
return;
}
isert_conn->conn_comp_batch = 0;
tx_desc->comp_llnode_batch = llist_del_all(&isert_conn->conn_comp_llist);
- mutex_unlock(&isert_conn->conn_comp_mutex);
+ mutex_unlock(&isert_conn->conn_mutex);
send_wr->send_flags = IB_SEND_SIGNALED;
}
@@ -1463,7 +1464,7 @@
case ISCSI_OP_SCSI_CMD:
spin_lock_bh(&conn->cmd_lock);
if (!list_empty(&cmd->i_conn_node))
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
if (cmd->data_direction == DMA_TO_DEVICE)
@@ -1475,7 +1476,7 @@
case ISCSI_OP_SCSI_TMFUNC:
spin_lock_bh(&conn->cmd_lock);
if (!list_empty(&cmd->i_conn_node))
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
transport_generic_free_cmd(&cmd->se_cmd, 0);
@@ -1485,7 +1486,7 @@
case ISCSI_OP_TEXT:
spin_lock_bh(&conn->cmd_lock);
if (!list_empty(&cmd->i_conn_node))
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
/*
@@ -1548,6 +1549,7 @@
iscsit_stop_dataout_timer(cmd);
device->unreg_rdma_mem(isert_cmd, isert_conn);
cmd->write_data_done = wr->cur_rdma_length;
+ wr->send_wr_num = 0;
pr_debug("Cmd: %p RDMA_READ comp calling execute_cmd\n", isert_cmd);
spin_lock_bh(&cmd->istate_lock);
@@ -1588,7 +1590,7 @@
pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n");
/*
* Call atomic_dec(&isert_conn->post_send_buf_count)
- * from isert_free_conn()
+ * from isert_wait_conn()
*/
isert_conn->logout_posted = true;
iscsit_logout_post_handler(cmd, cmd->conn);
@@ -1612,6 +1614,7 @@
struct ib_device *ib_dev)
{
struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd;
+ struct isert_rdma_wr *wr = &isert_cmd->rdma_wr;
if (cmd->i_state == ISTATE_SEND_TASKMGTRSP ||
cmd->i_state == ISTATE_SEND_LOGOUTRSP ||
@@ -1623,7 +1626,7 @@
queue_work(isert_comp_wq, &isert_cmd->comp_work);
return;
}
- atomic_dec(&isert_conn->post_send_buf_count);
+ atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
cmd->i_state = ISTATE_SENT_STATUS;
isert_completion_put(tx_desc, isert_cmd, ib_dev);
@@ -1661,7 +1664,7 @@
case ISER_IB_RDMA_READ:
pr_debug("isert_send_completion: Got ISER_IB_RDMA_READ:\n");
- atomic_dec(&isert_conn->post_send_buf_count);
+ atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count);
isert_completion_rdma_read(tx_desc, isert_cmd);
break;
default:
@@ -1690,31 +1693,76 @@
}
static void
-isert_cq_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn)
+isert_cq_drain_comp_llist(struct isert_conn *isert_conn, struct ib_device *ib_dev)
+{
+ struct llist_node *llnode;
+ struct isert_rdma_wr *wr;
+ struct iser_tx_desc *t;
+
+ mutex_lock(&isert_conn->conn_mutex);
+ llnode = llist_del_all(&isert_conn->conn_comp_llist);
+ isert_conn->conn_comp_batch = 0;
+ mutex_unlock(&isert_conn->conn_mutex);
+
+ while (llnode) {
+ t = llist_entry(llnode, struct iser_tx_desc, comp_llnode);
+ llnode = llist_next(llnode);
+ wr = &t->isert_cmd->rdma_wr;
+
+ atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
+ isert_completion_put(t, t->isert_cmd, ib_dev);
+ }
+}
+
+static void
+isert_cq_tx_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn)
{
struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+ struct isert_cmd *isert_cmd = tx_desc->isert_cmd;
+ struct llist_node *llnode = tx_desc->comp_llnode_batch;
+ struct isert_rdma_wr *wr;
+ struct iser_tx_desc *t;
- if (tx_desc) {
- struct isert_cmd *isert_cmd = tx_desc->isert_cmd;
+ while (llnode) {
+ t = llist_entry(llnode, struct iser_tx_desc, comp_llnode);
+ llnode = llist_next(llnode);
+ wr = &t->isert_cmd->rdma_wr;
- if (!isert_cmd)
- isert_unmap_tx_desc(tx_desc, ib_dev);
- else
- isert_completion_put(tx_desc, isert_cmd, ib_dev);
+ atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
+ isert_completion_put(t, t->isert_cmd, ib_dev);
+ }
+ tx_desc->comp_llnode_batch = NULL;
+
+ if (!isert_cmd)
+ isert_unmap_tx_desc(tx_desc, ib_dev);
+ else
+ isert_completion_put(tx_desc, isert_cmd, ib_dev);
+}
+
+static void
+isert_cq_rx_comp_err(struct isert_conn *isert_conn)
+{
+ struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+ struct iscsi_conn *conn = isert_conn->conn;
+
+ if (isert_conn->post_recv_buf_count)
+ return;
+
+ isert_cq_drain_comp_llist(isert_conn, ib_dev);
+
+ if (conn->sess) {
+ target_sess_cmd_list_set_waiting(conn->sess->se_sess);
+ target_wait_for_sess_cmds(conn->sess->se_sess);
}
- if (isert_conn->post_recv_buf_count == 0 &&
- atomic_read(&isert_conn->post_send_buf_count) == 0) {
- pr_debug("isert_cq_comp_err >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
- pr_debug("Calling wake_up from isert_cq_comp_err\n");
+ while (atomic_read(&isert_conn->post_send_buf_count))
+ msleep(3000);
- mutex_lock(&isert_conn->conn_mutex);
- if (isert_conn->state != ISER_CONN_DOWN)
- isert_conn->state = ISER_CONN_TERMINATING;
- mutex_unlock(&isert_conn->conn_mutex);
+ mutex_lock(&isert_conn->conn_mutex);
+ isert_conn->state = ISER_CONN_DOWN;
+ mutex_unlock(&isert_conn->conn_mutex);
- wake_up(&isert_conn->conn_wait_comp_err);
- }
+ complete(&isert_conn->conn_wait_comp_err);
}
static void
@@ -1739,8 +1787,14 @@
pr_debug("TX wc.status != IB_WC_SUCCESS >>>>>>>>>>>>>>\n");
pr_debug("TX wc.status: 0x%08x\n", wc.status);
pr_debug("TX wc.vendor_err: 0x%08x\n", wc.vendor_err);
- atomic_dec(&isert_conn->post_send_buf_count);
- isert_cq_comp_err(tx_desc, isert_conn);
+
+ if (wc.wr_id != ISER_FASTREG_LI_WRID) {
+ if (tx_desc->llnode_active)
+ continue;
+
+ atomic_dec(&isert_conn->post_send_buf_count);
+ isert_cq_tx_comp_err(tx_desc, isert_conn);
+ }
}
}
@@ -1783,7 +1837,7 @@
wc.vendor_err);
}
isert_conn->post_recv_buf_count--;
- isert_cq_comp_err(NULL, isert_conn);
+ isert_cq_rx_comp_err(isert_conn);
}
}
@@ -2201,6 +2255,7 @@
if (!fr_desc->valid) {
memset(&inv_wr, 0, sizeof(inv_wr));
+ inv_wr.wr_id = ISER_FASTREG_LI_WRID;
inv_wr.opcode = IB_WR_LOCAL_INV;
inv_wr.ex.invalidate_rkey = fr_desc->data_mr->rkey;
wr = &inv_wr;
@@ -2211,6 +2266,7 @@
/* Prepare FASTREG WR */
memset(&fr_wr, 0, sizeof(fr_wr));
+ fr_wr.wr_id = ISER_FASTREG_LI_WRID;
fr_wr.opcode = IB_WR_FAST_REG_MR;
fr_wr.wr.fast_reg.iova_start =
fr_desc->data_frpl->page_list[0] + page_off;
@@ -2376,12 +2432,12 @@
isert_init_send_wr(isert_conn, isert_cmd,
&isert_cmd->tx_desc.send_wr, true);
- atomic_inc(&isert_conn->post_send_buf_count);
+ atomic_add(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed);
if (rc) {
pr_warn("ib_post_send() failed for IB_WR_RDMA_WRITE\n");
- atomic_dec(&isert_conn->post_send_buf_count);
+ atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
}
pr_debug("Cmd: %p posted RDMA_WRITE + Response for iSER Data READ\n",
isert_cmd);
@@ -2409,12 +2465,12 @@
return rc;
}
- atomic_inc(&isert_conn->post_send_buf_count);
+ atomic_add(wr->send_wr_num, &isert_conn->post_send_buf_count);
rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed);
if (rc) {
pr_warn("ib_post_send() failed for IB_WR_RDMA_READ\n");
- atomic_dec(&isert_conn->post_send_buf_count);
+ atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count);
}
pr_debug("Cmd: %p posted RDMA_READ memory for ISER Data WRITE\n",
isert_cmd);
@@ -2701,22 +2757,11 @@
kfree(isert_np);
}
-static int isert_check_state(struct isert_conn *isert_conn, int state)
-{
- int ret;
-
- mutex_lock(&isert_conn->conn_mutex);
- ret = (isert_conn->state == state);
- mutex_unlock(&isert_conn->conn_mutex);
-
- return ret;
-}
-
-static void isert_free_conn(struct iscsi_conn *conn)
+static void isert_wait_conn(struct iscsi_conn *conn)
{
struct isert_conn *isert_conn = conn->context;
- pr_debug("isert_free_conn: Starting \n");
+ pr_debug("isert_wait_conn: Starting \n");
/*
* Decrement post_send_buf_count for special case when called
* from isert_do_control_comp() -> iscsit_logout_post_handler()
@@ -2726,38 +2771,29 @@
atomic_dec(&isert_conn->post_send_buf_count);
if (isert_conn->conn_cm_id && isert_conn->state != ISER_CONN_DOWN) {
- pr_debug("Calling rdma_disconnect from isert_free_conn\n");
+ pr_debug("Calling rdma_disconnect from isert_wait_conn\n");
rdma_disconnect(isert_conn->conn_cm_id);
}
/*
* Only wait for conn_wait_comp_err if the isert_conn made it
* into full feature phase..
*/
- if (isert_conn->state == ISER_CONN_UP) {
- pr_debug("isert_free_conn: Before wait_event comp_err %d\n",
- isert_conn->state);
- mutex_unlock(&isert_conn->conn_mutex);
-
- wait_event(isert_conn->conn_wait_comp_err,
- (isert_check_state(isert_conn, ISER_CONN_TERMINATING)));
-
- wait_event(isert_conn->conn_wait,
- (isert_check_state(isert_conn, ISER_CONN_DOWN)));
-
- isert_put_conn(isert_conn);
- return;
- }
if (isert_conn->state == ISER_CONN_INIT) {
mutex_unlock(&isert_conn->conn_mutex);
- isert_put_conn(isert_conn);
return;
}
- pr_debug("isert_free_conn: wait_event conn_wait %d\n",
- isert_conn->state);
+ if (isert_conn->state == ISER_CONN_UP)
+ isert_conn->state = ISER_CONN_TERMINATING;
mutex_unlock(&isert_conn->conn_mutex);
- wait_event(isert_conn->conn_wait,
- (isert_check_state(isert_conn, ISER_CONN_DOWN)));
+ wait_for_completion(&isert_conn->conn_wait_comp_err);
+
+ wait_for_completion(&isert_conn->conn_wait);
+}
+
+static void isert_free_conn(struct iscsi_conn *conn)
+{
+ struct isert_conn *isert_conn = conn->context;
isert_put_conn(isert_conn);
}
@@ -2770,6 +2806,7 @@
.iscsit_setup_np = isert_setup_np,
.iscsit_accept_np = isert_accept_np,
.iscsit_free_np = isert_free_np,
+ .iscsit_wait_conn = isert_wait_conn,
.iscsit_free_conn = isert_free_conn,
.iscsit_get_login_rx = isert_get_login_rx,
.iscsit_put_login_tx = isert_put_login_tx,
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 708a069..f6ae7f5 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -6,6 +6,7 @@
#define ISERT_RDMA_LISTEN_BACKLOG 10
#define ISCSI_ISER_SG_TABLESIZE 256
+#define ISER_FASTREG_LI_WRID 0xffffffffffffffffULL
enum isert_desc_type {
ISCSI_TX_CONTROL,
@@ -45,6 +46,7 @@
struct isert_cmd *isert_cmd;
struct llist_node *comp_llnode_batch;
struct llist_node comp_llnode;
+ bool llnode_active;
struct ib_send_wr send_wr;
} __packed;
@@ -116,8 +118,8 @@
struct isert_device *conn_device;
struct work_struct conn_logout_work;
struct mutex conn_mutex;
- wait_queue_head_t conn_wait;
- wait_queue_head_t conn_wait_comp_err;
+ struct completion conn_wait;
+ struct completion conn_wait_comp_err;
struct kref conn_kref;
struct list_head conn_fr_pool;
int conn_fr_pool_size;
@@ -126,7 +128,6 @@
#define ISERT_COMP_BATCH_COUNT 8
int conn_comp_batch;
struct llist_head conn_comp_llist;
- struct mutex conn_comp_mutex;
};
#define ISERT_MAX_CQ 64
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 520a7e5..0e537d8 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -3666,9 +3666,9 @@
unsigned long val;
int ret;
- ret = strict_strtoul(page, 0, &val);
+ ret = kstrtoul(page, 0, &val);
if (ret < 0) {
- pr_err("strict_strtoul() failed with ret: %d\n", ret);
+ pr_err("kstrtoul() failed with ret: %d\n", ret);
return -EINVAL;
}
if (val > MAX_SRPT_RDMA_SIZE) {
@@ -3706,9 +3706,9 @@
unsigned long val;
int ret;
- ret = strict_strtoul(page, 0, &val);
+ ret = kstrtoul(page, 0, &val);
if (ret < 0) {
- pr_err("strict_strtoul() failed with ret: %d\n", ret);
+ pr_err("kstrtoul() failed with ret: %d\n", ret);
return -EINVAL;
}
if (val > MAX_SRPT_RSP_SIZE) {
@@ -3746,9 +3746,9 @@
unsigned long val;
int ret;
- ret = strict_strtoul(page, 0, &val);
+ ret = kstrtoul(page, 0, &val);
if (ret < 0) {
- pr_err("strict_strtoul() failed with ret: %d\n", ret);
+ pr_err("kstrtoul() failed with ret: %d\n", ret);
return -EINVAL;
}
if (val > MAX_SRPT_SRQ_SIZE) {
@@ -3793,7 +3793,7 @@
unsigned long tmp;
int ret;
- ret = strict_strtoul(page, 0, &tmp);
+ ret = kstrtoul(page, 0, &tmp);
if (ret < 0) {
printk(KERN_ERR "Unable to extract srpt_tpg_store_enable\n");
return -EINVAL;
diff --git a/drivers/input/keyboard/adp5588-keys.c b/drivers/input/keyboard/adp5588-keys.c
index bb3b57b..5ef7fcf 100644
--- a/drivers/input/keyboard/adp5588-keys.c
+++ b/drivers/input/keyboard/adp5588-keys.c
@@ -76,8 +76,18 @@
struct adp5588_kpad *kpad = container_of(chip, struct adp5588_kpad, gc);
unsigned int bank = ADP5588_BANK(kpad->gpiomap[off]);
unsigned int bit = ADP5588_BIT(kpad->gpiomap[off]);
+ int val;
- return !!(adp5588_read(kpad->client, GPIO_DAT_STAT1 + bank) & bit);
+ mutex_lock(&kpad->gpio_lock);
+
+ if (kpad->dir[bank] & bit)
+ val = kpad->dat_out[bank];
+ else
+ val = adp5588_read(kpad->client, GPIO_DAT_STAT1 + bank);
+
+ mutex_unlock(&kpad->gpio_lock);
+
+ return !!(val & bit);
}
static void adp5588_gpio_set_value(struct gpio_chip *chip,
diff --git a/drivers/input/misc/arizona-haptics.c b/drivers/input/misc/arizona-haptics.c
index 7a04f54..ef2e281 100644
--- a/drivers/input/misc/arizona-haptics.c
+++ b/drivers/input/misc/arizona-haptics.c
@@ -37,7 +37,6 @@
struct arizona_haptics,
work);
struct arizona *arizona = haptics->arizona;
- struct mutex *dapm_mutex = &arizona->dapm->card->dapm_mutex;
int ret;
if (!haptics->arizona->dapm) {
@@ -67,13 +66,10 @@
return;
}
- mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-
ret = snd_soc_dapm_enable_pin(arizona->dapm, "HAPTICS");
if (ret != 0) {
dev_err(arizona->dev, "Failed to start HAPTICS: %d\n",
ret);
- mutex_unlock(dapm_mutex);
return;
}
@@ -81,21 +77,14 @@
if (ret != 0) {
dev_err(arizona->dev, "Failed to sync DAPM: %d\n",
ret);
- mutex_unlock(dapm_mutex);
return;
}
-
- mutex_unlock(dapm_mutex);
-
} else {
/* This disable sequence will be a noop if already enabled */
- mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-
ret = snd_soc_dapm_disable_pin(arizona->dapm, "HAPTICS");
if (ret != 0) {
dev_err(arizona->dev, "Failed to disable HAPTICS: %d\n",
ret);
- mutex_unlock(dapm_mutex);
return;
}
@@ -103,12 +92,9 @@
if (ret != 0) {
dev_err(arizona->dev, "Failed to sync DAPM: %d\n",
ret);
- mutex_unlock(dapm_mutex);
return;
}
- mutex_unlock(dapm_mutex);
-
ret = regmap_update_bits(arizona->regmap,
ARIZONA_HAPTICS_CONTROL_1,
ARIZONA_HAP_CTRL_MASK,
@@ -155,16 +141,11 @@
static void arizona_haptics_close(struct input_dev *input)
{
struct arizona_haptics *haptics = input_get_drvdata(input);
- struct mutex *dapm_mutex = &haptics->arizona->dapm->card->dapm_mutex;
cancel_work_sync(&haptics->work);
- mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-
if (haptics->arizona->dapm)
snd_soc_dapm_disable_pin(haptics->arizona->dapm, "HAPTICS");
-
- mutex_unlock(dapm_mutex);
}
static int arizona_haptics_probe(struct platform_device *pdev)
diff --git a/drivers/input/misc/da9052_onkey.c b/drivers/input/misc/da9052_onkey.c
index 1f695f2..184c8f2 100644
--- a/drivers/input/misc/da9052_onkey.c
+++ b/drivers/input/misc/da9052_onkey.c
@@ -27,29 +27,32 @@
static void da9052_onkey_query(struct da9052_onkey *onkey)
{
- int key_stat;
+ int ret;
- key_stat = da9052_reg_read(onkey->da9052, DA9052_EVENT_B_REG);
- if (key_stat < 0) {
+ ret = da9052_reg_read(onkey->da9052, DA9052_STATUS_A_REG);
+ if (ret < 0) {
dev_err(onkey->da9052->dev,
- "Failed to read onkey event %d\n", key_stat);
+ "Failed to read onkey event err=%d\n", ret);
} else {
/*
* Since interrupt for deassertion of ONKEY pin is not
* generated, onkey event state determines the onkey
* button state.
*/
- key_stat &= DA9052_EVENTB_ENONKEY;
- input_report_key(onkey->input, KEY_POWER, key_stat);
- input_sync(onkey->input);
- }
+ bool pressed = !(ret & DA9052_STATUSA_NONKEY);
- /*
- * Interrupt is generated only when the ONKEY pin is asserted.
- * Hence the deassertion of the pin is simulated through work queue.
- */
- if (key_stat)
- schedule_delayed_work(&onkey->work, msecs_to_jiffies(50));
+ input_report_key(onkey->input, KEY_POWER, pressed);
+ input_sync(onkey->input);
+
+ /*
+ * Interrupt is generated only when the ONKEY pin
+ * is asserted. Hence the deassertion of the pin
+ * is simulated through work queue.
+ */
+ if (pressed)
+ schedule_delayed_work(&onkey->work,
+ msecs_to_jiffies(50));
+ }
}
static void da9052_onkey_work(struct work_struct *work)
diff --git a/drivers/input/mouse/cypress_ps2.c b/drivers/input/mouse/cypress_ps2.c
index 87095e2..8af34ff 100644
--- a/drivers/input/mouse/cypress_ps2.c
+++ b/drivers/input/mouse/cypress_ps2.c
@@ -409,7 +409,6 @@
__clear_bit(REL_X, input->relbit);
__clear_bit(REL_Y, input->relbit);
- __set_bit(INPUT_PROP_BUTTONPAD, input->propbit);
__set_bit(EV_KEY, input->evbit);
__set_bit(BTN_LEFT, input->keybit);
__set_bit(BTN_RIGHT, input->keybit);
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 26386f9..d8d49d1 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -265,11 +265,22 @@
* Read touchpad resolution and maximum reported coordinates
* Resolution is left zero if touchpad does not support the query
*/
+
+static const int *quirk_min_max;
+
static int synaptics_resolution(struct psmouse *psmouse)
{
struct synaptics_data *priv = psmouse->private;
unsigned char resp[3];
+ if (quirk_min_max) {
+ priv->x_min = quirk_min_max[0];
+ priv->x_max = quirk_min_max[1];
+ priv->y_min = quirk_min_max[2];
+ priv->y_max = quirk_min_max[3];
+ return 0;
+ }
+
if (SYN_ID_MAJOR(priv->identity) < 4)
return 0;
@@ -1485,10 +1496,54 @@
{ }
};
+static const struct dmi_system_id min_max_dmi_table[] __initconst = {
+#if defined(CONFIG_DMI)
+ {
+ /* Lenovo ThinkPad Helix */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix"),
+ },
+ .driver_data = (int []){1024, 5052, 2258, 4832},
+ },
+ {
+ /* Lenovo ThinkPad X240 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X240"),
+ },
+ .driver_data = (int []){1232, 5710, 1156, 4696},
+ },
+ {
+ /* Lenovo ThinkPad T440s */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T440"),
+ },
+ .driver_data = (int []){1024, 5112, 2024, 4832},
+ },
+ {
+ /* Lenovo ThinkPad T540p */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T540"),
+ },
+ .driver_data = (int []){1024, 5056, 2058, 4832},
+ },
+#endif
+ { }
+};
+
void __init synaptics_module_init(void)
{
+ const struct dmi_system_id *min_max_dmi;
+
impaired_toshiba_kbc = dmi_check_system(toshiba_dmi_table);
broken_olpc_ec = dmi_check_system(olpc_dmi_table);
+
+ min_max_dmi = dmi_first_match(min_max_dmi_table);
+ if (min_max_dmi)
+ quirk_min_max = min_max_dmi->driver_data;
}
static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 8911850..1d9ab39 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -79,7 +79,6 @@
#define ARM_SMMU_PTE_CONT_SIZE (PAGE_SIZE * ARM_SMMU_PTE_CONT_ENTRIES)
#define ARM_SMMU_PTE_CONT_MASK (~(ARM_SMMU_PTE_CONT_SIZE - 1))
-#define ARM_SMMU_PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(pte_t))
/* Stage-1 PTE */
#define ARM_SMMU_PTE_AP_UNPRIV (((pteval_t)1) << 6)
@@ -191,6 +190,9 @@
#define ARM_SMMU_GR1_CBAR(n) (0x0 + ((n) << 2))
#define CBAR_VMID_SHIFT 0
#define CBAR_VMID_MASK 0xff
+#define CBAR_S1_BPSHCFG_SHIFT 8
+#define CBAR_S1_BPSHCFG_MASK 3
+#define CBAR_S1_BPSHCFG_NSH 3
#define CBAR_S1_MEMATTR_SHIFT 12
#define CBAR_S1_MEMATTR_MASK 0xf
#define CBAR_S1_MEMATTR_WB 0xf
@@ -393,7 +395,7 @@
struct arm_smmu_cfg root_cfg;
phys_addr_t output_mask;
- struct mutex lock;
+ spinlock_t lock;
};
static DEFINE_SPINLOCK(arm_smmu_devices_lock);
@@ -632,6 +634,28 @@
return IRQ_HANDLED;
}
+static void arm_smmu_flush_pgtable(struct arm_smmu_device *smmu, void *addr,
+ size_t size)
+{
+ unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
+
+
+ /* Ensure new page tables are visible to the hardware walker */
+ if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) {
+ dsb();
+ } else {
+ /*
+ * If the SMMU can't walk tables in the CPU caches, treat them
+ * like non-coherent DMA since we need to flush the new entries
+ * all the way out to memory. There's no possibility of
+ * recursion here as the SMMU table walker will not be wired
+ * through another SMMU.
+ */
+ dma_map_page(smmu->dev, virt_to_page(addr), offset, size,
+ DMA_TO_DEVICE);
+ }
+}
+
static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
{
u32 reg;
@@ -650,11 +674,16 @@
if (smmu->version == 1)
reg |= root_cfg->irptndx << CBAR_IRPTNDX_SHIFT;
- /* Use the weakest memory type, so it is overridden by the pte */
- if (stage1)
- reg |= (CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
- else
+ /*
+ * Use the weakest shareability/memory types, so they are
+ * overridden by the ttbcr/pte.
+ */
+ if (stage1) {
+ reg |= (CBAR_S1_BPSHCFG_NSH << CBAR_S1_BPSHCFG_SHIFT) |
+ (CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
+ } else {
reg |= ARM_SMMU_CB_VMID(root_cfg) << CBAR_VMID_SHIFT;
+ }
writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(root_cfg->cbndx));
if (smmu->version > 1) {
@@ -715,6 +744,8 @@
}
/* TTBR0 */
+ arm_smmu_flush_pgtable(smmu, root_cfg->pgd,
+ PTRS_PER_PGD * sizeof(pgd_t));
reg = __pa(root_cfg->pgd);
writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32;
@@ -901,7 +932,7 @@
goto out_free_domain;
smmu_domain->root_cfg.pgd = pgd;
- mutex_init(&smmu_domain->lock);
+ spin_lock_init(&smmu_domain->lock);
domain->priv = smmu_domain;
return 0;
@@ -1128,6 +1159,7 @@
struct arm_smmu_domain *smmu_domain = domain->priv;
struct arm_smmu_device *device_smmu = dev->archdata.iommu;
struct arm_smmu_master *master;
+ unsigned long flags;
if (!device_smmu) {
dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
@@ -1138,7 +1170,7 @@
* Sanity check the domain. We don't currently support domains
* that cross between different SMMU chains.
*/
- mutex_lock(&smmu_domain->lock);
+ spin_lock_irqsave(&smmu_domain->lock, flags);
if (!smmu_domain->leaf_smmu) {
/* Now that we have a master, we can finalise the domain */
ret = arm_smmu_init_domain_context(domain, dev);
@@ -1153,7 +1185,7 @@
dev_name(device_smmu->dev));
goto err_unlock;
}
- mutex_unlock(&smmu_domain->lock);
+ spin_unlock_irqrestore(&smmu_domain->lock, flags);
/* Looks ok, so add the device to the domain */
master = find_smmu_master(smmu_domain->leaf_smmu, dev->of_node);
@@ -1163,7 +1195,7 @@
return arm_smmu_domain_add_master(smmu_domain, master);
err_unlock:
- mutex_unlock(&smmu_domain->lock);
+ spin_unlock_irqrestore(&smmu_domain->lock, flags);
return ret;
}
@@ -1177,23 +1209,6 @@
arm_smmu_domain_remove_master(smmu_domain, master);
}
-static void arm_smmu_flush_pgtable(struct arm_smmu_device *smmu, void *addr,
- size_t size)
-{
- unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
-
- /*
- * If the SMMU can't walk tables in the CPU caches, treat them
- * like non-coherent DMA since we need to flush the new entries
- * all the way out to memory. There's no possibility of recursion
- * here as the SMMU table walker will not be wired through another
- * SMMU.
- */
- if (!(smmu->features & ARM_SMMU_FEAT_COHERENT_WALK))
- dma_map_page(smmu->dev, virt_to_page(addr), offset, size,
- DMA_TO_DEVICE);
-}
-
static bool arm_smmu_pte_is_contiguous_range(unsigned long addr,
unsigned long end)
{
@@ -1210,12 +1225,11 @@
if (pmd_none(*pmd)) {
/* Allocate a new set of tables */
- pgtable_t table = alloc_page(PGALLOC_GFP);
+ pgtable_t table = alloc_page(GFP_ATOMIC|__GFP_ZERO);
if (!table)
return -ENOMEM;
- arm_smmu_flush_pgtable(smmu, page_address(table),
- ARM_SMMU_PTE_HWTABLE_SIZE);
+ arm_smmu_flush_pgtable(smmu, page_address(table), PAGE_SIZE);
if (!pgtable_page_ctor(table)) {
__free_page(table);
return -ENOMEM;
@@ -1317,9 +1331,15 @@
#ifndef __PAGETABLE_PMD_FOLDED
if (pud_none(*pud)) {
- pmd = pmd_alloc_one(NULL, addr);
+ pmd = (pmd_t *)get_zeroed_page(GFP_ATOMIC);
if (!pmd)
return -ENOMEM;
+
+ arm_smmu_flush_pgtable(smmu, pmd, PAGE_SIZE);
+ pud_populate(NULL, pud, pmd);
+ arm_smmu_flush_pgtable(smmu, pud, sizeof(*pud));
+
+ pmd += pmd_index(addr);
} else
#endif
pmd = pmd_offset(pud, addr);
@@ -1328,8 +1348,6 @@
next = pmd_addr_end(addr, end);
ret = arm_smmu_alloc_init_pte(smmu, pmd, addr, end, pfn,
flags, stage);
- pud_populate(NULL, pud, pmd);
- arm_smmu_flush_pgtable(smmu, pud, sizeof(*pud));
phys += next - addr;
} while (pmd++, addr = next, addr < end);
@@ -1346,9 +1364,15 @@
#ifndef __PAGETABLE_PUD_FOLDED
if (pgd_none(*pgd)) {
- pud = pud_alloc_one(NULL, addr);
+ pud = (pud_t *)get_zeroed_page(GFP_ATOMIC);
if (!pud)
return -ENOMEM;
+
+ arm_smmu_flush_pgtable(smmu, pud, PAGE_SIZE);
+ pgd_populate(NULL, pgd, pud);
+ arm_smmu_flush_pgtable(smmu, pgd, sizeof(*pgd));
+
+ pud += pud_index(addr);
} else
#endif
pud = pud_offset(pgd, addr);
@@ -1357,8 +1381,6 @@
next = pud_addr_end(addr, end);
ret = arm_smmu_alloc_init_pmd(smmu, pud, addr, next, phys,
flags, stage);
- pgd_populate(NULL, pud, pgd);
- arm_smmu_flush_pgtable(smmu, pgd, sizeof(*pgd));
phys += next - addr;
} while (pud++, addr = next, addr < end);
@@ -1375,6 +1397,7 @@
struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
pgd_t *pgd = root_cfg->pgd;
struct arm_smmu_device *smmu = root_cfg->smmu;
+ unsigned long irqflags;
if (root_cfg->cbar == CBAR_TYPE_S2_TRANS) {
stage = 2;
@@ -1397,7 +1420,7 @@
if (paddr & ~output_mask)
return -ERANGE;
- mutex_lock(&smmu_domain->lock);
+ spin_lock_irqsave(&smmu_domain->lock, irqflags);
pgd += pgd_index(iova);
end = iova + size;
do {
@@ -1413,11 +1436,7 @@
} while (pgd++, iova != end);
out_unlock:
- mutex_unlock(&smmu_domain->lock);
-
- /* Ensure new page tables are visible to the hardware walker */
- if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
- dsb();
+ spin_unlock_irqrestore(&smmu_domain->lock, irqflags);
return ret;
}
@@ -1987,8 +2006,10 @@
if (!iommu_present(&platform_bus_type))
bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
+#ifdef CONFIG_ARM_AMBA
if (!iommu_present(&amba_bustype))
bus_set_iommu(&amba_bustype, &arm_smmu_ops);
+#endif
return 0;
}
diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c
index d97fbe4..80fffba 100644
--- a/drivers/iommu/omap-iommu-debug.c
+++ b/drivers/iommu/omap-iommu-debug.c
@@ -354,8 +354,8 @@
return -ENOMEM; \
}
-#define DEBUG_ADD_FILE(name) __DEBUG_ADD_FILE(name, 600)
-#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 400)
+#define DEBUG_ADD_FILE(name) __DEBUG_ADD_FILE(name, 0600)
+#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 0400)
static int iommu_debug_register(struct device *dev, void *data)
{
diff --git a/drivers/irqchip/irq-metag-ext.c b/drivers/irqchip/irq-metag-ext.c
index 92c41ab..2cb474a 100644
--- a/drivers/irqchip/irq-metag-ext.c
+++ b/drivers/irqchip/irq-metag-ext.c
@@ -515,7 +515,7 @@
* one cpu (the interrupt code doesn't support it), so we just
* pick the first cpu we find in 'cpumask'.
*/
- cpu = cpumask_any(cpumask);
+ cpu = cpumask_any_and(cpumask, cpu_online_mask);
thread = cpu_2_hwthread_id[cpu];
metag_out32(TBI_TRIG_VEC(TBID_SIGNUM_TR2(thread)), vec_addr);
diff --git a/drivers/irqchip/irq-metag.c b/drivers/irqchip/irq-metag.c
index 8e94d7a..c16c186 100644
--- a/drivers/irqchip/irq-metag.c
+++ b/drivers/irqchip/irq-metag.c
@@ -201,7 +201,7 @@
* one cpu (the interrupt code doesn't support it), so we just
* pick the first cpu we find in 'cpumask'.
*/
- cpu = cpumask_any(cpumask);
+ cpu = cpumask_any_and(cpumask, cpu_online_mask);
thread = cpu_2_hwthread_id[cpu];
metag_out32(TBI_TRIG_VEC(TBID_SIGNUM_TR1(thread)),
diff --git a/drivers/irqchip/irq-orion.c b/drivers/irqchip/irq-orion.c
index e51d400..8e41be6 100644
--- a/drivers/irqchip/irq-orion.c
+++ b/drivers/irqchip/irq-orion.c
@@ -111,7 +111,8 @@
static void orion_bridge_irq_handler(unsigned int irq, struct irq_desc *desc)
{
struct irq_domain *d = irq_get_handler_data(irq);
- struct irq_chip_generic *gc = irq_get_domain_generic_chip(d, irq);
+
+ struct irq_chip_generic *gc = irq_get_domain_generic_chip(d, 0);
u32 stat = readl_relaxed(gc->reg_base + ORION_BRIDGE_IRQ_CAUSE) &
gc->mask_cache;
@@ -123,6 +124,19 @@
}
}
+/*
+ * Bridge IRQ_CAUSE is asserted regardless of IRQ_MASK register.
+ * To avoid interrupt events on stale irqs, we clear them before unmask.
+ */
+static unsigned int orion_bridge_irq_startup(struct irq_data *d)
+{
+ struct irq_chip_type *ct = irq_data_get_chip_type(d);
+
+ ct->chip.irq_ack(d);
+ ct->chip.irq_unmask(d);
+ return 0;
+}
+
static int __init orion_bridge_irq_init(struct device_node *np,
struct device_node *parent)
{
@@ -143,7 +157,7 @@
}
ret = irq_alloc_domain_generic_chips(domain, nrirqs, 1, np->name,
- handle_level_irq, clr, 0, IRQ_GC_INIT_MASK_CACHE);
+ handle_edge_irq, clr, 0, IRQ_GC_INIT_MASK_CACHE);
if (ret) {
pr_err("%s: unable to alloc irq domain gc\n", np->name);
return ret;
@@ -176,12 +190,14 @@
gc->chip_types[0].regs.ack = ORION_BRIDGE_IRQ_CAUSE;
gc->chip_types[0].regs.mask = ORION_BRIDGE_IRQ_MASK;
+ gc->chip_types[0].chip.irq_startup = orion_bridge_irq_startup;
gc->chip_types[0].chip.irq_ack = irq_gc_ack_clr_bit;
gc->chip_types[0].chip.irq_mask = irq_gc_mask_clr_bit;
gc->chip_types[0].chip.irq_unmask = irq_gc_mask_set_bit;
- /* mask all interrupts */
+ /* mask and clear all interrupts */
writel(0, gc->reg_base + ORION_BRIDGE_IRQ_MASK);
+ writel(0, gc->reg_base + ORION_BRIDGE_IRQ_CAUSE);
irq_set_handler_data(irq, domain);
irq_set_chained_handler(irq, orion_bridge_irq_handler);
diff --git a/drivers/isdn/act2000/module.c b/drivers/isdn/act2000/module.c
index b4147c0..c3a1b06 100644
--- a/drivers/isdn/act2000/module.c
+++ b/drivers/isdn/act2000/module.c
@@ -796,7 +796,7 @@
act2000_card *last;
while (card) {
unregister_card(card);
- del_timer(&card->ptimer);
+ del_timer_sync(&card->ptimer);
card = card->next;
}
card = cards;
diff --git a/drivers/isdn/capi/Kconfig b/drivers/isdn/capi/Kconfig
index f046865..9816c51 100644
--- a/drivers/isdn/capi/Kconfig
+++ b/drivers/isdn/capi/Kconfig
@@ -16,16 +16,6 @@
This will increase the size of the kernelcapi module by 20 KB.
If unsure, say Y.
-config ISDN_CAPI_MIDDLEWARE
- bool "CAPI2.0 Middleware support"
- depends on TTY
- help
- This option will enhance the capabilities of the /dev/capi20
- interface. It will provide a means of moving a data connection,
- established via the usual /dev/capi20 interface to a special tty
- device. If you want to use pppd with pppdcapiplugin to dial up to
- your ISP, say Y here.
-
config ISDN_CAPI_CAPI20
tristate "CAPI2.0 /dev/capi support"
help
@@ -34,6 +24,16 @@
standardized libcapi20 to access this functionality. You should say
Y/M here.
+config ISDN_CAPI_MIDDLEWARE
+ bool "CAPI2.0 Middleware support"
+ depends on ISDN_CAPI_CAPI20 && TTY
+ help
+ This option will enhance the capabilities of the /dev/capi20
+ interface. It will provide a means of moving a data connection,
+ established via the usual /dev/capi20 interface to a special tty
+ device. If you want to use pppd with pppdcapiplugin to dial up to
+ your ISP, say Y here.
+
config ISDN_CAPI_CAPIDRV
tristate "CAPI2.0 capidrv interface support"
depends on ISDN_I4L
diff --git a/drivers/isdn/divert/divert_procfs.c b/drivers/isdn/divert/divert_procfs.c
index fb4f1ba..1c5dc34 100644
--- a/drivers/isdn/divert/divert_procfs.c
+++ b/drivers/isdn/divert/divert_procfs.c
@@ -86,12 +86,13 @@
struct divert_info *inf;
int len;
- if (!*((struct divert_info **) file->private_data)) {
+ if (!(inf = *((struct divert_info **) file->private_data))) {
if (file->f_flags & O_NONBLOCK)
return -EAGAIN;
- interruptible_sleep_on(&(rd_queue));
+ wait_event_interruptible(rd_queue, (inf =
+ *((struct divert_info **) file->private_data)));
}
- if (!(inf = *((struct divert_info **) file->private_data)))
+ if (!inf)
return (0);
inf->usage_cnt--; /* new usage count */
diff --git a/drivers/isdn/hisax/elsa.c b/drivers/isdn/hisax/elsa.c
index 2be1c8a..d8ef64d 100644
--- a/drivers/isdn/hisax/elsa.c
+++ b/drivers/isdn/hisax/elsa.c
@@ -509,7 +509,8 @@
set_arcofi(struct IsdnCardState *cs, int bc) {
cs->dc.isac.arcofi_bc = bc;
arcofi_fsm(cs, ARCOFI_START, &ARCOFI_COP_5);
- interruptible_sleep_on(&cs->dc.isac.arcofi_wait);
+ wait_event_interruptible(cs->dc.isac.arcofi_wait,
+ cs->dc.isac.arcofi_state == ARCOFI_NOP);
}
static int
@@ -528,7 +529,8 @@
}
cs->dc.isac.arcofi_bc = 0;
arcofi_fsm(cs, ARCOFI_START, &ARCOFI_VERSION);
- interruptible_sleep_on(&cs->dc.isac.arcofi_wait);
+ wait_event_interruptible(cs->dc.isac.arcofi_wait,
+ cs->dc.isac.arcofi_state == ARCOFI_NOP);
if (!test_and_clear_bit(FLG_ARCOFI_ERROR, &cs->HW_Flags)) {
debugl1(cs, "Arcofi response received %d bytes", cs->dc.isac.mon_rxp);
p = cs->dc.isac.mon_rx;
@@ -595,7 +597,8 @@
Elsa_Types[cs->subtyp],
cs->hw.elsa.base + 8);
arcofi_fsm(cs, ARCOFI_START, &ARCOFI_XOP_0);
- interruptible_sleep_on(&cs->dc.isac.arcofi_wait);
+ wait_event_interruptible(cs->dc.isac.arcofi_wait,
+ cs->dc.isac.arcofi_state == ARCOFI_NOP);
return (1);
}
return (0);
diff --git a/drivers/isdn/hisax/elsa_ser.c b/drivers/isdn/hisax/elsa_ser.c
index 3f84dd8..a2a358c 100644
--- a/drivers/isdn/hisax/elsa_ser.c
+++ b/drivers/isdn/hisax/elsa_ser.c
@@ -573,7 +573,8 @@
test_and_clear_bit(BC_FLG_ACTIV, &bcs->Flag);
bcs->cs->dc.isac.arcofi_bc = st->l1.bc;
arcofi_fsm(bcs->cs, ARCOFI_START, &ARCOFI_XOP_0);
- interruptible_sleep_on(&bcs->cs->dc.isac.arcofi_wait);
+ wait_event_interruptible(bcs->cs->dc.isac.arcofi_wait,
+ bcs->cs->dc.isac.arcofi_state == ARCOFI_NOP);
bcs->cs->hw.elsa.MFlag = 1;
} else {
printk(KERN_WARNING "ElsaSer: unknown pr %x\n", pr);
diff --git a/drivers/isdn/hisax/q931.c b/drivers/isdn/hisax/q931.c
index af1b020..b420f8b 100644
--- a/drivers/isdn/hisax/q931.c
+++ b/drivers/isdn/hisax/q931.c
@@ -810,7 +810,7 @@
dp += sprintf(dp, " octet 3 ");
dp += prbits(dp, *p, 8, 8);
*dp++ = '\n';
- if (!(*p++ & 80)) {
+ if (!(*p++ & 0x80)) {
dp += sprintf(dp, " octet 4 ");
dp += prbits(dp, *p++, 8, 8);
*dp++ = '\n';
diff --git a/drivers/isdn/hysdn/hysdn_proclog.c b/drivers/isdn/hysdn/hysdn_proclog.c
index b61e8d5..7b5fd8f 100644
--- a/drivers/isdn/hysdn/hysdn_proclog.c
+++ b/drivers/isdn/hysdn/hysdn_proclog.c
@@ -175,14 +175,15 @@
int len;
hysdn_card *card = PDE_DATA(file_inode(file));
- if (!*((struct log_data **) file->private_data)) {
+ if (!(inf = *((struct log_data **) file->private_data))) {
struct procdata *pd = card->proclog;
if (file->f_flags & O_NONBLOCK)
return (-EAGAIN);
- interruptible_sleep_on(&(pd->rd_queue));
+ wait_event_interruptible(pd->rd_queue, (inf =
+ *((struct log_data **) file->private_data)));
}
- if (!(inf = *((struct log_data **) file->private_data)))
+ if (!inf)
return (0);
inf->usage_cnt--; /* new usage count */
diff --git a/drivers/isdn/i4l/isdn_common.c b/drivers/isdn/i4l/isdn_common.c
index 9bb12ba..9b856e1 100644
--- a/drivers/isdn/i4l/isdn_common.c
+++ b/drivers/isdn/i4l/isdn_common.c
@@ -777,7 +777,8 @@
return 0;
if (skb_queue_empty(&dev->drv[di]->rpqueue[channel])) {
if (sleep)
- interruptible_sleep_on(sleep);
+ wait_event_interruptible(*sleep,
+ !skb_queue_empty(&dev->drv[di]->rpqueue[channel]));
else
return 0;
}
@@ -1072,7 +1073,8 @@
retval = -EAGAIN;
goto out;
}
- interruptible_sleep_on(&(dev->info_waitq));
+ wait_event_interruptible(dev->info_waitq,
+ file->private_data);
}
p = isdn_statstr();
file->private_data = NULL;
@@ -1128,7 +1130,8 @@
retval = -EAGAIN;
goto out;
}
- interruptible_sleep_on(&(dev->drv[drvidx]->st_waitq));
+ wait_event_interruptible(dev->drv[drvidx]->st_waitq,
+ dev->drv[drvidx]->stavail);
}
if (dev->drv[drvidx]->interface->readstat) {
if (count > dev->drv[drvidx]->stavail)
@@ -1188,8 +1191,8 @@
goto out;
}
chidx = isdn_minor2chan(minor);
- while ((retval = isdn_writebuf_stub(drvidx, chidx, buf, count)) == 0)
- interruptible_sleep_on(&dev->drv[drvidx]->snd_waitq[chidx]);
+ wait_event_interruptible(dev->drv[drvidx]->snd_waitq[chidx],
+ (retval = isdn_writebuf_stub(drvidx, chidx, buf, count)));
goto out;
}
if (minor <= ISDN_MINOR_CTRLMAX) {
@@ -2378,7 +2381,7 @@
}
isdn_tty_exit();
unregister_chrdev(ISDN_MAJOR, "isdn");
- del_timer(&dev->timer);
+ del_timer_sync(&dev->timer);
/* call vfree with interrupts enabled, else it will hang */
vfree(dev);
printk(KERN_NOTICE "ISDN-subsystem unloaded\n");
diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index 38ceac5..a5da511 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -378,10 +378,15 @@
is->slcomp = NULL;
#endif
#ifdef CONFIG_IPPP_FILTER
- kfree(is->pass_filter);
- is->pass_filter = NULL;
- kfree(is->active_filter);
- is->active_filter = NULL;
+ if (is->pass_filter) {
+ sk_unattached_filter_destroy(is->pass_filter);
+ is->pass_filter = NULL;
+ }
+
+ if (is->active_filter) {
+ sk_unattached_filter_destroy(is->active_filter);
+ is->active_filter = NULL;
+ }
#endif
/* TODO: if this was the previous master: link the stuff to the new master */
@@ -629,25 +634,41 @@
#ifdef CONFIG_IPPP_FILTER
case PPPIOCSPASS:
{
+ struct sock_fprog fprog;
struct sock_filter *code;
- int len = get_filter(argp, &code);
+ int err, len = get_filter(argp, &code);
+
if (len < 0)
return len;
- kfree(is->pass_filter);
- is->pass_filter = code;
- is->pass_len = len;
- break;
+
+ fprog.len = len;
+ fprog.filter = code;
+
+ if (is->pass_filter)
+ sk_unattached_filter_destroy(is->pass_filter);
+ err = sk_unattached_filter_create(&is->pass_filter, &fprog);
+ kfree(code);
+
+ return err;
}
case PPPIOCSACTIVE:
{
+ struct sock_fprog fprog;
struct sock_filter *code;
- int len = get_filter(argp, &code);
+ int err, len = get_filter(argp, &code);
+
if (len < 0)
return len;
- kfree(is->active_filter);
- is->active_filter = code;
- is->active_len = len;
- break;
+
+ fprog.len = len;
+ fprog.filter = code;
+
+ if (is->active_filter)
+ sk_unattached_filter_destroy(is->active_filter);
+ err = sk_unattached_filter_create(&is->active_filter, &fprog);
+ kfree(code);
+
+ return err;
}
#endif /* CONFIG_IPPP_FILTER */
default:
@@ -1147,14 +1168,14 @@
}
if (is->pass_filter
- && sk_run_filter(skb, is->pass_filter) == 0) {
+ && SK_RUN_FILTER(is->pass_filter, skb) == 0) {
if (is->debug & 0x2)
printk(KERN_DEBUG "IPPP: inbound frame filtered.\n");
kfree_skb(skb);
return;
}
if (!(is->active_filter
- && sk_run_filter(skb, is->active_filter) == 0)) {
+ && SK_RUN_FILTER(is->active_filter, skb) == 0)) {
if (is->debug & 0x2)
printk(KERN_DEBUG "IPPP: link-active filter: resetting huptimer.\n");
lp->huptimer = 0;
@@ -1293,14 +1314,14 @@
}
if (ipt->pass_filter
- && sk_run_filter(skb, ipt->pass_filter) == 0) {
+ && SK_RUN_FILTER(ipt->pass_filter, skb) == 0) {
if (ipt->debug & 0x4)
printk(KERN_DEBUG "IPPP: outbound frame filtered.\n");
kfree_skb(skb);
goto unlock;
}
if (!(ipt->active_filter
- && sk_run_filter(skb, ipt->active_filter) == 0)) {
+ && SK_RUN_FILTER(ipt->active_filter, skb) == 0)) {
if (ipt->debug & 0x4)
printk(KERN_DEBUG "IPPP: link-active filter: resetting huptimer.\n");
lp->huptimer = 0;
@@ -1490,9 +1511,9 @@
}
drop |= is->pass_filter
- && sk_run_filter(skb, is->pass_filter) == 0;
+ && SK_RUN_FILTER(is->pass_filter, skb) == 0;
drop |= is->active_filter
- && sk_run_filter(skb, is->active_filter) == 0;
+ && SK_RUN_FILTER(is->active_filter, skb) == 0;
skb_push(skb, IPPP_MAX_HEADER - 4);
return drop;
diff --git a/drivers/isdn/pcbit/drv.c b/drivers/isdn/pcbit/drv.c
index 1eaf622..f02cc50 100644
--- a/drivers/isdn/pcbit/drv.c
+++ b/drivers/isdn/pcbit/drv.c
@@ -796,6 +796,7 @@
#endif
dev = (struct pcbit_dev *) ptr;
+ dev->l2_state = L2_DOWN;
wake_up_interruptible(&dev->set_running_wq);
}
@@ -818,7 +819,8 @@
add_timer(&dev->set_running_timer);
- interruptible_sleep_on(&dev->set_running_wq);
+ wait_event(dev->set_running_wq, dev->l2_state == L2_RUNNING ||
+ dev->l2_state == L2_DOWN);
del_timer(&dev->set_running_timer);
@@ -842,8 +844,6 @@
printk(KERN_DEBUG "pcbit: initialization failed\n");
printk(KERN_DEBUG "pcbit: firmware not loaded\n");
- dev->l2_state = L2_DOWN;
-
#ifdef DEBUG
printk(KERN_DEBUG "Bank3 = %02x\n",
readb(dev->sh_mem + BANK3));
diff --git a/drivers/isdn/sc/init.c b/drivers/isdn/sc/init.c
index 92acc81..d6f19b1 100644
--- a/drivers/isdn/sc/init.c
+++ b/drivers/isdn/sc/init.c
@@ -390,8 +390,8 @@
/*
* kill the timers
*/
- del_timer(&(sc_adapter[i]->reset_timer));
- del_timer(&(sc_adapter[i]->stat_timer));
+ del_timer_sync(&(sc_adapter[i]->reset_timer));
+ del_timer_sync(&(sc_adapter[i]->stat_timer));
/*
* Tell I4L we're toast
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 9a06fe8..95ad936 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -254,16 +254,6 @@
---help---
Provides thin provisioning and snapshots that share a data store.
-config DM_DEBUG_BLOCK_STACK_TRACING
- boolean "Keep stack trace of persistent data block lock holders"
- depends on STACKTRACE_SUPPORT && DM_PERSISTENT_DATA
- select STACKTRACE
- ---help---
- Enable this for messages that may help debug problems with the
- block manager locking used by thin provisioning and caching.
-
- If unsure, say N.
-
config DM_CACHE
tristate "Cache target (EXPERIMENTAL)"
depends on BLK_DEV_DM
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 0c707e4..a4c7306 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -210,7 +210,9 @@
#define GC_MARK_RECLAIMABLE 0
#define GC_MARK_DIRTY 1
#define GC_MARK_METADATA 2
-BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 13);
+#define GC_SECTORS_USED_SIZE 13
+#define MAX_GC_SECTORS_USED (~(~0ULL << GC_SECTORS_USED_SIZE))
+BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, GC_SECTORS_USED_SIZE);
BITMASK(GC_MOVE, struct bucket, gc_mark, 15, 1);
#include "journal.h"
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 4f6b594..3f74b4b 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -23,7 +23,7 @@
for (k = i->start; k < bset_bkey_last(i); k = next) {
next = bkey_next(k);
- printk(KERN_ERR "block %u key %zi/%u: ", set,
+ printk(KERN_ERR "block %u key %li/%u: ", set,
(uint64_t *) k - i->d, i->keys);
if (b->ops->key_dump)
@@ -1185,9 +1185,12 @@
struct bset *out = (void *) __get_free_pages(__GFP_NOWARN|GFP_NOIO,
order);
if (!out) {
+ struct page *outp;
+
BUG_ON(order > state->page_order);
- out = page_address(mempool_alloc(state->pool, GFP_NOIO));
+ outp = mempool_alloc(state->pool, GFP_NOIO);
+ out = page_address(outp);
used_mempool = true;
order = state->page_order;
}
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 98cc0a8..5f9c2a6 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1167,7 +1167,7 @@
/* guard against overflow */
SET_GC_SECTORS_USED(g, min_t(unsigned,
GC_SECTORS_USED(g) + KEY_SIZE(k),
- (1 << 14) - 1));
+ MAX_GC_SECTORS_USED));
BUG_ON(!GC_SECTORS_USED(g));
}
@@ -1805,7 +1805,7 @@
static size_t insert_u64s_remaining(struct btree *b)
{
- ssize_t ret = bch_btree_keys_u64s_remaining(&b->keys);
+ long ret = bch_btree_keys_u64s_remaining(&b->keys);
/*
* Might land in the middle of an existing extent and have to split it
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index c3ead58..416d1a3 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -194,7 +194,7 @@
mutex_unlock(&b->c->bucket_lock);
bch_extent_to_text(buf, sizeof(buf), k);
btree_bug(b,
-"inconsistent btree pointer %s: bucket %li pin %i prio %i gen %i last_gc %i mark %llu gc_gen %i",
+"inconsistent btree pointer %s: bucket %zi pin %i prio %i gen %i last_gc %i mark %llu gc_gen %i",
buf, PTR_BUCKET_NR(b->c, k, i), atomic_read(&g->pin),
g->prio, g->gen, g->last_gc, GC_MARK(g), g->gc_gen);
return true;
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 72cd213..5d5d031 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -353,14 +353,14 @@
struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
struct bio *bio = op->bio, *n;
- if (op->bypass)
- return bch_data_invalidate(cl);
-
if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) {
set_gc_sectors(op->c);
wake_up_gc(op->c);
}
+ if (op->bypass)
+ return bch_data_invalidate(cl);
+
/*
* Journal writes are marked REQ_FLUSH; if the original write was a
* flush, it'll wait on the journal write.
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index c6ab693..d8458d4 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -416,7 +416,7 @@
return MAP_CONTINUE;
}
-int bch_bset_print_stats(struct cache_set *c, char *buf)
+static int bch_bset_print_stats(struct cache_set *c, char *buf)
{
struct bset_stats_op op;
int ret;
diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c
index 1e018e9..0e385e4 100644
--- a/drivers/md/dm-cache-policy-mq.c
+++ b/drivers/md/dm-cache-policy-mq.c
@@ -872,7 +872,7 @@
{
struct mq_policy *mq = to_mq_policy(p);
- kfree(mq->table);
+ vfree(mq->table);
epool_exit(&mq->cache_pool);
epool_exit(&mq->pre_cache_pool);
kfree(mq);
@@ -1245,7 +1245,7 @@
mq->nr_buckets = next_power(from_cblock(cache_size) / 2, 16);
mq->hash_bits = ffs(mq->nr_buckets) - 1;
- mq->table = kzalloc(sizeof(*mq->table) * mq->nr_buckets, GFP_KERNEL);
+ mq->table = vzalloc(sizeof(*mq->table) * mq->nr_buckets);
if (!mq->table)
goto bad_alloc_table;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index ffd472e..074b9c8 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -289,6 +289,7 @@
bool tick:1;
unsigned req_nr:2;
struct dm_deferred_entry *all_io_entry;
+ struct dm_hook_info hook_info;
/*
* writethrough fields. These MUST remain at the end of this
@@ -297,7 +298,6 @@
*/
struct cache *cache;
dm_cblock_t cblock;
- struct dm_hook_info hook_info;
struct dm_bio_details bio_details;
};
@@ -671,15 +671,16 @@
dm_cblock_t cblock)
{
sector_t bi_sector = bio->bi_iter.bi_sector;
+ sector_t block = from_cblock(cblock);
bio->bi_bdev = cache->cache_dev->bdev;
if (!block_size_is_power_of_two(cache))
bio->bi_iter.bi_sector =
- (from_cblock(cblock) * cache->sectors_per_block) +
+ (block * cache->sectors_per_block) +
sector_div(bi_sector, cache->sectors_per_block);
else
bio->bi_iter.bi_sector =
- (from_cblock(cblock) << cache->sectors_per_block_shift) |
+ (block << cache->sectors_per_block_shift) |
(bi_sector & (cache->sectors_per_block - 1));
}
@@ -978,12 +979,13 @@
int r;
struct dm_io_region o_region, c_region;
struct cache *cache = mg->cache;
+ sector_t cblock = from_cblock(mg->cblock);
o_region.bdev = cache->origin_dev->bdev;
o_region.count = cache->sectors_per_block;
c_region.bdev = cache->cache_dev->bdev;
- c_region.sector = from_cblock(mg->cblock) * cache->sectors_per_block;
+ c_region.sector = cblock * cache->sectors_per_block;
c_region.count = cache->sectors_per_block;
if (mg->writeback || mg->demote) {
@@ -1010,13 +1012,15 @@
struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size);
unsigned long flags;
+ dm_unhook_bio(&pb->hook_info, bio);
+
if (err)
mg->err = true;
+ mg->requeue_holder = false;
+
spin_lock_irqsave(&cache->lock, flags);
list_add_tail(&mg->list, &cache->completed_migrations);
- dm_unhook_bio(&pb->hook_info, bio);
- mg->requeue_holder = false;
spin_unlock_irqrestore(&cache->lock, flags);
wake_worker(cache);
@@ -2461,20 +2465,18 @@
bool discarded_block;
struct dm_bio_prison_cell *cell;
struct policy_result lookup_result;
- struct per_bio_data *pb;
+ struct per_bio_data *pb = init_per_bio_data(bio, pb_data_size);
- if (from_oblock(block) > from_oblock(cache->origin_blocks)) {
+ if (unlikely(from_oblock(block) >= from_oblock(cache->origin_blocks))) {
/*
* This can only occur if the io goes to a partial block at
* the end of the origin device. We don't cache these.
* Just remap to the origin and carry on.
*/
- remap_to_origin_clear_discard(cache, bio, block);
+ remap_to_origin(cache, bio);
return DM_MAPIO_REMAPPED;
}
- pb = init_per_bio_data(bio, pb_data_size);
-
if (bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD)) {
defer_bio(cache, bio);
return DM_MAPIO_SUBMITTED;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index b2b8a10..3842ac7 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -201,29 +201,28 @@
/*
* Functions for getting the pages from a bvec.
*/
-static void bio_get_page(struct dpages *dp,
- struct page **p, unsigned long *len, unsigned *offset)
+static void bio_get_page(struct dpages *dp, struct page **p,
+ unsigned long *len, unsigned *offset)
{
- struct bio *bio = dp->context_ptr;
- struct bio_vec bvec = bio_iovec(bio);
- *p = bvec.bv_page;
- *len = bvec.bv_len;
- *offset = bvec.bv_offset;
+ struct bio_vec *bvec = dp->context_ptr;
+ *p = bvec->bv_page;
+ *len = bvec->bv_len - dp->context_u;
+ *offset = bvec->bv_offset + dp->context_u;
}
static void bio_next_page(struct dpages *dp)
{
- struct bio *bio = dp->context_ptr;
- struct bio_vec bvec = bio_iovec(bio);
-
- bio_advance(bio, bvec.bv_len);
+ struct bio_vec *bvec = dp->context_ptr;
+ dp->context_ptr = bvec + 1;
+ dp->context_u = 0;
}
static void bio_dp_init(struct dpages *dp, struct bio *bio)
{
dp->get_page = bio_get_page;
dp->next_page = bio_next_page;
- dp->context_ptr = bio;
+ dp->context_ptr = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
+ dp->context_u = bio->bi_iter.bi_bvec_done;
}
/*
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 6eb9dc9..422a9fd 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1626,8 +1626,11 @@
/*
* Only pass ioctls through if the device sizes match exactly.
*/
- if (!r && ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT)
- r = scsi_verify_blk_ioctl(NULL, cmd);
+ if (!bdev || ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT) {
+ int err = scsi_verify_blk_ioctl(NULL, cmd);
+ if (err)
+ r = err;
+ }
if (r == -ENOTCONN && !fatal_signal_pending(current))
queue_work(kmultipathd, &m->process_queued_ios);
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index f284e0b..7dfdb5c 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1244,6 +1244,9 @@
dm_bio_restore(bd, bio);
bio_record->details.bi_bdev = NULL;
+
+ atomic_inc(&bio->bi_remaining);
+
queue_bio(ms, bio, rw);
return DM_ENDIO_INCOMPLETE;
}
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index afc3d01..d6e8817 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -546,6 +546,9 @@
r = insert_exceptions(ps, area, callback, callback_context,
&full);
+ if (!full)
+ memcpy(ps->area, area, ps->store->chunk_size << SECTOR_SHIFT);
+
dm_bufio_release(bp);
dm_bufio_forget(client, chunk);
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 7da3476..fb9efc8 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -76,7 +76,7 @@
#define THIN_SUPERBLOCK_MAGIC 27022010
#define THIN_SUPERBLOCK_LOCATION 0
-#define THIN_VERSION 1
+#define THIN_VERSION 2
#define THIN_METADATA_CACHE_SIZE 64
#define SECTOR_TO_BLOCK_SHIFT 3
@@ -483,7 +483,7 @@
disk_super->data_mapping_root = cpu_to_le64(pmd->root);
disk_super->device_details_root = cpu_to_le64(pmd->details_root);
- disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
+ disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE);
disk_super->metadata_nr_blocks = cpu_to_le64(bdev_size >> SECTOR_TO_BLOCK_SHIFT);
disk_super->data_block_size = cpu_to_le32(pmd->data_block_size);
@@ -651,7 +651,7 @@
{
int r;
- pmd->bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE,
+ pmd->bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE << SECTOR_SHIFT,
THIN_METADATA_CACHE_SIZE,
THIN_MAX_CONCURRENT_LOCKS);
if (IS_ERR(pmd->bm)) {
@@ -1489,6 +1489,23 @@
return r;
}
+bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd)
+{
+ bool r = false;
+ struct dm_thin_device *td, *tmp;
+
+ down_read(&pmd->root_lock);
+ list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) {
+ if (td->changed) {
+ r = td->changed;
+ break;
+ }
+ }
+ up_read(&pmd->root_lock);
+
+ return r;
+}
+
bool dm_thin_aborted_changes(struct dm_thin_device *td)
{
bool r;
@@ -1738,3 +1755,38 @@
return r;
}
+
+int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd)
+{
+ int r;
+ struct dm_block *sblock;
+ struct thin_disk_superblock *disk_super;
+
+ down_write(&pmd->root_lock);
+ pmd->flags |= THIN_METADATA_NEEDS_CHECK_FLAG;
+
+ r = superblock_lock(pmd, &sblock);
+ if (r) {
+ DMERR("couldn't read superblock");
+ goto out;
+ }
+
+ disk_super = dm_block_data(sblock);
+ disk_super->flags = cpu_to_le32(pmd->flags);
+
+ dm_bm_unlock(sblock);
+out:
+ up_write(&pmd->root_lock);
+ return r;
+}
+
+bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd)
+{
+ bool needs_check;
+
+ down_read(&pmd->root_lock);
+ needs_check = pmd->flags & THIN_METADATA_NEEDS_CHECK_FLAG;
+ up_read(&pmd->root_lock);
+
+ return needs_check;
+}
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index 9a36856..e3c857d 100644
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -9,16 +9,14 @@
#include "persistent-data/dm-block-manager.h"
#include "persistent-data/dm-space-map.h"
+#include "persistent-data/dm-space-map-metadata.h"
-#define THIN_METADATA_BLOCK_SIZE 4096
+#define THIN_METADATA_BLOCK_SIZE DM_SM_METADATA_BLOCK_SIZE
/*
* The metadata device is currently limited in size.
- *
- * We have one block of index, which can hold 255 index entries. Each
- * index entry contains allocation info about 16k metadata blocks.
*/
-#define THIN_METADATA_MAX_SECTORS (255 * (1 << 14) * (THIN_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT)))
+#define THIN_METADATA_MAX_SECTORS DM_SM_METADATA_MAX_SECTORS
/*
* A metadata device larger than 16GB triggers a warning.
@@ -27,6 +25,11 @@
/*----------------------------------------------------------------*/
+/*
+ * Thin metadata superblock flags.
+ */
+#define THIN_METADATA_NEEDS_CHECK_FLAG (1 << 0)
+
struct dm_pool_metadata;
struct dm_thin_device;
@@ -161,6 +164,8 @@
*/
bool dm_thin_changed_this_transaction(struct dm_thin_device *td);
+bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd);
+
bool dm_thin_aborted_changes(struct dm_thin_device *td);
int dm_thin_get_highest_mapped_block(struct dm_thin_device *td,
@@ -202,6 +207,12 @@
dm_sm_threshold_fn fn,
void *context);
+/*
+ * Updates the superblock immediately.
+ */
+int dm_pool_metadata_set_needs_check(struct dm_pool_metadata *pmd);
+bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd);
+
/*----------------------------------------------------------------*/
#endif
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index faaf944..be70d38 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -130,10 +130,11 @@
struct dm_thin_new_mapping;
/*
- * The pool runs in 3 modes. Ordered in degraded order for comparisons.
+ * The pool runs in 4 modes. Ordered in degraded order for comparisons.
*/
enum pool_mode {
PM_WRITE, /* metadata may be changed */
+ PM_OUT_OF_DATA_SPACE, /* metadata may be changed, though data may not be allocated */
PM_READ_ONLY, /* metadata may not be changed */
PM_FAIL, /* all I/O fails */
};
@@ -198,7 +199,6 @@
};
static enum pool_mode get_pool_mode(struct pool *pool);
-static void out_of_data_space(struct pool *pool);
static void metadata_operation_failed(struct pool *pool, const char *op, int r);
/*
@@ -226,6 +226,7 @@
struct pool *pool;
struct dm_thin_device *td;
+ bool requeue_mode:1;
};
/*----------------------------------------------------------------*/
@@ -369,14 +370,18 @@
struct dm_thin_new_mapping *overwrite_mapping;
};
-static void __requeue_bio_list(struct thin_c *tc, struct bio_list *master)
+static void requeue_bio_list(struct thin_c *tc, struct bio_list *master)
{
struct bio *bio;
struct bio_list bios;
+ unsigned long flags;
bio_list_init(&bios);
+
+ spin_lock_irqsave(&tc->pool->lock, flags);
bio_list_merge(&bios, master);
bio_list_init(master);
+ spin_unlock_irqrestore(&tc->pool->lock, flags);
while ((bio = bio_list_pop(&bios))) {
struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
@@ -391,12 +396,26 @@
static void requeue_io(struct thin_c *tc)
{
struct pool *pool = tc->pool;
+
+ requeue_bio_list(tc, &pool->deferred_bios);
+ requeue_bio_list(tc, &pool->retry_on_resume_list);
+}
+
+static void error_retry_list(struct pool *pool)
+{
+ struct bio *bio;
unsigned long flags;
+ struct bio_list bios;
+
+ bio_list_init(&bios);
spin_lock_irqsave(&pool->lock, flags);
- __requeue_bio_list(tc, &pool->deferred_bios);
- __requeue_bio_list(tc, &pool->retry_on_resume_list);
+ bio_list_merge(&bios, &pool->retry_on_resume_list);
+ bio_list_init(&pool->retry_on_resume_list);
spin_unlock_irqrestore(&pool->lock, flags);
+
+ while ((bio = bio_list_pop(&bios)))
+ bio_io_error(bio);
}
/*
@@ -925,13 +944,15 @@
}
}
+static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
+
static int alloc_data_block(struct thin_c *tc, dm_block_t *result)
{
int r;
dm_block_t free_blocks;
struct pool *pool = tc->pool;
- if (get_pool_mode(pool) != PM_WRITE)
+ if (WARN_ON(get_pool_mode(pool) != PM_WRITE))
return -EINVAL;
r = dm_pool_get_free_block_count(pool->pmd, &free_blocks);
@@ -958,7 +979,7 @@
}
if (!free_blocks) {
- out_of_data_space(pool);
+ set_pool_mode(pool, PM_OUT_OF_DATA_SPACE);
return -ENOSPC;
}
}
@@ -988,15 +1009,32 @@
spin_unlock_irqrestore(&pool->lock, flags);
}
+static bool should_error_unserviceable_bio(struct pool *pool)
+{
+ enum pool_mode m = get_pool_mode(pool);
+
+ switch (m) {
+ case PM_WRITE:
+ /* Shouldn't get here */
+ DMERR_LIMIT("bio unserviceable, yet pool is in PM_WRITE mode");
+ return true;
+
+ case PM_OUT_OF_DATA_SPACE:
+ return pool->pf.error_if_no_space;
+
+ case PM_READ_ONLY:
+ case PM_FAIL:
+ return true;
+ default:
+ /* Shouldn't get here */
+ DMERR_LIMIT("bio unserviceable, yet pool has an unknown mode");
+ return true;
+ }
+}
+
static void handle_unserviceable_bio(struct pool *pool, struct bio *bio)
{
- /*
- * When pool is read-only, no cell locking is needed because
- * nothing is changing.
- */
- WARN_ON_ONCE(get_pool_mode(pool) != PM_READ_ONLY);
-
- if (pool->pf.error_if_no_space)
+ if (should_error_unserviceable_bio(pool))
bio_io_error(bio);
else
retry_on_resume(bio);
@@ -1007,11 +1045,20 @@
struct bio *bio;
struct bio_list bios;
+ if (should_error_unserviceable_bio(pool)) {
+ cell_error(pool, cell);
+ return;
+ }
+
bio_list_init(&bios);
cell_release(pool, cell, &bios);
- while ((bio = bio_list_pop(&bios)))
- handle_unserviceable_bio(pool, bio);
+ if (should_error_unserviceable_bio(pool))
+ while ((bio = bio_list_pop(&bios)))
+ bio_io_error(bio);
+ else
+ while ((bio = bio_list_pop(&bios)))
+ retry_on_resume(bio);
}
static void process_discard(struct thin_c *tc, struct bio *bio)
@@ -1296,6 +1343,11 @@
}
}
+static void process_bio_success(struct thin_c *tc, struct bio *bio)
+{
+ bio_endio(bio, 0);
+}
+
static void process_bio_fail(struct thin_c *tc, struct bio *bio)
{
bio_io_error(bio);
@@ -1328,6 +1380,11 @@
struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
struct thin_c *tc = h->tc;
+ if (tc->requeue_mode) {
+ bio_endio(bio, DM_ENDIO_REQUEUE);
+ continue;
+ }
+
/*
* If we've got no free new_mapping structs, and processing
* this bio might require one, we pause until there are some
@@ -1357,7 +1414,8 @@
bio_list_init(&pool->deferred_flush_bios);
spin_unlock_irqrestore(&pool->lock, flags);
- if (bio_list_empty(&bios) && !need_commit_due_to_time(pool))
+ if (bio_list_empty(&bios) &&
+ !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool)))
return;
if (commit(pool)) {
@@ -1393,51 +1451,134 @@
/*----------------------------------------------------------------*/
+struct noflush_work {
+ struct work_struct worker;
+ struct thin_c *tc;
+
+ atomic_t complete;
+ wait_queue_head_t wait;
+};
+
+static void complete_noflush_work(struct noflush_work *w)
+{
+ atomic_set(&w->complete, 1);
+ wake_up(&w->wait);
+}
+
+static void do_noflush_start(struct work_struct *ws)
+{
+ struct noflush_work *w = container_of(ws, struct noflush_work, worker);
+ w->tc->requeue_mode = true;
+ requeue_io(w->tc);
+ complete_noflush_work(w);
+}
+
+static void do_noflush_stop(struct work_struct *ws)
+{
+ struct noflush_work *w = container_of(ws, struct noflush_work, worker);
+ w->tc->requeue_mode = false;
+ complete_noflush_work(w);
+}
+
+static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *))
+{
+ struct noflush_work w;
+
+ INIT_WORK(&w.worker, fn);
+ w.tc = tc;
+ atomic_set(&w.complete, 0);
+ init_waitqueue_head(&w.wait);
+
+ queue_work(tc->pool->wq, &w.worker);
+
+ wait_event(w.wait, atomic_read(&w.complete));
+}
+
+/*----------------------------------------------------------------*/
+
static enum pool_mode get_pool_mode(struct pool *pool)
{
return pool->pf.mode;
}
+static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode)
+{
+ dm_table_event(pool->ti->table);
+ DMINFO("%s: switching pool to %s mode",
+ dm_device_name(pool->pool_md), new_mode);
+}
+
static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
{
- int r;
- enum pool_mode old_mode = pool->pf.mode;
+ struct pool_c *pt = pool->ti->private;
+ bool needs_check = dm_pool_metadata_needs_check(pool->pmd);
+ enum pool_mode old_mode = get_pool_mode(pool);
+
+ /*
+ * Never allow the pool to transition to PM_WRITE mode if user
+ * intervention is required to verify metadata and data consistency.
+ */
+ if (new_mode == PM_WRITE && needs_check) {
+ DMERR("%s: unable to switch pool to write mode until repaired.",
+ dm_device_name(pool->pool_md));
+ if (old_mode != new_mode)
+ new_mode = old_mode;
+ else
+ new_mode = PM_READ_ONLY;
+ }
+ /*
+ * If we were in PM_FAIL mode, rollback of metadata failed. We're
+ * not going to recover without a thin_repair. So we never let the
+ * pool move out of the old mode.
+ */
+ if (old_mode == PM_FAIL)
+ new_mode = old_mode;
switch (new_mode) {
case PM_FAIL:
if (old_mode != new_mode)
- DMERR("%s: switching pool to failure mode",
- dm_device_name(pool->pool_md));
+ notify_of_pool_mode_change(pool, "failure");
dm_pool_metadata_read_only(pool->pmd);
pool->process_bio = process_bio_fail;
pool->process_discard = process_bio_fail;
pool->process_prepared_mapping = process_prepared_mapping_fail;
pool->process_prepared_discard = process_prepared_discard_fail;
+
+ error_retry_list(pool);
break;
case PM_READ_ONLY:
if (old_mode != new_mode)
- DMERR("%s: switching pool to read-only mode",
- dm_device_name(pool->pool_md));
- r = dm_pool_abort_metadata(pool->pmd);
- if (r) {
- DMERR("%s: aborting transaction failed",
- dm_device_name(pool->pool_md));
- new_mode = PM_FAIL;
- set_pool_mode(pool, new_mode);
- } else {
- dm_pool_metadata_read_only(pool->pmd);
- pool->process_bio = process_bio_read_only;
- pool->process_discard = process_discard;
- pool->process_prepared_mapping = process_prepared_mapping_fail;
- pool->process_prepared_discard = process_prepared_discard_passdown;
- }
+ notify_of_pool_mode_change(pool, "read-only");
+ dm_pool_metadata_read_only(pool->pmd);
+ pool->process_bio = process_bio_read_only;
+ pool->process_discard = process_bio_success;
+ pool->process_prepared_mapping = process_prepared_mapping_fail;
+ pool->process_prepared_discard = process_prepared_discard_passdown;
+
+ error_retry_list(pool);
+ break;
+
+ case PM_OUT_OF_DATA_SPACE:
+ /*
+ * Ideally we'd never hit this state; the low water mark
+ * would trigger userland to extend the pool before we
+ * completely run out of data space. However, many small
+ * IOs to unprovisioned space can consume data space at an
+ * alarming rate. Adjust your low water mark if you're
+ * frequently seeing this mode.
+ */
+ if (old_mode != new_mode)
+ notify_of_pool_mode_change(pool, "out-of-data-space");
+ pool->process_bio = process_bio_read_only;
+ pool->process_discard = process_discard;
+ pool->process_prepared_mapping = process_prepared_mapping;
+ pool->process_prepared_discard = process_prepared_discard_passdown;
break;
case PM_WRITE:
if (old_mode != new_mode)
- DMINFO("%s: switching pool to write mode",
- dm_device_name(pool->pool_md));
+ notify_of_pool_mode_change(pool, "write");
dm_pool_metadata_read_write(pool->pmd);
pool->process_bio = process_bio;
pool->process_discard = process_discard;
@@ -1447,32 +1588,35 @@
}
pool->pf.mode = new_mode;
+ /*
+ * The pool mode may have changed, sync it so bind_control_target()
+ * doesn't cause an unexpected mode transition on resume.
+ */
+ pt->adjusted_pf.mode = new_mode;
}
-/*
- * Rather than calling set_pool_mode directly, use these which describe the
- * reason for mode degradation.
- */
-static void out_of_data_space(struct pool *pool)
+static void abort_transaction(struct pool *pool)
{
- DMERR_LIMIT("%s: no free data space available.",
- dm_device_name(pool->pool_md));
- set_pool_mode(pool, PM_READ_ONLY);
+ const char *dev_name = dm_device_name(pool->pool_md);
+
+ DMERR_LIMIT("%s: aborting current metadata transaction", dev_name);
+ if (dm_pool_abort_metadata(pool->pmd)) {
+ DMERR("%s: failed to abort metadata transaction", dev_name);
+ set_pool_mode(pool, PM_FAIL);
+ }
+
+ if (dm_pool_metadata_set_needs_check(pool->pmd)) {
+ DMERR("%s: failed to set 'needs_check' flag in metadata", dev_name);
+ set_pool_mode(pool, PM_FAIL);
+ }
}
static void metadata_operation_failed(struct pool *pool, const char *op, int r)
{
- dm_block_t free_blocks;
-
DMERR_LIMIT("%s: metadata operation '%s' failed: error = %d",
dm_device_name(pool->pool_md), op, r);
- if (r == -ENOSPC &&
- !dm_pool_get_free_metadata_block_count(pool->pmd, &free_blocks) &&
- !free_blocks)
- DMERR_LIMIT("%s: no free metadata space available.",
- dm_device_name(pool->pool_md));
-
+ abort_transaction(pool);
set_pool_mode(pool, PM_READ_ONLY);
}
@@ -1523,6 +1667,11 @@
thin_hook_bio(tc, bio);
+ if (tc->requeue_mode) {
+ bio_endio(bio, DM_ENDIO_REQUEUE);
+ return DM_MAPIO_SUBMITTED;
+ }
+
if (get_pool_mode(tc->pool) == PM_FAIL) {
bio_io_error(bio);
return DM_MAPIO_SUBMITTED;
@@ -1686,7 +1835,7 @@
/*
* We want to make sure that a pool in PM_FAIL mode is never upgraded.
*/
- enum pool_mode old_mode = pool->pf.mode;
+ enum pool_mode old_mode = get_pool_mode(pool);
enum pool_mode new_mode = pt->adjusted_pf.mode;
/*
@@ -1700,16 +1849,6 @@
pool->pf = pt->adjusted_pf;
pool->low_water_blocks = pt->low_water_blocks;
- /*
- * If we were in PM_FAIL mode, rollback of metadata failed. We're
- * not going to recover without a thin_repair. So we never let the
- * pool move out of the old mode. On the other hand a PM_READ_ONLY
- * may have been due to a lack of metadata or data space, and may
- * now work (ie. if the underlying devices have been resized).
- */
- if (old_mode == PM_FAIL)
- new_mode = old_mode;
-
set_pool_mode(pool, new_mode);
return 0;
@@ -1999,16 +2138,27 @@
dm_table_event(pool->ti->table);
}
-static sector_t get_metadata_dev_size(struct block_device *bdev)
+static sector_t get_dev_size(struct block_device *bdev)
{
- sector_t metadata_dev_size = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+ return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+}
+
+static void warn_if_metadata_device_too_big(struct block_device *bdev)
+{
+ sector_t metadata_dev_size = get_dev_size(bdev);
char buffer[BDEVNAME_SIZE];
- if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING) {
+ if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING)
DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.",
bdevname(bdev, buffer), THIN_METADATA_MAX_SECTORS);
- metadata_dev_size = THIN_METADATA_MAX_SECTORS_WARNING;
- }
+}
+
+static sector_t get_metadata_dev_size(struct block_device *bdev)
+{
+ sector_t metadata_dev_size = get_dev_size(bdev);
+
+ if (metadata_dev_size > THIN_METADATA_MAX_SECTORS)
+ metadata_dev_size = THIN_METADATA_MAX_SECTORS;
return metadata_dev_size;
}
@@ -2017,7 +2167,7 @@
{
sector_t metadata_dev_size = get_metadata_dev_size(bdev);
- sector_div(metadata_dev_size, THIN_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
+ sector_div(metadata_dev_size, THIN_METADATA_BLOCK_SIZE);
return metadata_dev_size;
}
@@ -2095,12 +2245,7 @@
ti->error = "Error opening metadata block device";
goto out_unlock;
}
-
- /*
- * Run for the side-effect of possibly issuing a warning if the
- * device is too big.
- */
- (void) get_metadata_dev_size(metadata_dev->bdev);
+ warn_if_metadata_device_too_big(metadata_dev->bdev);
r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &data_dev);
if (r) {
@@ -2246,6 +2391,12 @@
return -EINVAL;
} else if (data_size > sb_data_size) {
+ if (dm_pool_metadata_needs_check(pool->pmd)) {
+ DMERR("%s: unable to grow the data device until repaired.",
+ dm_device_name(pool->pool_md));
+ return 0;
+ }
+
if (sb_data_size)
DMINFO("%s: growing the data device from %llu to %llu blocks",
dm_device_name(pool->pool_md),
@@ -2287,6 +2438,13 @@
return -EINVAL;
} else if (metadata_dev_size > sb_metadata_dev_size) {
+ if (dm_pool_metadata_needs_check(pool->pmd)) {
+ DMERR("%s: unable to grow the metadata device until repaired.",
+ dm_device_name(pool->pool_md));
+ return 0;
+ }
+
+ warn_if_metadata_device_too_big(pool->md_dev);
DMINFO("%s: growing the metadata device from %llu to %llu blocks",
dm_device_name(pool->pool_md),
sb_metadata_dev_size, metadata_dev_size);
@@ -2673,7 +2831,9 @@
else
DMEMIT("- ");
- if (pool->pf.mode == PM_READ_ONLY)
+ if (pool->pf.mode == PM_OUT_OF_DATA_SPACE)
+ DMEMIT("out_of_data_space ");
+ else if (pool->pf.mode == PM_READ_ONLY)
DMEMIT("ro ");
else
DMEMIT("rw ");
@@ -2787,7 +2947,7 @@
.name = "thin-pool",
.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
DM_TARGET_IMMUTABLE,
- .version = {1, 10, 0},
+ .version = {1, 11, 0},
.module = THIS_MODULE,
.ctr = pool_ctr,
.dtr = pool_dtr,
@@ -2894,6 +3054,7 @@
if (get_pool_mode(tc->pool) == PM_FAIL) {
ti->error = "Couldn't open thin device, Pool is in fail mode";
+ r = -EINVAL;
goto bad_thin_open;
}
@@ -2905,7 +3066,7 @@
r = dm_set_target_max_io_len(ti, tc->pool->sectors_per_block);
if (r)
- goto bad_thin_open;
+ goto bad_target_max_io_len;
ti->num_flush_bios = 1;
ti->flush_supported = true;
@@ -2926,6 +3087,8 @@
return 0;
+bad_target_max_io_len:
+ dm_pool_close_thin_device(tc->td);
bad_thin_open:
__pool_dec(tc->pool);
bad_pool_lookup:
@@ -2986,10 +3149,23 @@
return 0;
}
+static void thin_presuspend(struct dm_target *ti)
+{
+ struct thin_c *tc = ti->private;
+
+ if (dm_noflush_suspending(ti))
+ noflush_work(tc, do_noflush_start);
+}
+
static void thin_postsuspend(struct dm_target *ti)
{
- if (dm_noflush_suspending(ti))
- requeue_io((struct thin_c *)ti->private);
+ struct thin_c *tc = ti->private;
+
+ /*
+ * The dm_noflush_suspending flag has been cleared by now, so
+ * unfortunately we must always run this.
+ */
+ noflush_work(tc, do_noflush_stop);
}
/*
@@ -3074,12 +3250,13 @@
static struct target_type thin_target = {
.name = "thin",
- .version = {1, 10, 0},
+ .version = {1, 11, 0},
.module = THIS_MODULE,
.ctr = thin_ctr,
.dtr = thin_dtr,
.map = thin_map,
.end_io = thin_endio,
+ .presuspend = thin_presuspend,
.postsuspend = thin_postsuspend,
.status = thin_status,
.iterate_devices = thin_iterate_devices,
diff --git a/drivers/md/persistent-data/Kconfig b/drivers/md/persistent-data/Kconfig
index 19b2687..0c2dec7 100644
--- a/drivers/md/persistent-data/Kconfig
+++ b/drivers/md/persistent-data/Kconfig
@@ -6,3 +6,13 @@
---help---
Library providing immutable on-disk data structure support for
device-mapper targets such as the thin provisioning target.
+
+config DM_DEBUG_BLOCK_STACK_TRACING
+ boolean "Keep stack trace of persistent data block lock holders"
+ depends on STACKTRACE_SUPPORT && DM_PERSISTENT_DATA
+ select STACKTRACE
+ ---help---
+ Enable this for messages that may help debug problems with the
+ block manager locking used by thin provisioning and caching.
+
+ If unsure, say N.
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 536782e..786b689 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -91,6 +91,69 @@
dm_block_t block;
};
+struct bop_ring_buffer {
+ unsigned begin;
+ unsigned end;
+ struct block_op bops[MAX_RECURSIVE_ALLOCATIONS + 1];
+};
+
+static void brb_init(struct bop_ring_buffer *brb)
+{
+ brb->begin = 0;
+ brb->end = 0;
+}
+
+static bool brb_empty(struct bop_ring_buffer *brb)
+{
+ return brb->begin == brb->end;
+}
+
+static unsigned brb_next(struct bop_ring_buffer *brb, unsigned old)
+{
+ unsigned r = old + 1;
+ return (r >= (sizeof(brb->bops) / sizeof(*brb->bops))) ? 0 : r;
+}
+
+static int brb_push(struct bop_ring_buffer *brb,
+ enum block_op_type type, dm_block_t b)
+{
+ struct block_op *bop;
+ unsigned next = brb_next(brb, brb->end);
+
+ /*
+ * We don't allow the last bop to be filled, this way we can
+ * differentiate between full and empty.
+ */
+ if (next == brb->begin)
+ return -ENOMEM;
+
+ bop = brb->bops + brb->end;
+ bop->type = type;
+ bop->block = b;
+
+ brb->end = next;
+
+ return 0;
+}
+
+static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result)
+{
+ struct block_op *bop;
+
+ if (brb_empty(brb))
+ return -ENODATA;
+
+ bop = brb->bops + brb->begin;
+ result->type = bop->type;
+ result->block = bop->block;
+
+ brb->begin = brb_next(brb, brb->begin);
+
+ return 0;
+}
+
+/*----------------------------------------------------------------*/
+
struct sm_metadata {
struct dm_space_map sm;
@@ -101,25 +164,20 @@
unsigned recursion_count;
unsigned allocated_this_transaction;
- unsigned nr_uncommitted;
- struct block_op uncommitted[MAX_RECURSIVE_ALLOCATIONS];
+ struct bop_ring_buffer uncommitted;
struct threshold threshold;
};
static int add_bop(struct sm_metadata *smm, enum block_op_type type, dm_block_t b)
{
- struct block_op *op;
+ int r = brb_push(&smm->uncommitted, type, b);
- if (smm->nr_uncommitted == MAX_RECURSIVE_ALLOCATIONS) {
+ if (r) {
DMERR("too many recursive allocations");
return -ENOMEM;
}
- op = smm->uncommitted + smm->nr_uncommitted++;
- op->type = type;
- op->block = b;
-
return 0;
}
@@ -158,11 +216,17 @@
return -ENOMEM;
}
- if (smm->recursion_count == 1 && smm->nr_uncommitted) {
- while (smm->nr_uncommitted && !r) {
- smm->nr_uncommitted--;
- r = commit_bop(smm, smm->uncommitted +
- smm->nr_uncommitted);
+ if (smm->recursion_count == 1) {
+ while (!brb_empty(&smm->uncommitted)) {
+ struct block_op bop;
+
+ r = brb_pop(&smm->uncommitted, &bop);
+ if (r) {
+ DMERR("bug in bop ring buffer");
+ break;
+ }
+
+ r = commit_bop(smm, &bop);
if (r)
break;
}
@@ -217,7 +281,8 @@
static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b,
uint32_t *result)
{
- int r, i;
+ int r;
+ unsigned i;
struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
unsigned adjustment = 0;
@@ -225,8 +290,10 @@
* We may have some uncommitted adjustments to add. This list
* should always be really short.
*/
- for (i = 0; i < smm->nr_uncommitted; i++) {
- struct block_op *op = smm->uncommitted + i;
+ for (i = smm->uncommitted.begin;
+ i != smm->uncommitted.end;
+ i = brb_next(&smm->uncommitted, i)) {
+ struct block_op *op = smm->uncommitted.bops + i;
if (op->block != b)
continue;
@@ -254,7 +321,8 @@
static int sm_metadata_count_is_more_than_one(struct dm_space_map *sm,
dm_block_t b, int *result)
{
- int r, i, adjustment = 0;
+ int r, adjustment = 0;
+ unsigned i;
struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
uint32_t rc;
@@ -262,8 +330,11 @@
* We may have some uncommitted adjustments to add. This list
* should always be really short.
*/
- for (i = 0; i < smm->nr_uncommitted; i++) {
- struct block_op *op = smm->uncommitted + i;
+ for (i = smm->uncommitted.begin;
+ i != smm->uncommitted.end;
+ i = brb_next(&smm->uncommitted, i)) {
+
+ struct block_op *op = smm->uncommitted.bops + i;
if (op->block != b)
continue;
@@ -671,7 +742,7 @@
smm->begin = superblock + 1;
smm->recursion_count = 0;
smm->allocated_this_transaction = 0;
- smm->nr_uncommitted = 0;
+ brb_init(&smm->uncommitted);
threshold_init(&smm->threshold);
memcpy(&smm->sm, &bootstrap_ops, sizeof(smm->sm));
@@ -680,6 +751,8 @@
if (r)
return r;
+ if (nr_blocks > DM_SM_METADATA_MAX_BLOCKS)
+ nr_blocks = DM_SM_METADATA_MAX_BLOCKS;
r = sm_ll_extend(&smm->ll, nr_blocks);
if (r)
return r;
@@ -713,7 +786,7 @@
smm->begin = 0;
smm->recursion_count = 0;
smm->allocated_this_transaction = 0;
- smm->nr_uncommitted = 0;
+ brb_init(&smm->uncommitted);
threshold_init(&smm->threshold);
memcpy(&smm->old_ll, &smm->ll, sizeof(smm->old_ll));
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.h b/drivers/md/persistent-data/dm-space-map-metadata.h
index 39bba08..64df923 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.h
+++ b/drivers/md/persistent-data/dm-space-map-metadata.h
@@ -9,6 +9,17 @@
#include "dm-transaction-manager.h"
+#define DM_SM_METADATA_BLOCK_SIZE (4096 >> SECTOR_SHIFT)
+
+/*
+ * The metadata device is currently limited in size.
+ *
+ * We have one block of index, which can hold 255 index entries. Each
+ * index entry contains allocation info about ~16k metadata blocks.
+ */
+#define DM_SM_METADATA_MAX_BLOCKS (255 * ((1 << 14) - 64))
+#define DM_SM_METADATA_MAX_SECTORS (DM_SM_METADATA_MAX_BLOCKS * DM_SM_METADATA_BLOCK_SIZE)
+
/*
* Unfortunately we have to use two-phase construction due to the cycle
* between the tm and sm.
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index fd3a2a1..4a6ca1c 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1953,11 +1953,15 @@
for (i = 0; i < conf->raid_disks * 2; i++) {
int j;
int size;
+ int uptodate;
struct bio *b = r1_bio->bios[i];
if (b->bi_end_io != end_sync_read)
continue;
- /* fixup the bio for reuse */
+ /* fixup the bio for reuse, but preserve BIO_UPTODATE */
+ uptodate = test_bit(BIO_UPTODATE, &b->bi_flags);
bio_reset(b);
+ if (!uptodate)
+ clear_bit(BIO_UPTODATE, &b->bi_flags);
b->bi_vcnt = vcnt;
b->bi_iter.bi_size = r1_bio->sectors << 9;
b->bi_iter.bi_sector = r1_bio->sector +
@@ -1990,11 +1994,14 @@
int j;
struct bio *pbio = r1_bio->bios[primary];
struct bio *sbio = r1_bio->bios[i];
+ int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags);
if (sbio->bi_end_io != end_sync_read)
continue;
+ /* Now we can 'fixup' the BIO_UPTODATE flag */
+ set_bit(BIO_UPTODATE, &sbio->bi_flags);
- if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) {
+ if (uptodate) {
for (j = vcnt; j-- ; ) {
struct page *p, *s;
p = pbio->bi_io_vec[j].bv_page;
@@ -2009,7 +2016,7 @@
if (j >= 0)
atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
- && test_bit(BIO_UPTODATE, &sbio->bi_flags))) {
+ && uptodate)) {
/* No need to write to this device. */
sbio->bi_end_io = NULL;
rdev_dec_pending(conf->mirrors[i].rdev, mddev);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f1feade..16f5c21 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5514,23 +5514,43 @@
return sectors * (raid_disks - conf->max_degraded);
}
+static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
+{
+ safe_put_page(percpu->spare_page);
+ kfree(percpu->scribble);
+ percpu->spare_page = NULL;
+ percpu->scribble = NULL;
+}
+
+static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
+{
+ if (conf->level == 6 && !percpu->spare_page)
+ percpu->spare_page = alloc_page(GFP_KERNEL);
+ if (!percpu->scribble)
+ percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
+
+ if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) {
+ free_scratch_buffer(conf, percpu);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
static void raid5_free_percpu(struct r5conf *conf)
{
- struct raid5_percpu *percpu;
unsigned long cpu;
if (!conf->percpu)
return;
- get_online_cpus();
- for_each_possible_cpu(cpu) {
- percpu = per_cpu_ptr(conf->percpu, cpu);
- safe_put_page(percpu->spare_page);
- kfree(percpu->scribble);
- }
#ifdef CONFIG_HOTPLUG_CPU
unregister_cpu_notifier(&conf->cpu_notify);
#endif
+
+ get_online_cpus();
+ for_each_possible_cpu(cpu)
+ free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
put_online_cpus();
free_percpu(conf->percpu);
@@ -5557,15 +5577,7 @@
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- if (conf->level == 6 && !percpu->spare_page)
- percpu->spare_page = alloc_page(GFP_KERNEL);
- if (!percpu->scribble)
- percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
-
- if (!percpu->scribble ||
- (conf->level == 6 && !percpu->spare_page)) {
- safe_put_page(percpu->spare_page);
- kfree(percpu->scribble);
+ if (alloc_scratch_buffer(conf, percpu)) {
pr_err("%s: failed memory allocation for cpu%ld\n",
__func__, cpu);
return notifier_from_errno(-ENOMEM);
@@ -5573,10 +5585,7 @@
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
- safe_put_page(percpu->spare_page);
- kfree(percpu->scribble);
- percpu->spare_page = NULL;
- percpu->scribble = NULL;
+ free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
break;
default:
break;
@@ -5588,40 +5597,29 @@
static int raid5_alloc_percpu(struct r5conf *conf)
{
unsigned long cpu;
- struct page *spare_page;
- struct raid5_percpu __percpu *allcpus;
- void *scribble;
- int err;
+ int err = 0;
- allcpus = alloc_percpu(struct raid5_percpu);
- if (!allcpus)
+ conf->percpu = alloc_percpu(struct raid5_percpu);
+ if (!conf->percpu)
return -ENOMEM;
- conf->percpu = allcpus;
- get_online_cpus();
- err = 0;
- for_each_present_cpu(cpu) {
- if (conf->level == 6) {
- spare_page = alloc_page(GFP_KERNEL);
- if (!spare_page) {
- err = -ENOMEM;
- break;
- }
- per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page;
- }
- scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
- if (!scribble) {
- err = -ENOMEM;
- break;
- }
- per_cpu_ptr(conf->percpu, cpu)->scribble = scribble;
- }
#ifdef CONFIG_HOTPLUG_CPU
conf->cpu_notify.notifier_call = raid456_cpu_notify;
conf->cpu_notify.priority = 0;
- if (err == 0)
- err = register_cpu_notifier(&conf->cpu_notify);
+ err = register_cpu_notifier(&conf->cpu_notify);
+ if (err)
+ return err;
#endif
+
+ get_online_cpus();
+ for_each_present_cpu(cpu) {
+ err = alloc_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
+ if (err) {
+ pr_err("%s: failed memory allocation for cpu%ld\n",
+ __func__, cpu);
+ break;
+ }
+ }
put_online_cpus();
return err;
diff --git a/drivers/message/i2o/i2o_config.c b/drivers/message/i2o/i2o_config.c
index a60c188..04bd3b6 100644
--- a/drivers/message/i2o/i2o_config.c
+++ b/drivers/message/i2o/i2o_config.c
@@ -754,19 +754,19 @@
unsigned long arg)
{
int ret;
- mutex_lock(&i2o_cfg_mutex);
switch (cmd) {
case I2OGETIOPS:
ret = i2o_cfg_ioctl(file, cmd, arg);
break;
case I2OPASSTHRU32:
+ mutex_lock(&i2o_cfg_mutex);
ret = i2o_cfg_passthru32(file, cmd, arg);
+ mutex_unlock(&i2o_cfg_mutex);
break;
default:
ret = -ENOIOCTLCMD;
break;
}
- mutex_unlock(&i2o_cfg_mutex);
return ret;
}
diff --git a/drivers/mfd/da9055-i2c.c b/drivers/mfd/da9055-i2c.c
index 13af7e5..8103e43 100644
--- a/drivers/mfd/da9055-i2c.c
+++ b/drivers/mfd/da9055-i2c.c
@@ -53,17 +53,25 @@
return 0;
}
+/*
+ * DO NOT change the device Ids. The naming is intentionally specific as both
+ * the PMIC and CODEC parts of this chip are instantiated separately as I2C
+ * devices (both have configurable I2C addresses, and are to all intents and
+ * purposes separate). As a result there are specific DA9055 ids for PMIC
+ * and CODEC, which must be different to operate together.
+ */
static struct i2c_device_id da9055_i2c_id[] = {
- {"da9055", 0},
+ {"da9055-pmic", 0},
{ }
};
+MODULE_DEVICE_TABLE(i2c, da9055_i2c_id);
static struct i2c_driver da9055_i2c_driver = {
.probe = da9055_i2c_probe,
.remove = da9055_i2c_remove,
.id_table = da9055_i2c_id,
.driver = {
- .name = "da9055",
+ .name = "da9055-pmic",
.owner = THIS_MODULE,
},
};
diff --git a/drivers/mfd/max14577.c b/drivers/mfd/max14577.c
index ac514fb..71aa14a 100644
--- a/drivers/mfd/max14577.c
+++ b/drivers/mfd/max14577.c
@@ -173,6 +173,7 @@
};
MODULE_DEVICE_TABLE(i2c, max14577_i2c_id);
+#ifdef CONFIG_PM_SLEEP
static int max14577_suspend(struct device *dev)
{
struct i2c_client *i2c = container_of(dev, struct i2c_client, dev);
@@ -208,6 +209,7 @@
return 0;
}
+#endif /* CONFIG_PM_SLEEP */
static struct of_device_id max14577_dt_match[] = {
{ .compatible = "maxim,max14577", },
diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c
index be88a3b..5adede0 100644
--- a/drivers/mfd/max8997.c
+++ b/drivers/mfd/max8997.c
@@ -164,15 +164,15 @@
return pd;
}
-static inline int max8997_i2c_get_driver_data(struct i2c_client *i2c,
+static inline unsigned long max8997_i2c_get_driver_data(struct i2c_client *i2c,
const struct i2c_device_id *id)
{
if (IS_ENABLED(CONFIG_OF) && i2c->dev.of_node) {
const struct of_device_id *match;
match = of_match_node(max8997_pmic_dt_match, i2c->dev.of_node);
- return (int)match->data;
+ return (unsigned long)match->data;
}
- return (int)id->driver_data;
+ return id->driver_data;
}
static int max8997_i2c_probe(struct i2c_client *i2c,
diff --git a/drivers/mfd/max8998.c b/drivers/mfd/max8998.c
index 612ca40..5d5e186 100644
--- a/drivers/mfd/max8998.c
+++ b/drivers/mfd/max8998.c
@@ -169,16 +169,16 @@
return pd;
}
-static inline int max8998_i2c_get_driver_data(struct i2c_client *i2c,
+static inline unsigned long max8998_i2c_get_driver_data(struct i2c_client *i2c,
const struct i2c_device_id *id)
{
if (IS_ENABLED(CONFIG_OF) && i2c->dev.of_node) {
const struct of_device_id *match;
match = of_match_node(max8998_dt_match, i2c->dev.of_node);
- return (int)(long)match->data;
+ return (unsigned long)match->data;
}
- return (int)id->driver_data;
+ return id->driver_data;
}
static int max8998_i2c_probe(struct i2c_client *i2c,
diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c
index a139798..714e213 100644
--- a/drivers/mfd/sec-core.c
+++ b/drivers/mfd/sec-core.c
@@ -315,6 +315,7 @@
return 0;
}
+#ifdef CONFIG_PM_SLEEP
static int sec_pmic_suspend(struct device *dev)
{
struct i2c_client *i2c = container_of(dev, struct i2c_client, dev);
@@ -349,6 +350,7 @@
return 0;
}
+#endif /* CONFIG_PM_SLEEP */
static SIMPLE_DEV_PM_OPS(sec_pmic_pm_ops, sec_pmic_suspend, sec_pmic_resume);
diff --git a/drivers/mfd/tps65217.c b/drivers/mfd/tps65217.c
index 966cf65..3cc4c70 100644
--- a/drivers/mfd/tps65217.c
+++ b/drivers/mfd/tps65217.c
@@ -158,7 +158,7 @@
{
struct tps65217 *tps;
unsigned int version;
- unsigned int chip_id = ids->driver_data;
+ unsigned long chip_id = ids->driver_data;
const struct of_device_id *match;
bool status_off = false;
int ret;
@@ -170,7 +170,7 @@
"Failed to find matching dt id\n");
return -EINVAL;
}
- chip_id = (unsigned int)(unsigned long)match->data;
+ chip_id = (unsigned long)match->data;
status_off = of_property_read_bool(client->dev.of_node,
"ti,pmic-shutdown-controller");
}
diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c
index ba04f1b..e6fab94 100644
--- a/drivers/mfd/wm8994-core.c
+++ b/drivers/mfd/wm8994-core.c
@@ -636,7 +636,7 @@
if (i2c->dev.of_node) {
of_id = of_match_device(wm8994_of_match, &i2c->dev);
if (of_id)
- wm8994->type = (int)of_id->data;
+ wm8994->type = (enum wm8994_type)of_id->data;
} else {
wm8994->type = id->driver_data;
}
diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c
index 8f8a6b3..2c2c9cc 100644
--- a/drivers/misc/genwqe/card_dev.c
+++ b/drivers/misc/genwqe/card_dev.c
@@ -787,6 +787,7 @@
if (rc != 0) {
dev_err(&pci_dev->dev,
"[%s] genwqe_user_vmap rc=%d\n", __func__, rc);
+ kfree(dma_map);
return rc;
}
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index 1ee2b94..89a5579 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -666,7 +666,6 @@
goto err;
cb->fop_type = MEI_FOP_READ;
- cl->read_cb = cb;
if (dev->hbuf_is_ready) {
dev->hbuf_is_ready = false;
if (mei_hbm_cl_flow_control_req(dev, cl)) {
@@ -678,6 +677,9 @@
} else {
list_add_tail(&cb->list, &dev->ctrl_wr_list.list);
}
+
+ cl->read_cb = cb;
+
return rets;
err:
mei_io_cb_free(cb);
@@ -908,7 +910,6 @@
list_for_each_entry_safe(cl, next, &dev->file_list, link) {
cl->state = MEI_FILE_DISCONNECTED;
cl->mei_flow_ctrl_creds = 0;
- cl->read_cb = NULL;
cl->timer_count = 0;
}
}
@@ -942,8 +943,16 @@
void mei_cl_all_write_clear(struct mei_device *dev)
{
struct mei_cl_cb *cb, *next;
+ struct list_head *list;
- list_for_each_entry_safe(cb, next, &dev->write_list.list, list) {
+ list = &dev->write_list.list;
+ list_for_each_entry_safe(cb, next, list, list) {
+ list_del(&cb->list);
+ mei_io_cb_free(cb);
+ }
+
+ list = &dev->write_waiting_list.list;
+ list_for_each_entry_safe(cb, next, list, list) {
list_del(&cb->list);
mei_io_cb_free(cb);
}
diff --git a/drivers/misc/mic/host/mic_virtio.c b/drivers/misc/mic/host/mic_virtio.c
index 752ff87..7e1ef0e 100644
--- a/drivers/misc/mic/host/mic_virtio.c
+++ b/drivers/misc/mic/host/mic_virtio.c
@@ -156,7 +156,8 @@
static int _mic_virtio_copy(struct mic_vdev *mvdev,
struct mic_copy_desc *copy)
{
- int ret = 0, iovcnt = copy->iovcnt;
+ int ret = 0;
+ u32 iovcnt = copy->iovcnt;
struct iovec iov;
struct iovec __user *u_iov = copy->iov;
void __user *ubuf = NULL;
diff --git a/drivers/misc/sgi-gru/grukdump.c b/drivers/misc/sgi-gru/grukdump.c
index 9b2062d..2bef3f7 100644
--- a/drivers/misc/sgi-gru/grukdump.c
+++ b/drivers/misc/sgi-gru/grukdump.c
@@ -139,8 +139,11 @@
ubuf += sizeof(hdr);
ubufcch = ubuf;
- if (gru_user_copy_handle(&ubuf, cch))
- goto fail;
+ if (gru_user_copy_handle(&ubuf, cch)) {
+ if (cch_locked)
+ unlock_cch_handle(cch);
+ return -EFAULT;
+ }
if (cch_locked)
ubufcch->delresp = 0;
bytes = sizeof(hdr) + GRU_CACHE_LINE_BYTES;
@@ -179,10 +182,6 @@
ret = -EFAULT;
return ret ? ret : bytes;
-
-fail:
- unlock_cch_handle(cch);
- return -EFAULT;
}
int gru_dump_chiplet_request(unsigned long arg)
diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c
index b9e2000..95c8944 100644
--- a/drivers/misc/sgi-xp/xpc_uv.c
+++ b/drivers/misc/sgi-xp/xpc_uv.c
@@ -240,7 +240,7 @@
nid = cpu_to_node(cpu);
page = alloc_pages_exact_node(nid,
- GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
pg_order);
if (page == NULL) {
dev_err(xpc_part, "xpc_create_gru_mq_uv() failed to alloc %d "
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index 357bbc5..3e049c1 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -197,7 +197,7 @@
struct mmc_queue_req *mqrq_prev = &mq->mqrq[1];
if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask)
- limit = dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT;
+ limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT;
mq->card = card;
mq->queue = blk_init_queue(mmc_request_fn, lock);
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 59eba5d..9715a7b 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -1584,7 +1584,7 @@
}
if (mtd->ecc_stats.failed - ecc_failures) {
- if (retry_mode + 1 <= chip->read_retries) {
+ if (retry_mode + 1 < chip->read_retries) {
retry_mode++;
ret = nand_setup_read_retry(mtd,
retry_mode);
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index ef4190a..bf642ce 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -1633,6 +1633,7 @@
int i;
dma_cap_mask_t mask;
unsigned sig;
+ unsigned oob_index;
struct resource *res;
struct mtd_part_parser_data ppdata = {};
@@ -1826,11 +1827,14 @@
(mtd->writesize /
nand_chip->ecc.size);
if (nand_chip->options & NAND_BUSWIDTH_16)
- ecclayout->eccpos[0] = BADBLOCK_MARKER_LENGTH;
+ oob_index = BADBLOCK_MARKER_LENGTH;
else
- ecclayout->eccpos[0] = 1;
- ecclayout->oobfree->offset = ecclayout->eccpos[0] +
- ecclayout->eccbytes;
+ oob_index = 1;
+ for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
+ ecclayout->eccpos[i] = oob_index;
+ /* no reserved-marker in ecclayout for this ecc-scheme */
+ ecclayout->oobfree->offset =
+ ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
break;
case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
@@ -1847,9 +1851,15 @@
ecclayout->eccbytes = nand_chip->ecc.bytes *
(mtd->writesize /
nand_chip->ecc.size);
- ecclayout->eccpos[0] = BADBLOCK_MARKER_LENGTH;
- ecclayout->oobfree->offset = ecclayout->eccpos[0] +
- ecclayout->eccbytes;
+ oob_index = BADBLOCK_MARKER_LENGTH;
+ for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) {
+ ecclayout->eccpos[i] = oob_index;
+ if (((i + 1) % nand_chip->ecc.bytes) == 0)
+ oob_index++;
+ }
+ /* include reserved-marker in ecclayout->oobfree calculation */
+ ecclayout->oobfree->offset = 1 +
+ ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
/* software bch library is used for locating errors */
nand_chip->ecc.priv = nand_bch_init(mtd,
nand_chip->ecc.size,
@@ -1883,9 +1893,12 @@
ecclayout->eccbytes = nand_chip->ecc.bytes *
(mtd->writesize /
nand_chip->ecc.size);
- ecclayout->eccpos[0] = BADBLOCK_MARKER_LENGTH;
- ecclayout->oobfree->offset = ecclayout->eccpos[0] +
- ecclayout->eccbytes;
+ oob_index = BADBLOCK_MARKER_LENGTH;
+ for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
+ ecclayout->eccpos[i] = oob_index;
+ /* reserved marker already included in ecclayout->eccbytes */
+ ecclayout->oobfree->offset =
+ ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
/* This ECC scheme requires ELM H/W block */
if (is_elm_present(info, pdata->elm_of_node, BCH4_ECC) < 0) {
pr_err("nand: error: could not initialize ELM\n");
@@ -1913,9 +1926,15 @@
ecclayout->eccbytes = nand_chip->ecc.bytes *
(mtd->writesize /
nand_chip->ecc.size);
- ecclayout->eccpos[0] = BADBLOCK_MARKER_LENGTH;
- ecclayout->oobfree->offset = ecclayout->eccpos[0] +
- ecclayout->eccbytes;
+ oob_index = BADBLOCK_MARKER_LENGTH;
+ for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) {
+ ecclayout->eccpos[i] = oob_index;
+ if (((i + 1) % nand_chip->ecc.bytes) == 0)
+ oob_index++;
+ }
+ /* include reserved-marker in ecclayout->oobfree calculation */
+ ecclayout->oobfree->offset = 1 +
+ ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
/* software bch library is used for locating errors */
nand_chip->ecc.priv = nand_bch_init(mtd,
nand_chip->ecc.size,
@@ -1956,9 +1975,12 @@
ecclayout->eccbytes = nand_chip->ecc.bytes *
(mtd->writesize /
nand_chip->ecc.size);
- ecclayout->eccpos[0] = BADBLOCK_MARKER_LENGTH;
- ecclayout->oobfree->offset = ecclayout->eccpos[0] +
- ecclayout->eccbytes;
+ oob_index = BADBLOCK_MARKER_LENGTH;
+ for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
+ ecclayout->eccpos[i] = oob_index;
+ /* reserved marker already included in ecclayout->eccbytes */
+ ecclayout->oobfree->offset =
+ ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
break;
#else
pr_err("nand: error: CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
@@ -1972,11 +1994,8 @@
goto return_error;
}
- /* populate remaining ECC layout data */
- ecclayout->oobfree->length = mtd->oobsize - (BADBLOCK_MARKER_LENGTH +
- ecclayout->eccbytes);
- for (i = 1; i < ecclayout->eccbytes; i++)
- ecclayout->eccpos[i] = ecclayout->eccpos[0] + i;
+ /* all OOB bytes from oobfree->offset till end off OOB are free */
+ ecclayout->oobfree->length = mtd->oobsize - ecclayout->oobfree->offset;
/* check if NAND device's OOB is enough to store ECC signatures */
if (mtd->oobsize < (ecclayout->eccbytes + BADBLOCK_MARKER_LENGTH)) {
pr_err("not enough OOB bytes required = %d, available=%d\n",
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index ead8613..c5dad65 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -463,8 +463,8 @@
}
}
if (found_orphan) {
- kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
list_del(&tmp_aeb->u.list);
+ kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
}
new_aeb = kmem_cache_alloc(ai->aeb_slab_cache,
@@ -846,16 +846,16 @@
ret = UBI_BAD_FASTMAP;
fail:
list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &used, u.list) {
- kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
list_del(&tmp_aeb->u.list);
+ kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
}
list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &eba_orphans, u.list) {
- kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
list_del(&tmp_aeb->u.list);
+ kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
}
list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &free, u.list) {
- kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
list_del(&tmp_aeb->u.list);
+ kmem_cache_free(ai->aeb_slab_cache, tmp_aeb);
}
return ret;
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index f342278..89402c3 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -139,7 +139,7 @@
This adds a specialized tap character device driver that is based
on the MAC-VLAN network interface, called macvtap. A macvtap device
can be added in the same way as a macvlan device, using 'type
- macvlan', and then be accessed through the tap user space interface.
+ macvtap', and then be accessed through the tap user space interface.
To compile this driver as a module, choose M here: the module
will be called macvtap.
@@ -177,11 +177,6 @@
config NETPOLL
def_bool NETCONSOLE
-config NETPOLL_TRAP
- bool "Netpoll traffic trapping"
- default n
- depends on NETPOLL
-
config NET_POLL_CONTROLLER
def_bool NETPOLL
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index cce1f1b..b667a51 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -181,7 +181,7 @@
*/
static inline void __disable_port(struct port *port)
{
- bond_set_slave_inactive_flags(port->slave);
+ bond_set_slave_inactive_flags(port->slave, BOND_SLAVE_NOTIFY_LATER);
}
/**
@@ -193,7 +193,7 @@
struct slave *slave = port->slave;
if ((slave->link == BOND_LINK_UP) && IS_UP(slave->dev))
- bond_set_slave_active_flags(slave);
+ bond_set_slave_active_flags(slave, BOND_SLAVE_NOTIFY_LATER);
}
/**
@@ -768,11 +768,11 @@
lacpdu_header = (struct lacpdu_header *)skb_put(skb, length);
- memcpy(lacpdu_header->hdr.h_dest, lacpdu_mcast_addr, ETH_ALEN);
+ ether_addr_copy(lacpdu_header->hdr.h_dest, lacpdu_mcast_addr);
/* Note: source address is set to be the member's PERMANENT address,
* because we use it to identify loopback lacpdus in receive.
*/
- memcpy(lacpdu_header->hdr.h_source, slave->perm_hwaddr, ETH_ALEN);
+ ether_addr_copy(lacpdu_header->hdr.h_source, slave->perm_hwaddr);
lacpdu_header->hdr.h_proto = PKT_TYPE_LACPDU;
lacpdu_header->lacpdu = port->lacpdu;
@@ -810,11 +810,11 @@
marker_header = (struct bond_marker_header *)skb_put(skb, length);
- memcpy(marker_header->hdr.h_dest, lacpdu_mcast_addr, ETH_ALEN);
+ ether_addr_copy(marker_header->hdr.h_dest, lacpdu_mcast_addr);
/* Note: source address is set to be the member's PERMANENT address,
* because we use it to identify loopback MARKERs in receive.
*/
- memcpy(marker_header->hdr.h_source, slave->perm_hwaddr, ETH_ALEN);
+ ether_addr_copy(marker_header->hdr.h_source, slave->perm_hwaddr);
marker_header->hdr.h_proto = PKT_TYPE_LACPDU;
marker_header->marker = *marker;
@@ -1079,7 +1079,8 @@
/* detect loopback situation */
if (MAC_ADDRESS_EQUAL(&(lacpdu->actor_system),
&(port->actor_system))) {
- pr_err("%s: An illegal loopback occurred on adapter (%s).\nCheck the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n",
+ pr_err("%s: An illegal loopback occurred on adapter (%s)\n"
+ "Check the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n",
port->slave->bond->dev->name,
port->slave->dev->name);
return;
@@ -1283,11 +1284,11 @@
/* meaning: the port was related to an aggregator
* but was not on the aggregator port list
*/
- pr_warn("%s: Warning: Port %d (on %s) was related to aggregator %d but was not on its port list\n",
- port->slave->bond->dev->name,
- port->actor_port_number,
- port->slave->dev->name,
- port->aggregator->aggregator_identifier);
+ pr_warn_ratelimited("%s: Warning: Port %d (on %s) was related to aggregator %d but was not on its port list\n",
+ port->slave->bond->dev->name,
+ port->actor_port_number,
+ port->slave->dev->name,
+ port->aggregator->aggregator_identifier);
}
}
/* search on all aggregators for a suitable aggregator for this port */
@@ -1444,9 +1445,9 @@
break;
default:
- pr_warn("%s: Impossible agg select mode %d\n",
- curr->slave->bond->dev->name,
- __get_agg_selection_mode(curr->lag_ports));
+ pr_warn_ratelimited("%s: Impossible agg select mode %d\n",
+ curr->slave->bond->dev->name,
+ __get_agg_selection_mode(curr->lag_ports));
break;
}
@@ -1559,9 +1560,9 @@
/* check if any partner replys */
if (best->is_individual) {
- pr_warn("%s: Warning: No 802.3ad response from the link partner for any adapters in the bond\n",
- best->slave ?
- best->slave->bond->dev->name : "NULL");
+ pr_warn_ratelimited("%s: Warning: No 802.3ad response from the link partner for any adapters in the bond\n",
+ best->slave ?
+ best->slave->bond->dev->name : "NULL");
}
best->is_active = 1;
@@ -1796,8 +1797,6 @@
BOND_AD_INFO(bond).agg_select_timer = timeout;
}
-static u16 aggregator_identifier;
-
/**
* bond_3ad_initialize - initialize a bond's 802.3ad parameters and structures
* @bond: bonding struct to work on
@@ -1811,7 +1810,7 @@
if (!MAC_ADDRESS_EQUAL(&(BOND_AD_INFO(bond).system.sys_mac_addr),
bond->dev->dev_addr)) {
- aggregator_identifier = 0;
+ BOND_AD_INFO(bond).aggregator_identifier = 0;
BOND_AD_INFO(bond).system.sys_priority = 0xFFFF;
BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->dev->dev_addr);
@@ -1880,7 +1879,7 @@
ad_initialize_agg(aggregator);
aggregator->aggregator_mac_address = *((struct mac_addr *)bond->dev->dev_addr);
- aggregator->aggregator_identifier = (++aggregator_identifier);
+ aggregator->aggregator_identifier = ++BOND_AD_INFO(bond).aggregator_identifier;
aggregator->slave = slave;
aggregator->is_active = 0;
aggregator->num_of_ports = 0;
@@ -1950,7 +1949,7 @@
* new aggregator
*/
if ((new_aggregator) && ((!new_aggregator->lag_ports) || ((new_aggregator->lag_ports == port) && !new_aggregator->lag_ports->next_port_in_aggregator))) {
- pr_debug("Some port(s) related to LAG %d - replaceing with LAG %d\n",
+ pr_debug("Some port(s) related to LAG %d - replacing with LAG %d\n",
aggregator->aggregator_identifier,
new_aggregator->aggregator_identifier);
@@ -2064,6 +2063,7 @@
struct list_head *iter;
struct slave *slave;
struct port *port;
+ bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER;
read_lock(&bond->lock);
rcu_read_lock();
@@ -2081,8 +2081,8 @@
/* select the active aggregator for the bond */
if (port) {
if (!port->slave) {
- pr_warn("%s: Warning: bond's first port is uninitialized\n",
- bond->dev->name);
+ pr_warn_ratelimited("%s: Warning: bond's first port is uninitialized\n",
+ bond->dev->name);
goto re_arm;
}
@@ -2096,8 +2096,8 @@
bond_for_each_slave_rcu(bond, slave, iter) {
port = &(SLAVE_AD_INFO(slave).port);
if (!port->slave) {
- pr_warn("%s: Warning: Found an uninitialized port\n",
- bond->dev->name);
+ pr_warn_ratelimited("%s: Warning: Found an uninitialized port\n",
+ bond->dev->name);
goto re_arm;
}
@@ -2121,8 +2121,19 @@
}
re_arm:
+ bond_for_each_slave_rcu(bond, slave, iter) {
+ if (slave->should_notify) {
+ should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW;
+ break;
+ }
+ }
rcu_read_unlock();
read_unlock(&bond->lock);
+
+ if (should_notify_rtnl && rtnl_trylock()) {
+ bond_slave_state_notify(bond);
+ rtnl_unlock();
+ }
queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks);
}
@@ -2147,8 +2158,8 @@
port = &(SLAVE_AD_INFO(slave).port);
if (!port->slave) {
- pr_warn("%s: Warning: port of slave %s is uninitialized\n",
- slave->dev->name, slave->bond->dev->name);
+ pr_warn_ratelimited("%s: Warning: port of slave %s is uninitialized\n",
+ slave->dev->name, slave->bond->dev->name);
return ret;
}
@@ -2300,9 +2311,9 @@
port->actor_oper_port_key = (port->actor_admin_port_key &=
~AD_SPEED_KEY_BITS);
}
- pr_debug("Port %d changed link status to %s",
- port->actor_port_number,
- (link == BOND_LINK_UP) ? "UP" : "DOWN");
+ pr_debug("Port %d changed link status to %s\n",
+ port->actor_port_number,
+ link == BOND_LINK_UP ? "UP" : "DOWN");
/* there is no need to reselect a new aggregator, just signal the
* state machines to reinitialize
*/
@@ -2380,17 +2391,16 @@
}
}
- if (aggregator) {
- ad_info->aggregator_id = aggregator->aggregator_identifier;
- ad_info->ports = aggregator->num_of_ports;
- ad_info->actor_key = aggregator->actor_oper_aggregator_key;
- ad_info->partner_key = aggregator->partner_oper_aggregator_key;
- memcpy(ad_info->partner_system,
- aggregator->partner_system.mac_addr_value, ETH_ALEN);
- return 0;
- }
+ if (!aggregator)
+ return -1;
- return -1;
+ ad_info->aggregator_id = aggregator->aggregator_identifier;
+ ad_info->ports = aggregator->num_of_ports;
+ ad_info->actor_key = aggregator->actor_oper_aggregator_key;
+ ad_info->partner_key = aggregator->partner_oper_aggregator_key;
+ ether_addr_copy(ad_info->partner_system,
+ aggregator->partner_system.mac_addr_value);
+ return 0;
}
/* Wrapper used to hold bond->lock so no slave manipulation can occur */
@@ -2469,7 +2479,7 @@
return NETDEV_TX_OK;
err_free:
/* no suitable interface, frame not sent */
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
goto out;
}
diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h
index 13dc9d3..bb03b1d 100644
--- a/drivers/net/bonding/bond_3ad.h
+++ b/drivers/net/bonding/bond_3ad.h
@@ -28,7 +28,7 @@
#include <linux/netdevice.h>
#include <linux/if_ether.h>
-// General definitions
+/* General definitions */
#define PKT_TYPE_LACPDU cpu_to_be16(ETH_P_SLOW)
#define AD_TIMER_INTERVAL 100 /*msec*/
@@ -47,54 +47,54 @@
BOND_AD_COUNT = 2,
};
-// rx machine states(43.4.11 in the 802.3ad standard)
+/* rx machine states(43.4.11 in the 802.3ad standard) */
typedef enum {
AD_RX_DUMMY,
- AD_RX_INITIALIZE, // rx Machine
- AD_RX_PORT_DISABLED, // rx Machine
- AD_RX_LACP_DISABLED, // rx Machine
- AD_RX_EXPIRED, // rx Machine
- AD_RX_DEFAULTED, // rx Machine
- AD_RX_CURRENT // rx Machine
+ AD_RX_INITIALIZE, /* rx Machine */
+ AD_RX_PORT_DISABLED, /* rx Machine */
+ AD_RX_LACP_DISABLED, /* rx Machine */
+ AD_RX_EXPIRED, /* rx Machine */
+ AD_RX_DEFAULTED, /* rx Machine */
+ AD_RX_CURRENT /* rx Machine */
} rx_states_t;
-// periodic machine states(43.4.12 in the 802.3ad standard)
+/* periodic machine states(43.4.12 in the 802.3ad standard) */
typedef enum {
AD_PERIODIC_DUMMY,
- AD_NO_PERIODIC, // periodic machine
- AD_FAST_PERIODIC, // periodic machine
- AD_SLOW_PERIODIC, // periodic machine
- AD_PERIODIC_TX // periodic machine
+ AD_NO_PERIODIC, /* periodic machine */
+ AD_FAST_PERIODIC, /* periodic machine */
+ AD_SLOW_PERIODIC, /* periodic machine */
+ AD_PERIODIC_TX /* periodic machine */
} periodic_states_t;
-// mux machine states(43.4.13 in the 802.3ad standard)
+/* mux machine states(43.4.13 in the 802.3ad standard) */
typedef enum {
AD_MUX_DUMMY,
- AD_MUX_DETACHED, // mux machine
- AD_MUX_WAITING, // mux machine
- AD_MUX_ATTACHED, // mux machine
- AD_MUX_COLLECTING_DISTRIBUTING // mux machine
+ AD_MUX_DETACHED, /* mux machine */
+ AD_MUX_WAITING, /* mux machine */
+ AD_MUX_ATTACHED, /* mux machine */
+ AD_MUX_COLLECTING_DISTRIBUTING /* mux machine */
} mux_states_t;
-// tx machine states(43.4.15 in the 802.3ad standard)
+/* tx machine states(43.4.15 in the 802.3ad standard) */
typedef enum {
AD_TX_DUMMY,
- AD_TRANSMIT // tx Machine
+ AD_TRANSMIT /* tx Machine */
} tx_states_t;
-// rx indication types
+/* rx indication types */
typedef enum {
- AD_TYPE_LACPDU = 1, // type lacpdu
- AD_TYPE_MARKER // type marker
+ AD_TYPE_LACPDU = 1, /* type lacpdu */
+ AD_TYPE_MARKER /* type marker */
} pdu_type_t;
-// rx marker indication types
+/* rx marker indication types */
typedef enum {
- AD_MARKER_INFORMATION_SUBTYPE = 1, // marker imformation subtype
- AD_MARKER_RESPONSE_SUBTYPE // marker response subtype
+ AD_MARKER_INFORMATION_SUBTYPE = 1, /* marker imformation subtype */
+ AD_MARKER_RESPONSE_SUBTYPE /* marker response subtype */
} bond_marker_subtype_t;
-// timers types(43.4.9 in the 802.3ad standard)
+/* timers types(43.4.9 in the 802.3ad standard) */
typedef enum {
AD_CURRENT_WHILE_TIMER,
AD_ACTOR_CHURN_TIMER,
@@ -105,35 +105,35 @@
#pragma pack(1)
-// Link Aggregation Control Protocol(LACP) data unit structure(43.4.2.2 in the 802.3ad standard)
+/* Link Aggregation Control Protocol(LACP) data unit structure(43.4.2.2 in the 802.3ad standard) */
typedef struct lacpdu {
- u8 subtype; // = LACP(= 0x01)
+ u8 subtype; /* = LACP(= 0x01) */
u8 version_number;
- u8 tlv_type_actor_info; // = actor information(type/length/value)
- u8 actor_information_length; // = 20
+ u8 tlv_type_actor_info; /* = actor information(type/length/value) */
+ u8 actor_information_length; /* = 20 */
__be16 actor_system_priority;
struct mac_addr actor_system;
__be16 actor_key;
__be16 actor_port_priority;
__be16 actor_port;
u8 actor_state;
- u8 reserved_3_1[3]; // = 0
- u8 tlv_type_partner_info; // = partner information
- u8 partner_information_length; // = 20
+ u8 reserved_3_1[3]; /* = 0 */
+ u8 tlv_type_partner_info; /* = partner information */
+ u8 partner_information_length; /* = 20 */
__be16 partner_system_priority;
struct mac_addr partner_system;
__be16 partner_key;
__be16 partner_port_priority;
__be16 partner_port;
u8 partner_state;
- u8 reserved_3_2[3]; // = 0
- u8 tlv_type_collector_info; // = collector information
- u8 collector_information_length; // = 16
+ u8 reserved_3_2[3]; /* = 0 */
+ u8 tlv_type_collector_info; /* = collector information */
+ u8 collector_information_length;/* = 16 */
__be16 collector_max_delay;
u8 reserved_12[12];
- u8 tlv_type_terminator; // = terminator
- u8 terminator_length; // = 0
- u8 reserved_50[50]; // = 0
+ u8 tlv_type_terminator; /* = terminator */
+ u8 terminator_length; /* = 0 */
+ u8 reserved_50[50]; /* = 0 */
} __packed lacpdu_t;
typedef struct lacpdu_header {
@@ -141,20 +141,20 @@
struct lacpdu lacpdu;
} __packed lacpdu_header_t;
-// Marker Protocol Data Unit(PDU) structure(43.5.3.2 in the 802.3ad standard)
+/* Marker Protocol Data Unit(PDU) structure(43.5.3.2 in the 802.3ad standard) */
typedef struct bond_marker {
- u8 subtype; // = 0x02 (marker PDU)
- u8 version_number; // = 0x01
- u8 tlv_type; // = 0x01 (marker information)
- // = 0x02 (marker response information)
- u8 marker_length; // = 0x16
- u16 requester_port; // The number assigned to the port by the requester
- struct mac_addr requester_system; // The requester's system id
- u32 requester_transaction_id; // The transaction id allocated by the requester,
- u16 pad; // = 0
- u8 tlv_type_terminator; // = 0x00
- u8 terminator_length; // = 0x00
- u8 reserved_90[90]; // = 0
+ u8 subtype; /* = 0x02 (marker PDU) */
+ u8 version_number; /* = 0x01 */
+ u8 tlv_type; /* = 0x01 (marker information) */
+ /* = 0x02 (marker response information) */
+ u8 marker_length; /* = 0x16 */
+ u16 requester_port; /* The number assigned to the port by the requester */
+ struct mac_addr requester_system; /* The requester's system id */
+ u32 requester_transaction_id; /* The transaction id allocated by the requester, */
+ u16 pad; /* = 0 */
+ u8 tlv_type_terminator; /* = 0x00 */
+ u8 terminator_length; /* = 0x00 */
+ u8 reserved_90[90]; /* = 0 */
} __packed bond_marker_t;
typedef struct bond_marker_header {
@@ -173,7 +173,7 @@
#pragma pack(8)
#endif
-// aggregator structure(43.4.5 in the 802.3ad standard)
+/* aggregator structure(43.4.5 in the 802.3ad standard) */
typedef struct aggregator {
struct mac_addr aggregator_mac_address;
u16 aggregator_identifier;
@@ -183,12 +183,12 @@
struct mac_addr partner_system;
u16 partner_system_priority;
u16 partner_oper_aggregator_key;
- u16 receive_state; // BOOLEAN
- u16 transmit_state; // BOOLEAN
+ u16 receive_state; /* BOOLEAN */
+ u16 transmit_state; /* BOOLEAN */
struct port *lag_ports;
- // ****** PRIVATE PARAMETERS ******
- struct slave *slave; // pointer to the bond slave that this aggregator belongs to
- u16 is_active; // BOOLEAN. Indicates if this aggregator is active
+ /* ****** PRIVATE PARAMETERS ****** */
+ struct slave *slave; /* pointer to the bond slave that this aggregator belongs to */
+ u16 is_active; /* BOOLEAN. Indicates if this aggregator is active */
u16 num_of_ports;
} aggregator_t;
@@ -201,12 +201,12 @@
u16 port_state;
};
-// port structure(43.4.6 in the 802.3ad standard)
+/* port structure(43.4.6 in the 802.3ad standard) */
typedef struct port {
u16 actor_port_number;
u16 actor_port_priority;
- struct mac_addr actor_system; // This parameter is added here although it is not specified in the standard, just for simplification
- u16 actor_system_priority; // This parameter is added here although it is not specified in the standard, just for simplification
+ struct mac_addr actor_system; /* This parameter is added here although it is not specified in the standard, just for simplification */
+ u16 actor_system_priority; /* This parameter is added here although it is not specified in the standard, just for simplification */
u16 actor_port_aggregator_identifier;
bool ntt;
u16 actor_admin_port_key;
@@ -219,24 +219,24 @@
bool is_enabled;
- // ****** PRIVATE PARAMETERS ******
- u16 sm_vars; // all state machines variables for this port
- rx_states_t sm_rx_state; // state machine rx state
- u16 sm_rx_timer_counter; // state machine rx timer counter
- periodic_states_t sm_periodic_state;// state machine periodic state
- u16 sm_periodic_timer_counter; // state machine periodic timer counter
- mux_states_t sm_mux_state; // state machine mux state
- u16 sm_mux_timer_counter; // state machine mux timer counter
- tx_states_t sm_tx_state; // state machine tx state
- u16 sm_tx_timer_counter; // state machine tx timer counter(allways on - enter to transmit state 3 time per second)
- struct slave *slave; // pointer to the bond slave that this port belongs to
- struct aggregator *aggregator; // pointer to an aggregator that this port related to
- struct port *next_port_in_aggregator; // Next port on the linked list of the parent aggregator
- u32 transaction_id; // continuous number for identification of Marker PDU's;
- struct lacpdu lacpdu; // the lacpdu that will be sent for this port
+ /* ****** PRIVATE PARAMETERS ****** */
+ u16 sm_vars; /* all state machines variables for this port */
+ rx_states_t sm_rx_state; /* state machine rx state */
+ u16 sm_rx_timer_counter; /* state machine rx timer counter */
+ periodic_states_t sm_periodic_state; /* state machine periodic state */
+ u16 sm_periodic_timer_counter; /* state machine periodic timer counter */
+ mux_states_t sm_mux_state; /* state machine mux state */
+ u16 sm_mux_timer_counter; /* state machine mux timer counter */
+ tx_states_t sm_tx_state; /* state machine tx state */
+ u16 sm_tx_timer_counter; /* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */
+ struct slave *slave; /* pointer to the bond slave that this port belongs to */
+ struct aggregator *aggregator; /* pointer to an aggregator that this port related to */
+ struct port *next_port_in_aggregator; /* Next port on the linked list of the parent aggregator */
+ u32 transaction_id; /* continuous number for identification of Marker PDU's; */
+ struct lacpdu lacpdu; /* the lacpdu that will be sent for this port */
} port_t;
-// system structure
+/* system structure */
struct ad_system {
u16 sys_priority;
struct mac_addr sys_mac_addr;
@@ -246,26 +246,26 @@
#pragma pack()
#endif
-// ================= AD Exported structures to the main bonding code ==================
+/* ========== AD Exported structures to the main bonding code ========== */
#define BOND_AD_INFO(bond) ((bond)->ad_info)
#define SLAVE_AD_INFO(slave) ((slave)->ad_info)
struct ad_bond_info {
- struct ad_system system; /* 802.3ad system structure */
- u32 agg_select_timer; // Timer to select aggregator after all adapter's hand shakes
+ struct ad_system system; /* 802.3ad system structure */
+ u32 agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */
+ u16 aggregator_identifier;
};
struct ad_slave_info {
- struct aggregator aggregator; // 802.3ad aggregator structure
- struct port port; // 802.3ad port structure
- spinlock_t state_machine_lock; /* mutex state machines vs.
- incoming LACPDU */
+ struct aggregator aggregator; /* 802.3ad aggregator structure */
+ struct port port; /* 802.3ad port structure */
+ spinlock_t state_machine_lock; /* mutex state machines vs. incoming LACPDU */
u16 id;
};
-// ================= AD Exported functions to the main bonding code ==================
+/* ========== AD Exported functions to the main bonding code ========== */
void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution);
-void bond_3ad_bind_slave(struct slave *slave);
+void bond_3ad_bind_slave(struct slave *slave);
void bond_3ad_unbind_slave(struct slave *slave);
void bond_3ad_state_machine_handler(struct work_struct *);
void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout);
@@ -280,5 +280,5 @@
struct slave *slave);
int bond_3ad_set_carrier(struct bonding *bond);
void bond_3ad_update_lacp_rate(struct bonding *bond);
-#endif //__BOND_3AD_H__
+#endif /* __BOND_3AD_H__ */
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index a2c4747..9f69e81 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -93,9 +93,8 @@
int i;
u8 hash = 0;
- for (i = 0; i < hash_size; i++) {
+ for (i = 0; i < hash_size; i++)
hash ^= hash_start[i];
- }
return hash;
}
@@ -190,9 +189,8 @@
bond_info->tx_hashtbl = new_hashtbl;
- for (i = 0; i < TLB_HASH_TABLE_SIZE; i++) {
+ for (i = 0; i < TLB_HASH_TABLE_SIZE; i++)
tlb_init_table_entry(&bond_info->tx_hashtbl[i], 0);
- }
_unlock_tx_hashtbl_bh(bond);
@@ -264,9 +262,8 @@
hash_table[hash_index].next = next_index;
hash_table[hash_index].prev = TLB_NULL_INDEX;
- if (next_index != TLB_NULL_INDEX) {
+ if (next_index != TLB_NULL_INDEX)
hash_table[next_index].prev = hash_index;
- }
slave_info->head = hash_index;
slave_info->load +=
@@ -274,9 +271,8 @@
}
}
- if (assigned_slave) {
+ if (assigned_slave)
hash_table[hash_index].tx_bytes += skb_len;
- }
return assigned_slave;
}
@@ -329,7 +325,7 @@
_lock_rx_hashtbl_bh(bond);
- hash_index = _simple_hash((u8*)&(arp->ip_src), sizeof(arp->ip_src));
+ hash_index = _simple_hash((u8 *)&(arp->ip_src), sizeof(arp->ip_src));
client_info = &(bond_info->rx_hashtbl[hash_index]);
if ((client_info->assigned) &&
@@ -337,7 +333,7 @@
(client_info->ip_dst == arp->ip_src) &&
(!ether_addr_equal_64bits(client_info->mac_dst, arp->mac_src))) {
/* update the clients MAC address */
- memcpy(client_info->mac_dst, arp->mac_src, ETH_ALEN);
+ ether_addr_copy(client_info->mac_dst, arp->mac_src);
client_info->ntt = 1;
bond_info->rx_ntt = 1;
}
@@ -451,9 +447,8 @@
*/
static void rlb_teach_disabled_mac_on_primary(struct bonding *bond, u8 addr[])
{
- if (!bond->curr_active_slave) {
+ if (!bond->curr_active_slave)
return;
- }
if (!bond->alb_info.primary_is_promisc) {
if (!dev_set_promiscuity(bond->curr_active_slave->dev, 1))
@@ -513,9 +508,8 @@
write_lock_bh(&bond->curr_slave_lock);
- if (slave != bond->curr_active_slave) {
+ if (slave != bond->curr_active_slave)
rlb_teach_disabled_mac_on_primary(bond, slave->dev->dev_addr);
- }
write_unlock_bh(&bond->curr_slave_lock);
}
@@ -524,9 +518,8 @@
{
int i;
- if (!client_info->slave) {
+ if (!client_info->slave)
return;
- }
for (i = 0; i < RLB_ARP_BURST_SIZE; i++) {
struct sk_buff *skb;
@@ -574,9 +567,8 @@
client_info = &(bond_info->rx_hashtbl[hash_index]);
if (client_info->ntt) {
rlb_update_client(client_info);
- if (bond_info->rlb_update_retry_counter == 0) {
+ if (bond_info->rlb_update_retry_counter == 0)
client_info->ntt = 0;
- }
}
}
@@ -610,10 +602,10 @@
}
}
- // update the team's flag only after the whole iteration
+ /* update the team's flag only after the whole iteration */
if (ntt) {
bond_info->rx_ntt = 1;
- //fasten the change
+ /* fasten the change */
bond_info->rlb_update_retry_counter = RLB_UPDATE_RETRY;
}
@@ -677,9 +669,9 @@
/* the entry is already assigned to this client */
if (!ether_addr_equal_64bits(arp->mac_dst, mac_bcast)) {
/* update mac address from arp */
- memcpy(client_info->mac_dst, arp->mac_dst, ETH_ALEN);
+ ether_addr_copy(client_info->mac_dst, arp->mac_dst);
}
- memcpy(client_info->mac_src, arp->mac_src, ETH_ALEN);
+ ether_addr_copy(client_info->mac_src, arp->mac_src);
assigned_slave = client_info->slave;
if (assigned_slave) {
@@ -719,8 +711,8 @@
* will be updated with clients actual unicast mac address
* upon receiving an arp reply.
*/
- memcpy(client_info->mac_dst, arp->mac_dst, ETH_ALEN);
- memcpy(client_info->mac_src, arp->mac_src, ETH_ALEN);
+ ether_addr_copy(client_info->mac_dst, arp->mac_dst);
+ ether_addr_copy(client_info->mac_src, arp->mac_src);
client_info->slave = assigned_slave;
if (!ether_addr_equal_64bits(client_info->mac_dst, mac_bcast)) {
@@ -730,7 +722,7 @@
client_info->ntt = 0;
}
- if (!vlan_get_tag(skb, &client_info->vlan_id))
+ if (vlan_get_tag(skb, &client_info->vlan_id))
client_info->vlan_id = 0;
if (!client_info->assigned) {
@@ -770,9 +762,8 @@
* rx channel
*/
tx_slave = rlb_choose_channel(skb, bond);
- if (tx_slave) {
- memcpy(arp->mac_src,tx_slave->dev->dev_addr, ETH_ALEN);
- }
+ if (tx_slave)
+ ether_addr_copy(arp->mac_src, tx_slave->dev->dev_addr);
pr_debug("Server sent ARP Reply packet\n");
} else if (arp->op_code == htons(ARPOP_REQUEST)) {
/* Create an entry in the rx_hashtbl for this client as a
@@ -824,9 +815,8 @@
}
/* update the team's flag only after the whole iteration */
- if (ntt) {
+ if (ntt)
bond_info->rx_ntt = 1;
- }
_unlock_rx_hashtbl_bh(bond);
}
@@ -923,7 +913,7 @@
static void rlb_purge_src_ip(struct bonding *bond, struct arp_pkt *arp)
{
struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
- u32 ip_src_hash = _simple_hash((u8*)&(arp->ip_src), sizeof(arp->ip_src));
+ u32 ip_src_hash = _simple_hash((u8 *)&(arp->ip_src), sizeof(arp->ip_src));
u32 index;
_lock_rx_hashtbl_bh(bond);
@@ -957,9 +947,8 @@
bond_info->rx_hashtbl_used_head = RLB_NULL_INDEX;
- for (i = 0; i < RLB_HASH_TABLE_SIZE; i++) {
+ for (i = 0; i < RLB_HASH_TABLE_SIZE; i++)
rlb_init_table_entry(bond_info->rx_hashtbl + i);
- }
_unlock_rx_hashtbl_bh(bond);
@@ -1014,9 +1003,9 @@
char *data;
memset(&pkt, 0, size);
- memcpy(pkt.mac_dst, mac_addr, ETH_ALEN);
- memcpy(pkt.mac_src, mac_addr, ETH_ALEN);
- pkt.type = cpu_to_be16(ETH_P_LOOP);
+ ether_addr_copy(pkt.mac_dst, mac_addr);
+ ether_addr_copy(pkt.mac_src, mac_addr);
+ pkt.type = cpu_to_be16(ETH_P_LOOPBACK);
skb = dev_alloc_skb(size);
if (!skb)
@@ -1097,7 +1086,7 @@
{
u8 tmp_mac_addr[ETH_ALEN];
- memcpy(tmp_mac_addr, slave1->dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(tmp_mac_addr, slave1->dev->dev_addr);
alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr);
alb_set_slave_mac_addr(slave2, tmp_mac_addr);
@@ -1254,9 +1243,9 @@
if (free_mac_slave) {
alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr);
- pr_warning("%s: Warning: the hw address of slave %s is in use by the bond; giving it the hw address of %s\n",
- bond->dev->name, slave->dev->name,
- free_mac_slave->dev->name);
+ pr_warn("%s: Warning: the hw address of slave %s is in use by the bond; giving it the hw address of %s\n",
+ bond->dev->name, slave->dev->name,
+ free_mac_slave->dev->name);
} else if (has_bond_addr) {
pr_err("%s: Error: the hw address of slave %s is in use by the bond; couldn't find a slave with a free hw address to give it (this should not have happened)\n",
@@ -1294,12 +1283,12 @@
bond_for_each_slave(bond, slave, iter) {
/* save net_device's current hw address */
- memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(tmp_addr, slave->dev->dev_addr);
res = dev_set_mac_address(slave->dev, addr);
/* restore net_device's hw address */
- memcpy(slave->dev->dev_addr, tmp_addr, ETH_ALEN);
+ ether_addr_copy(slave->dev->dev_addr, tmp_addr);
if (res)
goto unwind;
@@ -1315,9 +1304,9 @@
bond_for_each_slave(bond, rollback_slave, iter) {
if (rollback_slave == slave)
break;
- memcpy(tmp_addr, rollback_slave->dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(tmp_addr, rollback_slave->dev->dev_addr);
dev_set_mac_address(rollback_slave->dev, &sa);
- memcpy(rollback_slave->dev->dev_addr, tmp_addr, ETH_ALEN);
+ ether_addr_copy(rollback_slave->dev->dev_addr, tmp_addr);
}
return res;
@@ -1330,9 +1319,8 @@
int res;
res = tlb_initialize(bond);
- if (res) {
+ if (res)
return res;
- }
if (rlb_enabled) {
bond->alb_info.rlb_enabled = 1;
@@ -1355,9 +1343,8 @@
tlb_deinitialize(bond);
- if (bond_info->rlb_enabled) {
+ if (bond_info->rlb_enabled)
rlb_deinitialize(bond);
- }
}
int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
@@ -1436,14 +1423,13 @@
break;
}
- hash_start = (char*)eth_data->h_dest;
+ hash_start = (char *)eth_data->h_dest;
hash_size = ETH_ALEN;
break;
case ETH_P_ARP:
do_tx_balance = 0;
- if (bond_info->rlb_enabled) {
+ if (bond_info->rlb_enabled)
tx_slave = rlb_arp_xmit(skb, bond);
- }
break;
default:
do_tx_balance = 0;
@@ -1463,23 +1449,22 @@
if (tx_slave && SLAVE_IS_OK(tx_slave)) {
if (tx_slave != rcu_dereference(bond->curr_active_slave)) {
- memcpy(eth_data->h_source,
- tx_slave->dev->dev_addr,
- ETH_ALEN);
+ ether_addr_copy(eth_data->h_source,
+ tx_slave->dev->dev_addr);
}
bond_dev_queue_xmit(bond, skb, tx_slave->dev);
goto out;
- } else {
- if (tx_slave) {
- _lock_tx_hashtbl(bond);
- __tlb_clear_slave(bond, tx_slave, 0);
- _unlock_tx_hashtbl(bond);
- }
+ }
+
+ if (tx_slave) {
+ _lock_tx_hashtbl(bond);
+ __tlb_clear_slave(bond, tx_slave, 0);
+ _unlock_tx_hashtbl(bond);
}
/* no suitable interface, frame not sent */
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
out:
return NETDEV_TX_OK;
}
@@ -1577,11 +1562,10 @@
--bond_info->rlb_update_delay_counter;
} else {
rlb_update_rx_clients(bond);
- if (bond_info->rlb_update_retry_counter) {
+ if (bond_info->rlb_update_retry_counter)
--bond_info->rlb_update_retry_counter;
- } else {
+ else
bond_info->rx_ntt = 0;
- }
}
}
}
@@ -1598,23 +1582,20 @@
int res;
res = alb_set_slave_mac_addr(slave, slave->perm_hwaddr);
- if (res) {
+ if (res)
return res;
- }
res = alb_handle_addr_collision_on_attach(bond, slave);
- if (res) {
+ if (res)
return res;
- }
tlb_init_slave(slave);
/* order a rebalance ASAP */
bond->alb_info.tx_rebalance_counter = BOND_TLB_REBALANCE_TICKS;
- if (bond->alb_info.rlb_enabled) {
+ if (bond->alb_info.rlb_enabled)
bond->alb_info.rlb_rebalance = 1;
- }
return 0;
}
@@ -1645,9 +1626,8 @@
if (link == BOND_LINK_DOWN) {
tlb_clear_slave(bond, slave, 0);
- if (bond->alb_info.rlb_enabled) {
+ if (bond->alb_info.rlb_enabled)
rlb_clear_slave(bond, slave);
- }
} else if (link == BOND_LINK_UP) {
/* order a rebalance ASAP */
bond_info->tx_rebalance_counter = BOND_TLB_REBALANCE_TICKS;
@@ -1723,14 +1703,14 @@
struct sockaddr sa;
u8 tmp_addr[ETH_ALEN];
- memcpy(tmp_addr, new_slave->dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(tmp_addr, new_slave->dev->dev_addr);
memcpy(sa.sa_data, bond->dev->dev_addr, bond->dev->addr_len);
sa.sa_family = bond->dev->type;
/* we don't care if it can't change its mac, best effort */
dev_set_mac_address(new_slave->dev, &sa);
- memcpy(new_slave->dev->dev_addr, tmp_addr, ETH_ALEN);
+ ether_addr_copy(new_slave->dev->dev_addr, tmp_addr);
}
/* curr_active_slave must be set before calling alb_swap_mac_addr */
@@ -1759,14 +1739,12 @@
struct slave *swap_slave;
int res;
- if (!is_valid_ether_addr(sa->sa_data)) {
+ if (!is_valid_ether_addr(sa->sa_data))
return -EADDRNOTAVAIL;
- }
res = alb_set_mac_address(bond, addr);
- if (res) {
+ if (res)
return res;
- }
memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len);
@@ -1774,9 +1752,8 @@
* Otherwise we'll need to pass the new address to it and handle
* duplications.
*/
- if (!bond->curr_active_slave) {
+ if (!bond->curr_active_slave)
return 0;
- }
swap_slave = bond_slave_has_mac(bond, bond_dev->dev_addr);
@@ -1800,8 +1777,7 @@
void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id)
{
- if (bond->alb_info.rlb_enabled) {
+ if (bond->alb_info.rlb_enabled)
rlb_clear_vlan(bond, vlan_id);
- }
}
diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
index 5fc4c23..2d3f7fa 100644
--- a/drivers/net/bonding/bond_debugfs.c
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -69,7 +69,7 @@
debugfs_create_dir(bond->dev->name, bonding_debug_root);
if (!bond->debug_dir) {
- pr_warning("%s: Warning: failed to register to debugfs\n",
+ pr_warn("%s: Warning: failed to register to debugfs\n",
bond->dev->name);
return;
}
@@ -98,9 +98,8 @@
if (d) {
bond->debug_dir = d;
} else {
- pr_warning("%s: Warning: failed to reregister, "
- "so just unregister old one\n",
- bond->dev->name);
+ pr_warn("%s: Warning: failed to reregister, so just unregister old one\n",
+ bond->dev->name);
bond_debug_unregister(bond);
}
}
@@ -110,8 +109,7 @@
bonding_debug_root = debugfs_create_dir("bonding", NULL);
if (!bonding_debug_root) {
- pr_warning("Warning: Cannot create bonding directory"
- " in debugfs\n");
+ pr_warn("Warning: Cannot create bonding directory in debugfs\n");
}
}
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 4c08018..95a6ca7 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -673,12 +673,12 @@
write_unlock_bh(&bond->curr_slave_lock);
if (old_active) {
- memcpy(tmp_mac, new_active->dev->dev_addr, ETH_ALEN);
- memcpy(saddr.sa_data, old_active->dev->dev_addr,
- ETH_ALEN);
+ ether_addr_copy(tmp_mac, new_active->dev->dev_addr);
+ ether_addr_copy(saddr.sa_data,
+ old_active->dev->dev_addr);
saddr.sa_family = new_active->dev->type;
} else {
- memcpy(saddr.sa_data, bond->dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(saddr.sa_data, bond->dev->dev_addr);
saddr.sa_family = bond->dev->type;
}
@@ -692,7 +692,7 @@
if (!old_active)
goto out;
- memcpy(saddr.sa_data, tmp_mac, ETH_ALEN);
+ ether_addr_copy(saddr.sa_data, tmp_mac);
saddr.sa_family = old_active->dev->type;
rv = dev_set_mac_address(old_active->dev, &saddr);
@@ -798,11 +798,11 @@
return;
if (new_active) {
- new_active->jiffies = jiffies;
+ new_active->last_link_up = jiffies;
if (new_active->link == BOND_LINK_BACK) {
if (USES_PRIMARY(bond->params.mode)) {
- pr_info("%s: making interface %s the new active one %d ms earlier.\n",
+ pr_info("%s: making interface %s the new active one %d ms earlier\n",
bond->dev->name, new_active->dev->name,
(bond->params.updelay - new_active->delay) * bond->params.miimon);
}
@@ -817,7 +817,7 @@
bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP);
} else {
if (USES_PRIMARY(bond->params.mode)) {
- pr_info("%s: making interface %s the new active one.\n",
+ pr_info("%s: making interface %s the new active one\n",
bond->dev->name, new_active->dev->name);
}
}
@@ -829,21 +829,25 @@
if (bond_is_lb(bond)) {
bond_alb_handle_active_change(bond, new_active);
if (old_active)
- bond_set_slave_inactive_flags(old_active);
+ bond_set_slave_inactive_flags(old_active,
+ BOND_SLAVE_NOTIFY_NOW);
if (new_active)
- bond_set_slave_active_flags(new_active);
+ bond_set_slave_active_flags(new_active,
+ BOND_SLAVE_NOTIFY_NOW);
} else {
rcu_assign_pointer(bond->curr_active_slave, new_active);
}
if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
if (old_active)
- bond_set_slave_inactive_flags(old_active);
+ bond_set_slave_inactive_flags(old_active,
+ BOND_SLAVE_NOTIFY_NOW);
if (new_active) {
bool should_notify_peers = false;
- bond_set_slave_active_flags(new_active);
+ bond_set_slave_active_flags(new_active,
+ BOND_SLAVE_NOTIFY_NOW);
if (bond->params.fail_over_mac)
bond_do_fail_over_mac(bond, new_active,
@@ -906,7 +910,7 @@
pr_info("%s: first active interface up!\n",
bond->dev->name);
} else {
- pr_info("%s: now running without any active interface !\n",
+ pr_info("%s: now running without any active interface!\n",
bond->dev->name);
}
}
@@ -918,12 +922,12 @@
struct netpoll *np;
int err = 0;
- np = kzalloc(sizeof(*np), GFP_ATOMIC);
+ np = kzalloc(sizeof(*np), GFP_KERNEL);
err = -ENOMEM;
if (!np)
goto out;
- err = __netpoll_setup(np, slave->dev, GFP_ATOMIC);
+ err = __netpoll_setup(np, slave->dev);
if (err) {
kfree(np);
goto out;
@@ -942,14 +946,6 @@
slave->np = NULL;
__netpoll_free_async(np);
}
-static inline bool slave_dev_support_netpoll(struct net_device *slave_dev)
-{
- if (slave_dev->priv_flags & IFF_DISABLE_NETPOLL)
- return false;
- if (!slave_dev->netdev_ops->ndo_poll_controller)
- return false;
- return true;
-}
static void bond_poll_controller(struct net_device *bond_dev)
{
@@ -966,7 +962,7 @@
slave_disable_netpoll(slave);
}
-static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, gfp_t gfp)
+static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
{
struct bonding *bond = netdev_priv(dev);
struct list_head *iter;
@@ -1115,9 +1111,6 @@
slave = bond_slave_get_rcu(skb->dev);
bond = slave->bond;
- if (bond->params.arp_interval)
- slave->dev->last_rx = jiffies;
-
recv_probe = ACCESS_ONCE(bond->recv_probe);
if (recv_probe) {
ret = recv_probe(skb, bond, slave);
@@ -1142,7 +1135,7 @@
kfree_skb(skb);
return RX_HANDLER_CONSUMED;
}
- memcpy(eth_hdr(skb)->h_dest, bond->dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr);
}
return ret;
@@ -1183,16 +1176,21 @@
if (!bond->params.use_carrier &&
slave_dev->ethtool_ops->get_link == NULL &&
slave_ops->ndo_do_ioctl == NULL) {
- pr_warning("%s: Warning: no link monitoring support for %s\n",
- bond_dev->name, slave_dev->name);
+ pr_warn("%s: Warning: no link monitoring support for %s\n",
+ bond_dev->name, slave_dev->name);
}
/* already enslaved */
if (slave_dev->flags & IFF_SLAVE) {
- pr_debug("Error, Device was already enslaved\n");
+ pr_debug("Error: Device was already enslaved\n");
return -EBUSY;
}
+ if (bond_dev == slave_dev) {
+ pr_err("%s: cannot enslave bond to itself.\n", bond_dev->name);
+ return -EPERM;
+ }
+
/* vlan challenged mutual exclusion */
/* no need to lock since we're protected by rtnl_lock */
if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) {
@@ -1202,9 +1200,9 @@
bond_dev->name, slave_dev->name, bond_dev->name);
return -EPERM;
} else {
- pr_warning("%s: Warning: enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n",
- bond_dev->name, slave_dev->name,
- slave_dev->name, bond_dev->name);
+ pr_warn("%s: Warning: enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n",
+ bond_dev->name, slave_dev->name,
+ slave_dev->name, bond_dev->name);
}
} else {
pr_debug("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name);
@@ -1217,7 +1215,7 @@
* enslaving it; the old ifenslave will not.
*/
if ((slave_dev->flags & IFF_UP)) {
- pr_err("%s is up. This may be due to an out of date ifenslave.\n",
+ pr_err("%s is up - this may be due to an out of date ifenslave\n",
slave_dev->name);
res = -EPERM;
goto err_undo_flags;
@@ -1261,20 +1259,23 @@
bond_dev);
}
} else if (bond_dev->type != slave_dev->type) {
- pr_err("%s ether type (%d) is different from other slaves (%d), can not enslave it.\n",
- slave_dev->name,
- slave_dev->type, bond_dev->type);
+ pr_err("%s ether type (%d) is different from other slaves (%d), can not enslave it\n",
+ slave_dev->name, slave_dev->type, bond_dev->type);
res = -EINVAL;
goto err_undo_flags;
}
if (slave_ops->ndo_set_mac_address == NULL) {
if (!bond_has_slaves(bond)) {
- pr_warning("%s: Warning: The first slave device specified does not support setting the MAC address. Setting fail_over_mac to active.",
- bond_dev->name);
- bond->params.fail_over_mac = BOND_FOM_ACTIVE;
+ pr_warn("%s: Warning: The first slave device specified does not support setting the MAC address\n",
+ bond_dev->name);
+ if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
+ bond->params.fail_over_mac = BOND_FOM_ACTIVE;
+ pr_warn("%s: Setting fail_over_mac to active for active-backup mode\n",
+ bond_dev->name);
+ }
} else if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) {
- pr_err("%s: Error: The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active.\n",
+ pr_err("%s: Error: The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active\n",
bond_dev->name);
res = -EOPNOTSUPP;
goto err_undo_flags;
@@ -1313,9 +1314,10 @@
* that need it, and for restoring it upon release, and then
* set it to the master's address
*/
- memcpy(new_slave->perm_hwaddr, slave_dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr);
- if (!bond->params.fail_over_mac) {
+ if (!bond->params.fail_over_mac ||
+ bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
/*
* Set slave to master's mac address. The application already
* set the master's mac address to that of the first slave
@@ -1396,10 +1398,10 @@
bond_update_speed_duplex(new_slave);
- new_slave->last_arp_rx = jiffies -
+ new_slave->last_rx = jiffies -
(msecs_to_jiffies(bond->params.arp_interval) + 1);
for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
- new_slave->target_last_arp_rx[i] = new_slave->last_arp_rx;
+ new_slave->target_last_arp_rx[i] = new_slave->last_rx;
if (bond->params.miimon && !bond->params.use_carrier) {
link_reporting = bond_check_dev_link(bond, slave_dev, 1);
@@ -1414,12 +1416,12 @@
* supported); thus, we don't need to change
* the messages for netif_carrier.
*/
- pr_warning("%s: Warning: MII and ETHTOOL support not available for interface %s, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details.\n",
- bond_dev->name, slave_dev->name);
+ pr_warn("%s: Warning: MII and ETHTOOL support not available for interface %s, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details\n",
+ bond_dev->name, slave_dev->name);
} else if (link_reporting == -1) {
/* unable get link status using mii/ethtool */
- pr_warning("%s: Warning: can't get link status from interface %s; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface.\n",
- bond_dev->name, slave_dev->name);
+ pr_warn("%s: Warning: can't get link status from interface %s; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface\n",
+ bond_dev->name, slave_dev->name);
}
}
@@ -1443,10 +1445,10 @@
}
if (new_slave->link != BOND_LINK_DOWN)
- new_slave->jiffies = jiffies;
+ new_slave->last_link_up = jiffies;
pr_debug("Initial state of slave_dev is BOND_LINK_%s\n",
- new_slave->link == BOND_LINK_DOWN ? "DOWN" :
- (new_slave->link == BOND_LINK_UP ? "UP" : "BACK"));
+ new_slave->link == BOND_LINK_DOWN ? "DOWN" :
+ (new_slave->link == BOND_LINK_UP ? "UP" : "BACK"));
if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) {
/* if there is a primary slave, remember it */
@@ -1458,14 +1460,15 @@
switch (bond->params.mode) {
case BOND_MODE_ACTIVEBACKUP:
- bond_set_slave_inactive_flags(new_slave);
+ bond_set_slave_inactive_flags(new_slave,
+ BOND_SLAVE_NOTIFY_NOW);
break;
case BOND_MODE_8023AD:
/* in 802.3ad mode, the internal mechanism
* will activate the slaves in the selected
* aggregator
*/
- bond_set_slave_inactive_flags(new_slave);
+ bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW);
/* if this is the first slave */
if (!prev_slave) {
SLAVE_AD_INFO(new_slave).id = 1;
@@ -1483,7 +1486,7 @@
case BOND_MODE_TLB:
case BOND_MODE_ALB:
bond_set_active_slave(new_slave);
- bond_set_slave_inactive_flags(new_slave);
+ bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW);
break;
default:
pr_debug("This slave is always active in trunk mode\n");
@@ -1505,10 +1508,8 @@
slave_dev->npinfo = bond->dev->npinfo;
if (slave_dev->npinfo) {
if (slave_enable_netpoll(new_slave)) {
- read_unlock(&bond->lock);
- pr_info("Error, %s: master_dev is using netpoll, "
- "but new slave device does not support netpoll.\n",
- bond_dev->name);
+ pr_info("Error, %s: master_dev is using netpoll, but new slave device does not support netpoll\n",
+ bond_dev->name);
res = -EBUSY;
goto err_detach;
}
@@ -1539,15 +1540,17 @@
bond_set_carrier(bond);
if (USES_PRIMARY(bond->params.mode)) {
+ block_netpoll_tx();
write_lock_bh(&bond->curr_slave_lock);
bond_select_active_slave(bond);
write_unlock_bh(&bond->curr_slave_lock);
+ unblock_netpoll_tx();
}
- pr_info("%s: enslaving %s as a%s interface with a%s link.\n",
+ pr_info("%s: Enslaving %s as %s interface with %s link\n",
bond_dev->name, slave_dev->name,
- bond_is_active_slave(new_slave) ? "n active" : " backup",
- new_slave->link != BOND_LINK_DOWN ? "n up" : " down");
+ bond_is_active_slave(new_slave) ? "an active" : "a backup",
+ new_slave->link != BOND_LINK_DOWN ? "an up" : "a down");
/* enslave is successful */
return 0;
@@ -1567,10 +1570,12 @@
if (bond->primary_slave == new_slave)
bond->primary_slave = NULL;
if (bond->curr_active_slave == new_slave) {
+ block_netpoll_tx();
write_lock_bh(&bond->curr_slave_lock);
bond_change_active_slave(bond, NULL);
bond_select_active_slave(bond);
write_unlock_bh(&bond->curr_slave_lock);
+ unblock_netpoll_tx();
}
slave_disable_netpoll(new_slave);
@@ -1579,12 +1584,13 @@
dev_close(slave_dev);
err_restore_mac:
- if (!bond->params.fail_over_mac) {
+ if (!bond->params.fail_over_mac ||
+ bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
/* XXX TODO - fom follow mode needs to change master's
* MAC if this slave's MAC is in use by the bond, or at
* least print a warning.
*/
- memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN);
+ ether_addr_copy(addr.sa_data, new_slave->perm_hwaddr);
addr.sa_family = slave_dev->type;
dev_set_mac_address(slave_dev, &addr);
}
@@ -1629,7 +1635,7 @@
/* slave is not a slave or master is not master of this slave */
if (!(slave_dev->flags & IFF_SLAVE) ||
!netdev_has_upper_dev(slave_dev, bond_dev)) {
- pr_err("%s: Error: cannot release %s.\n",
+ pr_err("%s: Error: cannot release %s\n",
bond_dev->name, slave_dev->name);
return -EINVAL;
}
@@ -1645,9 +1651,6 @@
return -EINVAL;
}
- /* release the slave from its bond */
- bond->slave_cnt--;
-
bond_sysfs_slave_del(slave);
bond_upper_dev_unlink(bond_dev, slave_dev);
@@ -1663,7 +1666,7 @@
write_unlock_bh(&bond->lock);
- pr_info("%s: releasing %s interface %s\n",
+ pr_info("%s: Releasing %s interface %s\n",
bond_dev->name,
bond_is_active_slave(slave) ? "active" : "backup",
slave_dev->name);
@@ -1672,13 +1675,14 @@
bond->current_arp_slave = NULL;
- if (!all && !bond->params.fail_over_mac) {
+ if (!all && (!bond->params.fail_over_mac ||
+ bond->params.mode != BOND_MODE_ACTIVEBACKUP)) {
if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) &&
bond_has_slaves(bond))
- pr_warn("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n",
- bond_dev->name, slave_dev->name,
- slave->perm_hwaddr,
- bond_dev->name, slave_dev->name);
+ pr_warn("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s - set the HWaddr of %s to a different address to avoid conflicts\n",
+ bond_dev->name, slave_dev->name,
+ slave->perm_hwaddr,
+ bond_dev->name, slave_dev->name);
}
if (bond->primary_slave == slave)
@@ -1719,15 +1723,16 @@
eth_hw_addr_random(bond_dev);
if (vlan_uses_dev(bond_dev)) {
- pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n",
- bond_dev->name, bond_dev->name);
- pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n",
- bond_dev->name);
+ pr_warn("%s: Warning: clearing HW address of %s while it still has VLANs\n",
+ bond_dev->name, bond_dev->name);
+ pr_warn("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs\n",
+ bond_dev->name);
}
}
unblock_netpoll_tx();
synchronize_rcu();
+ bond->slave_cnt--;
if (!bond_has_slaves(bond)) {
call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev);
@@ -1737,7 +1742,7 @@
bond_compute_features(bond);
if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) &&
(old_features & NETIF_F_VLAN_CHALLENGED))
- pr_info("%s: last VLAN challenged slave %s left bond %s. VLAN blocking is removed\n",
+ pr_info("%s: last VLAN challenged slave %s left bond %s - VLAN blocking is removed\n",
bond_dev->name, slave_dev->name, bond_dev->name);
/* must do this from outside any spinlocks */
@@ -1769,9 +1774,10 @@
/* close slave before restoring its mac address */
dev_close(slave_dev);
- if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) {
+ if (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
+ bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
/* restore original ("permanent") mac address */
- memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN);
+ ether_addr_copy(addr.sa_data, slave->perm_hwaddr);
addr.sa_family = slave_dev->type;
dev_set_mac_address(slave_dev, &addr);
}
@@ -1804,7 +1810,7 @@
ret = bond_release(bond_dev, slave_dev);
if (ret == 0 && !bond_has_slaves(bond)) {
bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
- pr_info("%s: destroying bond %s.\n",
+ pr_info("%s: Destroying bond %s\n",
bond_dev->name, bond_dev->name);
unregister_netdevice(bond_dev);
}
@@ -1818,9 +1824,7 @@
info->bond_mode = bond->params.mode;
info->miimon = bond->params.miimon;
- read_lock(&bond->lock);
info->num_slaves = bond->slave_cnt;
- read_unlock(&bond->lock);
return 0;
}
@@ -1832,7 +1836,6 @@
int i = 0, res = -ENODEV;
struct slave *slave;
- read_lock(&bond->lock);
bond_for_each_slave(bond, slave, iter) {
if (i++ == (int)info->slave_id) {
res = 0;
@@ -1843,7 +1846,6 @@
break;
}
}
- read_unlock(&bond->lock);
return res;
}
@@ -1873,7 +1875,7 @@
slave->link = BOND_LINK_FAIL;
slave->delay = bond->params.downdelay;
if (slave->delay) {
- pr_info("%s: link status down for %sinterface %s, disabling it in %d ms.\n",
+ pr_info("%s: link status down for %sinterface %s, disabling it in %d ms\n",
bond->dev->name,
(bond->params.mode ==
BOND_MODE_ACTIVEBACKUP) ?
@@ -1889,8 +1891,8 @@
* recovered before downdelay expired
*/
slave->link = BOND_LINK_UP;
- slave->jiffies = jiffies;
- pr_info("%s: link status up again after %d ms for interface %s.\n",
+ slave->last_link_up = jiffies;
+ pr_info("%s: link status up again after %d ms for interface %s\n",
bond->dev->name,
(bond->params.downdelay - slave->delay) *
bond->params.miimon,
@@ -1915,7 +1917,7 @@
slave->delay = bond->params.updelay;
if (slave->delay) {
- pr_info("%s: link status up for interface %s, enabling it in %d ms.\n",
+ pr_info("%s: link status up for interface %s, enabling it in %d ms\n",
bond->dev->name, slave->dev->name,
ignore_updelay ? 0 :
bond->params.updelay *
@@ -1925,7 +1927,7 @@
case BOND_LINK_BACK:
if (!link_state) {
slave->link = BOND_LINK_DOWN;
- pr_info("%s: link status down again after %d ms for interface %s.\n",
+ pr_info("%s: link status down again after %d ms for interface %s\n",
bond->dev->name,
(bond->params.updelay - slave->delay) *
bond->params.miimon,
@@ -1964,7 +1966,7 @@
case BOND_LINK_UP:
slave->link = BOND_LINK_UP;
- slave->jiffies = jiffies;
+ slave->last_link_up = jiffies;
if (bond->params.mode == BOND_MODE_8023AD) {
/* prevent it from being the active one */
@@ -1977,7 +1979,7 @@
bond_set_backup_slave(slave);
}
- pr_info("%s: link status definitely up for interface %s, %u Mbps %s duplex.\n",
+ pr_info("%s: link status definitely up for interface %s, %u Mbps %s duplex\n",
bond->dev->name, slave->dev->name,
slave->speed == SPEED_UNKNOWN ? 0 : slave->speed,
slave->duplex ? "full" : "half");
@@ -2004,7 +2006,8 @@
if (bond->params.mode == BOND_MODE_ACTIVEBACKUP ||
bond->params.mode == BOND_MODE_8023AD)
- bond_set_slave_inactive_flags(slave);
+ bond_set_slave_inactive_flags(slave,
+ BOND_SLAVE_NOTIFY_NOW);
pr_info("%s: link status definitely down for interface %s, disabling it\n",
bond->dev->name, slave->dev->name);
@@ -2121,24 +2124,40 @@
* switches in VLAN mode (especially if ports are configured as
* "native" to a VLAN) might not pass non-tagged frames.
*/
-static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ip, __be32 src_ip, unsigned short vlan_id)
+static void bond_arp_send(struct net_device *slave_dev, int arp_op,
+ __be32 dest_ip, __be32 src_ip,
+ struct bond_vlan_tag *inner,
+ struct bond_vlan_tag *outer)
{
struct sk_buff *skb;
- pr_debug("arp %d on slave %s: dst %pI4 src %pI4 vid %d\n", arp_op,
- slave_dev->name, &dest_ip, &src_ip, vlan_id);
+ pr_debug("arp %d on slave %s: dst %pI4 src %pI4\n",
+ arp_op, slave_dev->name, &dest_ip, &src_ip);
skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip,
NULL, slave_dev->dev_addr, NULL);
if (!skb) {
- pr_err("ARP packet allocation failed\n");
+ net_err_ratelimited("ARP packet allocation failed\n");
return;
}
- if (vlan_id) {
- skb = vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_id);
+ if (outer->vlan_id) {
+ if (inner->vlan_id) {
+ pr_debug("inner tag: proto %X vid %X\n",
+ ntohs(inner->vlan_proto), inner->vlan_id);
+ skb = __vlan_put_tag(skb, inner->vlan_proto,
+ inner->vlan_id);
+ if (!skb) {
+ net_err_ratelimited("failed to insert inner VLAN tag\n");
+ return;
+ }
+ }
+
+ pr_debug("outer reg: proto %X vid %X\n",
+ ntohs(outer->vlan_proto), outer->vlan_id);
+ skb = vlan_put_tag(skb, outer->vlan_proto, outer->vlan_id);
if (!skb) {
- pr_err("failed to insert VLAN tag\n");
+ net_err_ratelimited("failed to insert outer VLAN tag\n");
return;
}
}
@@ -2151,23 +2170,32 @@
struct net_device *upper, *vlan_upper;
struct list_head *iter, *vlan_iter;
struct rtable *rt;
+ struct bond_vlan_tag inner, outer;
__be32 *targets = bond->params.arp_targets, addr;
- int i, vlan_id;
+ int i;
for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) {
pr_debug("basa: target %pI4\n", &targets[i]);
+ inner.vlan_proto = 0;
+ inner.vlan_id = 0;
+ outer.vlan_proto = 0;
+ outer.vlan_id = 0;
/* Find out through which dev should the packet go */
rt = ip_route_output(dev_net(bond->dev), targets[i], 0,
RTO_ONLINK, 0);
if (IS_ERR(rt)) {
- pr_debug("%s: no route to arp_ip_target %pI4\n",
- bond->dev->name, &targets[i]);
+ /* there's no route to target - try to send arp
+ * probe to generate any traffic (arp_validate=0)
+ */
+ if (bond->params.arp_validate)
+ net_warn_ratelimited("%s: no route to arp_ip_target %pI4 and arp_validate is set\n",
+ bond->dev->name,
+ &targets[i]);
+ bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], 0, &inner, &outer);
continue;
}
- vlan_id = 0;
-
/* bond device itself */
if (rt->dst.dev == bond->dev)
goto found;
@@ -2177,17 +2205,30 @@
* found we verify its upper dev list, searching for the
* rt->dst.dev. If found we save the tag of the vlan and
* proceed to send the packet.
- *
- * TODO: QinQ?
*/
netdev_for_each_all_upper_dev_rcu(bond->dev, vlan_upper,
vlan_iter) {
if (!is_vlan_dev(vlan_upper))
continue;
+
+ if (vlan_upper == rt->dst.dev) {
+ outer.vlan_proto = vlan_dev_vlan_proto(vlan_upper);
+ outer.vlan_id = vlan_dev_vlan_id(vlan_upper);
+ rcu_read_unlock();
+ goto found;
+ }
netdev_for_each_all_upper_dev_rcu(vlan_upper, upper,
iter) {
if (upper == rt->dst.dev) {
- vlan_id = vlan_dev_vlan_id(vlan_upper);
+ /* If the upper dev is a vlan dev too,
+ * set the vlan tag to inner tag.
+ */
+ if (is_vlan_dev(upper)) {
+ inner.vlan_proto = vlan_dev_vlan_proto(upper);
+ inner.vlan_id = vlan_dev_vlan_id(upper);
+ }
+ outer.vlan_proto = vlan_dev_vlan_proto(vlan_upper);
+ outer.vlan_id = vlan_dev_vlan_id(vlan_upper);
rcu_read_unlock();
goto found;
}
@@ -2200,10 +2241,6 @@
*/
netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
if (upper == rt->dst.dev) {
- /* if it's a vlan - get its VID */
- if (is_vlan_dev(upper))
- vlan_id = vlan_dev_vlan_id(upper);
-
rcu_read_unlock();
goto found;
}
@@ -2222,7 +2259,7 @@
addr = bond_confirm_addr(rt->dst.dev, targets[i], 0);
ip_rt_put(rt);
bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
- addr, vlan_id);
+ addr, &inner, &outer);
}
}
@@ -2240,7 +2277,7 @@
pr_debug("bva: sip %pI4 not found in targets\n", &sip);
return;
}
- slave->last_arp_rx = jiffies;
+ slave->last_rx = jiffies;
slave->target_last_arp_rx[i] = jiffies;
}
@@ -2248,17 +2285,19 @@
struct slave *slave)
{
struct arphdr *arp = (struct arphdr *)skb->data;
+ struct slave *curr_active_slave;
unsigned char *arp_ptr;
__be32 sip, tip;
- int alen;
+ int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
- if (skb->protocol != __cpu_to_be16(ETH_P_ARP))
+ if (!slave_do_arp_validate(bond, slave)) {
+ if ((slave_do_arp_validate_only(bond, slave) && is_arp) ||
+ !slave_do_arp_validate_only(bond, slave))
+ slave->last_rx = jiffies;
return RX_HANDLER_ANOTHER;
-
- read_lock(&bond->lock);
-
- if (!slave_do_arp_validate(bond, slave))
- goto out_unlock;
+ } else if (!is_arp) {
+ return RX_HANDLER_ANOTHER;
+ }
alen = arp_hdr_len(bond->dev);
@@ -2292,6 +2331,8 @@
bond->params.arp_validate, slave_do_arp_validate(bond, slave),
&sip, &tip);
+ curr_active_slave = rcu_dereference(bond->curr_active_slave);
+
/*
* Backup slaves won't see the ARP reply, but do come through
* here for each ARP probe (so we swap the sip/tip to validate
@@ -2305,15 +2346,15 @@
* is done to avoid endless looping when we can't reach the
* arp_ip_target and fool ourselves with our own arp requests.
*/
+
if (bond_is_active_slave(slave))
bond_validate_arp(bond, slave, sip, tip);
- else if (bond->curr_active_slave &&
- time_after(slave_last_rx(bond, bond->curr_active_slave),
- bond->curr_active_slave->jiffies))
+ else if (curr_active_slave &&
+ time_after(slave_last_rx(bond, curr_active_slave),
+ curr_active_slave->last_link_up))
bond_validate_arp(bond, slave, tip, sip);
out_unlock:
- read_unlock(&bond->lock);
if (arp != (struct arphdr *)skb->data)
kfree(arp);
return RX_HANDLER_ANOTHER;
@@ -2356,9 +2397,9 @@
oldcurrent = ACCESS_ONCE(bond->curr_active_slave);
/* see if any of the previous devices are up now (i.e. they have
* xmt and rcv traffic). the curr_active_slave does not come into
- * the picture unless it is null. also, slave->jiffies is not needed
- * here because we send an arp on each slave and give a slave as
- * long as it needs to get the tx/rx within the delta.
+ * the picture unless it is null. also, slave->last_link_up is not
+ * needed here because we send an arp on each slave and give a slave
+ * as long as it needs to get the tx/rx within the delta.
* TODO: what about up/down delay in arp mode? it wasn't here before
* so it can wait
*/
@@ -2367,7 +2408,7 @@
if (slave->link != BOND_LINK_UP) {
if (bond_time_in_interval(bond, trans_start, 1) &&
- bond_time_in_interval(bond, slave->dev->last_rx, 1)) {
+ bond_time_in_interval(bond, slave->last_rx, 1)) {
slave->link = BOND_LINK_UP;
slave_state_changed = 1;
@@ -2378,7 +2419,7 @@
* is closed.
*/
if (!oldcurrent) {
- pr_info("%s: link status definitely up for interface %s, ",
+ pr_info("%s: link status definitely up for interface %s\n",
bond->dev->name,
slave->dev->name);
do_failover = 1;
@@ -2396,7 +2437,7 @@
* if we don't know our ip yet
*/
if (!bond_time_in_interval(bond, trans_start, 2) ||
- !bond_time_in_interval(bond, slave->dev->last_rx, 2)) {
+ !bond_time_in_interval(bond, slave->last_rx, 2)) {
slave->link = BOND_LINK_DOWN;
slave_state_changed = 1;
@@ -2404,9 +2445,8 @@
if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
- pr_info("%s: interface %s is now down.\n",
- bond->dev->name,
- slave->dev->name);
+ pr_info("%s: interface %s is now down\n",
+ bond->dev->name, slave->dev->name);
if (slave == oldcurrent)
do_failover = 1;
@@ -2485,7 +2525,7 @@
* active. This avoids bouncing, as the last receive
* times need a full ARP monitor cycle to be updated.
*/
- if (bond_time_in_interval(bond, slave->jiffies, 2))
+ if (bond_time_in_interval(bond, slave->last_link_up, 2))
continue;
/*
@@ -2551,11 +2591,12 @@
slave->link = BOND_LINK_UP;
if (bond->current_arp_slave) {
bond_set_slave_inactive_flags(
- bond->current_arp_slave);
+ bond->current_arp_slave,
+ BOND_SLAVE_NOTIFY_NOW);
bond->current_arp_slave = NULL;
}
- pr_info("%s: link status definitely up for interface %s.\n",
+ pr_info("%s: link status definitely up for interface %s\n",
bond->dev->name, slave->dev->name);
if (!bond->curr_active_slave ||
@@ -2571,7 +2612,8 @@
slave->link_failure_count++;
slave->link = BOND_LINK_DOWN;
- bond_set_slave_inactive_flags(slave);
+ bond_set_slave_inactive_flags(slave,
+ BOND_SLAVE_NOTIFY_NOW);
pr_info("%s: link status definitely down for interface %s, disabling it\n",
bond->dev->name, slave->dev->name);
@@ -2604,17 +2646,17 @@
/*
* Send ARP probes for active-backup mode ARP monitor.
+ *
+ * Called with rcu_read_lock hold.
*/
static bool bond_ab_arp_probe(struct bonding *bond)
{
struct slave *slave, *before = NULL, *new_slave = NULL,
- *curr_arp_slave, *curr_active_slave;
+ *curr_arp_slave = rcu_dereference(bond->current_arp_slave),
+ *curr_active_slave = rcu_dereference(bond->curr_active_slave);
struct list_head *iter;
bool found = false;
-
- rcu_read_lock();
- curr_arp_slave = rcu_dereference(bond->current_arp_slave);
- curr_active_slave = rcu_dereference(bond->curr_active_slave);
+ bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER;
if (curr_arp_slave && curr_active_slave)
pr_info("PROBE: c_arp %s && cas %s BAD\n",
@@ -2623,32 +2665,23 @@
if (curr_active_slave) {
bond_arp_send_all(bond, curr_active_slave);
- rcu_read_unlock();
- return true;
+ return should_notify_rtnl;
}
- rcu_read_unlock();
/* if we don't have a curr_active_slave, search for the next available
* backup slave from the current_arp_slave and make it the candidate
* for becoming the curr_active_slave
*/
- if (!rtnl_trylock())
- return false;
- /* curr_arp_slave might have gone away */
- curr_arp_slave = ACCESS_ONCE(bond->current_arp_slave);
-
if (!curr_arp_slave) {
- curr_arp_slave = bond_first_slave(bond);
- if (!curr_arp_slave) {
- rtnl_unlock();
- return true;
- }
+ curr_arp_slave = bond_first_slave_rcu(bond);
+ if (!curr_arp_slave)
+ return should_notify_rtnl;
}
- bond_set_slave_inactive_flags(curr_arp_slave);
+ bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER);
- bond_for_each_slave(bond, slave, iter) {
+ bond_for_each_slave_rcu(bond, slave, iter) {
if (!found && !before && IS_UP(slave->dev))
before = slave;
@@ -2666,9 +2699,10 @@
if (slave->link_failure_count < UINT_MAX)
slave->link_failure_count++;
- bond_set_slave_inactive_flags(slave);
+ bond_set_slave_inactive_flags(slave,
+ BOND_SLAVE_NOTIFY_LATER);
- pr_info("%s: backup interface %s is now down.\n",
+ pr_info("%s: backup interface %s is now down\n",
bond->dev->name, slave->dev->name);
}
if (slave == curr_arp_slave)
@@ -2678,26 +2712,31 @@
if (!new_slave && before)
new_slave = before;
- if (!new_slave) {
- rtnl_unlock();
- return true;
- }
+ if (!new_slave)
+ goto check_state;
new_slave->link = BOND_LINK_BACK;
- bond_set_slave_active_flags(new_slave);
+ bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER);
bond_arp_send_all(bond, new_slave);
- new_slave->jiffies = jiffies;
+ new_slave->last_link_up = jiffies;
rcu_assign_pointer(bond->current_arp_slave, new_slave);
- rtnl_unlock();
- return true;
+check_state:
+ bond_for_each_slave_rcu(bond, slave, iter) {
+ if (slave->should_notify) {
+ should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW;
+ break;
+ }
+ }
+ return should_notify_rtnl;
}
static void bond_activebackup_arp_mon(struct work_struct *work)
{
struct bonding *bond = container_of(work, struct bonding,
arp_work.work);
- bool should_notify_peers = false, should_commit = false;
+ bool should_notify_peers = false;
+ bool should_notify_rtnl = false;
int delta_in_ticks;
delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
@@ -2706,11 +2745,12 @@
goto re_arm;
rcu_read_lock();
- should_notify_peers = bond_should_notify_peers(bond);
- should_commit = bond_ab_arp_inspect(bond);
- rcu_read_unlock();
- if (should_commit) {
+ should_notify_peers = bond_should_notify_peers(bond);
+
+ if (bond_ab_arp_inspect(bond)) {
+ rcu_read_unlock();
+
/* Race avoidance with bond_close flush of workqueue */
if (!rtnl_trylock()) {
delta_in_ticks = 1;
@@ -2719,23 +2759,28 @@
}
bond_ab_arp_commit(bond);
+
rtnl_unlock();
+ rcu_read_lock();
}
- if (!bond_ab_arp_probe(bond)) {
- /* rtnl locking failed, re-arm */
- delta_in_ticks = 1;
- should_notify_peers = false;
- }
+ should_notify_rtnl = bond_ab_arp_probe(bond);
+ rcu_read_unlock();
re_arm:
if (bond->params.arp_interval)
queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
- if (should_notify_peers) {
+ if (should_notify_peers || should_notify_rtnl) {
if (!rtnl_trylock())
return;
- call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
+
+ if (should_notify_peers)
+ call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
+ bond->dev);
+ if (should_notify_rtnl)
+ bond_slave_state_notify(bond);
+
rtnl_unlock();
}
}
@@ -2854,12 +2899,15 @@
break;
}
- pr_info("%s: Primary slave changed to %s, reselecting active slave.\n",
- bond->dev->name, bond->primary_slave ? slave_dev->name :
- "none");
+ pr_info("%s: Primary slave changed to %s, reselecting active slave\n",
+ bond->dev->name,
+ bond->primary_slave ? slave_dev->name : "none");
+
+ block_netpoll_tx();
write_lock_bh(&bond->curr_slave_lock);
bond_select_active_slave(bond);
write_unlock_bh(&bond->curr_slave_lock);
+ unblock_netpoll_tx();
break;
case NETDEV_FEAT_CHANGE:
bond_compute_features(bond);
@@ -2889,8 +2937,7 @@
struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
pr_debug("event_dev: %s, event: %lx\n",
- event_dev ? event_dev->name : "None",
- event);
+ event_dev ? event_dev->name : "None", event);
if (!(event_dev->priv_flags & IFF_BONDING))
return NOTIFY_DONE;
@@ -2939,7 +2986,7 @@
fk->ports = 0;
noff = skb_network_offset(skb);
if (skb->protocol == htons(ETH_P_IP)) {
- if (!pskb_may_pull(skb, noff + sizeof(*iph)))
+ if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph))))
return false;
iph = ip_hdr(skb);
fk->src = iph->saddr;
@@ -2948,7 +2995,7 @@
if (!ip_is_fragment(iph))
proto = iph->protocol;
} else if (skb->protocol == htons(ETH_P_IPV6)) {
- if (!pskb_may_pull(skb, noff + sizeof(*iph6)))
+ if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph6))))
return false;
iph6 = ipv6_hdr(skb);
fk->src = (__force __be32)ipv6_addr_hash(&iph6->saddr);
@@ -3032,9 +3079,11 @@
bond_for_each_slave(bond, slave, iter) {
if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP)
&& (slave != bond->curr_active_slave)) {
- bond_set_slave_inactive_flags(slave);
+ bond_set_slave_inactive_flags(slave,
+ BOND_SLAVE_NOTIFY_NOW);
} else {
- bond_set_slave_active_flags(slave);
+ bond_set_slave_active_flags(slave,
+ BOND_SLAVE_NOTIFY_NOW);
}
}
read_unlock(&bond->curr_slave_lock);
@@ -3057,8 +3106,7 @@
if (bond->params.arp_interval) { /* arp interval, in milliseconds. */
queue_delayed_work(bond->wq, &bond->arp_work, 0);
- if (bond->params.arp_validate)
- bond->recv_probe = bond_arp_rcv;
+ bond->recv_probe = bond_arp_rcv;
}
if (bond->params.mode == BOND_MODE_8023AD) {
@@ -3345,8 +3393,8 @@
struct list_head *iter;
int res = 0;
- pr_debug("bond=%p, name=%s, new_mtu=%d\n", bond,
- (bond_dev ? bond_dev->name : "None"), new_mtu);
+ pr_debug("bond=%p, name=%s, new_mtu=%d\n",
+ bond, bond_dev ? bond_dev->name : "None", new_mtu);
/* Can't hold bond->lock with bh disabled here since
* some base drivers panic. On the other hand we can't
@@ -3365,8 +3413,7 @@
bond_for_each_slave(bond, slave, iter) {
pr_debug("s %p c_m %p\n",
- slave,
- slave->dev->netdev_ops->ndo_change_mtu);
+ slave, slave->dev->netdev_ops->ndo_change_mtu);
res = dev_set_mtu(slave->dev, new_mtu);
@@ -3431,7 +3478,8 @@
/* If fail_over_mac is enabled, do nothing and return success.
* Returning an error causes ifenslave to fail.
*/
- if (bond->params.fail_over_mac)
+ if (bond->params.fail_over_mac &&
+ bond->params.mode == BOND_MODE_ACTIVEBACKUP)
return 0;
if (!is_valid_ether_addr(sa->sa_data))
@@ -3453,15 +3501,7 @@
*/
bond_for_each_slave(bond, slave, iter) {
- const struct net_device_ops *slave_ops = slave->dev->netdev_ops;
pr_debug("slave %p %s\n", slave, slave->dev->name);
-
- if (slave_ops->ndo_set_mac_address == NULL) {
- res = -EOPNOTSUPP;
- pr_debug("EOPNOTSUPP %s\n", slave->dev->name);
- goto unwind;
- }
-
res = dev_set_mac_address(slave->dev, addr);
if (res) {
/* TODO: consider downing the slave
@@ -3537,7 +3577,7 @@
}
}
/* no slave that can tx has been found */
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
}
/**
@@ -3613,7 +3653,7 @@
if (slave)
bond_dev_queue_xmit(bond, skb, slave->dev);
else
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -3645,8 +3685,8 @@
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2) {
- pr_err("%s: Error: bond_xmit_broadcast(): skb_clone() failed\n",
- bond_dev->name);
+ net_err_ratelimited("%s: Error: %s: skb_clone() failed\n",
+ bond_dev->name, __func__);
continue;
}
/* bond_dev_queue_xmit always returns 0 */
@@ -3656,7 +3696,7 @@
if (slave && IS_UP(slave->dev) && slave->link == BOND_LINK_UP)
bond_dev_queue_xmit(bond, skb, slave->dev);
else
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -3692,7 +3732,7 @@
static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv, select_queue_fallback_t fallback)
{
/*
* This helper function exists to help dev_pick_tx get the correct
@@ -3743,7 +3783,7 @@
pr_err("%s: Error: Unknown bonding mode %d\n",
dev->name, bond->params.mode);
WARN_ON_ONCE(1);
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
}
@@ -3757,14 +3797,14 @@
* If we risk deadlock from transmitting this in the
* netpoll path, tell netpoll to queue the frame for later tx
*/
- if (is_netpoll_tx_blocked(dev))
+ if (unlikely(is_netpoll_tx_blocked(dev)))
return NETDEV_TX_BUSY;
rcu_read_lock();
if (bond_has_slaves(bond))
ret = __bond_start_xmit(skb, dev);
else
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
rcu_read_unlock();
return ret;
@@ -3927,7 +3967,7 @@
/* Release the bonded slaves */
bond_for_each_slave(bond, slave, iter)
__bond_release_one(bond_dev, slave->dev, true);
- pr_info("%s: released all slaves\n", bond_dev->name);
+ pr_info("%s: Released all slaves\n", bond_dev->name);
list_del(&bond->bond_list);
@@ -3936,56 +3976,11 @@
/*------------------------- Module initialization ---------------------------*/
-int bond_parm_tbl_lookup(int mode, const struct bond_parm_tbl *tbl)
-{
- int i;
-
- for (i = 0; tbl[i].modename; i++)
- if (mode == tbl[i].mode)
- return tbl[i].mode;
-
- return -1;
-}
-
-static int bond_parm_tbl_lookup_name(const char *modename,
- const struct bond_parm_tbl *tbl)
-{
- int i;
-
- for (i = 0; tbl[i].modename; i++)
- if (strcmp(modename, tbl[i].modename) == 0)
- return tbl[i].mode;
-
- return -1;
-}
-
-/*
- * Convert string input module parms. Accept either the
- * number of the mode or its string name. A bit complicated because
- * some mode names are substrings of other names, and calls from sysfs
- * may have whitespace in the name (trailing newlines, for example).
- */
-int bond_parse_parm(const char *buf, const struct bond_parm_tbl *tbl)
-{
- int modeint;
- char *p, modestr[BOND_MAX_MODENAME_LEN + 1];
-
- for (p = (char *)buf; *p; p++)
- if (!(isdigit(*p) || isspace(*p)))
- break;
-
- if (*p && sscanf(buf, "%20s", modestr) != 0)
- return bond_parm_tbl_lookup_name(modestr, tbl);
- else if (sscanf(buf, "%d", &modeint) != 0)
- return bond_parm_tbl_lookup(modeint, tbl);
-
- return -1;
-}
-
static int bond_check_params(struct bond_params *params)
{
int arp_validate_value, fail_over_mac_value, primary_reselect_value, i;
- struct bond_opt_value newval, *valptr;
+ struct bond_opt_value newval;
+ const struct bond_opt_value *valptr;
int arp_all_targets_value;
/*
@@ -4005,7 +4000,7 @@
if ((bond_mode != BOND_MODE_XOR) &&
(bond_mode != BOND_MODE_8023AD)) {
pr_info("xmit_hash_policy param is irrelevant in mode %s\n",
- bond_mode_name(bond_mode));
+ bond_mode_name(bond_mode));
} else {
bond_opt_initstr(&newval, xmit_hash_policy);
valptr = bond_opt_parse(bond_opt_get(BOND_OPT_XMIT_HASH),
@@ -4046,74 +4041,71 @@
}
params->ad_select = valptr->value;
if (bond_mode != BOND_MODE_8023AD)
- pr_warning("ad_select param only affects 802.3ad mode\n");
+ pr_warn("ad_select param only affects 802.3ad mode\n");
} else {
params->ad_select = BOND_AD_STABLE;
}
if (max_bonds < 0) {
- pr_warning("Warning: max_bonds (%d) not in range %d-%d, so it was reset to BOND_DEFAULT_MAX_BONDS (%d)\n",
- max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS);
+ pr_warn("Warning: max_bonds (%d) not in range %d-%d, so it was reset to BOND_DEFAULT_MAX_BONDS (%d)\n",
+ max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS);
max_bonds = BOND_DEFAULT_MAX_BONDS;
}
if (miimon < 0) {
- pr_warning("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to 0\n",
- miimon, INT_MAX);
+ pr_warn("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to 0\n",
+ miimon, INT_MAX);
miimon = 0;
}
if (updelay < 0) {
- pr_warning("Warning: updelay module parameter (%d), not in range 0-%d, so it was reset to 0\n",
- updelay, INT_MAX);
+ pr_warn("Warning: updelay module parameter (%d), not in range 0-%d, so it was reset to 0\n",
+ updelay, INT_MAX);
updelay = 0;
}
if (downdelay < 0) {
- pr_warning("Warning: downdelay module parameter (%d), not in range 0-%d, so it was reset to 0\n",
- downdelay, INT_MAX);
+ pr_warn("Warning: downdelay module parameter (%d), not in range 0-%d, so it was reset to 0\n",
+ downdelay, INT_MAX);
downdelay = 0;
}
if ((use_carrier != 0) && (use_carrier != 1)) {
- pr_warning("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n",
- use_carrier);
+ pr_warn("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n",
+ use_carrier);
use_carrier = 1;
}
if (num_peer_notif < 0 || num_peer_notif > 255) {
- pr_warning("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n",
- num_peer_notif);
+ pr_warn("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n",
+ num_peer_notif);
num_peer_notif = 1;
}
/* reset values for 802.3ad/TLB/ALB */
if (BOND_NO_USES_ARP(bond_mode)) {
if (!miimon) {
- pr_warning("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n");
- pr_warning("Forcing miimon to 100msec\n");
+ pr_warn("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n");
+ pr_warn("Forcing miimon to 100msec\n");
miimon = BOND_DEFAULT_MIIMON;
}
}
if (tx_queues < 1 || tx_queues > 255) {
- pr_warning("Warning: tx_queues (%d) should be between "
- "1 and 255, resetting to %d\n",
- tx_queues, BOND_DEFAULT_TX_QUEUES);
+ pr_warn("Warning: tx_queues (%d) should be between 1 and 255, resetting to %d\n",
+ tx_queues, BOND_DEFAULT_TX_QUEUES);
tx_queues = BOND_DEFAULT_TX_QUEUES;
}
if ((all_slaves_active != 0) && (all_slaves_active != 1)) {
- pr_warning("Warning: all_slaves_active module parameter (%d), "
- "not of valid value (0/1), so it was set to "
- "0\n", all_slaves_active);
+ pr_warn("Warning: all_slaves_active module parameter (%d), not of valid value (0/1), so it was set to 0\n",
+ all_slaves_active);
all_slaves_active = 0;
}
if (resend_igmp < 0 || resend_igmp > 255) {
- pr_warning("Warning: resend_igmp (%d) should be between "
- "0 and 255, resetting to %d\n",
- resend_igmp, BOND_DEFAULT_RESEND_IGMP);
+ pr_warn("Warning: resend_igmp (%d) should be between 0 and 255, resetting to %d\n",
+ resend_igmp, BOND_DEFAULT_RESEND_IGMP);
resend_igmp = BOND_DEFAULT_RESEND_IGMP;
}
@@ -4134,37 +4126,36 @@
/* just warn the user the up/down delay will have
* no effect since miimon is zero...
*/
- pr_warning("Warning: miimon module parameter not set and updelay (%d) or downdelay (%d) module parameter is set; updelay and downdelay have no effect unless miimon is set\n",
- updelay, downdelay);
+ pr_warn("Warning: miimon module parameter not set and updelay (%d) or downdelay (%d) module parameter is set; updelay and downdelay have no effect unless miimon is set\n",
+ updelay, downdelay);
}
} else {
/* don't allow arp monitoring */
if (arp_interval) {
- pr_warning("Warning: miimon (%d) and arp_interval (%d) can't be used simultaneously, disabling ARP monitoring\n",
- miimon, arp_interval);
+ pr_warn("Warning: miimon (%d) and arp_interval (%d) can't be used simultaneously, disabling ARP monitoring\n",
+ miimon, arp_interval);
arp_interval = 0;
}
if ((updelay % miimon) != 0) {
- pr_warning("Warning: updelay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n",
- updelay, miimon,
- (updelay / miimon) * miimon);
+ pr_warn("Warning: updelay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n",
+ updelay, miimon, (updelay / miimon) * miimon);
}
updelay /= miimon;
if ((downdelay % miimon) != 0) {
- pr_warning("Warning: downdelay (%d) is not a multiple of miimon (%d), downdelay rounded to %d ms\n",
- downdelay, miimon,
- (downdelay / miimon) * miimon);
+ pr_warn("Warning: downdelay (%d) is not a multiple of miimon (%d), downdelay rounded to %d ms\n",
+ downdelay, miimon,
+ (downdelay / miimon) * miimon);
}
downdelay /= miimon;
}
if (arp_interval < 0) {
- pr_warning("Warning: arp_interval module parameter (%d) , not in range 0-%d, so it was reset to 0\n",
- arp_interval, INT_MAX);
+ pr_warn("Warning: arp_interval module parameter (%d), not in range 0-%d, so it was reset to 0\n",
+ arp_interval, INT_MAX);
arp_interval = 0;
}
@@ -4175,30 +4166,26 @@
__be32 ip;
if (!in4_pton(arp_ip_target[i], -1, (u8 *)&ip, -1, NULL) ||
IS_IP_TARGET_UNUSABLE_ADDRESS(ip)) {
- pr_warning("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n",
- arp_ip_target[i]);
+ pr_warn("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n",
+ arp_ip_target[i]);
arp_interval = 0;
} else {
if (bond_get_targets_ip(arp_target, ip) == -1)
arp_target[arp_ip_count++] = ip;
else
- pr_warning("Warning: duplicate address %pI4 in arp_ip_target, skipping\n",
- &ip);
+ pr_warn("Warning: duplicate address %pI4 in arp_ip_target, skipping\n",
+ &ip);
}
}
if (arp_interval && !arp_ip_count) {
/* don't allow arping if no arp_ip_target given... */
- pr_warning("Warning: arp_interval module parameter (%d) specified without providing an arp_ip_target parameter, arp_interval was reset to 0\n",
- arp_interval);
+ pr_warn("Warning: arp_interval module parameter (%d) specified without providing an arp_ip_target parameter, arp_interval was reset to 0\n",
+ arp_interval);
arp_interval = 0;
}
if (arp_validate) {
- if (bond_mode != BOND_MODE_ACTIVEBACKUP) {
- pr_err("arp_validate only supported in active-backup mode\n");
- return -EINVAL;
- }
if (!arp_interval) {
pr_err("arp_validate requires arp_interval\n");
return -EINVAL;
@@ -4240,23 +4227,23 @@
arp_interval, valptr->string, arp_ip_count);
for (i = 0; i < arp_ip_count; i++)
- pr_info(" %s", arp_ip_target[i]);
+ pr_cont(" %s", arp_ip_target[i]);
- pr_info("\n");
+ pr_cont("\n");
} else if (max_bonds) {
/* miimon and arp_interval not set, we need one so things
* work as expected, see bonding.txt for details
*/
- pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details.\n");
+ pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details\n");
}
if (primary && !USES_PRIMARY(bond_mode)) {
/* currently, using a primary only makes sense
* in active backup, TLB or ALB modes
*/
- pr_warning("Warning: %s primary device specified but has no effect in %s mode\n",
- primary, bond_mode_name(bond_mode));
+ pr_warn("Warning: %s primary device specified but has no effect in %s mode\n",
+ primary, bond_mode_name(bond_mode));
primary = NULL;
}
@@ -4285,14 +4272,14 @@
}
fail_over_mac_value = valptr->value;
if (bond_mode != BOND_MODE_ACTIVEBACKUP)
- pr_warning("Warning: fail_over_mac only affects active-backup mode.\n");
+ pr_warn("Warning: fail_over_mac only affects active-backup mode\n");
} else {
fail_over_mac_value = BOND_FOM_NONE;
}
if (lp_interval == 0) {
- pr_warning("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",
- INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL);
+ pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",
+ INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL);
lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL;
}
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 70651f8..f847e16 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -181,7 +181,7 @@
int arp_interval = nla_get_u32(data[IFLA_BOND_ARP_INTERVAL]);
if (arp_interval && miimon) {
- pr_err("%s: ARP monitoring cannot be used with MII monitoring.\n",
+ pr_err("%s: ARP monitoring cannot be used with MII monitoring\n",
bond->dev->name);
return -EINVAL;
}
@@ -199,7 +199,7 @@
nla_for_each_nested(attr, data[IFLA_BOND_ARP_IP_TARGET], rem) {
__be32 target = nla_get_be32(attr);
- bond_opt_initval(&newval, target);
+ bond_opt_initval(&newval, (__force u64)target);
err = __bond_opt_set(bond, BOND_OPT_ARP_TARGETS,
&newval);
if (err)
@@ -207,7 +207,7 @@
i++;
}
if (i == 0 && bond->params.arp_interval)
- pr_warn("%s: removing last arp target with arp_interval on\n",
+ pr_warn("%s: Removing last arp target with arp_interval on\n",
bond->dev->name);
if (err)
return err;
@@ -216,7 +216,7 @@
int arp_validate = nla_get_u32(data[IFLA_BOND_ARP_VALIDATE]);
if (arp_validate && miimon) {
- pr_err("%s: ARP validating cannot be used with MII monitoring.\n",
+ pr_err("%s: ARP validating cannot be used with MII monitoring\n",
bond->dev->name);
return -EINVAL;
}
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 11cb943..724e30f 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -14,13 +14,65 @@
#include <linux/errno.h>
#include <linux/if.h>
#include <linux/netdevice.h>
-#include <linux/rwlock.h>
+#include <linux/spinlock.h>
#include <linux/rcupdate.h>
#include <linux/ctype.h>
#include <linux/inet.h>
#include "bonding.h"
-static struct bond_opt_value bond_mode_tbl[] = {
+static int bond_option_active_slave_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_miimon_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_updelay_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_downdelay_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_use_carrier_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_arp_interval_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target);
+static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target);
+static int bond_option_arp_ip_targets_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_arp_validate_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_arp_all_targets_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_primary_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_primary_reselect_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_fail_over_mac_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_xmit_hash_policy_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_resend_igmp_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_num_peer_notif_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_all_slaves_active_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_min_links_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_lp_interval_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_pps_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_lacp_rate_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_ad_select_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_queue_id_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_mode_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+static int bond_option_slaves_set(struct bonding *bond,
+ const struct bond_opt_value *newval);
+
+
+static const struct bond_opt_value bond_mode_tbl[] = {
{ "balance-rr", BOND_MODE_ROUNDROBIN, BOND_VALFLAG_DEFAULT},
{ "active-backup", BOND_MODE_ACTIVEBACKUP, 0},
{ "balance-xor", BOND_MODE_XOR, 0},
@@ -31,13 +83,13 @@
{ NULL, -1, 0},
};
-static struct bond_opt_value bond_pps_tbl[] = {
+static const struct bond_opt_value bond_pps_tbl[] = {
{ "default", 1, BOND_VALFLAG_DEFAULT},
{ "maxval", USHRT_MAX, BOND_VALFLAG_MAX},
{ NULL, -1, 0},
};
-static struct bond_opt_value bond_xmit_hashtype_tbl[] = {
+static const struct bond_opt_value bond_xmit_hashtype_tbl[] = {
{ "layer2", BOND_XMIT_POLICY_LAYER2, BOND_VALFLAG_DEFAULT},
{ "layer3+4", BOND_XMIT_POLICY_LAYER34, 0},
{ "layer2+3", BOND_XMIT_POLICY_LAYER23, 0},
@@ -46,84 +98,88 @@
{ NULL, -1, 0},
};
-static struct bond_opt_value bond_arp_validate_tbl[] = {
- { "none", BOND_ARP_VALIDATE_NONE, BOND_VALFLAG_DEFAULT},
- { "active", BOND_ARP_VALIDATE_ACTIVE, 0},
- { "backup", BOND_ARP_VALIDATE_BACKUP, 0},
- { "all", BOND_ARP_VALIDATE_ALL, 0},
- { NULL, -1, 0},
+static const struct bond_opt_value bond_arp_validate_tbl[] = {
+ { "none", BOND_ARP_VALIDATE_NONE, BOND_VALFLAG_DEFAULT},
+ { "active", BOND_ARP_VALIDATE_ACTIVE, 0},
+ { "backup", BOND_ARP_VALIDATE_BACKUP, 0},
+ { "all", BOND_ARP_VALIDATE_ALL, 0},
+ { "filter", BOND_ARP_FILTER, 0},
+ { "filter_active", BOND_ARP_FILTER_ACTIVE, 0},
+ { "filter_backup", BOND_ARP_FILTER_BACKUP, 0},
+ { NULL, -1, 0},
};
-static struct bond_opt_value bond_arp_all_targets_tbl[] = {
+static const struct bond_opt_value bond_arp_all_targets_tbl[] = {
{ "any", BOND_ARP_TARGETS_ANY, BOND_VALFLAG_DEFAULT},
{ "all", BOND_ARP_TARGETS_ALL, 0},
{ NULL, -1, 0},
};
-static struct bond_opt_value bond_fail_over_mac_tbl[] = {
+static const struct bond_opt_value bond_fail_over_mac_tbl[] = {
{ "none", BOND_FOM_NONE, BOND_VALFLAG_DEFAULT},
{ "active", BOND_FOM_ACTIVE, 0},
{ "follow", BOND_FOM_FOLLOW, 0},
{ NULL, -1, 0},
};
-static struct bond_opt_value bond_intmax_tbl[] = {
+static const struct bond_opt_value bond_intmax_tbl[] = {
{ "off", 0, BOND_VALFLAG_DEFAULT},
{ "maxval", INT_MAX, BOND_VALFLAG_MAX},
};
-static struct bond_opt_value bond_lacp_rate_tbl[] = {
+static const struct bond_opt_value bond_lacp_rate_tbl[] = {
{ "slow", AD_LACP_SLOW, 0},
{ "fast", AD_LACP_FAST, 0},
{ NULL, -1, 0},
};
-static struct bond_opt_value bond_ad_select_tbl[] = {
+static const struct bond_opt_value bond_ad_select_tbl[] = {
{ "stable", BOND_AD_STABLE, BOND_VALFLAG_DEFAULT},
{ "bandwidth", BOND_AD_BANDWIDTH, 0},
{ "count", BOND_AD_COUNT, 0},
{ NULL, -1, 0},
};
-static struct bond_opt_value bond_num_peer_notif_tbl[] = {
+static const struct bond_opt_value bond_num_peer_notif_tbl[] = {
{ "off", 0, 0},
{ "maxval", 255, BOND_VALFLAG_MAX},
{ "default", 1, BOND_VALFLAG_DEFAULT},
{ NULL, -1, 0}
};
-static struct bond_opt_value bond_primary_reselect_tbl[] = {
+static const struct bond_opt_value bond_primary_reselect_tbl[] = {
{ "always", BOND_PRI_RESELECT_ALWAYS, BOND_VALFLAG_DEFAULT},
{ "better", BOND_PRI_RESELECT_BETTER, 0},
{ "failure", BOND_PRI_RESELECT_FAILURE, 0},
{ NULL, -1},
};
-static struct bond_opt_value bond_use_carrier_tbl[] = {
+static const struct bond_opt_value bond_use_carrier_tbl[] = {
{ "off", 0, 0},
{ "on", 1, BOND_VALFLAG_DEFAULT},
{ NULL, -1, 0}
};
-static struct bond_opt_value bond_all_slaves_active_tbl[] = {
+static const struct bond_opt_value bond_all_slaves_active_tbl[] = {
{ "off", 0, BOND_VALFLAG_DEFAULT},
{ "on", 1, 0},
{ NULL, -1, 0}
};
-static struct bond_opt_value bond_resend_igmp_tbl[] = {
+static const struct bond_opt_value bond_resend_igmp_tbl[] = {
{ "off", 0, 0},
{ "maxval", 255, BOND_VALFLAG_MAX},
{ "default", 1, BOND_VALFLAG_DEFAULT},
{ NULL, -1, 0}
};
-static struct bond_opt_value bond_lp_interval_tbl[] = {
+static const struct bond_opt_value bond_lp_interval_tbl[] = {
{ "minval", 1, BOND_VALFLAG_MIN | BOND_VALFLAG_DEFAULT},
{ "maxval", INT_MAX, BOND_VALFLAG_MAX},
+ { NULL, -1, 0},
};
-static struct bond_option bond_opts[] = {
+static const struct bond_option bond_opts[] = {
[BOND_OPT_MODE] = {
.id = BOND_OPT_MODE,
.name = "mode",
@@ -151,7 +207,8 @@
.id = BOND_OPT_ARP_VALIDATE,
.name = "arp_validate",
.desc = "validate src/dst of ARP probes",
- .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_ACTIVEBACKUP)),
+ .unsuppmodes = BIT(BOND_MODE_8023AD) | BIT(BOND_MODE_TLB) |
+ BIT(BOND_MODE_ALB),
.values = bond_arp_validate_tbl,
.set = bond_option_arp_validate_set
},
@@ -311,9 +368,9 @@
};
/* Searches for a value in opt's values[] table */
-struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val)
+const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val)
{
- struct bond_option *opt;
+ const struct bond_option *opt;
int i;
opt = bond_opt_get(option);
@@ -327,7 +384,7 @@
}
/* Searches for a value in opt's values[] table which matches the flagmask */
-static struct bond_opt_value *bond_opt_get_flags(const struct bond_option *opt,
+static const struct bond_opt_value *bond_opt_get_flags(const struct bond_option *opt,
u32 flagmask)
{
int i;
@@ -344,7 +401,7 @@
*/
static bool bond_opt_check_range(const struct bond_option *opt, u64 val)
{
- struct bond_opt_value *minval, *maxval;
+ const struct bond_opt_value *minval, *maxval;
minval = bond_opt_get_flags(opt, BOND_VALFLAG_MIN);
maxval = bond_opt_get_flags(opt, BOND_VALFLAG_MAX);
@@ -364,11 +421,12 @@
* or the struct_opt_value that matched. It also strips the new line from
* @val->string if it's present.
*/
-struct bond_opt_value *bond_opt_parse(const struct bond_option *opt,
- struct bond_opt_value *val)
+const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt,
+ struct bond_opt_value *val)
{
char *p, valstr[BOND_OPT_MAX_NAMELEN + 1] = { 0, };
- struct bond_opt_value *tbl, *ret = NULL;
+ const struct bond_opt_value *tbl;
+ const struct bond_opt_value *ret = NULL;
bool checkval;
int i, rv;
@@ -447,7 +505,7 @@
static void bond_opt_dep_print(struct bonding *bond,
const struct bond_option *opt)
{
- struct bond_opt_value *modeval;
+ const struct bond_opt_value *modeval;
struct bond_params *params;
params = &bond->params;
@@ -460,9 +518,9 @@
static void bond_opt_error_interpret(struct bonding *bond,
const struct bond_option *opt,
- int error, struct bond_opt_value *val)
+ int error, const struct bond_opt_value *val)
{
- struct bond_opt_value *minval, *maxval;
+ const struct bond_opt_value *minval, *maxval;
char *p;
switch (error) {
@@ -473,10 +531,10 @@
p = strchr(val->string, '\n');
if (p)
*p = '\0';
- pr_err("%s: option %s: invalid value (%s).\n",
+ pr_err("%s: option %s: invalid value (%s)\n",
bond->dev->name, opt->name, val->string);
} else {
- pr_err("%s: option %s: invalid value (%llu).\n",
+ pr_err("%s: option %s: invalid value (%llu)\n",
bond->dev->name, opt->name, val->value);
}
}
@@ -484,7 +542,7 @@
maxval = bond_opt_get_flags(opt, BOND_VALFLAG_MAX);
if (!maxval)
break;
- pr_err("%s: option %s: allowed values %llu - %llu.\n",
+ pr_err("%s: option %s: allowed values %llu - %llu\n",
bond->dev->name, opt->name, minval ? minval->value : 0,
maxval->value);
break;
@@ -492,11 +550,11 @@
bond_opt_dep_print(bond, opt);
break;
case -ENOTEMPTY:
- pr_err("%s: option %s: unable to set because the bond device has slaves.\n",
+ pr_err("%s: option %s: unable to set because the bond device has slaves\n",
bond->dev->name, opt->name);
break;
case -EBUSY:
- pr_err("%s: option %s: unable to set because the bond device is up.\n",
+ pr_err("%s: option %s: unable to set because the bond device is up\n",
bond->dev->name, opt->name);
break;
default:
@@ -517,7 +575,7 @@
int __bond_opt_set(struct bonding *bond,
unsigned int option, struct bond_opt_value *val)
{
- struct bond_opt_value *retval = NULL;
+ const struct bond_opt_value *retval = NULL;
const struct bond_option *opt;
int ret = -ENOENT;
@@ -572,7 +630,7 @@
* This function checks if option is valid and if so returns a pointer
* to its entry in the bond_opts[] option array.
*/
-struct bond_option *bond_opt_get(unsigned int option)
+const struct bond_option *bond_opt_get(unsigned int option)
{
if (!BOND_OPT_VALID(option))
return NULL;
@@ -580,7 +638,7 @@
return &bond_opts[option];
}
-int bond_option_mode_set(struct bonding *bond, struct bond_opt_value *newval)
+int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval)
{
if (BOND_NO_USES_ARP(newval->value) && bond->params.arp_interval) {
pr_info("%s: %s mode is incompatible with arp monitoring, start mii monitoring\n",
@@ -589,7 +647,7 @@
bond->params.arp_interval = 0;
/* set miimon to default value */
bond->params.miimon = BOND_DEFAULT_MIIMON;
- pr_info("%s: Setting MII monitoring interval to %d.\n",
+ pr_info("%s: Setting MII monitoring interval to %d\n",
bond->dev->name, bond->params.miimon);
}
@@ -618,8 +676,8 @@
return __bond_option_active_slave_get(bond, bond->curr_active_slave);
}
-int bond_option_active_slave_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_active_slave_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
char ifname[IFNAMSIZ] = { 0, };
struct net_device *slave_dev;
@@ -636,13 +694,13 @@
if (slave_dev) {
if (!netif_is_bond_slave(slave_dev)) {
- pr_err("Device %s is not bonding slave.\n",
+ pr_err("Device %s is not bonding slave\n",
slave_dev->name);
return -EINVAL;
}
if (bond->dev != netdev_master_upper_dev_get(slave_dev)) {
- pr_err("%s: Device %s is not our slave.\n",
+ pr_err("%s: Device %s is not our slave\n",
bond->dev->name, slave_dev->name);
return -EINVAL;
}
@@ -653,9 +711,8 @@
/* check to see if we are clearing active */
if (!slave_dev) {
- pr_info("%s: Clearing current active slave.\n",
- bond->dev->name);
- rcu_assign_pointer(bond->curr_active_slave, NULL);
+ pr_info("%s: Clearing current active slave\n", bond->dev->name);
+ RCU_INIT_POINTER(bond->curr_active_slave, NULL);
bond_select_active_slave(bond);
} else {
struct slave *old_active = bond->curr_active_slave;
@@ -665,16 +722,16 @@
if (new_active == old_active) {
/* do nothing */
- pr_info("%s: %s is already the current active slave.\n",
+ pr_info("%s: %s is already the current active slave\n",
bond->dev->name, new_active->dev->name);
} else {
if (old_active && (new_active->link == BOND_LINK_UP) &&
IS_UP(new_active->dev)) {
- pr_info("%s: Setting %s as active slave.\n",
+ pr_info("%s: Setting %s as active slave\n",
bond->dev->name, new_active->dev->name);
bond_change_active_slave(bond, new_active);
} else {
- pr_err("%s: Could not set %s as active slave; either %s is down or the link is down.\n",
+ pr_err("%s: Could not set %s as active slave; either %s is down or the link is down\n",
bond->dev->name, new_active->dev->name,
new_active->dev->name);
ret = -EINVAL;
@@ -688,21 +745,22 @@
return ret;
}
-int bond_option_miimon_set(struct bonding *bond, struct bond_opt_value *newval)
+static int bond_option_miimon_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
- pr_info("%s: Setting MII monitoring interval to %llu.\n",
+ pr_info("%s: Setting MII monitoring interval to %llu\n",
bond->dev->name, newval->value);
bond->params.miimon = newval->value;
if (bond->params.updelay)
- pr_info("%s: Note: Updating updelay (to %d) since it is a multiple of the miimon value.\n",
+ pr_info("%s: Note: Updating updelay (to %d) since it is a multiple of the miimon value\n",
bond->dev->name,
bond->params.updelay * bond->params.miimon);
if (bond->params.downdelay)
- pr_info("%s: Note: Updating downdelay (to %d) since it is a multiple of the miimon value.\n",
+ pr_info("%s: Note: Updating downdelay (to %d) since it is a multiple of the miimon value\n",
bond->dev->name,
bond->params.downdelay * bond->params.miimon);
if (newval->value && bond->params.arp_interval) {
- pr_info("%s: MII monitoring cannot be used with ARP monitoring. Disabling ARP monitoring...\n",
+ pr_info("%s: MII monitoring cannot be used with ARP monitoring - disabling ARP monitoring...\n",
bond->dev->name);
bond->params.arp_interval = 0;
if (bond->params.arp_validate)
@@ -725,7 +783,8 @@
return 0;
}
-int bond_option_updelay_set(struct bonding *bond, struct bond_opt_value *newval)
+static int bond_option_updelay_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
int value = newval->value;
@@ -742,15 +801,14 @@
bond->params.miimon);
}
bond->params.updelay = value / bond->params.miimon;
- pr_info("%s: Setting up delay to %d.\n",
- bond->dev->name,
- bond->params.updelay * bond->params.miimon);
+ pr_info("%s: Setting up delay to %d\n",
+ bond->dev->name, bond->params.updelay * bond->params.miimon);
return 0;
}
-int bond_option_downdelay_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_downdelay_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
int value = newval->value;
@@ -767,37 +825,36 @@
bond->params.miimon);
}
bond->params.downdelay = value / bond->params.miimon;
- pr_info("%s: Setting down delay to %d.\n",
- bond->dev->name,
- bond->params.downdelay * bond->params.miimon);
+ pr_info("%s: Setting down delay to %d\n",
+ bond->dev->name, bond->params.downdelay * bond->params.miimon);
return 0;
}
-int bond_option_use_carrier_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_use_carrier_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
- pr_info("%s: Setting use_carrier to %llu.\n",
+ pr_info("%s: Setting use_carrier to %llu\n",
bond->dev->name, newval->value);
bond->params.use_carrier = newval->value;
return 0;
}
-int bond_option_arp_interval_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_arp_interval_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
- pr_info("%s: Setting ARP monitoring interval to %llu.\n",
+ pr_info("%s: Setting ARP monitoring interval to %llu\n",
bond->dev->name, newval->value);
bond->params.arp_interval = newval->value;
if (newval->value) {
if (bond->params.miimon) {
- pr_info("%s: ARP monitoring cannot be used with MII monitoring. %s Disabling MII monitoring.\n",
+ pr_info("%s: ARP monitoring cannot be used with MII monitoring. %s Disabling MII monitoring\n",
bond->dev->name, bond->dev->name);
bond->params.miimon = 0;
}
if (!bond->params.arp_targets[0])
- pr_info("%s: ARP monitoring has been set up, but no ARP targets have been specified.\n",
+ pr_info("%s: ARP monitoring has been set up, but no ARP targets have been specified\n",
bond->dev->name);
}
if (bond->dev->flags & IFF_UP) {
@@ -812,8 +869,7 @@
cancel_delayed_work_sync(&bond->arp_work);
} else {
/* arp_validate can be set only in active-backup mode */
- if (bond->params.arp_validate)
- bond->recv_probe = bond_arp_rcv;
+ bond->recv_probe = bond_arp_rcv;
cancel_delayed_work_sync(&bond->mii_work);
queue_delayed_work(bond->wq, &bond->arp_work, 0);
}
@@ -856,19 +912,18 @@
ind = bond_get_targets_ip(targets, 0); /* first free slot */
if (ind == -1) {
- pr_err("%s: ARP target table is full!\n",
- bond->dev->name);
+ pr_err("%s: ARP target table is full!\n", bond->dev->name);
return -EINVAL;
}
- pr_info("%s: adding ARP target %pI4.\n", bond->dev->name, &target);
+ pr_info("%s: Adding ARP target %pI4\n", bond->dev->name, &target);
_bond_options_arp_ip_target_set(bond, ind, target, jiffies);
return 0;
}
-int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target)
+static int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target)
{
int ret;
@@ -880,7 +935,7 @@
return ret;
}
-int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target)
+static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target)
{
__be32 *targets = bond->params.arp_targets;
struct list_head *iter;
@@ -896,17 +951,16 @@
ind = bond_get_targets_ip(targets, target);
if (ind == -1) {
- pr_err("%s: unable to remove nonexistent ARP target %pI4.\n",
+ pr_err("%s: unable to remove nonexistent ARP target %pI4\n",
bond->dev->name, &target);
return -EINVAL;
}
if (ind == 0 && !targets[1] && bond->params.arp_interval)
- pr_warn("%s: removing last arp target with arp_interval on\n",
+ pr_warn("%s: Removing last arp target with arp_interval on\n",
bond->dev->name);
- pr_info("%s: removing ARP target %pI4.\n", bond->dev->name,
- &target);
+ pr_info("%s: Removing ARP target %pI4\n", bond->dev->name, &target);
/* not to race with bond_arp_rcv */
write_lock_bh(&bond->lock);
@@ -937,8 +991,8 @@
write_unlock_bh(&bond->lock);
}
-int bond_option_arp_ip_targets_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_arp_ip_targets_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
int ret = -EPERM;
__be32 target;
@@ -954,7 +1008,7 @@
else if (newval->string[0] == '-')
ret = bond_option_arp_ip_target_rem(bond, target);
else
- pr_err("no command found in arp_ip_targets file for bond %s. Use +<addr> or -<addr>.\n",
+ pr_err("no command found in arp_ip_targets file for bond %s - use +<addr> or -<addr>\n",
bond->dev->name);
} else {
target = newval->value;
@@ -964,10 +1018,10 @@
return ret;
}
-int bond_option_arp_validate_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_arp_validate_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
- pr_info("%s: setting arp_validate to %s (%llu).\n",
+ pr_info("%s: Setting arp_validate to %s (%llu)\n",
bond->dev->name, newval->string, newval->value);
if (bond->dev->flags & IFF_UP) {
@@ -981,17 +1035,18 @@
return 0;
}
-int bond_option_arp_all_targets_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_arp_all_targets_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
- pr_info("%s: setting arp_all_targets to %s (%llu).\n",
+ pr_info("%s: Setting arp_all_targets to %s (%llu)\n",
bond->dev->name, newval->string, newval->value);
bond->params.arp_all_targets = newval->value;
return 0;
}
-int bond_option_primary_set(struct bonding *bond, struct bond_opt_value *newval)
+static int bond_option_primary_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
char *p, *primary = newval->string;
struct list_head *iter;
@@ -1006,8 +1061,7 @@
*p = '\0';
/* check to see if we are clearing primary */
if (!strlen(primary)) {
- pr_info("%s: Setting primary slave to None.\n",
- bond->dev->name);
+ pr_info("%s: Setting primary slave to None\n", bond->dev->name);
bond->primary_slave = NULL;
memset(bond->params.primary, 0, sizeof(bond->params.primary));
bond_select_active_slave(bond);
@@ -1016,7 +1070,7 @@
bond_for_each_slave(bond, slave, iter) {
if (strncmp(slave->dev->name, primary, IFNAMSIZ) == 0) {
- pr_info("%s: Setting %s as primary slave.\n",
+ pr_info("%s: Setting %s as primary slave\n",
bond->dev->name, slave->dev->name);
bond->primary_slave = slave;
strcpy(bond->params.primary, slave->dev->name);
@@ -1026,15 +1080,14 @@
}
if (bond->primary_slave) {
- pr_info("%s: Setting primary slave to None.\n",
- bond->dev->name);
+ pr_info("%s: Setting primary slave to None\n", bond->dev->name);
bond->primary_slave = NULL;
bond_select_active_slave(bond);
}
strncpy(bond->params.primary, primary, IFNAMSIZ);
bond->params.primary[IFNAMSIZ - 1] = 0;
- pr_info("%s: Recording %s as primary, but it has not been enslaved to %s yet.\n",
+ pr_info("%s: Recording %s as primary, but it has not been enslaved to %s yet\n",
bond->dev->name, primary, bond->dev->name);
out:
@@ -1045,10 +1098,10 @@
return 0;
}
-int bond_option_primary_reselect_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_primary_reselect_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
- pr_info("%s: setting primary_reselect to %s (%llu).\n",
+ pr_info("%s: Setting primary_reselect to %s (%llu)\n",
bond->dev->name, newval->string, newval->value);
bond->params.primary_reselect = newval->value;
@@ -1061,46 +1114,46 @@
return 0;
}
-int bond_option_fail_over_mac_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_fail_over_mac_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
- pr_info("%s: Setting fail_over_mac to %s (%llu).\n",
+ pr_info("%s: Setting fail_over_mac to %s (%llu)\n",
bond->dev->name, newval->string, newval->value);
bond->params.fail_over_mac = newval->value;
return 0;
}
-int bond_option_xmit_hash_policy_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_xmit_hash_policy_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
- pr_info("%s: setting xmit hash policy to %s (%llu).\n",
+ pr_info("%s: Setting xmit hash policy to %s (%llu)\n",
bond->dev->name, newval->string, newval->value);
bond->params.xmit_policy = newval->value;
return 0;
}
-int bond_option_resend_igmp_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_resend_igmp_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
- pr_info("%s: Setting resend_igmp to %llu.\n",
+ pr_info("%s: Setting resend_igmp to %llu\n",
bond->dev->name, newval->value);
bond->params.resend_igmp = newval->value;
return 0;
}
-int bond_option_num_peer_notif_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_num_peer_notif_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
bond->params.num_peer_notif = newval->value;
return 0;
}
-int bond_option_all_slaves_active_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_all_slaves_active_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
struct list_head *iter;
struct slave *slave;
@@ -1120,8 +1173,8 @@
return 0;
}
-int bond_option_min_links_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_min_links_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
pr_info("%s: Setting min links value to %llu\n",
bond->dev->name, newval->value);
@@ -1130,15 +1183,16 @@
return 0;
}
-int bond_option_lp_interval_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_lp_interval_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
bond->params.lp_interval = newval->value;
return 0;
}
-int bond_option_pps_set(struct bonding *bond, struct bond_opt_value *newval)
+static int bond_option_pps_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
bond->params.packets_per_slave = newval->value;
if (newval->value > 0) {
@@ -1155,10 +1209,10 @@
return 0;
}
-int bond_option_lacp_rate_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_lacp_rate_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
- pr_info("%s: Setting LACP rate to %s (%llu).\n",
+ pr_info("%s: Setting LACP rate to %s (%llu)\n",
bond->dev->name, newval->string, newval->value);
bond->params.lacp_fast = newval->value;
bond_3ad_update_lacp_rate(bond);
@@ -1166,18 +1220,18 @@
return 0;
}
-int bond_option_ad_select_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_ad_select_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
- pr_info("%s: Setting ad_select to %s (%llu).\n",
+ pr_info("%s: Setting ad_select to %s (%llu)\n",
bond->dev->name, newval->string, newval->value);
bond->params.ad_select = newval->value;
return 0;
}
-int bond_option_queue_id_set(struct bonding *bond,
- struct bond_opt_value *newval)
+static int bond_option_queue_id_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
struct slave *slave, *update_slave;
struct net_device *sdev;
@@ -1199,8 +1253,7 @@
goto err_no_cmd;
/* Check buffer length, valid ifname and queue id */
- if (strlen(newval->string) > IFNAMSIZ ||
- !dev_valid_name(newval->string) ||
+ if (!dev_valid_name(newval->string) ||
qid > bond->dev->real_num_tx_queues)
goto err_no_cmd;
@@ -1232,14 +1285,14 @@
return ret;
err_no_cmd:
- pr_info("invalid input for queue_id set for %s.\n",
- bond->dev->name);
+ pr_info("invalid input for queue_id set for %s\n", bond->dev->name);
ret = -EPERM;
goto out;
}
-int bond_option_slaves_set(struct bonding *bond, struct bond_opt_value *newval)
+static int bond_option_slaves_set(struct bonding *bond,
+ const struct bond_opt_value *newval)
{
char command[IFNAMSIZ + 1] = { 0, };
struct net_device *dev;
@@ -1254,7 +1307,7 @@
dev = __dev_get_by_name(dev_net(bond->dev), ifname);
if (!dev) {
- pr_info("%s: Interface %s does not exist!\n",
+ pr_info("%s: interface %s does not exist!\n",
bond->dev->name, ifname);
ret = -ENODEV;
goto out;
@@ -1262,12 +1315,12 @@
switch (command[0]) {
case '+':
- pr_info("%s: Adding slave %s.\n", bond->dev->name, dev->name);
+ pr_info("%s: Adding slave %s\n", bond->dev->name, dev->name);
ret = bond_enslave(bond->dev, dev);
break;
case '-':
- pr_info("%s: Removing slave %s.\n", bond->dev->name, dev->name);
+ pr_info("%s: Removing slave %s\n", bond->dev->name, dev->name);
ret = bond_release(bond->dev, dev);
break;
@@ -1279,7 +1332,7 @@
return ret;
err_no_cmd:
- pr_err("no command found in slaves file for bond %s. Use +ifname or -ifname.\n",
+ pr_err("no command found in slaves file for bond %s - use +ifname or -ifname\n",
bond->dev->name);
ret = -EPERM;
goto out;
diff --git a/drivers/net/bonding/bond_options.h b/drivers/net/bonding/bond_options.h
index 433d37f..12be9e1 100644
--- a/drivers/net/bonding/bond_options.h
+++ b/drivers/net/bonding/bond_options.h
@@ -81,8 +81,8 @@
struct bond_option {
int id;
- char *name;
- char *desc;
+ const char *name;
+ const char *desc;
u32 flags;
/* unsuppmodes is used to denote modes in which the option isn't
@@ -92,18 +92,19 @@
/* supported values which this option can have, can be a subset of
* BOND_OPTVAL_RANGE's value range
*/
- struct bond_opt_value *values;
+ const struct bond_opt_value *values;
- int (*set)(struct bonding *bond, struct bond_opt_value *val);
+ int (*set)(struct bonding *bond, const struct bond_opt_value *val);
};
int __bond_opt_set(struct bonding *bond, unsigned int option,
struct bond_opt_value *val);
int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf);
-struct bond_opt_value *bond_opt_parse(const struct bond_option *opt,
- struct bond_opt_value *val);
-struct bond_option *bond_opt_get(unsigned int option);
-struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val);
+
+const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt,
+ struct bond_opt_value *val);
+const struct bond_option *bond_opt_get(unsigned int option);
+const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val);
/* This helper is used to initialize a bond_opt_value structure for parameter
* passing. There should be either a valid string or value, but not both.
@@ -122,49 +123,6 @@
#define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value)
#define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX)
-int bond_option_mode_set(struct bonding *bond, struct bond_opt_value *newval);
-int bond_option_pps_set(struct bonding *bond, struct bond_opt_value *newval);
-int bond_option_xmit_hash_policy_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_arp_validate_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_arp_all_targets_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_fail_over_mac_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_arp_interval_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_arp_ip_targets_set(struct bonding *bond,
- struct bond_opt_value *newval);
void bond_option_arp_ip_targets_clear(struct bonding *bond);
-int bond_option_downdelay_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_updelay_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_lacp_rate_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_min_links_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_ad_select_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_num_peer_notif_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_miimon_set(struct bonding *bond, struct bond_opt_value *newval);
-int bond_option_primary_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_primary_reselect_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_use_carrier_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_active_slave_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_queue_id_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_all_slaves_active_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_resend_igmp_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_lp_interval_set(struct bonding *bond,
- struct bond_opt_value *newval);
-int bond_option_slaves_set(struct bonding *bond, struct bond_opt_value *newval);
+
#endif /* _BOND_OPTIONS_H */
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index 3ac20e7..013fdd0 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -65,13 +65,11 @@
static void bond_info_show_master(struct seq_file *seq)
{
struct bonding *bond = seq->private;
- struct bond_opt_value *optval;
+ const struct bond_opt_value *optval;
struct slave *curr;
int i;
- read_lock(&bond->curr_slave_lock);
- curr = bond->curr_active_slave;
- read_unlock(&bond->curr_slave_lock);
+ curr = rcu_dereference(bond->curr_active_slave);
seq_printf(seq, "Bonding Mode: %s",
bond_mode_name(bond->params.mode));
@@ -254,8 +252,8 @@
S_IRUGO, bn->proc_dir,
&bond_info_fops, bond);
if (bond->proc_entry == NULL)
- pr_warning("Warning: Cannot create /proc/net/%s/%s\n",
- DRV_NAME, bond_dev->name);
+ pr_warn("Warning: Cannot create /proc/net/%s/%s\n",
+ DRV_NAME, bond_dev->name);
else
memcpy(bond->proc_file_name, bond_dev->name, IFNAMSIZ);
}
@@ -281,8 +279,8 @@
if (!bn->proc_dir) {
bn->proc_dir = proc_mkdir(DRV_NAME, bn->net->proc_net);
if (!bn->proc_dir)
- pr_warning("Warning: cannot create /proc/net/%s\n",
- DRV_NAME);
+ pr_warn("Warning: Cannot create /proc/net/%s\n",
+ DRV_NAME);
}
}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 643fcc1..0e8b268 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -117,9 +117,9 @@
rv = bond_create(bn->net, ifname);
if (rv) {
if (rv == -EEXIST)
- pr_info("%s already exists.\n", ifname);
+ pr_info("%s already exists\n", ifname);
else
- pr_info("%s creation failed.\n", ifname);
+ pr_info("%s creation failed\n", ifname);
res = rv;
}
} else if (command[0] == '-') {
@@ -144,7 +144,7 @@
return res;
err_no_cmd:
- pr_err("no command found in bonding_masters. Use +ifname or -ifname.\n");
+ pr_err("no command found in bonding_masters - use +ifname or -ifname\n");
return -EPERM;
}
@@ -220,7 +220,7 @@
struct device_attribute *attr, char *buf)
{
struct bonding *bond = to_bond(d);
- struct bond_opt_value *val;
+ const struct bond_opt_value *val;
val = bond_opt_get_val(BOND_OPT_MODE, bond->params.mode);
@@ -251,7 +251,7 @@
char *buf)
{
struct bonding *bond = to_bond(d);
- struct bond_opt_value *val;
+ const struct bond_opt_value *val;
val = bond_opt_get_val(BOND_OPT_XMIT_HASH, bond->params.xmit_policy);
@@ -282,7 +282,7 @@
char *buf)
{
struct bonding *bond = to_bond(d);
- struct bond_opt_value *val;
+ const struct bond_opt_value *val;
val = bond_opt_get_val(BOND_OPT_ARP_VALIDATE,
bond->params.arp_validate);
@@ -314,7 +314,7 @@
char *buf)
{
struct bonding *bond = to_bond(d);
- struct bond_opt_value *val;
+ const struct bond_opt_value *val;
val = bond_opt_get_val(BOND_OPT_ARP_ALL_TARGETS,
bond->params.arp_all_targets);
@@ -348,7 +348,7 @@
char *buf)
{
struct bonding *bond = to_bond(d);
- struct bond_opt_value *val;
+ const struct bond_opt_value *val;
val = bond_opt_get_val(BOND_OPT_FAIL_OVER_MAC,
bond->params.fail_over_mac);
@@ -505,7 +505,7 @@
char *buf)
{
struct bonding *bond = to_bond(d);
- struct bond_opt_value *val;
+ const struct bond_opt_value *val;
val = bond_opt_get_val(BOND_OPT_LACP_RATE, bond->params.lacp_fast);
@@ -558,7 +558,7 @@
char *buf)
{
struct bonding *bond = to_bond(d);
- struct bond_opt_value *val;
+ const struct bond_opt_value *val;
val = bond_opt_get_val(BOND_OPT_AD_SELECT, bond->params.ad_select);
@@ -686,7 +686,7 @@
char *buf)
{
struct bonding *bond = to_bond(d);
- struct bond_opt_value *val;
+ const struct bond_opt_value *val;
val = bond_opt_get_val(BOND_OPT_PRIMARY_RESELECT,
bond->params.primary_reselect);
@@ -1135,7 +1135,7 @@
/* Is someone being kinky and naming a device bonding_master? */
if (__dev_get_by_name(bn->net,
class_attr_bonding_masters.attr.name))
- pr_err("network device named %s already exists in sysfs",
+ pr_err("network device named %s already exists in sysfs\n",
class_attr_bonding_masters.attr.name);
ret = 0;
}
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 86ccfb9..b8bdd0a 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -188,14 +188,16 @@
struct net_device *dev; /* first - useful for panic debug */
struct bonding *bond; /* our master */
int delay;
- unsigned long jiffies;
- unsigned long last_arp_rx;
+ /* all three in jiffies */
+ unsigned long last_link_up;
+ unsigned long last_rx;
unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS];
s8 link; /* one of BOND_LINK_XXXX */
s8 new_link;
u8 backup:1, /* indicates backup slave. Value corresponds with
BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
- inactive:1; /* indicates inactive slave */
+ inactive:1, /* indicates inactive slave */
+ should_notify:1; /* indicateds whether the state changed */
u8 duplex;
u32 original_mtu;
u32 link_failure_count;
@@ -264,6 +266,11 @@
#define bond_slave_get_rtnl(dev) \
((struct slave *) rtnl_dereference(dev->rx_handler_data))
+struct bond_vlan_tag {
+ __be16 vlan_proto;
+ unsigned short vlan_id;
+};
+
/**
* Returns NULL if the net_device does not belong to any of the bond's slaves
*
@@ -291,7 +298,7 @@
{
if (slave->backup) {
slave->backup = 0;
- rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_KERNEL);
+ rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
}
}
@@ -299,7 +306,25 @@
{
if (!slave->backup) {
slave->backup = 1;
- rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_KERNEL);
+ rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
+ }
+}
+
+static inline void bond_set_slave_state(struct slave *slave,
+ int slave_state, bool notify)
+{
+ if (slave->backup == slave_state)
+ return;
+
+ slave->backup = slave_state;
+ if (notify) {
+ rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
+ slave->should_notify = 0;
+ } else {
+ if (slave->should_notify)
+ slave->should_notify = 0;
+ else
+ slave->should_notify = 1;
}
}
@@ -316,6 +341,19 @@
}
}
+static inline void bond_slave_state_notify(struct bonding *bond)
+{
+ struct list_head *iter;
+ struct slave *tmp;
+
+ bond_for_each_slave(bond, tmp, iter) {
+ if (tmp->should_notify) {
+ rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_ATOMIC);
+ tmp->should_notify = 0;
+ }
+ }
+}
+
static inline int bond_slave_state(struct slave *slave)
{
return slave->backup;
@@ -342,6 +380,14 @@
#define BOND_ARP_VALIDATE_BACKUP (1 << BOND_STATE_BACKUP)
#define BOND_ARP_VALIDATE_ALL (BOND_ARP_VALIDATE_ACTIVE | \
BOND_ARP_VALIDATE_BACKUP)
+#define BOND_ARP_FILTER (BOND_ARP_VALIDATE_ALL + 1)
+#define BOND_ARP_FILTER_ACTIVE (BOND_ARP_VALIDATE_ACTIVE | \
+ BOND_ARP_FILTER)
+#define BOND_ARP_FILTER_BACKUP (BOND_ARP_VALIDATE_BACKUP | \
+ BOND_ARP_FILTER)
+
+#define BOND_SLAVE_NOTIFY_NOW true
+#define BOND_SLAVE_NOTIFY_LATER false
static inline int slave_do_arp_validate(struct bonding *bond,
struct slave *slave)
@@ -349,6 +395,12 @@
return bond->params.arp_validate & (1 << bond_slave_state(slave));
}
+static inline int slave_do_arp_validate_only(struct bonding *bond,
+ struct slave *slave)
+{
+ return bond->params.arp_validate & BOND_ARP_FILTER;
+}
+
/* Get the oldest arp which we've received on this slave for bond's
* arp_targets.
*/
@@ -368,14 +420,10 @@
static inline unsigned long slave_last_rx(struct bonding *bond,
struct slave *slave)
{
- if (slave_do_arp_validate(bond, slave)) {
- if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL)
- return slave_oldest_target_arp_rx(bond, slave);
- else
- return slave->last_arp_rx;
- }
+ if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL)
+ return slave_oldest_target_arp_rx(bond, slave);
- return slave->dev->last_rx;
+ return slave->last_rx;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
@@ -394,17 +442,19 @@
}
#endif
-static inline void bond_set_slave_inactive_flags(struct slave *slave)
+static inline void bond_set_slave_inactive_flags(struct slave *slave,
+ bool notify)
{
if (!bond_is_lb(slave->bond))
- bond_set_backup_slave(slave);
+ bond_set_slave_state(slave, BOND_STATE_BACKUP, notify);
if (!slave->bond->params.all_slaves_active)
slave->inactive = 1;
}
-static inline void bond_set_slave_active_flags(struct slave *slave)
+static inline void bond_set_slave_active_flags(struct slave *slave,
+ bool notify)
{
- bond_set_active_slave(slave);
+ bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify);
slave->inactive = 0;
}
@@ -450,8 +500,6 @@
int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev);
int bond_release(struct net_device *bond_dev, struct net_device *slave_dev);
int bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, int count);
-int bond_parse_parm(const char *mode_arg, const struct bond_parm_tbl *tbl);
-int bond_parm_tbl_lookup(int mode, const struct bond_parm_tbl *tbl);
void bond_select_active_slave(struct bonding *bond);
void bond_change_active_slave(struct bonding *bond, struct slave *new_active);
void bond_create_debugfs(void);
@@ -464,8 +512,6 @@
unsigned int bond_get_num_tx_queues(void);
int bond_netlink_init(void);
void bond_netlink_fini(void);
-int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target);
-int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target);
struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
struct net_device *bond_option_active_slave_get(struct bonding *bond);
const char *bond_slave_link_status(s8 link);
diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index 88a6a58..fc73865 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -204,7 +204,6 @@
skb->protocol = htons(ETH_P_CAIF);
skb_reset_mac_header(skb);
- skb->dev = ser->dev;
debugfs_rx(ser, data, count);
/* Push received packet up the stack. */
ret = netif_rx_ni(skb);
diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c
index 155db68..ff54c0e 100644
--- a/drivers/net/caif/caif_spi.c
+++ b/drivers/net/caif/caif_spi.c
@@ -554,7 +554,6 @@
skb->protocol = htons(ETH_P_CAIF);
skb_reset_mac_header(skb);
- skb->dev = cfspi->ndev;
/*
* Push received packet up the stack.
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index d447b88..9e7d95d 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -104,7 +104,7 @@
config CAN_FLEXCAN
tristate "Support for Freescale FLEXCAN based chips"
- depends on (ARM && CPU_LITTLE_ENDIAN) || PPC
+ depends on ARM || PPC
---help---
Say Y here if you want to support for Freescale FlexCAN.
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index 6efe274..f07fa89 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -420,7 +420,11 @@
at91_transceiver_switch(priv, 1);
/* enable chip */
- at91_write(priv, AT91_MR, AT91_MR_CANEN);
+ if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+ reg_mr = AT91_MR_CANEN | AT91_MR_ABM;
+ else
+ reg_mr = AT91_MR_CANEN;
+ at91_write(priv, AT91_MR, reg_mr);
priv->can.state = CAN_STATE_ERROR_ACTIVE;
@@ -1190,6 +1194,7 @@
.ndo_open = at91_open,
.ndo_stop = at91_close,
.ndo_start_xmit = at91_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
static ssize_t at91_sysfs_show_mb0_id(struct device *dev,
@@ -1341,7 +1346,8 @@
priv->can.bittiming_const = &at91_bittiming_const;
priv->can.do_set_mode = at91_set_mode;
priv->can.do_get_berr_counter = at91_get_berr_counter;
- priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES;
+ priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES |
+ CAN_CTRLMODE_LISTENONLY;
priv->dev = dev;
priv->reg_base = addr;
priv->devtype_data = *devtype_data;
diff --git a/drivers/net/can/bfin_can.c b/drivers/net/can/bfin_can.c
index 8d2b89a..543ecce 100644
--- a/drivers/net/can/bfin_can.c
+++ b/drivers/net/can/bfin_can.c
@@ -528,6 +528,7 @@
.ndo_open = bfin_can_open,
.ndo_stop = bfin_can_close,
.ndo_start_xmit = bfin_can_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
static int bfin_can_probe(struct platform_device *pdev)
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index 951bfed..9c32e9e 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -1277,6 +1277,7 @@
.ndo_open = c_can_open,
.ndo_stop = c_can_close,
.ndo_start_xmit = c_can_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
int register_c_can_dev(struct net_device *dev)
diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c
index 0f12abf..d837927 100644
--- a/drivers/net/can/cc770/cc770.c
+++ b/drivers/net/can/cc770/cc770.c
@@ -823,6 +823,7 @@
.ndo_open = cc770_open,
.ndo_stop = cc770_close,
.ndo_start_xmit = cc770_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
int register_cc770dev(struct net_device *dev)
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 13a9098..c7a2604 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -99,10 +99,10 @@
return 1000 * (tseg + 1 - *tseg2) / (tseg + 1);
}
-static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt)
+static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt,
+ const struct can_bittiming_const *btc)
{
struct can_priv *priv = netdev_priv(dev);
- const struct can_bittiming_const *btc = priv->bittiming_const;
long rate, best_rate = 0;
long best_error = 1000000000, error = 0;
int best_tseg = 0, best_brp = 0, brp = 0;
@@ -110,9 +110,6 @@
int spt_error = 1000, spt = 0, sampl_pt;
u64 v64;
- if (!priv->bittiming_const)
- return -ENOTSUPP;
-
/* Use CIA recommended sample points */
if (bt->sample_point) {
sampl_pt = bt->sample_point;
@@ -204,7 +201,8 @@
return 0;
}
#else /* !CONFIG_CAN_CALC_BITTIMING */
-static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt)
+static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt,
+ const struct can_bittiming_const *btc)
{
netdev_err(dev, "bit-timing calculation not available\n");
return -EINVAL;
@@ -217,16 +215,13 @@
* prescaler value brp. You can find more information in the header
* file linux/can/netlink.h.
*/
-static int can_fixup_bittiming(struct net_device *dev, struct can_bittiming *bt)
+static int can_fixup_bittiming(struct net_device *dev, struct can_bittiming *bt,
+ const struct can_bittiming_const *btc)
{
struct can_priv *priv = netdev_priv(dev);
- const struct can_bittiming_const *btc = priv->bittiming_const;
int tseg1, alltseg;
u64 brp64;
- if (!priv->bittiming_const)
- return -ENOTSUPP;
-
tseg1 = bt->prop_seg + bt->phase_seg1;
if (!bt->sjw)
bt->sjw = 1;
@@ -254,26 +249,29 @@
return 0;
}
-static int can_get_bittiming(struct net_device *dev, struct can_bittiming *bt)
+static int can_get_bittiming(struct net_device *dev, struct can_bittiming *bt,
+ const struct can_bittiming_const *btc)
{
- struct can_priv *priv = netdev_priv(dev);
int err;
/* Check if the CAN device has bit-timing parameters */
- if (priv->bittiming_const) {
+ if (!btc)
+ return -ENOTSUPP;
- /* Non-expert mode? Check if the bitrate has been pre-defined */
- if (!bt->tq)
- /* Determine bit-timing parameters */
- err = can_calc_bittiming(dev, bt);
- else
- /* Check bit-timing params and calculate proper brp */
- err = can_fixup_bittiming(dev, bt);
- if (err)
- return err;
- }
+ /*
+ * Depending on the given can_bittiming parameter structure the CAN
+ * timing parameters are calculated based on the provided bitrate OR
+ * alternatively the CAN timing parameters (tq, prop_seg, etc.) are
+ * provided directly which are then checked and fixed up.
+ */
+ if (!bt->tq && bt->bitrate)
+ err = can_calc_bittiming(dev, bt, btc);
+ else if (bt->tq && !bt->bitrate)
+ err = can_fixup_bittiming(dev, bt, btc);
+ else
+ err = -EINVAL;
- return 0;
+ return err;
}
/*
@@ -317,28 +315,20 @@
BUG_ON(idx >= priv->echo_skb_max);
/* check flag whether this packet has to be looped back */
- if (!(dev->flags & IFF_ECHO) || skb->pkt_type != PACKET_LOOPBACK) {
+ if (!(dev->flags & IFF_ECHO) || skb->pkt_type != PACKET_LOOPBACK ||
+ (skb->protocol != htons(ETH_P_CAN) &&
+ skb->protocol != htons(ETH_P_CANFD))) {
kfree_skb(skb);
return;
}
if (!priv->echo_skb[idx]) {
- struct sock *srcsk = skb->sk;
- if (atomic_read(&skb->users) != 1) {
- struct sk_buff *old_skb = skb;
-
- skb = skb_clone(old_skb, GFP_ATOMIC);
- kfree_skb(old_skb);
- if (!skb)
- return;
- } else
- skb_orphan(skb);
-
- skb->sk = srcsk;
+ skb = can_create_echo_skb(skb);
+ if (!skb)
+ return;
/* make settings for echo to reduce code in irq context */
- skb->protocol = htons(ETH_P_CAN);
skb->pkt_type = PACKET_BROADCAST;
skb->ip_summed = CHECKSUM_UNNECESSARY;
skb->dev = dev;
@@ -521,6 +511,30 @@
}
EXPORT_SYMBOL_GPL(alloc_can_skb);
+struct sk_buff *alloc_canfd_skb(struct net_device *dev,
+ struct canfd_frame **cfd)
+{
+ struct sk_buff *skb;
+
+ skb = netdev_alloc_skb(dev, sizeof(struct can_skb_priv) +
+ sizeof(struct canfd_frame));
+ if (unlikely(!skb))
+ return NULL;
+
+ skb->protocol = htons(ETH_P_CANFD);
+ skb->pkt_type = PACKET_BROADCAST;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ can_skb_reserve(skb);
+ can_skb_prv(skb)->ifindex = dev->ifindex;
+
+ *cfd = (struct canfd_frame *)skb_put(skb, sizeof(struct canfd_frame));
+ memset(*cfd, 0, sizeof(struct canfd_frame));
+
+ return skb;
+}
+EXPORT_SYMBOL_GPL(alloc_canfd_skb);
+
struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf)
{
struct sk_buff *skb;
@@ -581,6 +595,39 @@
EXPORT_SYMBOL_GPL(free_candev);
/*
+ * changing MTU and control mode for CAN/CANFD devices
+ */
+int can_change_mtu(struct net_device *dev, int new_mtu)
+{
+ struct can_priv *priv = netdev_priv(dev);
+
+ /* Do not allow changing the MTU while running */
+ if (dev->flags & IFF_UP)
+ return -EBUSY;
+
+ /* allow change of MTU according to the CANFD ability of the device */
+ switch (new_mtu) {
+ case CAN_MTU:
+ priv->ctrlmode &= ~CAN_CTRLMODE_FD;
+ break;
+
+ case CANFD_MTU:
+ if (!(priv->ctrlmode_supported & CAN_CTRLMODE_FD))
+ return -EINVAL;
+
+ priv->ctrlmode |= CAN_CTRLMODE_FD;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ dev->mtu = new_mtu;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(can_change_mtu);
+
+/*
* Common open function when the device gets opened.
*
* This function should be called in the open function of the device
@@ -590,11 +637,19 @@
{
struct can_priv *priv = netdev_priv(dev);
- if (!priv->bittiming.tq && !priv->bittiming.bitrate) {
+ if (!priv->bittiming.bitrate) {
netdev_err(dev, "bit-timing not yet defined\n");
return -EINVAL;
}
+ /* For CAN FD the data bitrate has to be >= the arbitration bitrate */
+ if ((priv->ctrlmode & CAN_CTRLMODE_FD) &&
+ (!priv->data_bittiming.bitrate ||
+ (priv->data_bittiming.bitrate < priv->bittiming.bitrate))) {
+ netdev_err(dev, "incorrect/missing data bit-timing\n");
+ return -EINVAL;
+ }
+
/* Switch carrier on if device was stopped while in bus-off state */
if (!netif_carrier_ok(dev))
netif_carrier_on(dev);
@@ -633,6 +688,10 @@
= { .len = sizeof(struct can_bittiming_const) },
[IFLA_CAN_CLOCK] = { .len = sizeof(struct can_clock) },
[IFLA_CAN_BERR_COUNTER] = { .len = sizeof(struct can_berr_counter) },
+ [IFLA_CAN_DATA_BITTIMING]
+ = { .len = sizeof(struct can_bittiming) },
+ [IFLA_CAN_DATA_BITTIMING_CONST]
+ = { .len = sizeof(struct can_bittiming_const) },
};
static int can_changelink(struct net_device *dev,
@@ -651,9 +710,7 @@
if (dev->flags & IFF_UP)
return -EBUSY;
memcpy(&bt, nla_data(data[IFLA_CAN_BITTIMING]), sizeof(bt));
- if ((!bt.bitrate && !bt.tq) || (bt.bitrate && bt.tq))
- return -EINVAL;
- err = can_get_bittiming(dev, &bt);
+ err = can_get_bittiming(dev, &bt, priv->bittiming_const);
if (err)
return err;
memcpy(&priv->bittiming, &bt, sizeof(bt));
@@ -677,6 +734,12 @@
return -EOPNOTSUPP;
priv->ctrlmode &= ~cm->mask;
priv->ctrlmode |= cm->flags;
+
+ /* CAN_CTRLMODE_FD can only be set when driver supports FD */
+ if (priv->ctrlmode & CAN_CTRLMODE_FD)
+ dev->mtu = CANFD_MTU;
+ else
+ dev->mtu = CAN_MTU;
}
if (data[IFLA_CAN_RESTART_MS]) {
@@ -695,6 +758,27 @@
return err;
}
+ if (data[IFLA_CAN_DATA_BITTIMING]) {
+ struct can_bittiming dbt;
+
+ /* Do not allow changing bittiming while running */
+ if (dev->flags & IFF_UP)
+ return -EBUSY;
+ memcpy(&dbt, nla_data(data[IFLA_CAN_DATA_BITTIMING]),
+ sizeof(dbt));
+ err = can_get_bittiming(dev, &dbt, priv->data_bittiming_const);
+ if (err)
+ return err;
+ memcpy(&priv->data_bittiming, &dbt, sizeof(dbt));
+
+ if (priv->do_set_data_bittiming) {
+ /* Finally, set the bit-timing registers */
+ err = priv->do_set_data_bittiming(dev);
+ if (err)
+ return err;
+ }
+ }
+
return 0;
}
@@ -703,7 +787,8 @@
struct can_priv *priv = netdev_priv(dev);
size_t size = 0;
- size += nla_total_size(sizeof(struct can_bittiming)); /* IFLA_CAN_BITTIMING */
+ if (priv->bittiming.bitrate) /* IFLA_CAN_BITTIMING */
+ size += nla_total_size(sizeof(struct can_bittiming));
if (priv->bittiming_const) /* IFLA_CAN_BITTIMING_CONST */
size += nla_total_size(sizeof(struct can_bittiming_const));
size += nla_total_size(sizeof(struct can_clock)); /* IFLA_CAN_CLOCK */
@@ -712,6 +797,10 @@
size += nla_total_size(sizeof(u32)); /* IFLA_CAN_RESTART_MS */
if (priv->do_get_berr_counter) /* IFLA_CAN_BERR_COUNTER */
size += nla_total_size(sizeof(struct can_berr_counter));
+ if (priv->data_bittiming.bitrate) /* IFLA_CAN_DATA_BITTIMING */
+ size += nla_total_size(sizeof(struct can_bittiming));
+ if (priv->data_bittiming_const) /* IFLA_CAN_DATA_BITTIMING_CONST */
+ size += nla_total_size(sizeof(struct can_bittiming_const));
return size;
}
@@ -725,19 +814,34 @@
if (priv->do_get_state)
priv->do_get_state(dev, &state);
- if (nla_put(skb, IFLA_CAN_BITTIMING,
- sizeof(priv->bittiming), &priv->bittiming) ||
+
+ if ((priv->bittiming.bitrate &&
+ nla_put(skb, IFLA_CAN_BITTIMING,
+ sizeof(priv->bittiming), &priv->bittiming)) ||
+
(priv->bittiming_const &&
nla_put(skb, IFLA_CAN_BITTIMING_CONST,
sizeof(*priv->bittiming_const), priv->bittiming_const)) ||
+
nla_put(skb, IFLA_CAN_CLOCK, sizeof(cm), &priv->clock) ||
nla_put_u32(skb, IFLA_CAN_STATE, state) ||
nla_put(skb, IFLA_CAN_CTRLMODE, sizeof(cm), &cm) ||
nla_put_u32(skb, IFLA_CAN_RESTART_MS, priv->restart_ms) ||
+
(priv->do_get_berr_counter &&
!priv->do_get_berr_counter(dev, &bec) &&
- nla_put(skb, IFLA_CAN_BERR_COUNTER, sizeof(bec), &bec)))
+ nla_put(skb, IFLA_CAN_BERR_COUNTER, sizeof(bec), &bec)) ||
+
+ (priv->data_bittiming.bitrate &&
+ nla_put(skb, IFLA_CAN_DATA_BITTIMING,
+ sizeof(priv->data_bittiming), &priv->data_bittiming)) ||
+
+ (priv->data_bittiming_const &&
+ nla_put(skb, IFLA_CAN_DATA_BITTIMING_CONST,
+ sizeof(*priv->data_bittiming_const),
+ priv->data_bittiming_const)))
return -EMSGSIZE;
+
return 0;
}
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index aaed97b..f425ec2 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -144,6 +144,8 @@
#define FLEXCAN_MB_CODE_MASK (0xf0ffffff)
+#define FLEXCAN_TIMEOUT_US (50)
+
/*
* FLEXCAN hardware feature flags
*
@@ -235,9 +237,12 @@
};
/*
- * Abstract off the read/write for arm versus ppc.
+ * Abstract off the read/write for arm versus ppc. This
+ * assumes that PPC uses big-endian registers and everything
+ * else uses little-endian registers, independent of CPU
+ * endianess.
*/
-#if defined(__BIG_ENDIAN)
+#if defined(CONFIG_PPC)
static inline u32 flexcan_read(void __iomem *addr)
{
return in_be32(addr);
@@ -259,6 +264,22 @@
}
#endif
+static inline int flexcan_transceiver_enable(const struct flexcan_priv *priv)
+{
+ if (!priv->reg_xceiver)
+ return 0;
+
+ return regulator_enable(priv->reg_xceiver);
+}
+
+static inline int flexcan_transceiver_disable(const struct flexcan_priv *priv)
+{
+ if (!priv->reg_xceiver)
+ return 0;
+
+ return regulator_disable(priv->reg_xceiver);
+}
+
static inline int flexcan_has_and_handle_berr(const struct flexcan_priv *priv,
u32 reg_esr)
{
@@ -266,26 +287,95 @@
(reg_esr & FLEXCAN_ESR_ERR_BUS);
}
-static inline void flexcan_chip_enable(struct flexcan_priv *priv)
+static int flexcan_chip_enable(struct flexcan_priv *priv)
{
struct flexcan_regs __iomem *regs = priv->base;
+ unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;
u32 reg;
reg = flexcan_read(®s->mcr);
reg &= ~FLEXCAN_MCR_MDIS;
flexcan_write(reg, ®s->mcr);
- udelay(10);
+ while (timeout-- && (flexcan_read(®s->mcr) & FLEXCAN_MCR_LPM_ACK))
+ usleep_range(10, 20);
+
+ if (flexcan_read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)
+ return -ETIMEDOUT;
+
+ return 0;
}
-static inline void flexcan_chip_disable(struct flexcan_priv *priv)
+static int flexcan_chip_disable(struct flexcan_priv *priv)
{
struct flexcan_regs __iomem *regs = priv->base;
+ unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;
u32 reg;
reg = flexcan_read(®s->mcr);
reg |= FLEXCAN_MCR_MDIS;
flexcan_write(reg, ®s->mcr);
+
+ while (timeout-- && !(flexcan_read(®s->mcr) & FLEXCAN_MCR_LPM_ACK))
+ usleep_range(10, 20);
+
+ if (!(flexcan_read(®s->mcr) & FLEXCAN_MCR_LPM_ACK))
+ return -ETIMEDOUT;
+
+ return 0;
+}
+
+static int flexcan_chip_freeze(struct flexcan_priv *priv)
+{
+ struct flexcan_regs __iomem *regs = priv->base;
+ unsigned int timeout = 1000 * 1000 * 10 / priv->can.bittiming.bitrate;
+ u32 reg;
+
+ reg = flexcan_read(®s->mcr);
+ reg |= FLEXCAN_MCR_HALT;
+ flexcan_write(reg, ®s->mcr);
+
+ while (timeout-- && !(flexcan_read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK))
+ usleep_range(100, 200);
+
+ if (!(flexcan_read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK))
+ return -ETIMEDOUT;
+
+ return 0;
+}
+
+static int flexcan_chip_unfreeze(struct flexcan_priv *priv)
+{
+ struct flexcan_regs __iomem *regs = priv->base;
+ unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;
+ u32 reg;
+
+ reg = flexcan_read(®s->mcr);
+ reg &= ~FLEXCAN_MCR_HALT;
+ flexcan_write(reg, ®s->mcr);
+
+ while (timeout-- && (flexcan_read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK))
+ usleep_range(10, 20);
+
+ if (flexcan_read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK)
+ return -ETIMEDOUT;
+
+ return 0;
+}
+
+static int flexcan_chip_softreset(struct flexcan_priv *priv)
+{
+ struct flexcan_regs __iomem *regs = priv->base;
+ unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;
+
+ flexcan_write(FLEXCAN_MCR_SOFTRST, ®s->mcr);
+ while (timeout-- && (flexcan_read(®s->mcr) & FLEXCAN_MCR_SOFTRST))
+ usleep_range(10, 20);
+
+ if (flexcan_read(®s->mcr) & FLEXCAN_MCR_SOFTRST)
+ return -ETIMEDOUT;
+
+ return 0;
}
static int flexcan_get_berr_counter(const struct net_device *dev,
@@ -706,19 +796,14 @@
u32 reg_mcr, reg_ctrl;
/* enable module */
- flexcan_chip_enable(priv);
+ err = flexcan_chip_enable(priv);
+ if (err)
+ return err;
/* soft reset */
- flexcan_write(FLEXCAN_MCR_SOFTRST, ®s->mcr);
- udelay(10);
-
- reg_mcr = flexcan_read(®s->mcr);
- if (reg_mcr & FLEXCAN_MCR_SOFTRST) {
- netdev_err(dev, "Failed to softreset can module (mcr=0x%08x)\n",
- reg_mcr);
- err = -ENODEV;
- goto out;
- }
+ err = flexcan_chip_softreset(priv);
+ if (err)
+ goto out_chip_disable;
flexcan_set_bittiming(dev);
@@ -785,16 +870,14 @@
if (priv->devtype_data->features & FLEXCAN_HAS_V10_FEATURES)
flexcan_write(0x0, ®s->rxfgmask);
- if (priv->reg_xceiver) {
- err = regulator_enable(priv->reg_xceiver);
- if (err)
- goto out;
- }
+ err = flexcan_transceiver_enable(priv);
+ if (err)
+ goto out_chip_disable;
/* synchronize with the can bus */
- reg_mcr = flexcan_read(®s->mcr);
- reg_mcr &= ~FLEXCAN_MCR_HALT;
- flexcan_write(reg_mcr, ®s->mcr);
+ err = flexcan_chip_unfreeze(priv);
+ if (err)
+ goto out_transceiver_disable;
priv->can.state = CAN_STATE_ERROR_ACTIVE;
@@ -807,7 +890,9 @@
return 0;
- out:
+ out_transceiver_disable:
+ flexcan_transceiver_disable(priv);
+ out_chip_disable:
flexcan_chip_disable(priv);
return err;
}
@@ -822,18 +907,17 @@
{
struct flexcan_priv *priv = netdev_priv(dev);
struct flexcan_regs __iomem *regs = priv->base;
- u32 reg;
+
+ /* freeze + disable module */
+ flexcan_chip_freeze(priv);
+ flexcan_chip_disable(priv);
/* Disable all interrupts */
flexcan_write(0, ®s->imask1);
+ flexcan_write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL,
+ ®s->ctrl);
- /* Disable + halt module */
- reg = flexcan_read(®s->mcr);
- reg |= FLEXCAN_MCR_MDIS | FLEXCAN_MCR_HALT;
- flexcan_write(reg, ®s->mcr);
-
- if (priv->reg_xceiver)
- regulator_disable(priv->reg_xceiver);
+ flexcan_transceiver_disable(priv);
priv->can.state = CAN_STATE_STOPPED;
return;
@@ -863,7 +947,7 @@
/* start chip and queuing */
err = flexcan_chip_start(dev);
if (err)
- goto out_close;
+ goto out_free_irq;
can_led_event(dev, CAN_LED_EVENT_OPEN);
@@ -872,6 +956,8 @@
return 0;
+ out_free_irq:
+ free_irq(dev->irq, dev);
out_close:
close_candev(dev);
out_disable_per:
@@ -925,6 +1011,7 @@
.ndo_open = flexcan_open,
.ndo_stop = flexcan_close,
.ndo_start_xmit = flexcan_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
static int register_flexcandev(struct net_device *dev)
@@ -942,12 +1029,16 @@
goto out_disable_ipg;
/* select "bus clock", chip must be disabled */
- flexcan_chip_disable(priv);
+ err = flexcan_chip_disable(priv);
+ if (err)
+ goto out_disable_per;
reg = flexcan_read(®s->ctrl);
reg |= FLEXCAN_CTRL_CLK_SRC;
flexcan_write(reg, ®s->ctrl);
- flexcan_chip_enable(priv);
+ err = flexcan_chip_enable(priv);
+ if (err)
+ goto out_chip_disable;
/* set freeze, halt and activate FIFO, restrict register access */
reg = flexcan_read(®s->mcr);
@@ -964,14 +1055,15 @@
if (!(reg & FLEXCAN_MCR_FEN)) {
netdev_err(dev, "Could not enable RX FIFO, unsupported core\n");
err = -ENODEV;
- goto out_disable_per;
+ goto out_chip_disable;
}
err = register_candev(dev);
- out_disable_per:
/* disable core and turn off clocks */
+ out_chip_disable:
flexcan_chip_disable(priv);
+ out_disable_per:
clk_disable_unprepare(priv->clk_per);
out_disable_ipg:
clk_disable_unprepare(priv->clk_ipg);
@@ -1041,9 +1133,9 @@
of_id = of_match_device(flexcan_of_match, &pdev->dev);
if (of_id) {
devtype_data = of_id->data;
- } else if (pdev->id_entry->driver_data) {
+ } else if (platform_get_device_id(pdev)->driver_data) {
devtype_data = (struct flexcan_devtype_data *)
- pdev->id_entry->driver_data;
+ platform_get_device_id(pdev)->driver_data;
} else {
return -ENODEV;
}
@@ -1101,21 +1193,24 @@
static int flexcan_remove(struct platform_device *pdev)
{
struct net_device *dev = platform_get_drvdata(pdev);
+ struct flexcan_priv *priv = netdev_priv(dev);
unregister_flexcandev(dev);
-
+ netif_napi_del(&priv->napi);
free_candev(dev);
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int flexcan_suspend(struct device *device)
+static int __maybe_unused flexcan_suspend(struct device *device)
{
struct net_device *dev = dev_get_drvdata(device);
struct flexcan_priv *priv = netdev_priv(dev);
+ int err;
- flexcan_chip_disable(priv);
+ err = flexcan_chip_disable(priv);
+ if (err)
+ return err;
if (netif_running(dev)) {
netif_stop_queue(dev);
@@ -1126,7 +1221,7 @@
return 0;
}
-static int flexcan_resume(struct device *device)
+static int __maybe_unused flexcan_resume(struct device *device)
{
struct net_device *dev = dev_get_drvdata(device);
struct flexcan_priv *priv = netdev_priv(dev);
@@ -1136,11 +1231,8 @@
netif_device_attach(dev);
netif_start_queue(dev);
}
- flexcan_chip_enable(priv);
-
- return 0;
+ return flexcan_chip_enable(priv);
}
-#endif /* CONFIG_PM_SLEEP */
static SIMPLE_DEV_PM_OPS(flexcan_pm_ops, flexcan_suspend, flexcan_resume);
diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c
index ab506d6..3fd9fd9 100644
--- a/drivers/net/can/grcan.c
+++ b/drivers/net/can/grcan.c
@@ -1578,6 +1578,7 @@
.ndo_open = grcan_open,
.ndo_stop = grcan_close,
.ndo_start_xmit = grcan_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
static int grcan_setup_netdev(struct platform_device *ofdev,
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index e24e669..2382c04 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -18,6 +18,7 @@
#include <linux/netdevice.h>
#include <linux/can.h>
#include <linux/can/dev.h>
+#include <linux/can/skb.h>
#include <linux/can/error.h>
#include <linux/mfd/janz.h>
@@ -197,9 +198,6 @@
struct net_device *ndev;
struct napi_struct napi;
- /* Device for printing */
- struct device *dev;
-
/* module number */
unsigned int num;
@@ -294,7 +292,7 @@
xord = locl ^ peer;
if ((xord & MSYNC_RB_MASK) == 0x00) {
- dev_dbg(mod->dev, "no mbox for reading\n");
+ netdev_dbg(mod->ndev, "no mbox for reading\n");
return -ENOMEM;
}
@@ -339,7 +337,7 @@
xord = locl ^ peer;
if ((xord & MSYNC_WB_MASK) == MSYNC_WB_MASK) {
- dev_err(mod->dev, "no mbox for writing\n");
+ netdev_err(mod->ndev, "no mbox for writing\n");
return -ENOMEM;
}
@@ -541,7 +539,7 @@
memcpy_fromio(&desc, desc_addr, sizeof(desc));
if (!(desc.control & DESC_VALID)) {
- dev_dbg(mod->dev, "%s: no free buffers\n", __func__);
+ netdev_dbg(mod->ndev, "%s: no free buffers\n", __func__);
return -ENOMEM;
}
@@ -572,7 +570,7 @@
memcpy_fromio(&desc, desc_addr, sizeof(desc));
if (!(desc.control & DESC_VALID)) {
- dev_dbg(mod->dev, "%s: no buffers to recv\n", __func__);
+ netdev_dbg(mod->ndev, "%s: no buffers to recv\n", __func__);
return -ENOMEM;
}
@@ -882,7 +880,7 @@
*/
static void ican3_handle_idvers(struct ican3_dev *mod, struct ican3_msg *msg)
{
- dev_dbg(mod->dev, "IDVERS response: %s\n", msg->data);
+ netdev_dbg(mod->ndev, "IDVERS response: %s\n", msg->data);
}
static void ican3_handle_msglost(struct ican3_dev *mod, struct ican3_msg *msg)
@@ -898,7 +896,7 @@
* error frame for userspace
*/
if (msg->spec == MSG_MSGLOST) {
- dev_err(mod->dev, "lost %d control messages\n", msg->data[0]);
+ netdev_err(mod->ndev, "lost %d control messages\n", msg->data[0]);
return;
}
@@ -938,13 +936,13 @@
/* we can only handle the SJA1000 part */
if (msg->data[1] != CEVTIND_CHIP_SJA1000) {
- dev_err(mod->dev, "unable to handle errors on non-SJA1000\n");
+ netdev_err(mod->ndev, "unable to handle errors on non-SJA1000\n");
return -ENODEV;
}
/* check the message length for sanity */
if (le16_to_cpu(msg->len) < 6) {
- dev_err(mod->dev, "error message too short\n");
+ netdev_err(mod->ndev, "error message too short\n");
return -EINVAL;
}
@@ -966,7 +964,7 @@
*/
if (isrc == CEVTIND_BEI) {
int ret;
- dev_dbg(mod->dev, "bus error interrupt\n");
+ netdev_dbg(mod->ndev, "bus error interrupt\n");
/* TX error */
if (!(ecc & ECC_DIR)) {
@@ -982,7 +980,7 @@
*/
ret = ican3_set_buserror(mod, 1);
if (ret) {
- dev_err(mod->dev, "unable to re-enable bus-error\n");
+ netdev_err(mod->ndev, "unable to re-enable bus-error\n");
return ret;
}
@@ -997,7 +995,7 @@
/* data overrun interrupt */
if (isrc == CEVTIND_DOI || isrc == CEVTIND_LOST) {
- dev_dbg(mod->dev, "data overrun interrupt\n");
+ netdev_dbg(mod->ndev, "data overrun interrupt\n");
cf->can_id |= CAN_ERR_CRTL;
cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
stats->rx_over_errors++;
@@ -1006,7 +1004,7 @@
/* error warning + passive interrupt */
if (isrc == CEVTIND_EI) {
- dev_dbg(mod->dev, "error warning + passive interrupt\n");
+ netdev_dbg(mod->ndev, "error warning + passive interrupt\n");
if (status & SR_BS) {
state = CAN_STATE_BUS_OFF;
cf->can_id |= CAN_ERR_BUSOFF;
@@ -1087,7 +1085,7 @@
complete(&mod->termination_comp);
break;
default:
- dev_err(mod->dev, "received an unknown inquiry response\n");
+ netdev_err(mod->ndev, "received an unknown inquiry response\n");
break;
}
}
@@ -1095,7 +1093,7 @@
static void ican3_handle_unknown_message(struct ican3_dev *mod,
struct ican3_msg *msg)
{
- dev_warn(mod->dev, "received unknown message: spec 0x%.2x length %d\n",
+ netdev_warn(mod->ndev, "received unknown message: spec 0x%.2x length %d\n",
msg->spec, le16_to_cpu(msg->len));
}
@@ -1104,7 +1102,7 @@
*/
static void ican3_handle_message(struct ican3_dev *mod, struct ican3_msg *msg)
{
- dev_dbg(mod->dev, "%s: modno %d spec 0x%.2x len %d bytes\n", __func__,
+ netdev_dbg(mod->ndev, "%s: modno %d spec 0x%.2x len %d bytes\n", __func__,
mod->num, msg->spec, le16_to_cpu(msg->len));
switch (msg->spec) {
@@ -1133,20 +1131,9 @@
*/
static void ican3_put_echo_skb(struct ican3_dev *mod, struct sk_buff *skb)
{
- struct sock *srcsk = skb->sk;
-
- if (atomic_read(&skb->users) != 1) {
- struct sk_buff *old_skb = skb;
-
- skb = skb_clone(old_skb, GFP_ATOMIC);
- kfree_skb(old_skb);
- if (!skb)
- return;
- } else {
- skb_orphan(skb);
- }
-
- skb->sk = srcsk;
+ skb = can_create_echo_skb(skb);
+ if (!skb)
+ return;
/* save this skb for tx interrupt echo handling */
skb_queue_tail(&mod->echoq, skb);
@@ -1322,7 +1309,7 @@
/* process all communication messages */
while (true) {
- struct ican3_msg msg;
+ struct ican3_msg uninitialized_var(msg);
ret = ican3_recv_msg(mod, &msg);
if (ret)
break;
@@ -1416,7 +1403,7 @@
msleep(10);
} while (time_before(jiffies, start + HZ / 4));
- dev_err(mod->dev, "failed to reset CAN module\n");
+ netdev_err(mod->ndev, "failed to reset CAN module\n");
return -ETIMEDOUT;
}
@@ -1435,7 +1422,7 @@
ret = ican3_reset_module(mod);
if (ret) {
- dev_err(mod->dev, "unable to reset module\n");
+ netdev_err(mod->ndev, "unable to reset module\n");
return ret;
}
@@ -1444,41 +1431,41 @@
ret = ican3_msg_connect(mod);
if (ret) {
- dev_err(mod->dev, "unable to connect to module\n");
+ netdev_err(mod->ndev, "unable to connect to module\n");
return ret;
}
ican3_init_new_host_interface(mod);
ret = ican3_msg_newhostif(mod);
if (ret) {
- dev_err(mod->dev, "unable to switch to new-style interface\n");
+ netdev_err(mod->ndev, "unable to switch to new-style interface\n");
return ret;
}
/* default to "termination on" */
ret = ican3_set_termination(mod, true);
if (ret) {
- dev_err(mod->dev, "unable to enable termination\n");
+ netdev_err(mod->ndev, "unable to enable termination\n");
return ret;
}
/* default to "bus errors enabled" */
ret = ican3_set_buserror(mod, 1);
if (ret) {
- dev_err(mod->dev, "unable to set bus-error\n");
+ netdev_err(mod->ndev, "unable to set bus-error\n");
return ret;
}
ican3_init_fast_host_interface(mod);
ret = ican3_msg_fasthostif(mod);
if (ret) {
- dev_err(mod->dev, "unable to switch to fast host interface\n");
+ netdev_err(mod->ndev, "unable to switch to fast host interface\n");
return ret;
}
ret = ican3_set_id_filter(mod, true);
if (ret) {
- dev_err(mod->dev, "unable to set acceptance filter\n");
+ netdev_err(mod->ndev, "unable to set acceptance filter\n");
return ret;
}
@@ -1497,14 +1484,14 @@
/* open the CAN layer */
ret = open_candev(ndev);
if (ret) {
- dev_err(mod->dev, "unable to start CAN layer\n");
+ netdev_err(mod->ndev, "unable to start CAN layer\n");
return ret;
}
/* bring the bus online */
ret = ican3_set_bus_state(mod, true);
if (ret) {
- dev_err(mod->dev, "unable to set bus-on\n");
+ netdev_err(mod->ndev, "unable to set bus-on\n");
close_candev(ndev);
return ret;
}
@@ -1528,7 +1515,7 @@
/* bring the bus offline, stop receiving packets */
ret = ican3_set_bus_state(mod, false);
if (ret) {
- dev_err(mod->dev, "unable to set bus-off\n");
+ netdev_err(mod->ndev, "unable to set bus-off\n");
return ret;
}
@@ -1555,7 +1542,7 @@
/* check that we can actually transmit */
if (!ican3_txok(mod)) {
- dev_err(mod->dev, "BUG: no free descriptors\n");
+ netdev_err(mod->ndev, "BUG: no free descriptors\n");
spin_unlock_irqrestore(&mod->lock, flags);
return NETDEV_TX_BUSY;
}
@@ -1607,6 +1594,7 @@
.ndo_open = ican3_open,
.ndo_stop = ican3_stop,
.ndo_start_xmit = ican3_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
/*
@@ -1667,7 +1655,7 @@
/* bring the bus online */
ret = ican3_set_bus_state(mod, true);
if (ret) {
- dev_err(mod->dev, "unable to set bus-on\n");
+ netdev_err(ndev, "unable to set bus-on\n");
return ret;
}
@@ -1692,7 +1680,7 @@
ret = wait_for_completion_timeout(&mod->buserror_comp, HZ);
if (ret == 0) {
- dev_info(mod->dev, "%s timed out\n", __func__);
+ netdev_info(mod->ndev, "%s timed out\n", __func__);
return -ETIMEDOUT;
}
@@ -1718,7 +1706,7 @@
ret = wait_for_completion_timeout(&mod->termination_comp, HZ);
if (ret == 0) {
- dev_info(mod->dev, "%s timed out\n", __func__);
+ netdev_info(mod->ndev, "%s timed out\n", __func__);
return -ETIMEDOUT;
}
@@ -1788,7 +1776,6 @@
platform_set_drvdata(pdev, ndev);
mod = netdev_priv(ndev);
mod->ndev = ndev;
- mod->dev = &pdev->dev;
mod->num = pdata->modno;
netif_napi_add(ndev, &mod->napi, ican3_napi, ICAN3_RX_BUFFERS);
skb_queue_head_init(&mod->echoq);
diff --git a/drivers/net/can/mcp251x.c b/drivers/net/can/mcp251x.c
index cdb9808..28c11f8 100644
--- a/drivers/net/can/mcp251x.c
+++ b/drivers/net/can/mcp251x.c
@@ -601,10 +601,10 @@
(bt->prop_seg - 1));
mcp251x_write_bits(spi, CNF3, CNF3_PHSEG2_MASK,
(bt->phase_seg2 - 1));
- dev_info(&spi->dev, "CNF: 0x%02x 0x%02x 0x%02x\n",
- mcp251x_read_reg(spi, CNF1),
- mcp251x_read_reg(spi, CNF2),
- mcp251x_read_reg(spi, CNF3));
+ dev_dbg(&spi->dev, "CNF: 0x%02x 0x%02x 0x%02x\n",
+ mcp251x_read_reg(spi, CNF1),
+ mcp251x_read_reg(spi, CNF2),
+ mcp251x_read_reg(spi, CNF3));
return 0;
}
@@ -672,7 +672,7 @@
static int mcp251x_power_enable(struct regulator *reg, int enable)
{
- if (IS_ERR(reg))
+ if (IS_ERR_OR_NULL(reg))
return 0;
if (enable)
@@ -996,6 +996,7 @@
.ndo_open = mcp251x_open,
.ndo_stop = mcp251x_stop,
.ndo_start_xmit = mcp251x_hard_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
static const struct of_device_id mcp251x_of_match[] = {
@@ -1155,8 +1156,6 @@
devm_can_led_init(net);
- dev_info(&spi->dev, "probed\n");
-
return ret;
error_probe:
@@ -1197,9 +1196,7 @@
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-
-static int mcp251x_can_suspend(struct device *dev)
+static int __maybe_unused mcp251x_can_suspend(struct device *dev)
{
struct spi_device *spi = to_spi_device(dev);
struct mcp251x_priv *priv = spi_get_drvdata(spi);
@@ -1221,7 +1218,7 @@
priv->after_suspend = AFTER_SUSPEND_DOWN;
}
- if (!IS_ERR(priv->power)) {
+ if (!IS_ERR_OR_NULL(priv->power)) {
regulator_disable(priv->power);
priv->after_suspend |= AFTER_SUSPEND_POWER;
}
@@ -1229,7 +1226,7 @@
return 0;
}
-static int mcp251x_can_resume(struct device *dev)
+static int __maybe_unused mcp251x_can_resume(struct device *dev)
{
struct spi_device *spi = to_spi_device(dev);
struct mcp251x_priv *priv = spi_get_drvdata(spi);
@@ -1249,7 +1246,6 @@
enable_irq(spi->irq);
return 0;
}
-#endif
static SIMPLE_DEV_PM_OPS(mcp251x_can_pm_ops, mcp251x_can_suspend,
mcp251x_can_resume);
diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c
index b9f3faa..e0c9be5 100644
--- a/drivers/net/can/mscan/mscan.c
+++ b/drivers/net/can/mscan/mscan.c
@@ -647,9 +647,10 @@
}
static const struct net_device_ops mscan_netdev_ops = {
- .ndo_open = mscan_open,
- .ndo_stop = mscan_close,
- .ndo_start_xmit = mscan_start_xmit,
+ .ndo_open = mscan_open,
+ .ndo_stop = mscan_close,
+ .ndo_start_xmit = mscan_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
int register_mscandev(struct net_device *dev, int mscan_clksrc)
diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c
index 6c077eb..6472562 100644
--- a/drivers/net/can/pch_can.c
+++ b/drivers/net/can/pch_can.c
@@ -950,6 +950,7 @@
.ndo_open = pch_can_open,
.ndo_stop = pch_close,
.ndo_start_xmit = pch_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
static void pch_can_remove(struct pci_dev *pdev)
diff --git a/drivers/net/can/sja1000/Kconfig b/drivers/net/can/sja1000/Kconfig
index ff2ba86..4b18b87 100644
--- a/drivers/net/can/sja1000/Kconfig
+++ b/drivers/net/can/sja1000/Kconfig
@@ -17,16 +17,9 @@
the "platform bus" (Linux abstraction for directly to the
processor attached devices). Which can be found on various
boards from Phytec (http://www.phytec.de) like the PCM027,
- PCM038.
-
-config CAN_SJA1000_OF_PLATFORM
- tristate "Generic OF Platform Bus based SJA1000 driver"
- depends on OF
- ---help---
- This driver adds support for the SJA1000 chips connected to
- the OpenFirmware "platform bus" found on embedded systems with
- OpenFirmware bindings, e.g. if you have a PowerPC based system
- you may want to enable this option.
+ PCM038. It also provides the OpenFirmware "platform bus" found
+ on embedded systems with OpenFirmware bindings, e.g. if you
+ have a PowerPC based system you may want to enable this option.
config CAN_EMS_PCMCIA
tristate "EMS CPC-CARD Card"
diff --git a/drivers/net/can/sja1000/Makefile b/drivers/net/can/sja1000/Makefile
index b3d05cb..531d5fc 100644
--- a/drivers/net/can/sja1000/Makefile
+++ b/drivers/net/can/sja1000/Makefile
@@ -5,7 +5,6 @@
obj-$(CONFIG_CAN_SJA1000) += sja1000.o
obj-$(CONFIG_CAN_SJA1000_ISA) += sja1000_isa.o
obj-$(CONFIG_CAN_SJA1000_PLATFORM) += sja1000_platform.o
-obj-$(CONFIG_CAN_SJA1000_OF_PLATFORM) += sja1000_of_platform.o
obj-$(CONFIG_CAN_EMS_PCMCIA) += ems_pcmcia.o
obj-$(CONFIG_CAN_EMS_PCI) += ems_pci.o
obj-$(CONFIG_CAN_KVASER_PCI) += kvaser_pci.o
diff --git a/drivers/net/can/sja1000/ems_pci.c b/drivers/net/can/sja1000/ems_pci.c
index d790b87..fd13dbf 100644
--- a/drivers/net/can/sja1000/ems_pci.c
+++ b/drivers/net/can/sja1000/ems_pci.c
@@ -323,6 +323,7 @@
priv->cdr = EMS_PCI_CDR;
SET_NETDEV_DEV(dev, &pdev->dev);
+ dev->dev_id = i;
if (card->version == 1)
/* reset int flag of pita */
diff --git a/drivers/net/can/sja1000/ems_pcmcia.c b/drivers/net/can/sja1000/ems_pcmcia.c
index 9e535f2..381de99 100644
--- a/drivers/net/can/sja1000/ems_pcmcia.c
+++ b/drivers/net/can/sja1000/ems_pcmcia.c
@@ -211,6 +211,7 @@
priv = netdev_priv(dev);
priv->priv = card;
SET_NETDEV_DEV(dev, &pdev->dev);
+ dev->dev_id = i;
priv->irq_flags = IRQF_SHARED;
dev->irq = pdev->irq;
diff --git a/drivers/net/can/sja1000/kvaser_pci.c b/drivers/net/can/sja1000/kvaser_pci.c
index c96eb14..23b8e13 100644
--- a/drivers/net/can/sja1000/kvaser_pci.c
+++ b/drivers/net/can/sja1000/kvaser_pci.c
@@ -270,6 +270,7 @@
priv->reg_base, board->conf_addr, dev->irq);
SET_NETDEV_DEV(dev, &pdev->dev);
+ dev->dev_id = channel;
/* Register SJA1000 device */
err = register_sja1000dev(dev);
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index 065ca49..c540e3d 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -642,6 +642,7 @@
icr |= chan->icr_mask;
SET_NETDEV_DEV(dev, &pdev->dev);
+ dev->dev_id = i;
/* Create chain of SJA1000 devices */
chan->prev_dev = pci_get_drvdata(pdev);
diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c
index f7ad754..dd56133 100644
--- a/drivers/net/can/sja1000/peak_pcmcia.c
+++ b/drivers/net/can/sja1000/peak_pcmcia.c
@@ -550,6 +550,7 @@
priv = netdev_priv(netdev);
priv->priv = card;
SET_NETDEV_DEV(netdev, &pdev->dev);
+ netdev->dev_id = i;
priv->irq_flags = IRQF_SHARED;
netdev->irq = pdev->irq;
diff --git a/drivers/net/can/sja1000/plx_pci.c b/drivers/net/can/sja1000/plx_pci.c
index fbb61a0..ec39b7c 100644
--- a/drivers/net/can/sja1000/plx_pci.c
+++ b/drivers/net/can/sja1000/plx_pci.c
@@ -587,6 +587,7 @@
priv->cdr = ci->cdr;
SET_NETDEV_DEV(dev, &pdev->dev);
+ dev->dev_id = i;
/* Register SJA1000 device */
err = register_sja1000dev(dev);
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index f17c301..f31499a 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -106,8 +106,7 @@
struct sja1000_priv *priv = netdev_priv(dev);
if (priv->reg_base && sja1000_is_absent(priv)) {
- printk(KERN_INFO "%s: probing @0x%lX failed\n",
- DRV_NAME, dev->base_addr);
+ netdev_err(dev, "probing failed\n");
return 0;
}
return -1;
@@ -643,9 +642,10 @@
EXPORT_SYMBOL_GPL(free_sja1000dev);
static const struct net_device_ops sja1000_netdev_ops = {
- .ndo_open = sja1000_open,
- .ndo_stop = sja1000_close,
- .ndo_start_xmit = sja1000_start_xmit,
+ .ndo_open = sja1000_open,
+ .ndo_stop = sja1000_close,
+ .ndo_start_xmit = sja1000_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
int register_sja1000dev(struct net_device *dev)
diff --git a/drivers/net/can/sja1000/sja1000_of_platform.c b/drivers/net/can/sja1000/sja1000_of_platform.c
deleted file mode 100644
index 2f6e245..0000000
--- a/drivers/net/can/sja1000/sja1000_of_platform.c
+++ /dev/null
@@ -1,220 +0,0 @@
-/*
- * Driver for SJA1000 CAN controllers on the OpenFirmware platform bus
- *
- * Copyright (C) 2008-2009 Wolfgang Grandegger <wg@grandegger.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the version 2 of the GNU General Public License
- * as published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-
-/* This is a generic driver for SJA1000 chips on the OpenFirmware platform
- * bus found on embedded PowerPC systems. You need a SJA1000 CAN node
- * definition in your flattened device tree source (DTS) file similar to:
- *
- * can@3,100 {
- * compatible = "nxp,sja1000";
- * reg = <3 0x100 0x80>;
- * interrupts = <2 0>;
- * interrupt-parent = <&mpic>;
- * nxp,external-clock-frequency = <16000000>;
- * };
- *
- * See "Documentation/devicetree/bindings/net/can/sja1000.txt" for further
- * information.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/can/dev.h>
-
-#include <linux/of_platform.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-
-#include "sja1000.h"
-
-#define DRV_NAME "sja1000_of_platform"
-
-MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>");
-MODULE_DESCRIPTION("Socket-CAN driver for SJA1000 on the OF platform bus");
-MODULE_LICENSE("GPL v2");
-
-#define SJA1000_OFP_CAN_CLOCK (16000000 / 2)
-
-#define SJA1000_OFP_OCR OCR_TX0_PULLDOWN
-#define SJA1000_OFP_CDR (CDR_CBP | CDR_CLK_OFF)
-
-static u8 sja1000_ofp_read_reg(const struct sja1000_priv *priv, int reg)
-{
- return ioread8(priv->reg_base + reg);
-}
-
-static void sja1000_ofp_write_reg(const struct sja1000_priv *priv,
- int reg, u8 val)
-{
- iowrite8(val, priv->reg_base + reg);
-}
-
-static int sja1000_ofp_remove(struct platform_device *ofdev)
-{
- struct net_device *dev = platform_get_drvdata(ofdev);
- struct sja1000_priv *priv = netdev_priv(dev);
- struct device_node *np = ofdev->dev.of_node;
- struct resource res;
-
- unregister_sja1000dev(dev);
- free_sja1000dev(dev);
- iounmap(priv->reg_base);
- irq_dispose_mapping(dev->irq);
-
- of_address_to_resource(np, 0, &res);
- release_mem_region(res.start, resource_size(&res));
-
- return 0;
-}
-
-static int sja1000_ofp_probe(struct platform_device *ofdev)
-{
- struct device_node *np = ofdev->dev.of_node;
- struct net_device *dev;
- struct sja1000_priv *priv;
- struct resource res;
- u32 prop;
- int err, irq, res_size;
- void __iomem *base;
-
- err = of_address_to_resource(np, 0, &res);
- if (err) {
- dev_err(&ofdev->dev, "invalid address\n");
- return err;
- }
-
- res_size = resource_size(&res);
-
- if (!request_mem_region(res.start, res_size, DRV_NAME)) {
- dev_err(&ofdev->dev, "couldn't request %pR\n", &res);
- return -EBUSY;
- }
-
- base = ioremap_nocache(res.start, res_size);
- if (!base) {
- dev_err(&ofdev->dev, "couldn't ioremap %pR\n", &res);
- err = -ENOMEM;
- goto exit_release_mem;
- }
-
- irq = irq_of_parse_and_map(np, 0);
- if (irq == 0) {
- dev_err(&ofdev->dev, "no irq found\n");
- err = -ENODEV;
- goto exit_unmap_mem;
- }
-
- dev = alloc_sja1000dev(0);
- if (!dev) {
- err = -ENOMEM;
- goto exit_dispose_irq;
- }
-
- priv = netdev_priv(dev);
-
- priv->read_reg = sja1000_ofp_read_reg;
- priv->write_reg = sja1000_ofp_write_reg;
-
- err = of_property_read_u32(np, "nxp,external-clock-frequency", &prop);
- if (!err)
- priv->can.clock.freq = prop / 2;
- else
- priv->can.clock.freq = SJA1000_OFP_CAN_CLOCK; /* default */
-
- err = of_property_read_u32(np, "nxp,tx-output-mode", &prop);
- if (!err)
- priv->ocr |= prop & OCR_MODE_MASK;
- else
- priv->ocr |= OCR_MODE_NORMAL; /* default */
-
- err = of_property_read_u32(np, "nxp,tx-output-config", &prop);
- if (!err)
- priv->ocr |= (prop << OCR_TX_SHIFT) & OCR_TX_MASK;
- else
- priv->ocr |= OCR_TX0_PULLDOWN; /* default */
-
- err = of_property_read_u32(np, "nxp,clock-out-frequency", &prop);
- if (!err && prop) {
- u32 divider = priv->can.clock.freq * 2 / prop;
-
- if (divider > 1)
- priv->cdr |= divider / 2 - 1;
- else
- priv->cdr |= CDR_CLKOUT_MASK;
- } else {
- priv->cdr |= CDR_CLK_OFF; /* default */
- }
-
- if (!of_property_read_bool(np, "nxp,no-comparator-bypass"))
- priv->cdr |= CDR_CBP; /* default */
-
- priv->irq_flags = IRQF_SHARED;
- priv->reg_base = base;
-
- dev->irq = irq;
-
- dev_info(&ofdev->dev,
- "reg_base=0x%p irq=%d clock=%d ocr=0x%02x cdr=0x%02x\n",
- priv->reg_base, dev->irq, priv->can.clock.freq,
- priv->ocr, priv->cdr);
-
- platform_set_drvdata(ofdev, dev);
- SET_NETDEV_DEV(dev, &ofdev->dev);
-
- err = register_sja1000dev(dev);
- if (err) {
- dev_err(&ofdev->dev, "registering %s failed (err=%d)\n",
- DRV_NAME, err);
- goto exit_free_sja1000;
- }
-
- return 0;
-
-exit_free_sja1000:
- free_sja1000dev(dev);
-exit_dispose_irq:
- irq_dispose_mapping(irq);
-exit_unmap_mem:
- iounmap(base);
-exit_release_mem:
- release_mem_region(res.start, res_size);
-
- return err;
-}
-
-static struct of_device_id sja1000_ofp_table[] = {
- {.compatible = "nxp,sja1000"},
- {},
-};
-MODULE_DEVICE_TABLE(of, sja1000_ofp_table);
-
-static struct platform_driver sja1000_ofp_driver = {
- .driver = {
- .owner = THIS_MODULE,
- .name = DRV_NAME,
- .of_match_table = sja1000_ofp_table,
- },
- .probe = sja1000_ofp_probe,
- .remove = sja1000_ofp_remove,
-};
-
-module_platform_driver(sja1000_ofp_driver);
diff --git a/drivers/net/can/sja1000/sja1000_platform.c b/drivers/net/can/sja1000/sja1000_platform.c
index 943df64..95a844a 100644
--- a/drivers/net/can/sja1000/sja1000_platform.c
+++ b/drivers/net/can/sja1000/sja1000_platform.c
@@ -26,12 +26,16 @@
#include <linux/can/dev.h>
#include <linux/can/platform/sja1000.h>
#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
#include "sja1000.h"
#define DRV_NAME "sja1000_platform"
+#define SP_CAN_CLOCK (16000000 / 2)
MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de>");
+MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>");
MODULE_DESCRIPTION("Socket-CAN driver for SJA1000 on the platform bus");
MODULE_ALIAS("platform:" DRV_NAME);
MODULE_LICENSE("GPL v2");
@@ -66,59 +70,16 @@
iowrite8(val, priv->reg_base + reg * 4);
}
-static int sp_probe(struct platform_device *pdev)
+static void sp_populate(struct sja1000_priv *priv,
+ struct sja1000_platform_data *pdata,
+ unsigned long resource_mem_flags)
{
- int err;
- void __iomem *addr;
- struct net_device *dev;
- struct sja1000_priv *priv;
- struct resource *res_mem, *res_irq;
- struct sja1000_platform_data *pdata;
-
- pdata = dev_get_platdata(&pdev->dev);
- if (!pdata) {
- dev_err(&pdev->dev, "No platform data provided!\n");
- err = -ENODEV;
- goto exit;
- }
-
- res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
- if (!res_mem || !res_irq) {
- err = -ENODEV;
- goto exit;
- }
-
- if (!request_mem_region(res_mem->start, resource_size(res_mem),
- DRV_NAME)) {
- err = -EBUSY;
- goto exit;
- }
-
- addr = ioremap_nocache(res_mem->start, resource_size(res_mem));
- if (!addr) {
- err = -ENOMEM;
- goto exit_release;
- }
-
- dev = alloc_sja1000dev(0);
- if (!dev) {
- err = -ENOMEM;
- goto exit_iounmap;
- }
- priv = netdev_priv(dev);
-
- dev->irq = res_irq->start;
- priv->irq_flags = res_irq->flags & IRQF_TRIGGER_MASK;
- if (res_irq->flags & IORESOURCE_IRQ_SHAREABLE)
- priv->irq_flags |= IRQF_SHARED;
- priv->reg_base = addr;
/* The CAN clock frequency is half the oscillator clock frequency */
priv->can.clock.freq = pdata->osc_freq / 2;
priv->ocr = pdata->ocr;
priv->cdr = pdata->cdr;
- switch (res_mem->flags & IORESOURCE_MEM_TYPE_MASK) {
+ switch (resource_mem_flags & IORESOURCE_MEM_TYPE_MASK) {
case IORESOURCE_MEM_32BIT:
priv->read_reg = sp_read_reg32;
priv->write_reg = sp_write_reg32;
@@ -133,6 +94,124 @@
priv->write_reg = sp_write_reg8;
break;
}
+}
+
+static void sp_populate_of(struct sja1000_priv *priv, struct device_node *of)
+{
+ int err;
+ u32 prop;
+
+ err = of_property_read_u32(of, "reg-io-width", &prop);
+ if (err)
+ prop = 1; /* 8 bit is default */
+
+ switch (prop) {
+ case 4:
+ priv->read_reg = sp_read_reg32;
+ priv->write_reg = sp_write_reg32;
+ break;
+ case 2:
+ priv->read_reg = sp_read_reg16;
+ priv->write_reg = sp_write_reg16;
+ break;
+ case 1: /* fallthrough */
+ default:
+ priv->read_reg = sp_read_reg8;
+ priv->write_reg = sp_write_reg8;
+ }
+
+ err = of_property_read_u32(of, "nxp,external-clock-frequency", &prop);
+ if (!err)
+ priv->can.clock.freq = prop / 2;
+ else
+ priv->can.clock.freq = SP_CAN_CLOCK; /* default */
+
+ err = of_property_read_u32(of, "nxp,tx-output-mode", &prop);
+ if (!err)
+ priv->ocr |= prop & OCR_MODE_MASK;
+ else
+ priv->ocr |= OCR_MODE_NORMAL; /* default */
+
+ err = of_property_read_u32(of, "nxp,tx-output-config", &prop);
+ if (!err)
+ priv->ocr |= (prop << OCR_TX_SHIFT) & OCR_TX_MASK;
+ else
+ priv->ocr |= OCR_TX0_PULLDOWN; /* default */
+
+ err = of_property_read_u32(of, "nxp,clock-out-frequency", &prop);
+ if (!err && prop) {
+ u32 divider = priv->can.clock.freq * 2 / prop;
+
+ if (divider > 1)
+ priv->cdr |= divider / 2 - 1;
+ else
+ priv->cdr |= CDR_CLKOUT_MASK;
+ } else {
+ priv->cdr |= CDR_CLK_OFF; /* default */
+ }
+
+ if (!of_property_read_bool(of, "nxp,no-comparator-bypass"))
+ priv->cdr |= CDR_CBP; /* default */
+}
+
+static int sp_probe(struct platform_device *pdev)
+{
+ int err, irq = 0;
+ void __iomem *addr;
+ struct net_device *dev;
+ struct sja1000_priv *priv;
+ struct resource *res_mem, *res_irq = NULL;
+ struct sja1000_platform_data *pdata;
+ struct device_node *of = pdev->dev.of_node;
+
+ pdata = dev_get_platdata(&pdev->dev);
+ if (!pdata && !of) {
+ dev_err(&pdev->dev, "No platform data provided!\n");
+ return -ENODEV;
+ }
+
+ res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res_mem)
+ return -ENODEV;
+
+ if (!devm_request_mem_region(&pdev->dev, res_mem->start,
+ resource_size(res_mem), DRV_NAME))
+ return -EBUSY;
+
+ addr = devm_ioremap_nocache(&pdev->dev, res_mem->start,
+ resource_size(res_mem));
+ if (!addr)
+ return -ENOMEM;
+
+ if (of)
+ irq = irq_of_parse_and_map(of, 0);
+ else
+ res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+
+ if (!irq && !res_irq)
+ return -ENODEV;
+
+ dev = alloc_sja1000dev(0);
+ if (!dev)
+ return -ENOMEM;
+ priv = netdev_priv(dev);
+
+ if (res_irq) {
+ irq = res_irq->start;
+ priv->irq_flags = res_irq->flags & IRQF_TRIGGER_MASK;
+ if (res_irq->flags & IORESOURCE_IRQ_SHAREABLE)
+ priv->irq_flags |= IRQF_SHARED;
+ } else {
+ priv->irq_flags = IRQF_SHARED;
+ }
+
+ dev->irq = irq;
+ priv->reg_base = addr;
+
+ if (of)
+ sp_populate_of(priv, of);
+ else
+ sp_populate(priv, pdata, res_mem->flags);
platform_set_drvdata(pdev, dev);
SET_NETDEV_DEV(dev, &pdev->dev);
@@ -150,39 +229,32 @@
exit_free:
free_sja1000dev(dev);
- exit_iounmap:
- iounmap(addr);
- exit_release:
- release_mem_region(res_mem->start, resource_size(res_mem));
- exit:
return err;
}
static int sp_remove(struct platform_device *pdev)
{
struct net_device *dev = platform_get_drvdata(pdev);
- struct sja1000_priv *priv = netdev_priv(dev);
- struct resource *res;
unregister_sja1000dev(dev);
-
- if (priv->reg_base)
- iounmap(priv->reg_base);
-
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- release_mem_region(res->start, resource_size(res));
-
free_sja1000dev(dev);
return 0;
}
+static struct of_device_id sp_of_table[] = {
+ {.compatible = "nxp,sja1000"},
+ {},
+};
+MODULE_DEVICE_TABLE(of, sp_of_table);
+
static struct platform_driver sp_driver = {
.probe = sp_probe,
.remove = sp_remove,
.driver = {
.name = DRV_NAME,
.owner = THIS_MODULE,
+ .of_match_table = sp_of_table,
},
};
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 3fcdae2..f5b16e0 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -411,10 +411,16 @@
slcan_devs[i] = NULL;
}
+static int slcan_change_mtu(struct net_device *dev, int new_mtu)
+{
+ return -EINVAL;
+}
+
static const struct net_device_ops slc_netdev_ops = {
.ndo_open = slc_open,
.ndo_stop = slc_close,
.ndo_start_xmit = slc_xmit,
+ .ndo_change_mtu = slcan_change_mtu,
};
static void slc_setup(struct net_device *dev)
diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c
index 9ea0dcd..7d8c8f3 100644
--- a/drivers/net/can/softing/softing_main.c
+++ b/drivers/net/can/softing/softing_main.c
@@ -628,6 +628,7 @@
.ndo_open = softing_netdev_open,
.ndo_stop = softing_netdev_stop,
.ndo_start_xmit = softing_netdev_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
static const struct can_bittiming_const softing_btr_const = {
@@ -832,6 +833,7 @@
ret = -ENOMEM;
goto netdev_failed;
}
+ netdev->dev_id = j;
priv = netdev_priv(card->net[j]);
priv->index = j;
ret = softing_netdev_register(netdev);
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 2c62fe6..258b9c4 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -871,6 +871,7 @@
.ndo_open = ti_hecc_open,
.ndo_stop = ti_hecc_close,
.ndo_start_xmit = ti_hecc_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
static int ti_hecc_probe(struct platform_device *pdev)
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 52c42fd..00f2534 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -883,6 +883,7 @@
.ndo_open = ems_usb_open,
.ndo_stop = ems_usb_close,
.ndo_start_xmit = ems_usb_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
static const struct can_bittiming_const ems_usb_bittiming_const = {
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index 7fbe859..b7c9e8b 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -888,6 +888,7 @@
.ndo_open = esd_usb2_open,
.ndo_stop = esd_usb2_close,
.ndo_start_xmit = esd_usb2_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
static const struct can_bittiming_const esd_usb2_bittiming_const = {
@@ -1024,6 +1025,7 @@
netdev->netdev_ops = &esd_usb2_netdev_ops;
SET_NETDEV_DEV(netdev, &intf->dev);
+ netdev->dev_id = index;
err = register_candev(netdev);
if (err) {
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 6c859bb..4ca46ed 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -473,6 +473,8 @@
return err;
dev->nchannels = msg.u.cardinfo.nchannels;
+ if (dev->nchannels > MAX_NET_DEVICES)
+ return -EINVAL;
return 0;
}
@@ -1386,6 +1388,7 @@
.ndo_open = kvaser_usb_open,
.ndo_stop = kvaser_usb_close,
.ndo_start_xmit = kvaser_usb_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
static const struct can_bittiming_const kvaser_usb_bittiming_const = {
@@ -1527,6 +1530,7 @@
netdev->netdev_ops = &kvaser_usb_netdev_ops;
SET_NETDEV_DEV(netdev, &intf->dev);
+ netdev->dev_id = channel;
dev->nets[channel] = priv;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 0b7a4c3..644e6ab 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -702,6 +702,7 @@
.ndo_open = peak_usb_ndo_open,
.ndo_stop = peak_usb_ndo_stop,
.ndo_start_xmit = peak_usb_ndo_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
/*
@@ -769,6 +770,7 @@
usb_set_intfdata(intf, dev);
SET_NETDEV_DEV(netdev, &intf->dev);
+ netdev->dev_id = ctrl_idx;
err = register_candev(netdev);
if (err) {
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index a0fa1fd..cde2634 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -887,6 +887,7 @@
.ndo_open = usb_8dev_open,
.ndo_stop = usb_8dev_close,
.ndo_start_xmit = usb_8dev_start_xmit,
+ .ndo_change_mtu = can_change_mtu,
};
static const struct can_bittiming_const usb_8dev_bittiming_const = {
diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c
index 0a2a5ee..4e94057 100644
--- a/drivers/net/can/vcan.c
+++ b/drivers/net/can/vcan.c
@@ -46,6 +46,7 @@
#include <linux/if_ether.h>
#include <linux/can.h>
#include <linux/can/dev.h>
+#include <linux/can/skb.h>
#include <linux/slab.h>
#include <net/rtnetlink.h>
@@ -109,25 +110,23 @@
stats->rx_packets++;
stats->rx_bytes += cfd->len;
}
- kfree_skb(skb);
+ consume_skb(skb);
return NETDEV_TX_OK;
}
/* perform standard echo handling for CAN network interfaces */
if (loop) {
- struct sock *srcsk = skb->sk;
- skb = skb_share_check(skb, GFP_ATOMIC);
+ skb = can_create_echo_skb(skb);
if (!skb)
return NETDEV_TX_OK;
/* receive with packet counting */
- skb->sk = srcsk;
vcan_rx(skb, dev);
} else {
/* no looped packets => no counting */
- kfree_skb(skb);
+ consume_skb(skb);
}
return NETDEV_TX_OK;
}
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index bd8f84b..0932ffb 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -63,10 +63,10 @@
dstats = per_cpu_ptr(dev->dstats, i);
do {
- start = u64_stats_fetch_begin_bh(&dstats->syncp);
+ start = u64_stats_fetch_begin_irq(&dstats->syncp);
tbytes = dstats->tx_bytes;
tpackets = dstats->tx_packets;
- } while (u64_stats_fetch_retry_bh(&dstats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&dstats->syncp, start));
stats->tx_bytes += tbytes;
stats->tx_packets += tpackets;
}
@@ -88,16 +88,10 @@
static int dummy_dev_init(struct net_device *dev)
{
- int i;
- dev->dstats = alloc_percpu(struct pcpu_dstats);
+ dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
if (!dev->dstats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct pcpu_dstats *dstats;
- dstats = per_cpu_ptr(dev->dstats, i);
- u64_stats_init(&dstats->syncp);
- }
return 0;
}
diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c
index c53384d..35df0b9 100644
--- a/drivers/net/ethernet/3com/3c509.c
+++ b/drivers/net/ethernet/3com/3c509.c
@@ -749,7 +749,7 @@
spin_unlock_irqrestore(&lp->lock, flags);
- dev_kfree_skb (skb);
+ dev_consume_skb_any (skb);
/* Clear the Tx status stack. */
{
diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c
index 5992860..063557e 100644
--- a/drivers/net/ethernet/3com/3c589_cs.c
+++ b/drivers/net/ethernet/3com/3c589_cs.c
@@ -1,23 +1,24 @@
-/*======================================================================
-
- A PCMCIA ethernet driver for the 3com 3c589 card.
-
- Copyright (C) 1999 David A. Hinds -- dahinds@users.sourceforge.net
-
- 3c589_cs.c 1.162 2001/10/13 00:08:50
-
- The network driver code is based on Donald Becker's 3c589 code:
-
- Written 1994 by Donald Becker.
- Copyright 1993 United States Government as represented by the
- Director, National Security Agency. This software may be used and
- distributed according to the terms of the GNU General Public License,
- incorporated herein by reference.
- Donald Becker may be reached at becker@scyld.com
-
- Updated for 2.5.x by Alan Cox <alan@lxorguk.ukuu.org.uk>
-
-======================================================================*/
+/* ======================================================================
+ *
+ * A PCMCIA ethernet driver for the 3com 3c589 card.
+ *
+ * Copyright (C) 1999 David A. Hinds -- dahinds@users.sourceforge.net
+ *
+ * 3c589_cs.c 1.162 2001/10/13 00:08:50
+ *
+ * The network driver code is based on Donald Becker's 3c589 code:
+ *
+ * Written 1994 by Donald Becker.
+ * Copyright 1993 United States Government as represented by the
+ * Director, National Security Agency. This software may be used and
+ * distributed according to the terms of the GNU General Public License,
+ * incorporated herein by reference.
+ * Donald Becker may be reached at becker@scyld.com
+ *
+ * Updated for 2.5.x by Alan Cox <alan@lxorguk.ukuu.org.uk>
+ *
+ * ======================================================================
+ */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -41,18 +42,20 @@
#include <linux/ioport.h>
#include <linux/bitops.h>
#include <linux/jiffies.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
#include <pcmcia/cistpl.h>
#include <pcmcia/cisreg.h>
#include <pcmcia/ciscode.h>
#include <pcmcia/ds.h>
-#include <asm/uaccess.h>
-#include <asm/io.h>
/* To minimize the size of the driver source I only define operating
- constants if they are used several times. You'll need the manual
- if you want to understand driver details. */
+ * constants if they are used several times. You'll need the manual
+ * if you want to understand driver details.
+ */
+
/* Offsets from base I/O address. */
#define EL3_DATA 0x00
#define EL3_TIMER 0x0a
@@ -65,7 +68,9 @@
#define EL3WINDOW(win_num) outw(SelectWindow + (win_num), ioaddr + EL3_CMD)
/* The top five bits written to EL3_CMD are a command, the lower
- 11 bits are the parameter, if applicable. */
+ * 11 bits are the parameter, if applicable.
+ */
+
enum c509cmd {
TotalReset = 0<<11,
SelectWindow = 1<<11,
@@ -190,138 +195,142 @@
static int tc589_probe(struct pcmcia_device *link)
{
- struct el3_private *lp;
- struct net_device *dev;
+ struct el3_private *lp;
+ struct net_device *dev;
- dev_dbg(&link->dev, "3c589_attach()\n");
+ dev_dbg(&link->dev, "3c589_attach()\n");
- /* Create new ethernet device */
- dev = alloc_etherdev(sizeof(struct el3_private));
- if (!dev)
- return -ENOMEM;
- lp = netdev_priv(dev);
- link->priv = dev;
- lp->p_dev = link;
+ /* Create new ethernet device */
+ dev = alloc_etherdev(sizeof(struct el3_private));
+ if (!dev)
+ return -ENOMEM;
+ lp = netdev_priv(dev);
+ link->priv = dev;
+ lp->p_dev = link;
- spin_lock_init(&lp->lock);
- link->resource[0]->end = 16;
- link->resource[0]->flags |= IO_DATA_PATH_WIDTH_16;
+ spin_lock_init(&lp->lock);
+ link->resource[0]->end = 16;
+ link->resource[0]->flags |= IO_DATA_PATH_WIDTH_16;
- link->config_flags |= CONF_ENABLE_IRQ;
- link->config_index = 1;
+ link->config_flags |= CONF_ENABLE_IRQ;
+ link->config_index = 1;
- dev->netdev_ops = &el3_netdev_ops;
- dev->watchdog_timeo = TX_TIMEOUT;
+ dev->netdev_ops = &el3_netdev_ops;
+ dev->watchdog_timeo = TX_TIMEOUT;
- SET_ETHTOOL_OPS(dev, &netdev_ethtool_ops);
+ SET_ETHTOOL_OPS(dev, &netdev_ethtool_ops);
- return tc589_config(link);
+ return tc589_config(link);
}
static void tc589_detach(struct pcmcia_device *link)
{
- struct net_device *dev = link->priv;
+ struct net_device *dev = link->priv;
- dev_dbg(&link->dev, "3c589_detach\n");
+ dev_dbg(&link->dev, "3c589_detach\n");
- unregister_netdev(dev);
+ unregister_netdev(dev);
- tc589_release(link);
+ tc589_release(link);
- free_netdev(dev);
+ free_netdev(dev);
} /* tc589_detach */
static int tc589_config(struct pcmcia_device *link)
{
- struct net_device *dev = link->priv;
- __be16 *phys_addr;
- int ret, i, j, multi = 0, fifo;
- unsigned int ioaddr;
- static const char * const ram_split[] = {"5:3", "3:1", "1:1", "3:5"};
- u8 *buf;
- size_t len;
+ struct net_device *dev = link->priv;
+ __be16 *phys_addr;
+ int ret, i, j, multi = 0, fifo;
+ unsigned int ioaddr;
+ static const char * const ram_split[] = {"5:3", "3:1", "1:1", "3:5"};
+ u8 *buf;
+ size_t len;
- dev_dbg(&link->dev, "3c589_config\n");
+ dev_dbg(&link->dev, "3c589_config\n");
- phys_addr = (__be16 *)dev->dev_addr;
- /* Is this a 3c562? */
- if (link->manf_id != MANFID_3COM)
- dev_info(&link->dev, "hmmm, is this really a 3Com card??\n");
- multi = (link->card_id == PRODID_3COM_3C562);
+ phys_addr = (__be16 *)dev->dev_addr;
+ /* Is this a 3c562? */
+ if (link->manf_id != MANFID_3COM)
+ dev_info(&link->dev, "hmmm, is this really a 3Com card??\n");
+ multi = (link->card_id == PRODID_3COM_3C562);
- link->io_lines = 16;
+ link->io_lines = 16;
- /* For the 3c562, the base address must be xx00-xx7f */
- for (i = j = 0; j < 0x400; j += 0x10) {
- if (multi && (j & 0x80)) continue;
- link->resource[0]->start = j ^ 0x300;
- i = pcmcia_request_io(link);
- if (i == 0)
- break;
- }
- if (i != 0)
- goto failed;
-
- ret = pcmcia_request_irq(link, el3_interrupt);
- if (ret)
- goto failed;
-
- ret = pcmcia_enable_device(link);
- if (ret)
- goto failed;
-
- dev->irq = link->irq;
- dev->base_addr = link->resource[0]->start;
- ioaddr = dev->base_addr;
- EL3WINDOW(0);
-
- /* The 3c589 has an extra EEPROM for configuration info, including
- the hardware address. The 3c562 puts the address in the CIS. */
- len = pcmcia_get_tuple(link, 0x88, &buf);
- if (buf && len >= 6) {
- for (i = 0; i < 3; i++)
- phys_addr[i] = htons(le16_to_cpu(buf[i*2]));
- kfree(buf);
- } else {
- kfree(buf); /* 0 < len < 6 */
- for (i = 0; i < 3; i++)
- phys_addr[i] = htons(read_eeprom(ioaddr, i));
- if (phys_addr[0] == htons(0x6060)) {
- dev_err(&link->dev, "IO port conflict at 0x%03lx-0x%03lx\n",
- dev->base_addr, dev->base_addr+15);
- goto failed;
+ /* For the 3c562, the base address must be xx00-xx7f */
+ for (i = j = 0; j < 0x400; j += 0x10) {
+ if (multi && (j & 0x80))
+ continue;
+ link->resource[0]->start = j ^ 0x300;
+ i = pcmcia_request_io(link);
+ if (i == 0)
+ break;
}
- }
+ if (i != 0)
+ goto failed;
- /* The address and resource configuration register aren't loaded from
- the EEPROM and *must* be set to 0 and IRQ3 for the PCMCIA version. */
- outw(0x3f00, ioaddr + 8);
- fifo = inl(ioaddr);
+ ret = pcmcia_request_irq(link, el3_interrupt);
+ if (ret)
+ goto failed;
- /* The if_port symbol can be set when the module is loaded */
- if ((if_port >= 0) && (if_port <= 3))
- dev->if_port = if_port;
- else
- dev_err(&link->dev, "invalid if_port requested\n");
+ ret = pcmcia_enable_device(link);
+ if (ret)
+ goto failed;
- SET_NETDEV_DEV(dev, &link->dev);
+ dev->irq = link->irq;
+ dev->base_addr = link->resource[0]->start;
+ ioaddr = dev->base_addr;
+ EL3WINDOW(0);
- if (register_netdev(dev) != 0) {
- dev_err(&link->dev, "register_netdev() failed\n");
- goto failed;
- }
+ /* The 3c589 has an extra EEPROM for configuration info, including
+ * the hardware address. The 3c562 puts the address in the CIS.
+ */
+ len = pcmcia_get_tuple(link, 0x88, &buf);
+ if (buf && len >= 6) {
+ for (i = 0; i < 3; i++)
+ phys_addr[i] = htons(le16_to_cpu(buf[i*2]));
+ kfree(buf);
+ } else {
+ kfree(buf); /* 0 < len < 6 */
+ for (i = 0; i < 3; i++)
+ phys_addr[i] = htons(read_eeprom(ioaddr, i));
+ if (phys_addr[0] == htons(0x6060)) {
+ dev_err(&link->dev, "IO port conflict at 0x%03lx-0x%03lx\n",
+ dev->base_addr, dev->base_addr+15);
+ goto failed;
+ }
+ }
- netdev_info(dev, "3Com 3c%s, io %#3lx, irq %d, hw_addr %pM\n",
- (multi ? "562" : "589"), dev->base_addr, dev->irq,
- dev->dev_addr);
- netdev_info(dev, " %dK FIFO split %s Rx:Tx, %s xcvr\n",
- (fifo & 7) ? 32 : 8, ram_split[(fifo >> 16) & 3],
- if_names[dev->if_port]);
- return 0;
+ /* The address and resource configuration register aren't loaded from
+ * the EEPROM and *must* be set to 0 and IRQ3 for the PCMCIA version.
+ */
+
+ outw(0x3f00, ioaddr + 8);
+ fifo = inl(ioaddr);
+
+ /* The if_port symbol can be set when the module is loaded */
+ if ((if_port >= 0) && (if_port <= 3))
+ dev->if_port = if_port;
+ else
+ dev_err(&link->dev, "invalid if_port requested\n");
+
+ SET_NETDEV_DEV(dev, &link->dev);
+
+ if (register_netdev(dev) != 0) {
+ dev_err(&link->dev, "register_netdev() failed\n");
+ goto failed;
+ }
+
+ netdev_info(dev, "3Com 3c%s, io %#3lx, irq %d, hw_addr %pM\n",
+ (multi ? "562" : "589"), dev->base_addr, dev->irq,
+ dev->dev_addr);
+ netdev_info(dev, " %dK FIFO split %s Rx:Tx, %s xcvr\n",
+ (fifo & 7) ? 32 : 8, ram_split[(fifo >> 16) & 3],
+ if_names[dev->if_port]);
+ return 0;
failed:
- tc589_release(link);
- return -ENODEV;
+ tc589_release(link);
+ return -ENODEV;
} /* tc589_config */
static void tc589_release(struct pcmcia_device *link)
@@ -353,113 +362,120 @@
/*====================================================================*/
-/*
- Use this for commands that may take time to finish
-*/
+/* Use this for commands that may take time to finish */
+
static void tc589_wait_for_completion(struct net_device *dev, int cmd)
{
- int i = 100;
- outw(cmd, dev->base_addr + EL3_CMD);
- while (--i > 0)
- if (!(inw(dev->base_addr + EL3_STATUS) & 0x1000)) break;
- if (i == 0)
- netdev_warn(dev, "command 0x%04x did not complete!\n", cmd);
+ int i = 100;
+ outw(cmd, dev->base_addr + EL3_CMD);
+ while (--i > 0)
+ if (!(inw(dev->base_addr + EL3_STATUS) & 0x1000))
+ break;
+ if (i == 0)
+ netdev_warn(dev, "command 0x%04x did not complete!\n", cmd);
}
-/*
- Read a word from the EEPROM using the regular EEPROM access register.
- Assume that we are in register window zero.
-*/
+/* Read a word from the EEPROM using the regular EEPROM access register.
+ * Assume that we are in register window zero.
+ */
+
static u16 read_eeprom(unsigned int ioaddr, int index)
{
- int i;
- outw(EEPROM_READ + index, ioaddr + 10);
- /* Reading the eeprom takes 162 us */
- for (i = 1620; i >= 0; i--)
- if ((inw(ioaddr + 10) & EEPROM_BUSY) == 0)
- break;
- return inw(ioaddr + 12);
+ int i;
+ outw(EEPROM_READ + index, ioaddr + 10);
+ /* Reading the eeprom takes 162 us */
+ for (i = 1620; i >= 0; i--)
+ if ((inw(ioaddr + 10) & EEPROM_BUSY) == 0)
+ break;
+ return inw(ioaddr + 12);
}
-/*
- Set transceiver type, perhaps to something other than what the user
- specified in dev->if_port.
-*/
+/* Set transceiver type, perhaps to something other than what the user
+ * specified in dev->if_port.
+ */
+
static void tc589_set_xcvr(struct net_device *dev, int if_port)
{
- struct el3_private *lp = netdev_priv(dev);
- unsigned int ioaddr = dev->base_addr;
+ struct el3_private *lp = netdev_priv(dev);
+ unsigned int ioaddr = dev->base_addr;
- EL3WINDOW(0);
- switch (if_port) {
- case 0: case 1: outw(0, ioaddr + 6); break;
- case 2: outw(3<<14, ioaddr + 6); break;
- case 3: outw(1<<14, ioaddr + 6); break;
- }
- /* On PCMCIA, this just turns on the LED */
- outw((if_port == 2) ? StartCoax : StopCoax, ioaddr + EL3_CMD);
- /* 10baseT interface, enable link beat and jabber check. */
- EL3WINDOW(4);
- outw(MEDIA_LED | ((if_port < 2) ? MEDIA_TP : 0), ioaddr + WN4_MEDIA);
- EL3WINDOW(1);
- if (if_port == 2)
- lp->media_status = ((dev->if_port == 0) ? 0x8000 : 0x4000);
- else
- lp->media_status = ((dev->if_port == 0) ? 0x4010 : 0x8800);
+ EL3WINDOW(0);
+ switch (if_port) {
+ case 0:
+ case 1:
+ outw(0, ioaddr + 6);
+ break;
+ case 2:
+ outw(3<<14, ioaddr + 6);
+ break;
+ case 3:
+ outw(1<<14, ioaddr + 6);
+ break;
+ }
+ /* On PCMCIA, this just turns on the LED */
+ outw((if_port == 2) ? StartCoax : StopCoax, ioaddr + EL3_CMD);
+ /* 10baseT interface, enable link beat and jabber check. */
+ EL3WINDOW(4);
+ outw(MEDIA_LED | ((if_port < 2) ? MEDIA_TP : 0), ioaddr + WN4_MEDIA);
+ EL3WINDOW(1);
+ if (if_port == 2)
+ lp->media_status = ((dev->if_port == 0) ? 0x8000 : 0x4000);
+ else
+ lp->media_status = ((dev->if_port == 0) ? 0x4010 : 0x8800);
}
static void dump_status(struct net_device *dev)
{
- unsigned int ioaddr = dev->base_addr;
- EL3WINDOW(1);
- netdev_info(dev, " irq status %04x, rx status %04x, tx status %02x tx free %04x\n",
- inw(ioaddr+EL3_STATUS), inw(ioaddr+RX_STATUS),
- inb(ioaddr+TX_STATUS), inw(ioaddr+TX_FREE));
- EL3WINDOW(4);
- netdev_info(dev, " diagnostics: fifo %04x net %04x ethernet %04x media %04x\n",
- inw(ioaddr+0x04), inw(ioaddr+0x06), inw(ioaddr+0x08),
- inw(ioaddr+0x0a));
- EL3WINDOW(1);
+ unsigned int ioaddr = dev->base_addr;
+ EL3WINDOW(1);
+ netdev_info(dev, " irq status %04x, rx status %04x, tx status %02x tx free %04x\n",
+ inw(ioaddr+EL3_STATUS), inw(ioaddr+RX_STATUS),
+ inb(ioaddr+TX_STATUS), inw(ioaddr+TX_FREE));
+ EL3WINDOW(4);
+ netdev_info(dev, " diagnostics: fifo %04x net %04x ethernet %04x media %04x\n",
+ inw(ioaddr+0x04), inw(ioaddr+0x06), inw(ioaddr+0x08),
+ inw(ioaddr+0x0a));
+ EL3WINDOW(1);
}
/* Reset and restore all of the 3c589 registers. */
static void tc589_reset(struct net_device *dev)
{
- unsigned int ioaddr = dev->base_addr;
- int i;
+ unsigned int ioaddr = dev->base_addr;
+ int i;
- EL3WINDOW(0);
- outw(0x0001, ioaddr + 4); /* Activate board. */
- outw(0x3f00, ioaddr + 8); /* Set the IRQ line. */
+ EL3WINDOW(0);
+ outw(0x0001, ioaddr + 4); /* Activate board. */
+ outw(0x3f00, ioaddr + 8); /* Set the IRQ line. */
- /* Set the station address in window 2. */
- EL3WINDOW(2);
- for (i = 0; i < 6; i++)
- outb(dev->dev_addr[i], ioaddr + i);
+ /* Set the station address in window 2. */
+ EL3WINDOW(2);
+ for (i = 0; i < 6; i++)
+ outb(dev->dev_addr[i], ioaddr + i);
- tc589_set_xcvr(dev, dev->if_port);
+ tc589_set_xcvr(dev, dev->if_port);
- /* Switch to the stats window, and clear all stats by reading. */
- outw(StatsDisable, ioaddr + EL3_CMD);
- EL3WINDOW(6);
- for (i = 0; i < 9; i++)
- inb(ioaddr+i);
- inw(ioaddr + 10);
- inw(ioaddr + 12);
+ /* Switch to the stats window, and clear all stats by reading. */
+ outw(StatsDisable, ioaddr + EL3_CMD);
+ EL3WINDOW(6);
+ for (i = 0; i < 9; i++)
+ inb(ioaddr+i);
+ inw(ioaddr + 10);
+ inw(ioaddr + 12);
- /* Switch to register set 1 for normal use. */
- EL3WINDOW(1);
+ /* Switch to register set 1 for normal use. */
+ EL3WINDOW(1);
- set_rx_mode(dev);
- outw(StatsEnable, ioaddr + EL3_CMD); /* Turn on statistics. */
- outw(RxEnable, ioaddr + EL3_CMD); /* Enable the receiver. */
- outw(TxEnable, ioaddr + EL3_CMD); /* Enable transmitter. */
- /* Allow status bits to be seen. */
- outw(SetStatusEnb | 0xff, ioaddr + EL3_CMD);
- /* Ack all pending events, and set active indicator mask. */
- outw(AckIntr | IntLatch | TxAvailable | RxEarly | IntReq,
+ set_rx_mode(dev);
+ outw(StatsEnable, ioaddr + EL3_CMD); /* Turn on statistics. */
+ outw(RxEnable, ioaddr + EL3_CMD); /* Enable the receiver. */
+ outw(TxEnable, ioaddr + EL3_CMD); /* Enable transmitter. */
+ /* Allow status bits to be seen. */
+ outw(SetStatusEnb | 0xff, ioaddr + EL3_CMD);
+ /* Ack all pending events, and set active indicator mask. */
+ outw(AckIntr | IntLatch | TxAvailable | RxEarly | IntReq,
ioaddr + EL3_CMD);
- outw(SetIntrEnb | IntLatch | TxAvailable | RxComplete | StatsFull
+ outw(SetIntrEnb | IntLatch | TxAvailable | RxComplete | StatsFull
| AdapterFailure, ioaddr + EL3_CMD);
}
@@ -478,381 +494,406 @@
static int el3_config(struct net_device *dev, struct ifmap *map)
{
- if ((map->port != (u_char)(-1)) && (map->port != dev->if_port)) {
- if (map->port <= 3) {
- dev->if_port = map->port;
- netdev_info(dev, "switched to %s port\n", if_names[dev->if_port]);
- tc589_set_xcvr(dev, dev->if_port);
- } else
- return -EINVAL;
- }
- return 0;
+ if ((map->port != (u_char)(-1)) && (map->port != dev->if_port)) {
+ if (map->port <= 3) {
+ dev->if_port = map->port;
+ netdev_info(dev, "switched to %s port\n", if_names[dev->if_port]);
+ tc589_set_xcvr(dev, dev->if_port);
+ } else {
+ return -EINVAL;
+ }
+ }
+ return 0;
}
static int el3_open(struct net_device *dev)
{
- struct el3_private *lp = netdev_priv(dev);
- struct pcmcia_device *link = lp->p_dev;
+ struct el3_private *lp = netdev_priv(dev);
+ struct pcmcia_device *link = lp->p_dev;
- if (!pcmcia_dev_present(link))
- return -ENODEV;
+ if (!pcmcia_dev_present(link))
+ return -ENODEV;
- link->open++;
- netif_start_queue(dev);
+ link->open++;
+ netif_start_queue(dev);
- tc589_reset(dev);
- init_timer(&lp->media);
- lp->media.function = media_check;
- lp->media.data = (unsigned long) dev;
- lp->media.expires = jiffies + HZ;
- add_timer(&lp->media);
+ tc589_reset(dev);
+ init_timer(&lp->media);
+ lp->media.function = media_check;
+ lp->media.data = (unsigned long) dev;
+ lp->media.expires = jiffies + HZ;
+ add_timer(&lp->media);
- dev_dbg(&link->dev, "%s: opened, status %4.4x.\n",
+ dev_dbg(&link->dev, "%s: opened, status %4.4x.\n",
dev->name, inw(dev->base_addr + EL3_STATUS));
- return 0;
+ return 0;
}
static void el3_tx_timeout(struct net_device *dev)
{
- unsigned int ioaddr = dev->base_addr;
+ unsigned int ioaddr = dev->base_addr;
- netdev_warn(dev, "Transmit timed out!\n");
- dump_status(dev);
- dev->stats.tx_errors++;
- dev->trans_start = jiffies; /* prevent tx timeout */
- /* Issue TX_RESET and TX_START commands. */
- tc589_wait_for_completion(dev, TxReset);
- outw(TxEnable, ioaddr + EL3_CMD);
- netif_wake_queue(dev);
+ netdev_warn(dev, "Transmit timed out!\n");
+ dump_status(dev);
+ dev->stats.tx_errors++;
+ dev->trans_start = jiffies; /* prevent tx timeout */
+ /* Issue TX_RESET and TX_START commands. */
+ tc589_wait_for_completion(dev, TxReset);
+ outw(TxEnable, ioaddr + EL3_CMD);
+ netif_wake_queue(dev);
}
static void pop_tx_status(struct net_device *dev)
{
- unsigned int ioaddr = dev->base_addr;
- int i;
+ unsigned int ioaddr = dev->base_addr;
+ int i;
- /* Clear the Tx status stack. */
- for (i = 32; i > 0; i--) {
- u_char tx_status = inb(ioaddr + TX_STATUS);
- if (!(tx_status & 0x84)) break;
- /* reset transmitter on jabber error or underrun */
- if (tx_status & 0x30)
- tc589_wait_for_completion(dev, TxReset);
- if (tx_status & 0x38) {
- netdev_dbg(dev, "transmit error: status 0x%02x\n", tx_status);
- outw(TxEnable, ioaddr + EL3_CMD);
- dev->stats.tx_aborted_errors++;
+ /* Clear the Tx status stack. */
+ for (i = 32; i > 0; i--) {
+ u_char tx_status = inb(ioaddr + TX_STATUS);
+ if (!(tx_status & 0x84))
+ break;
+ /* reset transmitter on jabber error or underrun */
+ if (tx_status & 0x30)
+ tc589_wait_for_completion(dev, TxReset);
+ if (tx_status & 0x38) {
+ netdev_dbg(dev, "transmit error: status 0x%02x\n", tx_status);
+ outw(TxEnable, ioaddr + EL3_CMD);
+ dev->stats.tx_aborted_errors++;
+ }
+ outb(0x00, ioaddr + TX_STATUS); /* Pop the status stack. */
}
- outb(0x00, ioaddr + TX_STATUS); /* Pop the status stack. */
- }
}
static netdev_tx_t el3_start_xmit(struct sk_buff *skb,
struct net_device *dev)
{
- unsigned int ioaddr = dev->base_addr;
- struct el3_private *priv = netdev_priv(dev);
- unsigned long flags;
+ unsigned int ioaddr = dev->base_addr;
+ struct el3_private *priv = netdev_priv(dev);
+ unsigned long flags;
- netdev_dbg(dev, "el3_start_xmit(length = %ld) called, status %4.4x.\n",
+ netdev_dbg(dev, "el3_start_xmit(length = %ld) called, status %4.4x.\n",
(long)skb->len, inw(ioaddr + EL3_STATUS));
- spin_lock_irqsave(&priv->lock, flags);
+ spin_lock_irqsave(&priv->lock, flags);
- dev->stats.tx_bytes += skb->len;
+ dev->stats.tx_bytes += skb->len;
- /* Put out the doubleword header... */
- outw(skb->len, ioaddr + TX_FIFO);
- outw(0x00, ioaddr + TX_FIFO);
- /* ... and the packet rounded to a doubleword. */
- outsl(ioaddr + TX_FIFO, skb->data, (skb->len + 3) >> 2);
+ /* Put out the doubleword header... */
+ outw(skb->len, ioaddr + TX_FIFO);
+ outw(0x00, ioaddr + TX_FIFO);
+ /* ... and the packet rounded to a doubleword. */
+ outsl(ioaddr + TX_FIFO, skb->data, (skb->len + 3) >> 2);
- if (inw(ioaddr + TX_FREE) <= 1536) {
- netif_stop_queue(dev);
- /* Interrupt us when the FIFO has room for max-sized packet. */
- outw(SetTxThreshold + 1536, ioaddr + EL3_CMD);
- }
+ if (inw(ioaddr + TX_FREE) <= 1536) {
+ netif_stop_queue(dev);
+ /* Interrupt us when the FIFO has room for max-sized packet. */
+ outw(SetTxThreshold + 1536, ioaddr + EL3_CMD);
+ }
- pop_tx_status(dev);
- spin_unlock_irqrestore(&priv->lock, flags);
- dev_kfree_skb(skb);
+ pop_tx_status(dev);
+ spin_unlock_irqrestore(&priv->lock, flags);
+ dev_kfree_skb(skb);
- return NETDEV_TX_OK;
+ return NETDEV_TX_OK;
}
/* The EL3 interrupt handler. */
static irqreturn_t el3_interrupt(int irq, void *dev_id)
{
- struct net_device *dev = (struct net_device *) dev_id;
- struct el3_private *lp = netdev_priv(dev);
- unsigned int ioaddr;
- __u16 status;
- int i = 0, handled = 1;
+ struct net_device *dev = (struct net_device *) dev_id;
+ struct el3_private *lp = netdev_priv(dev);
+ unsigned int ioaddr;
+ __u16 status;
+ int i = 0, handled = 1;
- if (!netif_device_present(dev))
- return IRQ_NONE;
+ if (!netif_device_present(dev))
+ return IRQ_NONE;
- ioaddr = dev->base_addr;
+ ioaddr = dev->base_addr;
- netdev_dbg(dev, "interrupt, status %4.4x.\n", inw(ioaddr + EL3_STATUS));
+ netdev_dbg(dev, "interrupt, status %4.4x.\n", inw(ioaddr + EL3_STATUS));
- spin_lock(&lp->lock);
- while ((status = inw(ioaddr + EL3_STATUS)) &
+ spin_lock(&lp->lock);
+ while ((status = inw(ioaddr + EL3_STATUS)) &
(IntLatch | RxComplete | StatsFull)) {
- if ((status & 0xe000) != 0x2000) {
- netdev_dbg(dev, "interrupt from dead card\n");
- handled = 0;
- break;
- }
- if (status & RxComplete)
- el3_rx(dev);
- if (status & TxAvailable) {
- netdev_dbg(dev, " TX room bit was handled.\n");
- /* There's room in the FIFO for a full-sized packet. */
- outw(AckIntr | TxAvailable, ioaddr + EL3_CMD);
- netif_wake_queue(dev);
- }
- if (status & TxComplete)
- pop_tx_status(dev);
- if (status & (AdapterFailure | RxEarly | StatsFull)) {
- /* Handle all uncommon interrupts. */
- if (status & StatsFull) /* Empty statistics. */
- update_stats(dev);
- if (status & RxEarly) { /* Rx early is unused. */
- el3_rx(dev);
- outw(AckIntr | RxEarly, ioaddr + EL3_CMD);
- }
- if (status & AdapterFailure) {
- u16 fifo_diag;
- EL3WINDOW(4);
- fifo_diag = inw(ioaddr + 4);
- EL3WINDOW(1);
- netdev_warn(dev, "adapter failure, FIFO diagnostic register %04x.\n",
+ if ((status & 0xe000) != 0x2000) {
+ netdev_dbg(dev, "interrupt from dead card\n");
+ handled = 0;
+ break;
+ }
+ if (status & RxComplete)
+ el3_rx(dev);
+ if (status & TxAvailable) {
+ netdev_dbg(dev, " TX room bit was handled.\n");
+ /* There's room in the FIFO for a full-sized packet. */
+ outw(AckIntr | TxAvailable, ioaddr + EL3_CMD);
+ netif_wake_queue(dev);
+ }
+ if (status & TxComplete)
+ pop_tx_status(dev);
+ if (status & (AdapterFailure | RxEarly | StatsFull)) {
+ /* Handle all uncommon interrupts. */
+ if (status & StatsFull) /* Empty statistics. */
+ update_stats(dev);
+ if (status & RxEarly) {
+ /* Rx early is unused. */
+ el3_rx(dev);
+ outw(AckIntr | RxEarly, ioaddr + EL3_CMD);
+ }
+ if (status & AdapterFailure) {
+ u16 fifo_diag;
+ EL3WINDOW(4);
+ fifo_diag = inw(ioaddr + 4);
+ EL3WINDOW(1);
+ netdev_warn(dev, "adapter failure, FIFO diagnostic register %04x.\n",
fifo_diag);
- if (fifo_diag & 0x0400) {
- /* Tx overrun */
- tc589_wait_for_completion(dev, TxReset);
- outw(TxEnable, ioaddr + EL3_CMD);
+ if (fifo_diag & 0x0400) {
+ /* Tx overrun */
+ tc589_wait_for_completion(dev, TxReset);
+ outw(TxEnable, ioaddr + EL3_CMD);
+ }
+ if (fifo_diag & 0x2000) {
+ /* Rx underrun */
+ tc589_wait_for_completion(dev, RxReset);
+ set_rx_mode(dev);
+ outw(RxEnable, ioaddr + EL3_CMD);
+ }
+ outw(AckIntr | AdapterFailure, ioaddr + EL3_CMD);
+ }
}
- if (fifo_diag & 0x2000) {
- /* Rx underrun */
- tc589_wait_for_completion(dev, RxReset);
- set_rx_mode(dev);
- outw(RxEnable, ioaddr + EL3_CMD);
+ if (++i > 10) {
+ netdev_err(dev, "infinite loop in interrupt, status %4.4x.\n",
+ status);
+ /* Clear all interrupts */
+ outw(AckIntr | 0xFF, ioaddr + EL3_CMD);
+ break;
}
- outw(AckIntr | AdapterFailure, ioaddr + EL3_CMD);
- }
+ /* Acknowledge the IRQ. */
+ outw(AckIntr | IntReq | IntLatch, ioaddr + EL3_CMD);
}
- if (++i > 10) {
- netdev_err(dev, "infinite loop in interrupt, status %4.4x.\n",
- status);
- /* Clear all interrupts */
- outw(AckIntr | 0xFF, ioaddr + EL3_CMD);
- break;
- }
- /* Acknowledge the IRQ. */
- outw(AckIntr | IntReq | IntLatch, ioaddr + EL3_CMD);
- }
- lp->last_irq = jiffies;
- spin_unlock(&lp->lock);
- netdev_dbg(dev, "exiting interrupt, status %4.4x.\n",
- inw(ioaddr + EL3_STATUS));
- return IRQ_RETVAL(handled);
+ lp->last_irq = jiffies;
+ spin_unlock(&lp->lock);
+ netdev_dbg(dev, "exiting interrupt, status %4.4x.\n",
+ inw(ioaddr + EL3_STATUS));
+ return IRQ_RETVAL(handled);
}
static void media_check(unsigned long arg)
{
- struct net_device *dev = (struct net_device *)(arg);
- struct el3_private *lp = netdev_priv(dev);
- unsigned int ioaddr = dev->base_addr;
- u16 media, errs;
- unsigned long flags;
+ struct net_device *dev = (struct net_device *)(arg);
+ struct el3_private *lp = netdev_priv(dev);
+ unsigned int ioaddr = dev->base_addr;
+ u16 media, errs;
+ unsigned long flags;
- if (!netif_device_present(dev)) goto reschedule;
+ if (!netif_device_present(dev))
+ goto reschedule;
- /* Check for pending interrupt with expired latency timer: with
- this, we can limp along even if the interrupt is blocked */
- if ((inw(ioaddr + EL3_STATUS) & IntLatch) &&
+ /* Check for pending interrupt with expired latency timer: with
+ * this, we can limp along even if the interrupt is blocked
+ */
+ if ((inw(ioaddr + EL3_STATUS) & IntLatch) &&
(inb(ioaddr + EL3_TIMER) == 0xff)) {
- if (!lp->fast_poll)
- netdev_warn(dev, "interrupt(s) dropped!\n");
+ if (!lp->fast_poll)
+ netdev_warn(dev, "interrupt(s) dropped!\n");
- local_irq_save(flags);
- el3_interrupt(dev->irq, dev);
- local_irq_restore(flags);
+ local_irq_save(flags);
+ el3_interrupt(dev->irq, dev);
+ local_irq_restore(flags);
- lp->fast_poll = HZ;
- }
- if (lp->fast_poll) {
- lp->fast_poll--;
- lp->media.expires = jiffies + HZ/100;
- add_timer(&lp->media);
- return;
- }
+ lp->fast_poll = HZ;
+ }
+ if (lp->fast_poll) {
+ lp->fast_poll--;
+ lp->media.expires = jiffies + HZ/100;
+ add_timer(&lp->media);
+ return;
+ }
- /* lp->lock guards the EL3 window. Window should always be 1 except
- when the lock is held */
- spin_lock_irqsave(&lp->lock, flags);
- EL3WINDOW(4);
- media = inw(ioaddr+WN4_MEDIA) & 0xc810;
+ /* lp->lock guards the EL3 window. Window should always be 1 except
+ * when the lock is held
+ */
- /* Ignore collisions unless we've had no irq's recently */
- if (time_before(jiffies, lp->last_irq + HZ)) {
- media &= ~0x0010;
- } else {
- /* Try harder to detect carrier errors */
- EL3WINDOW(6);
- outw(StatsDisable, ioaddr + EL3_CMD);
- errs = inb(ioaddr + 0);
- outw(StatsEnable, ioaddr + EL3_CMD);
- dev->stats.tx_carrier_errors += errs;
- if (errs || (lp->media_status & 0x0010)) media |= 0x0010;
- }
+ spin_lock_irqsave(&lp->lock, flags);
+ EL3WINDOW(4);
+ media = inw(ioaddr+WN4_MEDIA) & 0xc810;
- if (media != lp->media_status) {
- if ((media & lp->media_status & 0x8000) &&
- ((lp->media_status ^ media) & 0x0800))
+ /* Ignore collisions unless we've had no irq's recently */
+ if (time_before(jiffies, lp->last_irq + HZ)) {
+ media &= ~0x0010;
+ } else {
+ /* Try harder to detect carrier errors */
+ EL3WINDOW(6);
+ outw(StatsDisable, ioaddr + EL3_CMD);
+ errs = inb(ioaddr + 0);
+ outw(StatsEnable, ioaddr + EL3_CMD);
+ dev->stats.tx_carrier_errors += errs;
+ if (errs || (lp->media_status & 0x0010))
+ media |= 0x0010;
+ }
+
+ if (media != lp->media_status) {
+ if ((media & lp->media_status & 0x8000) &&
+ ((lp->media_status ^ media) & 0x0800))
netdev_info(dev, "%s link beat\n",
- (lp->media_status & 0x0800 ? "lost" : "found"));
- else if ((media & lp->media_status & 0x4000) &&
+ (lp->media_status & 0x0800 ? "lost" : "found"));
+ else if ((media & lp->media_status & 0x4000) &&
((lp->media_status ^ media) & 0x0010))
netdev_info(dev, "coax cable %s\n",
- (lp->media_status & 0x0010 ? "ok" : "problem"));
- if (dev->if_port == 0) {
- if (media & 0x8000) {
- if (media & 0x0800)
- netdev_info(dev, "flipped to 10baseT\n");
- else
+ (lp->media_status & 0x0010 ? "ok" : "problem"));
+ if (dev->if_port == 0) {
+ if (media & 0x8000) {
+ if (media & 0x0800)
+ netdev_info(dev, "flipped to 10baseT\n");
+ else
tc589_set_xcvr(dev, 2);
- } else if (media & 0x4000) {
- if (media & 0x0010)
- tc589_set_xcvr(dev, 1);
- else
- netdev_info(dev, "flipped to 10base2\n");
- }
+ } else if (media & 0x4000) {
+ if (media & 0x0010)
+ tc589_set_xcvr(dev, 1);
+ else
+ netdev_info(dev, "flipped to 10base2\n");
+ }
+ }
+ lp->media_status = media;
}
- lp->media_status = media;
- }
- EL3WINDOW(1);
- spin_unlock_irqrestore(&lp->lock, flags);
+ EL3WINDOW(1);
+ spin_unlock_irqrestore(&lp->lock, flags);
reschedule:
- lp->media.expires = jiffies + HZ;
- add_timer(&lp->media);
+ lp->media.expires = jiffies + HZ;
+ add_timer(&lp->media);
}
static struct net_device_stats *el3_get_stats(struct net_device *dev)
{
- struct el3_private *lp = netdev_priv(dev);
- unsigned long flags;
- struct pcmcia_device *link = lp->p_dev;
+ struct el3_private *lp = netdev_priv(dev);
+ unsigned long flags;
+ struct pcmcia_device *link = lp->p_dev;
- if (pcmcia_dev_present(link)) {
- spin_lock_irqsave(&lp->lock, flags);
- update_stats(dev);
- spin_unlock_irqrestore(&lp->lock, flags);
- }
- return &dev->stats;
+ if (pcmcia_dev_present(link)) {
+ spin_lock_irqsave(&lp->lock, flags);
+ update_stats(dev);
+ spin_unlock_irqrestore(&lp->lock, flags);
+ }
+ return &dev->stats;
}
-/*
- Update statistics. We change to register window 6, so this should be run
- single-threaded if the device is active. This is expected to be a rare
- operation, and it's simpler for the rest of the driver to assume that
- window 1 is always valid rather than use a special window-state variable.
-
- Caller must hold the lock for this
+/* Update statistics. We change to register window 6, so this should be run
+* single-threaded if the device is active. This is expected to be a rare
+* operation, and it's simpler for the rest of the driver to assume that
+* window 1 is always valid rather than use a special window-state variable.
+*
+* Caller must hold the lock for this
*/
+
static void update_stats(struct net_device *dev)
{
- unsigned int ioaddr = dev->base_addr;
+ unsigned int ioaddr = dev->base_addr;
- netdev_dbg(dev, "updating the statistics.\n");
- /* Turn off statistics updates while reading. */
- outw(StatsDisable, ioaddr + EL3_CMD);
- /* Switch to the stats window, and read everything. */
- EL3WINDOW(6);
- dev->stats.tx_carrier_errors += inb(ioaddr + 0);
- dev->stats.tx_heartbeat_errors += inb(ioaddr + 1);
- /* Multiple collisions. */ inb(ioaddr + 2);
- dev->stats.collisions += inb(ioaddr + 3);
- dev->stats.tx_window_errors += inb(ioaddr + 4);
- dev->stats.rx_fifo_errors += inb(ioaddr + 5);
- dev->stats.tx_packets += inb(ioaddr + 6);
- /* Rx packets */ inb(ioaddr + 7);
- /* Tx deferrals */ inb(ioaddr + 8);
- /* Rx octets */ inw(ioaddr + 10);
- /* Tx octets */ inw(ioaddr + 12);
+ netdev_dbg(dev, "updating the statistics.\n");
+ /* Turn off statistics updates while reading. */
+ outw(StatsDisable, ioaddr + EL3_CMD);
+ /* Switch to the stats window, and read everything. */
+ EL3WINDOW(6);
+ dev->stats.tx_carrier_errors += inb(ioaddr + 0);
+ dev->stats.tx_heartbeat_errors += inb(ioaddr + 1);
+ /* Multiple collisions. */
+ inb(ioaddr + 2);
+ dev->stats.collisions += inb(ioaddr + 3);
+ dev->stats.tx_window_errors += inb(ioaddr + 4);
+ dev->stats.rx_fifo_errors += inb(ioaddr + 5);
+ dev->stats.tx_packets += inb(ioaddr + 6);
+ /* Rx packets */
+ inb(ioaddr + 7);
+ /* Tx deferrals */
+ inb(ioaddr + 8);
+ /* Rx octets */
+ inw(ioaddr + 10);
+ /* Tx octets */
+ inw(ioaddr + 12);
- /* Back to window 1, and turn statistics back on. */
- EL3WINDOW(1);
- outw(StatsEnable, ioaddr + EL3_CMD);
+ /* Back to window 1, and turn statistics back on. */
+ EL3WINDOW(1);
+ outw(StatsEnable, ioaddr + EL3_CMD);
}
static int el3_rx(struct net_device *dev)
{
- unsigned int ioaddr = dev->base_addr;
- int worklimit = 32;
- short rx_status;
+ unsigned int ioaddr = dev->base_addr;
+ int worklimit = 32;
+ short rx_status;
- netdev_dbg(dev, "in rx_packet(), status %4.4x, rx_status %4.4x.\n",
+ netdev_dbg(dev, "in rx_packet(), status %4.4x, rx_status %4.4x.\n",
inw(ioaddr+EL3_STATUS), inw(ioaddr+RX_STATUS));
- while (!((rx_status = inw(ioaddr + RX_STATUS)) & 0x8000) &&
+ while (!((rx_status = inw(ioaddr + RX_STATUS)) & 0x8000) &&
worklimit > 0) {
- worklimit--;
- if (rx_status & 0x4000) { /* Error, update stats. */
- short error = rx_status & 0x3800;
- dev->stats.rx_errors++;
- switch (error) {
- case 0x0000: dev->stats.rx_over_errors++; break;
- case 0x0800: dev->stats.rx_length_errors++; break;
- case 0x1000: dev->stats.rx_frame_errors++; break;
- case 0x1800: dev->stats.rx_length_errors++; break;
- case 0x2000: dev->stats.rx_frame_errors++; break;
- case 0x2800: dev->stats.rx_crc_errors++; break;
- }
- } else {
- short pkt_len = rx_status & 0x7ff;
- struct sk_buff *skb;
+ worklimit--;
+ if (rx_status & 0x4000) { /* Error, update stats. */
+ short error = rx_status & 0x3800;
+ dev->stats.rx_errors++;
+ switch (error) {
+ case 0x0000:
+ dev->stats.rx_over_errors++;
+ break;
+ case 0x0800:
+ dev->stats.rx_length_errors++;
+ break;
+ case 0x1000:
+ dev->stats.rx_frame_errors++;
+ break;
+ case 0x1800:
+ dev->stats.rx_length_errors++;
+ break;
+ case 0x2000:
+ dev->stats.rx_frame_errors++;
+ break;
+ case 0x2800:
+ dev->stats.rx_crc_errors++;
+ break;
+ }
+ } else {
+ short pkt_len = rx_status & 0x7ff;
+ struct sk_buff *skb;
- skb = netdev_alloc_skb(dev, pkt_len + 5);
+ skb = netdev_alloc_skb(dev, pkt_len + 5);
- netdev_dbg(dev, " Receiving packet size %d status %4.4x.\n",
+ netdev_dbg(dev, " Receiving packet size %d status %4.4x.\n",
pkt_len, rx_status);
- if (skb != NULL) {
- skb_reserve(skb, 2);
- insl(ioaddr+RX_FIFO, skb_put(skb, pkt_len),
+ if (skb != NULL) {
+ skb_reserve(skb, 2);
+ insl(ioaddr+RX_FIFO, skb_put(skb, pkt_len),
(pkt_len+3)>>2);
- skb->protocol = eth_type_trans(skb, dev);
- netif_rx(skb);
- dev->stats.rx_packets++;
- dev->stats.rx_bytes += pkt_len;
- } else {
- netdev_dbg(dev, "couldn't allocate a sk_buff of size %d.\n",
+ skb->protocol = eth_type_trans(skb, dev);
+ netif_rx(skb);
+ dev->stats.rx_packets++;
+ dev->stats.rx_bytes += pkt_len;
+ } else {
+ netdev_dbg(dev, "couldn't allocate a sk_buff of size %d.\n",
pkt_len);
- dev->stats.rx_dropped++;
- }
+ dev->stats.rx_dropped++;
+ }
+ }
+ /* Pop the top of the Rx FIFO */
+ tc589_wait_for_completion(dev, RxDiscard);
}
- /* Pop the top of the Rx FIFO */
- tc589_wait_for_completion(dev, RxDiscard);
- }
- if (worklimit == 0)
- netdev_warn(dev, "too much work in el3_rx!\n");
- return 0;
+ if (worklimit == 0)
+ netdev_warn(dev, "too much work in el3_rx!\n");
+ return 0;
}
static void set_rx_mode(struct net_device *dev)
{
- unsigned int ioaddr = dev->base_addr;
- u16 opts = SetRxFilter | RxStation | RxBroadcast;
+ unsigned int ioaddr = dev->base_addr;
+ u16 opts = SetRxFilter | RxStation | RxBroadcast;
- if (dev->flags & IFF_PROMISC)
- opts |= RxMulticast | RxProm;
- else if (!netdev_mc_empty(dev) || (dev->flags & IFF_ALLMULTI))
- opts |= RxMulticast;
- outw(opts, ioaddr + EL3_CMD);
+ if (dev->flags & IFF_PROMISC)
+ opts |= RxMulticast | RxProm;
+ else if (!netdev_mc_empty(dev) || (dev->flags & IFF_ALLMULTI))
+ opts |= RxMulticast;
+ outw(opts, ioaddr + EL3_CMD);
}
static void set_multicast_list(struct net_device *dev)
@@ -867,44 +908,44 @@
static int el3_close(struct net_device *dev)
{
- struct el3_private *lp = netdev_priv(dev);
- struct pcmcia_device *link = lp->p_dev;
- unsigned int ioaddr = dev->base_addr;
+ struct el3_private *lp = netdev_priv(dev);
+ struct pcmcia_device *link = lp->p_dev;
+ unsigned int ioaddr = dev->base_addr;
- dev_dbg(&link->dev, "%s: shutting down ethercard.\n", dev->name);
+ dev_dbg(&link->dev, "%s: shutting down ethercard.\n", dev->name);
- if (pcmcia_dev_present(link)) {
- /* Turn off statistics ASAP. We update dev->stats below. */
- outw(StatsDisable, ioaddr + EL3_CMD);
+ if (pcmcia_dev_present(link)) {
+ /* Turn off statistics ASAP. We update dev->stats below. */
+ outw(StatsDisable, ioaddr + EL3_CMD);
- /* Disable the receiver and transmitter. */
- outw(RxDisable, ioaddr + EL3_CMD);
- outw(TxDisable, ioaddr + EL3_CMD);
+ /* Disable the receiver and transmitter. */
+ outw(RxDisable, ioaddr + EL3_CMD);
+ outw(TxDisable, ioaddr + EL3_CMD);
- if (dev->if_port == 2)
- /* Turn off thinnet power. Green! */
- outw(StopCoax, ioaddr + EL3_CMD);
- else if (dev->if_port == 1) {
- /* Disable link beat and jabber */
- EL3WINDOW(4);
- outw(0, ioaddr + WN4_MEDIA);
+ if (dev->if_port == 2)
+ /* Turn off thinnet power. Green! */
+ outw(StopCoax, ioaddr + EL3_CMD);
+ else if (dev->if_port == 1) {
+ /* Disable link beat and jabber */
+ EL3WINDOW(4);
+ outw(0, ioaddr + WN4_MEDIA);
+ }
+
+ /* Switching back to window 0 disables the IRQ. */
+ EL3WINDOW(0);
+ /* But we explicitly zero the IRQ line select anyway. */
+ outw(0x0f00, ioaddr + WN0_IRQ);
+
+ /* Check if the card still exists */
+ if ((inw(ioaddr+EL3_STATUS) & 0xe000) == 0x2000)
+ update_stats(dev);
}
- /* Switching back to window 0 disables the IRQ. */
- EL3WINDOW(0);
- /* But we explicitly zero the IRQ line select anyway. */
- outw(0x0f00, ioaddr + WN0_IRQ);
+ link->open--;
+ netif_stop_queue(dev);
+ del_timer_sync(&lp->media);
- /* Check if the card still exists */
- if ((inw(ioaddr+EL3_STATUS) & 0xe000) == 0x2000)
- update_stats(dev);
- }
-
- link->open--;
- netif_stop_queue(dev);
- del_timer_sync(&lp->media);
-
- return 0;
+ return 0;
}
static const struct pcmcia_device_id tc589_ids[] = {
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 0f4241c..61477b8 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -2086,7 +2086,7 @@
/* ... and the packet rounded to a doubleword. */
skb_tx_timestamp(skb);
iowrite32_rep(ioaddr + TX_FIFO, skb->data, (skb->len + 3) >> 2);
- dev_kfree_skb (skb);
+ dev_consume_skb_any (skb);
if (ioread16(ioaddr + TxFree) > 1536) {
netif_start_queue (dev); /* AKPM: redundant? */
} else {
@@ -3294,7 +3294,6 @@
static void __exit vortex_eisa_cleanup(void)
{
- struct vortex_private *vp;
void __iomem *ioaddr;
#ifdef CONFIG_EISA
@@ -3303,7 +3302,6 @@
#endif
if (compaq_net_device) {
- vp = netdev_priv(compaq_net_device);
ioaddr = ioport_map(compaq_net_device->base_addr,
VORTEX_TOTAL_SIZE);
diff --git a/drivers/net/ethernet/8390/lib8390.c b/drivers/net/ethernet/8390/lib8390.c
index d2cd804..599311f 100644
--- a/drivers/net/ethernet/8390/lib8390.c
+++ b/drivers/net/ethernet/8390/lib8390.c
@@ -404,7 +404,7 @@
spin_unlock(&ei_local->page_lock);
enable_irq_lockdep_irqrestore(dev->irq, &flags);
skb_tx_timestamp(skb);
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
dev->stats.tx_bytes += send_length;
return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 506b024..39b26fe 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -22,6 +22,7 @@
source "drivers/net/ethernet/aeroflex/Kconfig"
source "drivers/net/ethernet/allwinner/Kconfig"
source "drivers/net/ethernet/alteon/Kconfig"
+source "drivers/net/ethernet/altera/Kconfig"
source "drivers/net/ethernet/amd/Kconfig"
source "drivers/net/ethernet/apple/Kconfig"
source "drivers/net/ethernet/arc/Kconfig"
@@ -149,6 +150,7 @@
To compile this driver as a module, choose M here. The module
will be called s6gmac.
+source "drivers/net/ethernet/samsung/Kconfig"
source "drivers/net/ethernet/seeq/Kconfig"
source "drivers/net/ethernet/silan/Kconfig"
source "drivers/net/ethernet/sis/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index c0b8789..545d0b3 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -8,6 +8,7 @@
obj-$(CONFIG_GRETH) += aeroflex/
obj-$(CONFIG_NET_VENDOR_ALLWINNER) += allwinner/
obj-$(CONFIG_NET_VENDOR_ALTEON) += alteon/
+obj-$(CONFIG_ALTERA_TSE) += altera/
obj-$(CONFIG_NET_VENDOR_AMD) += amd/
obj-$(CONFIG_NET_VENDOR_APPLE) += apple/
obj-$(CONFIG_NET_VENDOR_ARC) += arc/
@@ -60,6 +61,7 @@
obj-$(CONFIG_SH_ETH) += renesas/
obj-$(CONFIG_NET_VENDOR_RDC) += rdc/
obj-$(CONFIG_S6GMAC) += s6gmac.o
+obj-$(CONFIG_NET_VENDOR_SAMSUNG) += samsung/
obj-$(CONFIG_NET_VENDOR_SEEQ) += seeq/
obj-$(CONFIG_NET_VENDOR_SILAN) += silan/
obj-$(CONFIG_NET_VENDOR_SIS) += sis/
diff --git a/drivers/net/ethernet/adi/bfin_mac.c b/drivers/net/ethernet/adi/bfin_mac.c
index c0f68dc..7ae74d4 100644
--- a/drivers/net/ethernet/adi/bfin_mac.c
+++ b/drivers/net/ethernet/adi/bfin_mac.c
@@ -307,11 +307,6 @@
return bfin_mdio_poll();
}
-static int bfin_mdiobus_reset(struct mii_bus *bus)
-{
- return 0;
-}
-
static void bfin_mac_adjust_link(struct net_device *dev)
{
struct bfin_mac_local *lp = netdev_priv(dev);
@@ -1040,6 +1035,7 @@
.n_alarm = 0,
.n_ext_ts = 0,
.n_per_out = 0,
+ .n_pins = 0,
.pps = 0,
.adjfreq = bfin_ptp_adjfreq,
.adjtime = bfin_ptp_adjtime,
@@ -1086,7 +1082,7 @@
tx_list_head->desc_a.config &= ~DMAEN;
tx_list_head->status.status_word = 0;
if (tx_list_head->skb) {
- dev_kfree_skb(tx_list_head->skb);
+ dev_consume_skb_any(tx_list_head->skb);
tx_list_head->skb = NULL;
}
tx_list_head = tx_list_head->next;
@@ -1823,7 +1819,6 @@
goto out_err_alloc;
miibus->read = bfin_mdiobus_read;
miibus->write = bfin_mdiobus_write;
- miibus->reset = bfin_mdiobus_reset;
miibus->parent = &pdev->dev;
miibus->name = "bfin_mii_bus";
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index c5d75e7..23578df 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -1213,11 +1213,6 @@
return 0;
}
-static int greth_mdio_reset(struct mii_bus *bus)
-{
- return 0;
-}
-
static void greth_link_change(struct net_device *dev)
{
struct greth_private *greth = netdev_priv(dev);
@@ -1332,7 +1327,6 @@
snprintf(greth->mdio->id, MII_BUS_ID_SIZE, "%s-%d", greth->mdio->name, greth->irq);
greth->mdio->read = greth_mdio_read;
greth->mdio->write = greth_mdio_write;
- greth->mdio->reset = greth_mdio_reset;
greth->mdio->priv = greth;
greth->mdio->irq = greth->mdio_irqs;
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 0cc2143..fcaeeb8 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -476,7 +476,7 @@
spin_unlock_irqrestore(&db->lock, flags);
/* free this SKB */
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -929,6 +929,9 @@
}
static const struct of_device_id emac_of_match[] = {
+ {.compatible = "allwinner,sun4i-a10-emac",},
+
+ /* Deprecated */
{.compatible = "allwinner,sun4i-emac",},
{},
};
diff --git a/drivers/net/ethernet/altera/Kconfig b/drivers/net/ethernet/altera/Kconfig
new file mode 100644
index 0000000..80c1ab7
--- /dev/null
+++ b/drivers/net/ethernet/altera/Kconfig
@@ -0,0 +1,8 @@
+config ALTERA_TSE
+ tristate "Altera Triple-Speed Ethernet MAC support"
+ select PHYLIB
+ ---help---
+ This driver supports the Altera Triple-Speed (TSE) Ethernet MAC.
+
+ To compile this driver as a module, choose M here. The module
+ will be called alteratse.
diff --git a/drivers/net/ethernet/altera/Makefile b/drivers/net/ethernet/altera/Makefile
new file mode 100644
index 0000000..d4a187e
--- /dev/null
+++ b/drivers/net/ethernet/altera/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the Altera device drivers.
+#
+
+obj-$(CONFIG_ALTERA_TSE) += altera_tse.o
+altera_tse-objs := altera_tse_main.o altera_tse_ethtool.o \
+altera_msgdma.o altera_sgdma.o altera_utils.o
diff --git a/drivers/net/ethernet/altera/altera_msgdma.c b/drivers/net/ethernet/altera/altera_msgdma.c
new file mode 100644
index 0000000..3df1866
--- /dev/null
+++ b/drivers/net/ethernet/altera/altera_msgdma.c
@@ -0,0 +1,202 @@
+/* Altera TSE SGDMA and MSGDMA Linux driver
+ * Copyright (C) 2014 Altera Corporation. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/netdevice.h>
+#include "altera_utils.h"
+#include "altera_tse.h"
+#include "altera_msgdmahw.h"
+
+/* No initialization work to do for MSGDMA */
+int msgdma_initialize(struct altera_tse_private *priv)
+{
+ return 0;
+}
+
+void msgdma_uninitialize(struct altera_tse_private *priv)
+{
+}
+
+void msgdma_reset(struct altera_tse_private *priv)
+{
+ int counter;
+ struct msgdma_csr *txcsr =
+ (struct msgdma_csr *)priv->tx_dma_csr;
+ struct msgdma_csr *rxcsr =
+ (struct msgdma_csr *)priv->rx_dma_csr;
+
+ /* Reset Rx mSGDMA */
+ iowrite32(MSGDMA_CSR_STAT_MASK, &rxcsr->status);
+ iowrite32(MSGDMA_CSR_CTL_RESET, &rxcsr->control);
+
+ counter = 0;
+ while (counter++ < ALTERA_TSE_SW_RESET_WATCHDOG_CNTR) {
+ if (tse_bit_is_clear(&rxcsr->status,
+ MSGDMA_CSR_STAT_RESETTING))
+ break;
+ udelay(1);
+ }
+
+ if (counter >= ALTERA_TSE_SW_RESET_WATCHDOG_CNTR)
+ netif_warn(priv, drv, priv->dev,
+ "TSE Rx mSGDMA resetting bit never cleared!\n");
+
+ /* clear all status bits */
+ iowrite32(MSGDMA_CSR_STAT_MASK, &rxcsr->status);
+
+ /* Reset Tx mSGDMA */
+ iowrite32(MSGDMA_CSR_STAT_MASK, &txcsr->status);
+ iowrite32(MSGDMA_CSR_CTL_RESET, &txcsr->control);
+
+ counter = 0;
+ while (counter++ < ALTERA_TSE_SW_RESET_WATCHDOG_CNTR) {
+ if (tse_bit_is_clear(&txcsr->status,
+ MSGDMA_CSR_STAT_RESETTING))
+ break;
+ udelay(1);
+ }
+
+ if (counter >= ALTERA_TSE_SW_RESET_WATCHDOG_CNTR)
+ netif_warn(priv, drv, priv->dev,
+ "TSE Tx mSGDMA resetting bit never cleared!\n");
+
+ /* clear all status bits */
+ iowrite32(MSGDMA_CSR_STAT_MASK, &txcsr->status);
+}
+
+void msgdma_disable_rxirq(struct altera_tse_private *priv)
+{
+ struct msgdma_csr *csr = priv->rx_dma_csr;
+ tse_clear_bit(&csr->control, MSGDMA_CSR_CTL_GLOBAL_INTR);
+}
+
+void msgdma_enable_rxirq(struct altera_tse_private *priv)
+{
+ struct msgdma_csr *csr = priv->rx_dma_csr;
+ tse_set_bit(&csr->control, MSGDMA_CSR_CTL_GLOBAL_INTR);
+}
+
+void msgdma_disable_txirq(struct altera_tse_private *priv)
+{
+ struct msgdma_csr *csr = priv->tx_dma_csr;
+ tse_clear_bit(&csr->control, MSGDMA_CSR_CTL_GLOBAL_INTR);
+}
+
+void msgdma_enable_txirq(struct altera_tse_private *priv)
+{
+ struct msgdma_csr *csr = priv->tx_dma_csr;
+ tse_set_bit(&csr->control, MSGDMA_CSR_CTL_GLOBAL_INTR);
+}
+
+void msgdma_clear_rxirq(struct altera_tse_private *priv)
+{
+ struct msgdma_csr *csr = priv->rx_dma_csr;
+ iowrite32(MSGDMA_CSR_STAT_IRQ, &csr->status);
+}
+
+void msgdma_clear_txirq(struct altera_tse_private *priv)
+{
+ struct msgdma_csr *csr = priv->tx_dma_csr;
+ iowrite32(MSGDMA_CSR_STAT_IRQ, &csr->status);
+}
+
+/* return 0 to indicate transmit is pending */
+int msgdma_tx_buffer(struct altera_tse_private *priv, struct tse_buffer *buffer)
+{
+ struct msgdma_extended_desc *desc = priv->tx_dma_desc;
+
+ iowrite32(lower_32_bits(buffer->dma_addr), &desc->read_addr_lo);
+ iowrite32(upper_32_bits(buffer->dma_addr), &desc->read_addr_hi);
+ iowrite32(0, &desc->write_addr_lo);
+ iowrite32(0, &desc->write_addr_hi);
+ iowrite32(buffer->len, &desc->len);
+ iowrite32(0, &desc->burst_seq_num);
+ iowrite32(MSGDMA_DESC_TX_STRIDE, &desc->stride);
+ iowrite32(MSGDMA_DESC_CTL_TX_SINGLE, &desc->control);
+ return 0;
+}
+
+u32 msgdma_tx_completions(struct altera_tse_private *priv)
+{
+ u32 ready = 0;
+ u32 inuse;
+ u32 status;
+ struct msgdma_csr *txcsr =
+ (struct msgdma_csr *)priv->tx_dma_csr;
+
+ /* Get number of sent descriptors */
+ inuse = ioread32(&txcsr->rw_fill_level) & 0xffff;
+
+ if (inuse) { /* Tx FIFO is not empty */
+ ready = priv->tx_prod - priv->tx_cons - inuse - 1;
+ } else {
+ /* Check for buffered last packet */
+ status = ioread32(&txcsr->status);
+ if (status & MSGDMA_CSR_STAT_BUSY)
+ ready = priv->tx_prod - priv->tx_cons - 1;
+ else
+ ready = priv->tx_prod - priv->tx_cons;
+ }
+ return ready;
+}
+
+/* Put buffer to the mSGDMA RX FIFO
+ */
+int msgdma_add_rx_desc(struct altera_tse_private *priv,
+ struct tse_buffer *rxbuffer)
+{
+ struct msgdma_extended_desc *desc = priv->rx_dma_desc;
+ u32 len = priv->rx_dma_buf_sz;
+ dma_addr_t dma_addr = rxbuffer->dma_addr;
+ u32 control = (MSGDMA_DESC_CTL_END_ON_EOP
+ | MSGDMA_DESC_CTL_END_ON_LEN
+ | MSGDMA_DESC_CTL_TR_COMP_IRQ
+ | MSGDMA_DESC_CTL_EARLY_IRQ
+ | MSGDMA_DESC_CTL_TR_ERR_IRQ
+ | MSGDMA_DESC_CTL_GO);
+
+ iowrite32(0, &desc->read_addr_lo);
+ iowrite32(0, &desc->read_addr_hi);
+ iowrite32(lower_32_bits(dma_addr), &desc->write_addr_lo);
+ iowrite32(upper_32_bits(dma_addr), &desc->write_addr_hi);
+ iowrite32(len, &desc->len);
+ iowrite32(0, &desc->burst_seq_num);
+ iowrite32(0x00010001, &desc->stride);
+ iowrite32(control, &desc->control);
+ return 1;
+}
+
+/* status is returned on upper 16 bits,
+ * length is returned in lower 16 bits
+ */
+u32 msgdma_rx_status(struct altera_tse_private *priv)
+{
+ u32 rxstatus = 0;
+ u32 pktlength;
+ u32 pktstatus;
+ struct msgdma_csr *rxcsr =
+ (struct msgdma_csr *)priv->rx_dma_csr;
+ struct msgdma_response *rxresp =
+ (struct msgdma_response *)priv->rx_dma_resp;
+
+ if (ioread32(&rxcsr->resp_fill_level) & 0xffff) {
+ pktlength = ioread32(&rxresp->bytes_transferred);
+ pktstatus = ioread32(&rxresp->status);
+ rxstatus = pktstatus;
+ rxstatus = rxstatus << 16;
+ rxstatus |= (pktlength & 0xffff);
+ }
+ return rxstatus;
+}
diff --git a/drivers/net/ethernet/altera/altera_msgdma.h b/drivers/net/ethernet/altera/altera_msgdma.h
new file mode 100644
index 0000000..7f0f5bf
--- /dev/null
+++ b/drivers/net/ethernet/altera/altera_msgdma.h
@@ -0,0 +1,34 @@
+/* Altera TSE SGDMA and MSGDMA Linux driver
+ * Copyright (C) 2014 Altera Corporation. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ALTERA_MSGDMA_H__
+#define __ALTERA_MSGDMA_H__
+
+void msgdma_reset(struct altera_tse_private *);
+void msgdma_enable_txirq(struct altera_tse_private *);
+void msgdma_enable_rxirq(struct altera_tse_private *);
+void msgdma_disable_rxirq(struct altera_tse_private *);
+void msgdma_disable_txirq(struct altera_tse_private *);
+void msgdma_clear_rxirq(struct altera_tse_private *);
+void msgdma_clear_txirq(struct altera_tse_private *);
+u32 msgdma_tx_completions(struct altera_tse_private *);
+int msgdma_add_rx_desc(struct altera_tse_private *, struct tse_buffer *);
+int msgdma_tx_buffer(struct altera_tse_private *, struct tse_buffer *);
+u32 msgdma_rx_status(struct altera_tse_private *);
+int msgdma_initialize(struct altera_tse_private *);
+void msgdma_uninitialize(struct altera_tse_private *);
+
+#endif /* __ALTERA_MSGDMA_H__ */
diff --git a/drivers/net/ethernet/altera/altera_msgdmahw.h b/drivers/net/ethernet/altera/altera_msgdmahw.h
new file mode 100644
index 0000000..d7b59ba
--- /dev/null
+++ b/drivers/net/ethernet/altera/altera_msgdmahw.h
@@ -0,0 +1,167 @@
+/* Altera TSE SGDMA and MSGDMA Linux driver
+ * Copyright (C) 2014 Altera Corporation. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ALTERA_MSGDMAHW_H__
+#define __ALTERA_MSGDMAHW_H__
+
+/* mSGDMA standard descriptor format
+ */
+struct msgdma_desc {
+ u32 read_addr; /* data buffer source address */
+ u32 write_addr; /* data buffer destination address */
+ u32 len; /* the number of bytes to transfer per descriptor */
+ u32 control; /* characteristics of the transfer */
+};
+
+/* mSGDMA extended descriptor format
+ */
+struct msgdma_extended_desc {
+ u32 read_addr_lo; /* data buffer source address low bits */
+ u32 write_addr_lo; /* data buffer destination address low bits */
+ u32 len; /* the number of bytes to transfer
+ * per descriptor
+ */
+ u32 burst_seq_num; /* bit 31:24 write burst
+ * bit 23:16 read burst
+ * bit 15:0 sequence number
+ */
+ u32 stride; /* bit 31:16 write stride
+ * bit 15:0 read stride
+ */
+ u32 read_addr_hi; /* data buffer source address high bits */
+ u32 write_addr_hi; /* data buffer destination address high bits */
+ u32 control; /* characteristics of the transfer */
+};
+
+/* mSGDMA descriptor control field bit definitions
+ */
+#define MSGDMA_DESC_CTL_SET_CH(x) ((x) & 0xff)
+#define MSGDMA_DESC_CTL_GEN_SOP BIT(8)
+#define MSGDMA_DESC_CTL_GEN_EOP BIT(9)
+#define MSGDMA_DESC_CTL_PARK_READS BIT(10)
+#define MSGDMA_DESC_CTL_PARK_WRITES BIT(11)
+#define MSGDMA_DESC_CTL_END_ON_EOP BIT(12)
+#define MSGDMA_DESC_CTL_END_ON_LEN BIT(13)
+#define MSGDMA_DESC_CTL_TR_COMP_IRQ BIT(14)
+#define MSGDMA_DESC_CTL_EARLY_IRQ BIT(15)
+#define MSGDMA_DESC_CTL_TR_ERR_IRQ (0xff << 16)
+#define MSGDMA_DESC_CTL_EARLY_DONE BIT(24)
+/* Writing ‘1’ to the ‘go’ bit commits the entire descriptor into the
+ * descriptor FIFO(s)
+ */
+#define MSGDMA_DESC_CTL_GO BIT(31)
+
+/* Tx buffer control flags
+ */
+#define MSGDMA_DESC_CTL_TX_FIRST (MSGDMA_DESC_CTL_GEN_SOP | \
+ MSGDMA_DESC_CTL_TR_ERR_IRQ | \
+ MSGDMA_DESC_CTL_GO)
+
+#define MSGDMA_DESC_CTL_TX_MIDDLE (MSGDMA_DESC_CTL_TR_ERR_IRQ | \
+ MSGDMA_DESC_CTL_GO)
+
+#define MSGDMA_DESC_CTL_TX_LAST (MSGDMA_DESC_CTL_GEN_EOP | \
+ MSGDMA_DESC_CTL_TR_COMP_IRQ | \
+ MSGDMA_DESC_CTL_TR_ERR_IRQ | \
+ MSGDMA_DESC_CTL_GO)
+
+#define MSGDMA_DESC_CTL_TX_SINGLE (MSGDMA_DESC_CTL_GEN_SOP | \
+ MSGDMA_DESC_CTL_GEN_EOP | \
+ MSGDMA_DESC_CTL_TR_COMP_IRQ | \
+ MSGDMA_DESC_CTL_TR_ERR_IRQ | \
+ MSGDMA_DESC_CTL_GO)
+
+#define MSGDMA_DESC_CTL_RX_SINGLE (MSGDMA_DESC_CTL_END_ON_EOP | \
+ MSGDMA_DESC_CTL_END_ON_LEN | \
+ MSGDMA_DESC_CTL_TR_COMP_IRQ | \
+ MSGDMA_DESC_CTL_EARLY_IRQ | \
+ MSGDMA_DESC_CTL_TR_ERR_IRQ | \
+ MSGDMA_DESC_CTL_GO)
+
+/* mSGDMA extended descriptor stride definitions
+ */
+#define MSGDMA_DESC_TX_STRIDE (0x00010001)
+#define MSGDMA_DESC_RX_STRIDE (0x00010001)
+
+/* mSGDMA dispatcher control and status register map
+ */
+struct msgdma_csr {
+ u32 status; /* Read/Clear */
+ u32 control; /* Read/Write */
+ u32 rw_fill_level; /* bit 31:16 - write fill level
+ * bit 15:0 - read fill level
+ */
+ u32 resp_fill_level; /* bit 15:0 */
+ u32 rw_seq_num; /* bit 31:16 - write sequence number
+ * bit 15:0 - read sequence number
+ */
+ u32 pad[3]; /* reserved */
+};
+
+/* mSGDMA CSR status register bit definitions
+ */
+#define MSGDMA_CSR_STAT_BUSY BIT(0)
+#define MSGDMA_CSR_STAT_DESC_BUF_EMPTY BIT(1)
+#define MSGDMA_CSR_STAT_DESC_BUF_FULL BIT(2)
+#define MSGDMA_CSR_STAT_RESP_BUF_EMPTY BIT(3)
+#define MSGDMA_CSR_STAT_RESP_BUF_FULL BIT(4)
+#define MSGDMA_CSR_STAT_STOPPED BIT(5)
+#define MSGDMA_CSR_STAT_RESETTING BIT(6)
+#define MSGDMA_CSR_STAT_STOPPED_ON_ERR BIT(7)
+#define MSGDMA_CSR_STAT_STOPPED_ON_EARLY BIT(8)
+#define MSGDMA_CSR_STAT_IRQ BIT(9)
+#define MSGDMA_CSR_STAT_MASK 0x3FF
+#define MSGDMA_CSR_STAT_MASK_WITHOUT_IRQ 0x1FF
+
+#define MSGDMA_CSR_STAT_BUSY_GET(v) GET_BIT_VALUE(v, 0)
+#define MSGDMA_CSR_STAT_DESC_BUF_EMPTY_GET(v) GET_BIT_VALUE(v, 1)
+#define MSGDMA_CSR_STAT_DESC_BUF_FULL_GET(v) GET_BIT_VALUE(v, 2)
+#define MSGDMA_CSR_STAT_RESP_BUF_EMPTY_GET(v) GET_BIT_VALUE(v, 3)
+#define MSGDMA_CSR_STAT_RESP_BUF_FULL_GET(v) GET_BIT_VALUE(v, 4)
+#define MSGDMA_CSR_STAT_STOPPED_GET(v) GET_BIT_VALUE(v, 5)
+#define MSGDMA_CSR_STAT_RESETTING_GET(v) GET_BIT_VALUE(v, 6)
+#define MSGDMA_CSR_STAT_STOPPED_ON_ERR_GET(v) GET_BIT_VALUE(v, 7)
+#define MSGDMA_CSR_STAT_STOPPED_ON_EARLY_GET(v) GET_BIT_VALUE(v, 8)
+#define MSGDMA_CSR_STAT_IRQ_GET(v) GET_BIT_VALUE(v, 9)
+
+/* mSGDMA CSR control register bit definitions
+ */
+#define MSGDMA_CSR_CTL_STOP BIT(0)
+#define MSGDMA_CSR_CTL_RESET BIT(1)
+#define MSGDMA_CSR_CTL_STOP_ON_ERR BIT(2)
+#define MSGDMA_CSR_CTL_STOP_ON_EARLY BIT(3)
+#define MSGDMA_CSR_CTL_GLOBAL_INTR BIT(4)
+#define MSGDMA_CSR_CTL_STOP_DESCS BIT(5)
+
+/* mSGDMA CSR fill level bits
+ */
+#define MSGDMA_CSR_WR_FILL_LEVEL_GET(v) (((v) & 0xffff0000) >> 16)
+#define MSGDMA_CSR_RD_FILL_LEVEL_GET(v) ((v) & 0x0000ffff)
+#define MSGDMA_CSR_RESP_FILL_LEVEL_GET(v) ((v) & 0x0000ffff)
+
+/* mSGDMA response register map
+ */
+struct msgdma_response {
+ u32 bytes_transferred;
+ u32 status;
+};
+
+/* mSGDMA response register bit definitions
+ */
+#define MSGDMA_RESP_EARLY_TERM BIT(8)
+#define MSGDMA_RESP_ERR_MASK 0xFF
+
+#endif /* __ALTERA_MSGDMA_H__*/
diff --git a/drivers/net/ethernet/altera/altera_sgdma.c b/drivers/net/ethernet/altera/altera_sgdma.c
new file mode 100644
index 0000000..0ee9663
--- /dev/null
+++ b/drivers/net/ethernet/altera/altera_sgdma.c
@@ -0,0 +1,509 @@
+/* Altera TSE SGDMA and MSGDMA Linux driver
+ * Copyright (C) 2014 Altera Corporation. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/list.h>
+#include "altera_utils.h"
+#include "altera_tse.h"
+#include "altera_sgdmahw.h"
+#include "altera_sgdma.h"
+
+static void sgdma_descrip(struct sgdma_descrip *desc,
+ struct sgdma_descrip *ndesc,
+ dma_addr_t ndesc_phys,
+ dma_addr_t raddr,
+ dma_addr_t waddr,
+ u16 length,
+ int generate_eop,
+ int rfixed,
+ int wfixed);
+
+static int sgdma_async_write(struct altera_tse_private *priv,
+ struct sgdma_descrip *desc);
+
+static int sgdma_async_read(struct altera_tse_private *priv);
+
+static dma_addr_t
+sgdma_txphysaddr(struct altera_tse_private *priv,
+ struct sgdma_descrip *desc);
+
+static dma_addr_t
+sgdma_rxphysaddr(struct altera_tse_private *priv,
+ struct sgdma_descrip *desc);
+
+static int sgdma_txbusy(struct altera_tse_private *priv);
+
+static int sgdma_rxbusy(struct altera_tse_private *priv);
+
+static void
+queue_tx(struct altera_tse_private *priv, struct tse_buffer *buffer);
+
+static void
+queue_rx(struct altera_tse_private *priv, struct tse_buffer *buffer);
+
+static struct tse_buffer *
+dequeue_tx(struct altera_tse_private *priv);
+
+static struct tse_buffer *
+dequeue_rx(struct altera_tse_private *priv);
+
+static struct tse_buffer *
+queue_rx_peekhead(struct altera_tse_private *priv);
+
+int sgdma_initialize(struct altera_tse_private *priv)
+{
+ priv->txctrlreg = SGDMA_CTRLREG_ILASTD;
+
+ priv->rxctrlreg = SGDMA_CTRLREG_IDESCRIP |
+ SGDMA_CTRLREG_ILASTD;
+
+ INIT_LIST_HEAD(&priv->txlisthd);
+ INIT_LIST_HEAD(&priv->rxlisthd);
+
+ priv->rxdescphys = (dma_addr_t) 0;
+ priv->txdescphys = (dma_addr_t) 0;
+
+ priv->rxdescphys = dma_map_single(priv->device, priv->rx_dma_desc,
+ priv->rxdescmem, DMA_BIDIRECTIONAL);
+
+ if (dma_mapping_error(priv->device, priv->rxdescphys)) {
+ sgdma_uninitialize(priv);
+ netdev_err(priv->dev, "error mapping rx descriptor memory\n");
+ return -EINVAL;
+ }
+
+ priv->txdescphys = dma_map_single(priv->device, priv->tx_dma_desc,
+ priv->txdescmem, DMA_TO_DEVICE);
+
+ if (dma_mapping_error(priv->device, priv->txdescphys)) {
+ sgdma_uninitialize(priv);
+ netdev_err(priv->dev, "error mapping tx descriptor memory\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+void sgdma_uninitialize(struct altera_tse_private *priv)
+{
+ if (priv->rxdescphys)
+ dma_unmap_single(priv->device, priv->rxdescphys,
+ priv->rxdescmem, DMA_BIDIRECTIONAL);
+
+ if (priv->txdescphys)
+ dma_unmap_single(priv->device, priv->txdescphys,
+ priv->txdescmem, DMA_TO_DEVICE);
+}
+
+/* This function resets the SGDMA controller and clears the
+ * descriptor memory used for transmits and receives.
+ */
+void sgdma_reset(struct altera_tse_private *priv)
+{
+ u32 *ptxdescripmem = (u32 *)priv->tx_dma_desc;
+ u32 txdescriplen = priv->txdescmem;
+ u32 *prxdescripmem = (u32 *)priv->rx_dma_desc;
+ u32 rxdescriplen = priv->rxdescmem;
+ struct sgdma_csr *ptxsgdma = (struct sgdma_csr *)priv->tx_dma_csr;
+ struct sgdma_csr *prxsgdma = (struct sgdma_csr *)priv->rx_dma_csr;
+
+ /* Initialize descriptor memory to 0 */
+ memset(ptxdescripmem, 0, txdescriplen);
+ memset(prxdescripmem, 0, rxdescriplen);
+
+ iowrite32(SGDMA_CTRLREG_RESET, &ptxsgdma->control);
+ iowrite32(0, &ptxsgdma->control);
+
+ iowrite32(SGDMA_CTRLREG_RESET, &prxsgdma->control);
+ iowrite32(0, &prxsgdma->control);
+}
+
+void sgdma_enable_rxirq(struct altera_tse_private *priv)
+{
+ struct sgdma_csr *csr = (struct sgdma_csr *)priv->rx_dma_csr;
+ priv->rxctrlreg |= SGDMA_CTRLREG_INTEN;
+ tse_set_bit(&csr->control, SGDMA_CTRLREG_INTEN);
+}
+
+void sgdma_enable_txirq(struct altera_tse_private *priv)
+{
+ struct sgdma_csr *csr = (struct sgdma_csr *)priv->tx_dma_csr;
+ priv->txctrlreg |= SGDMA_CTRLREG_INTEN;
+ tse_set_bit(&csr->control, SGDMA_CTRLREG_INTEN);
+}
+
+/* for SGDMA, RX interrupts remain enabled after enabling */
+void sgdma_disable_rxirq(struct altera_tse_private *priv)
+{
+}
+
+/* for SGDMA, TX interrupts remain enabled after enabling */
+void sgdma_disable_txirq(struct altera_tse_private *priv)
+{
+}
+
+void sgdma_clear_rxirq(struct altera_tse_private *priv)
+{
+ struct sgdma_csr *csr = (struct sgdma_csr *)priv->rx_dma_csr;
+ tse_set_bit(&csr->control, SGDMA_CTRLREG_CLRINT);
+}
+
+void sgdma_clear_txirq(struct altera_tse_private *priv)
+{
+ struct sgdma_csr *csr = (struct sgdma_csr *)priv->tx_dma_csr;
+ tse_set_bit(&csr->control, SGDMA_CTRLREG_CLRINT);
+}
+
+/* transmits buffer through SGDMA. Returns number of buffers
+ * transmitted, 0 if not possible.
+ *
+ * tx_lock is held by the caller
+ */
+int sgdma_tx_buffer(struct altera_tse_private *priv, struct tse_buffer *buffer)
+{
+ int pktstx = 0;
+ struct sgdma_descrip *descbase =
+ (struct sgdma_descrip *)priv->tx_dma_desc;
+
+ struct sgdma_descrip *cdesc = &descbase[0];
+ struct sgdma_descrip *ndesc = &descbase[1];
+
+ /* wait 'til the tx sgdma is ready for the next transmit request */
+ if (sgdma_txbusy(priv))
+ return 0;
+
+ sgdma_descrip(cdesc, /* current descriptor */
+ ndesc, /* next descriptor */
+ sgdma_txphysaddr(priv, ndesc),
+ buffer->dma_addr, /* address of packet to xmit */
+ 0, /* write addr 0 for tx dma */
+ buffer->len, /* length of packet */
+ SGDMA_CONTROL_EOP, /* Generate EOP */
+ 0, /* read fixed */
+ SGDMA_CONTROL_WR_FIXED); /* Generate SOP */
+
+ pktstx = sgdma_async_write(priv, cdesc);
+
+ /* enqueue the request to the pending transmit queue */
+ queue_tx(priv, buffer);
+
+ return 1;
+}
+
+
+/* tx_lock held to protect access to queued tx list
+ */
+u32 sgdma_tx_completions(struct altera_tse_private *priv)
+{
+ u32 ready = 0;
+ struct sgdma_descrip *desc = (struct sgdma_descrip *)priv->tx_dma_desc;
+
+ if (!sgdma_txbusy(priv) &&
+ ((desc->control & SGDMA_CONTROL_HW_OWNED) == 0) &&
+ (dequeue_tx(priv))) {
+ ready = 1;
+ }
+
+ return ready;
+}
+
+int sgdma_add_rx_desc(struct altera_tse_private *priv,
+ struct tse_buffer *rxbuffer)
+{
+ queue_rx(priv, rxbuffer);
+ return sgdma_async_read(priv);
+}
+
+/* status is returned on upper 16 bits,
+ * length is returned in lower 16 bits
+ */
+u32 sgdma_rx_status(struct altera_tse_private *priv)
+{
+ struct sgdma_csr *csr = (struct sgdma_csr *)priv->rx_dma_csr;
+ struct sgdma_descrip *base = (struct sgdma_descrip *)priv->rx_dma_desc;
+ struct sgdma_descrip *desc = NULL;
+ int pktsrx;
+ unsigned int rxstatus = 0;
+ unsigned int pktlength = 0;
+ unsigned int pktstatus = 0;
+ struct tse_buffer *rxbuffer = NULL;
+
+ dma_sync_single_for_cpu(priv->device,
+ priv->rxdescphys,
+ priv->rxdescmem,
+ DMA_BIDIRECTIONAL);
+
+ desc = &base[0];
+ if ((ioread32(&csr->status) & SGDMA_STSREG_EOP) ||
+ (desc->status & SGDMA_STATUS_EOP)) {
+ pktlength = desc->bytes_xferred;
+ pktstatus = desc->status & 0x3f;
+ rxstatus = pktstatus;
+ rxstatus = rxstatus << 16;
+ rxstatus |= (pktlength & 0xffff);
+
+ desc->status = 0;
+
+ rxbuffer = dequeue_rx(priv);
+ if (rxbuffer == NULL)
+ netdev_err(priv->dev,
+ "sgdma rx and rx queue empty!\n");
+
+ /* kick the rx sgdma after reaping this descriptor */
+ pktsrx = sgdma_async_read(priv);
+ }
+
+ return rxstatus;
+}
+
+
+/* Private functions */
+static void sgdma_descrip(struct sgdma_descrip *desc,
+ struct sgdma_descrip *ndesc,
+ dma_addr_t ndesc_phys,
+ dma_addr_t raddr,
+ dma_addr_t waddr,
+ u16 length,
+ int generate_eop,
+ int rfixed,
+ int wfixed)
+{
+ /* Clear the next descriptor as not owned by hardware */
+ u32 ctrl = ndesc->control;
+ ctrl &= ~SGDMA_CONTROL_HW_OWNED;
+ ndesc->control = ctrl;
+
+ ctrl = 0;
+ ctrl = SGDMA_CONTROL_HW_OWNED;
+ ctrl |= generate_eop;
+ ctrl |= rfixed;
+ ctrl |= wfixed;
+
+ /* Channel is implicitly zero, initialized to 0 by default */
+
+ desc->raddr = raddr;
+ desc->waddr = waddr;
+ desc->next = lower_32_bits(ndesc_phys);
+ desc->control = ctrl;
+ desc->status = 0;
+ desc->rburst = 0;
+ desc->wburst = 0;
+ desc->bytes = length;
+ desc->bytes_xferred = 0;
+}
+
+/* If hardware is busy, don't restart async read.
+ * if status register is 0 - meaning initial state, restart async read,
+ * probably for the first time when populating a receive buffer.
+ * If read status indicate not busy and a status, restart the async
+ * DMA read.
+ */
+static int sgdma_async_read(struct altera_tse_private *priv)
+{
+ struct sgdma_csr *csr = (struct sgdma_csr *)priv->rx_dma_csr;
+ struct sgdma_descrip *descbase =
+ (struct sgdma_descrip *)priv->rx_dma_desc;
+
+ struct sgdma_descrip *cdesc = &descbase[0];
+ struct sgdma_descrip *ndesc = &descbase[1];
+
+ unsigned int sts = ioread32(&csr->status);
+ struct tse_buffer *rxbuffer = NULL;
+
+ if (!sgdma_rxbusy(priv)) {
+ rxbuffer = queue_rx_peekhead(priv);
+ if (rxbuffer == NULL)
+ return 0;
+
+ sgdma_descrip(cdesc, /* current descriptor */
+ ndesc, /* next descriptor */
+ sgdma_rxphysaddr(priv, ndesc),
+ 0, /* read addr 0 for rx dma */
+ rxbuffer->dma_addr, /* write addr for rx dma */
+ 0, /* read 'til EOP */
+ 0, /* EOP: NA for rx dma */
+ 0, /* read fixed: NA for rx dma */
+ 0); /* SOP: NA for rx DMA */
+
+ /* clear control and status */
+ iowrite32(0, &csr->control);
+
+ /* If status available, clear those bits */
+ if (sts & 0xf)
+ iowrite32(0xf, &csr->status);
+
+ dma_sync_single_for_device(priv->device,
+ priv->rxdescphys,
+ priv->rxdescmem,
+ DMA_BIDIRECTIONAL);
+
+ iowrite32(lower_32_bits(sgdma_rxphysaddr(priv, cdesc)),
+ &csr->next_descrip);
+
+ iowrite32((priv->rxctrlreg | SGDMA_CTRLREG_START),
+ &csr->control);
+
+ return 1;
+ }
+
+ return 0;
+}
+
+static int sgdma_async_write(struct altera_tse_private *priv,
+ struct sgdma_descrip *desc)
+{
+ struct sgdma_csr *csr = (struct sgdma_csr *)priv->tx_dma_csr;
+
+ if (sgdma_txbusy(priv))
+ return 0;
+
+ /* clear control and status */
+ iowrite32(0, &csr->control);
+ iowrite32(0x1f, &csr->status);
+
+ dma_sync_single_for_device(priv->device, priv->txdescphys,
+ priv->txdescmem, DMA_TO_DEVICE);
+
+ iowrite32(lower_32_bits(sgdma_txphysaddr(priv, desc)),
+ &csr->next_descrip);
+
+ iowrite32((priv->txctrlreg | SGDMA_CTRLREG_START),
+ &csr->control);
+
+ return 1;
+}
+
+static dma_addr_t
+sgdma_txphysaddr(struct altera_tse_private *priv,
+ struct sgdma_descrip *desc)
+{
+ dma_addr_t paddr = priv->txdescmem_busaddr;
+ uintptr_t offs = (uintptr_t)desc - (uintptr_t)priv->tx_dma_desc;
+ return (dma_addr_t)((uintptr_t)paddr + offs);
+}
+
+static dma_addr_t
+sgdma_rxphysaddr(struct altera_tse_private *priv,
+ struct sgdma_descrip *desc)
+{
+ dma_addr_t paddr = priv->rxdescmem_busaddr;
+ uintptr_t offs = (uintptr_t)desc - (uintptr_t)priv->rx_dma_desc;
+ return (dma_addr_t)((uintptr_t)paddr + offs);
+}
+
+#define list_remove_head(list, entry, type, member) \
+ do { \
+ entry = NULL; \
+ if (!list_empty(list)) { \
+ entry = list_entry((list)->next, type, member); \
+ list_del_init(&entry->member); \
+ } \
+ } while (0)
+
+#define list_peek_head(list, entry, type, member) \
+ do { \
+ entry = NULL; \
+ if (!list_empty(list)) { \
+ entry = list_entry((list)->next, type, member); \
+ } \
+ } while (0)
+
+/* adds a tse_buffer to the tail of a tx buffer list.
+ * assumes the caller is managing and holding a mutual exclusion
+ * primitive to avoid simultaneous pushes/pops to the list.
+ */
+static void
+queue_tx(struct altera_tse_private *priv, struct tse_buffer *buffer)
+{
+ list_add_tail(&buffer->lh, &priv->txlisthd);
+}
+
+
+/* adds a tse_buffer to the tail of a rx buffer list
+ * assumes the caller is managing and holding a mutual exclusion
+ * primitive to avoid simultaneous pushes/pops to the list.
+ */
+static void
+queue_rx(struct altera_tse_private *priv, struct tse_buffer *buffer)
+{
+ list_add_tail(&buffer->lh, &priv->rxlisthd);
+}
+
+/* dequeues a tse_buffer from the transmit buffer list, otherwise
+ * returns NULL if empty.
+ * assumes the caller is managing and holding a mutual exclusion
+ * primitive to avoid simultaneous pushes/pops to the list.
+ */
+static struct tse_buffer *
+dequeue_tx(struct altera_tse_private *priv)
+{
+ struct tse_buffer *buffer = NULL;
+ list_remove_head(&priv->txlisthd, buffer, struct tse_buffer, lh);
+ return buffer;
+}
+
+/* dequeues a tse_buffer from the receive buffer list, otherwise
+ * returns NULL if empty
+ * assumes the caller is managing and holding a mutual exclusion
+ * primitive to avoid simultaneous pushes/pops to the list.
+ */
+static struct tse_buffer *
+dequeue_rx(struct altera_tse_private *priv)
+{
+ struct tse_buffer *buffer = NULL;
+ list_remove_head(&priv->rxlisthd, buffer, struct tse_buffer, lh);
+ return buffer;
+}
+
+/* dequeues a tse_buffer from the receive buffer list, otherwise
+ * returns NULL if empty
+ * assumes the caller is managing and holding a mutual exclusion
+ * primitive to avoid simultaneous pushes/pops to the list while the
+ * head is being examined.
+ */
+static struct tse_buffer *
+queue_rx_peekhead(struct altera_tse_private *priv)
+{
+ struct tse_buffer *buffer = NULL;
+ list_peek_head(&priv->rxlisthd, buffer, struct tse_buffer, lh);
+ return buffer;
+}
+
+/* check and return rx sgdma status without polling
+ */
+static int sgdma_rxbusy(struct altera_tse_private *priv)
+{
+ struct sgdma_csr *csr = (struct sgdma_csr *)priv->rx_dma_csr;
+ return ioread32(&csr->status) & SGDMA_STSREG_BUSY;
+}
+
+/* waits for the tx sgdma to finish it's current operation, returns 0
+ * when it transitions to nonbusy, returns 1 if the operation times out
+ */
+static int sgdma_txbusy(struct altera_tse_private *priv)
+{
+ int delay = 0;
+ struct sgdma_csr *csr = (struct sgdma_csr *)priv->tx_dma_csr;
+
+ /* if DMA is busy, wait for current transactino to finish */
+ while ((ioread32(&csr->status) & SGDMA_STSREG_BUSY) && (delay++ < 100))
+ udelay(1);
+
+ if (ioread32(&csr->status) & SGDMA_STSREG_BUSY) {
+ netdev_err(priv->dev, "timeout waiting for tx dma\n");
+ return 1;
+ }
+ return 0;
+}
diff --git a/drivers/net/ethernet/altera/altera_sgdma.h b/drivers/net/ethernet/altera/altera_sgdma.h
new file mode 100644
index 0000000..07d4717
--- /dev/null
+++ b/drivers/net/ethernet/altera/altera_sgdma.h
@@ -0,0 +1,35 @@
+/* Altera TSE SGDMA and MSGDMA Linux driver
+ * Copyright (C) 2014 Altera Corporation. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ALTERA_SGDMA_H__
+#define __ALTERA_SGDMA_H__
+
+void sgdma_reset(struct altera_tse_private *);
+void sgdma_enable_txirq(struct altera_tse_private *);
+void sgdma_enable_rxirq(struct altera_tse_private *);
+void sgdma_disable_rxirq(struct altera_tse_private *);
+void sgdma_disable_txirq(struct altera_tse_private *);
+void sgdma_clear_rxirq(struct altera_tse_private *);
+void sgdma_clear_txirq(struct altera_tse_private *);
+int sgdma_tx_buffer(struct altera_tse_private *priv, struct tse_buffer *);
+u32 sgdma_tx_completions(struct altera_tse_private *);
+int sgdma_add_rx_desc(struct altera_tse_private *priv, struct tse_buffer *);
+void sgdma_status(struct altera_tse_private *);
+u32 sgdma_rx_status(struct altera_tse_private *);
+int sgdma_initialize(struct altera_tse_private *);
+void sgdma_uninitialize(struct altera_tse_private *);
+
+#endif /* __ALTERA_SGDMA_H__ */
diff --git a/drivers/net/ethernet/altera/altera_sgdmahw.h b/drivers/net/ethernet/altera/altera_sgdmahw.h
new file mode 100644
index 0000000..ba3334f
--- /dev/null
+++ b/drivers/net/ethernet/altera/altera_sgdmahw.h
@@ -0,0 +1,124 @@
+/* Altera TSE SGDMA and MSGDMA Linux driver
+ * Copyright (C) 2014 Altera Corporation. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ALTERA_SGDMAHW_H__
+#define __ALTERA_SGDMAHW_H__
+
+/* SGDMA descriptor structure */
+struct sgdma_descrip {
+ unsigned int raddr; /* address of data to be read */
+ unsigned int pad1;
+ unsigned int waddr;
+ unsigned int pad2;
+ unsigned int next;
+ unsigned int pad3;
+ unsigned short bytes;
+ unsigned char rburst;
+ unsigned char wburst;
+ unsigned short bytes_xferred; /* 16 bits, bytes xferred */
+
+ /* bit 0: error
+ * bit 1: length error
+ * bit 2: crc error
+ * bit 3: truncated error
+ * bit 4: phy error
+ * bit 5: collision error
+ * bit 6: reserved
+ * bit 7: status eop for recv case
+ */
+ unsigned char status;
+
+ /* bit 0: eop
+ * bit 1: read_fixed
+ * bit 2: write fixed
+ * bits 3,4,5,6: Channel (always 0)
+ * bit 7: hardware owned
+ */
+ unsigned char control;
+} __packed;
+
+
+#define SGDMA_STATUS_ERR BIT(0)
+#define SGDMA_STATUS_LENGTH_ERR BIT(1)
+#define SGDMA_STATUS_CRC_ERR BIT(2)
+#define SGDMA_STATUS_TRUNC_ERR BIT(3)
+#define SGDMA_STATUS_PHY_ERR BIT(4)
+#define SGDMA_STATUS_COLL_ERR BIT(5)
+#define SGDMA_STATUS_EOP BIT(7)
+
+#define SGDMA_CONTROL_EOP BIT(0)
+#define SGDMA_CONTROL_RD_FIXED BIT(1)
+#define SGDMA_CONTROL_WR_FIXED BIT(2)
+
+/* Channel is always 0, so just zero initialize it */
+
+#define SGDMA_CONTROL_HW_OWNED BIT(7)
+
+/* SGDMA register space */
+struct sgdma_csr {
+ /* bit 0: error
+ * bit 1: eop
+ * bit 2: descriptor completed
+ * bit 3: chain completed
+ * bit 4: busy
+ * remainder reserved
+ */
+ u32 status;
+ u32 pad1[3];
+
+ /* bit 0: interrupt on error
+ * bit 1: interrupt on eop
+ * bit 2: interrupt after every descriptor
+ * bit 3: interrupt after last descrip in a chain
+ * bit 4: global interrupt enable
+ * bit 5: starts descriptor processing
+ * bit 6: stop core on dma error
+ * bit 7: interrupt on max descriptors
+ * bits 8-15: max descriptors to generate interrupt
+ * bit 16: Software reset
+ * bit 17: clears owned by hardware if 0, does not clear otherwise
+ * bit 18: enables descriptor polling mode
+ * bit 19-26: clocks before polling again
+ * bit 27-30: reserved
+ * bit 31: clear interrupt
+ */
+ u32 control;
+ u32 pad2[3];
+ u32 next_descrip;
+ u32 pad3[3];
+};
+
+
+#define SGDMA_STSREG_ERR BIT(0) /* Error */
+#define SGDMA_STSREG_EOP BIT(1) /* EOP */
+#define SGDMA_STSREG_DESCRIP BIT(2) /* Descriptor completed */
+#define SGDMA_STSREG_CHAIN BIT(3) /* Chain completed */
+#define SGDMA_STSREG_BUSY BIT(4) /* Controller busy */
+
+#define SGDMA_CTRLREG_IOE BIT(0) /* Interrupt on error */
+#define SGDMA_CTRLREG_IOEOP BIT(1) /* Interrupt on EOP */
+#define SGDMA_CTRLREG_IDESCRIP BIT(2) /* Interrupt after every descriptor */
+#define SGDMA_CTRLREG_ILASTD BIT(3) /* Interrupt after last descriptor */
+#define SGDMA_CTRLREG_INTEN BIT(4) /* Global Interrupt enable */
+#define SGDMA_CTRLREG_START BIT(5) /* starts descriptor processing */
+#define SGDMA_CTRLREG_STOPERR BIT(6) /* stop on dma error */
+#define SGDMA_CTRLREG_INTMAX BIT(7) /* Interrupt on max descriptors */
+#define SGDMA_CTRLREG_RESET BIT(16)/* Software reset */
+#define SGDMA_CTRLREG_COBHW BIT(17)/* Clears owned by hardware */
+#define SGDMA_CTRLREG_POLL BIT(18)/* enables descriptor polling mode */
+#define SGDMA_CTRLREG_CLRINT BIT(31)/* Clears interrupt */
+
+#endif /* __ALTERA_SGDMAHW_H__ */
diff --git a/drivers/net/ethernet/altera/altera_tse.h b/drivers/net/ethernet/altera/altera_tse.h
new file mode 100644
index 0000000..8feeed0
--- /dev/null
+++ b/drivers/net/ethernet/altera/altera_tse.h
@@ -0,0 +1,486 @@
+/* Altera Triple-Speed Ethernet MAC driver
+ * Copyright (C) 2008-2014 Altera Corporation. All rights reserved
+ *
+ * Contributors:
+ * Dalon Westergreen
+ * Thomas Chou
+ * Ian Abbott
+ * Yuriy Kozlov
+ * Tobias Klauser
+ * Andriy Smolskyy
+ * Roman Bulgakov
+ * Dmytro Mytarchuk
+ * Matthew Gerlach
+ *
+ * Original driver contributed by SLS.
+ * Major updates contributed by GlobalLogic
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ALTERA_TSE_H__
+#define __ALTERA_TSE_H__
+
+#define ALTERA_TSE_RESOURCE_NAME "altera_tse"
+
+#include <linux/bitops.h>
+#include <linux/if_vlan.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+
+#define ALTERA_TSE_SW_RESET_WATCHDOG_CNTR 10000
+#define ALTERA_TSE_MAC_FIFO_WIDTH 4 /* TX/RX FIFO width in
+ * bytes
+ */
+/* Rx FIFO default settings */
+#define ALTERA_TSE_RX_SECTION_EMPTY 16
+#define ALTERA_TSE_RX_SECTION_FULL 0
+#define ALTERA_TSE_RX_ALMOST_EMPTY 8
+#define ALTERA_TSE_RX_ALMOST_FULL 8
+
+/* Tx FIFO default settings */
+#define ALTERA_TSE_TX_SECTION_EMPTY 16
+#define ALTERA_TSE_TX_SECTION_FULL 0
+#define ALTERA_TSE_TX_ALMOST_EMPTY 8
+#define ALTERA_TSE_TX_ALMOST_FULL 3
+
+/* MAC function configuration default settings */
+#define ALTERA_TSE_TX_IPG_LENGTH 12
+
+#define GET_BIT_VALUE(v, bit) (((v) >> (bit)) & 0x1)
+
+/* MAC Command_Config Register Bit Definitions
+ */
+#define MAC_CMDCFG_TX_ENA BIT(0)
+#define MAC_CMDCFG_RX_ENA BIT(1)
+#define MAC_CMDCFG_XON_GEN BIT(2)
+#define MAC_CMDCFG_ETH_SPEED BIT(3)
+#define MAC_CMDCFG_PROMIS_EN BIT(4)
+#define MAC_CMDCFG_PAD_EN BIT(5)
+#define MAC_CMDCFG_CRC_FWD BIT(6)
+#define MAC_CMDCFG_PAUSE_FWD BIT(7)
+#define MAC_CMDCFG_PAUSE_IGNORE BIT(8)
+#define MAC_CMDCFG_TX_ADDR_INS BIT(9)
+#define MAC_CMDCFG_HD_ENA BIT(10)
+#define MAC_CMDCFG_EXCESS_COL BIT(11)
+#define MAC_CMDCFG_LATE_COL BIT(12)
+#define MAC_CMDCFG_SW_RESET BIT(13)
+#define MAC_CMDCFG_MHASH_SEL BIT(14)
+#define MAC_CMDCFG_LOOP_ENA BIT(15)
+#define MAC_CMDCFG_TX_ADDR_SEL(v) (((v) & 0x7) << 16)
+#define MAC_CMDCFG_MAGIC_ENA BIT(19)
+#define MAC_CMDCFG_SLEEP BIT(20)
+#define MAC_CMDCFG_WAKEUP BIT(21)
+#define MAC_CMDCFG_XOFF_GEN BIT(22)
+#define MAC_CMDCFG_CNTL_FRM_ENA BIT(23)
+#define MAC_CMDCFG_NO_LGTH_CHECK BIT(24)
+#define MAC_CMDCFG_ENA_10 BIT(25)
+#define MAC_CMDCFG_RX_ERR_DISC BIT(26)
+#define MAC_CMDCFG_DISABLE_READ_TIMEOUT BIT(27)
+#define MAC_CMDCFG_CNT_RESET BIT(31)
+
+#define MAC_CMDCFG_TX_ENA_GET(v) GET_BIT_VALUE(v, 0)
+#define MAC_CMDCFG_RX_ENA_GET(v) GET_BIT_VALUE(v, 1)
+#define MAC_CMDCFG_XON_GEN_GET(v) GET_BIT_VALUE(v, 2)
+#define MAC_CMDCFG_ETH_SPEED_GET(v) GET_BIT_VALUE(v, 3)
+#define MAC_CMDCFG_PROMIS_EN_GET(v) GET_BIT_VALUE(v, 4)
+#define MAC_CMDCFG_PAD_EN_GET(v) GET_BIT_VALUE(v, 5)
+#define MAC_CMDCFG_CRC_FWD_GET(v) GET_BIT_VALUE(v, 6)
+#define MAC_CMDCFG_PAUSE_FWD_GET(v) GET_BIT_VALUE(v, 7)
+#define MAC_CMDCFG_PAUSE_IGNORE_GET(v) GET_BIT_VALUE(v, 8)
+#define MAC_CMDCFG_TX_ADDR_INS_GET(v) GET_BIT_VALUE(v, 9)
+#define MAC_CMDCFG_HD_ENA_GET(v) GET_BIT_VALUE(v, 10)
+#define MAC_CMDCFG_EXCESS_COL_GET(v) GET_BIT_VALUE(v, 11)
+#define MAC_CMDCFG_LATE_COL_GET(v) GET_BIT_VALUE(v, 12)
+#define MAC_CMDCFG_SW_RESET_GET(v) GET_BIT_VALUE(v, 13)
+#define MAC_CMDCFG_MHASH_SEL_GET(v) GET_BIT_VALUE(v, 14)
+#define MAC_CMDCFG_LOOP_ENA_GET(v) GET_BIT_VALUE(v, 15)
+#define MAC_CMDCFG_TX_ADDR_SEL_GET(v) (((v) >> 16) & 0x7)
+#define MAC_CMDCFG_MAGIC_ENA_GET(v) GET_BIT_VALUE(v, 19)
+#define MAC_CMDCFG_SLEEP_GET(v) GET_BIT_VALUE(v, 20)
+#define MAC_CMDCFG_WAKEUP_GET(v) GET_BIT_VALUE(v, 21)
+#define MAC_CMDCFG_XOFF_GEN_GET(v) GET_BIT_VALUE(v, 22)
+#define MAC_CMDCFG_CNTL_FRM_ENA_GET(v) GET_BIT_VALUE(v, 23)
+#define MAC_CMDCFG_NO_LGTH_CHECK_GET(v) GET_BIT_VALUE(v, 24)
+#define MAC_CMDCFG_ENA_10_GET(v) GET_BIT_VALUE(v, 25)
+#define MAC_CMDCFG_RX_ERR_DISC_GET(v) GET_BIT_VALUE(v, 26)
+#define MAC_CMDCFG_DISABLE_READ_TIMEOUT_GET(v) GET_BIT_VALUE(v, 27)
+#define MAC_CMDCFG_CNT_RESET_GET(v) GET_BIT_VALUE(v, 31)
+
+/* MDIO registers within MAC register Space
+ */
+struct altera_tse_mdio {
+ u32 control; /* PHY device operation control register */
+ u32 status; /* PHY device operation status register */
+ u32 phy_id1; /* Bits 31:16 of PHY identifier */
+ u32 phy_id2; /* Bits 15:0 of PHY identifier */
+ u32 auto_negotiation_advertisement; /* Auto-negotiation
+ * advertisement
+ * register
+ */
+ u32 remote_partner_base_page_ability;
+
+ u32 reg6;
+ u32 reg7;
+ u32 reg8;
+ u32 reg9;
+ u32 rega;
+ u32 regb;
+ u32 regc;
+ u32 regd;
+ u32 rege;
+ u32 regf;
+ u32 reg10;
+ u32 reg11;
+ u32 reg12;
+ u32 reg13;
+ u32 reg14;
+ u32 reg15;
+ u32 reg16;
+ u32 reg17;
+ u32 reg18;
+ u32 reg19;
+ u32 reg1a;
+ u32 reg1b;
+ u32 reg1c;
+ u32 reg1d;
+ u32 reg1e;
+ u32 reg1f;
+};
+
+/* MAC register Space. Note that some of these registers may or may not be
+ * present depending upon options chosen by the user when the core was
+ * configured and built. Please consult the Altera Triple Speed Ethernet User
+ * Guide for details.
+ */
+struct altera_tse_mac {
+ /* Bits 15:0: MegaCore function revision (0x0800). Bit 31:16: Customer
+ * specific revision
+ */
+ u32 megacore_revision;
+ /* Provides a memory location for user applications to test the device
+ * memory operation.
+ */
+ u32 scratch_pad;
+ /* The host processor uses this register to control and configure the
+ * MAC block
+ */
+ u32 command_config;
+ /* 32-bit primary MAC address word 0 bits 0 to 31 of the primary
+ * MAC address
+ */
+ u32 mac_addr_0;
+ /* 32-bit primary MAC address word 1 bits 32 to 47 of the primary
+ * MAC address
+ */
+ u32 mac_addr_1;
+ /* 14-bit maximum frame length. The MAC receive logic */
+ u32 frm_length;
+ /* The pause quanta is used in each pause frame sent to a remote
+ * Ethernet device, in increments of 512 Ethernet bit times
+ */
+ u32 pause_quanta;
+ /* 12-bit receive FIFO section-empty threshold */
+ u32 rx_section_empty;
+ /* 12-bit receive FIFO section-full threshold */
+ u32 rx_section_full;
+ /* 12-bit transmit FIFO section-empty threshold */
+ u32 tx_section_empty;
+ /* 12-bit transmit FIFO section-full threshold */
+ u32 tx_section_full;
+ /* 12-bit receive FIFO almost-empty threshold */
+ u32 rx_almost_empty;
+ /* 12-bit receive FIFO almost-full threshold */
+ u32 rx_almost_full;
+ /* 12-bit transmit FIFO almost-empty threshold */
+ u32 tx_almost_empty;
+ /* 12-bit transmit FIFO almost-full threshold */
+ u32 tx_almost_full;
+ /* MDIO address of PHY Device 0. Bits 0 to 4 hold a 5-bit PHY address */
+ u32 mdio_phy0_addr;
+ /* MDIO address of PHY Device 1. Bits 0 to 4 hold a 5-bit PHY address */
+ u32 mdio_phy1_addr;
+
+ /* Bit[15:0]—16-bit holdoff quanta */
+ u32 holdoff_quant;
+
+ /* only if 100/1000 BaseX PCS, reserved otherwise */
+ u32 reserved1[5];
+
+ /* Minimum IPG between consecutive transmit frame in terms of bytes */
+ u32 tx_ipg_length;
+
+ /* IEEE 802.3 oEntity Managed Object Support */
+
+ /* The MAC addresses */
+ u32 mac_id_1;
+ u32 mac_id_2;
+
+ /* Number of frames transmitted without error including pause frames */
+ u32 frames_transmitted_ok;
+ /* Number of frames received without error including pause frames */
+ u32 frames_received_ok;
+ /* Number of frames received with a CRC error */
+ u32 frames_check_sequence_errors;
+ /* Frame received with an alignment error */
+ u32 alignment_errors;
+ /* Sum of payload and padding octets of frames transmitted without
+ * error
+ */
+ u32 octets_transmitted_ok;
+ /* Sum of payload and padding octets of frames received without error */
+ u32 octets_received_ok;
+
+ /* IEEE 802.3 oPausedEntity Managed Object Support */
+
+ /* Number of transmitted pause frames */
+ u32 tx_pause_mac_ctrl_frames;
+ /* Number of Received pause frames */
+ u32 rx_pause_mac_ctrl_frames;
+
+ /* IETF MIB (MIB-II) Object Support */
+
+ /* Number of frames received with error */
+ u32 if_in_errors;
+ /* Number of frames transmitted with error */
+ u32 if_out_errors;
+ /* Number of valid received unicast frames */
+ u32 if_in_ucast_pkts;
+ /* Number of valid received multicasts frames (without pause) */
+ u32 if_in_multicast_pkts;
+ /* Number of valid received broadcast frames */
+ u32 if_in_broadcast_pkts;
+ u32 if_out_discards;
+ /* The number of valid unicast frames transmitted */
+ u32 if_out_ucast_pkts;
+ /* The number of valid multicast frames transmitted,
+ * excluding pause frames
+ */
+ u32 if_out_multicast_pkts;
+ u32 if_out_broadcast_pkts;
+
+ /* IETF RMON MIB Object Support */
+
+ /* Counts the number of dropped packets due to internal errors
+ * of the MAC client.
+ */
+ u32 ether_stats_drop_events;
+ /* Total number of bytes received. Good and bad frames. */
+ u32 ether_stats_octets;
+ /* Total number of packets received. Counts good and bad packets. */
+ u32 ether_stats_pkts;
+ /* Number of packets received with less than 64 bytes. */
+ u32 ether_stats_undersize_pkts;
+ /* The number of frames received that are longer than the
+ * value configured in the frm_length register
+ */
+ u32 ether_stats_oversize_pkts;
+ /* Number of received packet with 64 bytes */
+ u32 ether_stats_pkts_64_octets;
+ /* Frames (good and bad) with 65 to 127 bytes */
+ u32 ether_stats_pkts_65to127_octets;
+ /* Frames (good and bad) with 128 to 255 bytes */
+ u32 ether_stats_pkts_128to255_octets;
+ /* Frames (good and bad) with 256 to 511 bytes */
+ u32 ether_stats_pkts_256to511_octets;
+ /* Frames (good and bad) with 512 to 1023 bytes */
+ u32 ether_stats_pkts_512to1023_octets;
+ /* Frames (good and bad) with 1024 to 1518 bytes */
+ u32 ether_stats_pkts_1024to1518_octets;
+
+ /* Any frame length from 1519 to the maximum length configured in the
+ * frm_length register, if it is greater than 1518
+ */
+ u32 ether_stats_pkts_1519tox_octets;
+ /* Too long frames with CRC error */
+ u32 ether_stats_jabbers;
+ /* Too short frames with CRC error */
+ u32 ether_stats_fragments;
+
+ u32 reserved2;
+
+ /* FIFO control register */
+ u32 tx_cmd_stat;
+ u32 rx_cmd_stat;
+
+ /* Extended Statistics Counters */
+ u32 msb_octets_transmitted_ok;
+ u32 msb_octets_received_ok;
+ u32 msb_ether_stats_octets;
+
+ u32 reserved3;
+
+ /* Multicast address resolution table, mapped in the controller address
+ * space
+ */
+ u32 hash_table[64];
+
+ /* Registers 0 to 31 within PHY device 0/1 connected to the MDIO PHY
+ * management interface
+ */
+ struct altera_tse_mdio mdio_phy0;
+ struct altera_tse_mdio mdio_phy1;
+
+ /* 4 Supplemental MAC Addresses */
+ u32 supp_mac_addr_0_0;
+ u32 supp_mac_addr_0_1;
+ u32 supp_mac_addr_1_0;
+ u32 supp_mac_addr_1_1;
+ u32 supp_mac_addr_2_0;
+ u32 supp_mac_addr_2_1;
+ u32 supp_mac_addr_3_0;
+ u32 supp_mac_addr_3_1;
+
+ u32 reserved4[8];
+
+ /* IEEE 1588v2 Feature */
+ u32 tx_period;
+ u32 tx_adjust_fns;
+ u32 tx_adjust_ns;
+ u32 rx_period;
+ u32 rx_adjust_fns;
+ u32 rx_adjust_ns;
+
+ u32 reserved5[42];
+};
+
+/* Transmit and Receive Command Registers Bit Definitions
+ */
+#define ALTERA_TSE_TX_CMD_STAT_OMIT_CRC BIT(17)
+#define ALTERA_TSE_TX_CMD_STAT_TX_SHIFT16 BIT(18)
+#define ALTERA_TSE_RX_CMD_STAT_RX_SHIFT16 BIT(25)
+
+/* Wrapper around a pointer to a socket buffer,
+ * so a DMA handle can be stored along with the buffer
+ */
+struct tse_buffer {
+ struct list_head lh;
+ struct sk_buff *skb;
+ dma_addr_t dma_addr;
+ u32 len;
+ int mapped_as_page;
+};
+
+struct altera_tse_private;
+
+#define ALTERA_DTYPE_SGDMA 1
+#define ALTERA_DTYPE_MSGDMA 2
+
+/* standard DMA interface for SGDMA and MSGDMA */
+struct altera_dmaops {
+ int altera_dtype;
+ int dmamask;
+ void (*reset_dma)(struct altera_tse_private *);
+ void (*enable_txirq)(struct altera_tse_private *);
+ void (*enable_rxirq)(struct altera_tse_private *);
+ void (*disable_txirq)(struct altera_tse_private *);
+ void (*disable_rxirq)(struct altera_tse_private *);
+ void (*clear_txirq)(struct altera_tse_private *);
+ void (*clear_rxirq)(struct altera_tse_private *);
+ int (*tx_buffer)(struct altera_tse_private *, struct tse_buffer *);
+ u32 (*tx_completions)(struct altera_tse_private *);
+ int (*add_rx_desc)(struct altera_tse_private *, struct tse_buffer *);
+ u32 (*get_rx_status)(struct altera_tse_private *);
+ int (*init_dma)(struct altera_tse_private *);
+ void (*uninit_dma)(struct altera_tse_private *);
+};
+
+/* This structure is private to each device.
+ */
+struct altera_tse_private {
+ struct net_device *dev;
+ struct device *device;
+ struct napi_struct napi;
+
+ /* MAC address space */
+ struct altera_tse_mac __iomem *mac_dev;
+
+ /* TSE Revision */
+ u32 revision;
+
+ /* mSGDMA Rx Dispatcher address space */
+ void __iomem *rx_dma_csr;
+ void __iomem *rx_dma_desc;
+ void __iomem *rx_dma_resp;
+
+ /* mSGDMA Tx Dispatcher address space */
+ void __iomem *tx_dma_csr;
+ void __iomem *tx_dma_desc;
+
+ /* Rx buffers queue */
+ struct tse_buffer *rx_ring;
+ u32 rx_cons;
+ u32 rx_prod;
+ u32 rx_ring_size;
+ u32 rx_dma_buf_sz;
+
+ /* Tx ring buffer */
+ struct tse_buffer *tx_ring;
+ u32 tx_prod;
+ u32 tx_cons;
+ u32 tx_ring_size;
+
+ /* Interrupts */
+ u32 tx_irq;
+ u32 rx_irq;
+
+ /* RX/TX MAC FIFO configs */
+ u32 tx_fifo_depth;
+ u32 rx_fifo_depth;
+ u32 max_mtu;
+
+ /* Hash filter settings */
+ u32 hash_filter;
+ u32 added_unicast;
+
+ /* Descriptor memory info for managing SGDMA */
+ u32 txdescmem;
+ u32 rxdescmem;
+ dma_addr_t rxdescmem_busaddr;
+ dma_addr_t txdescmem_busaddr;
+ u32 txctrlreg;
+ u32 rxctrlreg;
+ dma_addr_t rxdescphys;
+ dma_addr_t txdescphys;
+
+ struct list_head txlisthd;
+ struct list_head rxlisthd;
+
+ /* MAC command_config register protection */
+ spinlock_t mac_cfg_lock;
+ /* Tx path protection */
+ spinlock_t tx_lock;
+ /* Rx DMA & interrupt control protection */
+ spinlock_t rxdma_irq_lock;
+
+ /* PHY */
+ int phy_addr; /* PHY's MDIO address, -1 for autodetection */
+ phy_interface_t phy_iface;
+ struct mii_bus *mdio;
+ struct phy_device *phydev;
+ int oldspeed;
+ int oldduplex;
+ int oldlink;
+
+ /* ethtool msglvl option */
+ u32 msg_enable;
+
+ struct altera_dmaops *dmaops;
+};
+
+/* Function prototypes
+ */
+void altera_tse_set_ethtool_ops(struct net_device *);
+
+#endif /* __ALTERA_TSE_H__ */
diff --git a/drivers/net/ethernet/altera/altera_tse_ethtool.c b/drivers/net/ethernet/altera/altera_tse_ethtool.c
new file mode 100644
index 0000000..319ca74
--- /dev/null
+++ b/drivers/net/ethernet/altera/altera_tse_ethtool.c
@@ -0,0 +1,235 @@
+/* Ethtool support for Altera Triple-Speed Ethernet MAC driver
+ * Copyright (C) 2008-2014 Altera Corporation. All rights reserved
+ *
+ * Contributors:
+ * Dalon Westergreen
+ * Thomas Chou
+ * Ian Abbott
+ * Yuriy Kozlov
+ * Tobias Klauser
+ * Andriy Smolskyy
+ * Roman Bulgakov
+ * Dmytro Mytarchuk
+ *
+ * Original driver contributed by SLS.
+ * Major updates contributed by GlobalLogic
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/ethtool.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+
+#include "altera_tse.h"
+
+#define TSE_STATS_LEN 31
+#define TSE_NUM_REGS 128
+
+static char const stat_gstrings[][ETH_GSTRING_LEN] = {
+ "tx_packets",
+ "rx_packets",
+ "rx_crc_errors",
+ "rx_align_errors",
+ "tx_bytes",
+ "rx_bytes",
+ "tx_pause",
+ "rx_pause",
+ "rx_errors",
+ "tx_errors",
+ "rx_unicast",
+ "rx_multicast",
+ "rx_broadcast",
+ "tx_discards",
+ "tx_unicast",
+ "tx_multicast",
+ "tx_broadcast",
+ "ether_drops",
+ "rx_total_bytes",
+ "rx_total_packets",
+ "rx_undersize",
+ "rx_oversize",
+ "rx_64_bytes",
+ "rx_65_127_bytes",
+ "rx_128_255_bytes",
+ "rx_256_511_bytes",
+ "rx_512_1023_bytes",
+ "rx_1024_1518_bytes",
+ "rx_gte_1519_bytes",
+ "rx_jabbers",
+ "rx_runts",
+};
+
+static void tse_get_drvinfo(struct net_device *dev,
+ struct ethtool_drvinfo *info)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ u32 rev = ioread32(&priv->mac_dev->megacore_revision);
+
+ strcpy(info->driver, "Altera TSE MAC IP Driver");
+ strcpy(info->version, "v8.0");
+ snprintf(info->fw_version, ETHTOOL_FWVERS_LEN, "v%d.%d",
+ rev & 0xFFFF, (rev & 0xFFFF0000) >> 16);
+ sprintf(info->bus_info, "platform");
+}
+
+/* Fill in a buffer with the strings which correspond to the
+ * stats
+ */
+static void tse_gstrings(struct net_device *dev, u32 stringset, u8 *buf)
+{
+ memcpy(buf, stat_gstrings, TSE_STATS_LEN * ETH_GSTRING_LEN);
+}
+
+static void tse_fill_stats(struct net_device *dev, struct ethtool_stats *dummy,
+ u64 *buf)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ struct altera_tse_mac *mac = priv->mac_dev;
+ u64 ext;
+
+ buf[0] = ioread32(&mac->frames_transmitted_ok);
+ buf[1] = ioread32(&mac->frames_received_ok);
+ buf[2] = ioread32(&mac->frames_check_sequence_errors);
+ buf[3] = ioread32(&mac->alignment_errors);
+
+ /* Extended aOctetsTransmittedOK counter */
+ ext = (u64) ioread32(&mac->msb_octets_transmitted_ok) << 32;
+ ext |= ioread32(&mac->octets_transmitted_ok);
+ buf[4] = ext;
+
+ /* Extended aOctetsReceivedOK counter */
+ ext = (u64) ioread32(&mac->msb_octets_received_ok) << 32;
+ ext |= ioread32(&mac->octets_received_ok);
+ buf[5] = ext;
+
+ buf[6] = ioread32(&mac->tx_pause_mac_ctrl_frames);
+ buf[7] = ioread32(&mac->rx_pause_mac_ctrl_frames);
+ buf[8] = ioread32(&mac->if_in_errors);
+ buf[9] = ioread32(&mac->if_out_errors);
+ buf[10] = ioread32(&mac->if_in_ucast_pkts);
+ buf[11] = ioread32(&mac->if_in_multicast_pkts);
+ buf[12] = ioread32(&mac->if_in_broadcast_pkts);
+ buf[13] = ioread32(&mac->if_out_discards);
+ buf[14] = ioread32(&mac->if_out_ucast_pkts);
+ buf[15] = ioread32(&mac->if_out_multicast_pkts);
+ buf[16] = ioread32(&mac->if_out_broadcast_pkts);
+ buf[17] = ioread32(&mac->ether_stats_drop_events);
+
+ /* Extended etherStatsOctets counter */
+ ext = (u64) ioread32(&mac->msb_ether_stats_octets) << 32;
+ ext |= ioread32(&mac->ether_stats_octets);
+ buf[18] = ext;
+
+ buf[19] = ioread32(&mac->ether_stats_pkts);
+ buf[20] = ioread32(&mac->ether_stats_undersize_pkts);
+ buf[21] = ioread32(&mac->ether_stats_oversize_pkts);
+ buf[22] = ioread32(&mac->ether_stats_pkts_64_octets);
+ buf[23] = ioread32(&mac->ether_stats_pkts_65to127_octets);
+ buf[24] = ioread32(&mac->ether_stats_pkts_128to255_octets);
+ buf[25] = ioread32(&mac->ether_stats_pkts_256to511_octets);
+ buf[26] = ioread32(&mac->ether_stats_pkts_512to1023_octets);
+ buf[27] = ioread32(&mac->ether_stats_pkts_1024to1518_octets);
+ buf[28] = ioread32(&mac->ether_stats_pkts_1519tox_octets);
+ buf[29] = ioread32(&mac->ether_stats_jabbers);
+ buf[30] = ioread32(&mac->ether_stats_fragments);
+}
+
+static int tse_sset_count(struct net_device *dev, int sset)
+{
+ switch (sset) {
+ case ETH_SS_STATS:
+ return TSE_STATS_LEN;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static u32 tse_get_msglevel(struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ return priv->msg_enable;
+}
+
+static void tse_set_msglevel(struct net_device *dev, uint32_t data)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ priv->msg_enable = data;
+}
+
+static int tse_reglen(struct net_device *dev)
+{
+ return TSE_NUM_REGS * sizeof(u32);
+}
+
+static void tse_get_regs(struct net_device *dev, struct ethtool_regs *regs,
+ void *regbuf)
+{
+ int i;
+ struct altera_tse_private *priv = netdev_priv(dev);
+ u32 *tse_mac_regs = (u32 *)priv->mac_dev;
+ u32 *buf = regbuf;
+
+ /* Set version to a known value, so ethtool knows
+ * how to do any special formatting of this data.
+ * This version number will need to change if and
+ * when this register table is changed.
+ */
+
+ regs->version = 1;
+
+ for (i = 0; i < TSE_NUM_REGS; i++)
+ buf[i] = ioread32(&tse_mac_regs[i]);
+}
+
+static int tse_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ struct phy_device *phydev = priv->phydev;
+
+ if (phydev == NULL)
+ return -ENODEV;
+
+ return phy_ethtool_gset(phydev, cmd);
+}
+
+static int tse_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ struct phy_device *phydev = priv->phydev;
+
+ if (phydev == NULL)
+ return -ENODEV;
+
+ return phy_ethtool_sset(phydev, cmd);
+}
+
+static const struct ethtool_ops tse_ethtool_ops = {
+ .get_drvinfo = tse_get_drvinfo,
+ .get_regs_len = tse_reglen,
+ .get_regs = tse_get_regs,
+ .get_link = ethtool_op_get_link,
+ .get_settings = tse_get_settings,
+ .set_settings = tse_set_settings,
+ .get_strings = tse_gstrings,
+ .get_sset_count = tse_sset_count,
+ .get_ethtool_stats = tse_fill_stats,
+ .get_msglevel = tse_get_msglevel,
+ .set_msglevel = tse_set_msglevel,
+};
+
+void altera_tse_set_ethtool_ops(struct net_device *netdev)
+{
+ SET_ETHTOOL_OPS(netdev, &tse_ethtool_ops);
+}
diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
new file mode 100644
index 0000000..c70a29e
--- /dev/null
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -0,0 +1,1543 @@
+/* Altera Triple-Speed Ethernet MAC driver
+ * Copyright (C) 2008-2014 Altera Corporation. All rights reserved
+ *
+ * Contributors:
+ * Dalon Westergreen
+ * Thomas Chou
+ * Ian Abbott
+ * Yuriy Kozlov
+ * Tobias Klauser
+ * Andriy Smolskyy
+ * Roman Bulgakov
+ * Dmytro Mytarchuk
+ * Matthew Gerlach
+ *
+ * Original driver contributed by SLS.
+ * Major updates contributed by GlobalLogic
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/atomic.h>
+#include <linux/delay.h>
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/skbuff.h>
+#include <asm/cacheflush.h>
+
+#include "altera_utils.h"
+#include "altera_tse.h"
+#include "altera_sgdma.h"
+#include "altera_msgdma.h"
+
+static atomic_t instance_count = ATOMIC_INIT(~0);
+/* Module parameters */
+static int debug = -1;
+module_param(debug, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(debug, "Message Level (-1: default, 0: no output, 16: all)");
+
+static const u32 default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE |
+ NETIF_MSG_LINK | NETIF_MSG_IFUP |
+ NETIF_MSG_IFDOWN);
+
+#define RX_DESCRIPTORS 64
+static int dma_rx_num = RX_DESCRIPTORS;
+module_param(dma_rx_num, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dma_rx_num, "Number of descriptors in the RX list");
+
+#define TX_DESCRIPTORS 64
+static int dma_tx_num = TX_DESCRIPTORS;
+module_param(dma_tx_num, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dma_tx_num, "Number of descriptors in the TX list");
+
+
+#define POLL_PHY (-1)
+
+/* Make sure DMA buffer size is larger than the max frame size
+ * plus some alignment offset and a VLAN header. If the max frame size is
+ * 1518, a VLAN header would be additional 4 bytes and additional
+ * headroom for alignment is 2 bytes, 2048 is just fine.
+ */
+#define ALTERA_RXDMABUFFER_SIZE 2048
+
+/* Allow network stack to resume queueing packets after we've
+ * finished transmitting at least 1/4 of the packets in the queue.
+ */
+#define TSE_TX_THRESH(x) (x->tx_ring_size / 4)
+
+#define TXQUEUESTOP_THRESHHOLD 2
+
+static struct of_device_id altera_tse_ids[];
+
+static inline u32 tse_tx_avail(struct altera_tse_private *priv)
+{
+ return priv->tx_cons + priv->tx_ring_size - priv->tx_prod - 1;
+}
+
+/* MDIO specific functions
+ */
+static int altera_tse_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
+{
+ struct altera_tse_mac *mac = (struct altera_tse_mac *)bus->priv;
+ unsigned int *mdio_regs = (unsigned int *)&mac->mdio_phy0;
+ u32 data;
+
+ /* set MDIO address */
+ iowrite32((mii_id & 0x1f), &mac->mdio_phy0_addr);
+
+ /* get the data */
+ data = ioread32(&mdio_regs[regnum]) & 0xffff;
+ return data;
+}
+
+static int altera_tse_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
+ u16 value)
+{
+ struct altera_tse_mac *mac = (struct altera_tse_mac *)bus->priv;
+ unsigned int *mdio_regs = (unsigned int *)&mac->mdio_phy0;
+
+ /* set MDIO address */
+ iowrite32((mii_id & 0x1f), &mac->mdio_phy0_addr);
+
+ /* write the data */
+ iowrite32((u32) value, &mdio_regs[regnum]);
+ return 0;
+}
+
+static int altera_tse_mdio_create(struct net_device *dev, unsigned int id)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ int ret;
+ int i;
+ struct device_node *mdio_node = NULL;
+ struct mii_bus *mdio = NULL;
+ struct device_node *child_node = NULL;
+
+ for_each_child_of_node(priv->device->of_node, child_node) {
+ if (of_device_is_compatible(child_node, "altr,tse-mdio")) {
+ mdio_node = child_node;
+ break;
+ }
+ }
+
+ if (mdio_node) {
+ netdev_dbg(dev, "FOUND MDIO subnode\n");
+ } else {
+ netdev_dbg(dev, "NO MDIO subnode\n");
+ return 0;
+ }
+
+ mdio = mdiobus_alloc();
+ if (mdio == NULL) {
+ netdev_err(dev, "Error allocating MDIO bus\n");
+ return -ENOMEM;
+ }
+
+ mdio->name = ALTERA_TSE_RESOURCE_NAME;
+ mdio->read = &altera_tse_mdio_read;
+ mdio->write = &altera_tse_mdio_write;
+ snprintf(mdio->id, MII_BUS_ID_SIZE, "%s-%u", mdio->name, id);
+
+ mdio->irq = kcalloc(PHY_MAX_ADDR, sizeof(int), GFP_KERNEL);
+ if (mdio->irq == NULL) {
+ ret = -ENOMEM;
+ goto out_free_mdio;
+ }
+ for (i = 0; i < PHY_MAX_ADDR; i++)
+ mdio->irq[i] = PHY_POLL;
+
+ mdio->priv = priv->mac_dev;
+ mdio->parent = priv->device;
+
+ ret = of_mdiobus_register(mdio, mdio_node);
+ if (ret != 0) {
+ netdev_err(dev, "Cannot register MDIO bus %s\n",
+ mdio->id);
+ goto out_free_mdio_irq;
+ }
+
+ if (netif_msg_drv(priv))
+ netdev_info(dev, "MDIO bus %s: created\n", mdio->id);
+
+ priv->mdio = mdio;
+ return 0;
+out_free_mdio_irq:
+ kfree(mdio->irq);
+out_free_mdio:
+ mdiobus_free(mdio);
+ mdio = NULL;
+ return ret;
+}
+
+static void altera_tse_mdio_destroy(struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+
+ if (priv->mdio == NULL)
+ return;
+
+ if (netif_msg_drv(priv))
+ netdev_info(dev, "MDIO bus %s: removed\n",
+ priv->mdio->id);
+
+ mdiobus_unregister(priv->mdio);
+ kfree(priv->mdio->irq);
+ mdiobus_free(priv->mdio);
+ priv->mdio = NULL;
+}
+
+static int tse_init_rx_buffer(struct altera_tse_private *priv,
+ struct tse_buffer *rxbuffer, int len)
+{
+ rxbuffer->skb = netdev_alloc_skb_ip_align(priv->dev, len);
+ if (!rxbuffer->skb)
+ return -ENOMEM;
+
+ rxbuffer->dma_addr = dma_map_single(priv->device, rxbuffer->skb->data,
+ len,
+ DMA_FROM_DEVICE);
+
+ if (dma_mapping_error(priv->device, rxbuffer->dma_addr)) {
+ netdev_err(priv->dev, "%s: DMA mapping error\n", __func__);
+ dev_kfree_skb_any(rxbuffer->skb);
+ return -EINVAL;
+ }
+ rxbuffer->len = len;
+ return 0;
+}
+
+static void tse_free_rx_buffer(struct altera_tse_private *priv,
+ struct tse_buffer *rxbuffer)
+{
+ struct sk_buff *skb = rxbuffer->skb;
+ dma_addr_t dma_addr = rxbuffer->dma_addr;
+
+ if (skb != NULL) {
+ if (dma_addr)
+ dma_unmap_single(priv->device, dma_addr,
+ rxbuffer->len,
+ DMA_FROM_DEVICE);
+ dev_kfree_skb_any(skb);
+ rxbuffer->skb = NULL;
+ rxbuffer->dma_addr = 0;
+ }
+}
+
+/* Unmap and free Tx buffer resources
+ */
+static void tse_free_tx_buffer(struct altera_tse_private *priv,
+ struct tse_buffer *buffer)
+{
+ if (buffer->dma_addr) {
+ if (buffer->mapped_as_page)
+ dma_unmap_page(priv->device, buffer->dma_addr,
+ buffer->len, DMA_TO_DEVICE);
+ else
+ dma_unmap_single(priv->device, buffer->dma_addr,
+ buffer->len, DMA_TO_DEVICE);
+ buffer->dma_addr = 0;
+ }
+ if (buffer->skb) {
+ dev_kfree_skb_any(buffer->skb);
+ buffer->skb = NULL;
+ }
+}
+
+static int alloc_init_skbufs(struct altera_tse_private *priv)
+{
+ unsigned int rx_descs = priv->rx_ring_size;
+ unsigned int tx_descs = priv->tx_ring_size;
+ int ret = -ENOMEM;
+ int i;
+
+ /* Create Rx ring buffer */
+ priv->rx_ring = kcalloc(rx_descs, sizeof(struct tse_buffer),
+ GFP_KERNEL);
+ if (!priv->rx_ring)
+ goto err_rx_ring;
+
+ /* Create Tx ring buffer */
+ priv->tx_ring = kcalloc(tx_descs, sizeof(struct tse_buffer),
+ GFP_KERNEL);
+ if (!priv->tx_ring)
+ goto err_tx_ring;
+
+ priv->tx_cons = 0;
+ priv->tx_prod = 0;
+
+ /* Init Rx ring */
+ for (i = 0; i < rx_descs; i++) {
+ ret = tse_init_rx_buffer(priv, &priv->rx_ring[i],
+ priv->rx_dma_buf_sz);
+ if (ret)
+ goto err_init_rx_buffers;
+ }
+
+ priv->rx_cons = 0;
+ priv->rx_prod = 0;
+
+ return 0;
+err_init_rx_buffers:
+ while (--i >= 0)
+ tse_free_rx_buffer(priv, &priv->rx_ring[i]);
+ kfree(priv->tx_ring);
+err_tx_ring:
+ kfree(priv->rx_ring);
+err_rx_ring:
+ return ret;
+}
+
+static void free_skbufs(struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ unsigned int rx_descs = priv->rx_ring_size;
+ unsigned int tx_descs = priv->tx_ring_size;
+ int i;
+
+ /* Release the DMA TX/RX socket buffers */
+ for (i = 0; i < rx_descs; i++)
+ tse_free_rx_buffer(priv, &priv->rx_ring[i]);
+ for (i = 0; i < tx_descs; i++)
+ tse_free_tx_buffer(priv, &priv->tx_ring[i]);
+
+
+ kfree(priv->tx_ring);
+}
+
+/* Reallocate the skb for the reception process
+ */
+static inline void tse_rx_refill(struct altera_tse_private *priv)
+{
+ unsigned int rxsize = priv->rx_ring_size;
+ unsigned int entry;
+ int ret;
+
+ for (; priv->rx_cons - priv->rx_prod > 0;
+ priv->rx_prod++) {
+ entry = priv->rx_prod % rxsize;
+ if (likely(priv->rx_ring[entry].skb == NULL)) {
+ ret = tse_init_rx_buffer(priv, &priv->rx_ring[entry],
+ priv->rx_dma_buf_sz);
+ if (unlikely(ret != 0))
+ break;
+ priv->dmaops->add_rx_desc(priv, &priv->rx_ring[entry]);
+ }
+ }
+}
+
+/* Pull out the VLAN tag and fix up the packet
+ */
+static inline void tse_rx_vlan(struct net_device *dev, struct sk_buff *skb)
+{
+ struct ethhdr *eth_hdr;
+ u16 vid;
+ if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+ !__vlan_get_tag(skb, &vid)) {
+ eth_hdr = (struct ethhdr *)skb->data;
+ memmove(skb->data + VLAN_HLEN, eth_hdr, ETH_ALEN * 2);
+ skb_pull(skb, VLAN_HLEN);
+ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
+ }
+}
+
+/* Receive a packet: retrieve and pass over to upper levels
+ */
+static int tse_rx(struct altera_tse_private *priv, int limit)
+{
+ unsigned int count = 0;
+ unsigned int next_entry;
+ struct sk_buff *skb;
+ unsigned int entry = priv->rx_cons % priv->rx_ring_size;
+ u32 rxstatus;
+ u16 pktlength;
+ u16 pktstatus;
+
+ while ((rxstatus = priv->dmaops->get_rx_status(priv)) != 0) {
+ pktstatus = rxstatus >> 16;
+ pktlength = rxstatus & 0xffff;
+
+ if ((pktstatus & 0xFF) || (pktlength == 0))
+ netdev_err(priv->dev,
+ "RCV pktstatus %08X pktlength %08X\n",
+ pktstatus, pktlength);
+
+ count++;
+ next_entry = (++priv->rx_cons) % priv->rx_ring_size;
+
+ skb = priv->rx_ring[entry].skb;
+ if (unlikely(!skb)) {
+ netdev_err(priv->dev,
+ "%s: Inconsistent Rx descriptor chain\n",
+ __func__);
+ priv->dev->stats.rx_dropped++;
+ break;
+ }
+ priv->rx_ring[entry].skb = NULL;
+
+ skb_put(skb, pktlength);
+
+ /* make cache consistent with receive packet buffer */
+ dma_sync_single_for_cpu(priv->device,
+ priv->rx_ring[entry].dma_addr,
+ priv->rx_ring[entry].len,
+ DMA_FROM_DEVICE);
+
+ dma_unmap_single(priv->device, priv->rx_ring[entry].dma_addr,
+ priv->rx_ring[entry].len, DMA_FROM_DEVICE);
+
+ if (netif_msg_pktdata(priv)) {
+ netdev_info(priv->dev, "frame received %d bytes\n",
+ pktlength);
+ print_hex_dump(KERN_ERR, "data: ", DUMP_PREFIX_OFFSET,
+ 16, 1, skb->data, pktlength, true);
+ }
+
+ tse_rx_vlan(priv->dev, skb);
+
+ skb->protocol = eth_type_trans(skb, priv->dev);
+ skb_checksum_none_assert(skb);
+
+ napi_gro_receive(&priv->napi, skb);
+
+ priv->dev->stats.rx_packets++;
+ priv->dev->stats.rx_bytes += pktlength;
+
+ entry = next_entry;
+ }
+
+ tse_rx_refill(priv);
+ return count;
+}
+
+/* Reclaim resources after transmission completes
+ */
+static int tse_tx_complete(struct altera_tse_private *priv)
+{
+ unsigned int txsize = priv->tx_ring_size;
+ u32 ready;
+ unsigned int entry;
+ struct tse_buffer *tx_buff;
+ int txcomplete = 0;
+
+ spin_lock(&priv->tx_lock);
+
+ ready = priv->dmaops->tx_completions(priv);
+
+ /* Free sent buffers */
+ while (ready && (priv->tx_cons != priv->tx_prod)) {
+ entry = priv->tx_cons % txsize;
+ tx_buff = &priv->tx_ring[entry];
+
+ if (netif_msg_tx_done(priv))
+ netdev_dbg(priv->dev, "%s: curr %d, dirty %d\n",
+ __func__, priv->tx_prod, priv->tx_cons);
+
+ if (likely(tx_buff->skb))
+ priv->dev->stats.tx_packets++;
+
+ tse_free_tx_buffer(priv, tx_buff);
+ priv->tx_cons++;
+
+ txcomplete++;
+ ready--;
+ }
+
+ if (unlikely(netif_queue_stopped(priv->dev) &&
+ tse_tx_avail(priv) > TSE_TX_THRESH(priv))) {
+ netif_tx_lock(priv->dev);
+ if (netif_queue_stopped(priv->dev) &&
+ tse_tx_avail(priv) > TSE_TX_THRESH(priv)) {
+ if (netif_msg_tx_done(priv))
+ netdev_dbg(priv->dev, "%s: restart transmit\n",
+ __func__);
+ netif_wake_queue(priv->dev);
+ }
+ netif_tx_unlock(priv->dev);
+ }
+
+ spin_unlock(&priv->tx_lock);
+ return txcomplete;
+}
+
+/* NAPI polling function
+ */
+static int tse_poll(struct napi_struct *napi, int budget)
+{
+ struct altera_tse_private *priv =
+ container_of(napi, struct altera_tse_private, napi);
+ int rxcomplete = 0;
+ int txcomplete = 0;
+ unsigned long int flags;
+
+ txcomplete = tse_tx_complete(priv);
+
+ rxcomplete = tse_rx(priv, budget);
+
+ if (rxcomplete >= budget || txcomplete > 0)
+ return rxcomplete;
+
+ napi_gro_flush(napi, false);
+ __napi_complete(napi);
+
+ netdev_dbg(priv->dev,
+ "NAPI Complete, did %d packets with budget %d\n",
+ txcomplete+rxcomplete, budget);
+
+ spin_lock_irqsave(&priv->rxdma_irq_lock, flags);
+ priv->dmaops->enable_rxirq(priv);
+ priv->dmaops->enable_txirq(priv);
+ spin_unlock_irqrestore(&priv->rxdma_irq_lock, flags);
+ return rxcomplete + txcomplete;
+}
+
+/* DMA TX & RX FIFO interrupt routing
+ */
+static irqreturn_t altera_isr(int irq, void *dev_id)
+{
+ struct net_device *dev = dev_id;
+ struct altera_tse_private *priv;
+ unsigned long int flags;
+
+
+ if (unlikely(!dev)) {
+ pr_err("%s: invalid dev pointer\n", __func__);
+ return IRQ_NONE;
+ }
+ priv = netdev_priv(dev);
+
+ /* turn off desc irqs and enable napi rx */
+ spin_lock_irqsave(&priv->rxdma_irq_lock, flags);
+
+ if (likely(napi_schedule_prep(&priv->napi))) {
+ priv->dmaops->disable_rxirq(priv);
+ priv->dmaops->disable_txirq(priv);
+ __napi_schedule(&priv->napi);
+ }
+
+ /* reset IRQs */
+ priv->dmaops->clear_rxirq(priv);
+ priv->dmaops->clear_txirq(priv);
+
+ spin_unlock_irqrestore(&priv->rxdma_irq_lock, flags);
+
+ return IRQ_HANDLED;
+}
+
+/* Transmit a packet (called by the kernel). Dispatches
+ * either the SGDMA method for transmitting or the
+ * MSGDMA method, assumes no scatter/gather support,
+ * implying an assumption that there's only one
+ * physically contiguous fragment starting at
+ * skb->data, for length of skb_headlen(skb).
+ */
+static int tse_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ unsigned int txsize = priv->tx_ring_size;
+ unsigned int entry;
+ struct tse_buffer *buffer = NULL;
+ int nfrags = skb_shinfo(skb)->nr_frags;
+ unsigned int nopaged_len = skb_headlen(skb);
+ enum netdev_tx ret = NETDEV_TX_OK;
+ dma_addr_t dma_addr;
+ int txcomplete = 0;
+
+ spin_lock_bh(&priv->tx_lock);
+
+ if (unlikely(tse_tx_avail(priv) < nfrags + 1)) {
+ if (!netif_queue_stopped(dev)) {
+ netif_stop_queue(dev);
+ /* This is a hard error, log it. */
+ netdev_err(priv->dev,
+ "%s: Tx list full when queue awake\n",
+ __func__);
+ }
+ ret = NETDEV_TX_BUSY;
+ goto out;
+ }
+
+ /* Map the first skb fragment */
+ entry = priv->tx_prod % txsize;
+ buffer = &priv->tx_ring[entry];
+
+ dma_addr = dma_map_single(priv->device, skb->data, nopaged_len,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(priv->device, dma_addr)) {
+ netdev_err(priv->dev, "%s: DMA mapping error\n", __func__);
+ ret = NETDEV_TX_OK;
+ goto out;
+ }
+
+ buffer->skb = skb;
+ buffer->dma_addr = dma_addr;
+ buffer->len = nopaged_len;
+
+ /* Push data out of the cache hierarchy into main memory */
+ dma_sync_single_for_device(priv->device, buffer->dma_addr,
+ buffer->len, DMA_TO_DEVICE);
+
+ txcomplete = priv->dmaops->tx_buffer(priv, buffer);
+
+ skb_tx_timestamp(skb);
+
+ priv->tx_prod++;
+ dev->stats.tx_bytes += skb->len;
+
+ if (unlikely(tse_tx_avail(priv) <= TXQUEUESTOP_THRESHHOLD)) {
+ if (netif_msg_hw(priv))
+ netdev_dbg(priv->dev, "%s: stop transmitted packets\n",
+ __func__);
+ netif_stop_queue(dev);
+ }
+
+out:
+ spin_unlock_bh(&priv->tx_lock);
+
+ return ret;
+}
+
+/* Called every time the controller might need to be made
+ * aware of new link state. The PHY code conveys this
+ * information through variables in the phydev structure, and this
+ * function converts those variables into the appropriate
+ * register values, and can bring down the device if needed.
+ */
+static void altera_tse_adjust_link(struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ struct phy_device *phydev = priv->phydev;
+ int new_state = 0;
+
+ /* only change config if there is a link */
+ spin_lock(&priv->mac_cfg_lock);
+ if (phydev->link) {
+ /* Read old config */
+ u32 cfg_reg = ioread32(&priv->mac_dev->command_config);
+
+ /* Check duplex */
+ if (phydev->duplex != priv->oldduplex) {
+ new_state = 1;
+ if (!(phydev->duplex))
+ cfg_reg |= MAC_CMDCFG_HD_ENA;
+ else
+ cfg_reg &= ~MAC_CMDCFG_HD_ENA;
+
+ netdev_dbg(priv->dev, "%s: Link duplex = 0x%x\n",
+ dev->name, phydev->duplex);
+
+ priv->oldduplex = phydev->duplex;
+ }
+
+ /* Check speed */
+ if (phydev->speed != priv->oldspeed) {
+ new_state = 1;
+ switch (phydev->speed) {
+ case 1000:
+ cfg_reg |= MAC_CMDCFG_ETH_SPEED;
+ cfg_reg &= ~MAC_CMDCFG_ENA_10;
+ break;
+ case 100:
+ cfg_reg &= ~MAC_CMDCFG_ETH_SPEED;
+ cfg_reg &= ~MAC_CMDCFG_ENA_10;
+ break;
+ case 10:
+ cfg_reg &= ~MAC_CMDCFG_ETH_SPEED;
+ cfg_reg |= MAC_CMDCFG_ENA_10;
+ break;
+ default:
+ if (netif_msg_link(priv))
+ netdev_warn(dev, "Speed (%d) is not 10/100/1000!\n",
+ phydev->speed);
+ break;
+ }
+ priv->oldspeed = phydev->speed;
+ }
+ iowrite32(cfg_reg, &priv->mac_dev->command_config);
+
+ if (!priv->oldlink) {
+ new_state = 1;
+ priv->oldlink = 1;
+ }
+ } else if (priv->oldlink) {
+ new_state = 1;
+ priv->oldlink = 0;
+ priv->oldspeed = 0;
+ priv->oldduplex = -1;
+ }
+
+ if (new_state && netif_msg_link(priv))
+ phy_print_status(phydev);
+
+ spin_unlock(&priv->mac_cfg_lock);
+}
+static struct phy_device *connect_local_phy(struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ struct phy_device *phydev = NULL;
+ char phy_id_fmt[MII_BUS_ID_SIZE + 3];
+ int ret;
+
+ if (priv->phy_addr != POLL_PHY) {
+ snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT,
+ priv->mdio->id, priv->phy_addr);
+
+ netdev_dbg(dev, "trying to attach to %s\n", phy_id_fmt);
+
+ phydev = phy_connect(dev, phy_id_fmt, &altera_tse_adjust_link,
+ priv->phy_iface);
+ if (IS_ERR(phydev))
+ netdev_err(dev, "Could not attach to PHY\n");
+
+ } else {
+ phydev = phy_find_first(priv->mdio);
+ if (phydev == NULL) {
+ netdev_err(dev, "No PHY found\n");
+ return phydev;
+ }
+
+ ret = phy_connect_direct(dev, phydev, &altera_tse_adjust_link,
+ priv->phy_iface);
+ if (ret != 0) {
+ netdev_err(dev, "Could not attach to PHY\n");
+ phydev = NULL;
+ }
+ }
+ return phydev;
+}
+
+/* Initialize driver's PHY state, and attach to the PHY
+ */
+static int init_phy(struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ struct phy_device *phydev;
+ struct device_node *phynode;
+
+ priv->oldlink = 0;
+ priv->oldspeed = 0;
+ priv->oldduplex = -1;
+
+ phynode = of_parse_phandle(priv->device->of_node, "phy-handle", 0);
+
+ if (!phynode) {
+ netdev_dbg(dev, "no phy-handle found\n");
+ if (!priv->mdio) {
+ netdev_err(dev,
+ "No phy-handle nor local mdio specified\n");
+ return -ENODEV;
+ }
+ phydev = connect_local_phy(dev);
+ } else {
+ netdev_dbg(dev, "phy-handle found\n");
+ phydev = of_phy_connect(dev, phynode,
+ &altera_tse_adjust_link, 0, priv->phy_iface);
+ }
+
+ if (!phydev) {
+ netdev_err(dev, "Could not find the PHY\n");
+ return -ENODEV;
+ }
+
+ /* Stop Advertising 1000BASE Capability if interface is not GMII
+ * Note: Checkpatch throws CHECKs for the camel case defines below,
+ * it's ok to ignore.
+ */
+ if ((priv->phy_iface == PHY_INTERFACE_MODE_MII) ||
+ (priv->phy_iface == PHY_INTERFACE_MODE_RMII))
+ phydev->advertising &= ~(SUPPORTED_1000baseT_Half |
+ SUPPORTED_1000baseT_Full);
+
+ /* Broken HW is sometimes missing the pull-up resistor on the
+ * MDIO line, which results in reads to non-existent devices returning
+ * 0 rather than 0xffff. Catch this here and treat 0 as a non-existent
+ * device as well.
+ * Note: phydev->phy_id is the result of reading the UID PHY registers.
+ */
+ if (phydev->phy_id == 0) {
+ netdev_err(dev, "Bad PHY UID 0x%08x\n", phydev->phy_id);
+ phy_disconnect(phydev);
+ return -ENODEV;
+ }
+
+ netdev_dbg(dev, "attached to PHY %d UID 0x%08x Link = %d\n",
+ phydev->addr, phydev->phy_id, phydev->link);
+
+ priv->phydev = phydev;
+ return 0;
+}
+
+static void tse_update_mac_addr(struct altera_tse_private *priv, u8 *addr)
+{
+ struct altera_tse_mac *mac = priv->mac_dev;
+ u32 msb;
+ u32 lsb;
+
+ msb = (addr[3] << 24) | (addr[2] << 16) | (addr[1] << 8) | addr[0];
+ lsb = ((addr[5] << 8) | addr[4]) & 0xffff;
+
+ /* Set primary MAC address */
+ iowrite32(msb, &mac->mac_addr_0);
+ iowrite32(lsb, &mac->mac_addr_1);
+}
+
+/* MAC software reset.
+ * When reset is triggered, the MAC function completes the current
+ * transmission or reception, and subsequently disables the transmit and
+ * receive logic, flushes the receive FIFO buffer, and resets the statistics
+ * counters.
+ */
+static int reset_mac(struct altera_tse_private *priv)
+{
+ void __iomem *cmd_cfg_reg = &priv->mac_dev->command_config;
+ int counter;
+ u32 dat;
+
+ dat = ioread32(cmd_cfg_reg);
+ dat &= ~(MAC_CMDCFG_TX_ENA | MAC_CMDCFG_RX_ENA);
+ dat |= MAC_CMDCFG_SW_RESET | MAC_CMDCFG_CNT_RESET;
+ iowrite32(dat, cmd_cfg_reg);
+
+ counter = 0;
+ while (counter++ < ALTERA_TSE_SW_RESET_WATCHDOG_CNTR) {
+ if (tse_bit_is_clear(cmd_cfg_reg, MAC_CMDCFG_SW_RESET))
+ break;
+ udelay(1);
+ }
+
+ if (counter >= ALTERA_TSE_SW_RESET_WATCHDOG_CNTR) {
+ dat = ioread32(cmd_cfg_reg);
+ dat &= ~MAC_CMDCFG_SW_RESET;
+ iowrite32(dat, cmd_cfg_reg);
+ return -1;
+ }
+ return 0;
+}
+
+/* Initialize MAC core registers
+*/
+static int init_mac(struct altera_tse_private *priv)
+{
+ struct altera_tse_mac *mac = priv->mac_dev;
+ unsigned int cmd = 0;
+ u32 frm_length;
+
+ /* Setup Rx FIFO */
+ iowrite32(priv->rx_fifo_depth - ALTERA_TSE_RX_SECTION_EMPTY,
+ &mac->rx_section_empty);
+ iowrite32(ALTERA_TSE_RX_SECTION_FULL, &mac->rx_section_full);
+ iowrite32(ALTERA_TSE_RX_ALMOST_EMPTY, &mac->rx_almost_empty);
+ iowrite32(ALTERA_TSE_RX_ALMOST_FULL, &mac->rx_almost_full);
+
+ /* Setup Tx FIFO */
+ iowrite32(priv->tx_fifo_depth - ALTERA_TSE_TX_SECTION_EMPTY,
+ &mac->tx_section_empty);
+ iowrite32(ALTERA_TSE_TX_SECTION_FULL, &mac->tx_section_full);
+ iowrite32(ALTERA_TSE_TX_ALMOST_EMPTY, &mac->tx_almost_empty);
+ iowrite32(ALTERA_TSE_TX_ALMOST_FULL, &mac->tx_almost_full);
+
+ /* MAC Address Configuration */
+ tse_update_mac_addr(priv, priv->dev->dev_addr);
+
+ /* MAC Function Configuration */
+ frm_length = ETH_HLEN + priv->dev->mtu + ETH_FCS_LEN;
+ iowrite32(frm_length, &mac->frm_length);
+ iowrite32(ALTERA_TSE_TX_IPG_LENGTH, &mac->tx_ipg_length);
+
+ /* Disable RX/TX shift 16 for alignment of all received frames on 16-bit
+ * start address
+ */
+ tse_clear_bit(&mac->rx_cmd_stat, ALTERA_TSE_RX_CMD_STAT_RX_SHIFT16);
+ tse_clear_bit(&mac->tx_cmd_stat, ALTERA_TSE_TX_CMD_STAT_TX_SHIFT16 |
+ ALTERA_TSE_TX_CMD_STAT_OMIT_CRC);
+
+ /* Set the MAC options */
+ cmd = ioread32(&mac->command_config);
+ cmd |= MAC_CMDCFG_PAD_EN; /* Padding Removal on Receive */
+ cmd &= ~MAC_CMDCFG_CRC_FWD; /* CRC Removal */
+ cmd |= MAC_CMDCFG_RX_ERR_DISC; /* Automatically discard frames
+ * with CRC errors
+ */
+ cmd |= MAC_CMDCFG_CNTL_FRM_ENA;
+ cmd &= ~MAC_CMDCFG_TX_ENA;
+ cmd &= ~MAC_CMDCFG_RX_ENA;
+ iowrite32(cmd, &mac->command_config);
+
+ if (netif_msg_hw(priv))
+ dev_dbg(priv->device,
+ "MAC post-initialization: CMD_CONFIG = 0x%08x\n", cmd);
+
+ return 0;
+}
+
+/* Start/stop MAC transmission logic
+ */
+static void tse_set_mac(struct altera_tse_private *priv, bool enable)
+{
+ struct altera_tse_mac *mac = priv->mac_dev;
+ u32 value = ioread32(&mac->command_config);
+
+ if (enable)
+ value |= MAC_CMDCFG_TX_ENA | MAC_CMDCFG_RX_ENA;
+ else
+ value &= ~(MAC_CMDCFG_TX_ENA | MAC_CMDCFG_RX_ENA);
+
+ iowrite32(value, &mac->command_config);
+}
+
+/* Change the MTU
+ */
+static int tse_change_mtu(struct net_device *dev, int new_mtu)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ unsigned int max_mtu = priv->max_mtu;
+ unsigned int min_mtu = ETH_ZLEN + ETH_FCS_LEN;
+
+ if (netif_running(dev)) {
+ netdev_err(dev, "must be stopped to change its MTU\n");
+ return -EBUSY;
+ }
+
+ if ((new_mtu < min_mtu) || (new_mtu > max_mtu)) {
+ netdev_err(dev, "invalid MTU, max MTU is: %u\n", max_mtu);
+ return -EINVAL;
+ }
+
+ dev->mtu = new_mtu;
+ netdev_update_features(dev);
+
+ return 0;
+}
+
+static void altera_tse_set_mcfilter(struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ struct altera_tse_mac *mac = priv->mac_dev;
+ int i;
+ struct netdev_hw_addr *ha;
+
+ /* clear the hash filter */
+ for (i = 0; i < 64; i++)
+ iowrite32(0, &(mac->hash_table[i]));
+
+ netdev_for_each_mc_addr(ha, dev) {
+ unsigned int hash = 0;
+ int mac_octet;
+
+ for (mac_octet = 5; mac_octet >= 0; mac_octet--) {
+ unsigned char xor_bit = 0;
+ unsigned char octet = ha->addr[mac_octet];
+ unsigned int bitshift;
+
+ for (bitshift = 0; bitshift < 8; bitshift++)
+ xor_bit ^= ((octet >> bitshift) & 0x01);
+
+ hash = (hash << 1) | xor_bit;
+ }
+ iowrite32(1, &(mac->hash_table[hash]));
+ }
+}
+
+
+static void altera_tse_set_mcfilterall(struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ struct altera_tse_mac *mac = priv->mac_dev;
+ int i;
+
+ /* set the hash filter */
+ for (i = 0; i < 64; i++)
+ iowrite32(1, &(mac->hash_table[i]));
+}
+
+/* Set or clear the multicast filter for this adaptor
+ */
+static void tse_set_rx_mode_hashfilter(struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ struct altera_tse_mac *mac = priv->mac_dev;
+
+ spin_lock(&priv->mac_cfg_lock);
+
+ if (dev->flags & IFF_PROMISC)
+ tse_set_bit(&mac->command_config, MAC_CMDCFG_PROMIS_EN);
+
+ if (dev->flags & IFF_ALLMULTI)
+ altera_tse_set_mcfilterall(dev);
+ else
+ altera_tse_set_mcfilter(dev);
+
+ spin_unlock(&priv->mac_cfg_lock);
+}
+
+/* Set or clear the multicast filter for this adaptor
+ */
+static void tse_set_rx_mode(struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ struct altera_tse_mac *mac = priv->mac_dev;
+
+ spin_lock(&priv->mac_cfg_lock);
+
+ if ((dev->flags & IFF_PROMISC) || (dev->flags & IFF_ALLMULTI) ||
+ !netdev_mc_empty(dev) || !netdev_uc_empty(dev))
+ tse_set_bit(&mac->command_config, MAC_CMDCFG_PROMIS_EN);
+ else
+ tse_clear_bit(&mac->command_config, MAC_CMDCFG_PROMIS_EN);
+
+ spin_unlock(&priv->mac_cfg_lock);
+}
+
+/* Open and initialize the interface
+ */
+static int tse_open(struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ int ret = 0;
+ int i;
+ unsigned long int flags;
+
+ /* Reset and configure TSE MAC and probe associated PHY */
+ ret = priv->dmaops->init_dma(priv);
+ if (ret != 0) {
+ netdev_err(dev, "Cannot initialize DMA\n");
+ goto phy_error;
+ }
+
+ if (netif_msg_ifup(priv))
+ netdev_warn(dev, "device MAC address %pM\n",
+ dev->dev_addr);
+
+ if ((priv->revision < 0xd00) || (priv->revision > 0xe00))
+ netdev_warn(dev, "TSE revision %x\n", priv->revision);
+
+ spin_lock(&priv->mac_cfg_lock);
+ ret = reset_mac(priv);
+ if (ret)
+ netdev_err(dev, "Cannot reset MAC core (error: %d)\n", ret);
+
+ ret = init_mac(priv);
+ spin_unlock(&priv->mac_cfg_lock);
+ if (ret) {
+ netdev_err(dev, "Cannot init MAC core (error: %d)\n", ret);
+ goto alloc_skbuf_error;
+ }
+
+ priv->dmaops->reset_dma(priv);
+
+ /* Create and initialize the TX/RX descriptors chains. */
+ priv->rx_ring_size = dma_rx_num;
+ priv->tx_ring_size = dma_tx_num;
+ ret = alloc_init_skbufs(priv);
+ if (ret) {
+ netdev_err(dev, "DMA descriptors initialization failed\n");
+ goto alloc_skbuf_error;
+ }
+
+
+ /* Register RX interrupt */
+ ret = request_irq(priv->rx_irq, altera_isr, IRQF_SHARED,
+ dev->name, dev);
+ if (ret) {
+ netdev_err(dev, "Unable to register RX interrupt %d\n",
+ priv->rx_irq);
+ goto init_error;
+ }
+
+ /* Register TX interrupt */
+ ret = request_irq(priv->tx_irq, altera_isr, IRQF_SHARED,
+ dev->name, dev);
+ if (ret) {
+ netdev_err(dev, "Unable to register TX interrupt %d\n",
+ priv->tx_irq);
+ goto tx_request_irq_error;
+ }
+
+ /* Enable DMA interrupts */
+ spin_lock_irqsave(&priv->rxdma_irq_lock, flags);
+ priv->dmaops->enable_rxirq(priv);
+ priv->dmaops->enable_txirq(priv);
+
+ /* Setup RX descriptor chain */
+ for (i = 0; i < priv->rx_ring_size; i++)
+ priv->dmaops->add_rx_desc(priv, &priv->rx_ring[i]);
+
+ spin_unlock_irqrestore(&priv->rxdma_irq_lock, flags);
+
+ /* Start MAC Rx/Tx */
+ spin_lock(&priv->mac_cfg_lock);
+ tse_set_mac(priv, true);
+ spin_unlock(&priv->mac_cfg_lock);
+
+ if (priv->phydev)
+ phy_start(priv->phydev);
+
+ napi_enable(&priv->napi);
+ netif_start_queue(dev);
+
+ return 0;
+
+tx_request_irq_error:
+ free_irq(priv->rx_irq, dev);
+init_error:
+ free_skbufs(dev);
+alloc_skbuf_error:
+ if (priv->phydev) {
+ phy_disconnect(priv->phydev);
+ priv->phydev = NULL;
+ }
+phy_error:
+ return ret;
+}
+
+/* Stop TSE MAC interface and put the device in an inactive state
+ */
+static int tse_shutdown(struct net_device *dev)
+{
+ struct altera_tse_private *priv = netdev_priv(dev);
+ int ret;
+ unsigned long int flags;
+
+ /* Stop and disconnect the PHY */
+ if (priv->phydev) {
+ phy_stop(priv->phydev);
+ phy_disconnect(priv->phydev);
+ priv->phydev = NULL;
+ }
+
+ netif_stop_queue(dev);
+ napi_disable(&priv->napi);
+
+ /* Disable DMA interrupts */
+ spin_lock_irqsave(&priv->rxdma_irq_lock, flags);
+ priv->dmaops->disable_rxirq(priv);
+ priv->dmaops->disable_txirq(priv);
+ spin_unlock_irqrestore(&priv->rxdma_irq_lock, flags);
+
+ /* Free the IRQ lines */
+ free_irq(priv->rx_irq, dev);
+ free_irq(priv->tx_irq, dev);
+
+ /* disable and reset the MAC, empties fifo */
+ spin_lock(&priv->mac_cfg_lock);
+ spin_lock(&priv->tx_lock);
+
+ ret = reset_mac(priv);
+ if (ret)
+ netdev_err(dev, "Cannot reset MAC core (error: %d)\n", ret);
+ priv->dmaops->reset_dma(priv);
+ free_skbufs(dev);
+
+ spin_unlock(&priv->tx_lock);
+ spin_unlock(&priv->mac_cfg_lock);
+
+ priv->dmaops->uninit_dma(priv);
+
+ return 0;
+}
+
+static struct net_device_ops altera_tse_netdev_ops = {
+ .ndo_open = tse_open,
+ .ndo_stop = tse_shutdown,
+ .ndo_start_xmit = tse_start_xmit,
+ .ndo_set_mac_address = eth_mac_addr,
+ .ndo_set_rx_mode = tse_set_rx_mode,
+ .ndo_change_mtu = tse_change_mtu,
+ .ndo_validate_addr = eth_validate_addr,
+};
+
+
+static int request_and_map(struct platform_device *pdev, const char *name,
+ struct resource **res, void __iomem **ptr)
+{
+ struct resource *region;
+ struct device *device = &pdev->dev;
+
+ *res = platform_get_resource_byname(pdev, IORESOURCE_MEM, name);
+ if (*res == NULL) {
+ dev_err(device, "resource %s not defined\n", name);
+ return -ENODEV;
+ }
+
+ region = devm_request_mem_region(device, (*res)->start,
+ resource_size(*res), dev_name(device));
+ if (region == NULL) {
+ dev_err(device, "unable to request %s\n", name);
+ return -EBUSY;
+ }
+
+ *ptr = devm_ioremap_nocache(device, region->start,
+ resource_size(region));
+ if (*ptr == NULL) {
+ dev_err(device, "ioremap_nocache of %s failed!", name);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+/* Probe Altera TSE MAC device
+ */
+static int altera_tse_probe(struct platform_device *pdev)
+{
+ struct net_device *ndev;
+ int ret = -ENODEV;
+ struct resource *control_port;
+ struct resource *dma_res;
+ struct altera_tse_private *priv;
+ const unsigned char *macaddr;
+ struct device_node *np = pdev->dev.of_node;
+ void __iomem *descmap;
+ const struct of_device_id *of_id = NULL;
+
+ ndev = alloc_etherdev(sizeof(struct altera_tse_private));
+ if (!ndev) {
+ dev_err(&pdev->dev, "Could not allocate network device\n");
+ return -ENODEV;
+ }
+
+ SET_NETDEV_DEV(ndev, &pdev->dev);
+
+ priv = netdev_priv(ndev);
+ priv->device = &pdev->dev;
+ priv->dev = ndev;
+ priv->msg_enable = netif_msg_init(debug, default_msg_level);
+
+ of_id = of_match_device(altera_tse_ids, &pdev->dev);
+
+ if (of_id)
+ priv->dmaops = (struct altera_dmaops *)of_id->data;
+
+
+ if (priv->dmaops &&
+ priv->dmaops->altera_dtype == ALTERA_DTYPE_SGDMA) {
+ /* Get the mapped address to the SGDMA descriptor memory */
+ ret = request_and_map(pdev, "s1", &dma_res, &descmap);
+ if (ret)
+ goto out_free;
+
+ /* Start of that memory is for transmit descriptors */
+ priv->tx_dma_desc = descmap;
+
+ /* First half is for tx descriptors, other half for tx */
+ priv->txdescmem = resource_size(dma_res)/2;
+
+ priv->txdescmem_busaddr = (dma_addr_t)dma_res->start;
+
+ priv->rx_dma_desc = (void __iomem *)((uintptr_t)(descmap +
+ priv->txdescmem));
+ priv->rxdescmem = resource_size(dma_res)/2;
+ priv->rxdescmem_busaddr = dma_res->start;
+ priv->rxdescmem_busaddr += priv->txdescmem;
+
+ if (upper_32_bits(priv->rxdescmem_busaddr)) {
+ dev_dbg(priv->device,
+ "SGDMA bus addresses greater than 32-bits\n");
+ goto out_free;
+ }
+ if (upper_32_bits(priv->txdescmem_busaddr)) {
+ dev_dbg(priv->device,
+ "SGDMA bus addresses greater than 32-bits\n");
+ goto out_free;
+ }
+ } else if (priv->dmaops &&
+ priv->dmaops->altera_dtype == ALTERA_DTYPE_MSGDMA) {
+ ret = request_and_map(pdev, "rx_resp", &dma_res,
+ &priv->rx_dma_resp);
+ if (ret)
+ goto out_free;
+
+ ret = request_and_map(pdev, "tx_desc", &dma_res,
+ &priv->tx_dma_desc);
+ if (ret)
+ goto out_free;
+
+ priv->txdescmem = resource_size(dma_res);
+ priv->txdescmem_busaddr = dma_res->start;
+
+ ret = request_and_map(pdev, "rx_desc", &dma_res,
+ &priv->rx_dma_desc);
+ if (ret)
+ goto out_free;
+
+ priv->rxdescmem = resource_size(dma_res);
+ priv->rxdescmem_busaddr = dma_res->start;
+
+ } else {
+ goto out_free;
+ }
+
+ if (!dma_set_mask(priv->device, DMA_BIT_MASK(priv->dmaops->dmamask)))
+ dma_set_coherent_mask(priv->device,
+ DMA_BIT_MASK(priv->dmaops->dmamask));
+ else if (!dma_set_mask(priv->device, DMA_BIT_MASK(32)))
+ dma_set_coherent_mask(priv->device, DMA_BIT_MASK(32));
+ else
+ goto out_free;
+
+ /* MAC address space */
+ ret = request_and_map(pdev, "control_port", &control_port,
+ (void __iomem **)&priv->mac_dev);
+ if (ret)
+ goto out_free;
+
+ /* xSGDMA Rx Dispatcher address space */
+ ret = request_and_map(pdev, "rx_csr", &dma_res,
+ &priv->rx_dma_csr);
+ if (ret)
+ goto out_free;
+
+
+ /* xSGDMA Tx Dispatcher address space */
+ ret = request_and_map(pdev, "tx_csr", &dma_res,
+ &priv->tx_dma_csr);
+ if (ret)
+ goto out_free;
+
+
+ /* Rx IRQ */
+ priv->rx_irq = platform_get_irq_byname(pdev, "rx_irq");
+ if (priv->rx_irq == -ENXIO) {
+ dev_err(&pdev->dev, "cannot obtain Rx IRQ\n");
+ ret = -ENXIO;
+ goto out_free;
+ }
+
+ /* Tx IRQ */
+ priv->tx_irq = platform_get_irq_byname(pdev, "tx_irq");
+ if (priv->tx_irq == -ENXIO) {
+ dev_err(&pdev->dev, "cannot obtain Tx IRQ\n");
+ ret = -ENXIO;
+ goto out_free;
+ }
+
+ /* get FIFO depths from device tree */
+ if (of_property_read_u32(pdev->dev.of_node, "rx-fifo-depth",
+ &priv->rx_fifo_depth)) {
+ dev_err(&pdev->dev, "cannot obtain rx-fifo-depth\n");
+ ret = -ENXIO;
+ goto out_free;
+ }
+
+ if (of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth",
+ &priv->rx_fifo_depth)) {
+ dev_err(&pdev->dev, "cannot obtain tx-fifo-depth\n");
+ ret = -ENXIO;
+ goto out_free;
+ }
+
+ /* get hash filter settings for this instance */
+ priv->hash_filter =
+ of_property_read_bool(pdev->dev.of_node,
+ "altr,has-hash-multicast-filter");
+
+ /* get supplemental address settings for this instance */
+ priv->added_unicast =
+ of_property_read_bool(pdev->dev.of_node,
+ "altr,has-supplementary-unicast");
+
+ /* Max MTU is 1500, ETH_DATA_LEN */
+ priv->max_mtu = ETH_DATA_LEN;
+
+ /* Get the max mtu from the device tree. Note that the
+ * "max-frame-size" parameter is actually max mtu. Definition
+ * in the ePAPR v1.1 spec and usage differ, so go with usage.
+ */
+ of_property_read_u32(pdev->dev.of_node, "max-frame-size",
+ &priv->max_mtu);
+
+ /* The DMA buffer size already accounts for an alignment bias
+ * to avoid unaligned access exceptions for the NIOS processor,
+ */
+ priv->rx_dma_buf_sz = ALTERA_RXDMABUFFER_SIZE;
+
+ /* get default MAC address from device tree */
+ macaddr = of_get_mac_address(pdev->dev.of_node);
+ if (macaddr)
+ ether_addr_copy(ndev->dev_addr, macaddr);
+ else
+ eth_hw_addr_random(ndev);
+
+ priv->phy_iface = of_get_phy_mode(np);
+
+ /* try to get PHY address from device tree, use PHY autodetection if
+ * no valid address is given
+ */
+ if (of_property_read_u32(pdev->dev.of_node, "phy-addr",
+ &priv->phy_addr)) {
+ priv->phy_addr = POLL_PHY;
+ }
+
+ if (!((priv->phy_addr == POLL_PHY) ||
+ ((priv->phy_addr >= 0) && (priv->phy_addr < PHY_MAX_ADDR)))) {
+ dev_err(&pdev->dev, "invalid phy-addr specified %d\n",
+ priv->phy_addr);
+ goto out_free;
+ }
+
+ /* Create/attach to MDIO bus */
+ ret = altera_tse_mdio_create(ndev,
+ atomic_add_return(1, &instance_count));
+
+ if (ret)
+ goto out_free;
+
+ /* initialize netdev */
+ ether_setup(ndev);
+ ndev->mem_start = control_port->start;
+ ndev->mem_end = control_port->end;
+ ndev->netdev_ops = &altera_tse_netdev_ops;
+ altera_tse_set_ethtool_ops(ndev);
+
+ altera_tse_netdev_ops.ndo_set_rx_mode = tse_set_rx_mode;
+
+ if (priv->hash_filter)
+ altera_tse_netdev_ops.ndo_set_rx_mode =
+ tse_set_rx_mode_hashfilter;
+
+ /* Scatter/gather IO is not supported,
+ * so it is turned off
+ */
+ ndev->hw_features &= ~NETIF_F_SG;
+ ndev->features |= ndev->hw_features | NETIF_F_HIGHDMA;
+
+ /* VLAN offloading of tagging, stripping and filtering is not
+ * supported by hardware, but driver will accommodate the
+ * extra 4-byte VLAN tag for processing by upper layers
+ */
+ ndev->features |= NETIF_F_HW_VLAN_CTAG_RX;
+
+ /* setup NAPI interface */
+ netif_napi_add(ndev, &priv->napi, tse_poll, NAPI_POLL_WEIGHT);
+
+ spin_lock_init(&priv->mac_cfg_lock);
+ spin_lock_init(&priv->tx_lock);
+ spin_lock_init(&priv->rxdma_irq_lock);
+
+ ret = register_netdev(ndev);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to register TSE net device\n");
+ goto out_free_mdio;
+ }
+
+ platform_set_drvdata(pdev, ndev);
+
+ priv->revision = ioread32(&priv->mac_dev->megacore_revision);
+
+ if (netif_msg_probe(priv))
+ dev_info(&pdev->dev, "Altera TSE MAC version %d.%d at 0x%08lx irq %d/%d\n",
+ (priv->revision >> 8) & 0xff,
+ priv->revision & 0xff,
+ (unsigned long) control_port->start, priv->rx_irq,
+ priv->tx_irq);
+
+ ret = init_phy(ndev);
+ if (ret != 0) {
+ netdev_err(ndev, "Cannot attach to PHY (error: %d)\n", ret);
+ goto out_free_mdio;
+ }
+ return 0;
+
+out_free_mdio:
+ altera_tse_mdio_destroy(ndev);
+out_free:
+ free_netdev(ndev);
+ return ret;
+}
+
+/* Remove Altera TSE MAC device
+ */
+static int altera_tse_remove(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+
+ platform_set_drvdata(pdev, NULL);
+ altera_tse_mdio_destroy(ndev);
+ unregister_netdev(ndev);
+ free_netdev(ndev);
+
+ return 0;
+}
+
+struct altera_dmaops altera_dtype_sgdma = {
+ .altera_dtype = ALTERA_DTYPE_SGDMA,
+ .dmamask = 32,
+ .reset_dma = sgdma_reset,
+ .enable_txirq = sgdma_enable_txirq,
+ .enable_rxirq = sgdma_enable_rxirq,
+ .disable_txirq = sgdma_disable_txirq,
+ .disable_rxirq = sgdma_disable_rxirq,
+ .clear_txirq = sgdma_clear_txirq,
+ .clear_rxirq = sgdma_clear_rxirq,
+ .tx_buffer = sgdma_tx_buffer,
+ .tx_completions = sgdma_tx_completions,
+ .add_rx_desc = sgdma_add_rx_desc,
+ .get_rx_status = sgdma_rx_status,
+ .init_dma = sgdma_initialize,
+ .uninit_dma = sgdma_uninitialize,
+};
+
+struct altera_dmaops altera_dtype_msgdma = {
+ .altera_dtype = ALTERA_DTYPE_MSGDMA,
+ .dmamask = 64,
+ .reset_dma = msgdma_reset,
+ .enable_txirq = msgdma_enable_txirq,
+ .enable_rxirq = msgdma_enable_rxirq,
+ .disable_txirq = msgdma_disable_txirq,
+ .disable_rxirq = msgdma_disable_rxirq,
+ .clear_txirq = msgdma_clear_txirq,
+ .clear_rxirq = msgdma_clear_rxirq,
+ .tx_buffer = msgdma_tx_buffer,
+ .tx_completions = msgdma_tx_completions,
+ .add_rx_desc = msgdma_add_rx_desc,
+ .get_rx_status = msgdma_rx_status,
+ .init_dma = msgdma_initialize,
+ .uninit_dma = msgdma_uninitialize,
+};
+
+static struct of_device_id altera_tse_ids[] = {
+ { .compatible = "altr,tse-msgdma-1.0", .data = &altera_dtype_msgdma, },
+ { .compatible = "altr,tse-1.0", .data = &altera_dtype_sgdma, },
+ { .compatible = "ALTR,tse-1.0", .data = &altera_dtype_sgdma, },
+ {},
+};
+MODULE_DEVICE_TABLE(of, altera_tse_ids);
+
+static struct platform_driver altera_tse_driver = {
+ .probe = altera_tse_probe,
+ .remove = altera_tse_remove,
+ .suspend = NULL,
+ .resume = NULL,
+ .driver = {
+ .name = ALTERA_TSE_RESOURCE_NAME,
+ .owner = THIS_MODULE,
+ .of_match_table = altera_tse_ids,
+ },
+};
+
+module_platform_driver(altera_tse_driver);
+
+MODULE_AUTHOR("Altera Corporation");
+MODULE_DESCRIPTION("Altera Triple Speed Ethernet MAC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/altera/altera_utils.c b/drivers/net/ethernet/altera/altera_utils.c
new file mode 100644
index 0000000..70fa13f
--- /dev/null
+++ b/drivers/net/ethernet/altera/altera_utils.c
@@ -0,0 +1,44 @@
+/* Altera TSE SGDMA and MSGDMA Linux driver
+ * Copyright (C) 2014 Altera Corporation. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "altera_tse.h"
+#include "altera_utils.h"
+
+void tse_set_bit(void __iomem *ioaddr, u32 bit_mask)
+{
+ u32 value = ioread32(ioaddr);
+ value |= bit_mask;
+ iowrite32(value, ioaddr);
+}
+
+void tse_clear_bit(void __iomem *ioaddr, u32 bit_mask)
+{
+ u32 value = ioread32(ioaddr);
+ value &= ~bit_mask;
+ iowrite32(value, ioaddr);
+}
+
+int tse_bit_is_set(void __iomem *ioaddr, u32 bit_mask)
+{
+ u32 value = ioread32(ioaddr);
+ return (value & bit_mask) ? 1 : 0;
+}
+
+int tse_bit_is_clear(void __iomem *ioaddr, u32 bit_mask)
+{
+ u32 value = ioread32(ioaddr);
+ return (value & bit_mask) ? 0 : 1;
+}
diff --git a/drivers/net/ethernet/altera/altera_utils.h b/drivers/net/ethernet/altera/altera_utils.h
new file mode 100644
index 0000000..ce1db36
--- /dev/null
+++ b/drivers/net/ethernet/altera/altera_utils.h
@@ -0,0 +1,27 @@
+/* Altera TSE SGDMA and MSGDMA Linux driver
+ * Copyright (C) 2014 Altera Corporation. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kernel.h>
+
+#ifndef __ALTERA_UTILS_H__
+#define __ALTERA_UTILS_H__
+
+void tse_set_bit(void __iomem *ioaddr, u32 bit_mask);
+void tse_clear_bit(void __iomem *ioaddr, u32 bit_mask);
+int tse_bit_is_set(void __iomem *ioaddr, u32 bit_mask);
+int tse_bit_is_clear(void __iomem *ioaddr, u32 bit_mask);
+
+#endif /* __ALTERA_UTILS_H__*/
diff --git a/drivers/net/ethernet/amd/7990.c b/drivers/net/ethernet/amd/7990.c
index 18e542f..98a10d5 100644
--- a/drivers/net/ethernet/amd/7990.c
+++ b/drivers/net/ethernet/amd/7990.c
@@ -578,7 +578,7 @@
outs++;
/* Kick the lance: transmit now */
WRITERDP(lp, LE_C0_INEA | LE_C0_TDMD);
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
spin_lock_irqsave(&lp->devlock, flags);
if (TX_BUFFS_AVAIL)
diff --git a/drivers/net/ethernet/amd/am79c961a.c b/drivers/net/ethernet/amd/am79c961a.c
index 9793767..87e727b 100644
--- a/drivers/net/ethernet/amd/am79c961a.c
+++ b/drivers/net/ethernet/amd/am79c961a.c
@@ -472,7 +472,7 @@
if (am_readword(dev, priv->txhdr + (priv->txhead << 3) + 2) & TMD_OWN)
netif_stop_queue(dev);
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index 2061b47..26efaaa 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -720,6 +720,9 @@
int rx_pkt_limit = budget;
unsigned long flags;
+ if (rx_pkt_limit <= 0)
+ goto rx_not_empty;
+
do{
/* process receive packets until we use the quota*/
/* If we own the next entry, it's a new packet. Send it up. */
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index 9339ccc..e7cc917 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -549,35 +549,35 @@
struct pcnet32_rx_head *new_rx_ring;
struct sk_buff **new_skb_list;
int new, overlap;
+ unsigned int entries = 1 << size;
new_rx_ring = pci_alloc_consistent(lp->pci_dev,
sizeof(struct pcnet32_rx_head) *
- (1 << size),
+ entries,
&new_ring_dma_addr);
if (new_rx_ring == NULL) {
netif_err(lp, drv, dev, "Consistent memory allocation failed\n");
return;
}
- memset(new_rx_ring, 0, sizeof(struct pcnet32_rx_head) * (1 << size));
+ memset(new_rx_ring, 0, sizeof(struct pcnet32_rx_head) * entries);
- new_dma_addr_list = kcalloc(1 << size, sizeof(dma_addr_t), GFP_ATOMIC);
+ new_dma_addr_list = kcalloc(entries, sizeof(dma_addr_t), GFP_ATOMIC);
if (!new_dma_addr_list)
goto free_new_rx_ring;
- new_skb_list = kcalloc(1 << size, sizeof(struct sk_buff *),
- GFP_ATOMIC);
+ new_skb_list = kcalloc(entries, sizeof(struct sk_buff *), GFP_ATOMIC);
if (!new_skb_list)
goto free_new_lists;
/* first copy the current receive buffers */
- overlap = min(size, lp->rx_ring_size);
+ overlap = min(entries, lp->rx_ring_size);
for (new = 0; new < overlap; new++) {
new_rx_ring[new] = lp->rx_ring[new];
new_dma_addr_list[new] = lp->rx_dma_addr[new];
new_skb_list[new] = lp->rx_skbuff[new];
}
/* now allocate any new buffers needed */
- for (; new < size; new++) {
+ for (; new < entries; new++) {
struct sk_buff *rx_skbuff;
new_skb_list[new] = netdev_alloc_skb(dev, PKT_BUF_SKB);
rx_skbuff = new_skb_list[new];
@@ -592,6 +592,13 @@
new_dma_addr_list[new] =
pci_map_single(lp->pci_dev, rx_skbuff->data,
PKT_BUF_SIZE, PCI_DMA_FROMDEVICE);
+ if (pci_dma_mapping_error(lp->pci_dev,
+ new_dma_addr_list[new])) {
+ netif_err(lp, drv, dev, "%s dma mapping failed\n",
+ __func__);
+ dev_kfree_skb(new_skb_list[new]);
+ goto free_all_new;
+ }
new_rx_ring[new].base = cpu_to_le32(new_dma_addr_list[new]);
new_rx_ring[new].buf_length = cpu_to_le16(NEG_BUF_SIZE);
new_rx_ring[new].status = cpu_to_le16(0x8000);
@@ -599,8 +606,12 @@
/* and free any unneeded buffers */
for (; new < lp->rx_ring_size; new++) {
if (lp->rx_skbuff[new]) {
- pci_unmap_single(lp->pci_dev, lp->rx_dma_addr[new],
- PKT_BUF_SIZE, PCI_DMA_FROMDEVICE);
+ if (!pci_dma_mapping_error(lp->pci_dev,
+ lp->rx_dma_addr[new]))
+ pci_unmap_single(lp->pci_dev,
+ lp->rx_dma_addr[new],
+ PKT_BUF_SIZE,
+ PCI_DMA_FROMDEVICE);
dev_kfree_skb(lp->rx_skbuff[new]);
}
}
@@ -612,7 +623,7 @@
lp->rx_ring_size, lp->rx_ring,
lp->rx_ring_dma_addr);
- lp->rx_ring_size = (1 << size);
+ lp->rx_ring_size = entries;
lp->rx_mod_mask = lp->rx_ring_size - 1;
lp->rx_len_bits = (size << 4);
lp->rx_ring = new_rx_ring;
@@ -624,8 +635,12 @@
free_all_new:
while (--new >= lp->rx_ring_size) {
if (new_skb_list[new]) {
- pci_unmap_single(lp->pci_dev, new_dma_addr_list[new],
- PKT_BUF_SIZE, PCI_DMA_FROMDEVICE);
+ if (!pci_dma_mapping_error(lp->pci_dev,
+ new_dma_addr_list[new]))
+ pci_unmap_single(lp->pci_dev,
+ new_dma_addr_list[new],
+ PKT_BUF_SIZE,
+ PCI_DMA_FROMDEVICE);
dev_kfree_skb(new_skb_list[new]);
}
}
@@ -634,8 +649,7 @@
kfree(new_dma_addr_list);
free_new_rx_ring:
pci_free_consistent(lp->pci_dev,
- sizeof(struct pcnet32_rx_head) *
- (1 << size),
+ sizeof(struct pcnet32_rx_head) * entries,
new_rx_ring,
new_ring_dma_addr);
}
@@ -650,8 +664,12 @@
lp->rx_ring[i].status = 0; /* CPU owns buffer */
wmb(); /* Make sure adapter sees owner change */
if (lp->rx_skbuff[i]) {
- pci_unmap_single(lp->pci_dev, lp->rx_dma_addr[i],
- PKT_BUF_SIZE, PCI_DMA_FROMDEVICE);
+ if (!pci_dma_mapping_error(lp->pci_dev,
+ lp->rx_dma_addr[i]))
+ pci_unmap_single(lp->pci_dev,
+ lp->rx_dma_addr[i],
+ PKT_BUF_SIZE,
+ PCI_DMA_FROMDEVICE);
dev_kfree_skb_any(lp->rx_skbuff[i]);
}
lp->rx_skbuff[i] = NULL;
@@ -930,6 +948,12 @@
lp->tx_dma_addr[x] =
pci_map_single(lp->pci_dev, skb->data, skb->len,
PCI_DMA_TODEVICE);
+ if (pci_dma_mapping_error(lp->pci_dev, lp->tx_dma_addr[x])) {
+ netif_printk(lp, hw, KERN_DEBUG, dev,
+ "DMA mapping error at line: %d!\n",
+ __LINE__);
+ goto clean_up;
+ }
lp->tx_ring[x].base = cpu_to_le32(lp->tx_dma_addr[x]);
wmb(); /* Make sure owner changes after all others are visible */
lp->tx_ring[x].status = cpu_to_le16(status);
@@ -1142,24 +1166,36 @@
if (pkt_len > rx_copybreak) {
struct sk_buff *newskb;
+ dma_addr_t new_dma_addr;
newskb = netdev_alloc_skb(dev, PKT_BUF_SKB);
+ /*
+ * map the new buffer, if mapping fails, drop the packet and
+ * reuse the old buffer
+ */
if (newskb) {
skb_reserve(newskb, NET_IP_ALIGN);
- skb = lp->rx_skbuff[entry];
- pci_unmap_single(lp->pci_dev,
- lp->rx_dma_addr[entry],
- PKT_BUF_SIZE,
- PCI_DMA_FROMDEVICE);
- skb_put(skb, pkt_len);
- lp->rx_skbuff[entry] = newskb;
- lp->rx_dma_addr[entry] =
- pci_map_single(lp->pci_dev,
- newskb->data,
- PKT_BUF_SIZE,
- PCI_DMA_FROMDEVICE);
- rxp->base = cpu_to_le32(lp->rx_dma_addr[entry]);
- rx_in_place = 1;
+ new_dma_addr = pci_map_single(lp->pci_dev,
+ newskb->data,
+ PKT_BUF_SIZE,
+ PCI_DMA_FROMDEVICE);
+ if (pci_dma_mapping_error(lp->pci_dev, new_dma_addr)) {
+ netif_err(lp, rx_err, dev,
+ "DMA mapping error.\n");
+ dev_kfree_skb(newskb);
+ skb = NULL;
+ } else {
+ skb = lp->rx_skbuff[entry];
+ pci_unmap_single(lp->pci_dev,
+ lp->rx_dma_addr[entry],
+ PKT_BUF_SIZE,
+ PCI_DMA_FROMDEVICE);
+ skb_put(skb, pkt_len);
+ lp->rx_skbuff[entry] = newskb;
+ lp->rx_dma_addr[entry] = new_dma_addr;
+ rxp->base = cpu_to_le32(new_dma_addr);
+ rx_in_place = 1;
+ }
} else
skb = NULL;
} else
@@ -2229,9 +2265,12 @@
lp->tx_ring[i].status = 0; /* CPU owns buffer */
wmb(); /* Make sure adapter sees owner change */
if (lp->tx_skbuff[i]) {
- pci_unmap_single(lp->pci_dev, lp->tx_dma_addr[i],
- lp->tx_skbuff[i]->len,
- PCI_DMA_TODEVICE);
+ if (!pci_dma_mapping_error(lp->pci_dev,
+ lp->tx_dma_addr[i]))
+ pci_unmap_single(lp->pci_dev,
+ lp->tx_dma_addr[i],
+ lp->tx_skbuff[i]->len,
+ PCI_DMA_TODEVICE);
dev_kfree_skb_any(lp->tx_skbuff[i]);
}
lp->tx_skbuff[i] = NULL;
@@ -2264,10 +2303,19 @@
}
rmb();
- if (lp->rx_dma_addr[i] == 0)
+ if (lp->rx_dma_addr[i] == 0) {
lp->rx_dma_addr[i] =
pci_map_single(lp->pci_dev, rx_skbuff->data,
PKT_BUF_SIZE, PCI_DMA_FROMDEVICE);
+ if (pci_dma_mapping_error(lp->pci_dev,
+ lp->rx_dma_addr[i])) {
+ /* there is not much we can do at this point */
+ netif_err(lp, drv, dev,
+ "%s pci dma mapping error\n",
+ __func__);
+ return -1;
+ }
+ }
lp->rx_ring[i].base = cpu_to_le32(lp->rx_dma_addr[i]);
lp->rx_ring[i].buf_length = cpu_to_le16(NEG_BUF_SIZE);
wmb(); /* Make sure owner changes after all others are visible */
@@ -2397,9 +2445,14 @@
lp->tx_ring[entry].misc = 0x00000000;
- lp->tx_skbuff[entry] = skb;
lp->tx_dma_addr[entry] =
pci_map_single(lp->pci_dev, skb->data, skb->len, PCI_DMA_TODEVICE);
+ if (pci_dma_mapping_error(lp->pci_dev, lp->tx_dma_addr[entry])) {
+ dev_kfree_skb_any(skb);
+ dev->stats.tx_dropped++;
+ goto drop_packet;
+ }
+ lp->tx_skbuff[entry] = skb;
lp->tx_ring[entry].base = cpu_to_le32(lp->tx_dma_addr[entry]);
wmb(); /* Make sure owner changes after all others are visible */
lp->tx_ring[entry].status = cpu_to_le16(status);
@@ -2414,6 +2467,7 @@
lp->tx_full = 1;
netif_stop_queue(dev);
}
+drop_packet:
spin_unlock_irqrestore(&lp->lock, flags);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index e92ffd6..17bb9ce 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -535,7 +535,7 @@
if (!alx->descmem.virt)
goto out_free;
- alx->txq.tpd = (void *)alx->descmem.virt;
+ alx->txq.tpd = alx->descmem.virt;
alx->txq.tpd_dma = alx->descmem.dma;
/* alignment requirement for next block */
@@ -1097,7 +1097,7 @@
return NETDEV_TX_OK;
drop:
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -1248,19 +1248,13 @@
* shared register for the high 32 bits, so only a single, aligned,
* 4 GB physical address range can be used for descriptors.
*/
- if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) &&
- !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) {
+ if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
dev_dbg(&pdev->dev, "DMA to 64-BIT addresses\n");
} else {
- err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
if (err) {
- err = dma_set_coherent_mask(&pdev->dev,
- DMA_BIT_MASK(32));
- if (err) {
- dev_err(&pdev->dev,
- "No usable DMA config, aborting\n");
- goto out_pci_disable;
- }
+ dev_err(&pdev->dev, "No usable DMA config, aborting\n");
+ goto out_pci_disable;
}
}
@@ -1292,6 +1286,7 @@
alx = netdev_priv(netdev);
spin_lock_init(&alx->hw.mdio_lock);
spin_lock_init(&alx->irq_lock);
+ spin_lock_init(&alx->stats_lock);
alx->dev = netdev;
alx->hw.pdev = pdev;
alx->msg_enable = NETIF_MSG_LINK | NETIF_MSG_HW | NETIF_MSG_IFUP |
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 4d3258d..e11bf18 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -832,7 +832,7 @@
}
static inline void atl1c_clean_buffer(struct pci_dev *pdev,
- struct atl1c_buffer *buffer_info, int in_irq)
+ struct atl1c_buffer *buffer_info)
{
u16 pci_driection;
if (buffer_info->flags & ATL1C_BUFFER_FREE)
@@ -850,12 +850,8 @@
pci_unmap_page(pdev, buffer_info->dma,
buffer_info->length, pci_driection);
}
- if (buffer_info->skb) {
- if (in_irq)
- dev_kfree_skb_irq(buffer_info->skb);
- else
- dev_kfree_skb(buffer_info->skb);
- }
+ if (buffer_info->skb)
+ dev_consume_skb_any(buffer_info->skb);
buffer_info->dma = 0;
buffer_info->skb = NULL;
ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_FREE);
@@ -875,7 +871,7 @@
ring_count = tpd_ring->count;
for (index = 0; index < ring_count; index++) {
buffer_info = &tpd_ring->buffer_info[index];
- atl1c_clean_buffer(pdev, buffer_info, 0);
+ atl1c_clean_buffer(pdev, buffer_info);
}
/* Zero out Tx-buffers */
@@ -899,7 +895,7 @@
for (j = 0; j < rfd_ring->count; j++) {
buffer_info = &rfd_ring->buffer_info[j];
- atl1c_clean_buffer(pdev, buffer_info, 0);
+ atl1c_clean_buffer(pdev, buffer_info);
}
/* zero out the descriptor ring */
memset(rfd_ring->desc, 0, rfd_ring->size);
@@ -1562,7 +1558,7 @@
while (next_to_clean != hw_next_to_clean) {
buffer_info = &tpd_ring->buffer_info[next_to_clean];
- atl1c_clean_buffer(pdev, buffer_info, 1);
+ atl1c_clean_buffer(pdev, buffer_info);
if (++next_to_clean == tpd_ring->count)
next_to_clean = 0;
atomic_set(&tpd_ring->next_to_clean, next_to_clean);
@@ -1977,17 +1973,17 @@
enum atl1c_trans_queue type)
{
struct pci_dev *pdev = adapter->pdev;
+ unsigned short offload_type;
u8 hdr_len;
u32 real_len;
- unsigned short offload_type;
- int err;
if (skb_is_gso(skb)) {
- if (skb_header_cloned(skb)) {
- err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (unlikely(err))
- return -1;
- }
+ int err;
+
+ err = skb_cow_head(skb, 0);
+ if (err < 0)
+ return err;
+
offload_type = skb_shinfo(skb)->gso_type;
if (offload_type & SKB_GSO_TCPV4) {
@@ -2085,7 +2081,7 @@
while (index != tpd_ring->next_to_use) {
tpd = ATL1C_TPD_DESC(tpd_ring, index);
buffer_info = &tpd_ring->buffer_info[index];
- atl1c_clean_buffer(adpt->pdev, buffer_info, 0);
+ atl1c_clean_buffer(adpt->pdev, buffer_info);
memset(tpd, 0, sizeof(struct atl1c_tpd_desc));
if (++index == tpd_ring->count)
index = 0;
@@ -2258,7 +2254,7 @@
/* roll back tpd/buffer */
atl1c_tx_rollback(adapter, tpd, type);
spin_unlock_irqrestore(&adapter->tx_lock, flags);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
} else {
atl1c_tx_queue(adapter, skb, tpd, type);
spin_unlock_irqrestore(&adapter->tx_lock, flags);
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index d5c2d3e..4345332 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -1641,17 +1641,17 @@
static int atl1e_tso_csum(struct atl1e_adapter *adapter,
struct sk_buff *skb, struct atl1e_tpd_desc *tpd)
{
+ unsigned short offload_type;
u8 hdr_len;
u32 real_len;
- unsigned short offload_type;
- int err;
if (skb_is_gso(skb)) {
- if (skb_header_cloned(skb)) {
- err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (unlikely(err))
- return -1;
- }
+ int err;
+
+ err = skb_cow_head(skb, 0);
+ if (err < 0)
+ return err;
+
offload_type = skb_shinfo(skb)->gso_type;
if (offload_type & SKB_GSO_TCPV4) {
@@ -2436,7 +2436,7 @@
err_register:
err_sw_init:
err_eeprom:
- iounmap(adapter->hw.hw_addr);
+ pci_iounmap(pdev, adapter->hw.hw_addr);
err_init_netdev:
err_ioremap:
free_netdev(netdev);
@@ -2474,7 +2474,7 @@
unregister_netdev(netdev);
atl1e_free_ring_resources(adapter);
atl1e_force_ps(&adapter->hw);
- iounmap(adapter->hw.hw_addr);
+ pci_iounmap(pdev, adapter->hw.hw_addr);
pci_release_regions(pdev);
free_netdev(netdev);
pci_disable_device(pdev);
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 287272d..dfd0e91 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -2118,18 +2118,17 @@
}
static int atl1_tso(struct atl1_adapter *adapter, struct sk_buff *skb,
- struct tx_packet_desc *ptpd)
+ struct tx_packet_desc *ptpd)
{
u8 hdr_len, ip_off;
u32 real_len;
- int err;
if (skb_shinfo(skb)->gso_size) {
- if (skb_header_cloned(skb)) {
- err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (unlikely(err))
- return -1;
- }
+ int err;
+
+ err = skb_cow_head(skb, 0);
+ if (err < 0)
+ return err;
if (skb->protocol == htons(ETH_P_IP)) {
struct iphdr *iph = ip_hdr(skb);
@@ -2175,7 +2174,7 @@
return 3;
}
}
- return false;
+ return 0;
}
static int atl1_tx_csum(struct atl1_adapter *adapter, struct sk_buff *skb,
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index 265ce1b..78befb5 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -55,6 +55,7 @@
static const char atl2_driver_string[] = "Atheros(R) L2 Ethernet Driver";
static const char atl2_copyright[] = "Copyright (c) 2007 Atheros Corporation.";
static const char atl2_driver_version[] = ATL2_DRV_VERSION;
+static const struct ethtool_ops atl2_ethtool_ops;
MODULE_AUTHOR("Atheros Corporation <xiong.huang@atheros.com>, Chris Snook <csnook@redhat.com>");
MODULE_DESCRIPTION("Atheros Fast Ethernet Network Driver");
@@ -71,8 +72,6 @@
};
MODULE_DEVICE_TABLE(pci, atl2_pci_tbl);
-static void atl2_set_ethtool_ops(struct net_device *netdev);
-
static void atl2_check_options(struct atl2_adapter *adapter);
/**
@@ -1397,7 +1396,7 @@
atl2_setup_pcicmd(pdev);
netdev->netdev_ops = &atl2_netdev_ops;
- atl2_set_ethtool_ops(netdev);
+ SET_ETHTOOL_OPS(netdev, &atl2_ethtool_ops);
netdev->watchdog_timeo = 5 * HZ;
strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1);
@@ -2105,11 +2104,6 @@
.set_eeprom = atl2_set_eeprom,
};
-static void atl2_set_ethtool_ops(struct net_device *netdev)
-{
- SET_ETHTOOL_OPS(netdev, &atl2_ethtool_ops);
-}
-
#define LBYTESWAP(a) ((((a) & 0x00ff00ff) << 8) | \
(((a) & 0xff00ff00) >> 8))
#define LONGSWAP(a) ((LBYTESWAP(a) << 16) | (LBYTESWAP(a) >> 16))
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 3f97d9f..85dbddd 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -60,6 +60,17 @@
This driver supports the ethernet MACs in the Broadcom 63xx
MIPS chipset family (BCM63XX).
+config BCMGENET
+ tristate "Broadcom GENET internal MAC support"
+ depends on OF
+ select MII
+ select PHYLIB
+ select FIXED_PHY if BCMGENET=y
+ select BCM7XXX_PHY
+ help
+ This driver supports the built-in Ethernet MACs found in the
+ Broadcom BCM7xxx Set Top Box family chipset.
+
config BNX2
tristate "Broadcom NetXtremeII support"
depends on PCI
diff --git a/drivers/net/ethernet/broadcom/Makefile b/drivers/net/ethernet/broadcom/Makefile
index 68efa1a..fd639a0 100644
--- a/drivers/net/ethernet/broadcom/Makefile
+++ b/drivers/net/ethernet/broadcom/Makefile
@@ -4,6 +4,7 @@
obj-$(CONFIG_B44) += b44.o
obj-$(CONFIG_BCM63XX_ENET) += bcm63xx_enet.o
+obj-$(CONFIG_BCMGENET) += genet/
obj-$(CONFIG_BNX2) += bnx2.o
obj-$(CONFIG_CNIC) += cnic.o
obj-$(CONFIG_BNX2X) += bnx2x/
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 1f7b5aa..05ba625 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -1484,6 +1484,10 @@
add_timer(&bp->timer);
b44_enable_ints(bp);
+
+ if (bp->flags & B44_FLAG_EXTERNAL_PHY)
+ phy_start(bp->phydev);
+
netif_start_queue(dev);
out:
return err;
@@ -1646,6 +1650,9 @@
netif_stop_queue(dev);
+ if (bp->flags & B44_FLAG_EXTERNAL_PHY)
+ phy_stop(bp->phydev);
+
napi_disable(&bp->napi);
del_timer_sync(&bp->timer);
@@ -1678,7 +1685,7 @@
unsigned int start;
do {
- start = u64_stats_fetch_begin_bh(&hwstat->syncp);
+ start = u64_stats_fetch_begin_irq(&hwstat->syncp);
/* Convert HW stats into rtnl_link_stats64 stats. */
nstat->rx_packets = hwstat->rx_pkts;
@@ -1712,7 +1719,7 @@
/* Carrier lost counter seems to be broken for some devices */
nstat->tx_carrier_errors = hwstat->tx_carrier_lost;
#endif
- } while (u64_stats_fetch_retry_bh(&hwstat->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&hwstat->syncp, start));
return nstat;
}
@@ -2066,12 +2073,12 @@
do {
data_src = &hwstat->tx_good_octets;
data_dst = data;
- start = u64_stats_fetch_begin_bh(&hwstat->syncp);
+ start = u64_stats_fetch_begin_irq(&hwstat->syncp);
for (i = 0; i < ARRAY_SIZE(b44_gstrings); i++)
*data_dst++ = *data_src++;
- } while (u64_stats_fetch_retry_bh(&hwstat->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&hwstat->syncp, start));
}
static void b44_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
@@ -2222,7 +2229,12 @@
}
if (status_changed) {
- b44_check_phy(bp);
+ u32 val = br32(bp, B44_TX_CTRL);
+ if (bp->flags & B44_FLAG_FULL_DUPLEX)
+ val |= TX_CTRL_DUPLEX;
+ else
+ val &= ~TX_CTRL_DUPLEX;
+ bw32(bp, B44_TX_CTRL, val);
phy_print_status(phydev);
}
}
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index b9a5fb6..a7d11f5 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -1722,9 +1722,6 @@
.ndo_set_rx_mode = bcm_enet_set_multicast_list,
.ndo_do_ioctl = bcm_enet_ioctl,
.ndo_change_mtu = bcm_enet_change_mtu,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = bcm_enet_netpoll,
-#endif
};
/*
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 9d2deda..a8efb18 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -85,7 +85,7 @@
static int disable_msi = 0;
-module_param(disable_msi, int, 0);
+module_param(disable_msi, int, S_IRUGO);
MODULE_PARM_DESC(disable_msi, "Disable Message Signaled Interrupt (MSI)");
typedef enum {
@@ -2507,6 +2507,7 @@
bp->fw_wr_seq++;
msg_data |= bp->fw_wr_seq;
+ bp->fw_last_msg = msg_data;
bnx2_shmem_wr(bp, BNX2_DRV_MB, msg_data);
@@ -2885,7 +2886,7 @@
sw_cons = BNX2_NEXT_TX_BD(sw_cons);
tx_bytes += skb->len;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
tx_pkt++;
if (tx_pkt == budget)
break;
@@ -3132,6 +3133,9 @@
struct l2_fhdr *rx_hdr;
int rx_pkt = 0, pg_ring_used = 0;
+ if (budget <= 0)
+ return rx_pkt;
+
hw_cons = bnx2_get_hw_rx_cons(bnapi);
sw_cons = rxr->rx_cons;
sw_prod = rxr->rx_prod;
@@ -4000,8 +4004,23 @@
wol_msg = BNX2_DRV_MSG_CODE_SUSPEND_NO_WOL;
}
- if (!(bp->flags & BNX2_FLAG_NO_WOL))
- bnx2_fw_sync(bp, BNX2_DRV_MSG_DATA_WAIT3 | wol_msg, 1, 0);
+ if (!(bp->flags & BNX2_FLAG_NO_WOL)) {
+ u32 val;
+
+ wol_msg |= BNX2_DRV_MSG_DATA_WAIT3;
+ if (bp->fw_last_msg || BNX2_CHIP(bp) != BNX2_CHIP_5709) {
+ bnx2_fw_sync(bp, wol_msg, 1, 0);
+ return;
+ }
+ /* Tell firmware not to power down the PHY yet, otherwise
+ * the chip will take a long time to respond to MMIO reads.
+ */
+ val = bnx2_shmem_rd(bp, BNX2_PORT_FEATURE);
+ bnx2_shmem_wr(bp, BNX2_PORT_FEATURE,
+ val | BNX2_PORT_FEATURE_ASF_ENABLED);
+ bnx2_fw_sync(bp, wol_msg, 1, 0);
+ bnx2_shmem_wr(bp, BNX2_PORT_FEATURE, val);
+ }
}
@@ -4033,9 +4052,22 @@
if (bp->wol)
pci_set_power_state(bp->pdev, PCI_D3hot);
- } else {
- pci_set_power_state(bp->pdev, PCI_D3hot);
+ break;
+
}
+ if (!bp->fw_last_msg && BNX2_CHIP(bp) == BNX2_CHIP_5709) {
+ u32 val;
+
+ /* Tell firmware not to power down the PHY yet,
+ * otherwise the other port may not respond to
+ * MMIO reads.
+ */
+ val = bnx2_shmem_rd(bp, BNX2_BC_STATE_CONDITION);
+ val &= ~BNX2_CONDITION_PM_STATE_MASK;
+ val |= BNX2_CONDITION_PM_STATE_UNPREP;
+ bnx2_shmem_wr(bp, BNX2_BC_STATE_CONDITION, val);
+ }
+ pci_set_power_state(bp->pdev, PCI_D3hot);
/* No more memory access after this point until
* device is brought back to D0.
@@ -6206,7 +6238,7 @@
static void
bnx2_enable_msix(struct bnx2 *bp, int msix_vecs)
{
- int i, total_vecs, rc;
+ int i, total_vecs;
struct msix_entry msix_ent[BNX2_MAX_MSIX_VEC];
struct net_device *dev = bp->dev;
const int len = sizeof(bp->irq_tbl[0].name);
@@ -6229,16 +6261,9 @@
#ifdef BCM_CNIC
total_vecs++;
#endif
- rc = -ENOSPC;
- while (total_vecs >= BNX2_MIN_MSIX_VEC) {
- rc = pci_enable_msix(bp->pdev, msix_ent, total_vecs);
- if (rc <= 0)
- break;
- if (rc > 0)
- total_vecs = rc;
- }
-
- if (rc != 0)
+ total_vecs = pci_enable_msix_range(bp->pdev, msix_ent,
+ BNX2_MIN_MSIX_VEC, total_vecs);
+ if (total_vecs < 0)
return;
msix_vecs = total_vecs;
@@ -6611,7 +6636,7 @@
mapping = dma_map_single(&bp->pdev->dev, skb->data, len, PCI_DMA_TODEVICE);
if (dma_mapping_error(&bp->pdev->dev, mapping)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -6704,7 +6729,7 @@
PCI_DMA_TODEVICE);
}
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/broadcom/bnx2.h b/drivers/net/ethernet/broadcom/bnx2.h
index f1cf2c4..e341bc3 100644
--- a/drivers/net/ethernet/broadcom/bnx2.h
+++ b/drivers/net/ethernet/broadcom/bnx2.h
@@ -6900,6 +6900,7 @@
u16 fw_wr_seq;
u16 fw_drv_pulse_wr_seq;
+ u32 fw_last_msg;
int rx_max_ring;
int rx_ring_size;
@@ -7406,6 +7407,10 @@
#define BNX2_CONDITION_MFW_RUN_NCSI 0x00006000
#define BNX2_CONDITION_MFW_RUN_NONE 0x0000e000
#define BNX2_CONDITION_MFW_RUN_MASK 0x0000e000
+#define BNX2_CONDITION_PM_STATE_MASK 0x00030000
+#define BNX2_CONDITION_PM_STATE_FULL 0x00030000
+#define BNX2_CONDITION_PM_STATE_PREP 0x00020000
+#define BNX2_CONDITION_PM_STATE_UNPREP 0x00010000
#define BNX2_BC_STATE_DEBUG_CMD 0x1dc
#define BNX2_BC_STATE_BC_DBG_CMD_SIGNATURE 0x42440000
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 391f29e..4d8f8ab 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -26,8 +26,8 @@
* (you will need to reboot afterwards) */
/* #define BNX2X_STOP_ON_ERROR */
-#define DRV_MODULE_VERSION "1.78.17-0"
-#define DRV_MODULE_RELDATE "2013/04/11"
+#define DRV_MODULE_VERSION "1.78.19-0"
+#define DRV_MODULE_RELDATE "2014/02/10"
#define BNX2X_BC_VER 0x040200
#if defined(CONFIG_DCB)
@@ -75,13 +75,22 @@
#define BNX2X_MSG_DCB 0x8000000
/* regular debug print */
+#define DP_INNER(fmt, ...) \
+ pr_notice("[%s:%d(%s)]" fmt, \
+ __func__, __LINE__, \
+ bp->dev ? (bp->dev->name) : "?", \
+ ##__VA_ARGS__);
+
#define DP(__mask, fmt, ...) \
do { \
if (unlikely(bp->msg_enable & (__mask))) \
- pr_notice("[%s:%d(%s)]" fmt, \
- __func__, __LINE__, \
- bp->dev ? (bp->dev->name) : "?", \
- ##__VA_ARGS__); \
+ DP_INNER(fmt, ##__VA_ARGS__); \
+} while (0)
+
+#define DP_AND(__mask, fmt, ...) \
+do { \
+ if (unlikely((bp->msg_enable & (__mask)) == __mask)) \
+ DP_INNER(fmt, ##__VA_ARGS__); \
} while (0)
#define DP_CONT(__mask, fmt, ...) \
@@ -1146,10 +1155,6 @@
(offsetof(struct bnx2x_eth_stats, stat_name) / 4)
/* slow path */
-
-/* slow path work-queue */
-extern struct workqueue_struct *bnx2x_wq;
-
#define BNX2X_MAX_NUM_OF_VFS 64
#define BNX2X_VF_CID_WND 4 /* log num of queues per VF. HW config. */
#define BNX2X_CIDS_PER_VF (1 << BNX2X_VF_CID_WND)
@@ -1261,6 +1266,7 @@
union {
struct client_init_ramrod_data init_data;
struct client_update_ramrod_data update_data;
+ struct tpa_update_ramrod_data tpa_data;
} q_rdata;
union {
@@ -1392,7 +1398,7 @@
};
/* Public slow path states */
-enum {
+enum sp_rtnl_flag {
BNX2X_SP_RTNL_SETUP_TC,
BNX2X_SP_RTNL_TX_TIMEOUT,
BNX2X_SP_RTNL_FAN_FAILURE,
@@ -1403,6 +1409,12 @@
BNX2X_SP_RTNL_RX_MODE,
BNX2X_SP_RTNL_HYPERVISOR_VLAN,
BNX2X_SP_RTNL_TX_STOP,
+ BNX2X_SP_RTNL_GET_DRV_VERSION,
+};
+
+enum bnx2x_iov_flag {
+ BNX2X_IOV_HANDLE_VF_MSG,
+ BNX2X_IOV_HANDLE_FLR,
};
struct bnx2x_prev_path_list {
@@ -1603,6 +1615,8 @@
int mrrs;
struct delayed_work sp_task;
+ struct delayed_work iov_task;
+
atomic_t interrupt_occurred;
struct delayed_work sp_rtnl_task;
@@ -1693,6 +1707,10 @@
struct bnx2x_slowpath *slowpath;
dma_addr_t slowpath_mapping;
+ /* Mechanism protecting the drv_info_to_mcp */
+ struct mutex drv_info_mutex;
+ bool drv_info_mng_owner;
+
/* Total number of FW statistics requests */
u8 fw_stats_num;
@@ -1882,6 +1900,9 @@
/* operation indication for the sp_rtnl task */
unsigned long sp_rtnl_state;
+ /* Indication of the IOV tasks */
+ unsigned long iov_task_state;
+
/* DCBX Negotiation results */
struct dcbx_features dcbx_local_feat;
u32 dcbx_error;
@@ -2525,6 +2546,8 @@
void bnx2x_set_local_cmng(struct bnx2x *bp);
+void bnx2x_update_mng_version(struct bnx2x *bp);
+
#define MCPR_SCRATCH_BASE(bp) \
(CHIP_IS_E1x(bp) ? MCP_REG_MCPR_SCRATCH : MCP_A_REG_MCPR_SCRATCH)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 9d7419e..9261d53 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -61,10 +61,14 @@
static int bnx2x_calc_num_queues(struct bnx2x *bp)
{
- return bnx2x_num_queues ?
- min_t(int, bnx2x_num_queues, BNX2X_MAX_QUEUES(bp)) :
- min_t(int, netif_get_num_default_rss_queues(),
- BNX2X_MAX_QUEUES(bp));
+ int nq = bnx2x_num_queues ? : netif_get_num_default_rss_queues();
+
+ /* Reduce memory usage in kdump environment by using only one queue */
+ if (reset_devices)
+ nq = 1;
+
+ nq = clamp(nq, 1, BNX2X_MAX_QUEUES(bp));
+ return nq;
}
/**
@@ -868,6 +872,8 @@
if (unlikely(bp->panic))
return 0;
#endif
+ if (budget <= 0)
+ return rx_pkt;
bd_cons = fp->rx_bd_cons;
bd_prod = fp->rx_bd_prod;
@@ -1638,36 +1644,16 @@
DP(BNX2X_MSG_SP, "about to request enable msix with %d vectors\n",
msix_vec);
- rc = pci_enable_msix(bp->pdev, &bp->msix_table[0], msix_vec);
-
+ rc = pci_enable_msix_range(bp->pdev, &bp->msix_table[0],
+ BNX2X_MIN_MSIX_VEC_CNT(bp), msix_vec);
/*
* reconfigure number of tx/rx queues according to available
* MSI-X vectors
*/
- if (rc >= BNX2X_MIN_MSIX_VEC_CNT(bp)) {
- /* how less vectors we will have? */
- int diff = msix_vec - rc;
-
- BNX2X_DEV_INFO("Trying to use less MSI-X vectors: %d\n", rc);
-
- rc = pci_enable_msix(bp->pdev, &bp->msix_table[0], rc);
-
- if (rc) {
- BNX2X_DEV_INFO("MSI-X is not attainable rc %d\n", rc);
- goto no_msix;
- }
- /*
- * decrease number of queues by number of unallocated entries
- */
- bp->num_ethernet_queues -= diff;
- bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues;
-
- BNX2X_DEV_INFO("New queue configuration set: %d\n",
- bp->num_queues);
- } else if (rc > 0) {
+ if (rc == -ENOSPC) {
/* Get by with single vector */
- rc = pci_enable_msix(bp->pdev, &bp->msix_table[0], 1);
- if (rc) {
+ rc = pci_enable_msix_range(bp->pdev, &bp->msix_table[0], 1, 1);
+ if (rc < 0) {
BNX2X_DEV_INFO("Single MSI-X is not attainable rc %d\n",
rc);
goto no_msix;
@@ -1680,8 +1666,22 @@
bp->num_ethernet_queues = 1;
bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues;
} else if (rc < 0) {
- BNX2X_DEV_INFO("MSI-X is not attainable rc %d\n", rc);
+ BNX2X_DEV_INFO("MSI-X is not attainable rc %d\n", rc);
goto no_msix;
+ } else if (rc < msix_vec) {
+ /* how less vectors we will have? */
+ int diff = msix_vec - rc;
+
+ BNX2X_DEV_INFO("Trying to use less MSI-X vectors: %d\n", rc);
+
+ /*
+ * decrease number of queues by number of unallocated entries
+ */
+ bp->num_ethernet_queues -= diff;
+ bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues;
+
+ BNX2X_DEV_INFO("New queue configuration set: %d\n",
+ bp->num_queues);
}
bp->flags |= USING_MSIX_FLAG;
@@ -1873,7 +1873,7 @@
}
u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv, select_queue_fallback_t fallback)
{
struct bnx2x *bp = netdev_priv(dev);
@@ -1895,7 +1895,7 @@
}
/* select a non-FCoE queue */
- return __netdev_pick_tx(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp);
+ return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp);
}
void bnx2x_set_num_queues(struct bnx2x *bp)
@@ -2234,8 +2234,10 @@
sizeof(struct per_queue_stats) * num_queue_stats +
sizeof(struct stats_counter);
- BNX2X_PCI_ALLOC(bp->fw_stats, &bp->fw_stats_mapping,
- bp->fw_stats_data_sz + bp->fw_stats_req_sz);
+ bp->fw_stats = BNX2X_PCI_ALLOC(&bp->fw_stats_mapping,
+ bp->fw_stats_data_sz + bp->fw_stats_req_sz);
+ if (!bp->fw_stats)
+ goto alloc_mem_err;
/* Set shortcuts */
bp->fw_stats_req = (struct bnx2x_fw_stats_req *)bp->fw_stats;
@@ -2802,6 +2804,9 @@
if (CNIC_ENABLED(bp))
bnx2x_load_cnic(bp);
+ if (IS_PF(bp))
+ bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_GET_DRV_VERSION, 0);
+
if (IS_PF(bp) && SHMEM2_HAS(bp, drv_capabilities_flag)) {
/* mark driver is loaded in shmem2 */
u32 val;
@@ -3028,6 +3033,10 @@
bp->state = BNX2X_STATE_CLOSED;
bp->cnic_loaded = false;
+ /* Clear driver version indication in shmem */
+ if (IS_PF(bp))
+ bnx2x_update_mng_version(bp);
+
/* Check if there are pending parity attentions. If there are - set
* RECOVERY_IN_PROGRESS.
*/
@@ -3875,7 +3884,9 @@
xmit_type);
}
- /* Add the macs to the parsing BD this is a vf */
+ /* Add the macs to the parsing BD if this is a vf or if
+ * Tx Switching is enabled.
+ */
if (IS_VF(bp)) {
/* override GRE parameters in BD */
bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.src_hi,
@@ -3887,6 +3898,11 @@
&pbd_e2->data.mac_addr.dst_mid,
&pbd_e2->data.mac_addr.dst_lo,
eth->h_dest);
+ } else if (bp->flags & TX_SWITCHING) {
+ bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.dst_hi,
+ &pbd_e2->data.mac_addr.dst_mid,
+ &pbd_e2->data.mac_addr.dst_lo,
+ eth->h_dest);
}
SET_FLAG(pbd_e2_parsing_data,
@@ -4363,14 +4379,17 @@
if (!IS_FCOE_IDX(index)) {
/* status blocks */
- if (!CHIP_IS_E1x(bp))
- BNX2X_PCI_ALLOC(sb->e2_sb,
- &bnx2x_fp(bp, index, status_blk_mapping),
- sizeof(struct host_hc_status_block_e2));
- else
- BNX2X_PCI_ALLOC(sb->e1x_sb,
- &bnx2x_fp(bp, index, status_blk_mapping),
- sizeof(struct host_hc_status_block_e1x));
+ if (!CHIP_IS_E1x(bp)) {
+ sb->e2_sb = BNX2X_PCI_ALLOC(&bnx2x_fp(bp, index, status_blk_mapping),
+ sizeof(struct host_hc_status_block_e2));
+ if (!sb->e2_sb)
+ goto alloc_mem_err;
+ } else {
+ sb->e1x_sb = BNX2X_PCI_ALLOC(&bnx2x_fp(bp, index, status_blk_mapping),
+ sizeof(struct host_hc_status_block_e1x));
+ if (!sb->e1x_sb)
+ goto alloc_mem_err;
+ }
}
/* FCoE Queue uses Default SB and doesn't ACK the SB, thus no need to
@@ -4389,35 +4408,49 @@
"allocating tx memory of fp %d cos %d\n",
index, cos);
- BNX2X_ALLOC(txdata->tx_buf_ring,
- sizeof(struct sw_tx_bd) * NUM_TX_BD);
- BNX2X_PCI_ALLOC(txdata->tx_desc_ring,
- &txdata->tx_desc_mapping,
- sizeof(union eth_tx_bd_types) * NUM_TX_BD);
+ txdata->tx_buf_ring = kcalloc(NUM_TX_BD,
+ sizeof(struct sw_tx_bd),
+ GFP_KERNEL);
+ if (!txdata->tx_buf_ring)
+ goto alloc_mem_err;
+ txdata->tx_desc_ring = BNX2X_PCI_ALLOC(&txdata->tx_desc_mapping,
+ sizeof(union eth_tx_bd_types) * NUM_TX_BD);
+ if (!txdata->tx_desc_ring)
+ goto alloc_mem_err;
}
}
/* Rx */
if (!skip_rx_queue(bp, index)) {
/* fastpath rx rings: rx_buf rx_desc rx_comp */
- BNX2X_ALLOC(bnx2x_fp(bp, index, rx_buf_ring),
- sizeof(struct sw_rx_bd) * NUM_RX_BD);
- BNX2X_PCI_ALLOC(bnx2x_fp(bp, index, rx_desc_ring),
- &bnx2x_fp(bp, index, rx_desc_mapping),
- sizeof(struct eth_rx_bd) * NUM_RX_BD);
+ bnx2x_fp(bp, index, rx_buf_ring) =
+ kcalloc(NUM_RX_BD, sizeof(struct sw_rx_bd), GFP_KERNEL);
+ if (!bnx2x_fp(bp, index, rx_buf_ring))
+ goto alloc_mem_err;
+ bnx2x_fp(bp, index, rx_desc_ring) =
+ BNX2X_PCI_ALLOC(&bnx2x_fp(bp, index, rx_desc_mapping),
+ sizeof(struct eth_rx_bd) * NUM_RX_BD);
+ if (!bnx2x_fp(bp, index, rx_desc_ring))
+ goto alloc_mem_err;
/* Seed all CQEs by 1s */
- BNX2X_PCI_FALLOC(bnx2x_fp(bp, index, rx_comp_ring),
- &bnx2x_fp(bp, index, rx_comp_mapping),
- sizeof(struct eth_fast_path_rx_cqe) *
- NUM_RCQ_BD);
+ bnx2x_fp(bp, index, rx_comp_ring) =
+ BNX2X_PCI_FALLOC(&bnx2x_fp(bp, index, rx_comp_mapping),
+ sizeof(struct eth_fast_path_rx_cqe) * NUM_RCQ_BD);
+ if (!bnx2x_fp(bp, index, rx_comp_ring))
+ goto alloc_mem_err;
/* SGE ring */
- BNX2X_ALLOC(bnx2x_fp(bp, index, rx_page_ring),
- sizeof(struct sw_rx_page) * NUM_RX_SGE);
- BNX2X_PCI_ALLOC(bnx2x_fp(bp, index, rx_sge_ring),
- &bnx2x_fp(bp, index, rx_sge_mapping),
- BCM_PAGE_SIZE * NUM_RX_SGE_PAGES);
+ bnx2x_fp(bp, index, rx_page_ring) =
+ kcalloc(NUM_RX_SGE, sizeof(struct sw_rx_page),
+ GFP_KERNEL);
+ if (!bnx2x_fp(bp, index, rx_page_ring))
+ goto alloc_mem_err;
+ bnx2x_fp(bp, index, rx_sge_ring) =
+ BNX2X_PCI_ALLOC(&bnx2x_fp(bp, index, rx_sge_mapping),
+ BCM_PAGE_SIZE * NUM_RX_SGE_PAGES);
+ if (!bnx2x_fp(bp, index, rx_sge_ring))
+ goto alloc_mem_err;
/* RX BD ring */
bnx2x_set_next_page_rx_bd(fp);
@@ -4773,12 +4806,8 @@
bnx2x_panic();
#endif
- smp_mb__before_clear_bit();
- set_bit(BNX2X_SP_RTNL_TX_TIMEOUT, &bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
-
/* This allows the netif to be shutdown gracefully before resetting */
- schedule_delayed_work(&bp->sp_rtnl_task, 0);
+ bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_TX_TIMEOUT, 0);
}
int bnx2x_suspend(struct pci_dev *pdev, pm_message_t state)
@@ -4906,3 +4935,15 @@
disable = disable ? 1 : (usec ? 0 : 1);
storm_memset_hc_disable(bp, port, fw_sb_id, sb_index, disable);
}
+
+void bnx2x_schedule_sp_rtnl(struct bnx2x *bp, enum sp_rtnl_flag flag,
+ u32 verbose)
+{
+ smp_mb__before_clear_bit();
+ set_bit(flag, &bp->sp_rtnl_state);
+ smp_mb__after_clear_bit();
+ DP((BNX2X_MSG_SP | verbose), "Scheduling sp_rtnl task [Flag: %d]\n",
+ flag);
+ schedule_delayed_work(&bp->sp_rtnl_task, 0);
+}
+EXPORT_SYMBOL(bnx2x_schedule_sp_rtnl);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 17d1689..05f4f5f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -47,31 +47,26 @@
} \
} while (0)
-#define BNX2X_PCI_ALLOC(x, y, size) \
- do { \
- x = dma_zalloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL); \
- if (x == NULL) \
- goto alloc_mem_err; \
- DP(NETIF_MSG_HW, "BNX2X_PCI_ALLOC: Physical %Lx Virtual %p\n", \
- (unsigned long long)(*y), x); \
- } while (0)
-
-#define BNX2X_PCI_FALLOC(x, y, size) \
- do { \
- x = dma_alloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL); \
- if (x == NULL) \
- goto alloc_mem_err; \
- memset((void *)x, 0xFFFFFFFF, size); \
- DP(NETIF_MSG_HW, "BNX2X_PCI_FALLOC: Physical %Lx Virtual %p\n",\
- (unsigned long long)(*y), x); \
- } while (0)
-
-#define BNX2X_ALLOC(x, size) \
- do { \
- x = kzalloc(size, GFP_KERNEL); \
- if (x == NULL) \
- goto alloc_mem_err; \
- } while (0)
+#define BNX2X_PCI_ALLOC(y, size) \
+({ \
+ void *x = dma_zalloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL); \
+ if (x) \
+ DP(NETIF_MSG_HW, \
+ "BNX2X_PCI_ALLOC: Physical %Lx Virtual %p\n", \
+ (unsigned long long)(*y), x); \
+ x; \
+})
+#define BNX2X_PCI_FALLOC(y, size) \
+({ \
+ void *x = dma_alloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL); \
+ if (x) { \
+ memset(x, 0xff, size); \
+ DP(NETIF_MSG_HW, \
+ "BNX2X_PCI_FALLOC: Physical %Lx Virtual %p\n", \
+ (unsigned long long)(*y), x); \
+ } \
+ x; \
+})
/*********************** Interfaces ****************************
* Functions that need to be implemented by each driver version
@@ -496,7 +491,7 @@
/* select_queue callback */
u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv);
+ void *accel_priv, select_queue_fallback_t fallback);
static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
struct bnx2x_fastpath *fp,
@@ -936,7 +931,7 @@
else /* CHIP_IS_E1X */
start_params->network_cos_mode = FW_WRR;
- start_params->gre_tunnel_mode = IPGRE_TUNNEL;
+ start_params->gre_tunnel_mode = L2GRE_TUNNEL;
start_params->gre_tunnel_rss = GRE_INNER_HEADERS_RSS;
return bnx2x_func_state_change(bp, &func_params);
@@ -1324,4 +1319,7 @@
int bnx2x_drain_tx_queues(struct bnx2x *bp);
void bnx2x_squeeze_objects(struct bnx2x *bp);
+void bnx2x_schedule_sp_rtnl(struct bnx2x*, enum sp_rtnl_flag,
+ u32 verbose);
+
#endif /* BNX2X_CMN_H */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
index fdace20..97ea542 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
@@ -710,8 +710,7 @@
* as we are handling an attention on a work queue which must be
* flushed at some rtnl-locked contexts (e.g. if down)
*/
- if (!test_and_set_bit(BNX2X_SP_RTNL_SETUP_TC, &bp->sp_rtnl_state))
- schedule_delayed_work(&bp->sp_rtnl_task, 0);
+ bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_SETUP_TC, 0);
}
void bnx2x_dcbx_set_params(struct bnx2x *bp, u32 state)
@@ -764,10 +763,7 @@
if (IS_MF(bp))
bnx2x_link_sync_notify(bp);
- set_bit(BNX2X_SP_RTNL_TX_STOP, &bp->sp_rtnl_state);
-
- schedule_delayed_work(&bp->sp_rtnl_task, 0);
-
+ bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_TX_STOP, 0);
return;
}
case BNX2X_DCBX_STATE_TX_PAUSED:
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 38fc794..b6de05e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -2969,8 +2969,9 @@
#define IS_PORT_STAT(i) \
((bnx2x_stats_arr[i].flags & STATS_FLAGS_BOTH) == STATS_FLAGS_PORT)
#define IS_FUNC_STAT(i) (bnx2x_stats_arr[i].flags & STATS_FLAGS_FUNC)
-#define IS_MF_MODE_STAT(bp) \
- (IS_MF(bp) && !(bp->msg_enable & BNX2X_MSG_STATS))
+#define HIDE_PORT_STAT(bp) \
+ ((IS_MF(bp) && !(bp->msg_enable & BNX2X_MSG_STATS)) || \
+ IS_VF(bp))
/* ethtool statistics are displayed for all regular ethernet queues and the
* fcoe L2 queue if not disabled
@@ -2992,7 +2993,7 @@
BNX2X_NUM_Q_STATS;
} else
num_strings = 0;
- if (IS_MF_MODE_STAT(bp)) {
+ if (HIDE_PORT_STAT(bp)) {
for (i = 0; i < BNX2X_NUM_STATS; i++)
if (IS_FUNC_STAT(i))
num_strings++;
@@ -3047,7 +3048,7 @@
}
for (i = 0, j = 0; i < BNX2X_NUM_STATS; i++) {
- if (IS_MF_MODE_STAT(bp) && IS_PORT_STAT(i))
+ if (HIDE_PORT_STAT(bp) && IS_PORT_STAT(i))
continue;
strcpy(buf + (k + j)*ETH_GSTRING_LEN,
bnx2x_stats_arr[i].string);
@@ -3105,7 +3106,7 @@
hw_stats = (u32 *)&bp->eth_stats;
for (i = 0, j = 0; i < BNX2X_NUM_STATS; i++) {
- if (IS_MF_MODE_STAT(bp) && IS_PORT_STAT(i))
+ if (HIDE_PORT_STAT(bp) && IS_PORT_STAT(i))
continue;
if (bnx2x_stats_arr[i].size == 0) {
/* skip this counter */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
index 84aecdf..95dc365 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h
@@ -87,7 +87,6 @@
(IRO[156].base + ((vfId) * IRO[156].m1))
#define CSTORM_VF_TO_PF_OFFSET(funcId) \
(IRO[150].base + ((funcId) * IRO[150].m1))
-#define TSTORM_ACCEPT_CLASSIFY_FAILED_OFFSET (IRO[204].base)
#define TSTORM_APPROXIMATE_MATCH_MULTICAST_FILTERING_OFFSET(pfId) \
(IRO[203].base + ((pfId) * IRO[203].m1))
#define TSTORM_ASSERT_LIST_INDEX_OFFSET (IRO[102].base)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
index cf1df8b..5ba8af5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
@@ -2003,6 +2003,23 @@
#define SHMEM_LFA_DONT_CLEAR_STAT (1<<24)
};
+/* Used to support NSCI get OS driver version
+ * on driver load the version value will be set
+ * on driver unload driver value of 0x0 will be set.
+ */
+struct os_drv_ver {
+#define DRV_VER_NOT_LOADED 0
+
+ /* personalties order is important */
+#define DRV_PERS_ETHERNET 0
+#define DRV_PERS_ISCSI 1
+#define DRV_PERS_FCOE 2
+
+ /* shmem2 struct is constant can't add more personalties here */
+#define MAX_DRV_PERS 3
+ u32 versions[MAX_DRV_PERS];
+};
+
struct ncsi_oem_fcoe_features {
u32 fcoe_features1;
#define FCOE_FEATURES1_IOS_PER_CONNECTION_MASK 0x0000FFFF
@@ -2217,6 +2234,18 @@
u32 reserved4; /* Offset 0x150 */
u32 link_attr_sync[PORT_MAX]; /* Offset 0x154 */
#define LINK_ATTR_SYNC_KR2_ENABLE (1<<0)
+
+ u32 reserved5[2];
+ u32 reserved6[PORT_MAX];
+
+ /* driver version for each personality */
+ struct os_drv_ver func_os_drv_ver[E2_FUNC_MAX]; /* Offset 0x16c */
+
+ /* Flag to the driver that PF's drv_info_host_addr buffer was read */
+ u32 mfw_drv_indication;
+
+ /* We use indication for each PF (0..3) */
+#define MFW_DRV_IND_READ_DONE_OFFSET(_pf_) (1 << (_pf_))
};
@@ -2848,7 +2877,7 @@
#define BCM_5710_FW_MAJOR_VERSION 7
#define BCM_5710_FW_MINOR_VERSION 8
-#define BCM_5710_FW_REVISION_VERSION 17
+#define BCM_5710_FW_REVISION_VERSION 19
#define BCM_5710_FW_ENGINEERING_VERSION 0
#define BCM_5710_FW_COMPILE_FLAGS 1
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c9c445e..a78edac 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -95,32 +95,33 @@
MODULE_FIRMWARE(FW_FILE_NAME_E2);
int bnx2x_num_queues;
-module_param_named(num_queues, bnx2x_num_queues, int, 0);
+module_param_named(num_queues, bnx2x_num_queues, int, S_IRUGO);
MODULE_PARM_DESC(num_queues,
" Set number of queues (default is as a number of CPUs)");
static int disable_tpa;
-module_param(disable_tpa, int, 0);
+module_param(disable_tpa, int, S_IRUGO);
MODULE_PARM_DESC(disable_tpa, " Disable the TPA (LRO) feature");
static int int_mode;
-module_param(int_mode, int, 0);
+module_param(int_mode, int, S_IRUGO);
MODULE_PARM_DESC(int_mode, " Force interrupt mode other than MSI-X "
"(1 INT#x; 2 MSI)");
static int dropless_fc;
-module_param(dropless_fc, int, 0);
+module_param(dropless_fc, int, S_IRUGO);
MODULE_PARM_DESC(dropless_fc, " Pause on exhausted host ring");
static int mrrs = -1;
-module_param(mrrs, int, 0);
+module_param(mrrs, int, S_IRUGO);
MODULE_PARM_DESC(mrrs, " Force Max Read Req Size (0..3) (for debug)");
static int debug;
-module_param(debug, int, 0);
+module_param(debug, int, S_IRUGO);
MODULE_PARM_DESC(debug, " Default debug msglevel");
-struct workqueue_struct *bnx2x_wq;
+static struct workqueue_struct *bnx2x_wq;
+struct workqueue_struct *bnx2x_iov_wq;
struct bnx2x_mac_vals {
u32 xmac_addr;
@@ -918,7 +919,7 @@
u16 start = 0, end = 0;
u8 cos;
#endif
- if (disable_int)
+ if (IS_PF(bp) && disable_int)
bnx2x_int_disable(bp);
bp->stats_state = STATS_STATE_DISABLED;
@@ -929,33 +930,41 @@
/* Indices */
/* Common */
- BNX2X_ERR("def_idx(0x%x) def_att_idx(0x%x) attn_state(0x%x) spq_prod_idx(0x%x) next_stats_cnt(0x%x)\n",
- bp->def_idx, bp->def_att_idx, bp->attn_state,
- bp->spq_prod_idx, bp->stats_counter);
- BNX2X_ERR("DSB: attn bits(0x%x) ack(0x%x) id(0x%x) idx(0x%x)\n",
- bp->def_status_blk->atten_status_block.attn_bits,
- bp->def_status_blk->atten_status_block.attn_bits_ack,
- bp->def_status_blk->atten_status_block.status_block_id,
- bp->def_status_blk->atten_status_block.attn_bits_index);
- BNX2X_ERR(" def (");
- for (i = 0; i < HC_SP_SB_MAX_INDICES; i++)
- pr_cont("0x%x%s",
- bp->def_status_blk->sp_sb.index_values[i],
- (i == HC_SP_SB_MAX_INDICES - 1) ? ") " : " ");
+ if (IS_PF(bp)) {
+ struct host_sp_status_block *def_sb = bp->def_status_blk;
+ int data_size, cstorm_offset;
- for (i = 0; i < sizeof(struct hc_sp_status_block_data)/sizeof(u32); i++)
- *((u32 *)&sp_sb_data + i) = REG_RD(bp, BAR_CSTRORM_INTMEM +
- CSTORM_SP_STATUS_BLOCK_DATA_OFFSET(func) +
- i*sizeof(u32));
+ BNX2X_ERR("def_idx(0x%x) def_att_idx(0x%x) attn_state(0x%x) spq_prod_idx(0x%x) next_stats_cnt(0x%x)\n",
+ bp->def_idx, bp->def_att_idx, bp->attn_state,
+ bp->spq_prod_idx, bp->stats_counter);
+ BNX2X_ERR("DSB: attn bits(0x%x) ack(0x%x) id(0x%x) idx(0x%x)\n",
+ def_sb->atten_status_block.attn_bits,
+ def_sb->atten_status_block.attn_bits_ack,
+ def_sb->atten_status_block.status_block_id,
+ def_sb->atten_status_block.attn_bits_index);
+ BNX2X_ERR(" def (");
+ for (i = 0; i < HC_SP_SB_MAX_INDICES; i++)
+ pr_cont("0x%x%s",
+ def_sb->sp_sb.index_values[i],
+ (i == HC_SP_SB_MAX_INDICES - 1) ? ") " : " ");
- pr_cont("igu_sb_id(0x%x) igu_seg_id(0x%x) pf_id(0x%x) vnic_id(0x%x) vf_id(0x%x) vf_valid (0x%x) state(0x%x)\n",
- sp_sb_data.igu_sb_id,
- sp_sb_data.igu_seg_id,
- sp_sb_data.p_func.pf_id,
- sp_sb_data.p_func.vnic_id,
- sp_sb_data.p_func.vf_id,
- sp_sb_data.p_func.vf_valid,
- sp_sb_data.state);
+ data_size = sizeof(struct hc_sp_status_block_data) /
+ sizeof(u32);
+ cstorm_offset = CSTORM_SP_STATUS_BLOCK_DATA_OFFSET(func);
+ for (i = 0; i < data_size; i++)
+ *((u32 *)&sp_sb_data + i) =
+ REG_RD(bp, BAR_CSTRORM_INTMEM + cstorm_offset +
+ i * sizeof(u32));
+
+ pr_cont("igu_sb_id(0x%x) igu_seg_id(0x%x) pf_id(0x%x) vnic_id(0x%x) vf_id(0x%x) vf_valid (0x%x) state(0x%x)\n",
+ sp_sb_data.igu_sb_id,
+ sp_sb_data.igu_seg_id,
+ sp_sb_data.p_func.pf_id,
+ sp_sb_data.p_func.vnic_id,
+ sp_sb_data.p_func.vf_id,
+ sp_sb_data.p_func.vf_valid,
+ sp_sb_data.state);
+ }
for_each_eth_queue(bp, i) {
struct bnx2x_fastpath *fp = &bp->fp[i];
@@ -1013,6 +1022,11 @@
pr_cont("0x%x%s",
fp->sb_index_values[j],
(j == loop - 1) ? ")" : " ");
+
+ /* VF cannot access FW refelection for status block */
+ if (IS_VF(bp))
+ continue;
+
/* fw sb data */
data_size = CHIP_IS_E1x(bp) ?
sizeof(struct hc_status_block_data_e1x) :
@@ -1064,16 +1078,18 @@
}
#ifdef BNX2X_STOP_ON_ERROR
+ if (IS_PF(bp)) {
+ /* event queue */
+ BNX2X_ERR("eq cons %x prod %x\n", bp->eq_cons, bp->eq_prod);
+ for (i = 0; i < NUM_EQ_DESC; i++) {
+ u32 *data = (u32 *)&bp->eq_ring[i].message.data;
- /* event queue */
- BNX2X_ERR("eq cons %x prod %x\n", bp->eq_cons, bp->eq_prod);
- for (i = 0; i < NUM_EQ_DESC; i++) {
- u32 *data = (u32 *)&bp->eq_ring[i].message.data;
-
- BNX2X_ERR("event queue [%d]: header: opcode %d, error %d\n",
- i, bp->eq_ring[i].message.opcode,
- bp->eq_ring[i].message.error);
- BNX2X_ERR("data: %x %x %x\n", data[0], data[1], data[2]);
+ BNX2X_ERR("event queue [%d]: header: opcode %d, error %d\n",
+ i, bp->eq_ring[i].message.opcode,
+ bp->eq_ring[i].message.error);
+ BNX2X_ERR("data: %x %x %x\n",
+ data[0], data[1], data[2]);
+ }
}
/* Rings */
@@ -1140,8 +1156,10 @@
}
}
#endif
- bnx2x_fw_dump(bp);
- bnx2x_mc_assert(bp);
+ if (IS_PF(bp)) {
+ bnx2x_fw_dump(bp);
+ bnx2x_mc_assert(bp);
+ }
BNX2X_ERR("end crash dump -----------------\n");
}
@@ -1814,6 +1832,11 @@
drv_cmd = BNX2X_Q_CMD_EMPTY;
break;
+ case (RAMROD_CMD_ID_ETH_TPA_UPDATE):
+ DP(BNX2X_MSG_SP, "got tpa update ramrod CID=%d\n", cid);
+ drv_cmd = BNX2X_Q_CMD_UPDATE_TPA;
+ break;
+
default:
BNX2X_ERR("unexpected MC reply (%d) on fp[%d]\n",
command, fp->index);
@@ -1834,8 +1857,6 @@
#else
return;
#endif
- /* SRIOV: reschedule any 'in_progress' operations */
- bnx2x_iov_sp_event(bp, cid, true);
smp_mb__before_atomic_inc();
atomic_inc(&bp->cq_spq_left);
@@ -3460,10 +3481,15 @@
bnx2x_fw_command(bp, DRV_MSG_CODE_EEE_RESULTS_ACK, 0);
}
+#define BNX2X_UPDATE_DRV_INFO_IND_LENGTH (20)
+#define BNX2X_UPDATE_DRV_INFO_IND_COUNT (25)
+
static void bnx2x_handle_drv_info_req(struct bnx2x *bp)
{
enum drv_info_opcode op_code;
u32 drv_info_ctl = SHMEM2_RD(bp, drv_info_control);
+ bool release = false;
+ int wait;
/* if drv_info version supported by MFW doesn't match - send NACK */
if ((drv_info_ctl & DRV_INFO_CONTROL_VER_MASK) != DRV_INFO_CUR_VER) {
@@ -3474,6 +3500,9 @@
op_code = (drv_info_ctl & DRV_INFO_CONTROL_OP_CODE_MASK) >>
DRV_INFO_CONTROL_OP_CODE_SHIFT;
+ /* Must prevent other flows from accessing drv_info_to_mcp */
+ mutex_lock(&bp->drv_info_mutex);
+
memset(&bp->slowpath->drv_info_to_mcp, 0,
sizeof(union drv_info_to_mcp));
@@ -3490,7 +3519,7 @@
default:
/* if op code isn't supported - send NACK */
bnx2x_fw_command(bp, DRV_MSG_CODE_DRV_INFO_NACK, 0);
- return;
+ goto out;
}
/* if we got drv_info attn from MFW then these fields are defined in
@@ -3502,6 +3531,106 @@
U64_HI(bnx2x_sp_mapping(bp, drv_info_to_mcp)));
bnx2x_fw_command(bp, DRV_MSG_CODE_DRV_INFO_ACK, 0);
+
+ /* Since possible management wants both this and get_driver_version
+ * need to wait until management notifies us it finished utilizing
+ * the buffer.
+ */
+ if (!SHMEM2_HAS(bp, mfw_drv_indication)) {
+ DP(BNX2X_MSG_MCP, "Management does not support indication\n");
+ } else if (!bp->drv_info_mng_owner) {
+ u32 bit = MFW_DRV_IND_READ_DONE_OFFSET((BP_ABS_FUNC(bp) >> 1));
+
+ for (wait = 0; wait < BNX2X_UPDATE_DRV_INFO_IND_COUNT; wait++) {
+ u32 indication = SHMEM2_RD(bp, mfw_drv_indication);
+
+ /* Management is done; need to clear indication */
+ if (indication & bit) {
+ SHMEM2_WR(bp, mfw_drv_indication,
+ indication & ~bit);
+ release = true;
+ break;
+ }
+
+ msleep(BNX2X_UPDATE_DRV_INFO_IND_LENGTH);
+ }
+ }
+ if (!release) {
+ DP(BNX2X_MSG_MCP, "Management did not release indication\n");
+ bp->drv_info_mng_owner = true;
+ }
+
+out:
+ mutex_unlock(&bp->drv_info_mutex);
+}
+
+static u32 bnx2x_update_mng_version_utility(u8 *version, bool bnx2x_format)
+{
+ u8 vals[4];
+ int i = 0;
+
+ if (bnx2x_format) {
+ i = sscanf(version, "1.%c%hhd.%hhd.%hhd",
+ &vals[0], &vals[1], &vals[2], &vals[3]);
+ if (i > 0)
+ vals[0] -= '0';
+ } else {
+ i = sscanf(version, "%hhd.%hhd.%hhd.%hhd",
+ &vals[0], &vals[1], &vals[2], &vals[3]);
+ }
+
+ while (i < 4)
+ vals[i++] = 0;
+
+ return (vals[0] << 24) | (vals[1] << 16) | (vals[2] << 8) | vals[3];
+}
+
+void bnx2x_update_mng_version(struct bnx2x *bp)
+{
+ u32 iscsiver = DRV_VER_NOT_LOADED;
+ u32 fcoever = DRV_VER_NOT_LOADED;
+ u32 ethver = DRV_VER_NOT_LOADED;
+ int idx = BP_FW_MB_IDX(bp);
+ u8 *version;
+
+ if (!SHMEM2_HAS(bp, func_os_drv_ver))
+ return;
+
+ mutex_lock(&bp->drv_info_mutex);
+ /* Must not proceed when `bnx2x_handle_drv_info_req' is feasible */
+ if (bp->drv_info_mng_owner)
+ goto out;
+
+ if (bp->state != BNX2X_STATE_OPEN)
+ goto out;
+
+ /* Parse ethernet driver version */
+ ethver = bnx2x_update_mng_version_utility(DRV_MODULE_VERSION, true);
+ if (!CNIC_LOADED(bp))
+ goto out;
+
+ /* Try getting storage driver version via cnic */
+ memset(&bp->slowpath->drv_info_to_mcp, 0,
+ sizeof(union drv_info_to_mcp));
+ bnx2x_drv_info_iscsi_stat(bp);
+ version = bp->slowpath->drv_info_to_mcp.iscsi_stat.version;
+ iscsiver = bnx2x_update_mng_version_utility(version, false);
+
+ memset(&bp->slowpath->drv_info_to_mcp, 0,
+ sizeof(union drv_info_to_mcp));
+ bnx2x_drv_info_fcoe_stat(bp);
+ version = bp->slowpath->drv_info_to_mcp.fcoe_stat.version;
+ fcoever = bnx2x_update_mng_version_utility(version, false);
+
+out:
+ SHMEM2_WR(bp, func_os_drv_ver[idx].versions[DRV_PERS_ETHERNET], ethver);
+ SHMEM2_WR(bp, func_os_drv_ver[idx].versions[DRV_PERS_ISCSI], iscsiver);
+ SHMEM2_WR(bp, func_os_drv_ver[idx].versions[DRV_PERS_FCOE], fcoever);
+
+ mutex_unlock(&bp->drv_info_mutex);
+
+ DP(BNX2X_MSG_MCP, "Setting driver version: ETH [%08x] iSCSI [%08x] FCoE [%08x]\n",
+ ethver, iscsiver, fcoever);
}
static void bnx2x_dcc_event(struct bnx2x *bp, u32 dcc_event)
@@ -3644,10 +3773,18 @@
cpu_to_le32((command << SPE_HDR_CMD_ID_SHIFT) |
HW_CID(bp, cid));
- type = (cmd_type << SPE_HDR_CONN_TYPE_SHIFT) & SPE_HDR_CONN_TYPE;
-
- type |= ((BP_FUNC(bp) << SPE_HDR_FUNCTION_ID_SHIFT) &
- SPE_HDR_FUNCTION_ID);
+ /* In some cases, type may already contain the func-id
+ * mainly in SRIOV related use cases, so we add it here only
+ * if it's not already set.
+ */
+ if (!(cmd_type & SPE_HDR_FUNCTION_ID)) {
+ type = (cmd_type << SPE_HDR_CONN_TYPE_SHIFT) &
+ SPE_HDR_CONN_TYPE;
+ type |= ((BP_FUNC(bp) << SPE_HDR_FUNCTION_ID_SHIFT) &
+ SPE_HDR_FUNCTION_ID);
+ } else {
+ type = cmd_type;
+ }
spe->hdr.type = cpu_to_le16(type);
@@ -3878,10 +4015,7 @@
* This is due to some boards consuming sufficient power when driver is
* up to overheat if fan fails.
*/
- smp_mb__before_clear_bit();
- set_bit(BNX2X_SP_RTNL_FAN_FAILURE, &bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
- schedule_delayed_work(&bp->sp_rtnl_task, 0);
+ bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_FAN_FAILURE, 0);
}
static void bnx2x_attn_int_deasserted0(struct bnx2x *bp, u32 attn)
@@ -4025,7 +4159,8 @@
bnx2x_handle_drv_info_req(bp);
if (val & DRV_STATUS_VF_DISABLED)
- bnx2x_vf_handle_flr_event(bp);
+ bnx2x_schedule_iov_task(bp,
+ BNX2X_IOV_HANDLE_FLR);
if ((bp->port.pmf == 0) && (val & DRV_STATUS_PMF))
bnx2x_pmf_update(bp);
@@ -5216,14 +5351,14 @@
/* handle eq element */
switch (opcode) {
case EVENT_RING_OPCODE_VF_PF_CHANNEL:
- DP(BNX2X_MSG_IOV, "vf pf channel element on eq\n");
- bnx2x_vf_mbx(bp, &elem->message.data.vf_pf_event);
+ bnx2x_vf_mbx_schedule(bp,
+ &elem->message.data.vf_pf_event);
continue;
case EVENT_RING_OPCODE_STAT_QUERY:
- DP(BNX2X_MSG_SP | BNX2X_MSG_STATS,
- "got statistics comp event %d\n",
- bp->stats_comp++);
+ DP_AND((BNX2X_MSG_SP | BNX2X_MSG_STATS),
+ "got statistics comp event %d\n",
+ bp->stats_comp++);
/* nothing to do with stats comp */
goto next_spqe;
@@ -5273,6 +5408,8 @@
break;
} else {
+ int cmd = BNX2X_SP_RTNL_AFEX_F_UPDATE;
+
DP(BNX2X_MSG_SP | BNX2X_MSG_MCP,
"AFEX: ramrod completed FUNCTION_UPDATE\n");
f_obj->complete_cmd(bp, f_obj,
@@ -5282,12 +5419,7 @@
* sp_rtnl task as all Queue SP operations
* should run under rtnl_lock.
*/
- smp_mb__before_clear_bit();
- set_bit(BNX2X_SP_RTNL_AFEX_F_UPDATE,
- &bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
-
- schedule_delayed_work(&bp->sp_rtnl_task, 0);
+ bnx2x_schedule_sp_rtnl(bp, cmd, 0);
}
goto next_spqe;
@@ -5435,13 +5567,6 @@
le16_to_cpu(bp->def_att_idx), IGU_INT_ENABLE, 1);
}
- /* must be called after the EQ processing (since eq leads to sriov
- * ramrod completion flows).
- * This flow may have been scheduled by the arrival of a ramrod
- * completion, or by the sriov code rescheduling itself.
- */
- bnx2x_iov_sp_task(bp);
-
/* afex - poll to check if VIFSET_ACK should be sent to MFW */
if (test_and_clear_bit(BNX2X_AFEX_PENDING_VIFSET_MCP_ACK,
&bp->sp_state)) {
@@ -6005,18 +6130,6 @@
{
int i;
- if (IS_MF_SI(bp))
- /*
- * In switch independent mode, the TSTORM needs to accept
- * packets that failed classification, since approximate match
- * mac addresses aren't written to NIG LLH
- */
- REG_WR8(bp, BAR_TSTRORM_INTMEM +
- TSTORM_ACCEPT_CLASSIFY_FAILED_OFFSET, 2);
- else if (!CHIP_IS_E1(bp)) /* 57710 doesn't support MF */
- REG_WR8(bp, BAR_TSTRORM_INTMEM +
- TSTORM_ACCEPT_CLASSIFY_FAILED_OFFSET, 0);
-
/* Zero this manually as its initialization is
currently missing in the initTool */
for (i = 0; i < (USTORM_AGG_DATA_SIZE >> 2); i++)
@@ -7989,19 +8102,25 @@
int bnx2x_alloc_mem_cnic(struct bnx2x *bp)
{
- if (!CHIP_IS_E1x(bp))
+ if (!CHIP_IS_E1x(bp)) {
/* size = the status block + ramrod buffers */
- BNX2X_PCI_ALLOC(bp->cnic_sb.e2_sb, &bp->cnic_sb_mapping,
- sizeof(struct host_hc_status_block_e2));
- else
- BNX2X_PCI_ALLOC(bp->cnic_sb.e1x_sb,
- &bp->cnic_sb_mapping,
- sizeof(struct
- host_hc_status_block_e1x));
+ bp->cnic_sb.e2_sb = BNX2X_PCI_ALLOC(&bp->cnic_sb_mapping,
+ sizeof(struct host_hc_status_block_e2));
+ if (!bp->cnic_sb.e2_sb)
+ goto alloc_mem_err;
+ } else {
+ bp->cnic_sb.e1x_sb = BNX2X_PCI_ALLOC(&bp->cnic_sb_mapping,
+ sizeof(struct host_hc_status_block_e1x));
+ if (!bp->cnic_sb.e1x_sb)
+ goto alloc_mem_err;
+ }
- if (CONFIGURE_NIC_MODE(bp) && !bp->t2)
+ if (CONFIGURE_NIC_MODE(bp) && !bp->t2) {
/* allocate searcher T2 table, as it wasn't allocated before */
- BNX2X_PCI_ALLOC(bp->t2, &bp->t2_mapping, SRC_T2_SZ);
+ bp->t2 = BNX2X_PCI_ALLOC(&bp->t2_mapping, SRC_T2_SZ);
+ if (!bp->t2)
+ goto alloc_mem_err;
+ }
/* write address to which L5 should insert its values */
bp->cnic_eth_dev.addr_drv_info_to_mcp =
@@ -8022,15 +8141,22 @@
{
int i, allocated, context_size;
- if (!CONFIGURE_NIC_MODE(bp) && !bp->t2)
+ if (!CONFIGURE_NIC_MODE(bp) && !bp->t2) {
/* allocate searcher T2 table */
- BNX2X_PCI_ALLOC(bp->t2, &bp->t2_mapping, SRC_T2_SZ);
+ bp->t2 = BNX2X_PCI_ALLOC(&bp->t2_mapping, SRC_T2_SZ);
+ if (!bp->t2)
+ goto alloc_mem_err;
+ }
- BNX2X_PCI_ALLOC(bp->def_status_blk, &bp->def_status_blk_mapping,
- sizeof(struct host_sp_status_block));
+ bp->def_status_blk = BNX2X_PCI_ALLOC(&bp->def_status_blk_mapping,
+ sizeof(struct host_sp_status_block));
+ if (!bp->def_status_blk)
+ goto alloc_mem_err;
- BNX2X_PCI_ALLOC(bp->slowpath, &bp->slowpath_mapping,
- sizeof(struct bnx2x_slowpath));
+ bp->slowpath = BNX2X_PCI_ALLOC(&bp->slowpath_mapping,
+ sizeof(struct bnx2x_slowpath));
+ if (!bp->slowpath)
+ goto alloc_mem_err;
/* Allocate memory for CDU context:
* This memory is allocated separately and not in the generic ILT
@@ -8050,12 +8176,16 @@
for (i = 0, allocated = 0; allocated < context_size; i++) {
bp->context[i].size = min(CDU_ILT_PAGE_SZ,
(context_size - allocated));
- BNX2X_PCI_ALLOC(bp->context[i].vcxt,
- &bp->context[i].cxt_mapping,
- bp->context[i].size);
+ bp->context[i].vcxt = BNX2X_PCI_ALLOC(&bp->context[i].cxt_mapping,
+ bp->context[i].size);
+ if (!bp->context[i].vcxt)
+ goto alloc_mem_err;
allocated += bp->context[i].size;
}
- BNX2X_ALLOC(bp->ilt->lines, sizeof(struct ilt_line) * ILT_MAX_LINES);
+ bp->ilt->lines = kcalloc(ILT_MAX_LINES, sizeof(struct ilt_line),
+ GFP_KERNEL);
+ if (!bp->ilt->lines)
+ goto alloc_mem_err;
if (bnx2x_ilt_mem_op(bp, ILT_MEMOP_ALLOC))
goto alloc_mem_err;
@@ -8064,11 +8194,15 @@
goto alloc_mem_err;
/* Slow path ring */
- BNX2X_PCI_ALLOC(bp->spq, &bp->spq_mapping, BCM_PAGE_SIZE);
+ bp->spq = BNX2X_PCI_ALLOC(&bp->spq_mapping, BCM_PAGE_SIZE);
+ if (!bp->spq)
+ goto alloc_mem_err;
/* EQ */
- BNX2X_PCI_ALLOC(bp->eq_ring, &bp->eq_mapping,
- BCM_PAGE_SIZE * NUM_EQ_PAGES);
+ bp->eq_ring = BNX2X_PCI_ALLOC(&bp->eq_mapping,
+ BCM_PAGE_SIZE * NUM_EQ_PAGES);
+ if (!bp->eq_ring)
+ goto alloc_mem_err;
return 0;
@@ -8849,6 +8983,7 @@
synchronize_irq(bp->pdev->irq);
flush_workqueue(bnx2x_wq);
+ flush_workqueue(bnx2x_iov_wq);
while (bnx2x_func_get_state(bp, &bp->func_obj) !=
BNX2X_F_STATE_STARTED && tout--)
@@ -9774,6 +9909,10 @@
bnx2x_dcbx_resume_hw_tx(bp);
}
+ if (test_and_clear_bit(BNX2X_SP_RTNL_GET_DRV_VERSION,
+ &bp->sp_rtnl_state))
+ bnx2x_update_mng_version(bp);
+
/* work which needs rtnl lock not-taken (as it takes the lock itself and
* can be called from other contexts as well)
*/
@@ -11724,12 +11863,15 @@
mutex_init(&bp->port.phy_mutex);
mutex_init(&bp->fw_mb_mutex);
+ mutex_init(&bp->drv_info_mutex);
+ bp->drv_info_mng_owner = false;
spin_lock_init(&bp->stats_lock);
sema_init(&bp->stats_sema, 1);
INIT_DELAYED_WORK(&bp->sp_task, bnx2x_sp_task);
INIT_DELAYED_WORK(&bp->sp_rtnl_task, bnx2x_sp_rtnl_task);
INIT_DELAYED_WORK(&bp->period_task, bnx2x_period_task);
+ INIT_DELAYED_WORK(&bp->iov_task, bnx2x_iov_task);
if (IS_PF(bp)) {
rc = bnx2x_get_hwinfo(bp);
if (rc)
@@ -11771,6 +11913,8 @@
bp->disable_tpa = disable_tpa;
bp->disable_tpa |= IS_MF_STORAGE_SD(bp) || IS_MF_FCOE_AFEX(bp);
+ /* Reduce memory usage in kdump environment by disabling TPA */
+ bp->disable_tpa |= reset_devices;
/* Set TPA flags */
if (bp->disable_tpa) {
@@ -11942,7 +12086,7 @@
{
int mc_count = netdev_mc_count(bp->dev);
struct bnx2x_mcast_list_elem *mc_mac =
- kzalloc(sizeof(*mc_mac) * mc_count, GFP_ATOMIC);
+ kcalloc(mc_count, sizeof(*mc_mac), GFP_ATOMIC);
struct netdev_hw_addr *ha;
if (!mc_mac)
@@ -12064,11 +12208,8 @@
return;
} else {
/* Schedule an SP task to handle rest of change */
- DP(NETIF_MSG_IFUP, "Scheduling an Rx mode change\n");
- smp_mb__before_clear_bit();
- set_bit(BNX2X_SP_RTNL_RX_MODE, &bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
- schedule_delayed_work(&bp->sp_rtnl_task, 0);
+ bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_RX_MODE,
+ NETIF_MSG_IFUP);
}
}
@@ -12101,11 +12242,8 @@
/* configuring mcast to a vf involves sleeping (when we
* wait for the pf's response).
*/
- smp_mb__before_clear_bit();
- set_bit(BNX2X_SP_RTNL_VFPF_MCAST,
- &bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
- schedule_delayed_work(&bp->sp_rtnl_task, 0);
+ bnx2x_schedule_sp_rtnl(bp,
+ BNX2X_SP_RTNL_VFPF_MCAST, 0);
}
}
@@ -13356,11 +13494,18 @@
pr_err("Cannot create workqueue\n");
return -ENOMEM;
}
+ bnx2x_iov_wq = create_singlethread_workqueue("bnx2x_iov");
+ if (!bnx2x_iov_wq) {
+ pr_err("Cannot create iov workqueue\n");
+ destroy_workqueue(bnx2x_wq);
+ return -ENOMEM;
+ }
ret = pci_register_driver(&bnx2x_pci_driver);
if (ret) {
pr_err("Cannot register driver\n");
destroy_workqueue(bnx2x_wq);
+ destroy_workqueue(bnx2x_iov_wq);
}
return ret;
}
@@ -13372,6 +13517,7 @@
pci_unregister_driver(&bnx2x_pci_driver);
destroy_workqueue(bnx2x_wq);
+ destroy_workqueue(bnx2x_iov_wq);
/* Free globally allocated resources */
list_for_each_safe(pos, q, &bnx2x_prev_list) {
@@ -13765,6 +13911,7 @@
REG_WR(bp, scratch_offset + i,
*(host_addr + i/4));
}
+ bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_GET_DRV_VERSION, 0);
break;
}
@@ -13782,6 +13929,7 @@
cap &= ~DRV_FLAGS_CAPABILITIES_LOADED_FCOE;
SHMEM2_WR(bp, drv_capabilities_flag[idx], cap);
}
+ bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_GET_DRV_VERSION, 0);
break;
}
@@ -13887,6 +14035,9 @@
rcu_assign_pointer(bp->cnic_ops, ops);
+ /* Schedule driver to read CNIC driver versions */
+ bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_GET_DRV_VERSION, 0);
+
return 0;
}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 0fb6ff2..31297266 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -2277,11 +2277,11 @@
data->header.rule_cnt, p->rx_accept_flags,
p->tx_accept_flags);
- /* No need for an explicit memory barrier here as long we would
- * need to ensure the ordering of writing to the SPQ element
+ /* No need for an explicit memory barrier here as long as we
+ * ensure the ordering of writing to the SPQ element
* and updating of the SPQ producer which involves a memory
- * read and we will have to put a full memory barrier there
- * (inside bnx2x_sp_post()).
+ * read. If the memory read is removed we will have to put a
+ * full memory barrier there (inside bnx2x_sp_post()).
*/
/* Send a ramrod */
@@ -2982,11 +2982,11 @@
raw->clear_pending(raw);
return 0;
} else {
- /* No need for an explicit memory barrier here as long we would
- * need to ensure the ordering of writing to the SPQ element
+ /* No need for an explicit memory barrier here as long as we
+ * ensure the ordering of writing to the SPQ element
* and updating of the SPQ producer which involves a memory
- * read and we will have to put a full memory barrier there
- * (inside bnx2x_sp_post()).
+ * read. If the memory read is removed we will have to put a
+ * full memory barrier there (inside bnx2x_sp_post()).
*/
/* Send a ramrod */
@@ -3466,11 +3466,11 @@
raw->clear_pending(raw);
return 0;
} else {
- /* No need for an explicit memory barrier here as long we would
- * need to ensure the ordering of writing to the SPQ element
+ /* No need for an explicit memory barrier here as long as we
+ * ensure the ordering of writing to the SPQ element
* and updating of the SPQ producer which involves a memory
- * read and we will have to put a full memory barrier there
- * (inside bnx2x_sp_post()).
+ * read. If the memory read is removed we will have to put a
+ * full memory barrier there (inside bnx2x_sp_post()).
*/
/* Send a ramrod */
@@ -4091,11 +4091,11 @@
data->capabilities |= ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY;
}
- /* No need for an explicit memory barrier here as long we would
- * need to ensure the ordering of writing to the SPQ element
+ /* No need for an explicit memory barrier here as long as we
+ * ensure the ordering of writing to the SPQ element
* and updating of the SPQ producer which involves a memory
- * read and we will have to put a full memory barrier there
- * (inside bnx2x_sp_post()).
+ * read. If the memory read is removed we will have to put a
+ * full memory barrier there (inside bnx2x_sp_post()).
*/
/* Send a ramrod */
@@ -4158,16 +4158,6 @@
rss_obj->config_rss = bnx2x_setup_rss;
}
-int validate_vlan_mac(struct bnx2x *bp,
- struct bnx2x_vlan_mac_obj *vlan_mac)
-{
- if (!vlan_mac->get_n_elements) {
- BNX2X_ERR("vlan mac object was not intialized\n");
- return -EINVAL;
- }
- return 0;
-}
-
/********************** Queue state object ***********************************/
/**
@@ -4587,13 +4577,12 @@
/* Fill the ramrod data */
bnx2x_q_fill_setup_data_cmn(bp, params, rdata);
- /* No need for an explicit memory barrier here as long we would
- * need to ensure the ordering of writing to the SPQ element
+ /* No need for an explicit memory barrier here as long as we
+ * ensure the ordering of writing to the SPQ element
* and updating of the SPQ producer which involves a memory
- * read and we will have to put a full memory barrier there
- * (inside bnx2x_sp_post()).
+ * read. If the memory read is removed we will have to put a
+ * full memory barrier there (inside bnx2x_sp_post()).
*/
-
return bnx2x_sp_post(bp, ramrod, o->cids[BNX2X_PRIMARY_CID_INDEX],
U64_HI(data_mapping),
U64_LO(data_mapping), ETH_CONNECTION_TYPE);
@@ -4615,13 +4604,12 @@
bnx2x_q_fill_setup_data_cmn(bp, params, rdata);
bnx2x_q_fill_setup_data_e2(bp, params, rdata);
- /* No need for an explicit memory barrier here as long we would
- * need to ensure the ordering of writing to the SPQ element
+ /* No need for an explicit memory barrier here as long as we
+ * ensure the ordering of writing to the SPQ element
* and updating of the SPQ producer which involves a memory
- * read and we will have to put a full memory barrier there
- * (inside bnx2x_sp_post()).
+ * read. If the memory read is removed we will have to put a
+ * full memory barrier there (inside bnx2x_sp_post()).
*/
-
return bnx2x_sp_post(bp, ramrod, o->cids[BNX2X_PRIMARY_CID_INDEX],
U64_HI(data_mapping),
U64_LO(data_mapping), ETH_CONNECTION_TYPE);
@@ -4659,13 +4647,12 @@
o->cids[cid_index], rdata->general.client_id,
rdata->general.sp_client_id, rdata->general.cos);
- /* No need for an explicit memory barrier here as long we would
- * need to ensure the ordering of writing to the SPQ element
+ /* No need for an explicit memory barrier here as long as we
+ * ensure the ordering of writing to the SPQ element
* and updating of the SPQ producer which involves a memory
- * read and we will have to put a full memory barrier there
- * (inside bnx2x_sp_post()).
+ * read. If the memory read is removed we will have to put a
+ * full memory barrier there (inside bnx2x_sp_post()).
*/
-
return bnx2x_sp_post(bp, ramrod, o->cids[cid_index],
U64_HI(data_mapping),
U64_LO(data_mapping), ETH_CONNECTION_TYPE);
@@ -4760,13 +4747,12 @@
/* Fill the ramrod data */
bnx2x_q_fill_update_data(bp, o, update_params, rdata);
- /* No need for an explicit memory barrier here as long we would
- * need to ensure the ordering of writing to the SPQ element
+ /* No need for an explicit memory barrier here as long as we
+ * ensure the ordering of writing to the SPQ element
* and updating of the SPQ producer which involves a memory
- * read and we will have to put a full memory barrier there
- * (inside bnx2x_sp_post()).
+ * read. If the memory read is removed we will have to put a
+ * full memory barrier there (inside bnx2x_sp_post()).
*/
-
return bnx2x_sp_post(bp, RAMROD_CMD_ID_ETH_CLIENT_UPDATE,
o->cids[cid_index], U64_HI(data_mapping),
U64_LO(data_mapping), ETH_CONNECTION_TYPE);
@@ -4813,11 +4799,62 @@
return bnx2x_q_send_update(bp, params);
}
+static void bnx2x_q_fill_update_tpa_data(struct bnx2x *bp,
+ struct bnx2x_queue_sp_obj *obj,
+ struct bnx2x_queue_update_tpa_params *params,
+ struct tpa_update_ramrod_data *data)
+{
+ data->client_id = obj->cl_id;
+ data->complete_on_both_clients = params->complete_on_both_clients;
+ data->dont_verify_rings_pause_thr_flg =
+ params->dont_verify_thr;
+ data->max_agg_size = cpu_to_le16(params->max_agg_sz);
+ data->max_sges_for_packet = params->max_sges_pkt;
+ data->max_tpa_queues = params->max_tpa_queues;
+ data->sge_buff_size = cpu_to_le16(params->sge_buff_sz);
+ data->sge_page_base_hi = cpu_to_le32(U64_HI(params->sge_map));
+ data->sge_page_base_lo = cpu_to_le32(U64_LO(params->sge_map));
+ data->sge_pause_thr_high = cpu_to_le16(params->sge_pause_thr_high);
+ data->sge_pause_thr_low = cpu_to_le16(params->sge_pause_thr_low);
+ data->tpa_mode = params->tpa_mode;
+ data->update_ipv4 = params->update_ipv4;
+ data->update_ipv6 = params->update_ipv6;
+}
+
static inline int bnx2x_q_send_update_tpa(struct bnx2x *bp,
struct bnx2x_queue_state_params *params)
{
- /* TODO: Not implemented yet. */
- return -1;
+ struct bnx2x_queue_sp_obj *o = params->q_obj;
+ struct tpa_update_ramrod_data *rdata =
+ (struct tpa_update_ramrod_data *)o->rdata;
+ dma_addr_t data_mapping = o->rdata_mapping;
+ struct bnx2x_queue_update_tpa_params *update_tpa_params =
+ ¶ms->params.update_tpa;
+ u16 type;
+
+ /* Clear the ramrod data */
+ memset(rdata, 0, sizeof(*rdata));
+
+ /* Fill the ramrod data */
+ bnx2x_q_fill_update_tpa_data(bp, o, update_tpa_params, rdata);
+
+ /* Add the function id inside the type, so that sp post function
+ * doesn't automatically add the PF func-id, this is required
+ * for operations done by PFs on behalf of their VFs
+ */
+ type = ETH_CONNECTION_TYPE |
+ ((o->func_id) << SPE_HDR_FUNCTION_ID_SHIFT);
+
+ /* No need for an explicit memory barrier here as long as we
+ * ensure the ordering of writing to the SPQ element
+ * and updating of the SPQ producer which involves a memory
+ * read. If the memory read is removed we will have to put a
+ * full memory barrier there (inside bnx2x_sp_post()).
+ */
+ return bnx2x_sp_post(bp, RAMROD_CMD_ID_ETH_TPA_UPDATE,
+ o->cids[BNX2X_PRIMARY_CID_INDEX],
+ U64_HI(data_mapping),
+ U64_LO(data_mapping), type);
}
static inline int bnx2x_q_send_halt(struct bnx2x *bp,
@@ -5647,6 +5684,12 @@
rdata->tx_switch_suspend = switch_update_params->suspend;
rdata->echo = SWITCH_UPDATE;
+ /* No need for an explicit memory barrier here as long as we
+ * ensure the ordering of writing to the SPQ element
+ * and updating of the SPQ producer which involves a memory
+ * read. If the memory read is removed we will have to put a
+ * full memory barrier there (inside bnx2x_sp_post()).
+ */
return bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_FUNCTION_UPDATE, 0,
U64_HI(data_mapping),
U64_LO(data_mapping), NONE_CONNECTION_TYPE);
@@ -5674,11 +5717,11 @@
rdata->allowed_priorities = afex_update_params->allowed_priorities;
rdata->echo = AFEX_UPDATE;
- /* No need for an explicit memory barrier here as long we would
- * need to ensure the ordering of writing to the SPQ element
- * and updating of the SPQ producer which involves a memory
- * read and we will have to put a full memory barrier there
- * (inside bnx2x_sp_post()).
+ /* No need for an explicit memory barrier here as long as we
+ * ensure the ordering of writing to the SPQ element
+ * and updating of the SPQ producer which involves a memory
+ * read. If the memory read is removed we will have to put a
+ * full memory barrier there (inside bnx2x_sp_post()).
*/
DP(BNX2X_MSG_SP,
"afex: sending func_update vif_id 0x%x dvlan 0x%x prio 0x%x\n",
@@ -5763,6 +5806,12 @@
rdata->traffic_type_to_priority_cos[i] =
tx_start_params->traffic_type_to_priority_cos[i];
+ /* No need for an explicit memory barrier here as long as we
+ * ensure the ordering of writing to the SPQ element
+ * and updating of the SPQ producer which involves a memory
+ * read. If the memory read is removed we will have to put a
+ * full memory barrier there (inside bnx2x_sp_post()).
+ */
return bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_START_TRAFFIC, 0,
U64_HI(data_mapping),
U64_LO(data_mapping), NONE_CONNECTION_TYPE);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
index 00d7f21..80f6c79 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
@@ -893,6 +893,24 @@
u8 cid_index;
};
+struct bnx2x_queue_update_tpa_params {
+ dma_addr_t sge_map;
+ u8 update_ipv4;
+ u8 update_ipv6;
+ u8 max_tpa_queues;
+ u8 max_sges_pkt;
+ u8 complete_on_both_clients;
+ u8 dont_verify_thr;
+ u8 tpa_mode;
+ u8 _pad;
+
+ u16 sge_buff_sz;
+ u16 max_agg_sz;
+
+ u16 sge_pause_thr_low;
+ u16 sge_pause_thr_high;
+};
+
struct rxq_pause_params {
u16 bd_th_lo;
u16 bd_th_hi;
@@ -987,6 +1005,7 @@
/* Params according to the current command */
union {
struct bnx2x_queue_update_params update;
+ struct bnx2x_queue_update_tpa_params update_tpa;
struct bnx2x_queue_setup_params setup;
struct bnx2x_queue_init_params init;
struct bnx2x_queue_setup_tx_only_params tx_only;
@@ -1403,6 +1422,4 @@
void bnx2x_get_rss_ind_table(struct bnx2x_rss_config_obj *rss_obj,
u8 *ind_table);
-int validate_vlan_mac(struct bnx2x *bp,
- struct bnx2x_vlan_mac_obj *vlan_mac);
#endif /* BNX2X_SP_VERBS */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index aec5ef2..5c523b3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -102,82 +102,22 @@
mmiowb();
barrier();
}
-/* VFOP - VF slow-path operation support */
-#define BNX2X_VFOP_FILTER_ADD_CNT_MAX 0x10000
+static bool bnx2x_validate_vf_sp_objs(struct bnx2x *bp,
+ struct bnx2x_virtf *vf,
+ bool print_err)
+{
+ if (!bnx2x_leading_vfq(vf, sp_initialized)) {
+ if (print_err)
+ BNX2X_ERR("Slowpath objects not yet initialized!\n");
+ else
+ DP(BNX2X_MSG_IOV, "Slowpath objects not yet initialized!\n");
+ return false;
+ }
+ return true;
+}
/* VFOP operations states */
-enum bnx2x_vfop_qctor_state {
- BNX2X_VFOP_QCTOR_INIT,
- BNX2X_VFOP_QCTOR_SETUP,
- BNX2X_VFOP_QCTOR_INT_EN
-};
-
-enum bnx2x_vfop_qdtor_state {
- BNX2X_VFOP_QDTOR_HALT,
- BNX2X_VFOP_QDTOR_TERMINATE,
- BNX2X_VFOP_QDTOR_CFCDEL,
- BNX2X_VFOP_QDTOR_DONE
-};
-
-enum bnx2x_vfop_vlan_mac_state {
- BNX2X_VFOP_VLAN_MAC_CONFIG_SINGLE,
- BNX2X_VFOP_VLAN_MAC_CLEAR,
- BNX2X_VFOP_VLAN_MAC_CHK_DONE,
- BNX2X_VFOP_MAC_CONFIG_LIST,
- BNX2X_VFOP_VLAN_CONFIG_LIST,
- BNX2X_VFOP_VLAN_CONFIG_LIST_0
-};
-
-enum bnx2x_vfop_qsetup_state {
- BNX2X_VFOP_QSETUP_CTOR,
- BNX2X_VFOP_QSETUP_VLAN0,
- BNX2X_VFOP_QSETUP_DONE
-};
-
-enum bnx2x_vfop_mcast_state {
- BNX2X_VFOP_MCAST_DEL,
- BNX2X_VFOP_MCAST_ADD,
- BNX2X_VFOP_MCAST_CHK_DONE
-};
-enum bnx2x_vfop_qflr_state {
- BNX2X_VFOP_QFLR_CLR_VLAN,
- BNX2X_VFOP_QFLR_CLR_MAC,
- BNX2X_VFOP_QFLR_TERMINATE,
- BNX2X_VFOP_QFLR_DONE
-};
-
-enum bnx2x_vfop_flr_state {
- BNX2X_VFOP_FLR_QUEUES,
- BNX2X_VFOP_FLR_HW
-};
-
-enum bnx2x_vfop_close_state {
- BNX2X_VFOP_CLOSE_QUEUES,
- BNX2X_VFOP_CLOSE_HW
-};
-
-enum bnx2x_vfop_rxmode_state {
- BNX2X_VFOP_RXMODE_CONFIG,
- BNX2X_VFOP_RXMODE_DONE
-};
-
-enum bnx2x_vfop_qteardown_state {
- BNX2X_VFOP_QTEARDOWN_RXMODE,
- BNX2X_VFOP_QTEARDOWN_CLR_VLAN,
- BNX2X_VFOP_QTEARDOWN_CLR_MAC,
- BNX2X_VFOP_QTEARDOWN_CLR_MCAST,
- BNX2X_VFOP_QTEARDOWN_QDTOR,
- BNX2X_VFOP_QTEARDOWN_DONE
-};
-
-enum bnx2x_vfop_rss_state {
- BNX2X_VFOP_RSS_CONFIG,
- BNX2X_VFOP_RSS_DONE
-};
-
-#define bnx2x_vfop_reset_wq(vf) atomic_set(&vf->op_in_progress, 0)
-
void bnx2x_vfop_qctor_dump_tx(struct bnx2x *bp, struct bnx2x_virtf *vf,
struct bnx2x_queue_init_params *init_params,
struct bnx2x_queue_setup_params *setup_params,
@@ -221,7 +161,7 @@
void bnx2x_vfop_qctor_prep(struct bnx2x *bp,
struct bnx2x_virtf *vf,
struct bnx2x_vf_queue *q,
- struct bnx2x_vfop_qctor_params *p,
+ struct bnx2x_vf_queue_construct_params *p,
unsigned long q_type)
{
struct bnx2x_queue_init_params *init_p = &p->qstate.params.init;
@@ -290,191 +230,85 @@
}
}
-/* VFOP queue construction */
-static void bnx2x_vfop_qctor(struct bnx2x *bp, struct bnx2x_virtf *vf)
+static int bnx2x_vf_queue_create(struct bnx2x *bp,
+ struct bnx2x_virtf *vf, int qid,
+ struct bnx2x_vf_queue_construct_params *qctor)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- struct bnx2x_vfop_args_qctor *args = &vfop->args.qctor;
- struct bnx2x_queue_state_params *q_params = &vfop->op_p->qctor.qstate;
- enum bnx2x_vfop_qctor_state state = vfop->state;
+ struct bnx2x_queue_state_params *q_params;
+ int rc = 0;
- bnx2x_vfop_reset_wq(vf);
+ DP(BNX2X_MSG_IOV, "vf[%d:%d]\n", vf->abs_vfid, qid);
- if (vfop->rc < 0)
- goto op_err;
+ /* Prepare ramrod information */
+ q_params = &qctor->qstate;
+ q_params->q_obj = &bnx2x_vfq(vf, qid, sp_obj);
+ set_bit(RAMROD_COMP_WAIT, &q_params->ramrod_flags);
- DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
-
- switch (state) {
- case BNX2X_VFOP_QCTOR_INIT:
-
- /* has this queue already been opened? */
- if (bnx2x_get_q_logical_state(bp, q_params->q_obj) ==
- BNX2X_Q_LOGICAL_STATE_ACTIVE) {
- DP(BNX2X_MSG_IOV,
- "Entered qctor but queue was already up. Aborting gracefully\n");
- goto op_done;
- }
-
- /* next state */
- vfop->state = BNX2X_VFOP_QCTOR_SETUP;
-
- q_params->cmd = BNX2X_Q_CMD_INIT;
- vfop->rc = bnx2x_queue_state_change(bp, q_params);
-
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
-
- case BNX2X_VFOP_QCTOR_SETUP:
- /* next state */
- vfop->state = BNX2X_VFOP_QCTOR_INT_EN;
-
- /* copy pre-prepared setup params to the queue-state params */
- vfop->op_p->qctor.qstate.params.setup =
- vfop->op_p->qctor.prep_qsetup;
-
- q_params->cmd = BNX2X_Q_CMD_SETUP;
- vfop->rc = bnx2x_queue_state_change(bp, q_params);
-
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
-
- case BNX2X_VFOP_QCTOR_INT_EN:
-
- /* enable interrupts */
- bnx2x_vf_igu_ack_sb(bp, vf, vf_igu_sb(vf, args->sb_idx),
- USTORM_ID, 0, IGU_INT_ENABLE, 0);
- goto op_done;
- default:
- bnx2x_vfop_default(state);
+ if (bnx2x_get_q_logical_state(bp, q_params->q_obj) ==
+ BNX2X_Q_LOGICAL_STATE_ACTIVE) {
+ DP(BNX2X_MSG_IOV, "queue was already up. Aborting gracefully\n");
+ goto out;
}
-op_err:
- BNX2X_ERR("QCTOR[%d:%d] error: cmd %d, rc %d\n",
- vf->abs_vfid, args->qid, q_params->cmd, vfop->rc);
-op_done:
- bnx2x_vfop_end(bp, vf, vfop);
-op_pending:
- return;
+
+ /* Run Queue 'construction' ramrods */
+ q_params->cmd = BNX2X_Q_CMD_INIT;
+ rc = bnx2x_queue_state_change(bp, q_params);
+ if (rc)
+ goto out;
+
+ memcpy(&q_params->params.setup, &qctor->prep_qsetup,
+ sizeof(struct bnx2x_queue_setup_params));
+ q_params->cmd = BNX2X_Q_CMD_SETUP;
+ rc = bnx2x_queue_state_change(bp, q_params);
+ if (rc)
+ goto out;
+
+ /* enable interrupts */
+ bnx2x_vf_igu_ack_sb(bp, vf, vf_igu_sb(vf, bnx2x_vfq(vf, qid, sb_idx)),
+ USTORM_ID, 0, IGU_INT_ENABLE, 0);
+out:
+ return rc;
}
-static int bnx2x_vfop_qctor_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- int qid)
+static int bnx2x_vf_queue_destroy(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ int qid)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+ enum bnx2x_queue_cmd cmds[] = {BNX2X_Q_CMD_HALT,
+ BNX2X_Q_CMD_TERMINATE,
+ BNX2X_Q_CMD_CFC_DEL};
+ struct bnx2x_queue_state_params q_params;
+ int rc, i;
- if (vfop) {
- vf->op_params.qctor.qstate.q_obj = &bnx2x_vfq(vf, qid, sp_obj);
+ DP(BNX2X_MSG_IOV, "vf[%d]\n", vf->abs_vfid);
- vfop->args.qctor.qid = qid;
- vfop->args.qctor.sb_idx = bnx2x_vfq(vf, qid, sb_idx);
+ /* Prepare ramrod information */
+ memset(&q_params, 0, sizeof(struct bnx2x_queue_state_params));
+ q_params.q_obj = &bnx2x_vfq(vf, qid, sp_obj);
+ set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags);
- bnx2x_vfop_opset(BNX2X_VFOP_QCTOR_INIT,
- bnx2x_vfop_qctor, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qctor,
- cmd->block);
+ if (bnx2x_get_q_logical_state(bp, q_params.q_obj) ==
+ BNX2X_Q_LOGICAL_STATE_STOPPED) {
+ DP(BNX2X_MSG_IOV, "queue was already stopped. Aborting gracefully\n");
+ goto out;
}
- return -ENOMEM;
-}
-/* VFOP queue destruction */
-static void bnx2x_vfop_qdtor(struct bnx2x *bp, struct bnx2x_virtf *vf)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- struct bnx2x_vfop_args_qdtor *qdtor = &vfop->args.qdtor;
- struct bnx2x_queue_state_params *q_params = &vfop->op_p->qctor.qstate;
- enum bnx2x_vfop_qdtor_state state = vfop->state;
-
- bnx2x_vfop_reset_wq(vf);
-
- if (vfop->rc < 0)
- goto op_err;
-
- DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
-
- switch (state) {
- case BNX2X_VFOP_QDTOR_HALT:
-
- /* has this queue already been stopped? */
- if (bnx2x_get_q_logical_state(bp, q_params->q_obj) ==
- BNX2X_Q_LOGICAL_STATE_STOPPED) {
- DP(BNX2X_MSG_IOV,
- "Entered qdtor but queue was already stopped. Aborting gracefully\n");
-
- /* next state */
- vfop->state = BNX2X_VFOP_QDTOR_DONE;
-
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
+ /* Run Queue 'destruction' ramrods */
+ for (i = 0; i < ARRAY_SIZE(cmds); i++) {
+ q_params.cmd = cmds[i];
+ rc = bnx2x_queue_state_change(bp, &q_params);
+ if (rc) {
+ BNX2X_ERR("Failed to run Queue command %d\n", cmds[i]);
+ return rc;
}
-
- /* next state */
- vfop->state = BNX2X_VFOP_QDTOR_TERMINATE;
-
- q_params->cmd = BNX2X_Q_CMD_HALT;
- vfop->rc = bnx2x_queue_state_change(bp, q_params);
-
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
-
- case BNX2X_VFOP_QDTOR_TERMINATE:
- /* next state */
- vfop->state = BNX2X_VFOP_QDTOR_CFCDEL;
-
- q_params->cmd = BNX2X_Q_CMD_TERMINATE;
- vfop->rc = bnx2x_queue_state_change(bp, q_params);
-
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
-
- case BNX2X_VFOP_QDTOR_CFCDEL:
- /* next state */
- vfop->state = BNX2X_VFOP_QDTOR_DONE;
-
- q_params->cmd = BNX2X_Q_CMD_CFC_DEL;
- vfop->rc = bnx2x_queue_state_change(bp, q_params);
-
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
-op_err:
- BNX2X_ERR("QDTOR[%d:%d] error: cmd %d, rc %d\n",
- vf->abs_vfid, qdtor->qid, q_params->cmd, vfop->rc);
-op_done:
- case BNX2X_VFOP_QDTOR_DONE:
- /* invalidate the context */
- if (qdtor->cxt) {
- qdtor->cxt->ustorm_ag_context.cdu_usage = 0;
- qdtor->cxt->xstorm_ag_context.cdu_reserved = 0;
- }
- bnx2x_vfop_end(bp, vf, vfop);
- return;
- default:
- bnx2x_vfop_default(state);
}
-op_pending:
- return;
-}
-
-static int bnx2x_vfop_qdtor_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- int qid)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
-
- if (vfop) {
- struct bnx2x_queue_state_params *qstate =
- &vf->op_params.qctor.qstate;
-
- memset(qstate, 0, sizeof(*qstate));
- qstate->q_obj = &bnx2x_vfq(vf, qid, sp_obj);
-
- vfop->args.qdtor.qid = qid;
- vfop->args.qdtor.cxt = bnx2x_vfq(vf, qid, cxt);
-
- bnx2x_vfop_opset(BNX2X_VFOP_QDTOR_HALT,
- bnx2x_vfop_qdtor, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qdtor,
- cmd->block);
- } else {
- BNX2X_ERR("VF[%d] failed to add a vfop\n", vf->abs_vfid);
- return -ENOMEM;
+out:
+ /* Clean Context */
+ if (bnx2x_vfq(vf, qid, cxt)) {
+ bnx2x_vfq(vf, qid, cxt)->ustorm_ag_context.cdu_usage = 0;
+ bnx2x_vfq(vf, qid, cxt)->xstorm_ag_context.cdu_reserved = 0;
}
+
+ return 0;
}
static void
@@ -496,751 +330,293 @@
BP_VFDB(bp)->vf_sbs_pool++;
}
-/* VFOP MAC/VLAN helpers */
-static inline void bnx2x_vfop_credit(struct bnx2x *bp,
- struct bnx2x_vfop *vfop,
- struct bnx2x_vlan_mac_obj *obj)
+static inline void bnx2x_vf_vlan_credit(struct bnx2x *bp,
+ struct bnx2x_vlan_mac_obj *obj,
+ atomic_t *counter)
{
- struct bnx2x_vfop_args_filters *args = &vfop->args.filters;
+ struct list_head *pos;
+ int read_lock;
+ int cnt = 0;
- /* update credit only if there is no error
- * and a valid credit counter
- */
- if (!vfop->rc && args->credit) {
- struct list_head *pos;
- int read_lock;
- int cnt = 0;
+ read_lock = bnx2x_vlan_mac_h_read_lock(bp, obj);
+ if (read_lock)
+ DP(BNX2X_MSG_SP, "Failed to take vlan mac read head; continuing anyway\n");
- read_lock = bnx2x_vlan_mac_h_read_lock(bp, obj);
- if (read_lock)
- DP(BNX2X_MSG_SP, "Failed to take vlan mac read head; continuing anyway\n");
+ list_for_each(pos, &obj->head)
+ cnt++;
- list_for_each(pos, &obj->head)
- cnt++;
+ if (!read_lock)
+ bnx2x_vlan_mac_h_read_unlock(bp, obj);
- if (!read_lock)
- bnx2x_vlan_mac_h_read_unlock(bp, obj);
-
- atomic_set(args->credit, cnt);
- }
+ atomic_set(counter, cnt);
}
-static int bnx2x_vfop_set_user_req(struct bnx2x *bp,
- struct bnx2x_vfop_filter *pos,
- struct bnx2x_vlan_mac_data *user_req)
+static int bnx2x_vf_vlan_mac_clear(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ int qid, bool drv_only, bool mac)
{
- user_req->cmd = pos->add ? BNX2X_VLAN_MAC_ADD :
- BNX2X_VLAN_MAC_DEL;
+ struct bnx2x_vlan_mac_ramrod_params ramrod;
+ int rc;
- switch (pos->type) {
- case BNX2X_VFOP_FILTER_MAC:
- memcpy(user_req->u.mac.mac, pos->mac, ETH_ALEN);
- break;
- case BNX2X_VFOP_FILTER_VLAN:
- user_req->u.vlan.vlan = pos->vid;
- break;
- default:
- BNX2X_ERR("Invalid filter type, skipping\n");
- return 1;
+ DP(BNX2X_MSG_IOV, "vf[%d] - deleting all %s\n", vf->abs_vfid,
+ mac ? "MACs" : "VLANs");
+
+ /* Prepare ramrod params */
+ memset(&ramrod, 0, sizeof(struct bnx2x_vlan_mac_ramrod_params));
+ if (mac) {
+ set_bit(BNX2X_ETH_MAC, &ramrod.user_req.vlan_mac_flags);
+ ramrod.vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj);
+ } else {
+ set_bit(BNX2X_DONT_CONSUME_CAM_CREDIT,
+ &ramrod.user_req.vlan_mac_flags);
+ ramrod.vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
}
+ ramrod.user_req.cmd = BNX2X_VLAN_MAC_DEL;
+
+ set_bit(RAMROD_EXEC, &ramrod.ramrod_flags);
+ if (drv_only)
+ set_bit(RAMROD_DRV_CLR_ONLY, &ramrod.ramrod_flags);
+ else
+ set_bit(RAMROD_COMP_WAIT, &ramrod.ramrod_flags);
+
+ /* Start deleting */
+ rc = ramrod.vlan_mac_obj->delete_all(bp,
+ ramrod.vlan_mac_obj,
+ &ramrod.user_req.vlan_mac_flags,
+ &ramrod.ramrod_flags);
+ if (rc) {
+ BNX2X_ERR("Failed to delete all %s\n",
+ mac ? "MACs" : "VLANs");
+ return rc;
+ }
+
+ /* Clear the vlan counters */
+ if (!mac)
+ atomic_set(&bnx2x_vfq(vf, qid, vlan_count), 0);
+
return 0;
}
-static int bnx2x_vfop_config_list(struct bnx2x *bp,
- struct bnx2x_vfop_filters *filters,
- struct bnx2x_vlan_mac_ramrod_params *vlan_mac)
+static int bnx2x_vf_mac_vlan_config(struct bnx2x *bp,
+ struct bnx2x_virtf *vf, int qid,
+ struct bnx2x_vf_mac_vlan_filter *filter,
+ bool drv_only)
{
- struct bnx2x_vfop_filter *pos, *tmp;
- struct list_head rollback_list, *filters_list = &filters->head;
- struct bnx2x_vlan_mac_data *user_req = &vlan_mac->user_req;
- int rc = 0, cnt = 0;
+ struct bnx2x_vlan_mac_ramrod_params ramrod;
+ int rc;
- INIT_LIST_HEAD(&rollback_list);
+ DP(BNX2X_MSG_IOV, "vf[%d] - %s a %s filter\n",
+ vf->abs_vfid, filter->add ? "Adding" : "Deleting",
+ filter->type == BNX2X_VF_FILTER_MAC ? "MAC" : "VLAN");
- list_for_each_entry_safe(pos, tmp, filters_list, link) {
- if (bnx2x_vfop_set_user_req(bp, pos, user_req))
- continue;
+ /* Prepare ramrod params */
+ memset(&ramrod, 0, sizeof(struct bnx2x_vlan_mac_ramrod_params));
+ if (filter->type == BNX2X_VF_FILTER_VLAN) {
+ set_bit(BNX2X_DONT_CONSUME_CAM_CREDIT,
+ &ramrod.user_req.vlan_mac_flags);
+ ramrod.vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
+ ramrod.user_req.u.vlan.vlan = filter->vid;
+ } else {
+ set_bit(BNX2X_ETH_MAC, &ramrod.user_req.vlan_mac_flags);
+ ramrod.vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj);
+ memcpy(&ramrod.user_req.u.mac.mac, filter->mac, ETH_ALEN);
+ }
+ ramrod.user_req.cmd = filter->add ? BNX2X_VLAN_MAC_ADD :
+ BNX2X_VLAN_MAC_DEL;
- rc = bnx2x_config_vlan_mac(bp, vlan_mac);
- if (rc >= 0) {
- cnt += pos->add ? 1 : -1;
- list_move(&pos->link, &rollback_list);
- rc = 0;
- } else if (rc == -EEXIST) {
- rc = 0;
- } else {
- BNX2X_ERR("Failed to add a new vlan_mac command\n");
+ /* Verify there are available vlan credits */
+ if (filter->add && filter->type == BNX2X_VF_FILTER_VLAN &&
+ (atomic_read(&bnx2x_vfq(vf, qid, vlan_count)) >=
+ vf_vlan_rules_cnt(vf))) {
+ BNX2X_ERR("No credits for vlan\n");
+ return -ENOMEM;
+ }
+
+ set_bit(RAMROD_EXEC, &ramrod.ramrod_flags);
+ if (drv_only)
+ set_bit(RAMROD_DRV_CLR_ONLY, &ramrod.ramrod_flags);
+ else
+ set_bit(RAMROD_COMP_WAIT, &ramrod.ramrod_flags);
+
+ /* Add/Remove the filter */
+ rc = bnx2x_config_vlan_mac(bp, &ramrod);
+ if (rc && rc != -EEXIST) {
+ BNX2X_ERR("Failed to %s %s\n",
+ filter->add ? "add" : "delete",
+ filter->type == BNX2X_VF_FILTER_MAC ? "MAC" :
+ "VLAN");
+ return rc;
+ }
+
+ /* Update the vlan counters */
+ if (filter->type == BNX2X_VF_FILTER_VLAN)
+ bnx2x_vf_vlan_credit(bp, ramrod.vlan_mac_obj,
+ &bnx2x_vfq(vf, qid, vlan_count));
+
+ return 0;
+}
+
+int bnx2x_vf_mac_vlan_config_list(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ struct bnx2x_vf_mac_vlan_filters *filters,
+ int qid, bool drv_only)
+{
+ int rc = 0, i;
+
+ DP(BNX2X_MSG_IOV, "vf[%d]\n", vf->abs_vfid);
+
+ if (!bnx2x_validate_vf_sp_objs(bp, vf, true))
+ return -EINVAL;
+
+ /* Prepare ramrod params */
+ for (i = 0; i < filters->count; i++) {
+ rc = bnx2x_vf_mac_vlan_config(bp, vf, qid,
+ &filters->filters[i], drv_only);
+ if (rc)
break;
+ }
+
+ /* Rollback if needed */
+ if (i != filters->count) {
+ BNX2X_ERR("Managed only %d/%d filters - rolling back\n",
+ i, filters->count + 1);
+ while (--i >= 0) {
+ filters->filters[i].add = !filters->filters[i].add;
+ bnx2x_vf_mac_vlan_config(bp, vf, qid,
+ &filters->filters[i],
+ drv_only);
}
}
- /* rollback if error or too many rules added */
- if (rc || cnt > filters->add_cnt) {
- BNX2X_ERR("error or too many rules added. Performing rollback\n");
- list_for_each_entry_safe(pos, tmp, &rollback_list, link) {
- pos->add = !pos->add; /* reverse op */
- bnx2x_vfop_set_user_req(bp, pos, user_req);
- bnx2x_config_vlan_mac(bp, vlan_mac);
- list_del(&pos->link);
- }
- cnt = 0;
- if (!rc)
- rc = -EINVAL;
- }
- filters->add_cnt = cnt;
+ /* It's our responsibility to free the filters */
+ kfree(filters);
+
return rc;
}
-/* VFOP set VLAN/MAC */
-static void bnx2x_vfop_vlan_mac(struct bnx2x *bp, struct bnx2x_virtf *vf)
+int bnx2x_vf_queue_setup(struct bnx2x *bp, struct bnx2x_virtf *vf, int qid,
+ struct bnx2x_vf_queue_construct_params *qctor)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- struct bnx2x_vlan_mac_ramrod_params *vlan_mac = &vfop->op_p->vlan_mac;
- struct bnx2x_vlan_mac_obj *obj = vlan_mac->vlan_mac_obj;
- struct bnx2x_vfop_filters *filters = vfop->args.filters.multi_filter;
+ int rc;
- enum bnx2x_vfop_vlan_mac_state state = vfop->state;
+ DP(BNX2X_MSG_IOV, "vf[%d:%d]\n", vf->abs_vfid, qid);
- if (vfop->rc < 0)
+ rc = bnx2x_vf_queue_create(bp, vf, qid, qctor);
+ if (rc)
goto op_err;
- DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
+ /* Configure vlan0 for leading queue */
+ if (!qid) {
+ struct bnx2x_vf_mac_vlan_filter filter;
- bnx2x_vfop_reset_wq(vf);
-
- switch (state) {
- case BNX2X_VFOP_VLAN_MAC_CLEAR:
- /* next state */
- vfop->state = BNX2X_VFOP_VLAN_MAC_CHK_DONE;
-
- /* do delete */
- vfop->rc = obj->delete_all(bp, obj,
- &vlan_mac->user_req.vlan_mac_flags,
- &vlan_mac->ramrod_flags);
-
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
-
- case BNX2X_VFOP_VLAN_MAC_CONFIG_SINGLE:
- /* next state */
- vfop->state = BNX2X_VFOP_VLAN_MAC_CHK_DONE;
-
- /* do config */
- vfop->rc = bnx2x_config_vlan_mac(bp, vlan_mac);
- if (vfop->rc == -EEXIST)
- vfop->rc = 0;
-
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
-
- case BNX2X_VFOP_VLAN_MAC_CHK_DONE:
- vfop->rc = !!obj->raw.check_pending(&obj->raw);
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
-
- case BNX2X_VFOP_MAC_CONFIG_LIST:
- /* next state */
- vfop->state = BNX2X_VFOP_VLAN_MAC_CHK_DONE;
-
- /* do list config */
- vfop->rc = bnx2x_vfop_config_list(bp, filters, vlan_mac);
- if (vfop->rc)
+ memset(&filter, 0, sizeof(struct bnx2x_vf_mac_vlan_filter));
+ filter.type = BNX2X_VF_FILTER_VLAN;
+ filter.add = true;
+ filter.vid = 0;
+ rc = bnx2x_vf_mac_vlan_config(bp, vf, qid, &filter, false);
+ if (rc)
goto op_err;
-
- set_bit(RAMROD_CONT, &vlan_mac->ramrod_flags);
- vfop->rc = bnx2x_config_vlan_mac(bp, vlan_mac);
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
-
- case BNX2X_VFOP_VLAN_CONFIG_LIST:
- /* next state */
- vfop->state = BNX2X_VFOP_VLAN_MAC_CHK_DONE;
-
- /* do list config */
- vfop->rc = bnx2x_vfop_config_list(bp, filters, vlan_mac);
- if (!vfop->rc) {
- set_bit(RAMROD_CONT, &vlan_mac->ramrod_flags);
- vfop->rc = bnx2x_config_vlan_mac(bp, vlan_mac);
- }
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
-
- default:
- bnx2x_vfop_default(state);
}
+
+ /* Schedule the configuration of any pending vlan filters */
+ vf->cfg_flags |= VF_CFG_VLAN;
+ bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_HYPERVISOR_VLAN,
+ BNX2X_MSG_IOV);
+ return 0;
op_err:
- BNX2X_ERR("VLAN-MAC error: rc %d\n", vfop->rc);
-op_done:
- kfree(filters);
- bnx2x_vfop_credit(bp, vfop, obj);
- bnx2x_vfop_end(bp, vf, vfop);
-op_pending:
- return;
+ BNX2X_ERR("QSETUP[%d:%d] error: rc %d\n", vf->abs_vfid, qid, rc);
+ return rc;
}
-struct bnx2x_vfop_vlan_mac_flags {
- bool drv_only;
- bool dont_consume;
- bool single_cmd;
- bool add;
-};
-
-static void
-bnx2x_vfop_vlan_mac_prep_ramrod(struct bnx2x_vlan_mac_ramrod_params *ramrod,
- struct bnx2x_vfop_vlan_mac_flags *flags)
-{
- struct bnx2x_vlan_mac_data *ureq = &ramrod->user_req;
-
- memset(ramrod, 0, sizeof(*ramrod));
-
- /* ramrod flags */
- if (flags->drv_only)
- set_bit(RAMROD_DRV_CLR_ONLY, &ramrod->ramrod_flags);
- if (flags->single_cmd)
- set_bit(RAMROD_EXEC, &ramrod->ramrod_flags);
-
- /* mac_vlan flags */
- if (flags->dont_consume)
- set_bit(BNX2X_DONT_CONSUME_CAM_CREDIT, &ureq->vlan_mac_flags);
-
- /* cmd */
- ureq->cmd = flags->add ? BNX2X_VLAN_MAC_ADD : BNX2X_VLAN_MAC_DEL;
-}
-
-static inline void
-bnx2x_vfop_mac_prep_ramrod(struct bnx2x_vlan_mac_ramrod_params *ramrod,
- struct bnx2x_vfop_vlan_mac_flags *flags)
-{
- bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, flags);
- set_bit(BNX2X_ETH_MAC, &ramrod->user_req.vlan_mac_flags);
-}
-
-static int bnx2x_vfop_mac_delall_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- int qid, bool drv_only)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
- int rc;
-
- if (vfop) {
- struct bnx2x_vfop_args_filters filters = {
- .multi_filter = NULL, /* single */
- .credit = NULL, /* consume credit */
- };
- struct bnx2x_vfop_vlan_mac_flags flags = {
- .drv_only = drv_only,
- .dont_consume = (filters.credit != NULL),
- .single_cmd = true,
- .add = false /* don't care */,
- };
- struct bnx2x_vlan_mac_ramrod_params *ramrod =
- &vf->op_params.vlan_mac;
-
- /* set ramrod params */
- bnx2x_vfop_mac_prep_ramrod(ramrod, &flags);
-
- /* set object */
- rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj));
- if (rc)
- return rc;
- ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj);
-
- /* set extra args */
- vfop->args.filters = filters;
-
- bnx2x_vfop_opset(BNX2X_VFOP_VLAN_MAC_CLEAR,
- bnx2x_vfop_vlan_mac, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_vlan_mac,
- cmd->block);
- }
- return -ENOMEM;
-}
-
-int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- struct bnx2x_vfop_filters *macs,
- int qid, bool drv_only)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
- int rc;
-
- if (vfop) {
- struct bnx2x_vfop_args_filters filters = {
- .multi_filter = macs,
- .credit = NULL, /* consume credit */
- };
- struct bnx2x_vfop_vlan_mac_flags flags = {
- .drv_only = drv_only,
- .dont_consume = (filters.credit != NULL),
- .single_cmd = false,
- .add = false, /* don't care since only the items in the
- * filters list affect the sp operation,
- * not the list itself
- */
- };
- struct bnx2x_vlan_mac_ramrod_params *ramrod =
- &vf->op_params.vlan_mac;
-
- /* set ramrod params */
- bnx2x_vfop_mac_prep_ramrod(ramrod, &flags);
-
- /* set object */
- rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj));
- if (rc)
- return rc;
- ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj);
-
- /* set extra args */
- filters.multi_filter->add_cnt = BNX2X_VFOP_FILTER_ADD_CNT_MAX;
- vfop->args.filters = filters;
-
- bnx2x_vfop_opset(BNX2X_VFOP_MAC_CONFIG_LIST,
- bnx2x_vfop_vlan_mac, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_vlan_mac,
- cmd->block);
- }
- return -ENOMEM;
-}
-
-static int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- int qid, u16 vid, bool add)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
- int rc;
-
- if (vfop) {
- struct bnx2x_vfop_args_filters filters = {
- .multi_filter = NULL, /* single command */
- .credit = &bnx2x_vfq(vf, qid, vlan_count),
- };
- struct bnx2x_vfop_vlan_mac_flags flags = {
- .drv_only = false,
- .dont_consume = (filters.credit != NULL),
- .single_cmd = true,
- .add = add,
- };
- struct bnx2x_vlan_mac_ramrod_params *ramrod =
- &vf->op_params.vlan_mac;
-
- /* set ramrod params */
- bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags);
- ramrod->user_req.u.vlan.vlan = vid;
-
- /* set object */
- rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj));
- if (rc)
- return rc;
- ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
-
- /* set extra args */
- vfop->args.filters = filters;
-
- bnx2x_vfop_opset(BNX2X_VFOP_VLAN_MAC_CONFIG_SINGLE,
- bnx2x_vfop_vlan_mac, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_vlan_mac,
- cmd->block);
- }
- return -ENOMEM;
-}
-
-static int bnx2x_vfop_vlan_delall_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- int qid, bool drv_only)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
- int rc;
-
- if (vfop) {
- struct bnx2x_vfop_args_filters filters = {
- .multi_filter = NULL, /* single command */
- .credit = &bnx2x_vfq(vf, qid, vlan_count),
- };
- struct bnx2x_vfop_vlan_mac_flags flags = {
- .drv_only = drv_only,
- .dont_consume = (filters.credit != NULL),
- .single_cmd = true,
- .add = false, /* don't care */
- };
- struct bnx2x_vlan_mac_ramrod_params *ramrod =
- &vf->op_params.vlan_mac;
-
- /* set ramrod params */
- bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags);
-
- /* set object */
- rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj));
- if (rc)
- return rc;
- ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
-
- /* set extra args */
- vfop->args.filters = filters;
-
- bnx2x_vfop_opset(BNX2X_VFOP_VLAN_MAC_CLEAR,
- bnx2x_vfop_vlan_mac, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_vlan_mac,
- cmd->block);
- }
- return -ENOMEM;
-}
-
-int bnx2x_vfop_vlan_list_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- struct bnx2x_vfop_filters *vlans,
- int qid, bool drv_only)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
- int rc;
-
- if (vfop) {
- struct bnx2x_vfop_args_filters filters = {
- .multi_filter = vlans,
- .credit = &bnx2x_vfq(vf, qid, vlan_count),
- };
- struct bnx2x_vfop_vlan_mac_flags flags = {
- .drv_only = drv_only,
- .dont_consume = (filters.credit != NULL),
- .single_cmd = false,
- .add = false, /* don't care */
- };
- struct bnx2x_vlan_mac_ramrod_params *ramrod =
- &vf->op_params.vlan_mac;
-
- /* set ramrod params */
- bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags);
-
- /* set object */
- rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj));
- if (rc)
- return rc;
- ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
-
- /* set extra args */
- filters.multi_filter->add_cnt = vf_vlan_rules_cnt(vf) -
- atomic_read(filters.credit);
-
- vfop->args.filters = filters;
-
- bnx2x_vfop_opset(BNX2X_VFOP_VLAN_CONFIG_LIST,
- bnx2x_vfop_vlan_mac, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_vlan_mac,
- cmd->block);
- }
- return -ENOMEM;
-}
-
-/* VFOP queue setup (queue constructor + set vlan 0) */
-static void bnx2x_vfop_qsetup(struct bnx2x *bp, struct bnx2x_virtf *vf)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- int qid = vfop->args.qctor.qid;
- enum bnx2x_vfop_qsetup_state state = vfop->state;
- struct bnx2x_vfop_cmd cmd = {
- .done = bnx2x_vfop_qsetup,
- .block = false,
- };
-
- if (vfop->rc < 0)
- goto op_err;
-
- DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
-
- switch (state) {
- case BNX2X_VFOP_QSETUP_CTOR:
- /* init the queue ctor command */
- vfop->state = BNX2X_VFOP_QSETUP_VLAN0;
- vfop->rc = bnx2x_vfop_qctor_cmd(bp, vf, &cmd, qid);
- if (vfop->rc)
- goto op_err;
- return;
-
- case BNX2X_VFOP_QSETUP_VLAN0:
- /* skip if non-leading or FPGA/EMU*/
- if (qid)
- goto op_done;
-
- /* init the queue set-vlan command (for vlan 0) */
- vfop->state = BNX2X_VFOP_QSETUP_DONE;
- vfop->rc = bnx2x_vfop_vlan_set_cmd(bp, vf, &cmd, qid, 0, true);
- if (vfop->rc)
- goto op_err;
- return;
-op_err:
- BNX2X_ERR("QSETUP[%d:%d] error: rc %d\n", vf->abs_vfid, qid, vfop->rc);
-op_done:
- case BNX2X_VFOP_QSETUP_DONE:
- vf->cfg_flags |= VF_CFG_VLAN;
- smp_mb__before_clear_bit();
- set_bit(BNX2X_SP_RTNL_HYPERVISOR_VLAN,
- &bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
- schedule_delayed_work(&bp->sp_rtnl_task, 0);
- bnx2x_vfop_end(bp, vf, vfop);
- return;
- default:
- bnx2x_vfop_default(state);
- }
-}
-
-int bnx2x_vfop_qsetup_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- int qid)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
-
- if (vfop) {
- vfop->args.qctor.qid = qid;
-
- bnx2x_vfop_opset(BNX2X_VFOP_QSETUP_CTOR,
- bnx2x_vfop_qsetup, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qsetup,
- cmd->block);
- }
- return -ENOMEM;
-}
-
-/* VFOP queue FLR handling (clear vlans, clear macs, queue destructor) */
-static void bnx2x_vfop_qflr(struct bnx2x *bp, struct bnx2x_virtf *vf)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- int qid = vfop->args.qx.qid;
- enum bnx2x_vfop_qflr_state state = vfop->state;
- struct bnx2x_queue_state_params *qstate;
- struct bnx2x_vfop_cmd cmd;
-
- bnx2x_vfop_reset_wq(vf);
-
- if (vfop->rc < 0)
- goto op_err;
-
- DP(BNX2X_MSG_IOV, "VF[%d] STATE: %d\n", vf->abs_vfid, state);
-
- cmd.done = bnx2x_vfop_qflr;
- cmd.block = false;
-
- switch (state) {
- case BNX2X_VFOP_QFLR_CLR_VLAN:
- /* vlan-clear-all: driver-only, don't consume credit */
- vfop->state = BNX2X_VFOP_QFLR_CLR_MAC;
-
- if (!validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj))) {
- /* the vlan_mac vfop will re-schedule us */
- vfop->rc = bnx2x_vfop_vlan_delall_cmd(bp, vf, &cmd,
- qid, true);
- if (vfop->rc)
- goto op_err;
- return;
-
- } else {
- /* need to reschedule ourselves */
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
- }
-
- case BNX2X_VFOP_QFLR_CLR_MAC:
- /* mac-clear-all: driver only consume credit */
- vfop->state = BNX2X_VFOP_QFLR_TERMINATE;
- if (!validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj))) {
- /* the vlan_mac vfop will re-schedule us */
- vfop->rc = bnx2x_vfop_mac_delall_cmd(bp, vf, &cmd,
- qid, true);
- if (vfop->rc)
- goto op_err;
- return;
-
- } else {
- /* need to reschedule ourselves */
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
- }
-
- case BNX2X_VFOP_QFLR_TERMINATE:
- qstate = &vfop->op_p->qctor.qstate;
- memset(qstate , 0, sizeof(*qstate));
- qstate->q_obj = &bnx2x_vfq(vf, qid, sp_obj);
- vfop->state = BNX2X_VFOP_QFLR_DONE;
-
- DP(BNX2X_MSG_IOV, "VF[%d] qstate during flr was %d\n",
- vf->abs_vfid, qstate->q_obj->state);
-
- if (qstate->q_obj->state != BNX2X_Q_STATE_RESET) {
- qstate->q_obj->state = BNX2X_Q_STATE_STOPPED;
- qstate->cmd = BNX2X_Q_CMD_TERMINATE;
- vfop->rc = bnx2x_queue_state_change(bp, qstate);
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_VERIFY_PEND);
- } else {
- goto op_done;
- }
-
-op_err:
- BNX2X_ERR("QFLR[%d:%d] error: rc %d\n",
- vf->abs_vfid, qid, vfop->rc);
-op_done:
- case BNX2X_VFOP_QFLR_DONE:
- bnx2x_vfop_end(bp, vf, vfop);
- return;
- default:
- bnx2x_vfop_default(state);
- }
-op_pending:
- return;
-}
-
-static int bnx2x_vfop_qflr_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
+static int bnx2x_vf_queue_flr(struct bnx2x *bp, struct bnx2x_virtf *vf,
int qid)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+ int rc;
- if (vfop) {
- vfop->args.qx.qid = qid;
- bnx2x_vfop_opset(BNX2X_VFOP_QFLR_CLR_VLAN,
- bnx2x_vfop_qflr, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qflr,
- cmd->block);
+ DP(BNX2X_MSG_IOV, "vf[%d:%d]\n", vf->abs_vfid, qid);
+
+ /* If needed, clean the filtering data base */
+ if ((qid == LEADING_IDX) &&
+ bnx2x_validate_vf_sp_objs(bp, vf, false)) {
+ rc = bnx2x_vf_vlan_mac_clear(bp, vf, qid, true, false);
+ if (rc)
+ goto op_err;
+ rc = bnx2x_vf_vlan_mac_clear(bp, vf, qid, true, true);
+ if (rc)
+ goto op_err;
}
- return -ENOMEM;
-}
-/* VFOP multi-casts */
-static void bnx2x_vfop_mcast(struct bnx2x *bp, struct bnx2x_virtf *vf)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- struct bnx2x_mcast_ramrod_params *mcast = &vfop->op_p->mcast;
- struct bnx2x_raw_obj *raw = &mcast->mcast_obj->raw;
- struct bnx2x_vfop_args_mcast *args = &vfop->args.mc_list;
- enum bnx2x_vfop_mcast_state state = vfop->state;
- int i;
+ /* Terminate queue */
+ if (bnx2x_vfq(vf, qid, sp_obj).state != BNX2X_Q_STATE_RESET) {
+ struct bnx2x_queue_state_params qstate;
- bnx2x_vfop_reset_wq(vf);
-
- if (vfop->rc < 0)
- goto op_err;
-
- DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
-
- switch (state) {
- case BNX2X_VFOP_MCAST_DEL:
- /* clear existing mcasts */
- vfop->state = (args->mc_num) ? BNX2X_VFOP_MCAST_ADD
- : BNX2X_VFOP_MCAST_CHK_DONE;
- mcast->mcast_list_len = vf->mcast_list_len;
- vf->mcast_list_len = args->mc_num;
- vfop->rc = bnx2x_config_mcast(bp, mcast, BNX2X_MCAST_CMD_DEL);
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
-
- case BNX2X_VFOP_MCAST_ADD:
- if (raw->check_pending(raw))
- goto op_pending;
-
- /* update mcast list on the ramrod params */
- INIT_LIST_HEAD(&mcast->mcast_list);
- for (i = 0; i < args->mc_num; i++)
- list_add_tail(&(args->mc[i].link),
- &mcast->mcast_list);
- mcast->mcast_list_len = args->mc_num;
-
- /* add new mcasts */
- vfop->state = BNX2X_VFOP_MCAST_CHK_DONE;
- vfop->rc = bnx2x_config_mcast(bp, mcast,
- BNX2X_MCAST_CMD_ADD);
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
-
- case BNX2X_VFOP_MCAST_CHK_DONE:
- vfop->rc = raw->check_pending(raw) ? 1 : 0;
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
- default:
- bnx2x_vfop_default(state);
+ memset(&qstate, 0, sizeof(struct bnx2x_queue_state_params));
+ qstate.q_obj = &bnx2x_vfq(vf, qid, sp_obj);
+ qstate.q_obj->state = BNX2X_Q_STATE_STOPPED;
+ qstate.cmd = BNX2X_Q_CMD_TERMINATE;
+ set_bit(RAMROD_COMP_WAIT, &qstate.ramrod_flags);
+ rc = bnx2x_queue_state_change(bp, &qstate);
+ if (rc)
+ goto op_err;
}
+
+ return 0;
op_err:
- BNX2X_ERR("MCAST CONFIG error: rc %d\n", vfop->rc);
-op_done:
- kfree(args->mc);
- bnx2x_vfop_end(bp, vf, vfop);
-op_pending:
- return;
+ BNX2X_ERR("vf[%d:%d] error: rc %d\n", vf->abs_vfid, qid, rc);
+ return rc;
}
-int bnx2x_vfop_mcast_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- bnx2x_mac_addr_t *mcasts,
- int mcast_num, bool drv_only)
+int bnx2x_vf_mcast(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ bnx2x_mac_addr_t *mcasts, int mc_num, bool drv_only)
{
- struct bnx2x_vfop *vfop = NULL;
- size_t mc_sz = mcast_num * sizeof(struct bnx2x_mcast_list_elem);
- struct bnx2x_mcast_list_elem *mc = mc_sz ? kzalloc(mc_sz, GFP_KERNEL) :
- NULL;
+ struct bnx2x_mcast_list_elem *mc = NULL;
+ struct bnx2x_mcast_ramrod_params mcast;
+ int rc, i;
- if (!mc_sz || mc) {
- vfop = bnx2x_vfop_add(bp, vf);
- if (vfop) {
- int i;
- struct bnx2x_mcast_ramrod_params *ramrod =
- &vf->op_params.mcast;
+ DP(BNX2X_MSG_IOV, "vf[%d]\n", vf->abs_vfid);
- /* set ramrod params */
- memset(ramrod, 0, sizeof(*ramrod));
- ramrod->mcast_obj = &vf->mcast_obj;
- if (drv_only)
- set_bit(RAMROD_DRV_CLR_ONLY,
- &ramrod->ramrod_flags);
-
- /* copy mcasts pointers */
- vfop->args.mc_list.mc_num = mcast_num;
- vfop->args.mc_list.mc = mc;
- for (i = 0; i < mcast_num; i++)
- mc[i].mac = mcasts[i];
-
- bnx2x_vfop_opset(BNX2X_VFOP_MCAST_DEL,
- bnx2x_vfop_mcast, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_mcast,
- cmd->block);
- } else {
- kfree(mc);
+ /* Prepare Multicast command */
+ memset(&mcast, 0, sizeof(struct bnx2x_mcast_ramrod_params));
+ mcast.mcast_obj = &vf->mcast_obj;
+ if (drv_only)
+ set_bit(RAMROD_DRV_CLR_ONLY, &mcast.ramrod_flags);
+ else
+ set_bit(RAMROD_COMP_WAIT, &mcast.ramrod_flags);
+ if (mc_num) {
+ mc = kzalloc(mc_num * sizeof(struct bnx2x_mcast_list_elem),
+ GFP_KERNEL);
+ if (!mc) {
+ BNX2X_ERR("Cannot Configure mulicasts due to lack of memory\n");
+ return -ENOMEM;
}
}
- return -ENOMEM;
-}
-/* VFOP rx-mode */
-static void bnx2x_vfop_rxmode(struct bnx2x *bp, struct bnx2x_virtf *vf)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- struct bnx2x_rx_mode_ramrod_params *ramrod = &vfop->op_p->rx_mode;
- enum bnx2x_vfop_rxmode_state state = vfop->state;
-
- bnx2x_vfop_reset_wq(vf);
-
- if (vfop->rc < 0)
- goto op_err;
-
- DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
-
- switch (state) {
- case BNX2X_VFOP_RXMODE_CONFIG:
- /* next state */
- vfop->state = BNX2X_VFOP_RXMODE_DONE;
-
- /* record the accept flags in vfdb so hypervisor can modify them
- * if necessary
- */
- bnx2x_vfq(vf, ramrod->cl_id - vf->igu_base_id, accept_flags) =
- ramrod->rx_accept_flags;
- vfop->rc = bnx2x_config_rx_mode(bp, ramrod);
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
-op_err:
- BNX2X_ERR("RXMODE error: rc %d\n", vfop->rc);
-op_done:
- case BNX2X_VFOP_RXMODE_DONE:
- bnx2x_vfop_end(bp, vf, vfop);
- return;
- default:
- bnx2x_vfop_default(state);
+ /* clear existing mcasts */
+ mcast.mcast_list_len = vf->mcast_list_len;
+ vf->mcast_list_len = mc_num;
+ rc = bnx2x_config_mcast(bp, &mcast, BNX2X_MCAST_CMD_DEL);
+ if (rc) {
+ BNX2X_ERR("Failed to remove multicasts\n");
+ if (mc)
+ kfree(mc);
+ return rc;
}
-op_pending:
- return;
+
+ /* update mcast list on the ramrod params */
+ if (mc_num) {
+ INIT_LIST_HEAD(&mcast.mcast_list);
+ for (i = 0; i < mc_num; i++) {
+ mc[i].mac = mcasts[i];
+ list_add_tail(&mc[i].link,
+ &mcast.mcast_list);
+ }
+
+ /* add new mcasts */
+ rc = bnx2x_config_mcast(bp, &mcast, BNX2X_MCAST_CMD_ADD);
+ if (rc)
+ BNX2X_ERR("Faled to add multicasts\n");
+ kfree(mc);
+ }
+
+ return rc;
}
static void bnx2x_vf_prep_rx_mode(struct bnx2x *bp, u8 qid,
@@ -1268,118 +644,56 @@
ramrod->rdata_mapping = bnx2x_vf_sp_map(bp, vf, rx_mode_rdata.e2);
}
-int bnx2x_vfop_rxmode_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- int qid, unsigned long accept_flags)
+int bnx2x_vf_rxmode(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ int qid, unsigned long accept_flags)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+ struct bnx2x_rx_mode_ramrod_params ramrod;
- if (vfop) {
- struct bnx2x_rx_mode_ramrod_params *ramrod =
- &vf->op_params.rx_mode;
+ DP(BNX2X_MSG_IOV, "vf[%d]\n", vf->abs_vfid);
- bnx2x_vf_prep_rx_mode(bp, qid, ramrod, vf, accept_flags);
-
- bnx2x_vfop_opset(BNX2X_VFOP_RXMODE_CONFIG,
- bnx2x_vfop_rxmode, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_rxmode,
- cmd->block);
- }
- return -ENOMEM;
+ bnx2x_vf_prep_rx_mode(bp, qid, &ramrod, vf, accept_flags);
+ set_bit(RAMROD_COMP_WAIT, &ramrod.ramrod_flags);
+ vfq_get(vf, qid)->accept_flags = ramrod.rx_accept_flags;
+ return bnx2x_config_rx_mode(bp, &ramrod);
}
-/* VFOP queue tear-down ('drop all' rx-mode, clear vlans, clear macs,
- * queue destructor)
- */
-static void bnx2x_vfop_qdown(struct bnx2x *bp, struct bnx2x_virtf *vf)
+int bnx2x_vf_queue_teardown(struct bnx2x *bp, struct bnx2x_virtf *vf, int qid)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- int qid = vfop->args.qx.qid;
- enum bnx2x_vfop_qteardown_state state = vfop->state;
- struct bnx2x_vfop_cmd cmd;
+ int rc;
- if (vfop->rc < 0)
+ DP(BNX2X_MSG_IOV, "vf[%d:%d]\n", vf->abs_vfid, qid);
+
+ /* Remove all classification configuration for leading queue */
+ if (qid == LEADING_IDX) {
+ rc = bnx2x_vf_rxmode(bp, vf, qid, 0);
+ if (rc)
+ goto op_err;
+
+ /* Remove filtering if feasible */
+ if (bnx2x_validate_vf_sp_objs(bp, vf, true)) {
+ rc = bnx2x_vf_vlan_mac_clear(bp, vf, qid,
+ false, false);
+ if (rc)
+ goto op_err;
+ rc = bnx2x_vf_vlan_mac_clear(bp, vf, qid,
+ false, true);
+ if (rc)
+ goto op_err;
+ rc = bnx2x_vf_mcast(bp, vf, NULL, 0, false);
+ if (rc)
+ goto op_err;
+ }
+ }
+
+ /* Destroy queue */
+ rc = bnx2x_vf_queue_destroy(bp, vf, qid);
+ if (rc)
goto op_err;
-
- DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
-
- cmd.done = bnx2x_vfop_qdown;
- cmd.block = false;
-
- switch (state) {
- case BNX2X_VFOP_QTEARDOWN_RXMODE:
- /* Drop all */
- vfop->state = BNX2X_VFOP_QTEARDOWN_CLR_VLAN;
- vfop->rc = bnx2x_vfop_rxmode_cmd(bp, vf, &cmd, qid, 0);
- if (vfop->rc)
- goto op_err;
- return;
-
- case BNX2X_VFOP_QTEARDOWN_CLR_VLAN:
- /* vlan-clear-all: don't consume credit */
- vfop->state = BNX2X_VFOP_QTEARDOWN_CLR_MAC;
- vfop->rc = bnx2x_vfop_vlan_delall_cmd(bp, vf, &cmd, qid, false);
- if (vfop->rc)
- goto op_err;
- return;
-
- case BNX2X_VFOP_QTEARDOWN_CLR_MAC:
- /* mac-clear-all: consume credit */
- vfop->state = BNX2X_VFOP_QTEARDOWN_CLR_MCAST;
- vfop->rc = bnx2x_vfop_mac_delall_cmd(bp, vf, &cmd, qid, false);
- if (vfop->rc)
- goto op_err;
- return;
-
- case BNX2X_VFOP_QTEARDOWN_CLR_MCAST:
- vfop->state = BNX2X_VFOP_QTEARDOWN_QDTOR;
- vfop->rc = bnx2x_vfop_mcast_cmd(bp, vf, &cmd, NULL, 0, false);
- if (vfop->rc)
- goto op_err;
- return;
-
- case BNX2X_VFOP_QTEARDOWN_QDTOR:
- /* run the queue destruction flow */
- DP(BNX2X_MSG_IOV, "case: BNX2X_VFOP_QTEARDOWN_QDTOR\n");
- vfop->state = BNX2X_VFOP_QTEARDOWN_DONE;
- DP(BNX2X_MSG_IOV, "new state: BNX2X_VFOP_QTEARDOWN_DONE\n");
- vfop->rc = bnx2x_vfop_qdtor_cmd(bp, vf, &cmd, qid);
- DP(BNX2X_MSG_IOV, "returned from cmd\n");
- if (vfop->rc)
- goto op_err;
- return;
+ return rc;
op_err:
- BNX2X_ERR("QTEARDOWN[%d:%d] error: rc %d\n",
- vf->abs_vfid, qid, vfop->rc);
-
- case BNX2X_VFOP_QTEARDOWN_DONE:
- bnx2x_vfop_end(bp, vf, vfop);
- return;
- default:
- bnx2x_vfop_default(state);
- }
-}
-
-int bnx2x_vfop_qdown_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- int qid)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
-
- /* for non leading queues skip directly to qdown sate */
- if (vfop) {
- vfop->args.qx.qid = qid;
- bnx2x_vfop_opset(qid == LEADING_IDX ?
- BNX2X_VFOP_QTEARDOWN_RXMODE :
- BNX2X_VFOP_QTEARDOWN_QDTOR, bnx2x_vfop_qdown,
- cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qdown,
- cmd->block);
- }
-
- return -ENOMEM;
+ BNX2X_ERR("vf[%d:%d] error: rc %d\n",
+ vf->abs_vfid, qid, rc);
+ return rc;
}
/* VF enable primitives
@@ -1446,12 +760,12 @@
if (vf->cfg_flags & VF_CFG_INT_SIMD)
val |= IGU_VF_CONF_SINGLE_ISR_EN;
val &= ~IGU_VF_CONF_PARENT_MASK;
- val |= BP_FUNC(bp) << IGU_VF_CONF_PARENT_SHIFT; /* parent PF */
+ val |= (BP_ABS_FUNC(bp) >> 1) << IGU_VF_CONF_PARENT_SHIFT;
REG_WR(bp, IGU_REG_VF_CONFIGURATION, val);
DP(BNX2X_MSG_IOV,
- "value in IGU_REG_VF_CONFIGURATION of vf %d after write %x\n",
- vf->abs_vfid, REG_RD(bp, IGU_REG_VF_CONFIGURATION));
+ "value in IGU_REG_VF_CONFIGURATION of vf %d after write is 0x%08x\n",
+ vf->abs_vfid, val);
bnx2x_pretend_func(bp, BP_ABS_FUNC(bp));
@@ -1579,120 +893,63 @@
bnx2x_tx_hw_flushed(bp, poll_cnt);
}
-static void bnx2x_vfop_flr(struct bnx2x *bp, struct bnx2x_virtf *vf)
+static void bnx2x_vf_flr(struct bnx2x *bp, struct bnx2x_virtf *vf)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- struct bnx2x_vfop_args_qx *qx = &vfop->args.qx;
- enum bnx2x_vfop_flr_state state = vfop->state;
- struct bnx2x_vfop_cmd cmd = {
- .done = bnx2x_vfop_flr,
- .block = false,
- };
+ int rc, i;
- if (vfop->rc < 0)
- goto op_err;
+ DP(BNX2X_MSG_IOV, "vf[%d]\n", vf->abs_vfid);
- DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
-
- switch (state) {
- case BNX2X_VFOP_FLR_QUEUES:
- /* the cleanup operations are valid if and only if the VF
- * was first acquired.
- */
- if (++(qx->qid) < vf_rxq_count(vf)) {
- vfop->rc = bnx2x_vfop_qflr_cmd(bp, vf, &cmd,
- qx->qid);
- if (vfop->rc)
- goto op_err;
- return;
- }
- /* remove multicasts */
- vfop->state = BNX2X_VFOP_FLR_HW;
- vfop->rc = bnx2x_vfop_mcast_cmd(bp, vf, &cmd, NULL,
- 0, true);
- if (vfop->rc)
- goto op_err;
- return;
- case BNX2X_VFOP_FLR_HW:
-
- /* dispatch final cleanup and wait for HW queues to flush */
- bnx2x_vf_flr_clnup_hw(bp, vf);
-
- /* release VF resources */
- bnx2x_vf_free_resc(bp, vf);
-
- /* re-open the mailbox */
- bnx2x_vf_enable_mbx(bp, vf->abs_vfid);
-
- goto op_done;
- default:
- bnx2x_vfop_default(state);
+ /* the cleanup operations are valid if and only if the VF
+ * was first acquired.
+ */
+ for (i = 0; i < vf_rxq_count(vf); i++) {
+ rc = bnx2x_vf_queue_flr(bp, vf, i);
+ if (rc)
+ goto out;
}
-op_err:
- BNX2X_ERR("VF[%d] FLR error: rc %d\n", vf->abs_vfid, vfop->rc);
-op_done:
- vf->flr_clnup_stage = VF_FLR_ACK;
- bnx2x_vfop_end(bp, vf, vfop);
- bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_FLR);
+
+ /* remove multicasts */
+ bnx2x_vf_mcast(bp, vf, NULL, 0, true);
+
+ /* dispatch final cleanup and wait for HW queues to flush */
+ bnx2x_vf_flr_clnup_hw(bp, vf);
+
+ /* release VF resources */
+ bnx2x_vf_free_resc(bp, vf);
+
+ /* re-open the mailbox */
+ bnx2x_vf_enable_mbx(bp, vf->abs_vfid);
+ return;
+out:
+ BNX2X_ERR("vf[%d:%d] failed flr: rc %d\n",
+ vf->abs_vfid, i, rc);
}
-static int bnx2x_vfop_flr_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- vfop_handler_t done)
+static void bnx2x_vf_flr_clnup(struct bnx2x *bp)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
- if (vfop) {
- vfop->args.qx.qid = -1; /* loop */
- bnx2x_vfop_opset(BNX2X_VFOP_FLR_QUEUES,
- bnx2x_vfop_flr, done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_flr, false);
- }
- return -ENOMEM;
-}
-
-static void bnx2x_vf_flr_clnup(struct bnx2x *bp, struct bnx2x_virtf *prev_vf)
-{
- int i = prev_vf ? prev_vf->index + 1 : 0;
struct bnx2x_virtf *vf;
+ int i;
- /* find next VF to cleanup */
-next_vf_to_clean:
- for (;
- i < BNX2X_NR_VIRTFN(bp) &&
- (bnx2x_vf(bp, i, state) != VF_RESET ||
- bnx2x_vf(bp, i, flr_clnup_stage) != VF_FLR_CLN);
- i++)
- ;
+ for (i = 0; i < BNX2X_NR_VIRTFN(bp); i++) {
+ /* VF should be RESET & in FLR cleanup states */
+ if (bnx2x_vf(bp, i, state) != VF_RESET ||
+ !bnx2x_vf(bp, i, flr_clnup_stage))
+ continue;
- DP(BNX2X_MSG_IOV, "next vf to cleanup: %d. Num of vfs: %d\n", i,
- BNX2X_NR_VIRTFN(bp));
+ DP(BNX2X_MSG_IOV, "next vf to cleanup: %d. Num of vfs: %d\n",
+ i, BNX2X_NR_VIRTFN(bp));
- if (i < BNX2X_NR_VIRTFN(bp)) {
vf = BP_VF(bp, i);
/* lock the vf pf channel */
bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_FLR);
/* invoke the VF FLR SM */
- if (bnx2x_vfop_flr_cmd(bp, vf, bnx2x_vf_flr_clnup)) {
- BNX2X_ERR("VF[%d]: FLR cleanup failed -ENOMEM\n",
- vf->abs_vfid);
+ bnx2x_vf_flr(bp, vf);
- /* mark the VF to be ACKED and continue */
- vf->flr_clnup_stage = VF_FLR_ACK;
- goto next_vf_to_clean;
- }
- return;
- }
-
- /* we are done, update vf records */
- for_each_vf(bp, i) {
- vf = BP_VF(bp, i);
-
- if (vf->flr_clnup_stage != VF_FLR_ACK)
- continue;
-
- vf->flr_clnup_stage = VF_FLR_EPILOG;
+ /* mark the VF to be ACKED and continue */
+ vf->flr_clnup_stage = false;
+ bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_FLR);
}
/* Acknowledge the handled VFs.
@@ -1742,7 +999,7 @@
if (reset) {
/* set as reset and ready for cleanup */
vf->state = VF_RESET;
- vf->flr_clnup_stage = VF_FLR_CLN;
+ vf->flr_clnup_stage = true;
DP(BNX2X_MSG_IOV,
"Initiating Final cleanup for VF %d\n",
@@ -1751,7 +1008,7 @@
}
/* do the FLR cleanup for all marked VFs*/
- bnx2x_vf_flr_clnup(bp, NULL);
+ bnx2x_vf_flr_clnup(bp);
}
/* IOV global initialization routines */
@@ -2018,7 +1275,6 @@
bnx2x_vf(bp, i, index) = i;
bnx2x_vf(bp, i, abs_vfid) = iov->first_vf_in_pf + i;
bnx2x_vf(bp, i, state) = VF_FREE;
- INIT_LIST_HEAD(&bnx2x_vf(bp, i, op_list_head));
mutex_init(&bnx2x_vf(bp, i, op_mutex));
bnx2x_vf(bp, i, op_current) = CHANNEL_TLV_NONE;
}
@@ -2039,6 +1295,9 @@
goto failed;
}
+ /* Prepare the VFs event synchronization mechanism */
+ mutex_init(&bp->vfdb->event_mutex);
+
return 0;
failed:
DP(BNX2X_MSG_IOV, "Failed err=%d\n", err);
@@ -2117,7 +1376,9 @@
cxt->size = min_t(size_t, tot_size, CDU_ILT_PAGE_SZ);
if (cxt->size) {
- BNX2X_PCI_ALLOC(cxt->addr, &cxt->mapping, cxt->size);
+ cxt->addr = BNX2X_PCI_ALLOC(&cxt->mapping, cxt->size);
+ if (!cxt->addr)
+ goto alloc_mem_err;
} else {
cxt->addr = NULL;
cxt->mapping = 0;
@@ -2127,20 +1388,28 @@
/* allocate vfs ramrods dma memory - client_init and set_mac */
tot_size = BNX2X_NR_VIRTFN(bp) * sizeof(struct bnx2x_vf_sp);
- BNX2X_PCI_ALLOC(BP_VFDB(bp)->sp_dma.addr, &BP_VFDB(bp)->sp_dma.mapping,
- tot_size);
+ BP_VFDB(bp)->sp_dma.addr = BNX2X_PCI_ALLOC(&BP_VFDB(bp)->sp_dma.mapping,
+ tot_size);
+ if (!BP_VFDB(bp)->sp_dma.addr)
+ goto alloc_mem_err;
BP_VFDB(bp)->sp_dma.size = tot_size;
/* allocate mailboxes */
tot_size = BNX2X_NR_VIRTFN(bp) * MBX_MSG_ALIGNED_SIZE;
- BNX2X_PCI_ALLOC(BP_VF_MBX_DMA(bp)->addr, &BP_VF_MBX_DMA(bp)->mapping,
- tot_size);
+ BP_VF_MBX_DMA(bp)->addr = BNX2X_PCI_ALLOC(&BP_VF_MBX_DMA(bp)->mapping,
+ tot_size);
+ if (!BP_VF_MBX_DMA(bp)->addr)
+ goto alloc_mem_err;
+
BP_VF_MBX_DMA(bp)->size = tot_size;
/* allocate local bulletin boards */
tot_size = BNX2X_NR_VIRTFN(bp) * BULLETIN_CONTENT_SIZE;
- BNX2X_PCI_ALLOC(BP_VF_BULLETIN_DMA(bp)->addr,
- &BP_VF_BULLETIN_DMA(bp)->mapping, tot_size);
+ BP_VF_BULLETIN_DMA(bp)->addr = BNX2X_PCI_ALLOC(&BP_VF_BULLETIN_DMA(bp)->mapping,
+ tot_size);
+ if (!BP_VF_BULLETIN_DMA(bp)->addr)
+ goto alloc_mem_err;
+
BP_VF_BULLETIN_DMA(bp)->size = tot_size;
return 0;
@@ -2166,6 +1435,9 @@
bnx2x_vf_sp_map(bp, vf, q_data),
q_type);
+ /* sp indication is set only when vlan/mac/etc. are initialized */
+ q->sp_initialized = false;
+
DP(BNX2X_MSG_IOV,
"initialized vf %d's queue object. func id set to %d. cid set to 0x%x\n",
vf->abs_vfid, q->sp_obj.func_id, q->cid);
@@ -2269,7 +1541,7 @@
/* release all the VFs */
for_each_vf(bp, i)
- bnx2x_vf_release(bp, BP_VF(bp, i), true); /* blocking */
+ bnx2x_vf_release(bp, BP_VF(bp, i));
return 0;
}
@@ -2359,6 +1631,12 @@
smp_mb__after_clear_bit();
}
+static void bnx2x_vf_handle_rss_update_eqe(struct bnx2x *bp,
+ struct bnx2x_virtf *vf)
+{
+ vf->rss_conf_obj.raw.clear_pending(&vf->rss_conf_obj.raw);
+}
+
int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem)
{
struct bnx2x_virtf *vf;
@@ -2383,6 +1661,7 @@
case EVENT_RING_OPCODE_CLASSIFICATION_RULES:
case EVENT_RING_OPCODE_MULTICAST_RULES:
case EVENT_RING_OPCODE_FILTERS_RULES:
+ case EVENT_RING_OPCODE_RSS_UPDATE_RULES:
cid = (elem->message.data.eth_event.echo &
BNX2X_SWCID_MASK);
DP(BNX2X_MSG_IOV, "checking filtering comp cid=%d\n", cid);
@@ -2447,13 +1726,15 @@
vf->abs_vfid, qidx);
bnx2x_vf_handle_filters_eqe(bp, vf);
break;
+ case EVENT_RING_OPCODE_RSS_UPDATE_RULES:
+ DP(BNX2X_MSG_IOV, "got VF [%d:%d] RSS update ramrod\n",
+ vf->abs_vfid, qidx);
+ bnx2x_vf_handle_rss_update_eqe(bp, vf);
case EVENT_RING_OPCODE_VF_FLR:
case EVENT_RING_OPCODE_MALICIOUS_VF:
/* Do nothing for now */
return 0;
}
- /* SRIOV: reschedule any 'in_progress' operations */
- bnx2x_iov_sp_event(bp, cid, false);
return 0;
}
@@ -2490,23 +1771,6 @@
}
}
-void bnx2x_iov_sp_event(struct bnx2x *bp, int vf_cid, bool queue_work)
-{
- struct bnx2x_virtf *vf;
-
- /* check if the cid is the VF range */
- if (!IS_SRIOV(bp) || !bnx2x_iov_is_vf_cid(bp, vf_cid))
- return;
-
- vf = bnx2x_vf_by_cid(bp, vf_cid);
- if (vf) {
- /* set in_progress flag */
- atomic_set(&vf->op_in_progress, 1);
- if (queue_work)
- queue_delayed_work(bnx2x_wq, &bp->sp_task, 0);
- }
-}
-
void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
{
int i;
@@ -2527,10 +1791,10 @@
first_queue_query_index = BNX2X_FIRST_QUEUE_QUERY_IDX -
(is_fcoe ? 0 : 1);
- DP(BNX2X_MSG_IOV,
- "BNX2X_NUM_ETH_QUEUES %d, is_fcoe %d, first_queue_query_index %d => determined the last non virtual statistics query index is %d. Will add queries on top of that\n",
- BNX2X_NUM_ETH_QUEUES(bp), is_fcoe, first_queue_query_index,
- first_queue_query_index + num_queues_req);
+ DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS),
+ "BNX2X_NUM_ETH_QUEUES %d, is_fcoe %d, first_queue_query_index %d => determined the last non virtual statistics query index is %d. Will add queries on top of that\n",
+ BNX2X_NUM_ETH_QUEUES(bp), is_fcoe, first_queue_query_index,
+ first_queue_query_index + num_queues_req);
cur_data_offset = bp->fw_stats_data_mapping +
offsetof(struct bnx2x_fw_stats_data, queue_stats) +
@@ -2544,9 +1808,9 @@
struct bnx2x_virtf *vf = BP_VF(bp, i);
if (vf->state != VF_ENABLED) {
- DP(BNX2X_MSG_IOV,
- "vf %d not enabled so no stats for it\n",
- vf->abs_vfid);
+ DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS),
+ "vf %d not enabled so no stats for it\n",
+ vf->abs_vfid);
continue;
}
@@ -2588,32 +1852,6 @@
bp->fw_stats_req->hdr.cmd_num = bp->fw_stats_num + stats_count;
}
-void bnx2x_iov_sp_task(struct bnx2x *bp)
-{
- int i;
-
- if (!IS_SRIOV(bp))
- return;
- /* Iterate over all VFs and invoke state transition for VFs with
- * 'in-progress' slow-path operations
- */
- DP(BNX2X_MSG_IOV, "searching for pending vf operations\n");
- for_each_vf(bp, i) {
- struct bnx2x_virtf *vf = BP_VF(bp, i);
-
- if (!vf) {
- BNX2X_ERR("VF was null! skipping...\n");
- continue;
- }
-
- if (!list_empty(&vf->op_list_head) &&
- atomic_read(&vf->op_in_progress)) {
- DP(BNX2X_MSG_IOV, "running pending op for vf %d\n", i);
- bnx2x_vfop_cur(bp, vf)->transition(bp, vf);
- }
- }
-}
-
static inline
struct bnx2x_virtf *__vf_from_stat_id(struct bnx2x *bp, u8 stat_id)
{
@@ -2849,52 +2087,26 @@
p->vf->state = p->state;
}
-/* VFOP close (teardown the queues, delete mcasts and close HW) */
-static void bnx2x_vfop_close(struct bnx2x *bp, struct bnx2x_virtf *vf)
+int bnx2x_vf_close(struct bnx2x *bp, struct bnx2x_virtf *vf)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- struct bnx2x_vfop_args_qx *qx = &vfop->args.qx;
- enum bnx2x_vfop_close_state state = vfop->state;
- struct bnx2x_vfop_cmd cmd = {
- .done = bnx2x_vfop_close,
- .block = false,
- };
+ int rc = 0, i;
- if (vfop->rc < 0)
- goto op_err;
+ DP(BNX2X_MSG_IOV, "vf[%d]\n", vf->abs_vfid);
- DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
-
- switch (state) {
- case BNX2X_VFOP_CLOSE_QUEUES:
-
- if (++(qx->qid) < vf_rxq_count(vf)) {
- vfop->rc = bnx2x_vfop_qdown_cmd(bp, vf, &cmd, qx->qid);
- if (vfop->rc)
- goto op_err;
- return;
- }
- vfop->state = BNX2X_VFOP_CLOSE_HW;
- vfop->rc = 0;
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
-
- case BNX2X_VFOP_CLOSE_HW:
-
- /* disable the interrupts */
- DP(BNX2X_MSG_IOV, "disabling igu\n");
- bnx2x_vf_igu_disable(bp, vf);
-
- /* disable the VF */
- DP(BNX2X_MSG_IOV, "clearing qtbl\n");
- bnx2x_vf_clr_qtbl(bp, vf);
-
- goto op_done;
- default:
- bnx2x_vfop_default(state);
+ /* Close all queues */
+ for (i = 0; i < vf_rxq_count(vf); i++) {
+ rc = bnx2x_vf_queue_teardown(bp, vf, i);
+ if (rc)
+ goto op_err;
}
-op_err:
- BNX2X_ERR("VF[%d] CLOSE error: rc %d\n", vf->abs_vfid, vfop->rc);
-op_done:
+
+ /* disable the interrupts */
+ DP(BNX2X_MSG_IOV, "disabling igu\n");
+ bnx2x_vf_igu_disable(bp, vf);
+
+ /* disable the VF */
+ DP(BNX2X_MSG_IOV, "clearing qtbl\n");
+ bnx2x_vf_clr_qtbl(bp, vf);
/* need to make sure there are no outstanding stats ramrods which may
* cause the device to access the VF's stats buffer which it will free
@@ -2909,43 +2121,20 @@
}
DP(BNX2X_MSG_IOV, "set state to acquired\n");
- bnx2x_vfop_end(bp, vf, vfop);
-op_pending:
- /* Not supported at the moment; Exists for macros only */
- return;
-}
-int bnx2x_vfop_close_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
- if (vfop) {
- vfop->args.qx.qid = -1; /* loop */
- bnx2x_vfop_opset(BNX2X_VFOP_CLOSE_QUEUES,
- bnx2x_vfop_close, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_close,
- cmd->block);
- }
- return -ENOMEM;
+ return 0;
+op_err:
+ BNX2X_ERR("vf[%d] CLOSE error: rc %d\n", vf->abs_vfid, rc);
+ return rc;
}
/* VF release can be called either: 1. The VF was acquired but
* not enabled 2. the vf was enabled or in the process of being
* enabled
*/
-static void bnx2x_vfop_release(struct bnx2x *bp, struct bnx2x_virtf *vf)
+int bnx2x_vf_free(struct bnx2x *bp, struct bnx2x_virtf *vf)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- struct bnx2x_vfop_cmd cmd = {
- .done = bnx2x_vfop_release,
- .block = false,
- };
-
- DP(BNX2X_MSG_IOV, "vfop->rc %d\n", vfop->rc);
-
- if (vfop->rc < 0)
- goto op_err;
+ int rc;
DP(BNX2X_MSG_IOV, "VF[%d] STATE: %s\n", vf->abs_vfid,
vf->state == VF_FREE ? "Free" :
@@ -2956,116 +2145,87 @@
switch (vf->state) {
case VF_ENABLED:
- vfop->rc = bnx2x_vfop_close_cmd(bp, vf, &cmd);
- if (vfop->rc)
+ rc = bnx2x_vf_close(bp, vf);
+ if (rc)
goto op_err;
- return;
-
+ /* Fallthrough to release resources */
case VF_ACQUIRED:
DP(BNX2X_MSG_IOV, "about to free resources\n");
bnx2x_vf_free_resc(bp, vf);
- DP(BNX2X_MSG_IOV, "vfop->rc %d\n", vfop->rc);
- goto op_done;
+ break;
case VF_FREE:
case VF_RESET:
- /* do nothing */
- goto op_done;
default:
- bnx2x_vfop_default(vf->state);
+ break;
}
+ return 0;
op_err:
- BNX2X_ERR("VF[%d] RELEASE error: rc %d\n", vf->abs_vfid, vfop->rc);
-op_done:
- bnx2x_vfop_end(bp, vf, vfop);
+ BNX2X_ERR("VF[%d] RELEASE error: rc %d\n", vf->abs_vfid, rc);
+ return rc;
}
-static void bnx2x_vfop_rss(struct bnx2x *bp, struct bnx2x_virtf *vf)
+int bnx2x_vf_rss_update(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ struct bnx2x_config_rss_params *rss)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- enum bnx2x_vfop_rss_state state;
-
- if (!vfop) {
- BNX2X_ERR("vfop was null\n");
- return;
- }
-
- state = vfop->state;
- bnx2x_vfop_reset_wq(vf);
-
- if (vfop->rc < 0)
- goto op_err;
-
- DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
-
- switch (state) {
- case BNX2X_VFOP_RSS_CONFIG:
- /* next state */
- vfop->state = BNX2X_VFOP_RSS_DONE;
- bnx2x_config_rss(bp, &vfop->op_p->rss);
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
-op_err:
- BNX2X_ERR("RSS error: rc %d\n", vfop->rc);
-op_done:
- case BNX2X_VFOP_RSS_DONE:
- bnx2x_vfop_end(bp, vf, vfop);
- return;
- default:
- bnx2x_vfop_default(state);
- }
-op_pending:
- return;
+ DP(BNX2X_MSG_IOV, "vf[%d]\n", vf->abs_vfid);
+ set_bit(RAMROD_COMP_WAIT, &rss->ramrod_flags);
+ return bnx2x_config_rss(bp, rss);
}
-int bnx2x_vfop_release_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd)
+int bnx2x_vf_tpa_update(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ struct vfpf_tpa_tlv *tlv,
+ struct bnx2x_queue_update_tpa_params *params)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
- if (vfop) {
- bnx2x_vfop_opset(-1, /* use vf->state */
- bnx2x_vfop_release, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_release,
- cmd->block);
- }
- return -ENOMEM;
-}
+ aligned_u64 *sge_addr = tlv->tpa_client_info.sge_addr;
+ struct bnx2x_queue_state_params qstate;
+ int qid, rc = 0;
-int bnx2x_vfop_rss_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd)
-{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+ DP(BNX2X_MSG_IOV, "vf[%d]\n", vf->abs_vfid);
- if (vfop) {
- bnx2x_vfop_opset(BNX2X_VFOP_RSS_CONFIG, bnx2x_vfop_rss,
- cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_rss,
- cmd->block);
+ /* Set ramrod params */
+ memset(&qstate, 0, sizeof(struct bnx2x_queue_state_params));
+ memcpy(&qstate.params.update_tpa, params,
+ sizeof(struct bnx2x_queue_update_tpa_params));
+ qstate.cmd = BNX2X_Q_CMD_UPDATE_TPA;
+ set_bit(RAMROD_COMP_WAIT, &qstate.ramrod_flags);
+
+ for (qid = 0; qid < vf_rxq_count(vf); qid++) {
+ qstate.q_obj = &bnx2x_vfq(vf, qid, sp_obj);
+ qstate.params.update_tpa.sge_map = sge_addr[qid];
+ DP(BNX2X_MSG_IOV, "sge_addr[%d:%d] %08x:%08x\n",
+ vf->abs_vfid, qid, U64_HI(sge_addr[qid]),
+ U64_LO(sge_addr[qid]));
+ rc = bnx2x_queue_state_change(bp, &qstate);
+ if (rc) {
+ BNX2X_ERR("Failed to configure sge_addr %08x:%08x for [%d:%d]\n",
+ U64_HI(sge_addr[qid]), U64_LO(sge_addr[qid]),
+ vf->abs_vfid, qid);
+ return rc;
+ }
}
- return -ENOMEM;
+
+ return rc;
}
/* VF release ~ VF close + VF release-resources
* Release is the ultimate SW shutdown and is called whenever an
* irrecoverable error is encountered.
*/
-void bnx2x_vf_release(struct bnx2x *bp, struct bnx2x_virtf *vf, bool block)
+int bnx2x_vf_release(struct bnx2x *bp, struct bnx2x_virtf *vf)
{
- struct bnx2x_vfop_cmd cmd = {
- .done = NULL,
- .block = block,
- };
int rc;
DP(BNX2X_MSG_IOV, "PF releasing vf %d\n", vf->abs_vfid);
bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_RELEASE_VF);
- rc = bnx2x_vfop_release_cmd(bp, vf, &cmd);
+ rc = bnx2x_vf_free(bp, vf);
if (rc)
WARN(rc,
"VF[%d] Failed to allocate resources for release op- rc=%d\n",
vf->abs_vfid, rc);
+ bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_RELEASE_VF);
+ return rc;
}
static inline void bnx2x_vf_get_sbdf(struct bnx2x *bp,
@@ -3074,16 +2234,6 @@
*sbdf = vf->devfn | (vf->bus << 8);
}
-static inline void bnx2x_vf_get_bars(struct bnx2x *bp, struct bnx2x_virtf *vf,
- struct bnx2x_vf_bar_info *bar_info)
-{
- int n;
-
- bar_info->nr_bars = bp->vfdb->sriov.nres;
- for (n = 0; n < bar_info->nr_bars; n++)
- bar_info->bars[n] = vf->bars[n];
-}
-
void bnx2x_lock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
enum channel_tlvs tlv)
{
@@ -3405,13 +2555,13 @@
ivi->spoofchk = 1; /*always enabled */
if (vf->state == VF_ENABLED) {
/* mac and vlan are in vlan_mac objects */
- if (validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj)))
+ if (bnx2x_validate_vf_sp_objs(bp, vf, false)) {
mac_obj->get_n_elements(bp, mac_obj, 1, (u8 *)&ivi->mac,
0, ETH_ALEN);
- if (validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, vlan_obj)))
vlan_obj->get_n_elements(bp, vlan_obj, 1,
(u8 *)&ivi->vlan, 0,
VLAN_HLEN);
+ }
} else {
/* mac */
if (bulletin->valid_bitmap & (1 << MAC_ADDR_VALID))
@@ -3485,17 +2635,17 @@
q_logical_state == BNX2X_Q_LOGICAL_STATE_ACTIVE) {
/* configure the mac in device on this vf's queue */
unsigned long ramrod_flags = 0;
- struct bnx2x_vlan_mac_obj *mac_obj =
- &bnx2x_leading_vfq(vf, mac_obj);
+ struct bnx2x_vlan_mac_obj *mac_obj;
- rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj));
- if (rc)
- return rc;
+ /* User should be able to see failure reason in system logs */
+ if (!bnx2x_validate_vf_sp_objs(bp, vf, true))
+ return -EINVAL;
/* must lock vfpf channel to protect against vf flows */
bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_MAC);
/* remove existing eth macs */
+ mac_obj = &bnx2x_leading_vfq(vf, mac_obj);
rc = bnx2x_del_all_macs(bp, mac_obj, BNX2X_ETH_MAC, true);
if (rc) {
BNX2X_ERR("failed to delete eth macs\n");
@@ -3569,17 +2719,16 @@
BNX2X_Q_LOGICAL_STATE_ACTIVE)
return rc;
- /* configure the vlan in device on this vf's queue */
- vlan_obj = &bnx2x_leading_vfq(vf, vlan_obj);
- rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj));
- if (rc)
- return rc;
+ /* User should be able to see error in system logs */
+ if (!bnx2x_validate_vf_sp_objs(bp, vf, true))
+ return -EINVAL;
/* must lock vfpf channel to protect against vf flows */
bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_VLAN);
/* remove existing vlans */
__set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
+ vlan_obj = &bnx2x_leading_vfq(vf, vlan_obj);
rc = vlan_obj->delete_all(bp, vlan_obj, &vlan_mac_flags,
&ramrod_flags);
if (rc) {
@@ -3736,13 +2885,9 @@
bnx2x_sample_bulletin(bp);
/* if channel is down we need to self destruct */
- if (bp->old_bulletin.valid_bitmap & 1 << CHANNEL_DOWN) {
- smp_mb__before_clear_bit();
- set_bit(BNX2X_SP_RTNL_VFPF_CHANNEL_DOWN,
- &bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
- schedule_delayed_work(&bp->sp_rtnl_task, 0);
- }
+ if (bp->old_bulletin.valid_bitmap & 1 << CHANNEL_DOWN)
+ bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_VFPF_CHANNEL_DOWN,
+ BNX2X_MSG_IOV);
}
void __iomem *bnx2x_vf_doorbells(struct bnx2x *bp)
@@ -3756,12 +2901,16 @@
mutex_init(&bp->vf2pf_mutex);
/* allocate vf2pf mailbox for vf to pf channel */
- BNX2X_PCI_ALLOC(bp->vf2pf_mbox, &bp->vf2pf_mbox_mapping,
- sizeof(struct bnx2x_vf_mbx_msg));
+ bp->vf2pf_mbox = BNX2X_PCI_ALLOC(&bp->vf2pf_mbox_mapping,
+ sizeof(struct bnx2x_vf_mbx_msg));
+ if (!bp->vf2pf_mbox)
+ goto alloc_mem_err;
/* allocate pf 2 vf bulletin board */
- BNX2X_PCI_ALLOC(bp->pf2vf_bulletin, &bp->pf2vf_bulletin_mapping,
- sizeof(union pf_vf_bulletin));
+ bp->pf2vf_bulletin = BNX2X_PCI_ALLOC(&bp->pf2vf_bulletin_mapping,
+ sizeof(union pf_vf_bulletin));
+ if (!bp->pf2vf_bulletin)
+ goto alloc_mem_err;
return 0;
@@ -3792,3 +2941,28 @@
bnx2x_post_vf_bulletin(bp, vf_idx);
}
}
+
+void bnx2x_iov_task(struct work_struct *work)
+{
+ struct bnx2x *bp = container_of(work, struct bnx2x, iov_task.work);
+
+ if (!netif_running(bp->dev))
+ return;
+
+ if (test_and_clear_bit(BNX2X_IOV_HANDLE_FLR,
+ &bp->iov_task_state))
+ bnx2x_vf_handle_flr_event(bp);
+
+ if (test_and_clear_bit(BNX2X_IOV_HANDLE_VF_MSG,
+ &bp->iov_task_state))
+ bnx2x_vf_mbx(bp);
+}
+
+void bnx2x_schedule_iov_task(struct bnx2x *bp, enum bnx2x_iov_flag flag)
+{
+ smp_mb__before_clear_bit();
+ set_bit(flag, &bp->iov_task_state);
+ smp_mb__after_clear_bit();
+ DP(BNX2X_MSG_IOV, "Scheduling iov task [Flag: %d]\n", flag);
+ queue_delayed_work(bnx2x_iov_wq, &bp->iov_task, 0);
+}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index d9fcca1..8bf7645 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -30,6 +30,8 @@
#ifdef CONFIG_BNX2X_SRIOV
+extern struct workqueue_struct *bnx2x_iov_wq;
+
/* The bnx2x device structure holds vfdb structure described below.
* The VF array is indexed by the relative vfid.
*/
@@ -83,108 +85,35 @@
u16 index;
u16 sb_idx;
bool is_leading;
+ bool sp_initialized;
};
-/* struct bnx2x_vfop_qctor_params - prepare queue construction parameters:
- * q-init, q-setup and SB index
+/* struct bnx2x_vf_queue_construct_params - prepare queue construction
+ * parameters: q-init, q-setup and SB index
*/
-struct bnx2x_vfop_qctor_params {
+struct bnx2x_vf_queue_construct_params {
struct bnx2x_queue_state_params qstate;
struct bnx2x_queue_setup_params prep_qsetup;
};
-/* VFOP parameters (one copy per VF) */
-union bnx2x_vfop_params {
- struct bnx2x_vlan_mac_ramrod_params vlan_mac;
- struct bnx2x_rx_mode_ramrod_params rx_mode;
- struct bnx2x_mcast_ramrod_params mcast;
- struct bnx2x_config_rss_params rss;
- struct bnx2x_vfop_qctor_params qctor;
-};
-
/* forward */
struct bnx2x_virtf;
/* VFOP definitions */
-typedef void (*vfop_handler_t)(struct bnx2x *bp, struct bnx2x_virtf *vf);
-struct bnx2x_vfop_cmd {
- vfop_handler_t done;
- bool block;
-};
-
-/* VFOP queue filters command additional arguments */
-struct bnx2x_vfop_filter {
- struct list_head link;
+struct bnx2x_vf_mac_vlan_filter {
int type;
-#define BNX2X_VFOP_FILTER_MAC 1
-#define BNX2X_VFOP_FILTER_VLAN 2
+#define BNX2X_VF_FILTER_MAC 1
+#define BNX2X_VF_FILTER_VLAN 2
bool add;
u8 *mac;
u16 vid;
};
-struct bnx2x_vfop_filters {
- int add_cnt;
- struct list_head head;
- struct bnx2x_vfop_filter filters[];
-};
-
-/* transient list allocated, built and saved until its
- * passed to the SP-VERBs layer.
- */
-struct bnx2x_vfop_args_mcast {
- int mc_num;
- struct bnx2x_mcast_list_elem *mc;
-};
-
-struct bnx2x_vfop_args_qctor {
- int qid;
- u16 sb_idx;
-};
-
-struct bnx2x_vfop_args_qdtor {
- int qid;
- struct eth_context *cxt;
-};
-
-struct bnx2x_vfop_args_defvlan {
- int qid;
- bool enable;
- u16 vid;
- u8 prio;
-};
-
-struct bnx2x_vfop_args_qx {
- int qid;
- bool en_add;
-};
-
-struct bnx2x_vfop_args_filters {
- struct bnx2x_vfop_filters *multi_filter;
- atomic_t *credit; /* non NULL means 'don't consume credit' */
-};
-
-union bnx2x_vfop_args {
- struct bnx2x_vfop_args_mcast mc_list;
- struct bnx2x_vfop_args_qctor qctor;
- struct bnx2x_vfop_args_qdtor qdtor;
- struct bnx2x_vfop_args_defvlan defvlan;
- struct bnx2x_vfop_args_qx qx;
- struct bnx2x_vfop_args_filters filters;
-};
-
-struct bnx2x_vfop {
- struct list_head link;
- int rc; /* return code */
- int state; /* next state */
- union bnx2x_vfop_args args; /* extra arguments */
- union bnx2x_vfop_params *op_p; /* ramrod params */
-
- /* state machine callbacks */
- vfop_handler_t transition;
- vfop_handler_t done;
+struct bnx2x_vf_mac_vlan_filters {
+ int count;
+ struct bnx2x_vf_mac_vlan_filter filters[];
};
/* vf context */
@@ -204,15 +133,7 @@
#define VF_ENABLED 2 /* VF Enabled */
#define VF_RESET 3 /* VF FLR'd, pending cleanup */
- /* non 0 during flr cleanup */
- u8 flr_clnup_stage;
-#define VF_FLR_CLN 1 /* reclaim resources and do 'final cleanup'
- * sans the end-wait
- */
-#define VF_FLR_ACK 2 /* ACK flr notification */
-#define VF_FLR_EPILOG 3 /* wait for VF remnants to dissipate in the HW
- * ~ final cleanup' end wait
- */
+ bool flr_clnup_stage; /* true during flr cleanup */
/* dma */
dma_addr_t fw_stat_map; /* valid iff VF_CFG_STATS */
@@ -276,11 +197,6 @@
struct bnx2x_rss_config_obj rss_conf_obj;
/* slow-path operations */
- atomic_t op_in_progress;
- int op_rc;
- bool op_wait_blocking;
- struct list_head op_list_head;
- union bnx2x_vfop_params op_params;
struct mutex op_mutex; /* one vfop at a time mutex */
enum channel_tlvs op_current;
};
@@ -338,11 +254,6 @@
u32 vf_addr_hi;
struct vfpf_first_tlv first_tlv; /* saved VF request header */
-
- u8 flags;
-#define VF_MSG_INPROCESS 0x1 /* failsafe - the FW should prevent
- * more then one pending msg
- */
};
struct bnx2x_vf_sp {
@@ -419,6 +330,10 @@
/* the number of msix vectors belonging to this PF designated for VFs */
u16 vf_sbs_pool;
u16 first_vf_igu_entry;
+
+ /* sp_rtnl synchronization */
+ struct mutex event_mutex;
+ u64 event_occur;
};
/* queue access */
@@ -468,13 +383,13 @@
void bnx2x_iov_init_dmae(struct bnx2x *bp);
void bnx2x_iov_set_queue_sp_obj(struct bnx2x *bp, int vf_cid,
struct bnx2x_queue_sp_obj **q_obj);
-void bnx2x_iov_sp_event(struct bnx2x *bp, int vf_cid, bool queue_work);
int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem);
void bnx2x_iov_adjust_stats_req(struct bnx2x *bp);
void bnx2x_iov_storm_stats_update(struct bnx2x *bp);
-void bnx2x_iov_sp_task(struct bnx2x *bp);
/* global vf mailbox routines */
-void bnx2x_vf_mbx(struct bnx2x *bp, struct vf_pf_event_data *vfpf_event);
+void bnx2x_vf_mbx(struct bnx2x *bp);
+void bnx2x_vf_mbx_schedule(struct bnx2x *bp,
+ struct vf_pf_event_data *vfpf_event);
void bnx2x_vf_enable_mbx(struct bnx2x *bp, u8 abs_vfid);
/* CORE VF API */
@@ -487,162 +402,6 @@
int bnx2x_vf_init(struct bnx2x *bp, struct bnx2x_virtf *vf,
dma_addr_t *sb_map);
-/* VFOP generic helpers */
-#define bnx2x_vfop_default(state) do { \
- BNX2X_ERR("Bad state %d\n", (state)); \
- vfop->rc = -EINVAL; \
- goto op_err; \
- } while (0)
-
-enum {
- VFOP_DONE,
- VFOP_CONT,
- VFOP_VERIFY_PEND,
-};
-
-#define bnx2x_vfop_finalize(vf, rc, next) do { \
- if ((rc) < 0) \
- goto op_err; \
- else if ((rc) > 0) \
- goto op_pending; \
- else if ((next) == VFOP_DONE) \
- goto op_done; \
- else if ((next) == VFOP_VERIFY_PEND) \
- BNX2X_ERR("expected pending\n"); \
- else { \
- DP(BNX2X_MSG_IOV, "no ramrod. Scheduling\n"); \
- atomic_set(&vf->op_in_progress, 1); \
- queue_delayed_work(bnx2x_wq, &bp->sp_task, 0); \
- return; \
- } \
- } while (0)
-
-#define bnx2x_vfop_opset(first_state, trans_hndlr, done_hndlr) \
- do { \
- vfop->state = first_state; \
- vfop->op_p = &vf->op_params; \
- vfop->transition = trans_hndlr; \
- vfop->done = done_hndlr; \
- } while (0)
-
-static inline struct bnx2x_vfop *bnx2x_vfop_cur(struct bnx2x *bp,
- struct bnx2x_virtf *vf)
-{
- WARN(!mutex_is_locked(&vf->op_mutex), "about to access vf op linked list but mutex was not locked!");
- WARN_ON(list_empty(&vf->op_list_head));
- return list_first_entry(&vf->op_list_head, struct bnx2x_vfop, link);
-}
-
-static inline struct bnx2x_vfop *bnx2x_vfop_add(struct bnx2x *bp,
- struct bnx2x_virtf *vf)
-{
- struct bnx2x_vfop *vfop = kzalloc(sizeof(*vfop), GFP_KERNEL);
-
- WARN(!mutex_is_locked(&vf->op_mutex), "about to access vf op linked list but mutex was not locked!");
- if (vfop) {
- INIT_LIST_HEAD(&vfop->link);
- list_add(&vfop->link, &vf->op_list_head);
- }
- return vfop;
-}
-
-static inline void bnx2x_vfop_end(struct bnx2x *bp, struct bnx2x_virtf *vf,
- struct bnx2x_vfop *vfop)
-{
- /* rc < 0 - error, otherwise set to 0 */
- DP(BNX2X_MSG_IOV, "rc was %d\n", vfop->rc);
- if (vfop->rc >= 0)
- vfop->rc = 0;
- DP(BNX2X_MSG_IOV, "rc is now %d\n", vfop->rc);
-
- /* unlink the current op context and propagate error code
- * must be done before invoking the 'done()' handler
- */
- WARN(!mutex_is_locked(&vf->op_mutex),
- "about to access vf op linked list but mutex was not locked!");
- list_del(&vfop->link);
-
- if (list_empty(&vf->op_list_head)) {
- DP(BNX2X_MSG_IOV, "list was empty %d\n", vfop->rc);
- vf->op_rc = vfop->rc;
- DP(BNX2X_MSG_IOV, "copying rc vf->op_rc %d, vfop->rc %d\n",
- vf->op_rc, vfop->rc);
- } else {
- struct bnx2x_vfop *cur_vfop;
-
- DP(BNX2X_MSG_IOV, "list not empty %d\n", vfop->rc);
- cur_vfop = bnx2x_vfop_cur(bp, vf);
- cur_vfop->rc = vfop->rc;
- DP(BNX2X_MSG_IOV, "copying rc vf->op_rc %d, vfop->rc %d\n",
- vf->op_rc, vfop->rc);
- }
-
- /* invoke done handler */
- if (vfop->done) {
- DP(BNX2X_MSG_IOV, "calling done handler\n");
- vfop->done(bp, vf);
- } else {
- /* there is no done handler for the operation to unlock
- * the mutex. Must have gotten here from PF initiated VF RELEASE
- */
- bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_RELEASE_VF);
- }
-
- DP(BNX2X_MSG_IOV, "done handler complete. vf->op_rc %d, vfop->rc %d\n",
- vf->op_rc, vfop->rc);
-
- /* if this is the last nested op reset the wait_blocking flag
- * to release any blocking wrappers, only after 'done()' is invoked
- */
- if (list_empty(&vf->op_list_head)) {
- DP(BNX2X_MSG_IOV, "list was empty after done %d\n", vfop->rc);
- vf->op_wait_blocking = false;
- }
-
- kfree(vfop);
-}
-
-static inline int bnx2x_vfop_wait_blocking(struct bnx2x *bp,
- struct bnx2x_virtf *vf)
-{
- /* can take a while if any port is running */
- int cnt = 5000;
-
- might_sleep();
- while (cnt--) {
- if (vf->op_wait_blocking == false) {
-#ifdef BNX2X_STOP_ON_ERROR
- DP(BNX2X_MSG_IOV, "exit (cnt %d)\n", 5000 - cnt);
-#endif
- return 0;
- }
- usleep_range(1000, 2000);
-
- if (bp->panic)
- return -EIO;
- }
-
- /* timeout! */
-#ifdef BNX2X_STOP_ON_ERROR
- bnx2x_panic();
-#endif
-
- return -EBUSY;
-}
-
-static inline int bnx2x_vfop_transition(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- vfop_handler_t transition,
- bool block)
-{
- if (block)
- vf->op_wait_blocking = true;
- transition(bp, vf);
- if (block)
- return bnx2x_vfop_wait_blocking(bp, vf);
- return 0;
-}
-
/* VFOP queue construction helpers */
void bnx2x_vfop_qctor_dump_tx(struct bnx2x *bp, struct bnx2x_virtf *vf,
struct bnx2x_queue_init_params *init_params,
@@ -657,59 +416,41 @@
void bnx2x_vfop_qctor_prep(struct bnx2x *bp,
struct bnx2x_virtf *vf,
struct bnx2x_vf_queue *q,
- struct bnx2x_vfop_qctor_params *p,
+ struct bnx2x_vf_queue_construct_params *p,
unsigned long q_type);
-int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- struct bnx2x_vfop_filters *macs,
- int qid, bool drv_only);
-int bnx2x_vfop_vlan_list_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- struct bnx2x_vfop_filters *vlans,
- int qid, bool drv_only);
+int bnx2x_vf_mac_vlan_config_list(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ struct bnx2x_vf_mac_vlan_filters *filters,
+ int qid, bool drv_only);
-int bnx2x_vfop_qsetup_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- int qid);
+int bnx2x_vf_queue_setup(struct bnx2x *bp, struct bnx2x_virtf *vf, int qid,
+ struct bnx2x_vf_queue_construct_params *qctor);
-int bnx2x_vfop_qdown_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- int qid);
+int bnx2x_vf_queue_teardown(struct bnx2x *bp, struct bnx2x_virtf *vf, int qid);
-int bnx2x_vfop_mcast_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- bnx2x_mac_addr_t *mcasts,
- int mcast_num, bool drv_only);
+int bnx2x_vf_mcast(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ bnx2x_mac_addr_t *mcasts, int mc_num, bool drv_only);
-int bnx2x_vfop_rxmode_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd,
- int qid, unsigned long accept_flags);
+int bnx2x_vf_rxmode(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ int qid, unsigned long accept_flags);
-int bnx2x_vfop_close_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd);
+int bnx2x_vf_close(struct bnx2x *bp, struct bnx2x_virtf *vf);
-int bnx2x_vfop_release_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd);
+int bnx2x_vf_free(struct bnx2x *bp, struct bnx2x_virtf *vf);
-int bnx2x_vfop_rss_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd);
+int bnx2x_vf_rss_update(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ struct bnx2x_config_rss_params *rss);
+
+int bnx2x_vf_tpa_update(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ struct vfpf_tpa_tlv *tlv,
+ struct bnx2x_queue_update_tpa_params *params);
/* VF release ~ VF close + VF release-resources
*
* Release is the ultimate SW shutdown and is called whenever an
* irrecoverable error is encountered.
*/
-void bnx2x_vf_release(struct bnx2x *bp, struct bnx2x_virtf *vf, bool block);
+int bnx2x_vf_release(struct bnx2x *bp, struct bnx2x_virtf *vf);
int bnx2x_vf_idx_by_abs_fid(struct bnx2x *bp, u16 abs_vfid);
u8 bnx2x_vf_max_queue_cnt(struct bnx2x *bp, struct bnx2x_virtf *vf);
@@ -772,18 +513,20 @@
int bnx2x_sriov_configure(struct pci_dev *dev, int num_vfs);
void bnx2x_iov_channel_down(struct bnx2x *bp);
+void bnx2x_iov_task(struct work_struct *work);
+
+void bnx2x_schedule_iov_task(struct bnx2x *bp, enum bnx2x_iov_flag flag);
+
#else /* CONFIG_BNX2X_SRIOV */
static inline void bnx2x_iov_set_queue_sp_obj(struct bnx2x *bp, int vf_cid,
struct bnx2x_queue_sp_obj **q_obj) {}
-static inline void bnx2x_iov_sp_event(struct bnx2x *bp, int vf_cid,
- bool queue_work) {}
static inline void bnx2x_vf_handle_flr_event(struct bnx2x *bp) {}
static inline int bnx2x_iov_eq_sp_event(struct bnx2x *bp,
union event_ring_elem *elem) {return 1; }
-static inline void bnx2x_iov_sp_task(struct bnx2x *bp) {}
-static inline void bnx2x_vf_mbx(struct bnx2x *bp,
- struct vf_pf_event_data *vfpf_event) {}
+static inline void bnx2x_vf_mbx(struct bnx2x *bp) {}
+static inline void bnx2x_vf_mbx_schedule(struct bnx2x *bp,
+ struct vf_pf_event_data *vfpf_event) {}
static inline int bnx2x_iov_init_ilt(struct bnx2x *bp, u16 line) {return line; }
static inline void bnx2x_iov_init_dq(struct bnx2x *bp) {}
static inline int bnx2x_iov_alloc_mem(struct bnx2x *bp) {return 0; }
@@ -830,5 +573,8 @@
static inline int bnx2x_sriov_configure(struct pci_dev *dev, int num_vfs) {return 0; }
static inline void bnx2x_iov_channel_down(struct bnx2x *bp) {}
+static inline void bnx2x_iov_task(struct work_struct *work) {}
+static inline void bnx2x_schedule_iov_task(struct bnx2x *bp, enum bnx2x_iov_flag flag) {}
+
#endif /* CONFIG_BNX2X_SRIOV */
#endif /* bnx2x_sriov.h */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 3fa6c2a..0622884 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -548,6 +548,7 @@
vf->leading_rss = cl_id;
q->is_leading = true;
+ q->sp_initialized = true;
}
/* ask the pf to open a queue for the vf */
@@ -672,6 +673,7 @@
out:
bnx2x_vfpf_finalize(bp, &req->first_tlv);
+
return rc;
}
@@ -894,29 +896,16 @@
DP(NETIF_MSG_IFUP, "Rx mode is %d\n", mode);
- switch (mode) {
- case BNX2X_RX_MODE_NONE: /* no Rx */
+ /* Ignore everything accept MODE_NONE */
+ if (mode == BNX2X_RX_MODE_NONE) {
req->rx_mask = VFPF_RX_MASK_ACCEPT_NONE;
- break;
- case BNX2X_RX_MODE_NORMAL:
+ } else {
+ /* Current PF driver will not look at the specific flags,
+ * but they are required when working with older drivers on hv.
+ */
req->rx_mask = VFPF_RX_MASK_ACCEPT_MATCHED_MULTICAST;
req->rx_mask |= VFPF_RX_MASK_ACCEPT_MATCHED_UNICAST;
req->rx_mask |= VFPF_RX_MASK_ACCEPT_BROADCAST;
- break;
- case BNX2X_RX_MODE_ALLMULTI:
- req->rx_mask = VFPF_RX_MASK_ACCEPT_ALL_MULTICAST;
- req->rx_mask |= VFPF_RX_MASK_ACCEPT_MATCHED_UNICAST;
- req->rx_mask |= VFPF_RX_MASK_ACCEPT_BROADCAST;
- break;
- case BNX2X_RX_MODE_PROMISC:
- req->rx_mask = VFPF_RX_MASK_ACCEPT_ALL_UNICAST;
- req->rx_mask |= VFPF_RX_MASK_ACCEPT_ALL_MULTICAST;
- req->rx_mask |= VFPF_RX_MASK_ACCEPT_BROADCAST;
- break;
- default:
- BNX2X_ERR("BAD rx mode (%d)\n", mode);
- rc = -EINVAL;
- goto out;
}
req->flags |= VFPF_SET_Q_FILTERS_RX_MASK_CHANGED;
@@ -937,7 +926,7 @@
BNX2X_ERR("Set Rx mode failed: %d\n", resp->hdr.status);
rc = -EINVAL;
}
-out:
+
bnx2x_vfpf_finalize(bp, &req->first_tlv);
return rc;
@@ -1047,7 +1036,8 @@
}
static void bnx2x_vf_mbx_resp_send_msg(struct bnx2x *bp,
- struct bnx2x_virtf *vf)
+ struct bnx2x_virtf *vf,
+ int vf_rc)
{
struct bnx2x_vf_mbx *mbx = BP_VF_MBX(bp, vf->index);
struct pfvf_general_resp_tlv *resp = &mbx->msg->resp.general_resp;
@@ -1059,7 +1049,7 @@
DP(BNX2X_MSG_IOV, "mailbox vf address hi 0x%x, lo 0x%x, offset 0x%x\n",
mbx->vf_addr_hi, mbx->vf_addr_lo, mbx->first_tlv.resp_msg_offset);
- resp->hdr.status = bnx2x_pfvf_status_codes(vf->op_rc);
+ resp->hdr.status = bnx2x_pfvf_status_codes(vf_rc);
/* send response */
vf_addr = HILO_U64(mbx->vf_addr_hi, mbx->vf_addr_lo) +
@@ -1088,9 +1078,6 @@
storm_memset_vf_mbx_ack(bp, vf->abs_vfid);
mmiowb();
- /* initiate dmae to send the response */
- mbx->flags &= ~VF_MSG_INPROCESS;
-
/* copy the response header including status-done field,
* must be last dmae, must be after FW is acked
*/
@@ -1110,14 +1097,15 @@
return;
mbx_error:
- bnx2x_vf_release(bp, vf, false); /* non blocking */
+ bnx2x_vf_release(bp, vf);
}
static void bnx2x_vf_mbx_resp(struct bnx2x *bp,
- struct bnx2x_virtf *vf)
+ struct bnx2x_virtf *vf,
+ int rc)
{
bnx2x_vf_mbx_resp_single_tlv(bp, vf);
- bnx2x_vf_mbx_resp_send_msg(bp, vf);
+ bnx2x_vf_mbx_resp_send_msg(bp, vf, rc);
}
static void bnx2x_vf_mbx_resp_phys_port(struct bnx2x *bp,
@@ -1159,7 +1147,8 @@
resp->pfdev_info.db_size = bp->db_size;
resp->pfdev_info.indices_per_sb = HC_SB_MAX_INDICES_E2;
resp->pfdev_info.pf_cap = (PFVF_CAP_RSS |
- /* PFVF_CAP_DHC |*/ PFVF_CAP_TPA);
+ PFVF_CAP_TPA |
+ PFVF_CAP_TPA_UPDATE);
bnx2x_fill_fw_str(bp, resp->pfdev_info.fw_ver,
sizeof(resp->pfdev_info.fw_ver));
@@ -1240,8 +1229,7 @@
sizeof(struct channel_list_end_tlv));
/* send the response */
- vf->op_rc = vfop_status;
- bnx2x_vf_mbx_resp_send_msg(bp, vf);
+ bnx2x_vf_mbx_resp_send_msg(bp, vf, vfop_status);
}
static void bnx2x_vf_mbx_acquire(struct bnx2x *bp, struct bnx2x_virtf *vf,
@@ -1273,19 +1261,20 @@
struct bnx2x_vf_mbx *mbx)
{
struct vfpf_init_tlv *init = &mbx->msg->req.init;
+ int rc;
/* record ghost addresses from vf message */
vf->spq_map = init->spq_addr;
vf->fw_stat_map = init->stats_addr;
vf->stats_stride = init->stats_stride;
- vf->op_rc = bnx2x_vf_init(bp, vf, (dma_addr_t *)init->sb_addr);
+ rc = bnx2x_vf_init(bp, vf, (dma_addr_t *)init->sb_addr);
/* set VF multiqueue statistics collection mode */
if (init->flags & VFPF_INIT_FLG_STATS_COALESCE)
vf->cfg_flags |= VF_CFG_STATS_COALESCE;
/* response */
- bnx2x_vf_mbx_resp(bp, vf);
+ bnx2x_vf_mbx_resp(bp, vf, rc);
}
/* convert MBX queue-flags to standard SP queue-flags */
@@ -1320,16 +1309,14 @@
struct bnx2x_vf_mbx *mbx)
{
struct vfpf_setup_q_tlv *setup_q = &mbx->msg->req.setup_q;
- struct bnx2x_vfop_cmd cmd = {
- .done = bnx2x_vf_mbx_resp,
- .block = false,
- };
+ struct bnx2x_vf_queue_construct_params qctor;
+ int rc = 0;
/* verify vf_qid */
if (setup_q->vf_qid >= vf_rxq_count(vf)) {
BNX2X_ERR("vf_qid %d invalid, max queue count is %d\n",
setup_q->vf_qid, vf_rxq_count(vf));
- vf->op_rc = -EINVAL;
+ rc = -EINVAL;
goto response;
}
@@ -1347,9 +1334,10 @@
bnx2x_leading_vfq_init(bp, vf, q);
/* re-init the VF operation context */
- memset(&vf->op_params.qctor, 0 , sizeof(vf->op_params.qctor));
- setup_p = &vf->op_params.qctor.prep_qsetup;
- init_p = &vf->op_params.qctor.qstate.params.init;
+ memset(&qctor, 0 ,
+ sizeof(struct bnx2x_vf_queue_construct_params));
+ setup_p = &qctor.prep_qsetup;
+ init_p = &qctor.qstate.params.init;
/* activate immediately */
__set_bit(BNX2X_Q_FLG_ACTIVE, &setup_p->flags);
@@ -1435,44 +1423,34 @@
q->index, q->sb_idx);
}
/* complete the preparations */
- bnx2x_vfop_qctor_prep(bp, vf, q, &vf->op_params.qctor, q_type);
+ bnx2x_vfop_qctor_prep(bp, vf, q, &qctor, q_type);
- vf->op_rc = bnx2x_vfop_qsetup_cmd(bp, vf, &cmd, q->index);
- if (vf->op_rc)
+ rc = bnx2x_vf_queue_setup(bp, vf, q->index, &qctor);
+ if (rc)
goto response;
- return;
}
response:
- bnx2x_vf_mbx_resp(bp, vf);
+ bnx2x_vf_mbx_resp(bp, vf, rc);
}
-enum bnx2x_vfop_filters_state {
- BNX2X_VFOP_MBX_Q_FILTERS_MACS,
- BNX2X_VFOP_MBX_Q_FILTERS_VLANS,
- BNX2X_VFOP_MBX_Q_FILTERS_RXMODE,
- BNX2X_VFOP_MBX_Q_FILTERS_MCAST,
- BNX2X_VFOP_MBX_Q_FILTERS_DONE
-};
-
static int bnx2x_vf_mbx_macvlan_list(struct bnx2x *bp,
struct bnx2x_virtf *vf,
struct vfpf_set_q_filters_tlv *tlv,
- struct bnx2x_vfop_filters **pfl,
+ struct bnx2x_vf_mac_vlan_filters **pfl,
u32 type_flag)
{
int i, j;
- struct bnx2x_vfop_filters *fl = NULL;
+ struct bnx2x_vf_mac_vlan_filters *fl = NULL;
size_t fsz;
- fsz = tlv->n_mac_vlan_filters * sizeof(struct bnx2x_vfop_filter) +
- sizeof(struct bnx2x_vfop_filters);
+ fsz = tlv->n_mac_vlan_filters *
+ sizeof(struct bnx2x_vf_mac_vlan_filter) +
+ sizeof(struct bnx2x_vf_mac_vlan_filters);
fl = kzalloc(fsz, GFP_KERNEL);
if (!fl)
return -ENOMEM;
- INIT_LIST_HEAD(&fl->head);
-
for (i = 0, j = 0; i < tlv->n_mac_vlan_filters; i++) {
struct vfpf_q_mac_vlan_filter *msg_filter = &tlv->filters[i];
@@ -1480,17 +1458,17 @@
continue;
if (type_flag == VFPF_Q_FILTER_DEST_MAC_VALID) {
fl->filters[j].mac = msg_filter->mac;
- fl->filters[j].type = BNX2X_VFOP_FILTER_MAC;
+ fl->filters[j].type = BNX2X_VF_FILTER_MAC;
} else {
fl->filters[j].vid = msg_filter->vlan_tag;
- fl->filters[j].type = BNX2X_VFOP_FILTER_VLAN;
+ fl->filters[j].type = BNX2X_VF_FILTER_VLAN;
}
fl->filters[j].add =
(msg_filter->flags & VFPF_Q_FILTER_SET_MAC) ?
true : false;
- list_add_tail(&fl->filters[j++].link, &fl->head);
+ fl->count++;
}
- if (list_empty(&fl->head))
+ if (!fl->count)
kfree(fl);
else
*pfl = fl;
@@ -1530,180 +1508,96 @@
#define VFPF_MAC_FILTER VFPF_Q_FILTER_DEST_MAC_VALID
#define VFPF_VLAN_FILTER VFPF_Q_FILTER_VLAN_TAG_VALID
-static void bnx2x_vfop_mbx_qfilters(struct bnx2x *bp, struct bnx2x_virtf *vf)
+static int bnx2x_vf_mbx_qfilters(struct bnx2x *bp, struct bnx2x_virtf *vf)
{
- int rc;
+ int rc = 0;
struct vfpf_set_q_filters_tlv *msg =
&BP_VF_MBX(bp, vf->index)->msg->req.set_q_filters;
- struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
- enum bnx2x_vfop_filters_state state = vfop->state;
+ /* check for any mac/vlan changes */
+ if (msg->flags & VFPF_SET_Q_FILTERS_MAC_VLAN_CHANGED) {
+ /* build mac list */
+ struct bnx2x_vf_mac_vlan_filters *fl = NULL;
- struct bnx2x_vfop_cmd cmd = {
- .done = bnx2x_vfop_mbx_qfilters,
- .block = false,
- };
+ rc = bnx2x_vf_mbx_macvlan_list(bp, vf, msg, &fl,
+ VFPF_MAC_FILTER);
+ if (rc)
+ goto op_err;
- DP(BNX2X_MSG_IOV, "STATE: %d\n", state);
+ if (fl) {
- if (vfop->rc < 0)
- goto op_err;
-
- switch (state) {
- case BNX2X_VFOP_MBX_Q_FILTERS_MACS:
- /* next state */
- vfop->state = BNX2X_VFOP_MBX_Q_FILTERS_VLANS;
-
- /* check for any vlan/mac changes */
- if (msg->flags & VFPF_SET_Q_FILTERS_MAC_VLAN_CHANGED) {
- /* build mac list */
- struct bnx2x_vfop_filters *fl = NULL;
-
- vfop->rc = bnx2x_vf_mbx_macvlan_list(bp, vf, msg, &fl,
- VFPF_MAC_FILTER);
- if (vfop->rc)
+ /* set mac list */
+ rc = bnx2x_vf_mac_vlan_config_list(bp, vf, fl,
+ msg->vf_qid,
+ false);
+ if (rc)
goto op_err;
-
- if (fl) {
- /* set mac list */
- rc = bnx2x_vfop_mac_list_cmd(bp, vf, &cmd, fl,
- msg->vf_qid,
- false);
- if (rc) {
- vfop->rc = rc;
- goto op_err;
- }
- return;
- }
}
- /* fall through */
- case BNX2X_VFOP_MBX_Q_FILTERS_VLANS:
- /* next state */
- vfop->state = BNX2X_VFOP_MBX_Q_FILTERS_RXMODE;
+ /* build vlan list */
+ fl = NULL;
- /* check for any vlan/mac changes */
- if (msg->flags & VFPF_SET_Q_FILTERS_MAC_VLAN_CHANGED) {
- /* build vlan list */
- struct bnx2x_vfop_filters *fl = NULL;
+ rc = bnx2x_vf_mbx_macvlan_list(bp, vf, msg, &fl,
+ VFPF_VLAN_FILTER);
+ if (rc)
+ goto op_err;
- vfop->rc = bnx2x_vf_mbx_macvlan_list(bp, vf, msg, &fl,
- VFPF_VLAN_FILTER);
- if (vfop->rc)
+ if (fl) {
+ /* set vlan list */
+ rc = bnx2x_vf_mac_vlan_config_list(bp, vf, fl,
+ msg->vf_qid,
+ false);
+ if (rc)
goto op_err;
-
- if (fl) {
- /* set vlan list */
- rc = bnx2x_vfop_vlan_list_cmd(bp, vf, &cmd, fl,
- msg->vf_qid,
- false);
- if (rc) {
- vfop->rc = rc;
- goto op_err;
- }
- return;
- }
}
- /* fall through */
+ }
- case BNX2X_VFOP_MBX_Q_FILTERS_RXMODE:
- /* next state */
- vfop->state = BNX2X_VFOP_MBX_Q_FILTERS_MCAST;
+ if (msg->flags & VFPF_SET_Q_FILTERS_RX_MASK_CHANGED) {
+ unsigned long accept = 0;
+ struct pf_vf_bulletin_content *bulletin =
+ BP_VF_BULLETIN(bp, vf->index);
- if (msg->flags & VFPF_SET_Q_FILTERS_RX_MASK_CHANGED) {
- unsigned long accept = 0;
- struct pf_vf_bulletin_content *bulletin =
- BP_VF_BULLETIN(bp, vf->index);
-
- /* covert VF-PF if mask to bnx2x accept flags */
- if (msg->rx_mask & VFPF_RX_MASK_ACCEPT_MATCHED_UNICAST)
- __set_bit(BNX2X_ACCEPT_UNICAST, &accept);
-
- if (msg->rx_mask &
- VFPF_RX_MASK_ACCEPT_MATCHED_MULTICAST)
- __set_bit(BNX2X_ACCEPT_MULTICAST, &accept);
-
- if (msg->rx_mask & VFPF_RX_MASK_ACCEPT_ALL_UNICAST)
- __set_bit(BNX2X_ACCEPT_ALL_UNICAST, &accept);
-
- if (msg->rx_mask & VFPF_RX_MASK_ACCEPT_ALL_MULTICAST)
- __set_bit(BNX2X_ACCEPT_ALL_MULTICAST, &accept);
-
- if (msg->rx_mask & VFPF_RX_MASK_ACCEPT_BROADCAST)
- __set_bit(BNX2X_ACCEPT_BROADCAST, &accept);
-
- /* A packet arriving the vf's mac should be accepted
- * with any vlan, unless a vlan has already been
- * configured.
- */
- if (!(bulletin->valid_bitmap & (1 << VLAN_VALID)))
- __set_bit(BNX2X_ACCEPT_ANY_VLAN, &accept);
-
- /* set rx-mode */
- rc = bnx2x_vfop_rxmode_cmd(bp, vf, &cmd,
- msg->vf_qid, accept);
- if (rc) {
- vfop->rc = rc;
- goto op_err;
- }
- return;
+ /* Ignore VF requested mode; instead set a regular mode */
+ if (msg->rx_mask != VFPF_RX_MASK_ACCEPT_NONE) {
+ __set_bit(BNX2X_ACCEPT_UNICAST, &accept);
+ __set_bit(BNX2X_ACCEPT_MULTICAST, &accept);
+ __set_bit(BNX2X_ACCEPT_BROADCAST, &accept);
}
- /* fall through */
- case BNX2X_VFOP_MBX_Q_FILTERS_MCAST:
- /* next state */
- vfop->state = BNX2X_VFOP_MBX_Q_FILTERS_DONE;
+ /* A packet arriving the vf's mac should be accepted
+ * with any vlan, unless a vlan has already been
+ * configured.
+ */
+ if (!(bulletin->valid_bitmap & (1 << VLAN_VALID)))
+ __set_bit(BNX2X_ACCEPT_ANY_VLAN, &accept);
- if (msg->flags & VFPF_SET_Q_FILTERS_MULTICAST_CHANGED) {
- /* set mcasts */
- rc = bnx2x_vfop_mcast_cmd(bp, vf, &cmd, msg->multicast,
- msg->n_multicast, false);
- if (rc) {
- vfop->rc = rc;
- goto op_err;
- }
- return;
- }
- /* fall through */
-op_done:
- case BNX2X_VFOP_MBX_Q_FILTERS_DONE:
- bnx2x_vfop_end(bp, vf, vfop);
- return;
+ /* set rx-mode */
+ rc = bnx2x_vf_rxmode(bp, vf, msg->vf_qid, accept);
+ if (rc)
+ goto op_err;
+ }
+
+ if (msg->flags & VFPF_SET_Q_FILTERS_MULTICAST_CHANGED) {
+ /* set mcasts */
+ rc = bnx2x_vf_mcast(bp, vf, msg->multicast,
+ msg->n_multicast, false);
+ if (rc)
+ goto op_err;
+ }
op_err:
- BNX2X_ERR("QFILTERS[%d:%d] error: rc %d\n",
- vf->abs_vfid, msg->vf_qid, vfop->rc);
- goto op_done;
-
- default:
- bnx2x_vfop_default(state);
- }
+ if (rc)
+ BNX2X_ERR("QFILTERS[%d:%d] error: rc %d\n",
+ vf->abs_vfid, msg->vf_qid, rc);
+ return rc;
}
-static int bnx2x_vfop_mbx_qfilters_cmd(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vfop_cmd *cmd)
+static int bnx2x_filters_validate_mac(struct bnx2x *bp,
+ struct bnx2x_virtf *vf,
+ struct vfpf_set_q_filters_tlv *filters)
{
- struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
- if (vfop) {
- bnx2x_vfop_opset(BNX2X_VFOP_MBX_Q_FILTERS_MACS,
- bnx2x_vfop_mbx_qfilters, cmd->done);
- return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_mbx_qfilters,
- cmd->block);
- }
- return -ENOMEM;
-}
-
-static void bnx2x_vf_mbx_set_q_filters(struct bnx2x *bp,
- struct bnx2x_virtf *vf,
- struct bnx2x_vf_mbx *mbx)
-{
- struct vfpf_set_q_filters_tlv *filters = &mbx->msg->req.set_q_filters;
struct pf_vf_bulletin_content *bulletin = BP_VF_BULLETIN(bp, vf->index);
- struct bnx2x_vfop_cmd cmd = {
- .done = bnx2x_vf_mbx_resp,
- .block = false,
- };
+ int rc = 0;
/* if a mac was already set for this VF via the set vf mac ndo, we only
* accept mac configurations of that mac. Why accept them at all?
@@ -1715,7 +1609,7 @@
if (filters->n_mac_vlan_filters > 1) {
BNX2X_ERR("VF[%d] requested the addition of multiple macs after set_vf_mac ndo was called\n",
vf->abs_vfid);
- vf->op_rc = -EPERM;
+ rc = -EPERM;
goto response;
}
@@ -1725,10 +1619,22 @@
BNX2X_ERR("VF[%d] requested the addition of a mac address not matching the one configured by set_vf_mac ndo\n",
vf->abs_vfid);
- vf->op_rc = -EPERM;
+ rc = -EPERM;
goto response;
}
}
+
+response:
+ return rc;
+}
+
+static int bnx2x_filters_validate_vlan(struct bnx2x *bp,
+ struct bnx2x_virtf *vf,
+ struct vfpf_set_q_filters_tlv *filters)
+{
+ struct pf_vf_bulletin_content *bulletin = BP_VF_BULLETIN(bp, vf->index);
+ int rc = 0;
+
/* if vlan was set by hypervisor we don't allow guest to config vlan */
if (bulletin->valid_bitmap & 1 << VLAN_VALID) {
int i;
@@ -1739,14 +1645,35 @@
VFPF_Q_FILTER_VLAN_TAG_VALID) {
BNX2X_ERR("VF[%d] attempted to configure vlan but one was already set by Hypervisor. Aborting request\n",
vf->abs_vfid);
- vf->op_rc = -EPERM;
+ rc = -EPERM;
goto response;
}
}
}
/* verify vf_qid */
- if (filters->vf_qid > vf_rxq_count(vf))
+ if (filters->vf_qid > vf_rxq_count(vf)) {
+ rc = -EPERM;
+ goto response;
+ }
+
+response:
+ return rc;
+}
+
+static void bnx2x_vf_mbx_set_q_filters(struct bnx2x *bp,
+ struct bnx2x_virtf *vf,
+ struct bnx2x_vf_mbx *mbx)
+{
+ struct vfpf_set_q_filters_tlv *filters = &mbx->msg->req.set_q_filters;
+ int rc;
+
+ rc = bnx2x_filters_validate_mac(bp, vf, filters);
+ if (rc)
+ goto response;
+
+ rc = bnx2x_filters_validate_vlan(bp, vf, filters);
+ if (rc)
goto response;
DP(BNX2X_MSG_IOV, "VF[%d] Q_FILTERS: queue[%d]\n",
@@ -1756,125 +1683,169 @@
/* print q_filter message */
bnx2x_vf_mbx_dp_q_filters(bp, BNX2X_MSG_IOV, filters);
- vf->op_rc = bnx2x_vfop_mbx_qfilters_cmd(bp, vf, &cmd);
- if (vf->op_rc)
- goto response;
- return;
-
+ rc = bnx2x_vf_mbx_qfilters(bp, vf);
response:
- bnx2x_vf_mbx_resp(bp, vf);
+ bnx2x_vf_mbx_resp(bp, vf, rc);
}
static void bnx2x_vf_mbx_teardown_q(struct bnx2x *bp, struct bnx2x_virtf *vf,
struct bnx2x_vf_mbx *mbx)
{
int qid = mbx->msg->req.q_op.vf_qid;
- struct bnx2x_vfop_cmd cmd = {
- .done = bnx2x_vf_mbx_resp,
- .block = false,
- };
+ int rc;
DP(BNX2X_MSG_IOV, "VF[%d] Q_TEARDOWN: vf_qid=%d\n",
vf->abs_vfid, qid);
- vf->op_rc = bnx2x_vfop_qdown_cmd(bp, vf, &cmd, qid);
- if (vf->op_rc)
- bnx2x_vf_mbx_resp(bp, vf);
+ rc = bnx2x_vf_queue_teardown(bp, vf, qid);
+ bnx2x_vf_mbx_resp(bp, vf, rc);
}
static void bnx2x_vf_mbx_close_vf(struct bnx2x *bp, struct bnx2x_virtf *vf,
struct bnx2x_vf_mbx *mbx)
{
- struct bnx2x_vfop_cmd cmd = {
- .done = bnx2x_vf_mbx_resp,
- .block = false,
- };
+ int rc;
DP(BNX2X_MSG_IOV, "VF[%d] VF_CLOSE\n", vf->abs_vfid);
- vf->op_rc = bnx2x_vfop_close_cmd(bp, vf, &cmd);
- if (vf->op_rc)
- bnx2x_vf_mbx_resp(bp, vf);
+ rc = bnx2x_vf_close(bp, vf);
+ bnx2x_vf_mbx_resp(bp, vf, rc);
}
static void bnx2x_vf_mbx_release_vf(struct bnx2x *bp, struct bnx2x_virtf *vf,
struct bnx2x_vf_mbx *mbx)
{
- struct bnx2x_vfop_cmd cmd = {
- .done = bnx2x_vf_mbx_resp,
- .block = false,
- };
+ int rc;
DP(BNX2X_MSG_IOV, "VF[%d] VF_RELEASE\n", vf->abs_vfid);
- vf->op_rc = bnx2x_vfop_release_cmd(bp, vf, &cmd);
- if (vf->op_rc)
- bnx2x_vf_mbx_resp(bp, vf);
+ rc = bnx2x_vf_free(bp, vf);
+ bnx2x_vf_mbx_resp(bp, vf, rc);
}
static void bnx2x_vf_mbx_update_rss(struct bnx2x *bp, struct bnx2x_virtf *vf,
struct bnx2x_vf_mbx *mbx)
{
- struct bnx2x_vfop_cmd cmd = {
- .done = bnx2x_vf_mbx_resp,
- .block = false,
- };
- struct bnx2x_config_rss_params *vf_op_params = &vf->op_params.rss;
+ struct bnx2x_config_rss_params rss;
struct vfpf_rss_tlv *rss_tlv = &mbx->msg->req.update_rss;
+ int rc = 0;
if (rss_tlv->ind_table_size != T_ETH_INDIRECTION_TABLE_SIZE ||
rss_tlv->rss_key_size != T_ETH_RSS_KEY) {
BNX2X_ERR("failing rss configuration of vf %d due to size mismatch\n",
vf->index);
- vf->op_rc = -EINVAL;
+ rc = -EINVAL;
goto mbx_resp;
}
+ memset(&rss, 0, sizeof(struct bnx2x_config_rss_params));
+
/* set vfop params according to rss tlv */
- memcpy(vf_op_params->ind_table, rss_tlv->ind_table,
+ memcpy(rss.ind_table, rss_tlv->ind_table,
T_ETH_INDIRECTION_TABLE_SIZE);
- memcpy(vf_op_params->rss_key, rss_tlv->rss_key,
- sizeof(rss_tlv->rss_key));
- vf_op_params->rss_obj = &vf->rss_conf_obj;
- vf_op_params->rss_result_mask = rss_tlv->rss_result_mask;
+ memcpy(rss.rss_key, rss_tlv->rss_key, sizeof(rss_tlv->rss_key));
+ rss.rss_obj = &vf->rss_conf_obj;
+ rss.rss_result_mask = rss_tlv->rss_result_mask;
/* flags handled individually for backward/forward compatability */
- vf_op_params->rss_flags = 0;
- vf_op_params->ramrod_flags = 0;
+ rss.rss_flags = 0;
+ rss.ramrod_flags = 0;
if (rss_tlv->rss_flags & VFPF_RSS_MODE_DISABLED)
- __set_bit(BNX2X_RSS_MODE_DISABLED, &vf_op_params->rss_flags);
+ __set_bit(BNX2X_RSS_MODE_DISABLED, &rss.rss_flags);
if (rss_tlv->rss_flags & VFPF_RSS_MODE_REGULAR)
- __set_bit(BNX2X_RSS_MODE_REGULAR, &vf_op_params->rss_flags);
+ __set_bit(BNX2X_RSS_MODE_REGULAR, &rss.rss_flags);
if (rss_tlv->rss_flags & VFPF_RSS_SET_SRCH)
- __set_bit(BNX2X_RSS_SET_SRCH, &vf_op_params->rss_flags);
+ __set_bit(BNX2X_RSS_SET_SRCH, &rss.rss_flags);
if (rss_tlv->rss_flags & VFPF_RSS_IPV4)
- __set_bit(BNX2X_RSS_IPV4, &vf_op_params->rss_flags);
+ __set_bit(BNX2X_RSS_IPV4, &rss.rss_flags);
if (rss_tlv->rss_flags & VFPF_RSS_IPV4_TCP)
- __set_bit(BNX2X_RSS_IPV4_TCP, &vf_op_params->rss_flags);
+ __set_bit(BNX2X_RSS_IPV4_TCP, &rss.rss_flags);
if (rss_tlv->rss_flags & VFPF_RSS_IPV4_UDP)
- __set_bit(BNX2X_RSS_IPV4_UDP, &vf_op_params->rss_flags);
+ __set_bit(BNX2X_RSS_IPV4_UDP, &rss.rss_flags);
if (rss_tlv->rss_flags & VFPF_RSS_IPV6)
- __set_bit(BNX2X_RSS_IPV6, &vf_op_params->rss_flags);
+ __set_bit(BNX2X_RSS_IPV6, &rss.rss_flags);
if (rss_tlv->rss_flags & VFPF_RSS_IPV6_TCP)
- __set_bit(BNX2X_RSS_IPV6_TCP, &vf_op_params->rss_flags);
+ __set_bit(BNX2X_RSS_IPV6_TCP, &rss.rss_flags);
if (rss_tlv->rss_flags & VFPF_RSS_IPV6_UDP)
- __set_bit(BNX2X_RSS_IPV6_UDP, &vf_op_params->rss_flags);
+ __set_bit(BNX2X_RSS_IPV6_UDP, &rss.rss_flags);
if ((!(rss_tlv->rss_flags & VFPF_RSS_IPV4_TCP) &&
rss_tlv->rss_flags & VFPF_RSS_IPV4_UDP) ||
(!(rss_tlv->rss_flags & VFPF_RSS_IPV6_TCP) &&
rss_tlv->rss_flags & VFPF_RSS_IPV6_UDP)) {
BNX2X_ERR("about to hit a FW assert. aborting...\n");
- vf->op_rc = -EINVAL;
+ rc = -EINVAL;
goto mbx_resp;
}
- vf->op_rc = bnx2x_vfop_rss_cmd(bp, vf, &cmd);
+ rc = bnx2x_vf_rss_update(bp, vf, &rss);
+mbx_resp:
+ bnx2x_vf_mbx_resp(bp, vf, rc);
+}
+
+static int bnx2x_validate_tpa_params(struct bnx2x *bp,
+ struct vfpf_tpa_tlv *tpa_tlv)
+{
+ int rc = 0;
+
+ if (tpa_tlv->tpa_client_info.max_sges_for_packet >
+ U_ETH_MAX_SGES_FOR_PACKET) {
+ rc = -EINVAL;
+ BNX2X_ERR("TPA update: max_sges received %d, max is %d\n",
+ tpa_tlv->tpa_client_info.max_sges_for_packet,
+ U_ETH_MAX_SGES_FOR_PACKET);
+ }
+
+ if (tpa_tlv->tpa_client_info.max_tpa_queues > MAX_AGG_QS(bp)) {
+ rc = -EINVAL;
+ BNX2X_ERR("TPA update: max_tpa_queues received %d, max is %d\n",
+ tpa_tlv->tpa_client_info.max_tpa_queues,
+ MAX_AGG_QS(bp));
+ }
+
+ return rc;
+}
+
+static void bnx2x_vf_mbx_update_tpa(struct bnx2x *bp, struct bnx2x_virtf *vf,
+ struct bnx2x_vf_mbx *mbx)
+{
+ struct bnx2x_queue_update_tpa_params vf_op_params;
+ struct vfpf_tpa_tlv *tpa_tlv = &mbx->msg->req.update_tpa;
+ int rc = 0;
+
+ memset(&vf_op_params, 0, sizeof(vf_op_params));
+
+ if (bnx2x_validate_tpa_params(bp, tpa_tlv))
+ goto mbx_resp;
+
+ vf_op_params.complete_on_both_clients =
+ tpa_tlv->tpa_client_info.complete_on_both_clients;
+ vf_op_params.dont_verify_thr =
+ tpa_tlv->tpa_client_info.dont_verify_thr;
+ vf_op_params.max_agg_sz =
+ tpa_tlv->tpa_client_info.max_agg_size;
+ vf_op_params.max_sges_pkt =
+ tpa_tlv->tpa_client_info.max_sges_for_packet;
+ vf_op_params.max_tpa_queues =
+ tpa_tlv->tpa_client_info.max_tpa_queues;
+ vf_op_params.sge_buff_sz =
+ tpa_tlv->tpa_client_info.sge_buff_size;
+ vf_op_params.sge_pause_thr_high =
+ tpa_tlv->tpa_client_info.sge_pause_thr_high;
+ vf_op_params.sge_pause_thr_low =
+ tpa_tlv->tpa_client_info.sge_pause_thr_low;
+ vf_op_params.tpa_mode =
+ tpa_tlv->tpa_client_info.tpa_mode;
+ vf_op_params.update_ipv4 =
+ tpa_tlv->tpa_client_info.update_ipv4;
+ vf_op_params.update_ipv6 =
+ tpa_tlv->tpa_client_info.update_ipv6;
+
+ rc = bnx2x_vf_tpa_update(bp, vf, tpa_tlv, &vf_op_params);
mbx_resp:
- if (vf->op_rc)
- bnx2x_vf_mbx_resp(bp, vf);
+ bnx2x_vf_mbx_resp(bp, vf, rc);
}
/* dispatch request */
@@ -1916,6 +1887,9 @@
case CHANNEL_TLV_UPDATE_RSS:
bnx2x_vf_mbx_update_rss(bp, vf, mbx);
return;
+ case CHANNEL_TLV_UPDATE_TPA:
+ bnx2x_vf_mbx_update_tpa(bp, vf, mbx);
+ return;
}
} else {
@@ -1935,11 +1909,8 @@
/* can we respond to VF (do we have an address for it?) */
if (vf->state == VF_ACQUIRED || vf->state == VF_ENABLED) {
- /* mbx_resp uses the op_rc of the VF */
- vf->op_rc = PFVF_STATUS_NOT_SUPPORTED;
-
/* notify the VF that we do not support this request */
- bnx2x_vf_mbx_resp(bp, vf);
+ bnx2x_vf_mbx_resp(bp, vf, PFVF_STATUS_NOT_SUPPORTED);
} else {
/* can't send a response since this VF is unknown to us
* just ack the FW to release the mailbox and unlock
@@ -1952,13 +1923,10 @@
}
}
-/* handle new vf-pf message */
-void bnx2x_vf_mbx(struct bnx2x *bp, struct vf_pf_event_data *vfpf_event)
+void bnx2x_vf_mbx_schedule(struct bnx2x *bp,
+ struct vf_pf_event_data *vfpf_event)
{
- struct bnx2x_virtf *vf;
- struct bnx2x_vf_mbx *mbx;
u8 vf_idx;
- int rc;
DP(BNX2X_MSG_IOV,
"vf pf event received: vfid %d, address_hi %x, address lo %x",
@@ -1970,50 +1938,73 @@
BNX2X_NR_VIRTFN(bp)) {
BNX2X_ERR("Illegal vf_id %d max allowed: %d\n",
vfpf_event->vf_id, BNX2X_NR_VIRTFN(bp));
- goto mbx_done;
+ return;
}
+
vf_idx = bnx2x_vf_idx_by_abs_fid(bp, vfpf_event->vf_id);
- mbx = BP_VF_MBX(bp, vf_idx);
- /* verify an event is not currently being processed -
- * debug failsafe only
- */
- if (mbx->flags & VF_MSG_INPROCESS) {
- BNX2X_ERR("Previous message is still being processed, vf_id %d\n",
- vfpf_event->vf_id);
- goto mbx_done;
+ /* Update VFDB with current message and schedule its handling */
+ mutex_lock(&BP_VFDB(bp)->event_mutex);
+ BP_VF_MBX(bp, vf_idx)->vf_addr_hi = vfpf_event->msg_addr_hi;
+ BP_VF_MBX(bp, vf_idx)->vf_addr_lo = vfpf_event->msg_addr_lo;
+ BP_VFDB(bp)->event_occur |= (1ULL << vf_idx);
+ mutex_unlock(&BP_VFDB(bp)->event_mutex);
+
+ bnx2x_schedule_iov_task(bp, BNX2X_IOV_HANDLE_VF_MSG);
+}
+
+/* handle new vf-pf messages */
+void bnx2x_vf_mbx(struct bnx2x *bp)
+{
+ struct bnx2x_vfdb *vfdb = BP_VFDB(bp);
+ u64 events;
+ u8 vf_idx;
+ int rc;
+
+ if (!vfdb)
+ return;
+
+ mutex_lock(&vfdb->event_mutex);
+ events = vfdb->event_occur;
+ vfdb->event_occur = 0;
+ mutex_unlock(&vfdb->event_mutex);
+
+ for_each_vf(bp, vf_idx) {
+ struct bnx2x_vf_mbx *mbx = BP_VF_MBX(bp, vf_idx);
+ struct bnx2x_virtf *vf = BP_VF(bp, vf_idx);
+
+ /* Handle VFs which have pending events */
+ if (!(events & (1ULL << vf_idx)))
+ continue;
+
+ DP(BNX2X_MSG_IOV,
+ "Handling vf pf event vfid %d, address: [%x:%x], resp_offset 0x%x\n",
+ vf_idx, mbx->vf_addr_hi, mbx->vf_addr_lo,
+ mbx->first_tlv.resp_msg_offset);
+
+ /* dmae to get the VF request */
+ rc = bnx2x_copy32_vf_dmae(bp, true, mbx->msg_mapping,
+ vf->abs_vfid, mbx->vf_addr_hi,
+ mbx->vf_addr_lo,
+ sizeof(union vfpf_tlvs)/4);
+ if (rc) {
+ BNX2X_ERR("Failed to copy request VF %d\n",
+ vf->abs_vfid);
+ bnx2x_vf_release(bp, vf);
+ return;
+ }
+
+ /* process the VF message header */
+ mbx->first_tlv = mbx->msg->req.first_tlv;
+
+ /* Clean response buffer to refrain from falsely
+ * seeing chains.
+ */
+ memset(&mbx->msg->resp, 0, sizeof(union pfvf_tlvs));
+
+ /* dispatch the request (will prepare the response) */
+ bnx2x_vf_mbx_request(bp, vf, mbx);
}
- vf = BP_VF(bp, vf_idx);
-
- /* save the VF message address */
- mbx->vf_addr_hi = vfpf_event->msg_addr_hi;
- mbx->vf_addr_lo = vfpf_event->msg_addr_lo;
- DP(BNX2X_MSG_IOV, "mailbox vf address hi 0x%x, lo 0x%x, offset 0x%x\n",
- mbx->vf_addr_hi, mbx->vf_addr_lo, mbx->first_tlv.resp_msg_offset);
-
- /* dmae to get the VF request */
- rc = bnx2x_copy32_vf_dmae(bp, true, mbx->msg_mapping, vf->abs_vfid,
- mbx->vf_addr_hi, mbx->vf_addr_lo,
- sizeof(union vfpf_tlvs)/4);
- if (rc) {
- BNX2X_ERR("Failed to copy request VF %d\n", vf->abs_vfid);
- goto mbx_error;
- }
-
- /* process the VF message header */
- mbx->first_tlv = mbx->msg->req.first_tlv;
-
- /* Clean response buffer to refrain from falsely seeing chains */
- memset(&mbx->msg->resp, 0, sizeof(union pfvf_tlvs));
-
- /* dispatch the request (will prepare the response) */
- bnx2x_vf_mbx_request(bp, vf, mbx);
- goto mbx_done;
-
-mbx_error:
- bnx2x_vf_release(bp, vf, false); /* non blocking */
-mbx_done:
- return;
}
/* propagate local bulletin board to vf */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
index 208568b..c922b81 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
@@ -162,6 +162,7 @@
#define PFVF_CAP_RSS 0x00000001
#define PFVF_CAP_DHC 0x00000002
#define PFVF_CAP_TPA 0x00000004
+#define PFVF_CAP_TPA_UPDATE 0x00000008
char fw_ver[32];
u16 db_size;
u8 indices_per_sb;
@@ -303,6 +304,25 @@
u32 rx_mask; /* see mask constants at the top of the file */
};
+struct vfpf_tpa_tlv {
+ struct vfpf_first_tlv first_tlv;
+
+ struct vf_pf_tpa_client_info {
+ aligned_u64 sge_addr[PFVF_MAX_QUEUES_PER_VF];
+ u8 update_ipv4;
+ u8 update_ipv6;
+ u8 max_tpa_queues;
+ u8 max_sges_for_packet;
+ u8 complete_on_both_clients;
+ u8 dont_verify_thr;
+ u8 tpa_mode;
+ u16 sge_buff_size;
+ u16 max_agg_size;
+ u16 sge_pause_thr_low;
+ u16 sge_pause_thr_high;
+ } tpa_client_info;
+};
+
/* close VF (disable VF) */
struct vfpf_close_tlv {
struct vfpf_first_tlv first_tlv;
@@ -331,6 +351,7 @@
struct vfpf_set_q_filters_tlv set_q_filters;
struct vfpf_release_tlv release;
struct vfpf_rss_tlv update_rss;
+ struct vfpf_tpa_tlv update_tpa;
struct channel_list_end_tlv list_end;
struct tlv_buffer_size tlv_buf_size;
};
@@ -405,6 +426,7 @@
CHANNEL_TLV_PF_SET_VLAN,
CHANNEL_TLV_UPDATE_RSS,
CHANNEL_TLV_PHYS_PORT_ID,
+ CHANNEL_TLV_UPDATE_TPA,
CHANNEL_TLV_MAX
};
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index fcf9105a5..09f3fef 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -1,6 +1,6 @@
/* cnic.c: Broadcom CNIC core network driver.
*
- * Copyright (c) 2006-2013 Broadcom Corporation
+ * Copyright (c) 2006-2014 Broadcom Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -342,7 +342,7 @@
while (retry < 3) {
rc = 0;
rcu_read_lock();
- ulp_ops = rcu_dereference(cnic_ulp_tbl[CNIC_ULP_ISCSI]);
+ ulp_ops = rcu_dereference(cp->ulp_ops[CNIC_ULP_ISCSI]);
if (ulp_ops)
rc = ulp_ops->iscsi_nl_send_msg(
cp->ulp_handle[CNIC_ULP_ISCSI],
@@ -726,7 +726,7 @@
for (i = 0; i < dma->num_pages; i++) {
if (dma->pg_arr[i]) {
- dma_free_coherent(&dev->pcidev->dev, BNX2_PAGE_SIZE,
+ dma_free_coherent(&dev->pcidev->dev, CNIC_PAGE_SIZE,
dma->pg_arr[i], dma->pg_map_arr[i]);
dma->pg_arr[i] = NULL;
}
@@ -785,7 +785,7 @@
for (i = 0; i < pages; i++) {
dma->pg_arr[i] = dma_alloc_coherent(&dev->pcidev->dev,
- BNX2_PAGE_SIZE,
+ CNIC_PAGE_SIZE,
&dma->pg_map_arr[i],
GFP_ATOMIC);
if (dma->pg_arr[i] == NULL)
@@ -794,8 +794,8 @@
if (!use_pg_tbl)
return 0;
- dma->pgtbl_size = ((pages * 8) + BNX2_PAGE_SIZE - 1) &
- ~(BNX2_PAGE_SIZE - 1);
+ dma->pgtbl_size = ((pages * 8) + CNIC_PAGE_SIZE - 1) &
+ ~(CNIC_PAGE_SIZE - 1);
dma->pgtbl = dma_alloc_coherent(&dev->pcidev->dev, dma->pgtbl_size,
&dma->pgtbl_map, GFP_ATOMIC);
if (dma->pgtbl == NULL)
@@ -900,8 +900,8 @@
if (BNX2_CHIP(cp) == BNX2_CHIP_5709) {
int i, k, arr_size;
- cp->ctx_blk_size = BNX2_PAGE_SIZE;
- cp->cids_per_blk = BNX2_PAGE_SIZE / 128;
+ cp->ctx_blk_size = CNIC_PAGE_SIZE;
+ cp->cids_per_blk = CNIC_PAGE_SIZE / 128;
arr_size = BNX2_MAX_CID / cp->cids_per_blk *
sizeof(struct cnic_ctx);
cp->ctx_arr = kzalloc(arr_size, GFP_KERNEL);
@@ -933,7 +933,7 @@
for (i = 0; i < cp->ctx_blks; i++) {
cp->ctx_arr[i].ctx =
dma_alloc_coherent(&dev->pcidev->dev,
- BNX2_PAGE_SIZE,
+ CNIC_PAGE_SIZE,
&cp->ctx_arr[i].mapping,
GFP_KERNEL);
if (cp->ctx_arr[i].ctx == NULL)
@@ -1013,7 +1013,7 @@
if (udev->l2_ring)
return 0;
- udev->l2_ring_size = pages * BNX2_PAGE_SIZE;
+ udev->l2_ring_size = pages * CNIC_PAGE_SIZE;
udev->l2_ring = dma_alloc_coherent(&udev->pdev->dev, udev->l2_ring_size,
&udev->l2_ring_map,
GFP_KERNEL | __GFP_COMP);
@@ -1021,7 +1021,7 @@
return -ENOMEM;
udev->l2_buf_size = (cp->l2_rx_ring_size + 1) * cp->l2_single_buf_size;
- udev->l2_buf_size = PAGE_ALIGN(udev->l2_buf_size);
+ udev->l2_buf_size = CNIC_PAGE_ALIGN(udev->l2_buf_size);
udev->l2_buf = dma_alloc_coherent(&udev->pdev->dev, udev->l2_buf_size,
&udev->l2_buf_map,
GFP_KERNEL | __GFP_COMP);
@@ -1102,7 +1102,7 @@
uinfo->mem[0].size = MB_GET_CID_ADDR(TX_TSS_CID +
TX_MAX_TSS_RINGS + 1);
uinfo->mem[1].addr = (unsigned long) cp->status_blk.gen &
- PAGE_MASK;
+ CNIC_PAGE_MASK;
if (cp->ethdev->drv_state & CNIC_DRV_STATE_USING_MSIX)
uinfo->mem[1].size = BNX2_SBLK_MSIX_ALIGN_SIZE * 9;
else
@@ -1113,7 +1113,7 @@
uinfo->mem[0].size = pci_resource_len(dev->pcidev, 0);
uinfo->mem[1].addr = (unsigned long) cp->bnx2x_def_status_blk &
- PAGE_MASK;
+ CNIC_PAGE_MASK;
uinfo->mem[1].size = sizeof(*cp->bnx2x_def_status_blk);
uinfo->name = "bnx2x_cnic";
@@ -1267,14 +1267,14 @@
for (i = MAX_ISCSI_TBL_SZ; i < cp->max_cid_space; i++)
cp->ctx_tbl[i].ulp_proto_id = CNIC_ULP_FCOE;
- pages = PAGE_ALIGN(cp->max_cid_space * CNIC_KWQ16_DATA_SIZE) /
- PAGE_SIZE;
+ pages = CNIC_PAGE_ALIGN(cp->max_cid_space * CNIC_KWQ16_DATA_SIZE) /
+ CNIC_PAGE_SIZE;
ret = cnic_alloc_dma(dev, kwq_16_dma, pages, 0);
if (ret)
return -ENOMEM;
- n = PAGE_SIZE / CNIC_KWQ16_DATA_SIZE;
+ n = CNIC_PAGE_SIZE / CNIC_KWQ16_DATA_SIZE;
for (i = 0, j = 0; i < cp->max_cid_space; i++) {
long off = CNIC_KWQ16_DATA_SIZE * (i % n);
@@ -1296,7 +1296,7 @@
goto error;
}
- pages = PAGE_ALIGN(BNX2X_ISCSI_GLB_BUF_SIZE) / PAGE_SIZE;
+ pages = CNIC_PAGE_ALIGN(BNX2X_ISCSI_GLB_BUF_SIZE) / CNIC_PAGE_SIZE;
ret = cnic_alloc_dma(dev, &cp->gbl_buf_info, pages, 0);
if (ret)
goto error;
@@ -1466,8 +1466,8 @@
cp->r2tq_size = cp->num_iscsi_tasks * BNX2X_ISCSI_MAX_PENDING_R2TS *
BNX2X_ISCSI_R2TQE_SIZE;
cp->hq_size = cp->num_ccells * BNX2X_ISCSI_HQ_BD_SIZE;
- pages = PAGE_ALIGN(cp->hq_size) / PAGE_SIZE;
- hq_bds = pages * (PAGE_SIZE / BNX2X_ISCSI_HQ_BD_SIZE);
+ pages = CNIC_PAGE_ALIGN(cp->hq_size) / CNIC_PAGE_SIZE;
+ hq_bds = pages * (CNIC_PAGE_SIZE / BNX2X_ISCSI_HQ_BD_SIZE);
cp->num_cqs = req1->num_cqs;
if (!dev->max_iscsi_conn)
@@ -1477,9 +1477,9 @@
CNIC_WR16(dev, BAR_TSTRORM_INTMEM + TSTORM_ISCSI_RQ_SIZE_OFFSET(pfid),
req1->rq_num_wqes);
CNIC_WR16(dev, BAR_TSTRORM_INTMEM + TSTORM_ISCSI_PAGE_SIZE_OFFSET(pfid),
- PAGE_SIZE);
+ CNIC_PAGE_SIZE);
CNIC_WR8(dev, BAR_TSTRORM_INTMEM +
- TSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), PAGE_SHIFT);
+ TSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), CNIC_PAGE_BITS);
CNIC_WR16(dev, BAR_TSTRORM_INTMEM +
TSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfid),
req1->num_tasks_per_conn);
@@ -1489,9 +1489,9 @@
USTORM_ISCSI_RQ_BUFFER_SIZE_OFFSET(pfid),
req1->rq_buffer_size);
CNIC_WR16(dev, BAR_USTRORM_INTMEM + USTORM_ISCSI_PAGE_SIZE_OFFSET(pfid),
- PAGE_SIZE);
+ CNIC_PAGE_SIZE);
CNIC_WR8(dev, BAR_USTRORM_INTMEM +
- USTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), PAGE_SHIFT);
+ USTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), CNIC_PAGE_BITS);
CNIC_WR16(dev, BAR_USTRORM_INTMEM +
USTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfid),
req1->num_tasks_per_conn);
@@ -1504,9 +1504,9 @@
/* init Xstorm RAM */
CNIC_WR16(dev, BAR_XSTRORM_INTMEM + XSTORM_ISCSI_PAGE_SIZE_OFFSET(pfid),
- PAGE_SIZE);
+ CNIC_PAGE_SIZE);
CNIC_WR8(dev, BAR_XSTRORM_INTMEM +
- XSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), PAGE_SHIFT);
+ XSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), CNIC_PAGE_BITS);
CNIC_WR16(dev, BAR_XSTRORM_INTMEM +
XSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfid),
req1->num_tasks_per_conn);
@@ -1519,9 +1519,9 @@
/* init Cstorm RAM */
CNIC_WR16(dev, BAR_CSTRORM_INTMEM + CSTORM_ISCSI_PAGE_SIZE_OFFSET(pfid),
- PAGE_SIZE);
+ CNIC_PAGE_SIZE);
CNIC_WR8(dev, BAR_CSTRORM_INTMEM +
- CSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), PAGE_SHIFT);
+ CSTORM_ISCSI_PAGE_SIZE_LOG_OFFSET(pfid), CNIC_PAGE_BITS);
CNIC_WR16(dev, BAR_CSTRORM_INTMEM +
CSTORM_ISCSI_NUM_OF_TASKS_OFFSET(pfid),
req1->num_tasks_per_conn);
@@ -1623,18 +1623,18 @@
}
ctx->cid = cid;
- pages = PAGE_ALIGN(cp->task_array_size) / PAGE_SIZE;
+ pages = CNIC_PAGE_ALIGN(cp->task_array_size) / CNIC_PAGE_SIZE;
ret = cnic_alloc_dma(dev, &iscsi->task_array_info, pages, 1);
if (ret)
goto error;
- pages = PAGE_ALIGN(cp->r2tq_size) / PAGE_SIZE;
+ pages = CNIC_PAGE_ALIGN(cp->r2tq_size) / CNIC_PAGE_SIZE;
ret = cnic_alloc_dma(dev, &iscsi->r2tq_info, pages, 1);
if (ret)
goto error;
- pages = PAGE_ALIGN(cp->hq_size) / PAGE_SIZE;
+ pages = CNIC_PAGE_ALIGN(cp->hq_size) / CNIC_PAGE_SIZE;
ret = cnic_alloc_dma(dev, &iscsi->hq_info, pages, 1);
if (ret)
goto error;
@@ -1760,7 +1760,7 @@
ictx->tstorm_st_context.iscsi.hdr_bytes_2_fetch = ISCSI_HEADER_SIZE;
/* TSTORM requires the base address of RQ DB & not PTE */
ictx->tstorm_st_context.iscsi.rq_db_phy_addr.lo =
- req2->rq_page_table_addr_lo & PAGE_MASK;
+ req2->rq_page_table_addr_lo & CNIC_PAGE_MASK;
ictx->tstorm_st_context.iscsi.rq_db_phy_addr.hi =
req2->rq_page_table_addr_hi;
ictx->tstorm_st_context.iscsi.iscsi_conn_id = req1->iscsi_conn_id;
@@ -1842,7 +1842,7 @@
/* CSTORM and USTORM initialization is different, CSTORM requires
* CQ DB base & not PTE addr */
ictx->cstorm_st_context.cq_db_base.lo =
- req1->cq_page_table_addr_lo & PAGE_MASK;
+ req1->cq_page_table_addr_lo & CNIC_PAGE_MASK;
ictx->cstorm_st_context.cq_db_base.hi = req1->cq_page_table_addr_hi;
ictx->cstorm_st_context.iscsi_conn_id = req1->iscsi_conn_id;
ictx->cstorm_st_context.cq_proc_en_bit_map = (1 << cp->num_cqs) - 1;
@@ -2911,7 +2911,7 @@
u16 hw_cons, sw_cons;
struct cnic_uio_dev *udev = cp->udev;
union eth_rx_cqe *cqe, *cqe_ring = (union eth_rx_cqe *)
- (udev->l2_ring + (2 * BNX2_PAGE_SIZE));
+ (udev->l2_ring + (2 * CNIC_PAGE_SIZE));
u32 cmd;
int comp = 0;
@@ -3244,7 +3244,8 @@
int rc;
mutex_lock(&cnic_lock);
- ulp_ops = cnic_ulp_tbl_prot(ulp_type);
+ ulp_ops = rcu_dereference_protected(cp->ulp_ops[ulp_type],
+ lockdep_is_held(&cnic_lock));
if (ulp_ops && ulp_ops->cnic_get_stats)
rc = ulp_ops->cnic_get_stats(cp->ulp_handle[ulp_type]);
else
@@ -4384,7 +4385,7 @@
u32 idx = cp->ctx_arr[i].cid / cp->cids_per_blk;
u32 val;
- memset(cp->ctx_arr[i].ctx, 0, BNX2_PAGE_SIZE);
+ memset(cp->ctx_arr[i].ctx, 0, CNIC_PAGE_SIZE);
CNIC_WR(dev, BNX2_CTX_HOST_PAGE_TBL_DATA0,
(cp->ctx_arr[i].mapping & 0xffffffff) | valid_bit);
@@ -4628,7 +4629,7 @@
val = BNX2_L2CTX_L2_STATUSB_NUM(sb_id);
cnic_ctx_wr(dev, cid_addr, BNX2_L2CTX_HOST_BDIDX, val);
- rxbd = udev->l2_ring + BNX2_PAGE_SIZE;
+ rxbd = udev->l2_ring + CNIC_PAGE_SIZE;
for (i = 0; i < BNX2_MAX_RX_DESC_CNT; i++, rxbd++) {
dma_addr_t buf_map;
int n = (i % cp->l2_rx_ring_size) + 1;
@@ -4639,11 +4640,11 @@
rxbd->rx_bd_haddr_hi = (u64) buf_map >> 32;
rxbd->rx_bd_haddr_lo = (u64) buf_map & 0xffffffff;
}
- val = (u64) (ring_map + BNX2_PAGE_SIZE) >> 32;
+ val = (u64) (ring_map + CNIC_PAGE_SIZE) >> 32;
cnic_ctx_wr(dev, cid_addr, BNX2_L2CTX_NX_BDHADDR_HI, val);
rxbd->rx_bd_haddr_hi = val;
- val = (u64) (ring_map + BNX2_PAGE_SIZE) & 0xffffffff;
+ val = (u64) (ring_map + CNIC_PAGE_SIZE) & 0xffffffff;
cnic_ctx_wr(dev, cid_addr, BNX2_L2CTX_NX_BDHADDR_LO, val);
rxbd->rx_bd_haddr_lo = val;
@@ -4709,10 +4710,10 @@
val = CNIC_RD(dev, BNX2_MQ_CONFIG);
val &= ~BNX2_MQ_CONFIG_KNL_BYP_BLK_SIZE;
- if (BNX2_PAGE_BITS > 12)
+ if (CNIC_PAGE_BITS > 12)
val |= (12 - 8) << 4;
else
- val |= (BNX2_PAGE_BITS - 8) << 4;
+ val |= (CNIC_PAGE_BITS - 8) << 4;
CNIC_WR(dev, BNX2_MQ_CONFIG, val);
@@ -4742,13 +4743,13 @@
/* Initialize the kernel work queue context. */
val = KRNLQ_TYPE_TYPE_KRNLQ | KRNLQ_SIZE_TYPE_SIZE |
- (BNX2_PAGE_BITS - 8) | KRNLQ_FLAGS_QE_SELF_SEQ;
+ (CNIC_PAGE_BITS - 8) | KRNLQ_FLAGS_QE_SELF_SEQ;
cnic_ctx_wr(dev, kwq_cid_addr, L5_KRNLQ_TYPE, val);
- val = (BNX2_PAGE_SIZE / sizeof(struct kwqe) - 1) << 16;
+ val = (CNIC_PAGE_SIZE / sizeof(struct kwqe) - 1) << 16;
cnic_ctx_wr(dev, kwq_cid_addr, L5_KRNLQ_QE_SELF_SEQ_MAX, val);
- val = ((BNX2_PAGE_SIZE / sizeof(struct kwqe)) << 16) | KWQ_PAGE_CNT;
+ val = ((CNIC_PAGE_SIZE / sizeof(struct kwqe)) << 16) | KWQ_PAGE_CNT;
cnic_ctx_wr(dev, kwq_cid_addr, L5_KRNLQ_PGTBL_NPAGES, val);
val = (u32) ((u64) cp->kwq_info.pgtbl_map >> 32);
@@ -4768,13 +4769,13 @@
/* Initialize the kernel complete queue context. */
val = KRNLQ_TYPE_TYPE_KRNLQ | KRNLQ_SIZE_TYPE_SIZE |
- (BNX2_PAGE_BITS - 8) | KRNLQ_FLAGS_QE_SELF_SEQ;
+ (CNIC_PAGE_BITS - 8) | KRNLQ_FLAGS_QE_SELF_SEQ;
cnic_ctx_wr(dev, kcq_cid_addr, L5_KRNLQ_TYPE, val);
- val = (BNX2_PAGE_SIZE / sizeof(struct kcqe) - 1) << 16;
+ val = (CNIC_PAGE_SIZE / sizeof(struct kcqe) - 1) << 16;
cnic_ctx_wr(dev, kcq_cid_addr, L5_KRNLQ_QE_SELF_SEQ_MAX, val);
- val = ((BNX2_PAGE_SIZE / sizeof(struct kcqe)) << 16) | KCQ_PAGE_CNT;
+ val = ((CNIC_PAGE_SIZE / sizeof(struct kcqe)) << 16) | KCQ_PAGE_CNT;
cnic_ctx_wr(dev, kcq_cid_addr, L5_KRNLQ_PGTBL_NPAGES, val);
val = (u32) ((u64) cp->kcq1.dma.pgtbl_map >> 32);
@@ -4918,7 +4919,7 @@
u32 cli = cp->ethdev->iscsi_l2_client_id;
u32 val;
- memset(txbd, 0, BNX2_PAGE_SIZE);
+ memset(txbd, 0, CNIC_PAGE_SIZE);
buf_map = udev->l2_buf_map;
for (i = 0; i < BNX2_MAX_TX_DESC_CNT; i += 3, txbd += 3) {
@@ -4978,9 +4979,9 @@
struct bnx2x *bp = netdev_priv(dev->netdev);
struct cnic_uio_dev *udev = cp->udev;
struct eth_rx_bd *rxbd = (struct eth_rx_bd *) (udev->l2_ring +
- BNX2_PAGE_SIZE);
+ CNIC_PAGE_SIZE);
struct eth_rx_cqe_next_page *rxcqe = (struct eth_rx_cqe_next_page *)
- (udev->l2_ring + (2 * BNX2_PAGE_SIZE));
+ (udev->l2_ring + (2 * CNIC_PAGE_SIZE));
struct host_sp_status_block *sb = cp->bnx2x_def_status_blk;
int i;
u32 cli = cp->ethdev->iscsi_l2_client_id;
@@ -5004,20 +5005,20 @@
rxbd->addr_lo = cpu_to_le32(buf_map & 0xffffffff);
}
- val = (u64) (ring_map + BNX2_PAGE_SIZE) >> 32;
+ val = (u64) (ring_map + CNIC_PAGE_SIZE) >> 32;
rxbd->addr_hi = cpu_to_le32(val);
data->rx.bd_page_base.hi = cpu_to_le32(val);
- val = (u64) (ring_map + BNX2_PAGE_SIZE) & 0xffffffff;
+ val = (u64) (ring_map + CNIC_PAGE_SIZE) & 0xffffffff;
rxbd->addr_lo = cpu_to_le32(val);
data->rx.bd_page_base.lo = cpu_to_le32(val);
rxcqe += BNX2X_MAX_RCQ_DESC_CNT;
- val = (u64) (ring_map + (2 * BNX2_PAGE_SIZE)) >> 32;
+ val = (u64) (ring_map + (2 * CNIC_PAGE_SIZE)) >> 32;
rxcqe->addr_hi = cpu_to_le32(val);
data->rx.cqe_page_base.hi = cpu_to_le32(val);
- val = (u64) (ring_map + (2 * BNX2_PAGE_SIZE)) & 0xffffffff;
+ val = (u64) (ring_map + (2 * CNIC_PAGE_SIZE)) & 0xffffffff;
rxcqe->addr_lo = cpu_to_le32(val);
data->rx.cqe_page_base.lo = cpu_to_le32(val);
@@ -5265,8 +5266,8 @@
msleep(10);
}
clear_bit(CNIC_LCL_FL_RINGS_INITED, &cp->cnic_local_flags);
- rx_ring = udev->l2_ring + BNX2_PAGE_SIZE;
- memset(rx_ring, 0, BNX2_PAGE_SIZE);
+ rx_ring = udev->l2_ring + CNIC_PAGE_SIZE;
+ memset(rx_ring, 0, CNIC_PAGE_SIZE);
}
static int cnic_register_netdev(struct cnic_dev *dev)
diff --git a/drivers/net/ethernet/broadcom/cnic.h b/drivers/net/ethernet/broadcom/cnic.h
index 0d6b13f..d535ae4 100644
--- a/drivers/net/ethernet/broadcom/cnic.h
+++ b/drivers/net/ethernet/broadcom/cnic.h
@@ -1,6 +1,6 @@
/* cnic.h: Broadcom CNIC core network driver.
*
- * Copyright (c) 2006-2013 Broadcom Corporation
+ * Copyright (c) 2006-2014 Broadcom Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
diff --git a/drivers/net/ethernet/broadcom/cnic_defs.h b/drivers/net/ethernet/broadcom/cnic_defs.h
index 95a8e4b..dcbca69 100644
--- a/drivers/net/ethernet/broadcom/cnic_defs.h
+++ b/drivers/net/ethernet/broadcom/cnic_defs.h
@@ -1,7 +1,7 @@
/* cnic.c: Broadcom CNIC core network driver.
*
- * Copyright (c) 2006-2013 Broadcom Corporation
+ * Copyright (c) 2006-2014 Broadcom Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
diff --git a/drivers/net/ethernet/broadcom/cnic_if.h b/drivers/net/ethernet/broadcom/cnic_if.h
index 8cf6b192..5f4d557 100644
--- a/drivers/net/ethernet/broadcom/cnic_if.h
+++ b/drivers/net/ethernet/broadcom/cnic_if.h
@@ -1,6 +1,6 @@
/* cnic_if.h: Broadcom CNIC core network driver.
*
- * Copyright (c) 2006-2013 Broadcom Corporation
+ * Copyright (c) 2006-2014 Broadcom Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -14,8 +14,8 @@
#include "bnx2x/bnx2x_mfw_req.h"
-#define CNIC_MODULE_VERSION "2.5.19"
-#define CNIC_MODULE_RELDATE "December 19, 2013"
+#define CNIC_MODULE_VERSION "2.5.20"
+#define CNIC_MODULE_RELDATE "March 14, 2014"
#define CNIC_ULP_RDMA 0
#define CNIC_ULP_ISCSI 1
@@ -24,6 +24,16 @@
#define MAX_CNIC_ULP_TYPE_EXT 3
#define MAX_CNIC_ULP_TYPE 4
+/* Use CPU native page size up to 16K for cnic ring sizes. */
+#if (PAGE_SHIFT > 14)
+#define CNIC_PAGE_BITS 14
+#else
+#define CNIC_PAGE_BITS PAGE_SHIFT
+#endif
+#define CNIC_PAGE_SIZE (1 << (CNIC_PAGE_BITS))
+#define CNIC_PAGE_ALIGN(addr) ALIGN(addr, CNIC_PAGE_SIZE)
+#define CNIC_PAGE_MASK (~((CNIC_PAGE_SIZE) - 1))
+
struct kwqe {
u32 kwqe_op_flag;
diff --git a/drivers/net/ethernet/broadcom/genet/Makefile b/drivers/net/ethernet/broadcom/genet/Makefile
new file mode 100644
index 0000000..31f55a9
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/genet/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_BCMGENET) += genet.o
+genet-objs := bcmgenet.o bcmmii.o
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
new file mode 100644
index 0000000..adf8acb
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -0,0 +1,2584 @@
+/*
+ * Broadcom GENET (Gigabit Ethernet) controller driver
+ *
+ * Copyright (c) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ */
+
+#define pr_fmt(fmt) "bcmgenet: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/fcntl.h>
+#include <linux/interrupt.h>
+#include <linux/string.h>
+#include <linux/if_ether.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/pm.h>
+#include <linux/clk.h>
+#include <linux/version.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <net/arp.h>
+
+#include <linux/mii.h>
+#include <linux/ethtool.h>
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/phy.h>
+
+#include <asm/unaligned.h>
+
+#include "bcmgenet.h"
+
+/* Maximum number of hardware queues, downsized if needed */
+#define GENET_MAX_MQ_CNT 4
+
+/* Default highest priority queue for multi queue support */
+#define GENET_Q0_PRIORITY 0
+
+#define GENET_DEFAULT_BD_CNT \
+ (TOTAL_DESC - priv->hw_params->tx_queues * priv->hw_params->bds_cnt)
+
+#define RX_BUF_LENGTH 2048
+#define SKB_ALIGNMENT 32
+
+/* Tx/Rx DMA register offset, skip 256 descriptors */
+#define WORDS_PER_BD(p) (p->hw_params->words_per_bd)
+#define DMA_DESC_SIZE (WORDS_PER_BD(priv) * sizeof(u32))
+
+#define GENET_TDMA_REG_OFF (priv->hw_params->tdma_offset + \
+ TOTAL_DESC * DMA_DESC_SIZE)
+
+#define GENET_RDMA_REG_OFF (priv->hw_params->rdma_offset + \
+ TOTAL_DESC * DMA_DESC_SIZE)
+
+static inline void dmadesc_set_length_status(struct bcmgenet_priv *priv,
+ void __iomem *d, u32 value)
+{
+ __raw_writel(value, d + DMA_DESC_LENGTH_STATUS);
+}
+
+static inline u32 dmadesc_get_length_status(struct bcmgenet_priv *priv,
+ void __iomem *d)
+{
+ return __raw_readl(d + DMA_DESC_LENGTH_STATUS);
+}
+
+static inline void dmadesc_set_addr(struct bcmgenet_priv *priv,
+ void __iomem *d,
+ dma_addr_t addr)
+{
+ __raw_writel(lower_32_bits(addr), d + DMA_DESC_ADDRESS_LO);
+
+ /* Register writes to GISB bus can take couple hundred nanoseconds
+ * and are done for each packet, save these expensive writes unless
+ * the platform is explicitely configured for 64-bits/LPAE.
+ */
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+ if (priv->hw_params->flags & GENET_HAS_40BITS)
+ __raw_writel(upper_32_bits(addr), d + DMA_DESC_ADDRESS_HI);
+#endif
+}
+
+/* Combined address + length/status setter */
+static inline void dmadesc_set(struct bcmgenet_priv *priv,
+ void __iomem *d, dma_addr_t addr, u32 val)
+{
+ dmadesc_set_length_status(priv, d, val);
+ dmadesc_set_addr(priv, d, addr);
+}
+
+static inline dma_addr_t dmadesc_get_addr(struct bcmgenet_priv *priv,
+ void __iomem *d)
+{
+ dma_addr_t addr;
+
+ addr = __raw_readl(d + DMA_DESC_ADDRESS_LO);
+
+ /* Register writes to GISB bus can take couple hundred nanoseconds
+ * and are done for each packet, save these expensive writes unless
+ * the platform is explicitely configured for 64-bits/LPAE.
+ */
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+ if (priv->hw_params->flags & GENET_HAS_40BITS)
+ addr |= (u64)__raw_readl(d + DMA_DESC_ADDRESS_HI) << 32;
+#endif
+ return addr;
+}
+
+#define GENET_VER_FMT "%1d.%1d EPHY: 0x%04x"
+
+#define GENET_MSG_DEFAULT (NETIF_MSG_DRV | NETIF_MSG_PROBE | \
+ NETIF_MSG_LINK)
+
+static inline u32 bcmgenet_rbuf_ctrl_get(struct bcmgenet_priv *priv)
+{
+ if (GENET_IS_V1(priv))
+ return bcmgenet_rbuf_readl(priv, RBUF_FLUSH_CTRL_V1);
+ else
+ return bcmgenet_sys_readl(priv, SYS_RBUF_FLUSH_CTRL);
+}
+
+static inline void bcmgenet_rbuf_ctrl_set(struct bcmgenet_priv *priv, u32 val)
+{
+ if (GENET_IS_V1(priv))
+ bcmgenet_rbuf_writel(priv, val, RBUF_FLUSH_CTRL_V1);
+ else
+ bcmgenet_sys_writel(priv, val, SYS_RBUF_FLUSH_CTRL);
+}
+
+/* These macros are defined to deal with register map change
+ * between GENET1.1 and GENET2. Only those currently being used
+ * by driver are defined.
+ */
+static inline u32 bcmgenet_tbuf_ctrl_get(struct bcmgenet_priv *priv)
+{
+ if (GENET_IS_V1(priv))
+ return bcmgenet_rbuf_readl(priv, TBUF_CTRL_V1);
+ else
+ return __raw_readl(priv->base +
+ priv->hw_params->tbuf_offset + TBUF_CTRL);
+}
+
+static inline void bcmgenet_tbuf_ctrl_set(struct bcmgenet_priv *priv, u32 val)
+{
+ if (GENET_IS_V1(priv))
+ bcmgenet_rbuf_writel(priv, val, TBUF_CTRL_V1);
+ else
+ __raw_writel(val, priv->base +
+ priv->hw_params->tbuf_offset + TBUF_CTRL);
+}
+
+static inline u32 bcmgenet_bp_mc_get(struct bcmgenet_priv *priv)
+{
+ if (GENET_IS_V1(priv))
+ return bcmgenet_rbuf_readl(priv, TBUF_BP_MC_V1);
+ else
+ return __raw_readl(priv->base +
+ priv->hw_params->tbuf_offset + TBUF_BP_MC);
+}
+
+static inline void bcmgenet_bp_mc_set(struct bcmgenet_priv *priv, u32 val)
+{
+ if (GENET_IS_V1(priv))
+ bcmgenet_rbuf_writel(priv, val, TBUF_BP_MC_V1);
+ else
+ __raw_writel(val, priv->base +
+ priv->hw_params->tbuf_offset + TBUF_BP_MC);
+}
+
+/* RX/TX DMA register accessors */
+enum dma_reg {
+ DMA_RING_CFG = 0,
+ DMA_CTRL,
+ DMA_STATUS,
+ DMA_SCB_BURST_SIZE,
+ DMA_ARB_CTRL,
+ DMA_PRIORITY,
+ DMA_RING_PRIORITY,
+};
+
+static const u8 bcmgenet_dma_regs_v3plus[] = {
+ [DMA_RING_CFG] = 0x00,
+ [DMA_CTRL] = 0x04,
+ [DMA_STATUS] = 0x08,
+ [DMA_SCB_BURST_SIZE] = 0x0C,
+ [DMA_ARB_CTRL] = 0x2C,
+ [DMA_PRIORITY] = 0x30,
+ [DMA_RING_PRIORITY] = 0x38,
+};
+
+static const u8 bcmgenet_dma_regs_v2[] = {
+ [DMA_RING_CFG] = 0x00,
+ [DMA_CTRL] = 0x04,
+ [DMA_STATUS] = 0x08,
+ [DMA_SCB_BURST_SIZE] = 0x0C,
+ [DMA_ARB_CTRL] = 0x30,
+ [DMA_PRIORITY] = 0x34,
+ [DMA_RING_PRIORITY] = 0x3C,
+};
+
+static const u8 bcmgenet_dma_regs_v1[] = {
+ [DMA_CTRL] = 0x00,
+ [DMA_STATUS] = 0x04,
+ [DMA_SCB_BURST_SIZE] = 0x0C,
+ [DMA_ARB_CTRL] = 0x30,
+ [DMA_PRIORITY] = 0x34,
+ [DMA_RING_PRIORITY] = 0x3C,
+};
+
+/* Set at runtime once bcmgenet version is known */
+static const u8 *bcmgenet_dma_regs;
+
+static inline struct bcmgenet_priv *dev_to_priv(struct device *dev)
+{
+ return netdev_priv(dev_get_drvdata(dev));
+}
+
+static inline u32 bcmgenet_tdma_readl(struct bcmgenet_priv *priv,
+ enum dma_reg r)
+{
+ return __raw_readl(priv->base + GENET_TDMA_REG_OFF +
+ DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
+}
+
+static inline void bcmgenet_tdma_writel(struct bcmgenet_priv *priv,
+ u32 val, enum dma_reg r)
+{
+ __raw_writel(val, priv->base + GENET_TDMA_REG_OFF +
+ DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
+}
+
+static inline u32 bcmgenet_rdma_readl(struct bcmgenet_priv *priv,
+ enum dma_reg r)
+{
+ return __raw_readl(priv->base + GENET_RDMA_REG_OFF +
+ DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
+}
+
+static inline void bcmgenet_rdma_writel(struct bcmgenet_priv *priv,
+ u32 val, enum dma_reg r)
+{
+ __raw_writel(val, priv->base + GENET_RDMA_REG_OFF +
+ DMA_RINGS_SIZE + bcmgenet_dma_regs[r]);
+}
+
+/* RDMA/TDMA ring registers and accessors
+ * we merge the common fields and just prefix with T/D the registers
+ * having different meaning depending on the direction
+ */
+enum dma_ring_reg {
+ TDMA_READ_PTR = 0,
+ RDMA_WRITE_PTR = TDMA_READ_PTR,
+ TDMA_READ_PTR_HI,
+ RDMA_WRITE_PTR_HI = TDMA_READ_PTR_HI,
+ TDMA_CONS_INDEX,
+ RDMA_PROD_INDEX = TDMA_CONS_INDEX,
+ TDMA_PROD_INDEX,
+ RDMA_CONS_INDEX = TDMA_PROD_INDEX,
+ DMA_RING_BUF_SIZE,
+ DMA_START_ADDR,
+ DMA_START_ADDR_HI,
+ DMA_END_ADDR,
+ DMA_END_ADDR_HI,
+ DMA_MBUF_DONE_THRESH,
+ TDMA_FLOW_PERIOD,
+ RDMA_XON_XOFF_THRESH = TDMA_FLOW_PERIOD,
+ TDMA_WRITE_PTR,
+ RDMA_READ_PTR = TDMA_WRITE_PTR,
+ TDMA_WRITE_PTR_HI,
+ RDMA_READ_PTR_HI = TDMA_WRITE_PTR_HI
+};
+
+/* GENET v4 supports 40-bits pointer addressing
+ * for obvious reasons the LO and HI word parts
+ * are contiguous, but this offsets the other
+ * registers.
+ */
+static const u8 genet_dma_ring_regs_v4[] = {
+ [TDMA_READ_PTR] = 0x00,
+ [TDMA_READ_PTR_HI] = 0x04,
+ [TDMA_CONS_INDEX] = 0x08,
+ [TDMA_PROD_INDEX] = 0x0C,
+ [DMA_RING_BUF_SIZE] = 0x10,
+ [DMA_START_ADDR] = 0x14,
+ [DMA_START_ADDR_HI] = 0x18,
+ [DMA_END_ADDR] = 0x1C,
+ [DMA_END_ADDR_HI] = 0x20,
+ [DMA_MBUF_DONE_THRESH] = 0x24,
+ [TDMA_FLOW_PERIOD] = 0x28,
+ [TDMA_WRITE_PTR] = 0x2C,
+ [TDMA_WRITE_PTR_HI] = 0x30,
+};
+
+static const u8 genet_dma_ring_regs_v123[] = {
+ [TDMA_READ_PTR] = 0x00,
+ [TDMA_CONS_INDEX] = 0x04,
+ [TDMA_PROD_INDEX] = 0x08,
+ [DMA_RING_BUF_SIZE] = 0x0C,
+ [DMA_START_ADDR] = 0x10,
+ [DMA_END_ADDR] = 0x14,
+ [DMA_MBUF_DONE_THRESH] = 0x18,
+ [TDMA_FLOW_PERIOD] = 0x1C,
+ [TDMA_WRITE_PTR] = 0x20,
+};
+
+/* Set at runtime once GENET version is known */
+static const u8 *genet_dma_ring_regs;
+
+static inline u32 bcmgenet_tdma_ring_readl(struct bcmgenet_priv *priv,
+ unsigned int ring,
+ enum dma_ring_reg r)
+{
+ return __raw_readl(priv->base + GENET_TDMA_REG_OFF +
+ (DMA_RING_SIZE * ring) +
+ genet_dma_ring_regs[r]);
+}
+
+static inline void bcmgenet_tdma_ring_writel(struct bcmgenet_priv *priv,
+ unsigned int ring,
+ u32 val,
+ enum dma_ring_reg r)
+{
+ __raw_writel(val, priv->base + GENET_TDMA_REG_OFF +
+ (DMA_RING_SIZE * ring) +
+ genet_dma_ring_regs[r]);
+}
+
+static inline u32 bcmgenet_rdma_ring_readl(struct bcmgenet_priv *priv,
+ unsigned int ring,
+ enum dma_ring_reg r)
+{
+ return __raw_readl(priv->base + GENET_RDMA_REG_OFF +
+ (DMA_RING_SIZE * ring) +
+ genet_dma_ring_regs[r]);
+}
+
+static inline void bcmgenet_rdma_ring_writel(struct bcmgenet_priv *priv,
+ unsigned int ring,
+ u32 val,
+ enum dma_ring_reg r)
+{
+ __raw_writel(val, priv->base + GENET_RDMA_REG_OFF +
+ (DMA_RING_SIZE * ring) +
+ genet_dma_ring_regs[r]);
+}
+
+static int bcmgenet_get_settings(struct net_device *dev,
+ struct ethtool_cmd *cmd)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
+ if (!netif_running(dev))
+ return -EINVAL;
+
+ if (!priv->phydev)
+ return -ENODEV;
+
+ return phy_ethtool_gset(priv->phydev, cmd);
+}
+
+static int bcmgenet_set_settings(struct net_device *dev,
+ struct ethtool_cmd *cmd)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
+ if (!netif_running(dev))
+ return -EINVAL;
+
+ if (!priv->phydev)
+ return -ENODEV;
+
+ return phy_ethtool_sset(priv->phydev, cmd);
+}
+
+static int bcmgenet_set_rx_csum(struct net_device *dev,
+ netdev_features_t wanted)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ u32 rbuf_chk_ctrl;
+ bool rx_csum_en;
+
+ rx_csum_en = !!(wanted & NETIF_F_RXCSUM);
+
+ rbuf_chk_ctrl = bcmgenet_rbuf_readl(priv, RBUF_CHK_CTRL);
+
+ /* enable rx checksumming */
+ if (rx_csum_en)
+ rbuf_chk_ctrl |= RBUF_RXCHK_EN;
+ else
+ rbuf_chk_ctrl &= ~RBUF_RXCHK_EN;
+ priv->desc_rxchk_en = rx_csum_en;
+
+ /* If UniMAC forwards CRC, we need to skip over it to get
+ * a valid CHK bit to be set in the per-packet status word
+ */
+ if (rx_csum_en && priv->crc_fwd_en)
+ rbuf_chk_ctrl |= RBUF_SKIP_FCS;
+ else
+ rbuf_chk_ctrl &= ~RBUF_SKIP_FCS;
+
+ bcmgenet_rbuf_writel(priv, rbuf_chk_ctrl, RBUF_CHK_CTRL);
+
+ return 0;
+}
+
+static int bcmgenet_set_tx_csum(struct net_device *dev,
+ netdev_features_t wanted)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ bool desc_64b_en;
+ u32 tbuf_ctrl, rbuf_ctrl;
+
+ tbuf_ctrl = bcmgenet_tbuf_ctrl_get(priv);
+ rbuf_ctrl = bcmgenet_rbuf_readl(priv, RBUF_CTRL);
+
+ desc_64b_en = !!(wanted & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM));
+
+ /* enable 64 bytes descriptor in both directions (RBUF and TBUF) */
+ if (desc_64b_en) {
+ tbuf_ctrl |= RBUF_64B_EN;
+ rbuf_ctrl |= RBUF_64B_EN;
+ } else {
+ tbuf_ctrl &= ~RBUF_64B_EN;
+ rbuf_ctrl &= ~RBUF_64B_EN;
+ }
+ priv->desc_64b_en = desc_64b_en;
+
+ bcmgenet_tbuf_ctrl_set(priv, tbuf_ctrl);
+ bcmgenet_rbuf_writel(priv, rbuf_ctrl, RBUF_CTRL);
+
+ return 0;
+}
+
+static int bcmgenet_set_features(struct net_device *dev,
+ netdev_features_t features)
+{
+ netdev_features_t changed = features ^ dev->features;
+ netdev_features_t wanted = dev->wanted_features;
+ int ret = 0;
+
+ if (changed & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))
+ ret = bcmgenet_set_tx_csum(dev, wanted);
+ if (changed & (NETIF_F_RXCSUM))
+ ret = bcmgenet_set_rx_csum(dev, wanted);
+
+ return ret;
+}
+
+static u32 bcmgenet_get_msglevel(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
+ return priv->msg_enable;
+}
+
+static void bcmgenet_set_msglevel(struct net_device *dev, u32 level)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
+ priv->msg_enable = level;
+}
+
+/* standard ethtool support functions. */
+enum bcmgenet_stat_type {
+ BCMGENET_STAT_NETDEV = -1,
+ BCMGENET_STAT_MIB_RX,
+ BCMGENET_STAT_MIB_TX,
+ BCMGENET_STAT_RUNT,
+ BCMGENET_STAT_MISC,
+};
+
+struct bcmgenet_stats {
+ char stat_string[ETH_GSTRING_LEN];
+ int stat_sizeof;
+ int stat_offset;
+ enum bcmgenet_stat_type type;
+ /* reg offset from UMAC base for misc counters */
+ u16 reg_offset;
+};
+
+#define STAT_NETDEV(m) { \
+ .stat_string = __stringify(m), \
+ .stat_sizeof = sizeof(((struct net_device_stats *)0)->m), \
+ .stat_offset = offsetof(struct net_device_stats, m), \
+ .type = BCMGENET_STAT_NETDEV, \
+}
+
+#define STAT_GENET_MIB(str, m, _type) { \
+ .stat_string = str, \
+ .stat_sizeof = sizeof(((struct bcmgenet_priv *)0)->m), \
+ .stat_offset = offsetof(struct bcmgenet_priv, m), \
+ .type = _type, \
+}
+
+#define STAT_GENET_MIB_RX(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_MIB_RX)
+#define STAT_GENET_MIB_TX(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_MIB_TX)
+#define STAT_GENET_RUNT(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_RUNT)
+
+#define STAT_GENET_MISC(str, m, offset) { \
+ .stat_string = str, \
+ .stat_sizeof = sizeof(((struct bcmgenet_priv *)0)->m), \
+ .stat_offset = offsetof(struct bcmgenet_priv, m), \
+ .type = BCMGENET_STAT_MISC, \
+ .reg_offset = offset, \
+}
+
+
+/* There is a 0xC gap between the end of RX and beginning of TX stats and then
+ * between the end of TX stats and the beginning of the RX RUNT
+ */
+#define BCMGENET_STAT_OFFSET 0xc
+
+/* Hardware counters must be kept in sync because the order/offset
+ * is important here (order in structure declaration = order in hardware)
+ */
+static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
+ /* general stats */
+ STAT_NETDEV(rx_packets),
+ STAT_NETDEV(tx_packets),
+ STAT_NETDEV(rx_bytes),
+ STAT_NETDEV(tx_bytes),
+ STAT_NETDEV(rx_errors),
+ STAT_NETDEV(tx_errors),
+ STAT_NETDEV(rx_dropped),
+ STAT_NETDEV(tx_dropped),
+ STAT_NETDEV(multicast),
+ /* UniMAC RSV counters */
+ STAT_GENET_MIB_RX("rx_64_octets", mib.rx.pkt_cnt.cnt_64),
+ STAT_GENET_MIB_RX("rx_65_127_oct", mib.rx.pkt_cnt.cnt_127),
+ STAT_GENET_MIB_RX("rx_128_255_oct", mib.rx.pkt_cnt.cnt_255),
+ STAT_GENET_MIB_RX("rx_256_511_oct", mib.rx.pkt_cnt.cnt_511),
+ STAT_GENET_MIB_RX("rx_512_1023_oct", mib.rx.pkt_cnt.cnt_1023),
+ STAT_GENET_MIB_RX("rx_1024_1518_oct", mib.rx.pkt_cnt.cnt_1518),
+ STAT_GENET_MIB_RX("rx_vlan_1519_1522_oct", mib.rx.pkt_cnt.cnt_mgv),
+ STAT_GENET_MIB_RX("rx_1522_2047_oct", mib.rx.pkt_cnt.cnt_2047),
+ STAT_GENET_MIB_RX("rx_2048_4095_oct", mib.rx.pkt_cnt.cnt_4095),
+ STAT_GENET_MIB_RX("rx_4096_9216_oct", mib.rx.pkt_cnt.cnt_9216),
+ STAT_GENET_MIB_RX("rx_pkts", mib.rx.pkt),
+ STAT_GENET_MIB_RX("rx_bytes", mib.rx.bytes),
+ STAT_GENET_MIB_RX("rx_multicast", mib.rx.mca),
+ STAT_GENET_MIB_RX("rx_broadcast", mib.rx.bca),
+ STAT_GENET_MIB_RX("rx_fcs", mib.rx.fcs),
+ STAT_GENET_MIB_RX("rx_control", mib.rx.cf),
+ STAT_GENET_MIB_RX("rx_pause", mib.rx.pf),
+ STAT_GENET_MIB_RX("rx_unknown", mib.rx.uo),
+ STAT_GENET_MIB_RX("rx_align", mib.rx.aln),
+ STAT_GENET_MIB_RX("rx_outrange", mib.rx.flr),
+ STAT_GENET_MIB_RX("rx_code", mib.rx.cde),
+ STAT_GENET_MIB_RX("rx_carrier", mib.rx.fcr),
+ STAT_GENET_MIB_RX("rx_oversize", mib.rx.ovr),
+ STAT_GENET_MIB_RX("rx_jabber", mib.rx.jbr),
+ STAT_GENET_MIB_RX("rx_mtu_err", mib.rx.mtue),
+ STAT_GENET_MIB_RX("rx_good_pkts", mib.rx.pok),
+ STAT_GENET_MIB_RX("rx_unicast", mib.rx.uc),
+ STAT_GENET_MIB_RX("rx_ppp", mib.rx.ppp),
+ STAT_GENET_MIB_RX("rx_crc", mib.rx.rcrc),
+ /* UniMAC TSV counters */
+ STAT_GENET_MIB_TX("tx_64_octets", mib.tx.pkt_cnt.cnt_64),
+ STAT_GENET_MIB_TX("tx_65_127_oct", mib.tx.pkt_cnt.cnt_127),
+ STAT_GENET_MIB_TX("tx_128_255_oct", mib.tx.pkt_cnt.cnt_255),
+ STAT_GENET_MIB_TX("tx_256_511_oct", mib.tx.pkt_cnt.cnt_511),
+ STAT_GENET_MIB_TX("tx_512_1023_oct", mib.tx.pkt_cnt.cnt_1023),
+ STAT_GENET_MIB_TX("tx_1024_1518_oct", mib.tx.pkt_cnt.cnt_1518),
+ STAT_GENET_MIB_TX("tx_vlan_1519_1522_oct", mib.tx.pkt_cnt.cnt_mgv),
+ STAT_GENET_MIB_TX("tx_1522_2047_oct", mib.tx.pkt_cnt.cnt_2047),
+ STAT_GENET_MIB_TX("tx_2048_4095_oct", mib.tx.pkt_cnt.cnt_4095),
+ STAT_GENET_MIB_TX("tx_4096_9216_oct", mib.tx.pkt_cnt.cnt_9216),
+ STAT_GENET_MIB_TX("tx_pkts", mib.tx.pkts),
+ STAT_GENET_MIB_TX("tx_multicast", mib.tx.mca),
+ STAT_GENET_MIB_TX("tx_broadcast", mib.tx.bca),
+ STAT_GENET_MIB_TX("tx_pause", mib.tx.pf),
+ STAT_GENET_MIB_TX("tx_control", mib.tx.cf),
+ STAT_GENET_MIB_TX("tx_fcs_err", mib.tx.fcs),
+ STAT_GENET_MIB_TX("tx_oversize", mib.tx.ovr),
+ STAT_GENET_MIB_TX("tx_defer", mib.tx.drf),
+ STAT_GENET_MIB_TX("tx_excess_defer", mib.tx.edf),
+ STAT_GENET_MIB_TX("tx_single_col", mib.tx.scl),
+ STAT_GENET_MIB_TX("tx_multi_col", mib.tx.mcl),
+ STAT_GENET_MIB_TX("tx_late_col", mib.tx.lcl),
+ STAT_GENET_MIB_TX("tx_excess_col", mib.tx.ecl),
+ STAT_GENET_MIB_TX("tx_frags", mib.tx.frg),
+ STAT_GENET_MIB_TX("tx_total_col", mib.tx.ncl),
+ STAT_GENET_MIB_TX("tx_jabber", mib.tx.jbr),
+ STAT_GENET_MIB_TX("tx_bytes", mib.tx.bytes),
+ STAT_GENET_MIB_TX("tx_good_pkts", mib.tx.pok),
+ STAT_GENET_MIB_TX("tx_unicast", mib.tx.uc),
+ /* UniMAC RUNT counters */
+ STAT_GENET_RUNT("rx_runt_pkts", mib.rx_runt_cnt),
+ STAT_GENET_RUNT("rx_runt_valid_fcs", mib.rx_runt_fcs),
+ STAT_GENET_RUNT("rx_runt_inval_fcs_align", mib.rx_runt_fcs_align),
+ STAT_GENET_RUNT("rx_runt_bytes", mib.rx_runt_bytes),
+ /* Misc UniMAC counters */
+ STAT_GENET_MISC("rbuf_ovflow_cnt", mib.rbuf_ovflow_cnt,
+ UMAC_RBUF_OVFL_CNT),
+ STAT_GENET_MISC("rbuf_err_cnt", mib.rbuf_err_cnt, UMAC_RBUF_ERR_CNT),
+ STAT_GENET_MISC("mdf_err_cnt", mib.mdf_err_cnt, UMAC_MDF_ERR_CNT),
+};
+
+#define BCMGENET_STATS_LEN ARRAY_SIZE(bcmgenet_gstrings_stats)
+
+static void bcmgenet_get_drvinfo(struct net_device *dev,
+ struct ethtool_drvinfo *info)
+{
+ strlcpy(info->driver, "bcmgenet", sizeof(info->driver));
+ strlcpy(info->version, "v2.0", sizeof(info->version));
+ info->n_stats = BCMGENET_STATS_LEN;
+
+}
+
+static int bcmgenet_get_sset_count(struct net_device *dev, int string_set)
+{
+ switch (string_set) {
+ case ETH_SS_STATS:
+ return BCMGENET_STATS_LEN;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static void bcmgenet_get_strings(struct net_device *dev,
+ u32 stringset, u8 *data)
+{
+ int i;
+
+ switch (stringset) {
+ case ETH_SS_STATS:
+ for (i = 0; i < BCMGENET_STATS_LEN; i++) {
+ memcpy(data + i * ETH_GSTRING_LEN,
+ bcmgenet_gstrings_stats[i].stat_string,
+ ETH_GSTRING_LEN);
+ }
+ break;
+ }
+}
+
+static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv)
+{
+ int i, j = 0;
+
+ for (i = 0; i < BCMGENET_STATS_LEN; i++) {
+ const struct bcmgenet_stats *s;
+ u8 offset = 0;
+ u32 val = 0;
+ char *p;
+
+ s = &bcmgenet_gstrings_stats[i];
+ switch (s->type) {
+ case BCMGENET_STAT_NETDEV:
+ continue;
+ case BCMGENET_STAT_MIB_RX:
+ case BCMGENET_STAT_MIB_TX:
+ case BCMGENET_STAT_RUNT:
+ if (s->type != BCMGENET_STAT_MIB_RX)
+ offset = BCMGENET_STAT_OFFSET;
+ val = bcmgenet_umac_readl(priv, UMAC_MIB_START +
+ j + offset);
+ break;
+ case BCMGENET_STAT_MISC:
+ val = bcmgenet_umac_readl(priv, s->reg_offset);
+ /* clear if overflowed */
+ if (val == ~0)
+ bcmgenet_umac_writel(priv, 0, s->reg_offset);
+ break;
+ }
+
+ j += s->stat_sizeof;
+ p = (char *)priv + s->stat_offset;
+ *(u32 *)p = val;
+ }
+}
+
+static void bcmgenet_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *stats,
+ u64 *data)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ int i;
+
+ if (netif_running(dev))
+ bcmgenet_update_mib_counters(priv);
+
+ for (i = 0; i < BCMGENET_STATS_LEN; i++) {
+ const struct bcmgenet_stats *s;
+ char *p;
+
+ s = &bcmgenet_gstrings_stats[i];
+ if (s->type == BCMGENET_STAT_NETDEV)
+ p = (char *)&dev->stats;
+ else
+ p = (char *)priv;
+ p += s->stat_offset;
+ data[i] = *(u32 *)p;
+ }
+}
+
+/* standard ethtool support functions. */
+static struct ethtool_ops bcmgenet_ethtool_ops = {
+ .get_strings = bcmgenet_get_strings,
+ .get_sset_count = bcmgenet_get_sset_count,
+ .get_ethtool_stats = bcmgenet_get_ethtool_stats,
+ .get_settings = bcmgenet_get_settings,
+ .set_settings = bcmgenet_set_settings,
+ .get_drvinfo = bcmgenet_get_drvinfo,
+ .get_link = ethtool_op_get_link,
+ .get_msglevel = bcmgenet_get_msglevel,
+ .set_msglevel = bcmgenet_set_msglevel,
+};
+
+/* Power down the unimac, based on mode. */
+static void bcmgenet_power_down(struct bcmgenet_priv *priv,
+ enum bcmgenet_power_mode mode)
+{
+ u32 reg;
+
+ switch (mode) {
+ case GENET_POWER_CABLE_SENSE:
+ phy_detach(priv->phydev);
+ break;
+
+ case GENET_POWER_PASSIVE:
+ /* Power down LED */
+ bcmgenet_mii_reset(priv->dev);
+ if (priv->hw_params->flags & GENET_HAS_EXT) {
+ reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
+ reg |= (EXT_PWR_DOWN_PHY |
+ EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
+ bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+static void bcmgenet_power_up(struct bcmgenet_priv *priv,
+ enum bcmgenet_power_mode mode)
+{
+ u32 reg;
+
+ if (!(priv->hw_params->flags & GENET_HAS_EXT))
+ return;
+
+ reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
+
+ switch (mode) {
+ case GENET_POWER_PASSIVE:
+ reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_PHY |
+ EXT_PWR_DOWN_BIAS);
+ /* fallthrough */
+ case GENET_POWER_CABLE_SENSE:
+ /* enable APD */
+ reg |= EXT_PWR_DN_EN_LD;
+ break;
+ default:
+ break;
+ }
+
+ bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+ bcmgenet_mii_reset(priv->dev);
+}
+
+/* ioctl handle special commands that are not present in ethtool. */
+static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ int val = 0;
+
+ if (!netif_running(dev))
+ return -EINVAL;
+
+ switch (cmd) {
+ case SIOCGMIIPHY:
+ case SIOCGMIIREG:
+ case SIOCSMIIREG:
+ if (!priv->phydev)
+ val = -ENODEV;
+ else
+ val = phy_mii_ioctl(priv->phydev, rq, cmd);
+ break;
+
+ default:
+ val = -EINVAL;
+ break;
+ }
+
+ return val;
+}
+
+static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv,
+ struct bcmgenet_tx_ring *ring)
+{
+ struct enet_cb *tx_cb_ptr;
+
+ tx_cb_ptr = ring->cbs;
+ tx_cb_ptr += ring->write_ptr - ring->cb_ptr;
+ tx_cb_ptr->bd_addr = priv->tx_bds + ring->write_ptr * DMA_DESC_SIZE;
+ /* Advancing local write pointer */
+ if (ring->write_ptr == ring->end_ptr)
+ ring->write_ptr = ring->cb_ptr;
+ else
+ ring->write_ptr++;
+
+ return tx_cb_ptr;
+}
+
+/* Simple helper to free a control block's resources */
+static void bcmgenet_free_cb(struct enet_cb *cb)
+{
+ dev_kfree_skb_any(cb->skb);
+ cb->skb = NULL;
+ dma_unmap_addr_set(cb, dma_addr, 0);
+}
+
+static inline void bcmgenet_tx_ring16_int_disable(struct bcmgenet_priv *priv,
+ struct bcmgenet_tx_ring *ring)
+{
+ bcmgenet_intrl2_0_writel(priv,
+ UMAC_IRQ_TXDMA_BDONE | UMAC_IRQ_TXDMA_PDONE,
+ INTRL2_CPU_MASK_SET);
+}
+
+static inline void bcmgenet_tx_ring16_int_enable(struct bcmgenet_priv *priv,
+ struct bcmgenet_tx_ring *ring)
+{
+ bcmgenet_intrl2_0_writel(priv,
+ UMAC_IRQ_TXDMA_BDONE | UMAC_IRQ_TXDMA_PDONE,
+ INTRL2_CPU_MASK_CLEAR);
+}
+
+static inline void bcmgenet_tx_ring_int_enable(struct bcmgenet_priv *priv,
+ struct bcmgenet_tx_ring *ring)
+{
+ bcmgenet_intrl2_1_writel(priv,
+ (1 << ring->index), INTRL2_CPU_MASK_CLEAR);
+ priv->int1_mask &= ~(1 << ring->index);
+}
+
+static inline void bcmgenet_tx_ring_int_disable(struct bcmgenet_priv *priv,
+ struct bcmgenet_tx_ring *ring)
+{
+ bcmgenet_intrl2_1_writel(priv,
+ (1 << ring->index), INTRL2_CPU_MASK_SET);
+ priv->int1_mask |= (1 << ring->index);
+}
+
+/* Unlocked version of the reclaim routine */
+static void __bcmgenet_tx_reclaim(struct net_device *dev,
+ struct bcmgenet_tx_ring *ring)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ int last_tx_cn, last_c_index, num_tx_bds;
+ struct enet_cb *tx_cb_ptr;
+ struct netdev_queue *txq;
+ unsigned int c_index;
+
+ /* Compute how many buffers are transmited since last xmit call */
+ c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX);
+ txq = netdev_get_tx_queue(dev, ring->queue);
+
+ last_c_index = ring->c_index;
+ num_tx_bds = ring->size;
+
+ c_index &= (num_tx_bds - 1);
+
+ if (c_index >= last_c_index)
+ last_tx_cn = c_index - last_c_index;
+ else
+ last_tx_cn = num_tx_bds - last_c_index + c_index;
+
+ netif_dbg(priv, tx_done, dev,
+ "%s ring=%d index=%d last_tx_cn=%d last_index=%d\n",
+ __func__, ring->index,
+ c_index, last_tx_cn, last_c_index);
+
+ /* Reclaim transmitted buffers */
+ while (last_tx_cn-- > 0) {
+ tx_cb_ptr = ring->cbs + last_c_index;
+ if (tx_cb_ptr->skb) {
+ dev->stats.tx_bytes += tx_cb_ptr->skb->len;
+ dma_unmap_single(&dev->dev,
+ dma_unmap_addr(tx_cb_ptr, dma_addr),
+ tx_cb_ptr->skb->len,
+ DMA_TO_DEVICE);
+ bcmgenet_free_cb(tx_cb_ptr);
+ } else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) {
+ dev->stats.tx_bytes +=
+ dma_unmap_len(tx_cb_ptr, dma_len);
+ dma_unmap_page(&dev->dev,
+ dma_unmap_addr(tx_cb_ptr, dma_addr),
+ dma_unmap_len(tx_cb_ptr, dma_len),
+ DMA_TO_DEVICE);
+ dma_unmap_addr_set(tx_cb_ptr, dma_addr, 0);
+ }
+ dev->stats.tx_packets++;
+ ring->free_bds += 1;
+
+ last_c_index++;
+ last_c_index &= (num_tx_bds - 1);
+ }
+
+ if (ring->free_bds > (MAX_SKB_FRAGS + 1))
+ ring->int_disable(priv, ring);
+
+ if (netif_tx_queue_stopped(txq))
+ netif_tx_wake_queue(txq);
+
+ ring->c_index = c_index;
+}
+
+static void bcmgenet_tx_reclaim(struct net_device *dev,
+ struct bcmgenet_tx_ring *ring)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&ring->lock, flags);
+ __bcmgenet_tx_reclaim(dev, ring);
+ spin_unlock_irqrestore(&ring->lock, flags);
+}
+
+static void bcmgenet_tx_reclaim_all(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ int i;
+
+ if (netif_is_multiqueue(dev)) {
+ for (i = 0; i < priv->hw_params->tx_queues; i++)
+ bcmgenet_tx_reclaim(dev, &priv->tx_rings[i]);
+ }
+
+ bcmgenet_tx_reclaim(dev, &priv->tx_rings[DESC_INDEX]);
+}
+
+/* Transmits a single SKB (either head of a fragment or a single SKB)
+ * caller must hold priv->lock
+ */
+static int bcmgenet_xmit_single(struct net_device *dev,
+ struct sk_buff *skb,
+ u16 dma_desc_flags,
+ struct bcmgenet_tx_ring *ring)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ struct device *kdev = &priv->pdev->dev;
+ struct enet_cb *tx_cb_ptr;
+ unsigned int skb_len;
+ dma_addr_t mapping;
+ u32 length_status;
+ int ret;
+
+ tx_cb_ptr = bcmgenet_get_txcb(priv, ring);
+
+ if (unlikely(!tx_cb_ptr))
+ BUG();
+
+ tx_cb_ptr->skb = skb;
+
+ skb_len = skb_headlen(skb) < ETH_ZLEN ? ETH_ZLEN : skb_headlen(skb);
+
+ mapping = dma_map_single(kdev, skb->data, skb_len, DMA_TO_DEVICE);
+ ret = dma_mapping_error(kdev, mapping);
+ if (ret) {
+ netif_err(priv, tx_err, dev, "Tx DMA map failed\n");
+ dev_kfree_skb(skb);
+ return ret;
+ }
+
+ dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping);
+ dma_unmap_len_set(tx_cb_ptr, dma_len, skb->len);
+ length_status = (skb_len << DMA_BUFLENGTH_SHIFT) | dma_desc_flags |
+ (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT) |
+ DMA_TX_APPEND_CRC;
+
+ if (skb->ip_summed == CHECKSUM_PARTIAL)
+ length_status |= DMA_TX_DO_CSUM;
+
+ dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, length_status);
+
+ /* Decrement total BD count and advance our write pointer */
+ ring->free_bds -= 1;
+ ring->prod_index += 1;
+ ring->prod_index &= DMA_P_INDEX_MASK;
+
+ return 0;
+}
+
+/* Transmit a SKB fragement */
+static int bcmgenet_xmit_frag(struct net_device *dev,
+ skb_frag_t *frag,
+ u16 dma_desc_flags,
+ struct bcmgenet_tx_ring *ring)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ struct device *kdev = &priv->pdev->dev;
+ struct enet_cb *tx_cb_ptr;
+ dma_addr_t mapping;
+ int ret;
+
+ tx_cb_ptr = bcmgenet_get_txcb(priv, ring);
+
+ if (unlikely(!tx_cb_ptr))
+ BUG();
+ tx_cb_ptr->skb = NULL;
+
+ mapping = skb_frag_dma_map(kdev, frag, 0,
+ skb_frag_size(frag), DMA_TO_DEVICE);
+ ret = dma_mapping_error(kdev, mapping);
+ if (ret) {
+ netif_err(priv, tx_err, dev, "%s: Tx DMA map failed\n",
+ __func__);
+ return ret;
+ }
+
+ dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping);
+ dma_unmap_len_set(tx_cb_ptr, dma_len, frag->size);
+
+ dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping,
+ (frag->size << DMA_BUFLENGTH_SHIFT) | dma_desc_flags |
+ (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT));
+
+
+ ring->free_bds -= 1;
+ ring->prod_index += 1;
+ ring->prod_index &= DMA_P_INDEX_MASK;
+
+ return 0;
+}
+
+/* Reallocate the SKB to put enough headroom in front of it and insert
+ * the transmit checksum offsets in the descriptors
+ */
+static int bcmgenet_put_tx_csum(struct net_device *dev, struct sk_buff *skb)
+{
+ struct status_64 *status = NULL;
+ struct sk_buff *new_skb;
+ u16 offset;
+ u8 ip_proto;
+ u16 ip_ver;
+ u32 tx_csum_info;
+
+ if (unlikely(skb_headroom(skb) < sizeof(*status))) {
+ /* If 64 byte status block enabled, must make sure skb has
+ * enough headroom for us to insert 64B status block.
+ */
+ new_skb = skb_realloc_headroom(skb, sizeof(*status));
+ dev_kfree_skb(skb);
+ if (!new_skb) {
+ dev->stats.tx_errors++;
+ dev->stats.tx_dropped++;
+ return -ENOMEM;
+ }
+ skb = new_skb;
+ }
+
+ skb_push(skb, sizeof(*status));
+ status = (struct status_64 *)skb->data;
+
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ ip_ver = htons(skb->protocol);
+ switch (ip_ver) {
+ case ETH_P_IP:
+ ip_proto = ip_hdr(skb)->protocol;
+ break;
+ case ETH_P_IPV6:
+ ip_proto = ipv6_hdr(skb)->nexthdr;
+ break;
+ default:
+ return 0;
+ }
+
+ offset = skb_checksum_start_offset(skb) - sizeof(*status);
+ tx_csum_info = (offset << STATUS_TX_CSUM_START_SHIFT) |
+ (offset + skb->csum_offset);
+
+ /* Set the length valid bit for TCP and UDP and just set
+ * the special UDP flag for IPv4, else just set to 0.
+ */
+ if (ip_proto == IPPROTO_TCP || ip_proto == IPPROTO_UDP) {
+ tx_csum_info |= STATUS_TX_CSUM_LV;
+ if (ip_proto == IPPROTO_UDP && ip_ver == ETH_P_IP)
+ tx_csum_info |= STATUS_TX_CSUM_PROTO_UDP;
+ } else
+ tx_csum_info = 0;
+
+ status->tx_csum_info = tx_csum_info;
+ }
+
+ return 0;
+}
+
+static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ struct bcmgenet_tx_ring *ring = NULL;
+ struct netdev_queue *txq;
+ unsigned long flags = 0;
+ int nr_frags, index;
+ u16 dma_desc_flags;
+ int ret;
+ int i;
+
+ index = skb_get_queue_mapping(skb);
+ /* Mapping strategy:
+ * queue_mapping = 0, unclassified, packet xmited through ring16
+ * queue_mapping = 1, goes to ring 0. (highest priority queue
+ * queue_mapping = 2, goes to ring 1.
+ * queue_mapping = 3, goes to ring 2.
+ * queue_mapping = 4, goes to ring 3.
+ */
+ if (index == 0)
+ index = DESC_INDEX;
+ else
+ index -= 1;
+
+ nr_frags = skb_shinfo(skb)->nr_frags;
+ ring = &priv->tx_rings[index];
+ txq = netdev_get_tx_queue(dev, ring->queue);
+
+ spin_lock_irqsave(&ring->lock, flags);
+ if (ring->free_bds <= nr_frags + 1) {
+ netif_tx_stop_queue(txq);
+ netdev_err(dev, "%s: tx ring %d full when queue %d awake\n",
+ __func__, index, ring->queue);
+ ret = NETDEV_TX_BUSY;
+ goto out;
+ }
+
+ /* set the SKB transmit checksum */
+ if (priv->desc_64b_en) {
+ ret = bcmgenet_put_tx_csum(dev, skb);
+ if (ret) {
+ ret = NETDEV_TX_OK;
+ goto out;
+ }
+ }
+
+ dma_desc_flags = DMA_SOP;
+ if (nr_frags == 0)
+ dma_desc_flags |= DMA_EOP;
+
+ /* Transmit single SKB or head of fragment list */
+ ret = bcmgenet_xmit_single(dev, skb, dma_desc_flags, ring);
+ if (ret) {
+ ret = NETDEV_TX_OK;
+ goto out;
+ }
+
+ /* xmit fragment */
+ for (i = 0; i < nr_frags; i++) {
+ ret = bcmgenet_xmit_frag(dev,
+ &skb_shinfo(skb)->frags[i],
+ (i == nr_frags - 1) ? DMA_EOP : 0, ring);
+ if (ret) {
+ ret = NETDEV_TX_OK;
+ goto out;
+ }
+ }
+
+ skb_tx_timestamp(skb);
+
+ /* we kept a software copy of how much we should advance the TDMA
+ * producer index, now write it down to the hardware
+ */
+ bcmgenet_tdma_ring_writel(priv, ring->index,
+ ring->prod_index, TDMA_PROD_INDEX);
+
+ if (ring->free_bds <= (MAX_SKB_FRAGS + 1)) {
+ netif_tx_stop_queue(txq);
+ ring->int_enable(priv, ring);
+ }
+
+out:
+ spin_unlock_irqrestore(&ring->lock, flags);
+
+ return ret;
+}
+
+
+static int bcmgenet_rx_refill(struct bcmgenet_priv *priv,
+ struct enet_cb *cb)
+{
+ struct device *kdev = &priv->pdev->dev;
+ struct sk_buff *skb;
+ dma_addr_t mapping;
+ int ret;
+
+ skb = netdev_alloc_skb(priv->dev,
+ priv->rx_buf_len + SKB_ALIGNMENT);
+ if (!skb)
+ return -ENOMEM;
+
+ /* a caller did not release this control block */
+ WARN_ON(cb->skb != NULL);
+ cb->skb = skb;
+ mapping = dma_map_single(kdev, skb->data,
+ priv->rx_buf_len, DMA_FROM_DEVICE);
+ ret = dma_mapping_error(kdev, mapping);
+ if (ret) {
+ bcmgenet_free_cb(cb);
+ netif_err(priv, rx_err, priv->dev,
+ "%s DMA map failed\n", __func__);
+ return ret;
+ }
+
+ dma_unmap_addr_set(cb, dma_addr, mapping);
+ /* assign packet, prepare descriptor, and advance pointer */
+
+ dmadesc_set_addr(priv, priv->rx_bd_assign_ptr, mapping);
+
+ /* turn on the newly assigned BD for DMA to use */
+ priv->rx_bd_assign_index++;
+ priv->rx_bd_assign_index &= (priv->num_rx_bds - 1);
+
+ priv->rx_bd_assign_ptr = priv->rx_bds +
+ (priv->rx_bd_assign_index * DMA_DESC_SIZE);
+
+ return 0;
+}
+
+/* bcmgenet_desc_rx - descriptor based rx process.
+ * this could be called from bottom half, or from NAPI polling method.
+ */
+static unsigned int bcmgenet_desc_rx(struct bcmgenet_priv *priv,
+ unsigned int budget)
+{
+ struct net_device *dev = priv->dev;
+ struct enet_cb *cb;
+ struct sk_buff *skb;
+ u32 dma_length_status;
+ unsigned long dma_flag;
+ int len, err;
+ unsigned int rxpktprocessed = 0, rxpkttoprocess;
+ unsigned int p_index;
+ unsigned int chksum_ok = 0;
+
+ p_index = bcmgenet_rdma_ring_readl(priv,
+ DESC_INDEX, RDMA_PROD_INDEX);
+ p_index &= DMA_P_INDEX_MASK;
+
+ if (p_index < priv->rx_c_index)
+ rxpkttoprocess = (DMA_C_INDEX_MASK + 1) -
+ priv->rx_c_index + p_index;
+ else
+ rxpkttoprocess = p_index - priv->rx_c_index;
+
+ netif_dbg(priv, rx_status, dev,
+ "RDMA: rxpkttoprocess=%d\n", rxpkttoprocess);
+
+ while ((rxpktprocessed < rxpkttoprocess) &&
+ (rxpktprocessed < budget)) {
+
+ /* Unmap the packet contents such that we can use the
+ * RSV from the 64 bytes descriptor when enabled and save
+ * a 32-bits register read
+ */
+ cb = &priv->rx_cbs[priv->rx_read_ptr];
+ skb = cb->skb;
+ dma_unmap_single(&dev->dev, dma_unmap_addr(cb, dma_addr),
+ priv->rx_buf_len, DMA_FROM_DEVICE);
+
+ if (!priv->desc_64b_en) {
+ dma_length_status = dmadesc_get_length_status(priv,
+ priv->rx_bds +
+ (priv->rx_read_ptr *
+ DMA_DESC_SIZE));
+ } else {
+ struct status_64 *status;
+ status = (struct status_64 *)skb->data;
+ dma_length_status = status->length_status;
+ }
+
+ /* DMA flags and length are still valid no matter how
+ * we got the Receive Status Vector (64B RSB or register)
+ */
+ dma_flag = dma_length_status & 0xffff;
+ len = dma_length_status >> DMA_BUFLENGTH_SHIFT;
+
+ netif_dbg(priv, rx_status, dev,
+ "%s: p_ind=%d c_ind=%d read_ptr=%d len_stat=0x%08x\n",
+ __func__, p_index, priv->rx_c_index, priv->rx_read_ptr,
+ dma_length_status);
+
+ rxpktprocessed++;
+
+ priv->rx_read_ptr++;
+ priv->rx_read_ptr &= (priv->num_rx_bds - 1);
+
+ /* out of memory, just drop packets at the hardware level */
+ if (unlikely(!skb)) {
+ dev->stats.rx_dropped++;
+ dev->stats.rx_errors++;
+ goto refill;
+ }
+
+ if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) {
+ netif_err(priv, rx_status, dev,
+ "Droping fragmented packet!\n");
+ dev->stats.rx_dropped++;
+ dev->stats.rx_errors++;
+ dev_kfree_skb_any(cb->skb);
+ cb->skb = NULL;
+ goto refill;
+ }
+ /* report errors */
+ if (unlikely(dma_flag & (DMA_RX_CRC_ERROR |
+ DMA_RX_OV |
+ DMA_RX_NO |
+ DMA_RX_LG |
+ DMA_RX_RXER))) {
+ netif_err(priv, rx_status, dev, "dma_flag=0x%x\n",
+ (unsigned int)dma_flag);
+ if (dma_flag & DMA_RX_CRC_ERROR)
+ dev->stats.rx_crc_errors++;
+ if (dma_flag & DMA_RX_OV)
+ dev->stats.rx_over_errors++;
+ if (dma_flag & DMA_RX_NO)
+ dev->stats.rx_frame_errors++;
+ if (dma_flag & DMA_RX_LG)
+ dev->stats.rx_length_errors++;
+ dev->stats.rx_dropped++;
+ dev->stats.rx_errors++;
+
+ /* discard the packet and advance consumer index.*/
+ dev_kfree_skb_any(cb->skb);
+ cb->skb = NULL;
+ goto refill;
+ } /* error packet */
+
+ chksum_ok = (dma_flag & priv->dma_rx_chk_bit) &&
+ priv->desc_rxchk_en;
+
+ skb_put(skb, len);
+ if (priv->desc_64b_en) {
+ skb_pull(skb, 64);
+ len -= 64;
+ }
+
+ if (likely(chksum_ok))
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ /* remove hardware 2bytes added for IP alignment */
+ skb_pull(skb, 2);
+ len -= 2;
+
+ if (priv->crc_fwd_en) {
+ skb_trim(skb, len - ETH_FCS_LEN);
+ len -= ETH_FCS_LEN;
+ }
+
+ /*Finish setting up the received SKB and send it to the kernel*/
+ skb->protocol = eth_type_trans(skb, priv->dev);
+ dev->stats.rx_packets++;
+ dev->stats.rx_bytes += len;
+ if (dma_flag & DMA_RX_MULT)
+ dev->stats.multicast++;
+
+ /* Notify kernel */
+ napi_gro_receive(&priv->napi, skb);
+ cb->skb = NULL;
+ netif_dbg(priv, rx_status, dev, "pushed up to kernel\n");
+
+ /* refill RX path on the current control block */
+refill:
+ err = bcmgenet_rx_refill(priv, cb);
+ if (err)
+ netif_err(priv, rx_err, dev, "Rx refill failed\n");
+ }
+
+ return rxpktprocessed;
+}
+
+/* Assign skb to RX DMA descriptor. */
+static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv)
+{
+ struct enet_cb *cb;
+ int ret = 0;
+ int i;
+
+ netif_dbg(priv, hw, priv->dev, "%s:\n", __func__);
+
+ /* loop here for each buffer needing assign */
+ for (i = 0; i < priv->num_rx_bds; i++) {
+ cb = &priv->rx_cbs[priv->rx_bd_assign_index];
+ if (cb->skb)
+ continue;
+
+ /* set the DMA descriptor length once and for all
+ * it will only change if we support dynamically sizing
+ * priv->rx_buf_len, but we do not
+ */
+ dmadesc_set_length_status(priv, priv->rx_bd_assign_ptr,
+ priv->rx_buf_len << DMA_BUFLENGTH_SHIFT);
+
+ ret = bcmgenet_rx_refill(priv, cb);
+ if (ret)
+ break;
+
+ }
+
+ return ret;
+}
+
+static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv)
+{
+ struct enet_cb *cb;
+ int i;
+
+ for (i = 0; i < priv->num_rx_bds; i++) {
+ cb = &priv->rx_cbs[i];
+
+ if (dma_unmap_addr(cb, dma_addr)) {
+ dma_unmap_single(&priv->dev->dev,
+ dma_unmap_addr(cb, dma_addr),
+ priv->rx_buf_len, DMA_FROM_DEVICE);
+ dma_unmap_addr_set(cb, dma_addr, 0);
+ }
+
+ if (cb->skb)
+ bcmgenet_free_cb(cb);
+ }
+}
+
+static int reset_umac(struct bcmgenet_priv *priv)
+{
+ struct device *kdev = &priv->pdev->dev;
+ unsigned int timeout = 0;
+ u32 reg;
+
+ /* 7358a0/7552a0: bad default in RBUF_FLUSH_CTRL.umac_sw_rst */
+ bcmgenet_rbuf_ctrl_set(priv, 0);
+ udelay(10);
+
+ /* disable MAC while updating its registers */
+ bcmgenet_umac_writel(priv, 0, UMAC_CMD);
+
+ /* issue soft reset, wait for it to complete */
+ bcmgenet_umac_writel(priv, CMD_SW_RESET, UMAC_CMD);
+ while (timeout++ < 1000) {
+ reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+ if (!(reg & CMD_SW_RESET))
+ return 0;
+
+ udelay(1);
+ }
+
+ if (timeout == 1000) {
+ dev_err(kdev,
+ "timeout waiting for MAC to come out of resetn\n");
+ return -ETIMEDOUT;
+ }
+
+ return 0;
+}
+
+static int init_umac(struct bcmgenet_priv *priv)
+{
+ struct device *kdev = &priv->pdev->dev;
+ int ret;
+ u32 reg, cpu_mask_clear;
+
+ dev_dbg(&priv->pdev->dev, "bcmgenet: init_umac\n");
+
+ ret = reset_umac(priv);
+ if (ret)
+ return ret;
+
+ bcmgenet_umac_writel(priv, 0, UMAC_CMD);
+ /* clear tx/rx counter */
+ bcmgenet_umac_writel(priv,
+ MIB_RESET_RX | MIB_RESET_TX | MIB_RESET_RUNT, UMAC_MIB_CTRL);
+ bcmgenet_umac_writel(priv, 0, UMAC_MIB_CTRL);
+
+ bcmgenet_umac_writel(priv, ENET_MAX_MTU_SIZE, UMAC_MAX_FRAME_LEN);
+
+ /* init rx registers, enable ip header optimization */
+ reg = bcmgenet_rbuf_readl(priv, RBUF_CTRL);
+ reg |= RBUF_ALIGN_2B;
+ bcmgenet_rbuf_writel(priv, reg, RBUF_CTRL);
+
+ if (!GENET_IS_V1(priv) && !GENET_IS_V2(priv))
+ bcmgenet_rbuf_writel(priv, 1, RBUF_TBUF_SIZE_CTRL);
+
+ /* Mask all interrupts.*/
+ bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
+ bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
+ bcmgenet_intrl2_0_writel(priv, 0, INTRL2_CPU_MASK_CLEAR);
+
+ cpu_mask_clear = UMAC_IRQ_RXDMA_BDONE;
+
+ dev_dbg(kdev, "%s:Enabling RXDMA_BDONE interrupt\n", __func__);
+
+ /* Monitor cable plug/unpluged event for internal PHY */
+ if (phy_is_internal(priv->phydev))
+ cpu_mask_clear |= (UMAC_IRQ_LINK_DOWN | UMAC_IRQ_LINK_UP);
+ else if (priv->ext_phy)
+ cpu_mask_clear |= (UMAC_IRQ_LINK_DOWN | UMAC_IRQ_LINK_UP);
+ else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
+ reg = bcmgenet_bp_mc_get(priv);
+ reg |= BIT(priv->hw_params->bp_in_en_shift);
+
+ /* bp_mask: back pressure mask */
+ if (netif_is_multiqueue(priv->dev))
+ reg |= priv->hw_params->bp_in_mask;
+ else
+ reg &= ~priv->hw_params->bp_in_mask;
+ bcmgenet_bp_mc_set(priv, reg);
+ }
+
+ /* Enable MDIO interrupts on GENET v3+ */
+ if (priv->hw_params->flags & GENET_HAS_MDIO_INTR)
+ cpu_mask_clear |= UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR;
+
+ bcmgenet_intrl2_0_writel(priv, cpu_mask_clear,
+ INTRL2_CPU_MASK_CLEAR);
+
+ /* Enable rx/tx engine.*/
+ dev_dbg(kdev, "done init umac\n");
+
+ return 0;
+}
+
+/* Initialize all house-keeping variables for a TX ring, along
+ * with corresponding hardware registers
+ */
+static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
+ unsigned int index, unsigned int size,
+ unsigned int write_ptr, unsigned int end_ptr)
+{
+ struct bcmgenet_tx_ring *ring = &priv->tx_rings[index];
+ u32 words_per_bd = WORDS_PER_BD(priv);
+ u32 flow_period_val = 0;
+ unsigned int first_bd;
+
+ spin_lock_init(&ring->lock);
+ ring->index = index;
+ if (index == DESC_INDEX) {
+ ring->queue = 0;
+ ring->int_enable = bcmgenet_tx_ring16_int_enable;
+ ring->int_disable = bcmgenet_tx_ring16_int_disable;
+ } else {
+ ring->queue = index + 1;
+ ring->int_enable = bcmgenet_tx_ring_int_enable;
+ ring->int_disable = bcmgenet_tx_ring_int_disable;
+ }
+ ring->cbs = priv->tx_cbs + write_ptr;
+ ring->size = size;
+ ring->c_index = 0;
+ ring->free_bds = size;
+ ring->write_ptr = write_ptr;
+ ring->cb_ptr = write_ptr;
+ ring->end_ptr = end_ptr - 1;
+ ring->prod_index = 0;
+
+ /* Set flow period for ring != 16 */
+ if (index != DESC_INDEX)
+ flow_period_val = ENET_MAX_MTU_SIZE << 16;
+
+ bcmgenet_tdma_ring_writel(priv, index, 0, TDMA_PROD_INDEX);
+ bcmgenet_tdma_ring_writel(priv, index, 0, TDMA_CONS_INDEX);
+ bcmgenet_tdma_ring_writel(priv, index, 1, DMA_MBUF_DONE_THRESH);
+ /* Disable rate control for now */
+ bcmgenet_tdma_ring_writel(priv, index, flow_period_val,
+ TDMA_FLOW_PERIOD);
+ /* Unclassified traffic goes to ring 16 */
+ bcmgenet_tdma_ring_writel(priv, index,
+ ((size << DMA_RING_SIZE_SHIFT) | RX_BUF_LENGTH),
+ DMA_RING_BUF_SIZE);
+
+ first_bd = write_ptr;
+
+ /* Set start and end address, read and write pointers */
+ bcmgenet_tdma_ring_writel(priv, index, first_bd * words_per_bd,
+ DMA_START_ADDR);
+ bcmgenet_tdma_ring_writel(priv, index, first_bd * words_per_bd,
+ TDMA_READ_PTR);
+ bcmgenet_tdma_ring_writel(priv, index, first_bd,
+ TDMA_WRITE_PTR);
+ bcmgenet_tdma_ring_writel(priv, index, end_ptr * words_per_bd - 1,
+ DMA_END_ADDR);
+}
+
+/* Initialize a RDMA ring */
+static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
+ unsigned int index, unsigned int size)
+{
+ u32 words_per_bd = WORDS_PER_BD(priv);
+ int ret;
+
+ priv->num_rx_bds = TOTAL_DESC;
+ priv->rx_bds = priv->base + priv->hw_params->rdma_offset;
+ priv->rx_bd_assign_ptr = priv->rx_bds;
+ priv->rx_bd_assign_index = 0;
+ priv->rx_c_index = 0;
+ priv->rx_read_ptr = 0;
+ priv->rx_cbs = kzalloc(priv->num_rx_bds * sizeof(struct enet_cb),
+ GFP_KERNEL);
+ if (!priv->rx_cbs)
+ return -ENOMEM;
+
+ ret = bcmgenet_alloc_rx_buffers(priv);
+ if (ret) {
+ kfree(priv->rx_cbs);
+ return ret;
+ }
+
+ bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_WRITE_PTR);
+ bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_PROD_INDEX);
+ bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_CONS_INDEX);
+ bcmgenet_rdma_ring_writel(priv, index,
+ ((size << DMA_RING_SIZE_SHIFT) | RX_BUF_LENGTH),
+ DMA_RING_BUF_SIZE);
+ bcmgenet_rdma_ring_writel(priv, index, 0, DMA_START_ADDR);
+ bcmgenet_rdma_ring_writel(priv, index,
+ words_per_bd * size - 1, DMA_END_ADDR);
+ bcmgenet_rdma_ring_writel(priv, index,
+ (DMA_FC_THRESH_LO << DMA_XOFF_THRESHOLD_SHIFT) |
+ DMA_FC_THRESH_HI, RDMA_XON_XOFF_THRESH);
+ bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_READ_PTR);
+
+ return ret;
+}
+
+/* init multi xmit queues, only available for GENET2+
+ * the queue is partitioned as follows:
+ *
+ * queue 0 - 3 is priority based, each one has 32 descriptors,
+ * with queue 0 being the highest priority queue.
+ *
+ * queue 16 is the default tx queue with GENET_DEFAULT_BD_CNT
+ * descriptors: 256 - (number of tx queues * bds per queues) = 128
+ * descriptors.
+ *
+ * The transmit control block pool is then partitioned as following:
+ * - tx_cbs[0...127] are for queue 16
+ * - tx_ring_cbs[0] points to tx_cbs[128..159]
+ * - tx_ring_cbs[1] points to tx_cbs[160..191]
+ * - tx_ring_cbs[2] points to tx_cbs[192..223]
+ * - tx_ring_cbs[3] points to tx_cbs[224..255]
+ */
+static void bcmgenet_init_multiq(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ unsigned int i, dma_enable;
+ u32 reg, dma_ctrl, ring_cfg = 0, dma_priority = 0;
+
+ if (!netif_is_multiqueue(dev)) {
+ netdev_warn(dev, "called with non multi queue aware HW\n");
+ return;
+ }
+
+ dma_ctrl = bcmgenet_tdma_readl(priv, DMA_CTRL);
+ dma_enable = dma_ctrl & DMA_EN;
+ dma_ctrl &= ~DMA_EN;
+ bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL);
+
+ /* Enable strict priority arbiter mode */
+ bcmgenet_tdma_writel(priv, DMA_ARBITER_SP, DMA_ARB_CTRL);
+
+ for (i = 0; i < priv->hw_params->tx_queues; i++) {
+ /* first 64 tx_cbs are reserved for default tx queue
+ * (ring 16)
+ */
+ bcmgenet_init_tx_ring(priv, i, priv->hw_params->bds_cnt,
+ i * priv->hw_params->bds_cnt,
+ (i + 1) * priv->hw_params->bds_cnt);
+
+ /* Configure ring as decriptor ring and setup priority */
+ ring_cfg |= 1 << i;
+ dma_priority |= ((GENET_Q0_PRIORITY + i) <<
+ (GENET_MAX_MQ_CNT + 1) * i);
+ dma_ctrl |= 1 << (i + DMA_RING_BUF_EN_SHIFT);
+ }
+
+ /* Enable rings */
+ reg = bcmgenet_tdma_readl(priv, DMA_RING_CFG);
+ reg |= ring_cfg;
+ bcmgenet_tdma_writel(priv, reg, DMA_RING_CFG);
+
+ /* Use configured rings priority and set ring #16 priority */
+ reg = bcmgenet_tdma_readl(priv, DMA_RING_PRIORITY);
+ reg |= ((GENET_Q0_PRIORITY + priv->hw_params->tx_queues) << 20);
+ reg |= dma_priority;
+ bcmgenet_tdma_writel(priv, reg, DMA_PRIORITY);
+
+ /* Configure ring as descriptor ring and re-enable DMA if enabled */
+ reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+ reg |= dma_ctrl;
+ if (dma_enable)
+ reg |= DMA_EN;
+ bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+}
+
+static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
+{
+ int i;
+
+ /* disable DMA */
+ bcmgenet_rdma_writel(priv, 0, DMA_CTRL);
+ bcmgenet_tdma_writel(priv, 0, DMA_CTRL);
+
+ for (i = 0; i < priv->num_tx_bds; i++) {
+ if (priv->tx_cbs[i].skb != NULL) {
+ dev_kfree_skb(priv->tx_cbs[i].skb);
+ priv->tx_cbs[i].skb = NULL;
+ }
+ }
+
+ bcmgenet_free_rx_buffers(priv);
+ kfree(priv->rx_cbs);
+ kfree(priv->tx_cbs);
+}
+
+/* init_edma: Initialize DMA control register */
+static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
+{
+ int ret;
+
+ netif_dbg(priv, hw, priv->dev, "bcmgenet: init_edma\n");
+
+ /* by default, enable ring 16 (descriptor based) */
+ ret = bcmgenet_init_rx_ring(priv, DESC_INDEX, TOTAL_DESC);
+ if (ret) {
+ netdev_err(priv->dev, "failed to initialize RX ring\n");
+ return ret;
+ }
+
+ /* init rDma */
+ bcmgenet_rdma_writel(priv, DMA_MAX_BURST_LENGTH, DMA_SCB_BURST_SIZE);
+
+ /* Init tDma */
+ bcmgenet_tdma_writel(priv, DMA_MAX_BURST_LENGTH, DMA_SCB_BURST_SIZE);
+
+ /* Initialize commont TX ring structures */
+ priv->tx_bds = priv->base + priv->hw_params->tdma_offset;
+ priv->num_tx_bds = TOTAL_DESC;
+ priv->tx_cbs = kzalloc(priv->num_tx_bds * sizeof(struct enet_cb),
+ GFP_KERNEL);
+ if (!priv->tx_cbs) {
+ bcmgenet_fini_dma(priv);
+ return -ENOMEM;
+ }
+
+ /* initialize multi xmit queue */
+ bcmgenet_init_multiq(priv->dev);
+
+ /* initialize special ring 16 */
+ bcmgenet_init_tx_ring(priv, DESC_INDEX, GENET_DEFAULT_BD_CNT,
+ priv->hw_params->tx_queues * priv->hw_params->bds_cnt,
+ TOTAL_DESC);
+
+ return 0;
+}
+
+/* NAPI polling method*/
+static int bcmgenet_poll(struct napi_struct *napi, int budget)
+{
+ struct bcmgenet_priv *priv = container_of(napi,
+ struct bcmgenet_priv, napi);
+ unsigned int work_done;
+
+ /* tx reclaim */
+ bcmgenet_tx_reclaim(priv->dev, &priv->tx_rings[DESC_INDEX]);
+
+ work_done = bcmgenet_desc_rx(priv, budget);
+
+ /* Advancing our consumer index*/
+ priv->rx_c_index += work_done;
+ priv->rx_c_index &= DMA_C_INDEX_MASK;
+ bcmgenet_rdma_ring_writel(priv, DESC_INDEX,
+ priv->rx_c_index, RDMA_CONS_INDEX);
+ if (work_done < budget) {
+ napi_complete(napi);
+ bcmgenet_intrl2_0_writel(priv,
+ UMAC_IRQ_RXDMA_BDONE, INTRL2_CPU_MASK_CLEAR);
+ }
+
+ return work_done;
+}
+
+/* Interrupt bottom half */
+static void bcmgenet_irq_task(struct work_struct *work)
+{
+ struct bcmgenet_priv *priv = container_of(
+ work, struct bcmgenet_priv, bcmgenet_irq_work);
+
+ netif_dbg(priv, intr, priv->dev, "%s\n", __func__);
+
+ /* Link UP/DOWN event */
+ if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
+ (priv->irq0_stat & (UMAC_IRQ_LINK_UP|UMAC_IRQ_LINK_DOWN))) {
+ phy_mac_interrupt(priv->phydev,
+ priv->irq0_stat & UMAC_IRQ_LINK_UP);
+ priv->irq0_stat &= ~(UMAC_IRQ_LINK_UP|UMAC_IRQ_LINK_DOWN);
+ }
+}
+
+/* bcmgenet_isr1: interrupt handler for ring buffer. */
+static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
+{
+ struct bcmgenet_priv *priv = dev_id;
+ unsigned int index;
+
+ /* Save irq status for bottom-half processing. */
+ priv->irq1_stat =
+ bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) &
+ ~priv->int1_mask;
+ /* clear inerrupts*/
+ bcmgenet_intrl2_1_writel(priv, priv->irq1_stat, INTRL2_CPU_CLEAR);
+
+ netif_dbg(priv, intr, priv->dev,
+ "%s: IRQ=0x%x\n", __func__, priv->irq1_stat);
+ /* Check the MBDONE interrupts.
+ * packet is done, reclaim descriptors
+ */
+ if (priv->irq1_stat & 0x0000ffff) {
+ index = 0;
+ for (index = 0; index < 16; index++) {
+ if (priv->irq1_stat & (1 << index))
+ bcmgenet_tx_reclaim(priv->dev,
+ &priv->tx_rings[index]);
+ }
+ }
+ return IRQ_HANDLED;
+}
+
+/* bcmgenet_isr0: Handle various interrupts. */
+static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
+{
+ struct bcmgenet_priv *priv = dev_id;
+
+ /* Save irq status for bottom-half processing. */
+ priv->irq0_stat =
+ bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT) &
+ ~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
+ /* clear inerrupts*/
+ bcmgenet_intrl2_0_writel(priv, priv->irq0_stat, INTRL2_CPU_CLEAR);
+
+ netif_dbg(priv, intr, priv->dev,
+ "IRQ=0x%x\n", priv->irq0_stat);
+
+ if (priv->irq0_stat & (UMAC_IRQ_RXDMA_BDONE | UMAC_IRQ_RXDMA_PDONE)) {
+ /* We use NAPI(software interrupt throttling, if
+ * Rx Descriptor throttling is not used.
+ * Disable interrupt, will be enabled in the poll method.
+ */
+ if (likely(napi_schedule_prep(&priv->napi))) {
+ bcmgenet_intrl2_0_writel(priv,
+ UMAC_IRQ_RXDMA_BDONE, INTRL2_CPU_MASK_SET);
+ __napi_schedule(&priv->napi);
+ }
+ }
+ if (priv->irq0_stat &
+ (UMAC_IRQ_TXDMA_BDONE | UMAC_IRQ_TXDMA_PDONE)) {
+ /* Tx reclaim */
+ bcmgenet_tx_reclaim(priv->dev, &priv->tx_rings[DESC_INDEX]);
+ }
+ if (priv->irq0_stat & (UMAC_IRQ_PHY_DET_R |
+ UMAC_IRQ_PHY_DET_F |
+ UMAC_IRQ_LINK_UP |
+ UMAC_IRQ_LINK_DOWN |
+ UMAC_IRQ_HFB_SM |
+ UMAC_IRQ_HFB_MM |
+ UMAC_IRQ_MPD_R)) {
+ /* all other interested interrupts handled in bottom half */
+ schedule_work(&priv->bcmgenet_irq_work);
+ }
+
+ if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
+ priv->irq0_stat & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
+ priv->irq0_stat &= ~(UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR);
+ wake_up(&priv->wq);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static void bcmgenet_umac_reset(struct bcmgenet_priv *priv)
+{
+ u32 reg;
+
+ reg = bcmgenet_rbuf_ctrl_get(priv);
+ reg |= BIT(1);
+ bcmgenet_rbuf_ctrl_set(priv, reg);
+ udelay(10);
+
+ reg &= ~BIT(1);
+ bcmgenet_rbuf_ctrl_set(priv, reg);
+ udelay(10);
+}
+
+static void bcmgenet_set_hw_addr(struct bcmgenet_priv *priv,
+ unsigned char *addr)
+{
+ bcmgenet_umac_writel(priv, (addr[0] << 24) | (addr[1] << 16) |
+ (addr[2] << 8) | addr[3], UMAC_MAC0);
+ bcmgenet_umac_writel(priv, (addr[4] << 8) | addr[5], UMAC_MAC1);
+}
+
+static int bcmgenet_wol_resume(struct bcmgenet_priv *priv)
+{
+ int ret;
+
+ /* From WOL-enabled suspend, switch to regular clock */
+ clk_disable(priv->clk_wol);
+ /* init umac registers to synchronize s/w with h/w */
+ ret = init_umac(priv);
+ if (ret)
+ return ret;
+
+ phy_init_hw(priv->phydev);
+ /* Speed settings must be restored */
+ bcmgenet_mii_config(priv->dev);
+
+ return 0;
+}
+
+/* Returns a reusable dma control register value */
+static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv)
+{
+ u32 reg;
+ u32 dma_ctrl;
+
+ /* disable DMA */
+ dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+ reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+ reg &= ~dma_ctrl;
+ bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+
+ reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
+ reg &= ~dma_ctrl;
+ bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
+
+ bcmgenet_umac_writel(priv, 1, UMAC_TX_FLUSH);
+ udelay(10);
+ bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH);
+
+ return dma_ctrl;
+}
+
+static void bcmgenet_enable_dma(struct bcmgenet_priv *priv, u32 dma_ctrl)
+{
+ u32 reg;
+
+ reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
+ reg |= dma_ctrl;
+ bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
+
+ reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+ reg |= dma_ctrl;
+ bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+}
+
+static int bcmgenet_open(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ unsigned long dma_ctrl;
+ u32 reg;
+ int ret;
+
+ netif_dbg(priv, ifup, dev, "bcmgenet_open\n");
+
+ /* Turn on the clock */
+ if (!IS_ERR(priv->clk))
+ clk_prepare_enable(priv->clk);
+
+ /* take MAC out of reset */
+ bcmgenet_umac_reset(priv);
+
+ ret = init_umac(priv);
+ if (ret)
+ goto err_clk_disable;
+
+ /* disable ethernet MAC while updating its registers */
+ reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+ reg &= ~(CMD_TX_EN | CMD_RX_EN);
+ bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+
+ bcmgenet_set_hw_addr(priv, dev->dev_addr);
+
+ if (priv->wol_enabled) {
+ ret = bcmgenet_wol_resume(priv);
+ if (ret)
+ return ret;
+ }
+
+ if (phy_is_internal(priv->phydev)) {
+ reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
+ reg |= EXT_ENERGY_DET_MASK;
+ bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+ }
+
+ /* Disable RX/TX DMA and flush TX queues */
+ dma_ctrl = bcmgenet_dma_disable(priv);
+
+ /* Reinitialize TDMA and RDMA and SW housekeeping */
+ ret = bcmgenet_init_dma(priv);
+ if (ret) {
+ netdev_err(dev, "failed to initialize DMA\n");
+ goto err_fini_dma;
+ }
+
+ /* Always enable ring 16 - descriptor ring */
+ bcmgenet_enable_dma(priv, dma_ctrl);
+
+ ret = request_irq(priv->irq0, bcmgenet_isr0, IRQF_SHARED,
+ dev->name, priv);
+ if (ret < 0) {
+ netdev_err(dev, "can't request IRQ %d\n", priv->irq0);
+ goto err_fini_dma;
+ }
+
+ ret = request_irq(priv->irq1, bcmgenet_isr1, IRQF_SHARED,
+ dev->name, priv);
+ if (ret < 0) {
+ netdev_err(dev, "can't request IRQ %d\n", priv->irq1);
+ goto err_irq0;
+ }
+
+ /* Start the network engine */
+ napi_enable(&priv->napi);
+
+ reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+ reg |= (CMD_TX_EN | CMD_RX_EN);
+ bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+
+ /* Make sure we reflect the value of CRC_CMD_FWD */
+ priv->crc_fwd_en = !!(reg & CMD_CRC_FWD);
+
+ device_set_wakeup_capable(&dev->dev, 1);
+
+ if (phy_is_internal(priv->phydev))
+ bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
+
+ netif_tx_start_all_queues(dev);
+
+ phy_start(priv->phydev);
+
+ return 0;
+
+err_irq0:
+ free_irq(priv->irq0, dev);
+err_fini_dma:
+ bcmgenet_fini_dma(priv);
+err_clk_disable:
+ if (!IS_ERR(priv->clk))
+ clk_disable_unprepare(priv->clk);
+ return ret;
+}
+
+static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv)
+{
+ int ret = 0;
+ int timeout = 0;
+ u32 reg;
+
+ /* Disable TDMA to stop add more frames in TX DMA */
+ reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+ reg &= ~DMA_EN;
+ bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+
+ /* Check TDMA status register to confirm TDMA is disabled */
+ while (timeout++ < DMA_TIMEOUT_VAL) {
+ reg = bcmgenet_tdma_readl(priv, DMA_STATUS);
+ if (reg & DMA_DISABLED)
+ break;
+
+ udelay(1);
+ }
+
+ if (timeout == DMA_TIMEOUT_VAL) {
+ netdev_warn(priv->dev,
+ "Timed out while disabling TX DMA\n");
+ ret = -ETIMEDOUT;
+ }
+
+ /* Wait 10ms for packet drain in both tx and rx dma */
+ usleep_range(10000, 20000);
+
+ /* Disable RDMA */
+ reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
+ reg &= ~DMA_EN;
+ bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
+
+ timeout = 0;
+ /* Check RDMA status register to confirm RDMA is disabled */
+ while (timeout++ < DMA_TIMEOUT_VAL) {
+ reg = bcmgenet_rdma_readl(priv, DMA_STATUS);
+ if (reg & DMA_DISABLED)
+ break;
+
+ udelay(1);
+ }
+
+ if (timeout == DMA_TIMEOUT_VAL) {
+ netdev_warn(priv->dev,
+ "Timed out while disabling RX DMA\n");
+ ret = -ETIMEDOUT;
+ }
+
+ return ret;
+}
+
+static int bcmgenet_close(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ int ret;
+ u32 reg;
+
+ netif_dbg(priv, ifdown, dev, "bcmgenet_close\n");
+
+ phy_stop(priv->phydev);
+
+ /* Disable MAC receive */
+ reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+ reg &= ~CMD_RX_EN;
+ bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+
+ netif_tx_stop_all_queues(dev);
+
+ ret = bcmgenet_dma_teardown(priv);
+ if (ret)
+ return ret;
+
+ /* Disable MAC transmit. TX DMA disabled have to done before this */
+ reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+ reg &= ~CMD_TX_EN;
+ bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+
+ napi_disable(&priv->napi);
+
+ /* tx reclaim */
+ bcmgenet_tx_reclaim_all(dev);
+ bcmgenet_fini_dma(priv);
+
+ free_irq(priv->irq0, priv);
+ free_irq(priv->irq1, priv);
+
+ /* Wait for pending work items to complete - we are stopping
+ * the clock now. Since interrupts are disabled, no new work
+ * will be scheduled.
+ */
+ cancel_work_sync(&priv->bcmgenet_irq_work);
+
+ if (phy_is_internal(priv->phydev))
+ bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
+
+ if (priv->wol_enabled)
+ clk_enable(priv->clk_wol);
+
+ if (!IS_ERR(priv->clk))
+ clk_disable_unprepare(priv->clk);
+
+ return 0;
+}
+
+static void bcmgenet_timeout(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
+ netif_dbg(priv, tx_err, dev, "bcmgenet_timeout\n");
+
+ dev->trans_start = jiffies;
+
+ dev->stats.tx_errors++;
+
+ netif_tx_wake_all_queues(dev);
+}
+
+#define MAX_MC_COUNT 16
+
+static inline void bcmgenet_set_mdf_addr(struct bcmgenet_priv *priv,
+ unsigned char *addr,
+ int *i,
+ int *mc)
+{
+ u32 reg;
+
+ bcmgenet_umac_writel(priv,
+ addr[0] << 8 | addr[1], UMAC_MDF_ADDR + (*i * 4));
+ bcmgenet_umac_writel(priv,
+ addr[2] << 24 | addr[3] << 16 |
+ addr[4] << 8 | addr[5],
+ UMAC_MDF_ADDR + ((*i + 1) * 4));
+ reg = bcmgenet_umac_readl(priv, UMAC_MDF_CTRL);
+ reg |= (1 << (MAX_MC_COUNT - *mc));
+ bcmgenet_umac_writel(priv, reg, UMAC_MDF_CTRL);
+ *i += 2;
+ (*mc)++;
+}
+
+static void bcmgenet_set_rx_mode(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ struct netdev_hw_addr *ha;
+ int i, mc;
+ u32 reg;
+
+ netif_dbg(priv, hw, dev, "%s: %08X\n", __func__, dev->flags);
+
+ /* Promiscous mode */
+ reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+ if (dev->flags & IFF_PROMISC) {
+ reg |= CMD_PROMISC;
+ bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+ bcmgenet_umac_writel(priv, 0, UMAC_MDF_CTRL);
+ return;
+ } else {
+ reg &= ~CMD_PROMISC;
+ bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+ }
+
+ /* UniMac doesn't support ALLMULTI */
+ if (dev->flags & IFF_ALLMULTI) {
+ netdev_warn(dev, "ALLMULTI is not supported\n");
+ return;
+ }
+
+ /* update MDF filter */
+ i = 0;
+ mc = 0;
+ /* Broadcast */
+ bcmgenet_set_mdf_addr(priv, dev->broadcast, &i, &mc);
+ /* my own address.*/
+ bcmgenet_set_mdf_addr(priv, dev->dev_addr, &i, &mc);
+ /* Unicast list*/
+ if (netdev_uc_count(dev) > (MAX_MC_COUNT - mc))
+ return;
+
+ if (!netdev_uc_empty(dev))
+ netdev_for_each_uc_addr(ha, dev)
+ bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc);
+ /* Multicast */
+ if (netdev_mc_empty(dev) || netdev_mc_count(dev) >= (MAX_MC_COUNT - mc))
+ return;
+
+ netdev_for_each_mc_addr(ha, dev)
+ bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc);
+}
+
+/* Set the hardware MAC address. */
+static int bcmgenet_set_mac_addr(struct net_device *dev, void *p)
+{
+ struct sockaddr *addr = p;
+
+ /* Setting the MAC address at the hardware level is not possible
+ * without disabling the UniMAC RX/TX enable bits.
+ */
+ if (netif_running(dev))
+ return -EBUSY;
+
+ ether_addr_copy(dev->dev_addr, addr->sa_data);
+
+ return 0;
+}
+
+static const struct net_device_ops bcmgenet_netdev_ops = {
+ .ndo_open = bcmgenet_open,
+ .ndo_stop = bcmgenet_close,
+ .ndo_start_xmit = bcmgenet_xmit,
+ .ndo_tx_timeout = bcmgenet_timeout,
+ .ndo_set_rx_mode = bcmgenet_set_rx_mode,
+ .ndo_set_mac_address = bcmgenet_set_mac_addr,
+ .ndo_do_ioctl = bcmgenet_ioctl,
+ .ndo_set_features = bcmgenet_set_features,
+};
+
+/* Array of GENET hardware parameters/characteristics */
+static struct bcmgenet_hw_params bcmgenet_hw_params[] = {
+ [GENET_V1] = {
+ .tx_queues = 0,
+ .rx_queues = 0,
+ .bds_cnt = 0,
+ .bp_in_en_shift = 16,
+ .bp_in_mask = 0xffff,
+ .hfb_filter_cnt = 16,
+ .qtag_mask = 0x1F,
+ .hfb_offset = 0x1000,
+ .rdma_offset = 0x2000,
+ .tdma_offset = 0x3000,
+ .words_per_bd = 2,
+ },
+ [GENET_V2] = {
+ .tx_queues = 4,
+ .rx_queues = 4,
+ .bds_cnt = 32,
+ .bp_in_en_shift = 16,
+ .bp_in_mask = 0xffff,
+ .hfb_filter_cnt = 16,
+ .qtag_mask = 0x1F,
+ .tbuf_offset = 0x0600,
+ .hfb_offset = 0x1000,
+ .hfb_reg_offset = 0x2000,
+ .rdma_offset = 0x3000,
+ .tdma_offset = 0x4000,
+ .words_per_bd = 2,
+ .flags = GENET_HAS_EXT,
+ },
+ [GENET_V3] = {
+ .tx_queues = 4,
+ .rx_queues = 4,
+ .bds_cnt = 32,
+ .bp_in_en_shift = 17,
+ .bp_in_mask = 0x1ffff,
+ .hfb_filter_cnt = 48,
+ .qtag_mask = 0x3F,
+ .tbuf_offset = 0x0600,
+ .hfb_offset = 0x8000,
+ .hfb_reg_offset = 0xfc00,
+ .rdma_offset = 0x10000,
+ .tdma_offset = 0x11000,
+ .words_per_bd = 2,
+ .flags = GENET_HAS_EXT | GENET_HAS_MDIO_INTR,
+ },
+ [GENET_V4] = {
+ .tx_queues = 4,
+ .rx_queues = 4,
+ .bds_cnt = 32,
+ .bp_in_en_shift = 17,
+ .bp_in_mask = 0x1ffff,
+ .hfb_filter_cnt = 48,
+ .qtag_mask = 0x3F,
+ .tbuf_offset = 0x0600,
+ .hfb_offset = 0x8000,
+ .hfb_reg_offset = 0xfc00,
+ .rdma_offset = 0x2000,
+ .tdma_offset = 0x4000,
+ .words_per_bd = 3,
+ .flags = GENET_HAS_40BITS | GENET_HAS_EXT | GENET_HAS_MDIO_INTR,
+ },
+};
+
+/* Infer hardware parameters from the detected GENET version */
+static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
+{
+ struct bcmgenet_hw_params *params;
+ u32 reg;
+ u8 major;
+
+ if (GENET_IS_V4(priv)) {
+ bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
+ genet_dma_ring_regs = genet_dma_ring_regs_v4;
+ priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS;
+ priv->version = GENET_V4;
+ } else if (GENET_IS_V3(priv)) {
+ bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
+ genet_dma_ring_regs = genet_dma_ring_regs_v123;
+ priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS;
+ priv->version = GENET_V3;
+ } else if (GENET_IS_V2(priv)) {
+ bcmgenet_dma_regs = bcmgenet_dma_regs_v2;
+ genet_dma_ring_regs = genet_dma_ring_regs_v123;
+ priv->dma_rx_chk_bit = DMA_RX_CHK_V12;
+ priv->version = GENET_V2;
+ } else if (GENET_IS_V1(priv)) {
+ bcmgenet_dma_regs = bcmgenet_dma_regs_v1;
+ genet_dma_ring_regs = genet_dma_ring_regs_v123;
+ priv->dma_rx_chk_bit = DMA_RX_CHK_V12;
+ priv->version = GENET_V1;
+ }
+
+ /* enum genet_version starts at 1 */
+ priv->hw_params = &bcmgenet_hw_params[priv->version];
+ params = priv->hw_params;
+
+ /* Read GENET HW version */
+ reg = bcmgenet_sys_readl(priv, SYS_REV_CTRL);
+ major = (reg >> 24 & 0x0f);
+ if (major == 5)
+ major = 4;
+ else if (major == 0)
+ major = 1;
+ if (major != priv->version) {
+ dev_err(&priv->pdev->dev,
+ "GENET version mismatch, got: %d, configured for: %d\n",
+ major, priv->version);
+ }
+
+ /* Print the GENET core version */
+ dev_info(&priv->pdev->dev, "GENET " GENET_VER_FMT,
+ major, (reg >> 16) & 0x0f, reg & 0xffff);
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+ if (!(params->flags & GENET_HAS_40BITS))
+ pr_warn("GENET does not support 40-bits PA\n");
+#endif
+
+ pr_debug("Configuration for version: %d\n"
+ "TXq: %1d, RXq: %1d, BDs: %1d\n"
+ "BP << en: %2d, BP msk: 0x%05x\n"
+ "HFB count: %2d, QTAQ msk: 0x%05x\n"
+ "TBUF: 0x%04x, HFB: 0x%04x, HFBreg: 0x%04x\n"
+ "RDMA: 0x%05x, TDMA: 0x%05x\n"
+ "Words/BD: %d\n",
+ priv->version,
+ params->tx_queues, params->rx_queues, params->bds_cnt,
+ params->bp_in_en_shift, params->bp_in_mask,
+ params->hfb_filter_cnt, params->qtag_mask,
+ params->tbuf_offset, params->hfb_offset,
+ params->hfb_reg_offset,
+ params->rdma_offset, params->tdma_offset,
+ params->words_per_bd);
+}
+
+static const struct of_device_id bcmgenet_match[] = {
+ { .compatible = "brcm,genet-v1", .data = (void *)GENET_V1 },
+ { .compatible = "brcm,genet-v2", .data = (void *)GENET_V2 },
+ { .compatible = "brcm,genet-v3", .data = (void *)GENET_V3 },
+ { .compatible = "brcm,genet-v4", .data = (void *)GENET_V4 },
+ { },
+};
+
+static int bcmgenet_probe(struct platform_device *pdev)
+{
+ struct device_node *dn = pdev->dev.of_node;
+ const struct of_device_id *of_id;
+ struct bcmgenet_priv *priv;
+ struct net_device *dev;
+ const void *macaddr;
+ struct resource *r;
+ int err = -EIO;
+
+ /* Up to GENET_MAX_MQ_CNT + 1 TX queues and a single RX queue */
+ dev = alloc_etherdev_mqs(sizeof(*priv), GENET_MAX_MQ_CNT + 1, 1);
+ if (!dev) {
+ dev_err(&pdev->dev, "can't allocate net device\n");
+ return -ENOMEM;
+ }
+
+ of_id = of_match_node(bcmgenet_match, dn);
+ if (!of_id)
+ return -EINVAL;
+
+ priv = netdev_priv(dev);
+ priv->irq0 = platform_get_irq(pdev, 0);
+ priv->irq1 = platform_get_irq(pdev, 1);
+ if (!priv->irq0 || !priv->irq1) {
+ dev_err(&pdev->dev, "can't find IRQs\n");
+ err = -EINVAL;
+ goto err;
+ }
+
+ macaddr = of_get_mac_address(dn);
+ if (!macaddr) {
+ dev_err(&pdev->dev, "can't find MAC address\n");
+ err = -EINVAL;
+ goto err;
+ }
+
+ r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ priv->base = devm_ioremap_resource(&pdev->dev, r);
+ if (IS_ERR(priv->base)) {
+ err = PTR_ERR(priv->base);
+ goto err;
+ }
+
+ SET_NETDEV_DEV(dev, &pdev->dev);
+ dev_set_drvdata(&pdev->dev, dev);
+ ether_addr_copy(dev->dev_addr, macaddr);
+ dev->watchdog_timeo = 2 * HZ;
+ SET_ETHTOOL_OPS(dev, &bcmgenet_ethtool_ops);
+ dev->netdev_ops = &bcmgenet_netdev_ops;
+ netif_napi_add(dev, &priv->napi, bcmgenet_poll, 64);
+
+ priv->msg_enable = netif_msg_init(-1, GENET_MSG_DEFAULT);
+
+ /* Set hardware features */
+ dev->hw_features |= NETIF_F_SG | NETIF_F_IP_CSUM |
+ NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM;
+
+ /* Set the needed headroom to account for any possible
+ * features enabling/disabling at runtime
+ */
+ dev->needed_headroom += 64;
+
+ netdev_boot_setup_check(dev);
+
+ priv->dev = dev;
+ priv->pdev = pdev;
+ priv->version = (enum bcmgenet_version)of_id->data;
+
+ bcmgenet_set_hw_params(priv);
+
+ /* Mii wait queue */
+ init_waitqueue_head(&priv->wq);
+ /* Always use RX_BUF_LENGTH (2KB) buffer for all chips */
+ priv->rx_buf_len = RX_BUF_LENGTH;
+ INIT_WORK(&priv->bcmgenet_irq_work, bcmgenet_irq_task);
+
+ priv->clk = devm_clk_get(&priv->pdev->dev, "enet");
+ if (IS_ERR(priv->clk))
+ dev_warn(&priv->pdev->dev, "failed to get enet clock\n");
+
+ priv->clk_wol = devm_clk_get(&priv->pdev->dev, "enet-wol");
+ if (IS_ERR(priv->clk_wol))
+ dev_warn(&priv->pdev->dev, "failed to get enet-wol clock\n");
+
+ if (!IS_ERR(priv->clk))
+ clk_prepare_enable(priv->clk);
+
+ err = reset_umac(priv);
+ if (err)
+ goto err_clk_disable;
+
+ err = bcmgenet_mii_init(dev);
+ if (err)
+ goto err_clk_disable;
+
+ /* setup number of real queues + 1 (GENET_V1 has 0 hardware queues
+ * just the ring 16 descriptor based TX
+ */
+ netif_set_real_num_tx_queues(priv->dev, priv->hw_params->tx_queues + 1);
+ netif_set_real_num_rx_queues(priv->dev, priv->hw_params->rx_queues + 1);
+
+ err = register_netdev(dev);
+ if (err)
+ goto err_clk_disable;
+
+ /* Turn off the main clock, WOL clock is handled separately */
+ if (!IS_ERR(priv->clk))
+ clk_disable_unprepare(priv->clk);
+
+ return err;
+
+err_clk_disable:
+ if (!IS_ERR(priv->clk))
+ clk_disable_unprepare(priv->clk);
+err:
+ free_netdev(dev);
+ return err;
+}
+
+static int bcmgenet_remove(struct platform_device *pdev)
+{
+ struct bcmgenet_priv *priv = dev_to_priv(&pdev->dev);
+
+ dev_set_drvdata(&pdev->dev, NULL);
+ unregister_netdev(priv->dev);
+ bcmgenet_mii_exit(priv->dev);
+ free_netdev(priv->dev);
+
+ return 0;
+}
+
+
+static struct platform_driver bcmgenet_driver = {
+ .probe = bcmgenet_probe,
+ .remove = bcmgenet_remove,
+ .driver = {
+ .name = "bcmgenet",
+ .owner = THIS_MODULE,
+ .of_match_table = bcmgenet_match,
+ },
+};
+module_platform_driver(bcmgenet_driver);
+
+MODULE_AUTHOR("Broadcom Corporation");
+MODULE_DESCRIPTION("Broadcom GENET Ethernet controller driver");
+MODULE_ALIAS("platform:bcmgenet");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
new file mode 100644
index 0000000..0f11710
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -0,0 +1,628 @@
+/*
+ * Copyright (c) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ *
+*/
+#ifndef __BCMGENET_H__
+#define __BCMGENET_H__
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/spinlock.h>
+#include <linux/clk.h>
+#include <linux/mii.h>
+#include <linux/if_vlan.h>
+#include <linux/phy.h>
+
+/* total number of Buffer Descriptors, same for Rx/Tx */
+#define TOTAL_DESC 256
+
+/* which ring is descriptor based */
+#define DESC_INDEX 16
+
+/* Body(1500) + EH_SIZE(14) + VLANTAG(4) + BRCMTAG(6) + FCS(4) = 1528.
+ * 1536 is multiple of 256 bytes
+ */
+#define ENET_BRCM_TAG_LEN 6
+#define ENET_PAD 8
+#define ENET_MAX_MTU_SIZE (ETH_DATA_LEN + ETH_HLEN + VLAN_HLEN + \
+ ENET_BRCM_TAG_LEN + ETH_FCS_LEN + ENET_PAD)
+#define DMA_MAX_BURST_LENGTH 0x10
+
+/* misc. configuration */
+#define CLEAR_ALL_HFB 0xFF
+#define DMA_FC_THRESH_HI (TOTAL_DESC >> 4)
+#define DMA_FC_THRESH_LO 5
+
+/* 64B receive/transmit status block */
+struct status_64 {
+ u32 length_status; /* length and peripheral status */
+ u32 ext_status; /* Extended status*/
+ u32 rx_csum; /* partial rx checksum */
+ u32 unused1[9]; /* unused */
+ u32 tx_csum_info; /* Tx checksum info. */
+ u32 unused2[3]; /* unused */
+};
+
+/* Rx status bits */
+#define STATUS_RX_EXT_MASK 0x1FFFFF
+#define STATUS_RX_CSUM_MASK 0xFFFF
+#define STATUS_RX_CSUM_OK 0x10000
+#define STATUS_RX_CSUM_FR 0x20000
+#define STATUS_RX_PROTO_TCP 0
+#define STATUS_RX_PROTO_UDP 1
+#define STATUS_RX_PROTO_ICMP 2
+#define STATUS_RX_PROTO_OTHER 3
+#define STATUS_RX_PROTO_MASK 3
+#define STATUS_RX_PROTO_SHIFT 18
+#define STATUS_FILTER_INDEX_MASK 0xFFFF
+/* Tx status bits */
+#define STATUS_TX_CSUM_START_MASK 0X7FFF
+#define STATUS_TX_CSUM_START_SHIFT 16
+#define STATUS_TX_CSUM_PROTO_UDP 0x8000
+#define STATUS_TX_CSUM_OFFSET_MASK 0x7FFF
+#define STATUS_TX_CSUM_LV 0x80000000
+
+/* DMA Descriptor */
+#define DMA_DESC_LENGTH_STATUS 0x00 /* in bytes of data in buffer */
+#define DMA_DESC_ADDRESS_LO 0x04 /* lower bits of PA */
+#define DMA_DESC_ADDRESS_HI 0x08 /* upper 32 bits of PA, GENETv4+ */
+
+/* Rx/Tx common counter group */
+struct bcmgenet_pkt_counters {
+ u32 cnt_64; /* RO Received/Transmited 64 bytes packet */
+ u32 cnt_127; /* RO Rx/Tx 127 bytes packet */
+ u32 cnt_255; /* RO Rx/Tx 65-255 bytes packet */
+ u32 cnt_511; /* RO Rx/Tx 256-511 bytes packet */
+ u32 cnt_1023; /* RO Rx/Tx 512-1023 bytes packet */
+ u32 cnt_1518; /* RO Rx/Tx 1024-1518 bytes packet */
+ u32 cnt_mgv; /* RO Rx/Tx 1519-1522 good VLAN packet */
+ u32 cnt_2047; /* RO Rx/Tx 1522-2047 bytes packet*/
+ u32 cnt_4095; /* RO Rx/Tx 2048-4095 bytes packet*/
+ u32 cnt_9216; /* RO Rx/Tx 4096-9216 bytes packet*/
+};
+
+/* RSV, Receive Status Vector */
+struct bcmgenet_rx_counters {
+ struct bcmgenet_pkt_counters pkt_cnt;
+ u32 pkt; /* RO (0x428) Received pkt count*/
+ u32 bytes; /* RO Received byte count */
+ u32 mca; /* RO # of Received multicast pkt */
+ u32 bca; /* RO # of Receive broadcast pkt */
+ u32 fcs; /* RO # of Received FCS error */
+ u32 cf; /* RO # of Received control frame pkt*/
+ u32 pf; /* RO # of Received pause frame pkt */
+ u32 uo; /* RO # of unknown op code pkt */
+ u32 aln; /* RO # of alignment error count */
+ u32 flr; /* RO # of frame length out of range count */
+ u32 cde; /* RO # of code error pkt */
+ u32 fcr; /* RO # of carrier sense error pkt */
+ u32 ovr; /* RO # of oversize pkt*/
+ u32 jbr; /* RO # of jabber count */
+ u32 mtue; /* RO # of MTU error pkt*/
+ u32 pok; /* RO # of Received good pkt */
+ u32 uc; /* RO # of unicast pkt */
+ u32 ppp; /* RO # of PPP pkt */
+ u32 rcrc; /* RO (0x470),# of CRC match pkt */
+};
+
+/* TSV, Transmit Status Vector */
+struct bcmgenet_tx_counters {
+ struct bcmgenet_pkt_counters pkt_cnt;
+ u32 pkts; /* RO (0x4a8) Transmited pkt */
+ u32 mca; /* RO # of xmited multicast pkt */
+ u32 bca; /* RO # of xmited broadcast pkt */
+ u32 pf; /* RO # of xmited pause frame count */
+ u32 cf; /* RO # of xmited control frame count */
+ u32 fcs; /* RO # of xmited FCS error count */
+ u32 ovr; /* RO # of xmited oversize pkt */
+ u32 drf; /* RO # of xmited deferral pkt */
+ u32 edf; /* RO # of xmited Excessive deferral pkt*/
+ u32 scl; /* RO # of xmited single collision pkt */
+ u32 mcl; /* RO # of xmited multiple collision pkt*/
+ u32 lcl; /* RO # of xmited late collision pkt */
+ u32 ecl; /* RO # of xmited excessive collision pkt*/
+ u32 frg; /* RO # of xmited fragments pkt*/
+ u32 ncl; /* RO # of xmited total collision count */
+ u32 jbr; /* RO # of xmited jabber count*/
+ u32 bytes; /* RO # of xmited byte count */
+ u32 pok; /* RO # of xmited good pkt */
+ u32 uc; /* RO (0x0x4f0)# of xmited unitcast pkt */
+};
+
+struct bcmgenet_mib_counters {
+ struct bcmgenet_rx_counters rx;
+ struct bcmgenet_tx_counters tx;
+ u32 rx_runt_cnt;
+ u32 rx_runt_fcs;
+ u32 rx_runt_fcs_align;
+ u32 rx_runt_bytes;
+ u32 rbuf_ovflow_cnt;
+ u32 rbuf_err_cnt;
+ u32 mdf_err_cnt;
+};
+
+#define UMAC_HD_BKP_CTRL 0x004
+#define HD_FC_EN (1 << 0)
+#define HD_FC_BKOFF_OK (1 << 1)
+#define IPG_CONFIG_RX_SHIFT 2
+#define IPG_CONFIG_RX_MASK 0x1F
+
+#define UMAC_CMD 0x008
+#define CMD_TX_EN (1 << 0)
+#define CMD_RX_EN (1 << 1)
+#define UMAC_SPEED_10 0
+#define UMAC_SPEED_100 1
+#define UMAC_SPEED_1000 2
+#define UMAC_SPEED_2500 3
+#define CMD_SPEED_SHIFT 2
+#define CMD_SPEED_MASK 3
+#define CMD_PROMISC (1 << 4)
+#define CMD_PAD_EN (1 << 5)
+#define CMD_CRC_FWD (1 << 6)
+#define CMD_PAUSE_FWD (1 << 7)
+#define CMD_RX_PAUSE_IGNORE (1 << 8)
+#define CMD_TX_ADDR_INS (1 << 9)
+#define CMD_HD_EN (1 << 10)
+#define CMD_SW_RESET (1 << 13)
+#define CMD_LCL_LOOP_EN (1 << 15)
+#define CMD_AUTO_CONFIG (1 << 22)
+#define CMD_CNTL_FRM_EN (1 << 23)
+#define CMD_NO_LEN_CHK (1 << 24)
+#define CMD_RMT_LOOP_EN (1 << 25)
+#define CMD_PRBL_EN (1 << 27)
+#define CMD_TX_PAUSE_IGNORE (1 << 28)
+#define CMD_TX_RX_EN (1 << 29)
+#define CMD_RUNT_FILTER_DIS (1 << 30)
+
+#define UMAC_MAC0 0x00C
+#define UMAC_MAC1 0x010
+#define UMAC_MAX_FRAME_LEN 0x014
+
+#define UMAC_TX_FLUSH 0x334
+
+#define UMAC_MIB_START 0x400
+
+#define UMAC_MDIO_CMD 0x614
+#define MDIO_START_BUSY (1 << 29)
+#define MDIO_READ_FAIL (1 << 28)
+#define MDIO_RD (2 << 26)
+#define MDIO_WR (1 << 26)
+#define MDIO_PMD_SHIFT 21
+#define MDIO_PMD_MASK 0x1F
+#define MDIO_REG_SHIFT 16
+#define MDIO_REG_MASK 0x1F
+
+#define UMAC_RBUF_OVFL_CNT 0x61C
+
+#define UMAC_MPD_CTRL 0x620
+#define MPD_EN (1 << 0)
+#define MPD_PW_EN (1 << 27)
+#define MPD_MSEQ_LEN_SHIFT 16
+#define MPD_MSEQ_LEN_MASK 0xFF
+
+#define UMAC_MPD_PW_MS 0x624
+#define UMAC_MPD_PW_LS 0x628
+#define UMAC_RBUF_ERR_CNT 0x634
+#define UMAC_MDF_ERR_CNT 0x638
+#define UMAC_MDF_CTRL 0x650
+#define UMAC_MDF_ADDR 0x654
+#define UMAC_MIB_CTRL 0x580
+#define MIB_RESET_RX (1 << 0)
+#define MIB_RESET_RUNT (1 << 1)
+#define MIB_RESET_TX (1 << 2)
+
+#define RBUF_CTRL 0x00
+#define RBUF_64B_EN (1 << 0)
+#define RBUF_ALIGN_2B (1 << 1)
+#define RBUF_BAD_DIS (1 << 2)
+
+#define RBUF_STATUS 0x0C
+#define RBUF_STATUS_WOL (1 << 0)
+#define RBUF_STATUS_MPD_INTR_ACTIVE (1 << 1)
+#define RBUF_STATUS_ACPI_INTR_ACTIVE (1 << 2)
+
+#define RBUF_CHK_CTRL 0x14
+#define RBUF_RXCHK_EN (1 << 0)
+#define RBUF_SKIP_FCS (1 << 4)
+
+#define RBUF_TBUF_SIZE_CTRL 0xb4
+
+#define RBUF_HFB_CTRL_V1 0x38
+#define RBUF_HFB_FILTER_EN_SHIFT 16
+#define RBUF_HFB_FILTER_EN_MASK 0xffff0000
+#define RBUF_HFB_EN (1 << 0)
+#define RBUF_HFB_256B (1 << 1)
+#define RBUF_ACPI_EN (1 << 2)
+
+#define RBUF_HFB_LEN_V1 0x3C
+#define RBUF_FLTR_LEN_MASK 0xFF
+#define RBUF_FLTR_LEN_SHIFT 8
+
+#define TBUF_CTRL 0x00
+#define TBUF_BP_MC 0x0C
+
+#define TBUF_CTRL_V1 0x80
+#define TBUF_BP_MC_V1 0xA0
+
+#define HFB_CTRL 0x00
+#define HFB_FLT_ENABLE_V3PLUS 0x04
+#define HFB_FLT_LEN_V2 0x04
+#define HFB_FLT_LEN_V3PLUS 0x1C
+
+/* uniMac intrl2 registers */
+#define INTRL2_CPU_STAT 0x00
+#define INTRL2_CPU_SET 0x04
+#define INTRL2_CPU_CLEAR 0x08
+#define INTRL2_CPU_MASK_STATUS 0x0C
+#define INTRL2_CPU_MASK_SET 0x10
+#define INTRL2_CPU_MASK_CLEAR 0x14
+
+/* INTRL2 instance 0 definitions */
+#define UMAC_IRQ_SCB (1 << 0)
+#define UMAC_IRQ_EPHY (1 << 1)
+#define UMAC_IRQ_PHY_DET_R (1 << 2)
+#define UMAC_IRQ_PHY_DET_F (1 << 3)
+#define UMAC_IRQ_LINK_UP (1 << 4)
+#define UMAC_IRQ_LINK_DOWN (1 << 5)
+#define UMAC_IRQ_UMAC (1 << 6)
+#define UMAC_IRQ_UMAC_TSV (1 << 7)
+#define UMAC_IRQ_TBUF_UNDERRUN (1 << 8)
+#define UMAC_IRQ_RBUF_OVERFLOW (1 << 9)
+#define UMAC_IRQ_HFB_SM (1 << 10)
+#define UMAC_IRQ_HFB_MM (1 << 11)
+#define UMAC_IRQ_MPD_R (1 << 12)
+#define UMAC_IRQ_RXDMA_MBDONE (1 << 13)
+#define UMAC_IRQ_RXDMA_PDONE (1 << 14)
+#define UMAC_IRQ_RXDMA_BDONE (1 << 15)
+#define UMAC_IRQ_TXDMA_MBDONE (1 << 16)
+#define UMAC_IRQ_TXDMA_PDONE (1 << 17)
+#define UMAC_IRQ_TXDMA_BDONE (1 << 18)
+/* Only valid for GENETv3+ */
+#define UMAC_IRQ_MDIO_DONE (1 << 23)
+#define UMAC_IRQ_MDIO_ERROR (1 << 24)
+
+/* Register block offsets */
+#define GENET_SYS_OFF 0x0000
+#define GENET_GR_BRIDGE_OFF 0x0040
+#define GENET_EXT_OFF 0x0080
+#define GENET_INTRL2_0_OFF 0x0200
+#define GENET_INTRL2_1_OFF 0x0240
+#define GENET_RBUF_OFF 0x0300
+#define GENET_UMAC_OFF 0x0800
+
+/* SYS block offsets and register definitions */
+#define SYS_REV_CTRL 0x00
+#define SYS_PORT_CTRL 0x04
+#define PORT_MODE_INT_EPHY 0
+#define PORT_MODE_INT_GPHY 1
+#define PORT_MODE_EXT_EPHY 2
+#define PORT_MODE_EXT_GPHY 3
+#define PORT_MODE_EXT_RVMII_25 (4 | BIT(4))
+#define PORT_MODE_EXT_RVMII_50 4
+#define LED_ACT_SOURCE_MAC (1 << 9)
+
+#define SYS_RBUF_FLUSH_CTRL 0x08
+#define SYS_TBUF_FLUSH_CTRL 0x0C
+#define RBUF_FLUSH_CTRL_V1 0x04
+
+/* Ext block register offsets and definitions */
+#define EXT_EXT_PWR_MGMT 0x00
+#define EXT_PWR_DOWN_BIAS (1 << 0)
+#define EXT_PWR_DOWN_DLL (1 << 1)
+#define EXT_PWR_DOWN_PHY (1 << 2)
+#define EXT_PWR_DN_EN_LD (1 << 3)
+#define EXT_ENERGY_DET (1 << 4)
+#define EXT_IDDQ_FROM_PHY (1 << 5)
+#define EXT_PHY_RESET (1 << 8)
+#define EXT_ENERGY_DET_MASK (1 << 12)
+
+#define EXT_RGMII_OOB_CTRL 0x0C
+#define RGMII_MODE_EN (1 << 0)
+#define RGMII_LINK (1 << 4)
+#define OOB_DISABLE (1 << 5)
+#define ID_MODE_DIS (1 << 16)
+
+#define EXT_GPHY_CTRL 0x1C
+#define EXT_CFG_IDDQ_BIAS (1 << 0)
+#define EXT_CFG_PWR_DOWN (1 << 1)
+#define EXT_GPHY_RESET (1 << 5)
+
+/* DMA rings size */
+#define DMA_RING_SIZE (0x40)
+#define DMA_RINGS_SIZE (DMA_RING_SIZE * (DESC_INDEX + 1))
+
+/* DMA registers common definitions */
+#define DMA_RW_POINTER_MASK 0x1FF
+#define DMA_P_INDEX_DISCARD_CNT_MASK 0xFFFF
+#define DMA_P_INDEX_DISCARD_CNT_SHIFT 16
+#define DMA_BUFFER_DONE_CNT_MASK 0xFFFF
+#define DMA_BUFFER_DONE_CNT_SHIFT 16
+#define DMA_P_INDEX_MASK 0xFFFF
+#define DMA_C_INDEX_MASK 0xFFFF
+
+/* DMA ring size register */
+#define DMA_RING_SIZE_MASK 0xFFFF
+#define DMA_RING_SIZE_SHIFT 16
+#define DMA_RING_BUFFER_SIZE_MASK 0xFFFF
+
+/* DMA interrupt threshold register */
+#define DMA_INTR_THRESHOLD_MASK 0x00FF
+
+/* DMA XON/XOFF register */
+#define DMA_XON_THREHOLD_MASK 0xFFFF
+#define DMA_XOFF_THRESHOLD_MASK 0xFFFF
+#define DMA_XOFF_THRESHOLD_SHIFT 16
+
+/* DMA flow period register */
+#define DMA_FLOW_PERIOD_MASK 0xFFFF
+#define DMA_MAX_PKT_SIZE_MASK 0xFFFF
+#define DMA_MAX_PKT_SIZE_SHIFT 16
+
+
+/* DMA control register */
+#define DMA_EN (1 << 0)
+#define DMA_RING_BUF_EN_SHIFT 0x01
+#define DMA_RING_BUF_EN_MASK 0xFFFF
+#define DMA_TSB_SWAP_EN (1 << 20)
+
+/* DMA status register */
+#define DMA_DISABLED (1 << 0)
+#define DMA_DESC_RAM_INIT_BUSY (1 << 1)
+
+/* DMA SCB burst size register */
+#define DMA_SCB_BURST_SIZE_MASK 0x1F
+
+/* DMA activity vector register */
+#define DMA_ACTIVITY_VECTOR_MASK 0x1FFFF
+
+/* DMA backpressure mask register */
+#define DMA_BACKPRESSURE_MASK 0x1FFFF
+#define DMA_PFC_ENABLE (1 << 31)
+
+/* DMA backpressure status register */
+#define DMA_BACKPRESSURE_STATUS_MASK 0x1FFFF
+
+/* DMA override register */
+#define DMA_LITTLE_ENDIAN_MODE (1 << 0)
+#define DMA_REGISTER_MODE (1 << 1)
+
+/* DMA timeout register */
+#define DMA_TIMEOUT_MASK 0xFFFF
+#define DMA_TIMEOUT_VAL 5000 /* micro seconds */
+
+/* TDMA rate limiting control register */
+#define DMA_RATE_LIMIT_EN_MASK 0xFFFF
+
+/* TDMA arbitration control register */
+#define DMA_ARBITER_MODE_MASK 0x03
+#define DMA_RING_BUF_PRIORITY_MASK 0x1F
+#define DMA_RING_BUF_PRIORITY_SHIFT 5
+#define DMA_RATE_ADJ_MASK 0xFF
+
+/* Tx/Rx Dma Descriptor common bits*/
+#define DMA_BUFLENGTH_MASK 0x0fff
+#define DMA_BUFLENGTH_SHIFT 16
+#define DMA_OWN 0x8000
+#define DMA_EOP 0x4000
+#define DMA_SOP 0x2000
+#define DMA_WRAP 0x1000
+/* Tx specific Dma descriptor bits */
+#define DMA_TX_UNDERRUN 0x0200
+#define DMA_TX_APPEND_CRC 0x0040
+#define DMA_TX_OW_CRC 0x0020
+#define DMA_TX_DO_CSUM 0x0010
+#define DMA_TX_QTAG_SHIFT 7
+
+/* Rx Specific Dma descriptor bits */
+#define DMA_RX_CHK_V3PLUS 0x8000
+#define DMA_RX_CHK_V12 0x1000
+#define DMA_RX_BRDCAST 0x0040
+#define DMA_RX_MULT 0x0020
+#define DMA_RX_LG 0x0010
+#define DMA_RX_NO 0x0008
+#define DMA_RX_RXER 0x0004
+#define DMA_RX_CRC_ERROR 0x0002
+#define DMA_RX_OV 0x0001
+#define DMA_RX_FI_MASK 0x001F
+#define DMA_RX_FI_SHIFT 0x0007
+#define DMA_DESC_ALLOC_MASK 0x00FF
+
+#define DMA_ARBITER_RR 0x00
+#define DMA_ARBITER_WRR 0x01
+#define DMA_ARBITER_SP 0x02
+
+struct enet_cb {
+ struct sk_buff *skb;
+ void __iomem *bd_addr;
+ DEFINE_DMA_UNMAP_ADDR(dma_addr);
+ DEFINE_DMA_UNMAP_LEN(dma_len);
+};
+
+/* power management mode */
+enum bcmgenet_power_mode {
+ GENET_POWER_CABLE_SENSE = 0,
+ GENET_POWER_PASSIVE,
+};
+
+struct bcmgenet_priv;
+
+/* We support both runtime GENET detection and compile-time
+ * to optimize code-paths for a given hardware
+ */
+enum bcmgenet_version {
+ GENET_V1 = 1,
+ GENET_V2,
+ GENET_V3,
+ GENET_V4
+};
+
+#define GENET_IS_V1(p) ((p)->version == GENET_V1)
+#define GENET_IS_V2(p) ((p)->version == GENET_V2)
+#define GENET_IS_V3(p) ((p)->version == GENET_V3)
+#define GENET_IS_V4(p) ((p)->version == GENET_V4)
+
+/* Hardware flags */
+#define GENET_HAS_40BITS (1 << 0)
+#define GENET_HAS_EXT (1 << 1)
+#define GENET_HAS_MDIO_INTR (1 << 2)
+
+/* BCMGENET hardware parameters, keep this structure nicely aligned
+ * since it is going to be used in hot paths
+ */
+struct bcmgenet_hw_params {
+ u8 tx_queues;
+ u8 rx_queues;
+ u8 bds_cnt;
+ u8 bp_in_en_shift;
+ u32 bp_in_mask;
+ u8 hfb_filter_cnt;
+ u8 qtag_mask;
+ u16 tbuf_offset;
+ u32 hfb_offset;
+ u32 hfb_reg_offset;
+ u32 rdma_offset;
+ u32 tdma_offset;
+ u32 words_per_bd;
+ u32 flags;
+};
+
+struct bcmgenet_tx_ring {
+ spinlock_t lock; /* ring lock */
+ unsigned int index; /* ring index */
+ unsigned int queue; /* queue index */
+ struct enet_cb *cbs; /* tx ring buffer control block*/
+ unsigned int size; /* size of each tx ring */
+ unsigned int c_index; /* last consumer index of each ring*/
+ unsigned int free_bds; /* # of free bds for each ring */
+ unsigned int write_ptr; /* Tx ring write pointer SW copy */
+ unsigned int prod_index; /* Tx ring producer index SW copy */
+ unsigned int cb_ptr; /* Tx ring initial CB ptr */
+ unsigned int end_ptr; /* Tx ring end CB ptr */
+ void (*int_enable)(struct bcmgenet_priv *priv,
+ struct bcmgenet_tx_ring *);
+ void (*int_disable)(struct bcmgenet_priv *priv,
+ struct bcmgenet_tx_ring *);
+};
+
+/* device context */
+struct bcmgenet_priv {
+ void __iomem *base;
+ enum bcmgenet_version version;
+ struct net_device *dev;
+ u32 int0_mask;
+ u32 int1_mask;
+
+ /* NAPI for descriptor based rx */
+ struct napi_struct napi ____cacheline_aligned;
+
+ /* transmit variables */
+ void __iomem *tx_bds;
+ struct enet_cb *tx_cbs;
+ unsigned int num_tx_bds;
+
+ struct bcmgenet_tx_ring tx_rings[DESC_INDEX + 1];
+
+ /* receive variables */
+ void __iomem *rx_bds;
+ void __iomem *rx_bd_assign_ptr;
+ int rx_bd_assign_index;
+ struct enet_cb *rx_cbs;
+ unsigned int num_rx_bds;
+ unsigned int rx_buf_len;
+ unsigned int rx_read_ptr;
+ unsigned int rx_c_index;
+
+ /* other misc variables */
+ struct bcmgenet_hw_params *hw_params;
+
+ /* MDIO bus variables */
+ wait_queue_head_t wq;
+ struct phy_device *phydev;
+ struct device_node *phy_dn;
+ struct mii_bus *mii_bus;
+
+ /* PHY device variables */
+ int old_duplex;
+ int old_link;
+ int old_pause;
+ phy_interface_t phy_interface;
+ int phy_addr;
+ int ext_phy;
+
+ /* Interrupt variables */
+ struct work_struct bcmgenet_irq_work;
+ int irq0;
+ int irq1;
+ unsigned int irq0_stat;
+ unsigned int irq1_stat;
+
+ /* HW descriptors/checksum variables */
+ bool desc_64b_en;
+ bool desc_rxchk_en;
+ bool crc_fwd_en;
+
+ unsigned int dma_rx_chk_bit;
+
+ u32 msg_enable;
+
+ struct clk *clk;
+ struct platform_device *pdev;
+
+ /* WOL */
+ unsigned long wol_enabled;
+ struct clk *clk_wol;
+ u32 wolopts;
+
+ struct bcmgenet_mib_counters mib;
+};
+
+#define GENET_IO_MACRO(name, offset) \
+static inline u32 bcmgenet_##name##_readl(struct bcmgenet_priv *priv, \
+ u32 off) \
+{ \
+ return __raw_readl(priv->base + offset + off); \
+} \
+static inline void bcmgenet_##name##_writel(struct bcmgenet_priv *priv, \
+ u32 val, u32 off) \
+{ \
+ __raw_writel(val, priv->base + offset + off); \
+}
+
+GENET_IO_MACRO(ext, GENET_EXT_OFF);
+GENET_IO_MACRO(umac, GENET_UMAC_OFF);
+GENET_IO_MACRO(sys, GENET_SYS_OFF);
+
+/* interrupt l2 registers accessors */
+GENET_IO_MACRO(intrl2_0, GENET_INTRL2_0_OFF);
+GENET_IO_MACRO(intrl2_1, GENET_INTRL2_1_OFF);
+
+/* HFB register accessors */
+GENET_IO_MACRO(hfb, priv->hw_params->hfb_offset);
+
+/* GENET v2+ HFB control and filter len helpers */
+GENET_IO_MACRO(hfb_reg, priv->hw_params->hfb_reg_offset);
+
+/* RBUF register accessors */
+GENET_IO_MACRO(rbuf, GENET_RBUF_OFF);
+
+/* MDIO routines */
+int bcmgenet_mii_init(struct net_device *dev);
+int bcmgenet_mii_config(struct net_device *dev);
+void bcmgenet_mii_exit(struct net_device *dev);
+void bcmgenet_mii_reset(struct net_device *dev);
+
+#endif /* __BCMGENET_H__ */
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
new file mode 100644
index 0000000..4608673
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -0,0 +1,464 @@
+/*
+ * Broadcom GENET MDIO routines
+ *
+ * Copyright (c) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ */
+
+
+#include <linux/types.h>
+#include <linux/delay.h>
+#include <linux/wait.h>
+#include <linux/mii.h>
+#include <linux/ethtool.h>
+#include <linux/bitops.h>
+#include <linux/netdevice.h>
+#include <linux/platform_device.h>
+#include <linux/phy.h>
+#include <linux/phy_fixed.h>
+#include <linux/brcmphy.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+#include <linux/of_mdio.h>
+
+#include "bcmgenet.h"
+
+/* read a value from the MII */
+static int bcmgenet_mii_read(struct mii_bus *bus, int phy_id, int location)
+{
+ int ret;
+ struct net_device *dev = bus->priv;
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ u32 reg;
+
+ bcmgenet_umac_writel(priv, (MDIO_RD | (phy_id << MDIO_PMD_SHIFT) |
+ (location << MDIO_REG_SHIFT)), UMAC_MDIO_CMD);
+ /* Start MDIO transaction*/
+ reg = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD);
+ reg |= MDIO_START_BUSY;
+ bcmgenet_umac_writel(priv, reg, UMAC_MDIO_CMD);
+ wait_event_timeout(priv->wq,
+ !(bcmgenet_umac_readl(priv, UMAC_MDIO_CMD)
+ & MDIO_START_BUSY),
+ HZ / 100);
+ ret = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD);
+
+ if (ret & MDIO_READ_FAIL)
+ return -EIO;
+
+ return ret & 0xffff;
+}
+
+/* write a value to the MII */
+static int bcmgenet_mii_write(struct mii_bus *bus, int phy_id,
+ int location, u16 val)
+{
+ struct net_device *dev = bus->priv;
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ u32 reg;
+
+ bcmgenet_umac_writel(priv, (MDIO_WR | (phy_id << MDIO_PMD_SHIFT) |
+ (location << MDIO_REG_SHIFT) | (0xffff & val)),
+ UMAC_MDIO_CMD);
+ reg = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD);
+ reg |= MDIO_START_BUSY;
+ bcmgenet_umac_writel(priv, reg, UMAC_MDIO_CMD);
+ wait_event_timeout(priv->wq,
+ !(bcmgenet_umac_readl(priv, UMAC_MDIO_CMD) &
+ MDIO_START_BUSY),
+ HZ / 100);
+
+ return 0;
+}
+
+/* setup netdev link state when PHY link status change and
+ * update UMAC and RGMII block when link up
+ */
+static void bcmgenet_mii_setup(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ struct phy_device *phydev = priv->phydev;
+ u32 reg, cmd_bits = 0;
+ unsigned int status_changed = 0;
+
+ if (priv->old_link != phydev->link) {
+ status_changed = 1;
+ priv->old_link = phydev->link;
+ }
+
+ if (phydev->link) {
+ /* program UMAC and RGMII block based on established link
+ * speed, pause, and duplex.
+ * the speed set in umac->cmd tell RGMII block which clock
+ * 25MHz(100Mbps)/125MHz(1Gbps) to use for transmit.
+ * receive clock is provided by PHY.
+ */
+ reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL);
+ reg &= ~OOB_DISABLE;
+ reg |= RGMII_LINK;
+ bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
+
+ /* speed */
+ if (phydev->speed == SPEED_1000)
+ cmd_bits = UMAC_SPEED_1000;
+ else if (phydev->speed == SPEED_100)
+ cmd_bits = UMAC_SPEED_100;
+ else
+ cmd_bits = UMAC_SPEED_10;
+ cmd_bits <<= CMD_SPEED_SHIFT;
+
+ if (priv->old_duplex != phydev->duplex) {
+ status_changed = 1;
+ priv->old_duplex = phydev->duplex;
+ }
+
+ /* duplex */
+ if (phydev->duplex != DUPLEX_FULL)
+ cmd_bits |= CMD_HD_EN;
+
+ if (priv->old_pause != phydev->pause) {
+ status_changed = 1;
+ priv->old_pause = phydev->pause;
+ }
+
+ /* pause capability */
+ if (!phydev->pause)
+ cmd_bits |= CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE;
+
+ reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+ reg &= ~((CMD_SPEED_MASK << CMD_SPEED_SHIFT) |
+ CMD_HD_EN |
+ CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE);
+ reg |= cmd_bits;
+ bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+ }
+
+ if (status_changed)
+ phy_print_status(phydev);
+}
+
+void bcmgenet_mii_reset(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
+ if (priv->phydev) {
+ phy_init_hw(priv->phydev);
+ phy_start_aneg(priv->phydev);
+ }
+}
+
+static void bcmgenet_ephy_power_up(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ u32 reg = 0;
+
+ /* EXT_GPHY_CTRL is only valid for GENETv4 and onward */
+ if (!GENET_IS_V4(priv))
+ return;
+
+ reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL);
+ reg &= ~(EXT_CFG_IDDQ_BIAS | EXT_CFG_PWR_DOWN);
+ reg |= EXT_GPHY_RESET;
+ bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
+ mdelay(2);
+
+ reg &= ~EXT_GPHY_RESET;
+ bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL);
+ udelay(20);
+}
+
+static void bcmgenet_internal_phy_setup(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ u32 reg;
+
+ /* Power up EPHY */
+ bcmgenet_ephy_power_up(dev);
+ /* enable APD */
+ reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
+ reg |= EXT_PWR_DN_EN_LD;
+ bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+ bcmgenet_mii_reset(dev);
+}
+
+static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
+{
+ u32 reg;
+
+ /* Speed settings are set in bcmgenet_mii_setup() */
+ reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL);
+ reg |= LED_ACT_SOURCE_MAC;
+ bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL);
+}
+
+int bcmgenet_mii_config(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ struct phy_device *phydev = priv->phydev;
+ struct device *kdev = &priv->pdev->dev;
+ const char *phy_name = NULL;
+ u32 id_mode_dis = 0;
+ u32 port_ctrl;
+ u32 reg;
+
+ priv->ext_phy = !phy_is_internal(priv->phydev) &&
+ (priv->phy_interface != PHY_INTERFACE_MODE_MOCA);
+
+ if (phy_is_internal(priv->phydev))
+ priv->phy_interface = PHY_INTERFACE_MODE_NA;
+
+ switch (priv->phy_interface) {
+ case PHY_INTERFACE_MODE_NA:
+ case PHY_INTERFACE_MODE_MOCA:
+ /* Irrespective of the actually configured PHY speed (100 or
+ * 1000) GENETv4 only has an internal GPHY so we will just end
+ * up masking the Gigabit features from what we support, not
+ * switching to the EPHY
+ */
+ if (GENET_IS_V4(priv))
+ port_ctrl = PORT_MODE_INT_GPHY;
+ else
+ port_ctrl = PORT_MODE_INT_EPHY;
+
+ bcmgenet_sys_writel(priv, port_ctrl, SYS_PORT_CTRL);
+
+ if (phy_is_internal(priv->phydev)) {
+ phy_name = "internal PHY";
+ bcmgenet_internal_phy_setup(dev);
+ } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
+ phy_name = "MoCA";
+ bcmgenet_moca_phy_setup(priv);
+ }
+ break;
+
+ case PHY_INTERFACE_MODE_MII:
+ phy_name = "external MII";
+ phydev->supported &= PHY_BASIC_FEATURES;
+ bcmgenet_sys_writel(priv,
+ PORT_MODE_EXT_EPHY, SYS_PORT_CTRL);
+ break;
+
+ case PHY_INTERFACE_MODE_REVMII:
+ phy_name = "external RvMII";
+ /* of_mdiobus_register took care of reading the 'max-speed'
+ * PHY property for us, effectively limiting the PHY supported
+ * capabilities, use that knowledge to also configure the
+ * Reverse MII interface correctly.
+ */
+ if ((priv->phydev->supported & PHY_BASIC_FEATURES) ==
+ PHY_BASIC_FEATURES)
+ port_ctrl = PORT_MODE_EXT_RVMII_25;
+ else
+ port_ctrl = PORT_MODE_EXT_RVMII_50;
+ bcmgenet_sys_writel(priv, port_ctrl, SYS_PORT_CTRL);
+ break;
+
+ case PHY_INTERFACE_MODE_RGMII:
+ /* RGMII_NO_ID: TXC transitions at the same time as TXD
+ * (requires PCB or receiver-side delay)
+ * RGMII: Add 2ns delay on TXC (90 degree shift)
+ *
+ * ID is implicitly disabled for 100Mbps (RG)MII operation.
+ */
+ id_mode_dis = BIT(16);
+ /* fall through */
+ case PHY_INTERFACE_MODE_RGMII_TXID:
+ if (id_mode_dis)
+ phy_name = "external RGMII (no delay)";
+ else
+ phy_name = "external RGMII (TX delay)";
+ reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL);
+ reg |= RGMII_MODE_EN | id_mode_dis;
+ bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
+ bcmgenet_sys_writel(priv,
+ PORT_MODE_EXT_GPHY, SYS_PORT_CTRL);
+ break;
+ default:
+ dev_err(kdev, "unknown phy mode: %d\n", priv->phy_interface);
+ return -EINVAL;
+ }
+
+ dev_info(kdev, "configuring instance for %s\n", phy_name);
+
+ return 0;
+}
+
+static int bcmgenet_mii_probe(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ struct phy_device *phydev;
+ unsigned int phy_flags;
+ int ret;
+
+ if (priv->phydev) {
+ pr_info("PHY already attached\n");
+ return 0;
+ }
+
+ if (priv->phy_dn)
+ phydev = of_phy_connect(dev, priv->phy_dn,
+ bcmgenet_mii_setup, 0,
+ priv->phy_interface);
+ else
+ phydev = of_phy_connect_fixed_link(dev,
+ bcmgenet_mii_setup,
+ priv->phy_interface);
+
+ if (!phydev) {
+ pr_err("could not attach to PHY\n");
+ return -ENODEV;
+ }
+
+ priv->old_link = -1;
+ priv->old_duplex = -1;
+ priv->old_pause = -1;
+ priv->phydev = phydev;
+
+ /* Configure port multiplexer based on what the probed PHY device since
+ * reading the 'max-speed' property determines the maximum supported
+ * PHY speed which is needed for bcmgenet_mii_config() to configure
+ * things appropriately.
+ */
+ ret = bcmgenet_mii_config(dev);
+ if (ret) {
+ phy_disconnect(priv->phydev);
+ return ret;
+ }
+
+ phy_flags = PHY_BRCM_100MBPS_WAR;
+
+ /* workarounds are only needed for 100Mpbs PHYs, and
+ * never on GENET V1 hardware
+ */
+ if ((phydev->supported & PHY_GBIT_FEATURES) || GENET_IS_V1(priv))
+ phy_flags = 0;
+
+ phydev->dev_flags |= phy_flags;
+ phydev->advertising = phydev->supported;
+
+ /* The internal PHY has its link interrupts routed to the
+ * Ethernet MAC ISRs
+ */
+ if (phy_is_internal(priv->phydev))
+ priv->mii_bus->irq[phydev->addr] = PHY_IGNORE_INTERRUPT;
+ else
+ priv->mii_bus->irq[phydev->addr] = PHY_POLL;
+
+ pr_info("attached PHY at address %d [%s]\n",
+ phydev->addr, phydev->drv->name);
+
+ return 0;
+}
+
+static int bcmgenet_mii_alloc(struct bcmgenet_priv *priv)
+{
+ struct mii_bus *bus;
+
+ if (priv->mii_bus)
+ return 0;
+
+ priv->mii_bus = mdiobus_alloc();
+ if (!priv->mii_bus) {
+ pr_err("failed to allocate\n");
+ return -ENOMEM;
+ }
+
+ bus = priv->mii_bus;
+ bus->priv = priv->dev;
+ bus->name = "bcmgenet MII bus";
+ bus->parent = &priv->pdev->dev;
+ bus->read = bcmgenet_mii_read;
+ bus->write = bcmgenet_mii_write;
+ snprintf(bus->id, MII_BUS_ID_SIZE, "%s-%d",
+ priv->pdev->name, priv->pdev->id);
+
+ bus->irq = kzalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL);
+ if (!bus->irq) {
+ mdiobus_free(priv->mii_bus);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv)
+{
+ struct device_node *dn = priv->pdev->dev.of_node;
+ struct device *kdev = &priv->pdev->dev;
+ struct device_node *mdio_dn;
+ char *compat;
+ int ret;
+
+ compat = kasprintf(GFP_KERNEL, "brcm,genet-mdio-v%d", priv->version);
+ if (!compat)
+ return -ENOMEM;
+
+ mdio_dn = of_find_compatible_node(dn, NULL, compat);
+ kfree(compat);
+ if (!mdio_dn) {
+ dev_err(kdev, "unable to find MDIO bus node\n");
+ return -ENODEV;
+ }
+
+ ret = of_mdiobus_register(priv->mii_bus, mdio_dn);
+ if (ret) {
+ dev_err(kdev, "failed to register MDIO bus\n");
+ return ret;
+ }
+
+ /* Fetch the PHY phandle */
+ priv->phy_dn = of_parse_phandle(dn, "phy-handle", 0);
+
+ /* Get the link mode */
+ priv->phy_interface = of_get_phy_mode(dn);
+
+ return 0;
+}
+
+int bcmgenet_mii_init(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ int ret;
+
+ ret = bcmgenet_mii_alloc(priv);
+ if (ret)
+ return ret;
+
+ ret = bcmgenet_mii_of_init(priv);
+ if (ret)
+ goto out_free;
+
+ ret = bcmgenet_mii_probe(dev);
+ if (ret)
+ goto out;
+
+ return 0;
+
+out:
+ mdiobus_unregister(priv->mii_bus);
+out_free:
+ kfree(priv->mii_bus->irq);
+ mdiobus_free(priv->mii_bus);
+ return ret;
+}
+
+void bcmgenet_mii_exit(struct net_device *dev)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
+ mdiobus_unregister(priv->mii_bus);
+ kfree(priv->mii_bus->irq);
+ mdiobus_free(priv->mii_bus);
+}
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index e2ca03e..b9f7022 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -1401,11 +1401,6 @@
return ret;
}
-static int tg3_mdio_reset(struct mii_bus *bp)
-{
- return 0;
-}
-
static void tg3_mdio_config_5785(struct tg3 *tp)
{
u32 val;
@@ -1542,7 +1537,6 @@
tp->mdio_bus->parent = &tp->pdev->dev;
tp->mdio_bus->read = &tg3_mdio_read;
tp->mdio_bus->write = &tg3_mdio_write;
- tp->mdio_bus->reset = &tg3_mdio_reset;
tp->mdio_bus->phy_mask = ~(1 << tp->phy_addr);
tp->mdio_bus->irq = &tp->mdio_irq[0];
@@ -2609,13 +2603,14 @@
tg3_writephy(tp, MII_CTRL1000, phy9_orig);
- if (!tg3_readphy(tp, MII_TG3_EXT_CTRL, ®32)) {
- reg32 &= ~0x3000;
- tg3_writephy(tp, MII_TG3_EXT_CTRL, reg32);
- } else if (!err)
- err = -EBUSY;
+ err = tg3_readphy(tp, MII_TG3_EXT_CTRL, ®32);
+ if (err)
+ return err;
- return err;
+ reg32 &= ~0x3000;
+ tg3_writephy(tp, MII_TG3_EXT_CTRL, reg32);
+
+ return 0;
}
static void tg3_carrier_off(struct tg3 *tp)
@@ -6321,6 +6316,7 @@
.n_alarm = 0,
.n_ext_ts = 0,
.n_per_out = 1,
+ .n_pins = 0,
.pps = 0,
.adjfreq = tg3_ptp_adjfreq,
.adjtime = tg3_ptp_adjtime,
@@ -6592,7 +6588,7 @@
pkts_compl++;
bytes_compl += skb->len;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
if (unlikely(tx_bug)) {
tg3_tx_recover(tp);
@@ -6842,8 +6838,7 @@
work_mask |= opaque_key;
- if ((desc->err_vlan & RXD_ERR_MASK) != 0 &&
- (desc->err_vlan != RXD_ERR_ODD_NIBBLE_RCVD_MII)) {
+ if (desc->err_vlan & RXD_ERR_MASK) {
drop_it:
tg3_recycle_rx(tnapi, tpr, opaque_key,
desc_idx, *post_ptr);
@@ -6924,7 +6919,7 @@
if (len > (tp->dev->mtu + ETH_HLEN) &&
skb->protocol != htons(ETH_P_8021Q)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
goto drop_it_no_recycle;
}
@@ -7807,7 +7802,7 @@
PCI_DMA_TODEVICE);
/* Make sure the mapping succeeded */
if (pci_dma_mapping_error(tp->pdev, new_addr)) {
- dev_kfree_skb(new_skb);
+ dev_kfree_skb_any(new_skb);
ret = -1;
} else {
u32 save_entry = *entry;
@@ -7822,13 +7817,13 @@
new_skb->len, base_flags,
mss, vlan)) {
tg3_tx_skb_unmap(tnapi, save_entry, -1);
- dev_kfree_skb(new_skb);
+ dev_kfree_skb_any(new_skb);
ret = -1;
}
}
}
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
*pskb = new_skb;
return ret;
}
@@ -7871,7 +7866,7 @@
} while (segs);
tg3_tso_bug_end:
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -7923,8 +7918,7 @@
struct iphdr *iph;
u32 tcp_opt_len, hdr_len;
- if (skb_header_cloned(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_cow_head(skb, 0))
goto drop;
iph = ip_hdr(skb);
@@ -8093,7 +8087,7 @@
tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, --i);
tnapi->tx_buffers[tnapi->tx_prod].skb = NULL;
drop:
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
drop_nofree:
tp->tx_dropped++;
return NETDEV_TX_OK;
@@ -11361,12 +11355,10 @@
msix_ent[i].vector = 0;
}
- rc = pci_enable_msix(tp->pdev, msix_ent, tp->irq_cnt);
+ rc = pci_enable_msix_range(tp->pdev, msix_ent, 1, tp->irq_cnt);
if (rc < 0) {
return false;
- } else if (rc != 0) {
- if (pci_enable_msix(tp->pdev, msix_ent, rc))
- return false;
+ } else if (rc < tp->irq_cnt) {
netdev_notice(tp->dev, "Requested %d MSI-X vectors, received %d\n",
tp->irq_cnt, rc);
tp->irq_cnt = rc;
@@ -14113,12 +14105,12 @@
tg3_netif_stop(tp);
+ tg3_set_mtu(dev, tp, new_mtu);
+
tg3_full_lock(tp, 1);
tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
- tg3_set_mtu(dev, tp, new_mtu);
-
/* Reset PHY, otherwise the read DMA engine will be in a mode that
* breaks all requests to 256 bytes.
*/
@@ -17649,8 +17641,6 @@
tg3_init_bufmgr_config(tp);
- features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
-
/* 5700 B0 chips do not support checksumming correctly due
* to hardware bugs.
*/
@@ -17682,7 +17672,8 @@
features |= NETIF_F_TSO_ECN;
}
- dev->features |= features;
+ dev->features |= features | NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX;
dev->vlan_features |= features;
/*
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index ef47238..04321e5 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -2608,7 +2608,11 @@
#define RXD_ERR_TOO_SMALL 0x00400000
#define RXD_ERR_NO_RESOURCES 0x00800000
#define RXD_ERR_HUGE_FRAME 0x01000000
-#define RXD_ERR_MASK 0xffff0000
+
+#define RXD_ERR_MASK (RXD_ERR_BAD_CRC | RXD_ERR_COLLISION | \
+ RXD_ERR_LINK_LOST | RXD_ERR_PHY_DECODE | \
+ RXD_ERR_MAC_ABRT | RXD_ERR_TOO_SMALL | \
+ RXD_ERR_NO_RESOURCES | RXD_ERR_HUGE_FRAME)
u32 reserved;
u32 opaque;
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index 1803c39..354ae97 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -1704,7 +1704,7 @@
while (!bfa_raw_sem_get(bar)) {
if (--n <= 0)
return BFA_STATUS_BADFLASH;
- udelay(10000);
+ mdelay(10);
}
return BFA_STATUS_OK;
}
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index cf64f3d..675550f 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -707,7 +707,8 @@
else
skb_checksum_none_assert(skb);
- if (flags & BNA_CQ_EF_VLAN)
+ if ((flags & BNA_CQ_EF_VLAN) &&
+ (bnad->netdev->features & NETIF_F_HW_VLAN_CTAG_RX))
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(cmpl->vlan_tag));
if (BNAD_RXBUF_IS_SK_BUFF(unmap_q->type))
@@ -2094,7 +2095,9 @@
rx_config->q1_buf_size = BFI_SMALL_RXBUF_SIZE;
}
- rx_config->vlan_strip_status = BNA_STATUS_T_ENABLED;
+ rx_config->vlan_strip_status =
+ (bnad->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) ?
+ BNA_STATUS_T_ENABLED : BNA_STATUS_T_DISABLED;
}
static void
@@ -2493,12 +2496,10 @@
{
int err;
- if (skb_header_cloned(skb)) {
- err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (err) {
- BNAD_UPDATE_CTR(bnad, tso_err);
- return err;
- }
+ err = skb_cow_head(skb, 0);
+ if (err < 0) {
+ BNAD_UPDATE_CTR(bnad, tso_err);
+ return err;
}
/*
@@ -2666,9 +2667,11 @@
for (i = 0; i < bnad->msix_num; i++)
bnad->msix_table[i].entry = i;
- ret = pci_enable_msix(bnad->pcidev, bnad->msix_table, bnad->msix_num);
- if (ret > 0) {
- /* Not enough MSI-X vectors. */
+ ret = pci_enable_msix_range(bnad->pcidev, bnad->msix_table,
+ 1, bnad->msix_num);
+ if (ret < 0) {
+ goto intx_mode;
+ } else if (ret < bnad->msix_num) {
pr_warn("BNA: %d MSI-X vectors allocated < %d requested\n",
ret, bnad->msix_num);
@@ -2681,18 +2684,11 @@
bnad->msix_num = BNAD_NUM_TXQ + BNAD_NUM_RXP +
BNAD_MAILBOX_MSIX_VECTORS;
- if (bnad->msix_num > ret)
+ if (bnad->msix_num > ret) {
+ pci_disable_msix(bnad->pcidev);
goto intx_mode;
-
- /* Try once more with adjusted numbers */
- /* If this fails, fall back to INTx */
- ret = pci_enable_msix(bnad->pcidev, bnad->msix_table,
- bnad->msix_num);
- if (ret)
- goto intx_mode;
-
- } else if (ret < 0)
- goto intx_mode;
+ }
+ }
pci_intx(bnad->pcidev, 0);
@@ -2847,13 +2843,11 @@
}
if (unlikely((gso_size + skb_transport_offset(skb) +
tcp_hdrlen(skb)) >= skb->len)) {
- txqent->hdr.wi.opcode =
- __constant_htons(BNA_TXQ_WI_SEND);
+ txqent->hdr.wi.opcode = htons(BNA_TXQ_WI_SEND);
txqent->hdr.wi.lso_mss = 0;
BNAD_UPDATE_CTR(bnad, tx_skb_tso_too_short);
} else {
- txqent->hdr.wi.opcode =
- __constant_htons(BNA_TXQ_WI_SEND_LSO);
+ txqent->hdr.wi.opcode = htons(BNA_TXQ_WI_SEND_LSO);
txqent->hdr.wi.lso_mss = htons(gso_size);
}
@@ -2867,7 +2861,7 @@
htons(BNA_TXQ_WI_L4_HDR_N_OFFSET(
tcp_hdrlen(skb) >> 2, skb_transport_offset(skb)));
} else {
- txqent->hdr.wi.opcode = __constant_htons(BNA_TXQ_WI_SEND);
+ txqent->hdr.wi.opcode = htons(BNA_TXQ_WI_SEND);
txqent->hdr.wi.lso_mss = 0;
if (unlikely(skb->len > (bnad->netdev->mtu + ETH_HLEN))) {
@@ -2878,11 +2872,10 @@
if (skb->ip_summed == CHECKSUM_PARTIAL) {
u8 proto = 0;
- if (skb->protocol == __constant_htons(ETH_P_IP))
+ if (skb->protocol == htons(ETH_P_IP))
proto = ip_hdr(skb)->protocol;
#ifdef NETIF_F_IPV6_CSUM
- else if (skb->protocol ==
- __constant_htons(ETH_P_IPV6)) {
+ else if (skb->protocol == htons(ETH_P_IPV6)) {
/* nexthdr may not be TCP immediately. */
proto = ipv6_hdr(skb)->nexthdr;
}
@@ -2951,17 +2944,17 @@
/* Sanity checks for the skb */
if (unlikely(skb->len <= ETH_HLEN)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
BNAD_UPDATE_CTR(bnad, tx_skb_too_short);
return NETDEV_TX_OK;
}
if (unlikely(len > BFI_TX_MAX_DATA_PER_VECTOR)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
BNAD_UPDATE_CTR(bnad, tx_skb_headlen_zero);
return NETDEV_TX_OK;
}
if (unlikely(len == 0)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
BNAD_UPDATE_CTR(bnad, tx_skb_headlen_zero);
return NETDEV_TX_OK;
}
@@ -2973,7 +2966,7 @@
* and the netif_tx_stop_all_queues() call.
*/
if (unlikely(!tcb || !test_bit(BNAD_TXQ_TX_STARTED, &tcb->flags))) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
BNAD_UPDATE_CTR(bnad, tx_skb_stopping);
return NETDEV_TX_OK;
}
@@ -2986,7 +2979,7 @@
wis = BNA_TXQ_WI_NEEDED(vectors); /* 4 vectors per work item */
if (unlikely(vectors > BFI_TX_MAX_VECTORS_PER_PKT)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
BNAD_UPDATE_CTR(bnad, tx_skb_max_vectors);
return NETDEV_TX_OK;
}
@@ -3026,7 +3019,7 @@
/* Program the opcode, flags, frame_len, num_vectors in WI */
if (bnad_txq_wi_prepare(bnad, tcb, skb, txqent)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
txqent->hdr.wi.reserved = 0;
@@ -3052,7 +3045,7 @@
/* Undo the changes starting at tcb->producer_index */
bnad_tx_buff_unmap(bnad, unmap_q, q_depth,
tcb->producer_index);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
BNAD_UPDATE_CTR(bnad, tx_skb_frag_zero);
return NETDEV_TX_OK;
}
@@ -3064,8 +3057,7 @@
vect_id = 0;
BNA_QE_INDX_INC(prod, q_depth);
txqent = &((struct bna_txq_entry *)tcb->sw_q)[prod];
- txqent->hdr.wi_ext.opcode =
- __constant_htons(BNA_TXQ_WI_EXTENSION);
+ txqent->hdr.wi_ext.opcode = htons(BNA_TXQ_WI_EXTENSION);
unmap = &unmap_q[prod];
}
@@ -3082,7 +3074,7 @@
if (unlikely(len != skb->len)) {
/* Undo the changes starting at tcb->producer_index */
bnad_tx_buff_unmap(bnad, unmap_q, q_depth, tcb->producer_index);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
BNAD_UPDATE_CTR(bnad, tx_skb_len_mismatch);
return NETDEV_TX_OK;
}
@@ -3245,11 +3237,6 @@
BNA_RXMODE_ALLMULTI;
bna_rx_mode_set(bnad->rx_info[0].rx, new_mode, mode_mask, NULL);
- if (bnad->cfg_flags & BNAD_CF_PROMISC)
- bna_rx_vlan_strip_disable(bnad->rx_info[0].rx);
- else
- bna_rx_vlan_strip_enable(bnad->rx_info[0].rx);
-
spin_unlock_irqrestore(&bnad->bna_lock, flags);
}
@@ -3374,6 +3361,27 @@
return 0;
}
+static int bnad_set_features(struct net_device *dev, netdev_features_t features)
+{
+ struct bnad *bnad = netdev_priv(dev);
+ netdev_features_t changed = features ^ dev->features;
+
+ if ((changed & NETIF_F_HW_VLAN_CTAG_RX) && netif_running(dev)) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&bnad->bna_lock, flags);
+
+ if (features & NETIF_F_HW_VLAN_CTAG_RX)
+ bna_rx_vlan_strip_enable(bnad->rx_info[0].rx);
+ else
+ bna_rx_vlan_strip_disable(bnad->rx_info[0].rx);
+
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
+ }
+
+ return 0;
+}
+
#ifdef CONFIG_NET_POLL_CONTROLLER
static void
bnad_netpoll(struct net_device *netdev)
@@ -3421,6 +3429,7 @@
.ndo_change_mtu = bnad_change_mtu,
.ndo_vlan_rx_add_vid = bnad_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = bnad_vlan_rx_kill_vid,
+ .ndo_set_features = bnad_set_features,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = bnad_netpoll
#endif
@@ -3433,14 +3442,14 @@
netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
- NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_VLAN_CTAG_TX;
+ NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX;
netdev->vlan_features = NETIF_F_SG | NETIF_F_HIGHDMA |
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_TSO | NETIF_F_TSO6;
- netdev->features |= netdev->hw_features |
- NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER;
+ netdev->features |= netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
if (using_dac)
netdev->features |= NETIF_F_HIGHDMA;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 3190d38..ca97005 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -199,11 +199,6 @@
return 0;
}
-static int macb_mdio_reset(struct mii_bus *bus)
-{
- return 0;
-}
-
/**
* macb_set_tx_clk() - Set a clock to a new frequency
* @clk Pointer to the clock to change
@@ -375,7 +370,6 @@
bp->mii_bus->name = "MACB_mii_bus";
bp->mii_bus->read = &macb_mdio_read;
bp->mii_bus->write = &macb_mdio_write;
- bp->mii_bus->reset = &macb_mdio_reset;
snprintf(bp->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
bp->pdev->name, bp->pdev->id);
bp->mii_bus->priv = bp;
@@ -632,11 +626,16 @@
"Unable to allocate sk_buff\n");
break;
}
- bp->rx_skbuff[entry] = skb;
/* now fill corresponding descriptor entry */
paddr = dma_map_single(&bp->pdev->dev, skb->data,
bp->rx_buffer_size, DMA_FROM_DEVICE);
+ if (dma_mapping_error(&bp->pdev->dev, paddr)) {
+ dev_kfree_skb(skb);
+ break;
+ }
+
+ bp->rx_skbuff[entry] = skb;
if (entry == RX_RING_SIZE - 1)
paddr |= MACB_BIT(RX_WRAP);
@@ -725,7 +724,7 @@
skb_put(skb, len);
addr = MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, addr));
dma_unmap_single(&bp->pdev->dev, addr,
- len, DMA_FROM_DEVICE);
+ bp->rx_buffer_size, DMA_FROM_DEVICE);
skb->protocol = eth_type_trans(skb, bp->dev);
skb_checksum_none_assert(skb);
@@ -1036,11 +1035,15 @@
}
entry = macb_tx_ring_wrap(bp->tx_head);
- bp->tx_head++;
netdev_vdbg(bp->dev, "Allocated ring entry %u\n", entry);
mapping = dma_map_single(&bp->pdev->dev, skb->data,
len, DMA_TO_DEVICE);
+ if (dma_mapping_error(&bp->pdev->dev, mapping)) {
+ dev_kfree_skb_any(skb);
+ goto unlock;
+ }
+ bp->tx_head++;
tx_skb = &bp->tx_skb[entry];
tx_skb->skb = skb;
tx_skb->mapping = mapping;
@@ -1066,6 +1069,7 @@
if (CIRC_SPACE(bp->tx_head, bp->tx_tail, TX_RING_SIZE) < 1)
netif_stop_queue(dev);
+unlock:
spin_unlock_irqrestore(&bp->lock, flags);
return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c
index d2a183c..521dfea 100644
--- a/drivers/net/ethernet/calxeda/xgmac.c
+++ b/drivers/net/ethernet/calxeda/xgmac.c
@@ -897,7 +897,7 @@
/* Check tx error on the last segment */
if (desc_get_tx_ls(p)) {
desc_get_tx_status(priv, p);
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
}
priv->tx_skbuff[entry] = NULL;
@@ -1105,7 +1105,7 @@
len = skb_headlen(skb);
paddr = dma_map_single(priv->device, skb->data, len, DMA_TO_DEVICE);
if (dma_mapping_error(priv->device, paddr)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
priv->tx_skbuff[entry] = skb;
@@ -1169,7 +1169,7 @@
desc = first;
dma_unmap_single(priv->device, desc_get_buf_addr(desc),
desc_get_buf_len(desc), DMA_TO_DEVICE);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 45d7733..07bbb71 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -3088,30 +3088,22 @@
{
struct msix_entry entries[SGE_QSETS + 1];
int vectors;
- int i, err;
+ int i;
vectors = ARRAY_SIZE(entries);
for (i = 0; i < vectors; ++i)
entries[i].entry = i;
- while ((err = pci_enable_msix(adap->pdev, entries, vectors)) > 0)
- vectors = err;
+ vectors = pci_enable_msix_range(adap->pdev, entries,
+ adap->params.nports + 1, vectors);
+ if (vectors < 0)
+ return vectors;
- if (err < 0)
- pci_disable_msix(adap->pdev);
+ for (i = 0; i < vectors; ++i)
+ adap->msix_info[i].vec = entries[i].vector;
+ adap->msix_nvectors = vectors;
- if (!err && vectors < (adap->params.nports + 1)) {
- pci_disable_msix(adap->pdev);
- err = -1;
- }
-
- if (!err) {
- for (i = 0; i < vectors; ++i)
- adap->msix_info[i].vec = entries[i].vector;
- adap->msix_nvectors = vectors;
- }
-
- return err;
+ return 0;
}
static void print_port_info(struct adapter *adap, const struct adapter_info *ai)
diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index 632b318..8b069f9 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -298,7 +298,7 @@
if (need_unmap)
unmap_skb(d->skb, q, cidx, pdev);
if (d->eop) {
- kfree_skb(d->skb);
+ dev_consume_skb_any(d->skb);
d->skb = NULL;
}
}
@@ -1188,7 +1188,7 @@
cpl->wr.wr_lo = htonl(V_WR_LEN(flits) | V_WR_GEN(gen) |
V_WR_TID(q->token));
wr_gen2(d, gen);
- kfree_skb(skb);
+ dev_consume_skb_any(skb);
return;
}
@@ -1233,7 +1233,7 @@
* anything shorter than an Ethernet header.
*/
if (unlikely(skb->len < ETH_HLEN)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 1f4b9b3..32db377 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -66,6 +66,7 @@
SERNUM_LEN = 24, /* Serial # length */
EC_LEN = 16, /* E/C length */
ID_LEN = 16, /* ID length */
+ PN_LEN = 16, /* Part Number length */
};
enum {
@@ -254,6 +255,7 @@
u8 ec[EC_LEN + 1];
u8 sn[SERNUM_LEN + 1];
u8 id[ID_LEN + 1];
+ u8 pn[PN_LEN + 1];
};
struct pci_params {
@@ -306,6 +308,7 @@
unsigned char bypass;
unsigned int ofldq_wr_cred;
+ bool ulptx_memwrite_dsgl; /* use of T5 DSGL allowed */
};
#include "t4fw_api.h"
@@ -497,6 +500,7 @@
spinlock_t db_lock;
int db_disabled;
unsigned short db_pidx;
+ unsigned short db_pidx_inc;
u64 udb;
};
@@ -553,8 +557,13 @@
u32 pktshift; /* padding between CPL & packet data */
u32 fl_align; /* response queue message alignment */
u32 fl_starve_thres; /* Free List starvation threshold */
- unsigned int starve_thres;
- u8 idma_state[2];
+
+ /* State variables for detecting an SGE Ingress DMA hang */
+ unsigned int idma_1s_thresh;/* SGE same State Counter 1s threshold */
+ unsigned int idma_stalled[2];/* SGE synthesized stalled timers in HZ */
+ unsigned int idma_state[2]; /* SGE IDMA Hang detect state */
+ unsigned int idma_qid[2]; /* SGE IDMA Hung Ingress Queue ID */
+
unsigned int egr_start;
unsigned int ingr_start;
void *egr_map[MAX_EGRQ]; /* qid->queue egress queue map */
@@ -957,7 +966,7 @@
u64 *parity);
int t4_edc_read(struct adapter *adap, int idx, u32 addr, __be32 *data,
u64 *parity);
-
+const char *t4_get_port_type_description(enum fw_port_type port_type);
void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p);
void t4_read_mtu_tbl(struct adapter *adap, u16 *mtus, u8 *mtu_log);
void t4_tp_wr_bits_indirect(struct adapter *adap, unsigned int addr,
@@ -1029,4 +1038,5 @@
int t4_mem_win_read_len(struct adapter *adap, u32 addr, __be32 *data, int len);
int t4_fwaddrspace_write(struct adapter *adap, unsigned int mbox,
u32 addr, u32 val);
+void t4_sge_decode_idma_state(struct adapter *adapter, int state);
#endif /* __CXGB4_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 43ab35f..6fe5891 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -254,6 +254,14 @@
CH_DEVICE(0x5011, 4),
CH_DEVICE(0x5012, 4),
CH_DEVICE(0x5013, 4),
+ CH_DEVICE(0x5014, 4),
+ CH_DEVICE(0x5015, 4),
+ CH_DEVICE(0x5080, 4),
+ CH_DEVICE(0x5081, 4),
+ CH_DEVICE(0x5082, 4),
+ CH_DEVICE(0x5083, 4),
+ CH_DEVICE(0x5084, 4),
+ CH_DEVICE(0x5085, 4),
CH_DEVICE(0x5401, 4),
CH_DEVICE(0x5402, 4),
CH_DEVICE(0x5403, 4),
@@ -273,6 +281,14 @@
CH_DEVICE(0x5411, 4),
CH_DEVICE(0x5412, 4),
CH_DEVICE(0x5413, 4),
+ CH_DEVICE(0x5414, 4),
+ CH_DEVICE(0x5415, 4),
+ CH_DEVICE(0x5480, 4),
+ CH_DEVICE(0x5481, 4),
+ CH_DEVICE(0x5482, 4),
+ CH_DEVICE(0x5483, 4),
+ CH_DEVICE(0x5484, 4),
+ CH_DEVICE(0x5485, 4),
{ 0, }
};
@@ -423,15 +439,18 @@
const struct port_info *p = netdev_priv(dev);
switch (p->link_cfg.speed) {
- case SPEED_10000:
+ case 10000:
s = "10Gbps";
break;
- case SPEED_1000:
+ case 1000:
s = "1000Mbps";
break;
- case SPEED_100:
+ case 100:
s = "100Mbps";
break;
+ case 40000:
+ s = "40Gbps";
+ break;
}
netdev_info(dev, "link up, %s, full-duplex, %s PAUSE\n", s,
@@ -2061,7 +2080,7 @@
0x40200, 0x40298,
0x402ac, 0x4033c,
0x403f8, 0x403fc,
- 0x41300, 0x413c4,
+ 0x41304, 0x413c4,
0x41400, 0x4141c,
0x41480, 0x414d0,
0x44000, 0x44078,
@@ -2089,7 +2108,7 @@
0x48200, 0x48298,
0x482ac, 0x4833c,
0x483f8, 0x483fc,
- 0x49300, 0x493c4,
+ 0x49304, 0x493c4,
0x49400, 0x4941c,
0x49480, 0x494d0,
0x4c000, 0x4c078,
@@ -2199,6 +2218,8 @@
else if (type == FW_PORT_TYPE_FIBER_XFI ||
type == FW_PORT_TYPE_FIBER_XAUI || type == FW_PORT_TYPE_SFP)
v |= SUPPORTED_FIBRE;
+ else if (type == FW_PORT_TYPE_BP40_BA)
+ v |= SUPPORTED_40000baseSR4_Full;
if (caps & FW_PORT_CAP_ANEG)
v |= SUPPORTED_Autoneg;
@@ -2215,6 +2236,8 @@
v |= FW_PORT_CAP_SPEED_1G;
if (caps & ADVERTISED_10000baseT_Full)
v |= FW_PORT_CAP_SPEED_10G;
+ if (caps & ADVERTISED_40000baseSR4_Full)
+ v |= FW_PORT_CAP_SPEED_40G;
return v;
}
@@ -2263,12 +2286,14 @@
static unsigned int speed_to_caps(int speed)
{
- if (speed == SPEED_100)
+ if (speed == 100)
return FW_PORT_CAP_SPEED_100M;
- if (speed == SPEED_1000)
+ if (speed == 1000)
return FW_PORT_CAP_SPEED_1G;
- if (speed == SPEED_10000)
+ if (speed == 10000)
return FW_PORT_CAP_SPEED_10G;
+ if (speed == 40000)
+ return FW_PORT_CAP_SPEED_40G;
return 0;
}
@@ -2296,8 +2321,10 @@
if (cmd->autoneg == AUTONEG_DISABLE) {
cap = speed_to_caps(speed);
- if (!(lc->supported & cap) || (speed == SPEED_1000) ||
- (speed == SPEED_10000))
+ if (!(lc->supported & cap) ||
+ (speed == 1000) ||
+ (speed == 10000) ||
+ (speed == 40000))
return -EINVAL;
lc->requested_speed = cap;
lc->advertising = 0;
@@ -3205,8 +3232,8 @@
c.op_to_write = htonl(FW_CMD_OP(FW_CLIP_CMD) |
FW_CMD_REQUEST | FW_CMD_WRITE);
c.alloc_to_len16 = htonl(F_FW_CLIP_CMD_ALLOC | FW_LEN16(c));
- *(__be64 *)&c.ip_hi = *(__be64 *)(lip->s6_addr);
- *(__be64 *)&c.ip_lo = *(__be64 *)(lip->s6_addr + 8);
+ c.ip_hi = *(__be64 *)(lip->s6_addr);
+ c.ip_lo = *(__be64 *)(lip->s6_addr + 8);
return t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, false);
}
@@ -3221,8 +3248,8 @@
c.op_to_write = htonl(FW_CMD_OP(FW_CLIP_CMD) |
FW_CMD_REQUEST | FW_CMD_READ);
c.alloc_to_len16 = htonl(F_FW_CLIP_CMD_FREE | FW_LEN16(c));
- *(__be64 *)&c.ip_hi = *(__be64 *)(lip->s6_addr);
- *(__be64 *)&c.ip_lo = *(__be64 *)(lip->s6_addr + 8);
+ c.ip_hi = *(__be64 *)(lip->s6_addr);
+ c.ip_lo = *(__be64 *)(lip->s6_addr + 8);
return t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, false);
}
@@ -3563,14 +3590,25 @@
static void disable_txq_db(struct sge_txq *q)
{
- spin_lock_irq(&q->db_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&q->db_lock, flags);
q->db_disabled = 1;
- spin_unlock_irq(&q->db_lock);
+ spin_unlock_irqrestore(&q->db_lock, flags);
}
-static void enable_txq_db(struct sge_txq *q)
+static void enable_txq_db(struct adapter *adap, struct sge_txq *q)
{
spin_lock_irq(&q->db_lock);
+ if (q->db_pidx_inc) {
+ /* Make sure that all writes to the TX descriptors
+ * are committed before we tell HW about them.
+ */
+ wmb();
+ t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL),
+ QID(q->cntxt_id) | PIDX(q->db_pidx_inc));
+ q->db_pidx_inc = 0;
+ }
q->db_disabled = 0;
spin_unlock_irq(&q->db_lock);
}
@@ -3592,11 +3630,32 @@
int i;
for_each_ethrxq(&adap->sge, i)
- enable_txq_db(&adap->sge.ethtxq[i].q);
+ enable_txq_db(adap, &adap->sge.ethtxq[i].q);
for_each_ofldrxq(&adap->sge, i)
- enable_txq_db(&adap->sge.ofldtxq[i].q);
+ enable_txq_db(adap, &adap->sge.ofldtxq[i].q);
for_each_port(adap, i)
- enable_txq_db(&adap->sge.ctrlq[i].q);
+ enable_txq_db(adap, &adap->sge.ctrlq[i].q);
+}
+
+static void notify_rdma_uld(struct adapter *adap, enum cxgb4_control cmd)
+{
+ if (adap->uld_handle[CXGB4_ULD_RDMA])
+ ulds[CXGB4_ULD_RDMA].control(adap->uld_handle[CXGB4_ULD_RDMA],
+ cmd);
+}
+
+static void process_db_full(struct work_struct *work)
+{
+ struct adapter *adap;
+
+ adap = container_of(work, struct adapter, db_full_task);
+
+ drain_db_fifo(adap, dbfifo_drain_delay);
+ enable_dbs(adap);
+ notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY);
+ t4_set_reg_field(adap, SGE_INT_ENABLE3,
+ DBFIFO_HP_INT | DBFIFO_LP_INT,
+ DBFIFO_HP_INT | DBFIFO_LP_INT);
}
static void sync_txq_pidx(struct adapter *adap, struct sge_txq *q)
@@ -3604,7 +3663,7 @@
u16 hw_pidx, hw_cidx;
int ret;
- spin_lock_bh(&q->db_lock);
+ spin_lock_irq(&q->db_lock);
ret = read_eq_indices(adap, (u16)q->cntxt_id, &hw_pidx, &hw_cidx);
if (ret)
goto out;
@@ -3621,7 +3680,8 @@
}
out:
q->db_disabled = 0;
- spin_unlock_bh(&q->db_lock);
+ q->db_pidx_inc = 0;
+ spin_unlock_irq(&q->db_lock);
if (ret)
CH_WARN(adap, "DB drop recovery failed.\n");
}
@@ -3637,29 +3697,6 @@
sync_txq_pidx(adap, &adap->sge.ctrlq[i].q);
}
-static void notify_rdma_uld(struct adapter *adap, enum cxgb4_control cmd)
-{
- mutex_lock(&uld_mutex);
- if (adap->uld_handle[CXGB4_ULD_RDMA])
- ulds[CXGB4_ULD_RDMA].control(adap->uld_handle[CXGB4_ULD_RDMA],
- cmd);
- mutex_unlock(&uld_mutex);
-}
-
-static void process_db_full(struct work_struct *work)
-{
- struct adapter *adap;
-
- adap = container_of(work, struct adapter, db_full_task);
-
- notify_rdma_uld(adap, CXGB4_CONTROL_DB_FULL);
- drain_db_fifo(adap, dbfifo_drain_delay);
- t4_set_reg_field(adap, SGE_INT_ENABLE3,
- DBFIFO_HP_INT | DBFIFO_LP_INT,
- DBFIFO_HP_INT | DBFIFO_LP_INT);
- notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY);
-}
-
static void process_db_drop(struct work_struct *work)
{
struct adapter *adap;
@@ -3667,11 +3704,13 @@
adap = container_of(work, struct adapter, db_drop_task);
if (is_t4(adap->params.chip)) {
- disable_dbs(adap);
+ drain_db_fifo(adap, dbfifo_drain_delay);
notify_rdma_uld(adap, CXGB4_CONTROL_DB_DROP);
- drain_db_fifo(adap, 1);
+ drain_db_fifo(adap, dbfifo_drain_delay);
recover_all_queues(adap);
+ drain_db_fifo(adap, dbfifo_drain_delay);
enable_dbs(adap);
+ notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY);
} else {
u32 dropped_db = t4_read_reg(adap, 0x010ac);
u16 qid = (dropped_db >> 15) & 0x1ffff;
@@ -3712,6 +3751,8 @@
void t4_db_full(struct adapter *adap)
{
if (is_t4(adap->params.chip)) {
+ disable_dbs(adap);
+ notify_rdma_uld(adap, CXGB4_CONTROL_DB_FULL);
t4_set_reg_field(adap, SGE_INT_ENABLE3,
DBFIFO_HP_INT | DBFIFO_LP_INT, 0);
queue_work(workq, &adap->db_full_task);
@@ -3720,8 +3761,11 @@
void t4_db_dropped(struct adapter *adap)
{
- if (is_t4(adap->params.chip))
- queue_work(workq, &adap->db_drop_task);
+ if (is_t4(adap->params.chip)) {
+ disable_dbs(adap);
+ notify_rdma_uld(adap, CXGB4_CONTROL_DB_FULL);
+ }
+ queue_work(workq, &adap->db_drop_task);
}
static void uld_attach(struct adapter *adap, unsigned int uld)
@@ -3765,6 +3809,7 @@
lli.dbfifo_int_thresh = dbfifo_int_thresh;
lli.sge_pktshift = adap->sge.pktshift;
lli.enable_fw_ofld_conn = adap->flags & FW_OFLD_CONN;
+ lli.ulptx_memwrite_dsgl = adap->params.ulptx_memwrite_dsgl;
handle = ulds[uld].add(&lli);
if (IS_ERR(handle)) {
@@ -5370,6 +5415,21 @@
(void) t4_set_params(adap, adap->mbox, adap->fn, 0, 1, params, val);
/*
+ * Find out whether we're allowed to use the T5+ ULPTX MEMWRITE DSGL
+ * capability. Earlier versions of the firmware didn't have the
+ * ULPTX_MEMWRITE_DSGL so we'll interpret a query failure as no
+ * permission to use ULPTX MEMWRITE DSGL.
+ */
+ if (is_t4(adap->params.chip)) {
+ adap->params.ulptx_memwrite_dsgl = false;
+ } else {
+ params[0] = FW_PARAM_DEV(ULPTX_MEMWRITE_DSGL);
+ ret = t4_query_params(adap, adap->mbox, adap->fn, 0,
+ 1, params, val);
+ adap->params.ulptx_memwrite_dsgl = (ret == 0 && val[0] != 0);
+ }
+
+ /*
* Get device capabilities so we can determine what resources we need
* to manage.
*/
@@ -5603,9 +5663,10 @@
.resume = eeh_resume,
};
-static inline bool is_10g_port(const struct link_config *lc)
+static inline bool is_x_10g_port(const struct link_config *lc)
{
- return (lc->supported & FW_PORT_CAP_SPEED_10G) != 0;
+ return (lc->supported & FW_PORT_CAP_SPEED_10G) != 0 ||
+ (lc->supported & FW_PORT_CAP_SPEED_40G) != 0;
}
static inline void init_rspq(struct sge_rspq *q, u8 timer_idx, u8 pkt_cnt_idx,
@@ -5629,7 +5690,7 @@
int i, q10g = 0, n10g = 0, qidx = 0;
for_each_port(adap, i)
- n10g += is_10g_port(&adap2pinfo(adap, i)->link_cfg);
+ n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
/*
* We default to 1 queue per non-10G port and up to # of cores queues
@@ -5644,7 +5705,7 @@
struct port_info *pi = adap2pinfo(adap, i);
pi->first_qset = qidx;
- pi->nqsets = is_10g_port(&pi->link_cfg) ? q10g : 1;
+ pi->nqsets = is_x_10g_port(&pi->link_cfg) ? q10g : 1;
qidx += pi->nqsets;
}
@@ -5737,7 +5798,7 @@
static int enable_msix(struct adapter *adap)
{
int ofld_need = 0;
- int i, err, want, need;
+ int i, want, need;
struct sge *s = &adap->sge;
unsigned int nchan = adap->params.nports;
struct msix_entry entries[MAX_INGQ + 1];
@@ -5753,32 +5814,30 @@
}
need = adap->params.nports + EXTRA_VECS + ofld_need;
- while ((err = pci_enable_msix(adap->pdev, entries, want)) >= need)
- want = err;
+ want = pci_enable_msix_range(adap->pdev, entries, need, want);
+ if (want < 0)
+ return want;
- if (!err) {
- /*
- * Distribute available vectors to the various queue groups.
- * Every group gets its minimum requirement and NIC gets top
- * priority for leftovers.
- */
- i = want - EXTRA_VECS - ofld_need;
- if (i < s->max_ethqsets) {
- s->max_ethqsets = i;
- if (i < s->ethqsets)
- reduce_ethqs(adap, i);
- }
- if (is_offload(adap)) {
- i = want - EXTRA_VECS - s->max_ethqsets;
- i -= ofld_need - nchan;
- s->ofldqsets = (i / nchan) * nchan; /* round down */
- }
- for (i = 0; i < want; ++i)
- adap->msix_info[i].vec = entries[i].vector;
- } else if (err > 0)
- dev_info(adap->pdev_dev,
- "only %d MSI-X vectors left, not using MSI-X\n", err);
- return err;
+ /*
+ * Distribute available vectors to the various queue groups.
+ * Every group gets its minimum requirement and NIC gets top
+ * priority for leftovers.
+ */
+ i = want - EXTRA_VECS - ofld_need;
+ if (i < s->max_ethqsets) {
+ s->max_ethqsets = i;
+ if (i < s->ethqsets)
+ reduce_ethqs(adap, i);
+ }
+ if (is_offload(adap)) {
+ i = want - EXTRA_VECS - s->max_ethqsets;
+ i -= ofld_need - nchan;
+ s->ofldqsets = (i / nchan) * nchan; /* round down */
+ }
+ for (i = 0; i < want; ++i)
+ adap->msix_info[i].vec = entries[i].vector;
+
+ return 0;
}
#undef EXTRA_VECS
@@ -5801,11 +5860,6 @@
static void print_port_info(const struct net_device *dev)
{
- static const char *base[] = {
- "R XFI", "R XAUI", "T SGMII", "T XFI", "T XAUI", "KX4", "CX4",
- "KX", "KR", "R SFP+", "KR/KX", "KR/KX/KX4"
- };
-
char buf[80];
char *bufp = buf;
const char *spd = "";
@@ -5823,9 +5877,11 @@
bufp += sprintf(bufp, "1000/");
if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_10G)
bufp += sprintf(bufp, "10G/");
+ if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_40G)
+ bufp += sprintf(bufp, "40G/");
if (bufp != buf)
--bufp;
- sprintf(bufp, "BASE-%s", base[pi->port_type]);
+ sprintf(bufp, "BASE-%s", t4_get_port_type_description(pi->port_type));
netdev_info(dev, "Chelsio %s rev %d %s %sNIC PCIe x%d%s%s\n",
adap->params.vpd.id,
@@ -5833,8 +5889,8 @@
is_offload(adap) ? "R" : "", adap->params.pci.width, spd,
(adap->flags & USING_MSIX) ? " MSI-X" :
(adap->flags & USING_MSI) ? " MSI" : "");
- netdev_info(dev, "S/N: %s, E/C: %s\n",
- adap->params.vpd.sn, adap->params.vpd.ec);
+ netdev_info(dev, "S/N: %s, P/N: %s\n",
+ adap->params.vpd.sn, adap->params.vpd.pn);
}
static void enable_pcie_relaxed_ordering(struct pci_dev *dev)
@@ -6179,6 +6235,7 @@
.id_table = cxgb4_pci_tbl,
.probe = init_one,
.remove = remove_one,
+ .shutdown = remove_one,
.err_handler = &cxgb4_eeh,
};
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 4dd0a82..e274a04 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -253,6 +253,7 @@
/* packet data */
bool enable_fw_ofld_conn; /* Enable connection through fw */
/* WR */
+ bool ulptx_memwrite_dsgl; /* use of T5 DSGL allowed */
};
struct cxgb4_uld_info {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 47ffa64..ca95cf2 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -93,6 +93,16 @@
*/
#define TX_QCHECK_PERIOD (HZ / 2)
+/* SGE Hung Ingress DMA Threshold Warning time (in Hz) and Warning Repeat Rate
+ * (in RX_QCHECK_PERIOD multiples). If we find one of the SGE Ingress DMA
+ * State Machines in the same state for this amount of time (in HZ) then we'll
+ * issue a warning about a potential hang. We'll repeat the warning as the
+ * SGE Ingress DMA Channel appears to be hung every N RX_QCHECK_PERIODs till
+ * the situation clears. If the situation clears, we'll note that as well.
+ */
+#define SGE_IDMA_WARN_THRESH (1 * HZ)
+#define SGE_IDMA_WARN_REPEAT (20 * RX_QCHECK_PERIOD)
+
/*
* Max number of Tx descriptors to be reclaimed by the Tx timer.
*/
@@ -373,7 +383,7 @@
if (d->skb) { /* an SGL is present */
if (unmap)
unmap_sgl(dev, d->skb, d->sgl, q);
- kfree_skb(d->skb);
+ dev_consume_skb_any(d->skb);
d->skb = NULL;
}
++d;
@@ -706,11 +716,17 @@
* @skb: the packet
*
* Returns whether an Ethernet packet is small enough to fit as
- * immediate data.
+ * immediate data. Return value corresponds to headroom required.
*/
static inline int is_eth_imm(const struct sk_buff *skb)
{
- return skb->len <= MAX_IMM_TX_PKT_LEN - sizeof(struct cpl_tx_pkt);
+ int hdrlen = skb_shinfo(skb)->gso_size ?
+ sizeof(struct cpl_tx_pkt_lso_core) : 0;
+
+ hdrlen += sizeof(struct cpl_tx_pkt);
+ if (skb->len <= MAX_IMM_TX_PKT_LEN - hdrlen)
+ return hdrlen;
+ return 0;
}
/**
@@ -723,9 +739,10 @@
static inline unsigned int calc_tx_flits(const struct sk_buff *skb)
{
unsigned int flits;
+ int hdrlen = is_eth_imm(skb);
- if (is_eth_imm(skb))
- return DIV_ROUND_UP(skb->len + sizeof(struct cpl_tx_pkt), 8);
+ if (hdrlen)
+ return DIV_ROUND_UP(skb->len + hdrlen, sizeof(__be64));
flits = sgl_len(skb_shinfo(skb)->nr_frags + 1) + 4;
if (skb_shinfo(skb)->gso_size)
@@ -843,9 +860,10 @@
static inline void ring_tx_db(struct adapter *adap, struct sge_txq *q, int n)
{
unsigned int *wr, index;
+ unsigned long flags;
wmb(); /* write descriptors before telling HW */
- spin_lock(&q->db_lock);
+ spin_lock_irqsave(&q->db_lock, flags);
if (!q->db_disabled) {
if (is_t4(adap->params.chip)) {
t4_write_reg(adap, MYPF_REG(SGE_PF_KDOORBELL),
@@ -861,9 +879,10 @@
writel(n, adap->bar2 + q->udb + 8);
wmb();
}
- }
+ } else
+ q->db_pidx_inc += n;
q->db_pidx = q->pidx;
- spin_unlock(&q->db_lock);
+ spin_unlock_irqrestore(&q->db_lock, flags);
}
/**
@@ -971,6 +990,7 @@
*/
netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
{
+ int len;
u32 wr_mid;
u64 cntrl, *end;
int qidx, credits;
@@ -982,13 +1002,14 @@
struct cpl_tx_pkt_core *cpl;
const struct skb_shared_info *ssi;
dma_addr_t addr[MAX_SKB_FRAGS + 1];
+ bool immediate = false;
/*
* The chip min packet length is 10 octets but play safe and reject
* anything shorter than an Ethernet header.
*/
if (unlikely(skb->len < ETH_HLEN)) {
-out_free: dev_kfree_skb(skb);
+out_free: dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -1011,7 +1032,10 @@
return NETDEV_TX_BUSY;
}
- if (!is_eth_imm(skb) &&
+ if (is_eth_imm(skb))
+ immediate = true;
+
+ if (!immediate &&
unlikely(map_skb(adap->pdev_dev, skb, addr) < 0)) {
q->mapping_err++;
goto out_free;
@@ -1028,6 +1052,7 @@
wr->r3 = cpu_to_be64(0);
end = (u64 *)wr + flits;
+ len = immediate ? skb->len : 0;
ssi = skb_shinfo(skb);
if (ssi->gso_size) {
struct cpl_tx_pkt_lso *lso = (void *)wr;
@@ -1035,8 +1060,9 @@
int l3hdr_len = skb_network_header_len(skb);
int eth_xtra_len = skb_network_offset(skb) - ETH_HLEN;
+ len += sizeof(*lso);
wr->op_immdlen = htonl(FW_WR_OP(FW_ETH_TX_PKT_WR) |
- FW_WR_IMMDLEN(sizeof(*lso)));
+ FW_WR_IMMDLEN(len));
lso->c.lso_ctrl = htonl(LSO_OPCODE(CPL_TX_PKT_LSO) |
LSO_FIRST_SLICE | LSO_LAST_SLICE |
LSO_IPV6(v6) |
@@ -1054,9 +1080,7 @@
q->tso++;
q->tx_cso += ssi->gso_segs;
} else {
- int len;
-
- len = is_eth_imm(skb) ? skb->len + sizeof(*cpl) : sizeof(*cpl);
+ len += sizeof(*cpl);
wr->op_immdlen = htonl(FW_WR_OP(FW_ETH_TX_PKT_WR) |
FW_WR_IMMDLEN(len));
cpl = (void *)(wr + 1);
@@ -1078,9 +1102,9 @@
cpl->len = htons(skb->len);
cpl->ctrl1 = cpu_to_be64(cntrl);
- if (is_eth_imm(skb)) {
+ if (immediate) {
inline_tx_skb(skb, &q->q, cpl + 1);
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
} else {
int last_desc;
@@ -1467,8 +1491,12 @@
{
unsigned int idx = skb_txq(skb);
- if (unlikely(is_ctrl_pkt(skb)))
+ if (unlikely(is_ctrl_pkt(skb))) {
+ /* Single ctrl queue is a requirement for LE workaround path */
+ if (adap->tids.nsftids)
+ idx = 0;
return ctrl_xmit(&adap->sge.ctrlq[idx], skb);
+ }
return ofld_xmit(&adap->sge.ofldtxq[idx], skb);
}
@@ -1992,7 +2020,7 @@
static void sge_rx_timer_cb(unsigned long data)
{
unsigned long m;
- unsigned int i, cnt[2];
+ unsigned int i, idma_same_state_cnt[2];
struct adapter *adap = (struct adapter *)data;
struct sge *s = &adap->sge;
@@ -2015,21 +2043,64 @@
}
t4_write_reg(adap, SGE_DEBUG_INDEX, 13);
- cnt[0] = t4_read_reg(adap, SGE_DEBUG_DATA_HIGH);
- cnt[1] = t4_read_reg(adap, SGE_DEBUG_DATA_LOW);
+ idma_same_state_cnt[0] = t4_read_reg(adap, SGE_DEBUG_DATA_HIGH);
+ idma_same_state_cnt[1] = t4_read_reg(adap, SGE_DEBUG_DATA_LOW);
- for (i = 0; i < 2; i++)
- if (cnt[i] >= s->starve_thres) {
- if (s->idma_state[i] || cnt[i] == 0xffffffff)
- continue;
- s->idma_state[i] = 1;
- t4_write_reg(adap, SGE_DEBUG_INDEX, 11);
- m = t4_read_reg(adap, SGE_DEBUG_DATA_LOW) >> (i * 16);
- dev_warn(adap->pdev_dev,
- "SGE idma%u starvation detected for "
- "queue %lu\n", i, m & 0xffff);
- } else if (s->idma_state[i])
- s->idma_state[i] = 0;
+ for (i = 0; i < 2; i++) {
+ u32 debug0, debug11;
+
+ /* If the Ingress DMA Same State Counter ("timer") is less
+ * than 1s, then we can reset our synthesized Stall Timer and
+ * continue. If we have previously emitted warnings about a
+ * potential stalled Ingress Queue, issue a note indicating
+ * that the Ingress Queue has resumed forward progress.
+ */
+ if (idma_same_state_cnt[i] < s->idma_1s_thresh) {
+ if (s->idma_stalled[i] >= SGE_IDMA_WARN_THRESH)
+ CH_WARN(adap, "SGE idma%d, queue%u,resumed after %d sec\n",
+ i, s->idma_qid[i],
+ s->idma_stalled[i]/HZ);
+ s->idma_stalled[i] = 0;
+ continue;
+ }
+
+ /* Synthesize an SGE Ingress DMA Same State Timer in the Hz
+ * domain. The first time we get here it'll be because we
+ * passed the 1s Threshold; each additional time it'll be
+ * because the RX Timer Callback is being fired on its regular
+ * schedule.
+ *
+ * If the stall is below our Potential Hung Ingress Queue
+ * Warning Threshold, continue.
+ */
+ if (s->idma_stalled[i] == 0)
+ s->idma_stalled[i] = HZ;
+ else
+ s->idma_stalled[i] += RX_QCHECK_PERIOD;
+
+ if (s->idma_stalled[i] < SGE_IDMA_WARN_THRESH)
+ continue;
+
+ /* We'll issue a warning every SGE_IDMA_WARN_REPEAT Hz */
+ if (((s->idma_stalled[i] - HZ) % SGE_IDMA_WARN_REPEAT) != 0)
+ continue;
+
+ /* Read and save the SGE IDMA State and Queue ID information.
+ * We do this every time in case it changes across time ...
+ */
+ t4_write_reg(adap, SGE_DEBUG_INDEX, 0);
+ debug0 = t4_read_reg(adap, SGE_DEBUG_DATA_LOW);
+ s->idma_state[i] = (debug0 >> (i * 9)) & 0x3f;
+
+ t4_write_reg(adap, SGE_DEBUG_INDEX, 11);
+ debug11 = t4_read_reg(adap, SGE_DEBUG_DATA_LOW);
+ s->idma_qid[i] = (debug11 >> (i * 16)) & 0xffff;
+
+ CH_WARN(adap, "SGE idma%u, queue%u, maybe stuck state%u %dsecs (debug0=%#x, debug11=%#x)\n",
+ i, s->idma_qid[i], s->idma_state[i],
+ s->idma_stalled[i]/HZ, debug0, debug11);
+ t4_sge_decode_idma_state(adap, s->idma_state[i]);
+ }
mod_timer(&s->rx_timer, jiffies + RX_QCHECK_PERIOD);
}
@@ -2580,11 +2651,19 @@
fl_small_mtu = READ_FL_BUF(RX_SMALL_MTU_BUF);
fl_large_mtu = READ_FL_BUF(RX_LARGE_MTU_BUF);
+ /* We only bother using the Large Page logic if the Large Page Buffer
+ * is larger than our Page Size Buffer.
+ */
+ if (fl_large_pg <= fl_small_pg)
+ fl_large_pg = 0;
+
#undef READ_FL_BUF
+ /* The Page Size Buffer must be exactly equal to our Page Size and the
+ * Large Page Size Buffer should be 0 (per above) or a power of 2.
+ */
if (fl_small_pg != PAGE_SIZE ||
- (fl_large_pg != 0 && (fl_large_pg < fl_small_pg ||
- (fl_large_pg & (fl_large_pg-1)) != 0))) {
+ (fl_large_pg & (fl_large_pg-1)) != 0) {
dev_err(adap->pdev_dev, "bad SGE FL page buffer sizes [%d, %d]\n",
fl_small_pg, fl_large_pg);
return -EINVAL;
@@ -2699,8 +2778,8 @@
int t4_sge_init(struct adapter *adap)
{
struct sge *s = &adap->sge;
- u32 sge_control;
- int ret;
+ u32 sge_control, sge_conm_ctrl;
+ int ret, egress_threshold;
/*
* Ingress Padding Boundary and Egress Status Page Size are set up by
@@ -2725,15 +2804,24 @@
* SGE's Egress Congestion Threshold. If it isn't, then we can get
* stuck waiting for new packets while the SGE is waiting for us to
* give it more Free List entries. (Note that the SGE's Egress
- * Congestion Threshold is in units of 2 Free List pointers.)
+ * Congestion Threshold is in units of 2 Free List pointers.) For T4,
+ * there was only a single field to control this. For T5 there's the
+ * original field which now only applies to Unpacked Mode Free List
+ * buffers and a new field which only applies to Packed Mode Free List
+ * buffers.
*/
- s->fl_starve_thres
- = EGRTHRESHOLD_GET(t4_read_reg(adap, SGE_CONM_CTRL))*2 + 1;
+ sge_conm_ctrl = t4_read_reg(adap, SGE_CONM_CTRL);
+ if (is_t4(adap->params.chip))
+ egress_threshold = EGRTHRESHOLD_GET(sge_conm_ctrl);
+ else
+ egress_threshold = EGRTHRESHOLDPACKING_GET(sge_conm_ctrl);
+ s->fl_starve_thres = 2*egress_threshold + 1;
setup_timer(&s->rx_timer, sge_rx_timer_cb, (unsigned long)adap);
setup_timer(&s->tx_timer, sge_tx_timer_cb, (unsigned long)adap);
- s->starve_thres = core_ticks_per_usec(adap) * 1000000; /* 1 s */
- s->idma_state[0] = s->idma_state[1] = 0;
+ s->idma_1s_thresh = core_ticks_per_usec(adap) * 1000000; /* 1 s */
+ s->idma_stalled[0] = 0;
+ s->idma_stalled[1] = 0;
spin_lock_init(&s->intrq_lock);
return 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 2c10934..fb2fe65 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -573,7 +573,7 @@
{
u32 cclk_param, cclk_val;
int i, ret, addr;
- int ec, sn;
+ int ec, sn, pn;
u8 *vpd, csum;
unsigned int vpdr_len, kw_offset, id_len;
@@ -638,6 +638,7 @@
FIND_VPD_KW(ec, "EC");
FIND_VPD_KW(sn, "SN");
+ FIND_VPD_KW(pn, "PN");
#undef FIND_VPD_KW
memcpy(p->id, vpd + PCI_VPD_LRDT_TAG_SIZE, id_len);
@@ -647,6 +648,8 @@
i = pci_vpd_info_field_size(vpd + sn - PCI_VPD_INFO_FLD_HDR_SIZE);
memcpy(p->sn, vpd + sn, min(i, SERNUM_LEN));
strim(p->sn);
+ memcpy(p->pn, vpd + pn, min(i, PN_LEN));
+ strim(p->pn);
/*
* Ask firmware for the Core Clock since it knows how to translate the
@@ -1155,7 +1158,8 @@
}
#define ADVERT_MASK (FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G |\
- FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_ANEG)
+ FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_40G | \
+ FW_PORT_CAP_ANEG)
/**
* t4_link_start - apply link configuration to MAC/PHY
@@ -2247,6 +2251,36 @@
}
/**
+ * t4_get_port_type_description - return Port Type string description
+ * @port_type: firmware Port Type enumeration
+ */
+const char *t4_get_port_type_description(enum fw_port_type port_type)
+{
+ static const char *const port_type_description[] = {
+ "R XFI",
+ "R XAUI",
+ "T SGMII",
+ "T XFI",
+ "T XAUI",
+ "KX4",
+ "CX4",
+ "KX",
+ "KR",
+ "R SFP+",
+ "KR/KX",
+ "KR/KX/KX4",
+ "R QSFP_10G",
+ "",
+ "R QSFP",
+ "R BP40_BA",
+ };
+
+ if (port_type < ARRAY_SIZE(port_type_description))
+ return port_type_description[port_type];
+ return "UNKNOWN";
+}
+
+/**
* t4_get_port_stats - collect port statistics
* @adap: the adapter
* @idx: the port index
@@ -2563,6 +2597,112 @@
}
/**
+ * t4_sge_decode_idma_state - decode the idma state
+ * @adap: the adapter
+ * @state: the state idma is stuck in
+ */
+void t4_sge_decode_idma_state(struct adapter *adapter, int state)
+{
+ static const char * const t4_decode[] = {
+ "IDMA_IDLE",
+ "IDMA_PUSH_MORE_CPL_FIFO",
+ "IDMA_PUSH_CPL_MSG_HEADER_TO_FIFO",
+ "Not used",
+ "IDMA_PHYSADDR_SEND_PCIEHDR",
+ "IDMA_PHYSADDR_SEND_PAYLOAD_FIRST",
+ "IDMA_PHYSADDR_SEND_PAYLOAD",
+ "IDMA_SEND_FIFO_TO_IMSG",
+ "IDMA_FL_REQ_DATA_FL_PREP",
+ "IDMA_FL_REQ_DATA_FL",
+ "IDMA_FL_DROP",
+ "IDMA_FL_H_REQ_HEADER_FL",
+ "IDMA_FL_H_SEND_PCIEHDR",
+ "IDMA_FL_H_PUSH_CPL_FIFO",
+ "IDMA_FL_H_SEND_CPL",
+ "IDMA_FL_H_SEND_IP_HDR_FIRST",
+ "IDMA_FL_H_SEND_IP_HDR",
+ "IDMA_FL_H_REQ_NEXT_HEADER_FL",
+ "IDMA_FL_H_SEND_NEXT_PCIEHDR",
+ "IDMA_FL_H_SEND_IP_HDR_PADDING",
+ "IDMA_FL_D_SEND_PCIEHDR",
+ "IDMA_FL_D_SEND_CPL_AND_IP_HDR",
+ "IDMA_FL_D_REQ_NEXT_DATA_FL",
+ "IDMA_FL_SEND_PCIEHDR",
+ "IDMA_FL_PUSH_CPL_FIFO",
+ "IDMA_FL_SEND_CPL",
+ "IDMA_FL_SEND_PAYLOAD_FIRST",
+ "IDMA_FL_SEND_PAYLOAD",
+ "IDMA_FL_REQ_NEXT_DATA_FL",
+ "IDMA_FL_SEND_NEXT_PCIEHDR",
+ "IDMA_FL_SEND_PADDING",
+ "IDMA_FL_SEND_COMPLETION_TO_IMSG",
+ "IDMA_FL_SEND_FIFO_TO_IMSG",
+ "IDMA_FL_REQ_DATAFL_DONE",
+ "IDMA_FL_REQ_HEADERFL_DONE",
+ };
+ static const char * const t5_decode[] = {
+ "IDMA_IDLE",
+ "IDMA_ALMOST_IDLE",
+ "IDMA_PUSH_MORE_CPL_FIFO",
+ "IDMA_PUSH_CPL_MSG_HEADER_TO_FIFO",
+ "IDMA_SGEFLRFLUSH_SEND_PCIEHDR",
+ "IDMA_PHYSADDR_SEND_PCIEHDR",
+ "IDMA_PHYSADDR_SEND_PAYLOAD_FIRST",
+ "IDMA_PHYSADDR_SEND_PAYLOAD",
+ "IDMA_SEND_FIFO_TO_IMSG",
+ "IDMA_FL_REQ_DATA_FL",
+ "IDMA_FL_DROP",
+ "IDMA_FL_DROP_SEND_INC",
+ "IDMA_FL_H_REQ_HEADER_FL",
+ "IDMA_FL_H_SEND_PCIEHDR",
+ "IDMA_FL_H_PUSH_CPL_FIFO",
+ "IDMA_FL_H_SEND_CPL",
+ "IDMA_FL_H_SEND_IP_HDR_FIRST",
+ "IDMA_FL_H_SEND_IP_HDR",
+ "IDMA_FL_H_REQ_NEXT_HEADER_FL",
+ "IDMA_FL_H_SEND_NEXT_PCIEHDR",
+ "IDMA_FL_H_SEND_IP_HDR_PADDING",
+ "IDMA_FL_D_SEND_PCIEHDR",
+ "IDMA_FL_D_SEND_CPL_AND_IP_HDR",
+ "IDMA_FL_D_REQ_NEXT_DATA_FL",
+ "IDMA_FL_SEND_PCIEHDR",
+ "IDMA_FL_PUSH_CPL_FIFO",
+ "IDMA_FL_SEND_CPL",
+ "IDMA_FL_SEND_PAYLOAD_FIRST",
+ "IDMA_FL_SEND_PAYLOAD",
+ "IDMA_FL_REQ_NEXT_DATA_FL",
+ "IDMA_FL_SEND_NEXT_PCIEHDR",
+ "IDMA_FL_SEND_PADDING",
+ "IDMA_FL_SEND_COMPLETION_TO_IMSG",
+ };
+ static const u32 sge_regs[] = {
+ SGE_DEBUG_DATA_LOW_INDEX_2,
+ SGE_DEBUG_DATA_LOW_INDEX_3,
+ SGE_DEBUG_DATA_HIGH_INDEX_10,
+ };
+ const char **sge_idma_decode;
+ int sge_idma_decode_nstates;
+ int i;
+
+ if (is_t4(adapter->params.chip)) {
+ sge_idma_decode = (const char **)t4_decode;
+ sge_idma_decode_nstates = ARRAY_SIZE(t4_decode);
+ } else {
+ sge_idma_decode = (const char **)t5_decode;
+ sge_idma_decode_nstates = ARRAY_SIZE(t5_decode);
+ }
+
+ if (state < sge_idma_decode_nstates)
+ CH_WARN(adapter, "idma state %s\n", sge_idma_decode[state]);
+ else
+ CH_WARN(adapter, "idma state %d unknown\n", state);
+
+ for (i = 0; i < ARRAY_SIZE(sge_regs); i++)
+ CH_WARN(adapter, "SGE register %#x value %#x\n",
+ sge_regs[i], t4_read_reg(adapter, sge_regs[i]));
+}
+
+/**
* t4_fw_hello - establish communication with FW
* @adap: the adapter
* @mbox: mailbox to use for the FW command
@@ -3533,11 +3673,13 @@
if (stat & FW_PORT_CMD_TXPAUSE)
fc |= PAUSE_TX;
if (stat & FW_PORT_CMD_LSPEED(FW_PORT_CAP_SPEED_100M))
- speed = SPEED_100;
+ speed = 100;
else if (stat & FW_PORT_CMD_LSPEED(FW_PORT_CAP_SPEED_1G))
- speed = SPEED_1000;
+ speed = 1000;
else if (stat & FW_PORT_CMD_LSPEED(FW_PORT_CAP_SPEED_10G))
- speed = SPEED_10000;
+ speed = 10000;
+ else if (stat & FW_PORT_CMD_LSPEED(FW_PORT_CAP_SPEED_40G))
+ speed = 40000;
if (link_ok != lc->link_ok || speed != lc->speed ||
fc != lc->fc) { /* something changed */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index cd6874b..f2738c7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -116,6 +116,7 @@
CPL_ERR_KEEPALIVE_TIMEDOUT = 34,
CPL_ERR_RTX_NEG_ADVICE = 35,
CPL_ERR_PERSIST_NEG_ADVICE = 36,
+ CPL_ERR_KEEPALV_NEG_ADVICE = 37,
CPL_ERR_ABORT_FAILED = 42,
CPL_ERR_IWARP_FLM = 50,
};
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index 4082522..225ad8a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -230,6 +230,12 @@
#define EGRTHRESHOLD(x) ((x) << EGRTHRESHOLDshift)
#define EGRTHRESHOLD_GET(x) (((x) & EGRTHRESHOLD_MASK) >> EGRTHRESHOLDshift)
+#define EGRTHRESHOLDPACKING_MASK 0x3fU
+#define EGRTHRESHOLDPACKING_SHIFT 14
+#define EGRTHRESHOLDPACKING(x) ((x) << EGRTHRESHOLDPACKING_SHIFT)
+#define EGRTHRESHOLDPACKING_GET(x) (((x) >> EGRTHRESHOLDPACKING_SHIFT) & \
+ EGRTHRESHOLDPACKING_MASK)
+
#define SGE_DBFIFO_STATUS 0x10a4
#define HP_INT_THRESH_SHIFT 28
#define HP_INT_THRESH_MASK 0xfU
@@ -278,6 +284,9 @@
#define SGE_DEBUG_INDEX 0x10cc
#define SGE_DEBUG_DATA_HIGH 0x10d0
#define SGE_DEBUG_DATA_LOW 0x10d4
+#define SGE_DEBUG_DATA_LOW_INDEX_2 0x12c8
+#define SGE_DEBUG_DATA_LOW_INDEX_3 0x12cc
+#define SGE_DEBUG_DATA_HIGH_INDEX_10 0x12a8
#define SGE_INGRESS_QUEUES_PER_PAGE_PF 0x10f4
#define S_HP_INT_THRESH 28
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index 74fea74..9cc973f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -932,6 +932,7 @@
FW_PARAMS_PARAM_DEV_FWREV = 0x0B,
FW_PARAMS_PARAM_DEV_TPREV = 0x0C,
FW_PARAMS_PARAM_DEV_CF = 0x0D,
+ FW_PARAMS_PARAM_DEV_ULPTX_MEMWRITE_DSGL = 0x17,
};
/*
@@ -1742,6 +1743,9 @@
FW_PORT_TYPE_SFP,
FW_PORT_TYPE_BP_AP,
FW_PORT_TYPE_BP4_AP,
+ FW_PORT_TYPE_QSFP_10G,
+ FW_PORT_TYPE_QSFP,
+ FW_PORT_TYPE_BP40_BA,
FW_PORT_TYPE_NONE = FW_PORT_CMD_PTYPE_MASK
};
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 0899c09..5285928 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -2444,7 +2444,7 @@
*/
static int enable_msix(struct adapter *adapter)
{
- int i, err, want, need;
+ int i, want, need, nqsets;
struct msix_entry entries[MSIX_ENTRIES];
struct sge *s = &adapter->sge;
@@ -2460,26 +2460,23 @@
*/
want = s->max_ethqsets + MSIX_EXTRAS;
need = adapter->params.nports + MSIX_EXTRAS;
- while ((err = pci_enable_msix(adapter->pdev, entries, want)) >= need)
- want = err;
- if (err == 0) {
- int nqsets = want - MSIX_EXTRAS;
- if (nqsets < s->max_ethqsets) {
- dev_warn(adapter->pdev_dev, "only enough MSI-X vectors"
- " for %d Queue Sets\n", nqsets);
- s->max_ethqsets = nqsets;
- if (nqsets < s->ethqsets)
- reduce_ethqs(adapter, nqsets);
- }
- for (i = 0; i < want; ++i)
- adapter->msix_info[i].vec = entries[i].vector;
- } else if (err > 0) {
- pci_disable_msix(adapter->pdev);
- dev_info(adapter->pdev_dev, "only %d MSI-X vectors left,"
- " not using MSI-X\n", err);
+ want = pci_enable_msix_range(adapter->pdev, entries, need, want);
+ if (want < 0)
+ return want;
+
+ nqsets = want - MSIX_EXTRAS;
+ if (nqsets < s->max_ethqsets) {
+ dev_warn(adapter->pdev_dev, "only enough MSI-X vectors"
+ " for %d Queue Sets\n", nqsets);
+ s->max_ethqsets = nqsets;
+ if (nqsets < s->ethqsets)
+ reduce_ethqs(adapter, nqsets);
}
- return err;
+ for (i = 0; i < want; ++i)
+ adapter->msix_info[i].vec = entries[i].vector;
+
+ return 0;
}
static const struct net_device_ops cxgb4vf_netdev_ops = {
@@ -2947,6 +2944,14 @@
CH_DEVICE(0x5811, 0), /* T520-lp-cr */
CH_DEVICE(0x5812, 0), /* T560-cr */
CH_DEVICE(0x5813, 0), /* T580-cr */
+ CH_DEVICE(0x5814, 0), /* T580-so-cr */
+ CH_DEVICE(0x5815, 0), /* T502-bt */
+ CH_DEVICE(0x5880, 0),
+ CH_DEVICE(0x5881, 0),
+ CH_DEVICE(0x5882, 0),
+ CH_DEVICE(0x5883, 0),
+ CH_DEVICE(0x5884, 0),
+ CH_DEVICE(0x5885, 0),
{ 0, }
};
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 0a89963..9cfa4b4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -401,7 +401,7 @@
if (sdesc->skb) {
if (need_unmap)
unmap_sgl(dev, sdesc->skb, sdesc->sgl, tq);
- kfree_skb(sdesc->skb);
+ dev_consume_skb_any(sdesc->skb);
sdesc->skb = NULL;
}
@@ -1275,7 +1275,7 @@
* need it any longer.
*/
inline_tx_skb(skb, &txq->q, cpl + 1);
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
} else {
/*
* Write the skb's Scatter/Gather list into the TX Packet CPL
@@ -1354,7 +1354,7 @@
* An error of some sort happened. Free the TX skb and tell the
* OS that we've "dealt" with the packet ...
*/
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c
index 19f642a..fe84fba 100644
--- a/drivers/net/ethernet/cirrus/cs89x0.c
+++ b/drivers/net/ethernet/cirrus/cs89x0.c
@@ -1174,7 +1174,7 @@
writewords(lp, TX_FRAME_PORT, skb->data, (skb->len + 1) >> 1);
spin_unlock_irqrestore(&lp->lock, flags);
dev->stats.tx_bytes += skb->len;
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
/* We DO NOT call netif_wake_queue() here.
* We also DO NOT call netif_start_queue().
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index b740bfc..2945718 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -521,7 +521,7 @@
unsigned int txq_map;
if (skb->len <= 0) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -536,7 +536,7 @@
if (skb_shinfo(skb)->gso_size == 0 &&
skb_shinfo(skb)->nr_frags + 1 > ENIC_NON_TSO_MAX_DESC &&
skb_linearize(skb)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -1086,14 +1086,15 @@
unsigned int intr = enic_legacy_io_intr();
unsigned int rq_work_to_do = budget;
unsigned int wq_work_to_do = -1; /* no limit */
- unsigned int work_done, rq_work_done, wq_work_done;
+ unsigned int work_done, rq_work_done = 0, wq_work_done;
int err;
/* Service RQ (first) and WQ
*/
- rq_work_done = vnic_cq_service(&enic->cq[cq_rq],
- rq_work_to_do, enic_rq_service, NULL);
+ if (budget > 0)
+ rq_work_done = vnic_cq_service(&enic->cq[cq_rq],
+ rq_work_to_do, enic_rq_service, NULL);
wq_work_done = vnic_cq_service(&enic->cq[cq_wq],
wq_work_to_do, enic_wq_service, NULL);
@@ -1141,14 +1142,15 @@
unsigned int cq = enic_cq_rq(enic, rq);
unsigned int intr = enic_msix_rq_intr(enic, rq);
unsigned int work_to_do = budget;
- unsigned int work_done;
+ unsigned int work_done = 0;
int err;
/* Service RQ
*/
- work_done = vnic_cq_service(&enic->cq[cq],
- work_to_do, enic_rq_service, NULL);
+ if (budget > 0)
+ work_done = vnic_cq_service(&enic->cq[cq],
+ work_to_do, enic_rq_service, NULL);
/* Return intr event credits for this polling
* cycle. An intr event is the completion of a
@@ -1796,7 +1798,8 @@
enic->cq_count >= n + m &&
enic->intr_count >= n + m + 2) {
- if (!pci_enable_msix(enic->pdev, enic->msix_entry, n + m + 2)) {
+ if (pci_enable_msix_range(enic->pdev, enic->msix_entry,
+ n + m + 2, n + m + 2) > 0) {
enic->rq_count = n;
enic->wq_count = m;
@@ -1815,7 +1818,8 @@
enic->wq_count >= m &&
enic->cq_count >= 1 + m &&
enic->intr_count >= 1 + m + 2) {
- if (!pci_enable_msix(enic->pdev, enic->msix_entry, 1 + m + 2)) {
+ if (pci_enable_msix_range(enic->pdev, enic->msix_entry,
+ 1 + m + 2, 1 + m + 2) > 0) {
enic->rq_count = 1;
enic->wq_count = m;
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index a1a2b40..8c4b93b 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1033,7 +1033,7 @@
spin_unlock_irqrestore(&db->lock, flags);
/* free this SKB */
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c
index 5ad9e3e..53f0c61 100644
--- a/drivers/net/ethernet/dec/tulip/dmfe.c
+++ b/drivers/net/ethernet/dec/tulip/dmfe.c
@@ -696,7 +696,7 @@
/* Too large packet check */
if (skb->len > MAX_PACKET_SIZE) {
pr_err("big packet = %d\n", (u16)skb->len);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -743,7 +743,7 @@
dw32(DCR7, db->cr7_data);
/* free this SKB */
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index add05f1..1642de7 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -1939,6 +1939,7 @@
pci_iounmap(pdev, tp->base_addr);
free_netdev (dev);
pci_release_regions (pdev);
+ pci_disable_device(pdev);
/* pci_power_off (pdev, -1); */
}
diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c
index aa4ee38..aa801a6 100644
--- a/drivers/net/ethernet/dec/tulip/uli526x.c
+++ b/drivers/net/ethernet/dec/tulip/uli526x.c
@@ -607,7 +607,7 @@
/* Too large packet check */
if (skb->len > MAX_PACKET_SIZE) {
netdev_err(dev, "big packet = %d\n", (u16)skb->len);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -648,7 +648,7 @@
uw32(DCR7, db->cr7_data);
/* free this SKB */
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index 113cd79..d9e5ca0 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -1137,7 +1137,7 @@
return NETDEV_TX_OK;
drop_frame:
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
np->tx_skbuff[entry] = NULL;
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c
index 8a79a32..e9b0fab 100644
--- a/drivers/net/ethernet/dnet.c
+++ b/drivers/net/ethernet/dnet.c
@@ -170,11 +170,6 @@
return 0;
}
-static int dnet_mdio_reset(struct mii_bus *bus)
-{
- return 0;
-}
-
static void dnet_handle_link_change(struct net_device *dev)
{
struct dnet *bp = netdev_priv(dev);
@@ -322,7 +317,6 @@
bp->mii_bus->name = "dnet_mii_bus";
bp->mii_bus->read = &dnet_mdio_read;
bp->mii_bus->write = &dnet_mdio_write;
- bp->mii_bus->reset = &dnet_mdio_reset;
snprintf(bp->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
bp->pdev->name, bp->pdev->id);
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 8d09615..8ccaa25 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2005 - 2013 Emulex
+ * Copyright (C) 2005 - 2014 Emulex
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
@@ -34,7 +34,7 @@
#include "be_hw.h"
#include "be_roce.h"
-#define DRV_VER "10.0.600.0u"
+#define DRV_VER "10.2u"
#define DRV_NAME "be2net"
#define BE_NAME "Emulex BladeEngine2"
#define BE3_NAME "Emulex BladeEngine3"
@@ -88,7 +88,6 @@
#define BE_MIN_MTU 256
#define BE_NUM_VLANS_SUPPORTED 64
-#define BE_UMC_NUM_VLANS_SUPPORTED 15
#define BE_MAX_EQD 128u
#define BE_MAX_TX_FRAG_COUNT 30
@@ -262,9 +261,10 @@
/* Struct to remember the pages posted for rx frags */
struct be_rx_page_info {
struct page *page;
+ /* set to page-addr for last frag of the page & frag-addr otherwise */
DEFINE_DMA_UNMAP_ADDR(bus);
u16 page_offset;
- bool last_page_user;
+ bool last_frag; /* last frag of the page */
};
struct be_rx_stats {
@@ -293,9 +293,10 @@
u8 ip_csum;
u8 l4_csum;
u8 ipv6;
- u8 vtm;
+ u8 qnq;
u8 pkt_type;
u8 ip_frag;
+ u8 tunneled;
};
struct be_rx_obj {
@@ -350,13 +351,16 @@
u32 roce_drops_crc;
};
+/* A vlan-id of 0xFFFF must be used to clear transparent vlan-tagging */
+#define BE_RESET_VLAN_TAG_ID 0xFFFF
+
struct be_vf_cfg {
unsigned char mac_addr[ETH_ALEN];
int if_handle;
int pmac_id;
- u16 def_vid;
u16 vlan_tag;
u32 tx_rate;
+ u32 plink_tracking;
};
enum vf_state {
@@ -368,10 +372,11 @@
#define BE_FLAGS_WORKER_SCHEDULED (1 << 3)
#define BE_FLAGS_VLAN_PROMISC (1 << 4)
#define BE_FLAGS_NAPI_ENABLED (1 << 9)
-#define BE_UC_PMAC_COUNT 30
-#define BE_VF_UC_PMAC_COUNT 2
#define BE_FLAGS_QNQ_ASYNC_EVT_RCVD (1 << 11)
+#define BE_FLAGS_VXLAN_OFFLOADS (1 << 12)
+#define BE_UC_PMAC_COUNT 30
+#define BE_VF_UC_PMAC_COUNT 2
/* Ethtool set_dump flags */
#define LANCER_INITIATE_FW_DUMP 0x1
@@ -465,6 +470,7 @@
u32 port_num;
bool promiscuous;
+ u8 mc_type;
u32 function_mode;
u32 function_caps;
u32 rx_fc; /* Rx flow control */
@@ -490,6 +496,7 @@
u32 sli_family;
u8 hba_port_num;
u16 pvid;
+ __be16 vxlan_port;
struct phy_info phy;
u8 wol_cap;
bool wol_en;
@@ -534,6 +541,14 @@
return min_t(u16, num, num_online_cpus());
}
+/* Is BE in pvid_tagging mode */
+#define be_pvid_tagging_enabled(adapter) (adapter->pvid)
+
+/* Is BE in QNQ multi-channel mode */
+#define be_is_qnq_mode(adapter) (adapter->mc_type == FLEX10 || \
+ adapter->mc_type == vNIC1 || \
+ adapter->mc_type == UFP)
+
#define lancer_chip(adapter) (adapter->pdev->device == OC_DEVICE_ID3 || \
adapter->pdev->device == OC_DEVICE_ID4)
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 48076a6..d1ec15a 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2005 - 2013 Emulex
+ * Copyright (C) 2005 - 2014 Emulex
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
@@ -202,8 +202,12 @@
/* When link status changes, link speed must be re-queried from FW */
adapter->phy.link_speed = -1;
- /* Ignore physical link event */
- if (lancer_chip(adapter) &&
+ /* On BEx the FW does not send a separate link status
+ * notification for physical and logical link.
+ * On other chips just process the logical link
+ * status notification
+ */
+ if (!BEx_chip(adapter) &&
!(evt->port_link_status & LOGICAL_LINK_STATUS_MASK))
return;
@@ -211,7 +215,8 @@
* it may not be received in some cases.
*/
if (adapter->flags & BE_FLAGS_LINK_STATUS_INIT)
- be_link_status_update(adapter, evt->port_link_status);
+ be_link_status_update(adapter,
+ evt->port_link_status & LINK_STATUS_MASK);
}
/* Grp5 CoS Priority evt */
@@ -239,10 +244,12 @@
static void be_async_grp5_pvid_state_process(struct be_adapter *adapter,
struct be_async_event_grp5_pvid_state *evt)
{
- if (evt->enabled)
+ if (evt->enabled) {
adapter->pvid = le16_to_cpu(evt->tag) & VLAN_VID_MASK;
- else
+ dev_info(&adapter->pdev->dev, "LPVID: %d\n", adapter->pvid);
+ } else {
adapter->pvid = 0;
+ }
}
static void be_async_grp5_evt_process(struct be_adapter *adapter,
@@ -3296,6 +3303,21 @@
return NULL;
}
+static struct be_port_res_desc *be_get_port_desc(u8 *buf, u32 desc_count)
+{
+ struct be_res_desc_hdr *hdr = (struct be_res_desc_hdr *)buf;
+ int i;
+
+ for (i = 0; i < desc_count; i++) {
+ if (hdr->desc_type == PORT_RESOURCE_DESC_TYPE_V1)
+ return (struct be_port_res_desc *)hdr;
+
+ hdr->desc_len = hdr->desc_len ? : RESOURCE_DESC_SIZE_V0;
+ hdr = (void *)hdr + hdr->desc_len;
+ }
+ return NULL;
+}
+
static void be_copy_nic_desc(struct be_resources *res,
struct be_nic_res_desc *desc)
{
@@ -3439,6 +3461,7 @@
{
struct be_cmd_resp_get_profile_config *resp;
struct be_pcie_res_desc *pcie;
+ struct be_port_res_desc *port;
struct be_nic_res_desc *nic;
struct be_queue_info *mccq = &adapter->mcc_obj.q;
struct be_dma_mem cmd;
@@ -3466,6 +3489,10 @@
if (pcie)
res->max_vfs = le16_to_cpu(pcie->num_vfs);
+ port = be_get_port_desc(resp->func_param, desc_count);
+ if (port)
+ adapter->mc_type = port->mc_type;
+
nic = be_get_nic_desc(resp->func_param, desc_count);
if (nic)
be_copy_nic_desc(res, nic);
@@ -3476,14 +3503,11 @@
return status;
}
-/* Currently only Lancer uses this command and it supports version 0 only
- * Uses sync mcc
- */
-int be_cmd_set_profile_config(struct be_adapter *adapter, u32 bps,
- u8 domain)
+int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
+ int size, u8 version, u8 domain)
{
- struct be_mcc_wrb *wrb;
struct be_cmd_req_set_profile_config *req;
+ struct be_mcc_wrb *wrb;
int status;
spin_lock_bh(&adapter->mcc_lock);
@@ -3495,44 +3519,116 @@
}
req = embedded_payload(wrb);
-
be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
OPCODE_COMMON_SET_PROFILE_CONFIG, sizeof(*req),
wrb, NULL);
+ req->hdr.version = version;
req->hdr.domain = domain;
req->desc_count = cpu_to_le32(1);
- req->nic_desc.hdr.desc_type = NIC_RESOURCE_DESC_TYPE_V0;
- req->nic_desc.hdr.desc_len = RESOURCE_DESC_SIZE_V0;
- req->nic_desc.flags = (1 << QUN) | (1 << IMM) | (1 << NOSV);
- req->nic_desc.pf_num = adapter->pf_number;
- req->nic_desc.vf_num = domain;
+ memcpy(req->desc, desc, size);
- /* Mark fields invalid */
- req->nic_desc.unicast_mac_count = 0xFFFF;
- req->nic_desc.mcc_count = 0xFFFF;
- req->nic_desc.vlan_count = 0xFFFF;
- req->nic_desc.mcast_mac_count = 0xFFFF;
- req->nic_desc.txq_count = 0xFFFF;
- req->nic_desc.rq_count = 0xFFFF;
- req->nic_desc.rssq_count = 0xFFFF;
- req->nic_desc.lro_count = 0xFFFF;
- req->nic_desc.cq_count = 0xFFFF;
- req->nic_desc.toe_conn_count = 0xFFFF;
- req->nic_desc.eq_count = 0xFFFF;
- req->nic_desc.link_param = 0xFF;
- req->nic_desc.bw_min = 0xFFFFFFFF;
- req->nic_desc.acpi_params = 0xFF;
- req->nic_desc.wol_param = 0x0F;
-
- /* Change BW */
- req->nic_desc.bw_min = cpu_to_le32(bps);
- req->nic_desc.bw_max = cpu_to_le32(bps);
status = be_mcc_notify_wait(adapter);
err:
spin_unlock_bh(&adapter->mcc_lock);
return status;
}
+/* Mark all fields invalid */
+void be_reset_nic_desc(struct be_nic_res_desc *nic)
+{
+ memset(nic, 0, sizeof(*nic));
+ nic->unicast_mac_count = 0xFFFF;
+ nic->mcc_count = 0xFFFF;
+ nic->vlan_count = 0xFFFF;
+ nic->mcast_mac_count = 0xFFFF;
+ nic->txq_count = 0xFFFF;
+ nic->rq_count = 0xFFFF;
+ nic->rssq_count = 0xFFFF;
+ nic->lro_count = 0xFFFF;
+ nic->cq_count = 0xFFFF;
+ nic->toe_conn_count = 0xFFFF;
+ nic->eq_count = 0xFFFF;
+ nic->link_param = 0xFF;
+ nic->acpi_params = 0xFF;
+ nic->wol_param = 0x0F;
+ nic->bw_min = 0xFFFFFFFF;
+ nic->bw_max = 0xFFFFFFFF;
+}
+
+int be_cmd_config_qos(struct be_adapter *adapter, u32 bps, u8 domain)
+{
+ if (lancer_chip(adapter)) {
+ struct be_nic_res_desc nic_desc;
+
+ be_reset_nic_desc(&nic_desc);
+ nic_desc.hdr.desc_type = NIC_RESOURCE_DESC_TYPE_V0;
+ nic_desc.hdr.desc_len = RESOURCE_DESC_SIZE_V0;
+ nic_desc.flags = (1 << QUN_SHIFT) | (1 << IMM_SHIFT) |
+ (1 << NOSV_SHIFT);
+ nic_desc.pf_num = adapter->pf_number;
+ nic_desc.vf_num = domain;
+ nic_desc.bw_max = cpu_to_le32(bps);
+
+ return be_cmd_set_profile_config(adapter, &nic_desc,
+ RESOURCE_DESC_SIZE_V0,
+ 0, domain);
+ } else {
+ return be_cmd_set_qos(adapter, bps, domain);
+ }
+}
+
+int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
+{
+ struct be_mcc_wrb *wrb;
+ struct be_cmd_req_manage_iface_filters *req;
+ int status;
+
+ if (iface == 0xFFFFFFFF)
+ return -1;
+
+ spin_lock_bh(&adapter->mcc_lock);
+
+ wrb = wrb_from_mccq(adapter);
+ if (!wrb) {
+ status = -EBUSY;
+ goto err;
+ }
+ req = embedded_payload(wrb);
+
+ be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+ OPCODE_COMMON_MANAGE_IFACE_FILTERS, sizeof(*req),
+ wrb, NULL);
+ req->op = op;
+ req->target_iface_id = cpu_to_le32(iface);
+
+ status = be_mcc_notify_wait(adapter);
+err:
+ spin_unlock_bh(&adapter->mcc_lock);
+ return status;
+}
+
+int be_cmd_set_vxlan_port(struct be_adapter *adapter, __be16 port)
+{
+ struct be_port_res_desc port_desc;
+
+ memset(&port_desc, 0, sizeof(port_desc));
+ port_desc.hdr.desc_type = PORT_RESOURCE_DESC_TYPE_V1;
+ port_desc.hdr.desc_len = RESOURCE_DESC_SIZE_V1;
+ port_desc.flags = (1 << IMM_SHIFT) | (1 << NOSV_SHIFT);
+ port_desc.link_num = adapter->hba_port_num;
+ if (port) {
+ port_desc.nv_flags = NV_TYPE_VXLAN | (1 << SOCVID_SHIFT) |
+ (1 << RCVID_SHIFT);
+ port_desc.nv_port = swab16(port);
+ } else {
+ port_desc.nv_flags = NV_TYPE_DISABLED;
+ port_desc.nv_port = 0;
+ }
+
+ return be_cmd_set_profile_config(adapter, &port_desc,
+ RESOURCE_DESC_SIZE_V1, 1, 0);
+}
+
int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
int vf_num)
{
@@ -3723,6 +3819,45 @@
return status;
}
+int be_cmd_set_logical_link_config(struct be_adapter *adapter,
+ int link_state, u8 domain)
+{
+ struct be_mcc_wrb *wrb;
+ struct be_cmd_req_set_ll_link *req;
+ int status;
+
+ if (BEx_chip(adapter) || lancer_chip(adapter))
+ return 0;
+
+ spin_lock_bh(&adapter->mcc_lock);
+
+ wrb = wrb_from_mccq(adapter);
+ if (!wrb) {
+ status = -EBUSY;
+ goto err;
+ }
+
+ req = embedded_payload(wrb);
+
+ be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+ OPCODE_COMMON_SET_LOGICAL_LINK_CONFIG,
+ sizeof(*req), wrb, NULL);
+
+ req->hdr.version = 1;
+ req->hdr.domain = domain;
+
+ if (link_state == IFLA_VF_LINK_STATE_ENABLE)
+ req->link_config |= 1;
+
+ if (link_state == IFLA_VF_LINK_STATE_AUTO)
+ req->link_config |= 1 << PLINK_TRACK_SHIFT;
+
+ status = be_mcc_notify_wait(adapter);
+err:
+ spin_unlock_bh(&adapter->mcc_lock);
+ return status;
+}
+
int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
int wrb_payload_size, u16 *cmd_status, u16 *ext_status)
{
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index fc4e076..b60e4d5 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2005 - 2013 Emulex
+ * Copyright (C) 2005 - 2014 Emulex
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
@@ -203,6 +203,7 @@
#define OPCODE_COMMON_GET_BEACON_STATE 70
#define OPCODE_COMMON_READ_TRANSRECV_DATA 73
#define OPCODE_COMMON_GET_PORT_NAME 77
+#define OPCODE_COMMON_SET_LOGICAL_LINK_CONFIG 80
#define OPCODE_COMMON_SET_INTERRUPT_ENABLE 89
#define OPCODE_COMMON_SET_FN_PRIVILEGES 100
#define OPCODE_COMMON_GET_PHY_DETAILS 102
@@ -221,6 +222,7 @@
#define OPCODE_COMMON_GET_FN_PRIVILEGES 170
#define OPCODE_COMMON_READ_OBJECT 171
#define OPCODE_COMMON_WRITE_OBJECT 172
+#define OPCODE_COMMON_MANAGE_IFACE_FILTERS 193
#define OPCODE_COMMON_GET_IFACE_LIST 194
#define OPCODE_COMMON_ENABLE_DISABLE_VF 196
@@ -1098,14 +1100,6 @@
u32 function_caps;
};
-/* Is BE in a multi-channel mode */
-static inline bool be_is_mc(struct be_adapter *adapter)
-{
- return adapter->function_mode & FLEX10_MODE ||
- adapter->function_mode & VNIC_MODE ||
- adapter->function_mode & UMC_ENABLED;
-}
-
/******************** RSS Config ****************************************/
/* RSS type Input parameters used to compute RX hash
* RSS_ENABLE_IPV4 SRC IPv4, DST IPv4
@@ -1828,20 +1822,36 @@
#define NIC_RESOURCE_DESC_TYPE_V0 0x41
#define PCIE_RESOURCE_DESC_TYPE_V1 0x50
#define NIC_RESOURCE_DESC_TYPE_V1 0x51
+#define PORT_RESOURCE_DESC_TYPE_V1 0x55
#define MAX_RESOURCE_DESC 264
-/* QOS unit number */
-#define QUN 4
-/* Immediate */
-#define IMM 6
-/* No save */
-#define NOSV 7
+#define IMM_SHIFT 6 /* Immediate */
+#define NOSV_SHIFT 7 /* No save */
struct be_res_desc_hdr {
u8 desc_type;
u8 desc_len;
} __packed;
+struct be_port_res_desc {
+ struct be_res_desc_hdr hdr;
+ u8 rsvd0;
+ u8 flags;
+ u8 link_num;
+ u8 mc_type;
+ u16 rsvd1;
+
+#define NV_TYPE_MASK 0x3 /* bits 0-1 */
+#define NV_TYPE_DISABLED 1
+#define NV_TYPE_VXLAN 3
+#define SOCVID_SHIFT 2 /* Strip outer vlan */
+#define RCVID_SHIFT 4 /* Report vlan */
+ u8 nv_flags;
+ u8 rsvd2;
+ __le16 nv_port; /* vxlan/gre port */
+ u32 rsvd3[19];
+} __packed;
+
struct be_pcie_res_desc {
struct be_res_desc_hdr hdr;
u8 rsvd0;
@@ -1862,6 +1872,8 @@
struct be_nic_res_desc {
struct be_res_desc_hdr hdr;
u8 rsvd1;
+
+#define QUN_SHIFT 4 /* QoS is in absolute units */
u8 flags;
u8 vf_num;
u8 rsvd2;
@@ -1891,6 +1903,23 @@
u32 rsvd8[7];
} __packed;
+/************ Multi-Channel type ***********/
+enum mc_type {
+ MC_NONE = 0x01,
+ UMC = 0x02,
+ FLEX10 = 0x03,
+ vNIC1 = 0x04,
+ nPAR = 0x05,
+ UFP = 0x06,
+ vNIC2 = 0x07
+};
+
+/* Is BE in a multi-channel mode */
+static inline bool be_is_mc(struct be_adapter *adapter)
+{
+ return adapter->mc_type > MC_NONE;
+}
+
struct be_cmd_req_get_func_config {
struct be_cmd_req_hdr hdr;
};
@@ -1919,7 +1948,7 @@
struct be_cmd_req_hdr hdr;
u32 rsvd;
u32 desc_count;
- struct be_nic_res_desc nic_desc;
+ u8 desc[RESOURCE_DESC_SIZE_V1];
};
struct be_cmd_resp_set_profile_config {
@@ -1971,6 +2000,33 @@
struct be_if_desc if_desc;
};
+/*************** Set logical link ********************/
+#define PLINK_TRACK_SHIFT 8
+struct be_cmd_req_set_ll_link {
+ struct be_cmd_req_hdr hdr;
+ u32 link_config; /* Bit 0: UP_DOWN, Bit 9: PLINK */
+};
+
+/************** Manage IFACE Filters *******************/
+#define OP_CONVERT_NORMAL_TO_TUNNEL 0
+#define OP_CONVERT_TUNNEL_TO_NORMAL 1
+
+struct be_cmd_req_manage_iface_filters {
+ struct be_cmd_req_hdr hdr;
+ u8 op;
+ u8 rsvd0;
+ u8 flags;
+ u8 rsvd1;
+ u32 tunnel_iface_id;
+ u32 target_iface_id;
+ u8 mac[6];
+ u16 vlan_tag;
+ u32 tenant_id;
+ u32 filter_id;
+ u32 cap_flags;
+ u32 cap_control_flags;
+} __packed;
+
int be_pci_fnum_get(struct be_adapter *adapter);
int be_fw_wait_ready(struct be_adapter *adapter);
int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
@@ -2045,7 +2101,7 @@
int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
u8 loopback_type, u8 enable);
int be_cmd_get_phy_info(struct be_adapter *adapter);
-int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain);
+int be_cmd_config_qos(struct be_adapter *adapter, u32 bps, u8 domain);
void be_detect_error(struct be_adapter *adapter);
int be_cmd_get_die_temperature(struct be_adapter *adapter);
int be_cmd_get_cntl_attributes(struct be_adapter *adapter);
@@ -2086,9 +2142,14 @@
struct be_resources *res);
int be_cmd_get_profile_config(struct be_adapter *adapter,
struct be_resources *res, u8 domain);
-int be_cmd_set_profile_config(struct be_adapter *adapter, u32 bps, u8 domain);
+int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
+ int size, u8 version, u8 domain);
int be_cmd_get_active_profile(struct be_adapter *adapter, u16 *profile);
int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
int vf_num);
int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain);
int be_cmd_intr_set(struct be_adapter *adapter, bool intr_enable);
+int be_cmd_set_logical_link_config(struct be_adapter *adapter,
+ int link_state, u8 domain);
+int be_cmd_set_vxlan_port(struct be_adapter *adapter, __be16 port);
+int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op);
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 05be007..15ba96c 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2005 - 2013 Emulex
+ * Copyright (C) 2005 - 2014 Emulex
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
@@ -357,10 +357,10 @@
struct be_rx_stats *stats = rx_stats(rxo);
do {
- start = u64_stats_fetch_begin_bh(&stats->sync);
+ start = u64_stats_fetch_begin_irq(&stats->sync);
data[base] = stats->rx_bytes;
data[base + 1] = stats->rx_pkts;
- } while (u64_stats_fetch_retry_bh(&stats->sync, start));
+ } while (u64_stats_fetch_retry_irq(&stats->sync, start));
for (i = 2; i < ETHTOOL_RXSTATS_NUM; i++) {
p = (u8 *)stats + et_rx_stats[i].offset;
@@ -373,19 +373,19 @@
struct be_tx_stats *stats = tx_stats(txo);
do {
- start = u64_stats_fetch_begin_bh(&stats->sync_compl);
+ start = u64_stats_fetch_begin_irq(&stats->sync_compl);
data[base] = stats->tx_compl;
- } while (u64_stats_fetch_retry_bh(&stats->sync_compl, start));
+ } while (u64_stats_fetch_retry_irq(&stats->sync_compl, start));
do {
- start = u64_stats_fetch_begin_bh(&stats->sync);
+ start = u64_stats_fetch_begin_irq(&stats->sync);
for (i = 1; i < ETHTOOL_TXSTATS_NUM; i++) {
p = (u8 *)stats + et_tx_stats[i].offset;
data[base + i] =
(et_tx_stats[i].size == sizeof(u64)) ?
*(u64 *)p : *(u32 *)p;
}
- } while (u64_stats_fetch_retry_bh(&stats->sync, start));
+ } while (u64_stats_fetch_retry_irq(&stats->sync, start));
base += ETHTOOL_TXSTATS_NUM;
}
}
@@ -802,16 +802,18 @@
if (test->flags & ETH_TEST_FL_OFFLINE) {
if (be_loopback_test(adapter, BE_MAC_LOOPBACK,
- &data[0]) != 0) {
+ &data[0]) != 0)
test->flags |= ETH_TEST_FL_FAILED;
- }
+
if (be_loopback_test(adapter, BE_PHY_LOOPBACK,
- &data[1]) != 0) {
+ &data[1]) != 0)
test->flags |= ETH_TEST_FL_FAILED;
- }
- if (be_loopback_test(adapter, BE_ONE_PORT_EXT_LOOPBACK,
- &data[2]) != 0) {
- test->flags |= ETH_TEST_FL_FAILED;
+
+ if (test->flags & ETH_TEST_FL_EXTERNAL_LB) {
+ if (be_loopback_test(adapter, BE_ONE_PORT_EXT_LOOPBACK,
+ &data[2]) != 0)
+ test->flags |= ETH_TEST_FL_FAILED;
+ test->flags |= ETH_TEST_FL_EXTERNAL_LB_DONE;
}
}
diff --git a/drivers/net/ethernet/emulex/benet/be_hw.h b/drivers/net/ethernet/emulex/benet/be_hw.h
index dc88782..3bd1985 100644
--- a/drivers/net/ethernet/emulex/benet/be_hw.h
+++ b/drivers/net/ethernet/emulex/benet/be_hw.h
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2005 - 2013 Emulex
+ * Copyright (C) 2005 - 2014 Emulex
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
@@ -368,7 +368,7 @@
u8 numfrags[3]; /* dword 1 */
u8 rss_flush; /* dword 2 */
u8 cast_enc[2]; /* dword 2 */
- u8 vtm; /* dword 2 */
+ u8 qnq; /* dword 2 */
u8 rss_bank; /* dword 2 */
u8 rsvd1[23]; /* dword 2 */
u8 lro_pkt; /* dword 2 */
@@ -401,13 +401,14 @@
u8 numfrags[3]; /* dword 1 */
u8 rss_flush; /* dword 2 */
u8 cast_enc[2]; /* dword 2 */
- u8 vtm; /* dword 2 */
+ u8 qnq; /* dword 2 */
u8 rss_bank; /* dword 2 */
u8 port[2]; /* dword 2 */
u8 vntagp; /* dword 2 */
u8 header_len[8]; /* dword 2 */
u8 header_split[2]; /* dword 2 */
- u8 rsvd1[13]; /* dword 2 */
+ u8 rsvd1[12]; /* dword 2 */
+ u8 tunneled;
u8 valid; /* dword 2 */
u8 rsshash[32]; /* dword 3 */
} __packed;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 04ac9c6..c89dc85 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2005 - 2013 Emulex
+ * Copyright (C) 2005 - 2014 Emulex
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
@@ -23,6 +23,7 @@
#include <linux/aer.h>
#include <linux/if_bridge.h>
#include <net/busy_poll.h>
+#include <net/vxlan.h>
MODULE_VERSION(DRV_VER);
MODULE_DEVICE_TABLE(pci, be_dev_ids);
@@ -591,10 +592,10 @@
for_all_rx_queues(adapter, rxo, i) {
const struct be_rx_stats *rx_stats = rx_stats(rxo);
do {
- start = u64_stats_fetch_begin_bh(&rx_stats->sync);
+ start = u64_stats_fetch_begin_irq(&rx_stats->sync);
pkts = rx_stats(rxo)->rx_pkts;
bytes = rx_stats(rxo)->rx_bytes;
- } while (u64_stats_fetch_retry_bh(&rx_stats->sync, start));
+ } while (u64_stats_fetch_retry_irq(&rx_stats->sync, start));
stats->rx_packets += pkts;
stats->rx_bytes += bytes;
stats->multicast += rx_stats(rxo)->rx_mcast_pkts;
@@ -605,10 +606,10 @@
for_all_tx_queues(adapter, txo, i) {
const struct be_tx_stats *tx_stats = tx_stats(txo);
do {
- start = u64_stats_fetch_begin_bh(&tx_stats->sync);
+ start = u64_stats_fetch_begin_irq(&tx_stats->sync);
pkts = tx_stats(txo)->tx_pkts;
bytes = tx_stats(txo)->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tx_stats->sync, start));
+ } while (u64_stats_fetch_retry_irq(&tx_stats->sync, start));
stats->tx_packets += pkts;
stats->tx_bytes += bytes;
}
@@ -652,7 +653,7 @@
adapter->flags |= BE_FLAGS_LINK_STATUS_INIT;
}
- if ((link_status & LINK_STATUS_MASK) == LINK_UP)
+ if (link_status)
netif_carrier_on(netdev);
else
netif_carrier_off(netdev);
@@ -718,10 +719,23 @@
return vlan_tag;
}
+/* Used only for IP tunnel packets */
+static u16 skb_inner_ip_proto(struct sk_buff *skb)
+{
+ return (inner_ip_hdr(skb)->version == 4) ?
+ inner_ip_hdr(skb)->protocol : inner_ipv6_hdr(skb)->nexthdr;
+}
+
+static u16 skb_ip_proto(struct sk_buff *skb)
+{
+ return (ip_hdr(skb)->version == 4) ?
+ ip_hdr(skb)->protocol : ipv6_hdr(skb)->nexthdr;
+}
+
static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr,
struct sk_buff *skb, u32 wrb_cnt, u32 len, bool skip_hw_vlan)
{
- u16 vlan_tag;
+ u16 vlan_tag, proto;
memset(hdr, 0, sizeof(*hdr));
@@ -734,9 +748,15 @@
if (skb_is_gso_v6(skb) && !lancer_chip(adapter))
AMAP_SET_BITS(struct amap_eth_hdr_wrb, lso6, hdr, 1);
} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
- if (is_tcp_pkt(skb))
+ if (skb->encapsulation) {
+ AMAP_SET_BITS(struct amap_eth_hdr_wrb, ipcs, hdr, 1);
+ proto = skb_inner_ip_proto(skb);
+ } else {
+ proto = skb_ip_proto(skb);
+ }
+ if (proto == IPPROTO_TCP)
AMAP_SET_BITS(struct amap_eth_hdr_wrb, tcpcs, hdr, 1);
- else if (is_udp_pkt(skb))
+ else if (proto == IPPROTO_UDP)
AMAP_SET_BITS(struct amap_eth_hdr_wrb, udpcs, hdr, 1);
}
@@ -913,24 +933,14 @@
return BE3_chip(adapter) && be_ipv6_exthdr_check(skb);
}
-static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter,
- struct sk_buff *skb,
- bool *skip_hw_vlan)
+static struct sk_buff *be_lancer_xmit_workarounds(struct be_adapter *adapter,
+ struct sk_buff *skb,
+ bool *skip_hw_vlan)
{
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
unsigned int eth_hdr_len;
struct iphdr *ip;
- /* Lancer, SH-R ASICs have a bug wherein Packets that are 32 bytes or less
- * may cause a transmit stall on that port. So the work-around is to
- * pad short packets (<= 32 bytes) to a 36-byte length.
- */
- if (unlikely(!BEx_chip(adapter) && skb->len <= 32)) {
- if (skb_padto(skb, 36))
- goto tx_drop;
- skb->len = 36;
- }
-
/* For padded packets, BE HW modifies tot_len field in IP header
* incorrecly when VLAN tag is inserted by HW.
* For padded packets, Lancer computes incorrect checksum.
@@ -945,9 +955,9 @@
}
/* If vlan tag is already inlined in the packet, skip HW VLAN
- * tagging in UMC mode
+ * tagging in pvid-tagging mode
*/
- if ((adapter->function_mode & UMC_ENABLED) &&
+ if (be_pvid_tagging_enabled(adapter) &&
veh->h_vlan_proto == htons(ETH_P_8021Q))
*skip_hw_vlan = true;
@@ -959,7 +969,7 @@
vlan_tx_tag_present(skb)) {
skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan);
if (unlikely(!skb))
- goto tx_drop;
+ goto err;
}
/* HW may lockup when VLAN HW tagging is requested on
@@ -981,15 +991,39 @@
be_vlan_tag_tx_chk(adapter, skb)) {
skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan);
if (unlikely(!skb))
- goto tx_drop;
+ goto err;
}
return skb;
tx_drop:
dev_kfree_skb_any(skb);
+err:
return NULL;
}
+static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter,
+ struct sk_buff *skb,
+ bool *skip_hw_vlan)
+{
+ /* Lancer, SH-R ASICs have a bug wherein Packets that are 32 bytes or
+ * less may cause a transmit stall on that port. So the work-around is
+ * to pad short packets (<= 32 bytes) to a 36-byte length.
+ */
+ if (unlikely(!BEx_chip(adapter) && skb->len <= 32)) {
+ if (skb_padto(skb, 36))
+ return NULL;
+ skb->len = 36;
+ }
+
+ if (BEx_chip(adapter) || lancer_chip(adapter)) {
+ skb = be_lancer_xmit_workarounds(adapter, skb, skip_hw_vlan);
+ if (!skb)
+ return NULL;
+ }
+
+ return skb;
+}
+
static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
{
struct be_adapter *adapter = netdev_priv(netdev);
@@ -1124,7 +1158,10 @@
/* Packets with VID 0 are always received by Lancer by default */
if (lancer_chip(adapter) && vid == 0)
- goto ret;
+ return status;
+
+ if (adapter->vlan_tag[vid])
+ return status;
adapter->vlan_tag[vid] = 1;
adapter->vlans_added++;
@@ -1134,7 +1171,7 @@
adapter->vlans_added--;
adapter->vlan_tag[vid] = 0;
}
-ret:
+
return status;
}
@@ -1157,6 +1194,14 @@
return status;
}
+static void be_clear_promisc(struct be_adapter *adapter)
+{
+ adapter->promiscuous = false;
+ adapter->flags &= ~BE_FLAGS_VLAN_PROMISC;
+
+ be_cmd_rx_filter(adapter, IFF_PROMISC, OFF);
+}
+
static void be_set_rx_mode(struct net_device *netdev)
{
struct be_adapter *adapter = netdev_priv(netdev);
@@ -1170,9 +1215,7 @@
/* BE was previously in promiscuous mode; disable it */
if (adapter->promiscuous) {
- adapter->promiscuous = false;
- be_cmd_rx_filter(adapter, IFF_PROMISC, OFF);
-
+ be_clear_promisc(adapter);
if (adapter->vlans_added)
be_vid_config(adapter);
}
@@ -1268,6 +1311,7 @@
vi->vlan = vf_cfg->vlan_tag & VLAN_VID_MASK;
vi->qos = vf_cfg->vlan_tag >> VLAN_PRIO_SHIFT;
memcpy(&vi->mac, vf_cfg->mac_addr, ETH_ALEN);
+ vi->linkstate = adapter->vf_cfg[vf].plink_tracking;
return 0;
}
@@ -1287,24 +1331,20 @@
if (vlan || qos) {
vlan |= qos << VLAN_PRIO_SHIFT;
- if (vf_cfg->vlan_tag != vlan) {
- /* If this is new value, program it. Else skip. */
- vf_cfg->vlan_tag = vlan;
+ if (vf_cfg->vlan_tag != vlan)
status = be_cmd_set_hsw_config(adapter, vlan, vf + 1,
vf_cfg->if_handle, 0);
- }
} else {
/* Reset Transparent Vlan Tagging. */
- vf_cfg->vlan_tag = 0;
- vlan = vf_cfg->def_vid;
- status = be_cmd_set_hsw_config(adapter, vlan, vf + 1,
- vf_cfg->if_handle, 0);
+ status = be_cmd_set_hsw_config(adapter, BE_RESET_VLAN_TAG_ID,
+ vf + 1, vf_cfg->if_handle, 0);
}
-
- if (status)
+ if (!status)
+ vf_cfg->vlan_tag = vlan;
+ else
dev_info(&adapter->pdev->dev,
- "VLAN %d config on VF %d failed\n", vlan, vf);
+ "VLAN %d config on VF %d failed\n", vlan, vf);
return status;
}
@@ -1326,11 +1366,7 @@
return -EINVAL;
}
- if (lancer_chip(adapter))
- status = be_cmd_set_profile_config(adapter, rate / 10, vf + 1);
- else
- status = be_cmd_set_qos(adapter, rate / 10, vf + 1);
-
+ status = be_cmd_config_qos(adapter, rate / 10, vf + 1);
if (status)
dev_err(&adapter->pdev->dev,
"tx rate %d on VF %d failed\n", rate, vf);
@@ -1338,6 +1374,24 @@
adapter->vf_cfg[vf].tx_rate = rate;
return status;
}
+static int be_set_vf_link_state(struct net_device *netdev, int vf,
+ int link_state)
+{
+ struct be_adapter *adapter = netdev_priv(netdev);
+ int status;
+
+ if (!sriov_enabled(adapter))
+ return -EPERM;
+
+ if (vf >= adapter->num_vfs)
+ return -EINVAL;
+
+ status = be_cmd_set_logical_link_config(adapter, link_state, vf+1);
+ if (!status)
+ adapter->vf_cfg[vf].plink_tracking = link_state;
+
+ return status;
+}
static void be_aic_update(struct be_aic_obj *aic, u64 rx_pkts, u64 tx_pkts,
ulong now)
@@ -1370,15 +1424,15 @@
rxo = &adapter->rx_obj[eqo->idx];
do {
- start = u64_stats_fetch_begin_bh(&rxo->stats.sync);
+ start = u64_stats_fetch_begin_irq(&rxo->stats.sync);
rx_pkts = rxo->stats.rx_pkts;
- } while (u64_stats_fetch_retry_bh(&rxo->stats.sync, start));
+ } while (u64_stats_fetch_retry_irq(&rxo->stats.sync, start));
txo = &adapter->tx_obj[eqo->idx];
do {
- start = u64_stats_fetch_begin_bh(&txo->stats.sync);
+ start = u64_stats_fetch_begin_irq(&txo->stats.sync);
tx_pkts = txo->stats.tx_reqs;
- } while (u64_stats_fetch_retry_bh(&txo->stats.sync, start));
+ } while (u64_stats_fetch_retry_irq(&txo->stats.sync, start));
/* Skip, if wrapped around or first calculation */
@@ -1433,9 +1487,10 @@
static inline bool csum_passed(struct be_rx_compl_info *rxcp)
{
/* L4 checksum is not reliable for non TCP/UDP packets.
- * Also ignore ipcksm for ipv6 pkts */
+ * Also ignore ipcksm for ipv6 pkts
+ */
return (rxcp->tcpf || rxcp->udpf) && rxcp->l4_csum &&
- (rxcp->ip_csum || rxcp->ipv6);
+ (rxcp->ip_csum || rxcp->ipv6) && !rxcp->err;
}
static struct be_rx_page_info *get_rx_page_info(struct be_rx_obj *rxo)
@@ -1448,11 +1503,15 @@
rx_page_info = &rxo->page_info_tbl[frag_idx];
BUG_ON(!rx_page_info->page);
- if (rx_page_info->last_page_user) {
+ if (rx_page_info->last_frag) {
dma_unmap_page(&adapter->pdev->dev,
dma_unmap_addr(rx_page_info, bus),
adapter->big_page_size, DMA_FROM_DEVICE);
- rx_page_info->last_page_user = false;
+ rx_page_info->last_frag = false;
+ } else {
+ dma_sync_single_for_cpu(&adapter->pdev->dev,
+ dma_unmap_addr(rx_page_info, bus),
+ rx_frag_size, DMA_FROM_DEVICE);
}
queue_tail_inc(rxq);
@@ -1574,6 +1633,8 @@
skb_record_rx_queue(skb, rxo - &adapter->rx_obj[0]);
if (netdev->features & NETIF_F_RXHASH)
skb_set_hash(skb, rxcp->rss_hash, PKT_HASH_TYPE_L3);
+
+ skb->encapsulation = rxcp->tunneled;
skb_mark_napi_id(skb, napi);
if (rxcp->vlanf)
@@ -1630,6 +1691,8 @@
skb_record_rx_queue(skb, rxo - &adapter->rx_obj[0]);
if (adapter->netdev->features & NETIF_F_RXHASH)
skb_set_hash(skb, rxcp->rss_hash, PKT_HASH_TYPE_L3);
+
+ skb->encapsulation = rxcp->tunneled;
skb_mark_napi_id(skb, napi);
if (rxcp->vlanf)
@@ -1660,12 +1723,14 @@
rxcp->rss_hash =
AMAP_GET_BITS(struct amap_eth_rx_compl_v1, rsshash, compl);
if (rxcp->vlanf) {
- rxcp->vtm = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vtm,
+ rxcp->qnq = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, qnq,
compl);
rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vlan_tag,
compl);
}
rxcp->port = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, port, compl);
+ rxcp->tunneled =
+ AMAP_GET_BITS(struct amap_eth_rx_compl_v1, tunneled, compl);
}
static void be_parse_rx_compl_v0(struct be_eth_rx_compl *compl,
@@ -1690,7 +1755,7 @@
rxcp->rss_hash =
AMAP_GET_BITS(struct amap_eth_rx_compl_v0, rsshash, compl);
if (rxcp->vlanf) {
- rxcp->vtm = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vtm,
+ rxcp->qnq = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, qnq,
compl);
rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vlan_tag,
compl);
@@ -1723,9 +1788,11 @@
rxcp->l4_csum = 0;
if (rxcp->vlanf) {
- /* vlanf could be wrongly set in some cards.
- * ignore if vtm is not set */
- if ((adapter->function_mode & FLEX10_MODE) && !rxcp->vtm)
+ /* In QNQ modes, if qnq bit is not set, then the packet was
+ * tagged only with the transparent outer vlan-tag and must
+ * not be treated as a vlan packet by host
+ */
+ if (be_is_qnq_mode(adapter) && !rxcp->qnq)
rxcp->vlanf = 0;
if (!lancer_chip(adapter))
@@ -1784,17 +1851,16 @@
rx_stats(rxo)->rx_post_fail++;
break;
}
- page_info->page_offset = 0;
+ page_offset = 0;
} else {
get_page(pagep);
- page_info->page_offset = page_offset + rx_frag_size;
+ page_offset += rx_frag_size;
}
- page_offset = page_info->page_offset;
+ page_info->page_offset = page_offset;
page_info->page = pagep;
- dma_unmap_addr_set(page_info, bus, page_dmaaddr);
- frag_dmaaddr = page_dmaaddr + page_info->page_offset;
rxd = queue_head_node(rxq);
+ frag_dmaaddr = page_dmaaddr + page_info->page_offset;
rxd->fragpa_lo = cpu_to_le32(frag_dmaaddr & 0xFFFFFFFF);
rxd->fragpa_hi = cpu_to_le32(upper_32_bits(frag_dmaaddr));
@@ -1802,15 +1868,24 @@
if ((page_offset + rx_frag_size + rx_frag_size) >
adapter->big_page_size) {
pagep = NULL;
- page_info->last_page_user = true;
+ page_info->last_frag = true;
+ dma_unmap_addr_set(page_info, bus, page_dmaaddr);
+ } else {
+ dma_unmap_addr_set(page_info, bus, frag_dmaaddr);
}
prev_page_info = page_info;
queue_head_inc(rxq);
page_info = &rxo->page_info_tbl[rxq->head];
}
- if (pagep)
- prev_page_info->last_page_user = true;
+
+ /* Mark the last frag of a page when we break out of the above loop
+ * with no more slots available in the RXQ
+ */
+ if (pagep) {
+ prev_page_info->last_frag = true;
+ dma_unmap_addr_set(prev_page_info, bus, page_dmaaddr);
+ }
if (posted) {
atomic_add(posted, &rxq->used);
@@ -1867,7 +1942,7 @@
queue_tail_inc(txq);
} while (cur_index != last_index);
- kfree_skb(sent_skb);
+ dev_kfree_skb_any(sent_skb);
return num_wrbs;
}
@@ -2423,6 +2498,9 @@
u32 ue_lo = 0, ue_hi = 0, ue_lo_mask = 0, ue_hi_mask = 0;
u32 sliport_status = 0, sliport_err1 = 0, sliport_err2 = 0;
u32 i;
+ bool error_detected = false;
+ struct device *dev = &adapter->pdev->dev;
+ struct net_device *netdev = adapter->netdev;
if (be_hw_error(adapter))
return;
@@ -2434,6 +2512,21 @@
SLIPORT_ERROR1_OFFSET);
sliport_err2 = ioread32(adapter->db +
SLIPORT_ERROR2_OFFSET);
+ adapter->hw_error = true;
+ /* Do not log error messages if its a FW reset */
+ if (sliport_err1 == SLIPORT_ERROR_FW_RESET1 &&
+ sliport_err2 == SLIPORT_ERROR_FW_RESET2) {
+ dev_info(dev, "Firmware update in progress\n");
+ } else {
+ error_detected = true;
+ dev_err(dev, "Error detected in the card\n");
+ dev_err(dev, "ERR: sliport status 0x%x\n",
+ sliport_status);
+ dev_err(dev, "ERR: sliport error1 0x%x\n",
+ sliport_err1);
+ dev_err(dev, "ERR: sliport error2 0x%x\n",
+ sliport_err2);
+ }
}
} else {
pci_read_config_dword(adapter->pdev,
@@ -2447,51 +2540,33 @@
ue_lo = (ue_lo & ~ue_lo_mask);
ue_hi = (ue_hi & ~ue_hi_mask);
- }
- /* On certain platforms BE hardware can indicate spurious UEs.
- * Allow the h/w to stop working completely in case of a real UE.
- * Hence not setting the hw_error for UE detection.
- */
- if (sliport_status & SLIPORT_STATUS_ERR_MASK) {
- adapter->hw_error = true;
- /* Do not log error messages if its a FW reset */
- if (sliport_err1 == SLIPORT_ERROR_FW_RESET1 &&
- sliport_err2 == SLIPORT_ERROR_FW_RESET2) {
- dev_info(&adapter->pdev->dev,
- "Firmware update in progress\n");
- return;
- } else {
- dev_err(&adapter->pdev->dev,
- "Error detected in the card\n");
+ /* On certain platforms BE hardware can indicate spurious UEs.
+ * Allow HW to stop working completely in case of a real UE.
+ * Hence not setting the hw_error for UE detection.
+ */
+
+ if (ue_lo || ue_hi) {
+ error_detected = true;
+ dev_err(dev,
+ "Unrecoverable Error detected in the adapter");
+ dev_err(dev, "Please reboot server to recover");
+ if (skyhawk_chip(adapter))
+ adapter->hw_error = true;
+ for (i = 0; ue_lo; ue_lo >>= 1, i++) {
+ if (ue_lo & 1)
+ dev_err(dev, "UE: %s bit set\n",
+ ue_status_low_desc[i]);
+ }
+ for (i = 0; ue_hi; ue_hi >>= 1, i++) {
+ if (ue_hi & 1)
+ dev_err(dev, "UE: %s bit set\n",
+ ue_status_hi_desc[i]);
+ }
}
}
-
- if (sliport_status & SLIPORT_STATUS_ERR_MASK) {
- dev_err(&adapter->pdev->dev,
- "ERR: sliport status 0x%x\n", sliport_status);
- dev_err(&adapter->pdev->dev,
- "ERR: sliport error1 0x%x\n", sliport_err1);
- dev_err(&adapter->pdev->dev,
- "ERR: sliport error2 0x%x\n", sliport_err2);
- }
-
- if (ue_lo) {
- for (i = 0; ue_lo; ue_lo >>= 1, i++) {
- if (ue_lo & 1)
- dev_err(&adapter->pdev->dev,
- "UE: %s bit set\n", ue_status_low_desc[i]);
- }
- }
-
- if (ue_hi) {
- for (i = 0; ue_hi; ue_hi >>= 1, i++) {
- if (ue_hi & 1)
- dev_err(&adapter->pdev->dev,
- "UE: %s bit set\n", ue_status_hi_desc[i]);
- }
- }
-
+ if (error_detected)
+ netif_carrier_off(netdev);
}
static void be_msix_disable(struct be_adapter *adapter)
@@ -2505,7 +2580,7 @@
static int be_msix_enable(struct be_adapter *adapter)
{
- int i, status, num_vec;
+ int i, num_vec;
struct device *dev = &adapter->pdev->dev;
/* If RoCE is supported, program the max number of NIC vectors that
@@ -2521,24 +2596,11 @@
for (i = 0; i < num_vec; i++)
adapter->msix_entries[i].entry = i;
- status = pci_enable_msix(adapter->pdev, adapter->msix_entries, num_vec);
- if (status == 0) {
- goto done;
- } else if (status >= MIN_MSIX_VECTORS) {
- num_vec = status;
- status = pci_enable_msix(adapter->pdev, adapter->msix_entries,
- num_vec);
- if (!status)
- goto done;
- }
+ num_vec = pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
+ MIN_MSIX_VECTORS, num_vec);
+ if (num_vec < 0)
+ goto fail;
- dev_warn(dev, "MSIx enable failed\n");
-
- /* INTx is not supported in VFs, so fail probe if enable_msix fails */
- if (!be_physfn(adapter))
- return status;
- return 0;
-done:
if (be_roce_supported(adapter) && num_vec > MIN_MSIX_VECTORS) {
adapter->num_msix_roce_vec = num_vec / 2;
dev_info(dev, "enabled %d MSI-x vector(s) for RoCE\n",
@@ -2550,6 +2612,14 @@
dev_info(dev, "enabled %d MSI-x vector(s) for NIC\n",
adapter->num_msix_vec);
return 0;
+
+fail:
+ dev_warn(dev, "MSIx enable failed\n");
+
+ /* INTx is not supported in VFs, so fail probe if enable_msix fails */
+ if (!be_physfn(adapter))
+ return num_vec;
+ return 0;
}
static inline int be_msix_vec_get(struct be_adapter *adapter,
@@ -2791,6 +2861,9 @@
netif_tx_start_all_queues(netdev);
be_roce_dev_open(adapter);
+
+ if (skyhawk_chip(adapter))
+ vxlan_get_rx_port(netdev);
return 0;
err:
be_close(adapter->netdev);
@@ -2946,6 +3019,19 @@
}
}
+static void be_disable_vxlan_offloads(struct be_adapter *adapter)
+{
+ if (adapter->flags & BE_FLAGS_VXLAN_OFFLOADS)
+ be_cmd_manage_iface(adapter, adapter->if_handle,
+ OP_CONVERT_TUNNEL_TO_NORMAL);
+
+ if (adapter->vxlan_port)
+ be_cmd_set_vxlan_port(adapter, 0);
+
+ adapter->flags &= ~BE_FLAGS_VXLAN_OFFLOADS;
+ adapter->vxlan_port = 0;
+}
+
static int be_clear(struct be_adapter *adapter)
{
be_cancel_worker(adapter);
@@ -2953,6 +3039,8 @@
if (sriov_enabled(adapter))
be_vf_clear(adapter);
+ be_disable_vxlan_offloads(adapter);
+
/* delete the primary mac along with the uc-mac list */
be_mac_clear(adapter);
@@ -3013,11 +3101,11 @@
static int be_vf_setup(struct be_adapter *adapter)
{
- struct be_vf_cfg *vf_cfg;
- u16 def_vlan, lnk_speed;
- int status, old_vfs, vf;
struct device *dev = &adapter->pdev->dev;
+ struct be_vf_cfg *vf_cfg;
+ int status, old_vfs, vf;
u32 privileges;
+ u16 lnk_speed;
old_vfs = pci_num_vf(adapter->pdev);
if (old_vfs) {
@@ -3077,21 +3165,19 @@
* Allow full available bandwidth
*/
if (BE3_chip(adapter) && !old_vfs)
- be_cmd_set_qos(adapter, 1000, vf+1);
+ be_cmd_config_qos(adapter, 1000, vf + 1);
status = be_cmd_link_status_query(adapter, &lnk_speed,
NULL, vf + 1);
if (!status)
vf_cfg->tx_rate = lnk_speed;
- status = be_cmd_get_hsw_config(adapter, &def_vlan,
- vf + 1, vf_cfg->if_handle, NULL);
- if (status)
- goto err;
- vf_cfg->def_vid = def_vlan;
-
- if (!old_vfs)
+ if (!old_vfs) {
be_cmd_enable_vf(adapter, vf + 1);
+ be_cmd_set_logical_link_config(adapter,
+ IFLA_VF_LINK_STATE_AUTO,
+ vf+1);
+ }
}
if (!old_vfs) {
@@ -3109,19 +3195,38 @@
return status;
}
+/* Converting function_mode bits on BE3 to SH mc_type enums */
+
+static u8 be_convert_mc_type(u32 function_mode)
+{
+ if (function_mode & VNIC_MODE && function_mode & FLEX10_MODE)
+ return vNIC1;
+ else if (function_mode & FLEX10_MODE)
+ return FLEX10;
+ else if (function_mode & VNIC_MODE)
+ return vNIC2;
+ else if (function_mode & UMC_ENABLED)
+ return UMC;
+ else
+ return MC_NONE;
+}
+
/* On BE2/BE3 FW does not suggest the supported limits */
static void BEx_get_resources(struct be_adapter *adapter,
struct be_resources *res)
{
struct pci_dev *pdev = adapter->pdev;
bool use_sriov = false;
- int max_vfs;
+ int max_vfs = 0;
- max_vfs = pci_sriov_get_totalvfs(pdev);
-
- if (BE3_chip(adapter) && sriov_want(adapter)) {
- res->max_vfs = max_vfs > 0 ? min(MAX_VFS, max_vfs) : 0;
- use_sriov = res->max_vfs;
+ if (be_physfn(adapter) && BE3_chip(adapter)) {
+ be_cmd_get_profile_config(adapter, res, 0);
+ /* Some old versions of BE3 FW don't report max_vfs value */
+ if (res->max_vfs == 0) {
+ max_vfs = pci_sriov_get_totalvfs(pdev);
+ res->max_vfs = max_vfs > 0 ? min(MAX_VFS, max_vfs) : 0;
+ }
+ use_sriov = res->max_vfs && sriov_want(adapter);
}
if (be_physfn(adapter))
@@ -3129,17 +3234,32 @@
else
res->max_uc_mac = BE_VF_UC_PMAC_COUNT;
- if (adapter->function_mode & FLEX10_MODE)
- res->max_vlans = BE_NUM_VLANS_SUPPORTED/8;
- else if (adapter->function_mode & UMC_ENABLED)
- res->max_vlans = BE_UMC_NUM_VLANS_SUPPORTED;
- else
+ adapter->mc_type = be_convert_mc_type(adapter->function_mode);
+
+ if (be_is_mc(adapter)) {
+ /* Assuming that there are 4 channels per port,
+ * when multi-channel is enabled
+ */
+ if (be_is_qnq_mode(adapter))
+ res->max_vlans = BE_NUM_VLANS_SUPPORTED/8;
+ else
+ /* In a non-qnq multichannel mode, the pvid
+ * takes up one vlan entry
+ */
+ res->max_vlans = (BE_NUM_VLANS_SUPPORTED / 4) - 1;
+ } else {
res->max_vlans = BE_NUM_VLANS_SUPPORTED;
+ }
+
res->max_mcast_mac = BE_MAX_MC;
- /* For BE3 1Gb ports, F/W does not properly support multiple TXQs */
- if (BE2_chip(adapter) || use_sriov || be_is_mc(adapter) ||
- !be_physfn(adapter) || (adapter->port_num > 1))
+ /* 1) For BE3 1Gb ports, FW does not support multiple TXQs
+ * 2) Create multiple TX rings on a BE3-R multi-channel interface
+ * *only* if it is RSS-capable.
+ */
+ if (BE2_chip(adapter) || use_sriov || (adapter->port_num > 1) ||
+ !be_physfn(adapter) || (be_is_mc(adapter) &&
+ !(adapter->function_caps & BE_FUNCTION_CAPS_RSS)))
res->max_tx_qs = 1;
else
res->max_tx_qs = BE3_MAX_TX_QS;
@@ -3151,7 +3271,7 @@
res->max_rx_qs = res->max_rss_qs + 1;
if (be_physfn(adapter))
- res->max_evt_qs = (max_vfs > 0) ?
+ res->max_evt_qs = (res->max_vfs > 0) ?
BE3_SRIOV_MAX_EVT_QS : BE3_MAX_EVT_QS;
else
res->max_evt_qs = 1;
@@ -3242,9 +3362,8 @@
if (status)
return status;
- /* primary mac needs 1 pmac entry */
- adapter->pmac_id = kcalloc(be_max_uc(adapter) + 1, sizeof(u32),
- GFP_KERNEL);
+ adapter->pmac_id = kcalloc(be_max_uc(adapter),
+ sizeof(*adapter->pmac_id), GFP_KERNEL);
if (!adapter->pmac_id)
return -ENOMEM;
@@ -3418,6 +3537,10 @@
be_cmd_set_flow_control(adapter, adapter->tx_fc,
adapter->rx_fc);
+ if (be_physfn(adapter))
+ be_cmd_set_logical_link_config(adapter,
+ IFLA_VF_LINK_STATE_AUTO, 0);
+
if (sriov_want(adapter)) {
if (be_max_vfs(adapter))
be_vf_setup(adapter);
@@ -4042,6 +4165,65 @@
BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB);
}
+static void be_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
+ __be16 port)
+{
+ struct be_adapter *adapter = netdev_priv(netdev);
+ struct device *dev = &adapter->pdev->dev;
+ int status;
+
+ if (lancer_chip(adapter) || BEx_chip(adapter))
+ return;
+
+ if (adapter->flags & BE_FLAGS_VXLAN_OFFLOADS) {
+ dev_warn(dev, "Cannot add UDP port %d for VxLAN offloads\n",
+ be16_to_cpu(port));
+ dev_info(dev,
+ "Only one UDP port supported for VxLAN offloads\n");
+ return;
+ }
+
+ status = be_cmd_manage_iface(adapter, adapter->if_handle,
+ OP_CONVERT_NORMAL_TO_TUNNEL);
+ if (status) {
+ dev_warn(dev, "Failed to convert normal interface to tunnel\n");
+ goto err;
+ }
+
+ status = be_cmd_set_vxlan_port(adapter, port);
+ if (status) {
+ dev_warn(dev, "Failed to add VxLAN port\n");
+ goto err;
+ }
+ adapter->flags |= BE_FLAGS_VXLAN_OFFLOADS;
+ adapter->vxlan_port = port;
+
+ dev_info(dev, "Enabled VxLAN offloads for UDP port %d\n",
+ be16_to_cpu(port));
+ return;
+err:
+ be_disable_vxlan_offloads(adapter);
+ return;
+}
+
+static void be_del_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
+ __be16 port)
+{
+ struct be_adapter *adapter = netdev_priv(netdev);
+
+ if (lancer_chip(adapter) || BEx_chip(adapter))
+ return;
+
+ if (adapter->vxlan_port != port)
+ return;
+
+ be_disable_vxlan_offloads(adapter);
+
+ dev_info(&adapter->pdev->dev,
+ "Disabled VxLAN offloads for UDP port %d\n",
+ be16_to_cpu(port));
+}
+
static const struct net_device_ops be_netdev_ops = {
.ndo_open = be_open,
.ndo_stop = be_close,
@@ -4057,20 +4239,29 @@
.ndo_set_vf_vlan = be_set_vf_vlan,
.ndo_set_vf_tx_rate = be_set_vf_tx_rate,
.ndo_get_vf_config = be_get_vf_config,
+ .ndo_set_vf_link_state = be_set_vf_link_state,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = be_netpoll,
#endif
.ndo_bridge_setlink = be_ndo_bridge_setlink,
.ndo_bridge_getlink = be_ndo_bridge_getlink,
#ifdef CONFIG_NET_RX_BUSY_POLL
- .ndo_busy_poll = be_busy_poll
+ .ndo_busy_poll = be_busy_poll,
#endif
+ .ndo_add_vxlan_port = be_add_vxlan_port,
+ .ndo_del_vxlan_port = be_del_vxlan_port,
};
static void be_netdev_init(struct net_device *netdev)
{
struct be_adapter *adapter = netdev_priv(netdev);
+ if (skyhawk_chip(adapter)) {
+ netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+ NETIF_F_TSO | NETIF_F_TSO6 |
+ NETIF_F_GSO_UDP_TUNNEL;
+ netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+ }
netdev->hw_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 |
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |
NETIF_F_HW_VLAN_CTAG_TX;
@@ -4417,14 +4608,32 @@
static char *mc_name(struct be_adapter *adapter)
{
- if (adapter->function_mode & FLEX10_MODE)
- return "FLEX10";
- else if (adapter->function_mode & VNIC_MODE)
- return "vNIC";
- else if (adapter->function_mode & UMC_ENABLED)
- return "UMC";
- else
- return "";
+ char *str = ""; /* default */
+
+ switch (adapter->mc_type) {
+ case UMC:
+ str = "UMC";
+ break;
+ case FLEX10:
+ str = "FLEX10";
+ break;
+ case vNIC1:
+ str = "vNIC-1";
+ break;
+ case nPAR:
+ str = "nPAR";
+ break;
+ case UFP:
+ str = "UFP";
+ break;
+ case vNIC2:
+ str = "vNIC-2";
+ break;
+ default:
+ str = "";
+ }
+
+ return str;
}
static inline char *func_name(struct be_adapter *adapter)
diff --git a/drivers/net/ethernet/emulex/benet/be_roce.c b/drivers/net/ethernet/emulex/benet/be_roce.c
index 9cd5415..a5dae4a 100644
--- a/drivers/net/ethernet/emulex/benet/be_roce.c
+++ b/drivers/net/ethernet/emulex/benet/be_roce.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2005 - 2013 Emulex
+ * Copyright (C) 2005 - 2014 Emulex
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
diff --git a/drivers/net/ethernet/emulex/benet/be_roce.h b/drivers/net/ethernet/emulex/benet/be_roce.h
index 2cd1129..a3ef8f8 100644
--- a/drivers/net/ethernet/emulex/benet/be_roce.h
+++ b/drivers/net/ethernet/emulex/benet/be_roce.h
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2005 - 2013 Emulex
+ * Copyright (C) 2005 - 2014 Emulex
* All rights reserved.
*
* This program is free software; you can redistribute it and/or
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 4de8cfd..8b70ca7 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -13,6 +13,7 @@
#include <linux/dma-mapping.h>
#include <linux/etherdevice.h>
+#include <linux/clk.h>
#include <linux/crc32.h>
#include <linux/interrupt.h>
#include <linux/io.h>
@@ -51,6 +52,7 @@
#define ETH_HASH0 0x48
#define ETH_HASH1 0x4c
#define ETH_TXCTRL 0x50
+#define ETH_END 0x54
/* mode register */
#define MODER_RXEN (1 << 0) /* receive enable */
@@ -179,6 +181,7 @@
* @membase: pointer to buffer memory region
* @dma_alloc: dma allocated buffer size
* @io_region_size: I/O memory region size
+ * @num_bd: number of buffer descriptors
* @num_tx: number of send buffers
* @cur_tx: last send buffer written
* @dty_tx: last buffer actually sent
@@ -199,6 +202,7 @@
int dma_alloc;
resource_size_t io_region_size;
+ unsigned int num_bd;
unsigned int num_tx;
unsigned int cur_tx;
unsigned int dty_tx;
@@ -216,6 +220,7 @@
struct phy_device *phy;
struct mii_bus *mdio;
+ struct clk *clk;
s8 phy_id;
};
@@ -655,11 +660,6 @@
return -EBUSY;
}
-static int ethoc_mdio_reset(struct mii_bus *bus)
-{
- return 0;
-}
-
static void ethoc_mdio_poll(struct net_device *dev)
{
}
@@ -688,6 +688,11 @@
}
priv->phy = phy;
+ phy->advertising &= ~(ADVERTISED_1000baseT_Full |
+ ADVERTISED_1000baseT_Half);
+ phy->supported &= ~(SUPPORTED_1000baseT_Full |
+ SUPPORTED_1000baseT_Half);
+
return 0;
}
@@ -890,6 +895,102 @@
return NETDEV_TX_OK;
}
+static int ethoc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+ struct ethoc *priv = netdev_priv(dev);
+ struct phy_device *phydev = priv->phy;
+
+ if (!phydev)
+ return -EOPNOTSUPP;
+
+ return phy_ethtool_gset(phydev, cmd);
+}
+
+static int ethoc_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+ struct ethoc *priv = netdev_priv(dev);
+ struct phy_device *phydev = priv->phy;
+
+ if (!phydev)
+ return -EOPNOTSUPP;
+
+ return phy_ethtool_sset(phydev, cmd);
+}
+
+static int ethoc_get_regs_len(struct net_device *netdev)
+{
+ return ETH_END;
+}
+
+static void ethoc_get_regs(struct net_device *dev, struct ethtool_regs *regs,
+ void *p)
+{
+ struct ethoc *priv = netdev_priv(dev);
+ u32 *regs_buff = p;
+ unsigned i;
+
+ regs->version = 0;
+ for (i = 0; i < ETH_END / sizeof(u32); ++i)
+ regs_buff[i] = ethoc_read(priv, i * sizeof(u32));
+}
+
+static void ethoc_get_ringparam(struct net_device *dev,
+ struct ethtool_ringparam *ring)
+{
+ struct ethoc *priv = netdev_priv(dev);
+
+ ring->rx_max_pending = priv->num_bd - 1;
+ ring->rx_mini_max_pending = 0;
+ ring->rx_jumbo_max_pending = 0;
+ ring->tx_max_pending = priv->num_bd - 1;
+
+ ring->rx_pending = priv->num_rx;
+ ring->rx_mini_pending = 0;
+ ring->rx_jumbo_pending = 0;
+ ring->tx_pending = priv->num_tx;
+}
+
+static int ethoc_set_ringparam(struct net_device *dev,
+ struct ethtool_ringparam *ring)
+{
+ struct ethoc *priv = netdev_priv(dev);
+
+ if (ring->tx_pending < 1 || ring->rx_pending < 1 ||
+ ring->tx_pending + ring->rx_pending > priv->num_bd)
+ return -EINVAL;
+ if (ring->rx_mini_pending || ring->rx_jumbo_pending)
+ return -EINVAL;
+
+ if (netif_running(dev)) {
+ netif_tx_disable(dev);
+ ethoc_disable_rx_and_tx(priv);
+ ethoc_disable_irq(priv, INT_MASK_TX | INT_MASK_RX);
+ synchronize_irq(dev->irq);
+ }
+
+ priv->num_tx = rounddown_pow_of_two(ring->tx_pending);
+ priv->num_rx = ring->rx_pending;
+ ethoc_init_ring(priv, dev->mem_start);
+
+ if (netif_running(dev)) {
+ ethoc_enable_irq(priv, INT_MASK_TX | INT_MASK_RX);
+ ethoc_enable_rx_and_tx(priv);
+ netif_wake_queue(dev);
+ }
+ return 0;
+}
+
+const struct ethtool_ops ethoc_ethtool_ops = {
+ .get_settings = ethoc_get_settings,
+ .set_settings = ethoc_set_settings,
+ .get_regs_len = ethoc_get_regs_len,
+ .get_regs = ethoc_get_regs,
+ .get_link = ethtool_op_get_link,
+ .get_ringparam = ethoc_get_ringparam,
+ .set_ringparam = ethoc_set_ringparam,
+ .get_ts_info = ethtool_op_get_ts_info,
+};
+
static const struct net_device_ops ethoc_netdev_ops = {
.ndo_open = ethoc_open,
.ndo_stop = ethoc_stop,
@@ -917,6 +1018,8 @@
int num_bd;
int ret = 0;
bool random_mac = false;
+ struct ethoc_platform_data *pdata = dev_get_platdata(&pdev->dev);
+ u32 eth_clkfreq = pdata ? pdata->eth_clkfreq : 0;
/* allocate networking device */
netdev = alloc_etherdev(sizeof(struct ethoc));
@@ -1016,6 +1119,7 @@
ret = -ENODEV;
goto error;
}
+ priv->num_bd = num_bd;
/* num_tx must be a power of two */
priv->num_tx = rounddown_pow_of_two(num_bd >> 1);
priv->num_rx = num_bd - priv->num_tx;
@@ -1030,8 +1134,7 @@
}
/* Allow the platform setup code to pass in a MAC address. */
- if (dev_get_platdata(&pdev->dev)) {
- struct ethoc_platform_data *pdata = dev_get_platdata(&pdev->dev);
+ if (pdata) {
memcpy(netdev->dev_addr, pdata->hwaddr, IFHWADDRLEN);
priv->phy_id = pdata->phy_id;
} else {
@@ -1069,6 +1172,27 @@
if (random_mac)
netdev->addr_assign_type = NET_ADDR_RANDOM;
+ /* Allow the platform setup code to adjust MII management bus clock. */
+ if (!eth_clkfreq) {
+ struct clk *clk = devm_clk_get(&pdev->dev, NULL);
+
+ if (!IS_ERR(clk)) {
+ priv->clk = clk;
+ clk_prepare_enable(clk);
+ eth_clkfreq = clk_get_rate(clk);
+ }
+ }
+ if (eth_clkfreq) {
+ u32 clkdiv = MIIMODER_CLKDIV(eth_clkfreq / 2500000 + 1);
+
+ if (!clkdiv)
+ clkdiv = 2;
+ dev_dbg(&pdev->dev, "setting MII clkdiv to %u\n", clkdiv);
+ ethoc_write(priv, MIIMODER,
+ (ethoc_read(priv, MIIMODER) & MIIMODER_NOPRE) |
+ clkdiv);
+ }
+
/* register MII bus */
priv->mdio = mdiobus_alloc();
if (!priv->mdio) {
@@ -1081,7 +1205,6 @@
priv->mdio->name, pdev->id);
priv->mdio->read = ethoc_mdio_read;
priv->mdio->write = ethoc_mdio_write;
- priv->mdio->reset = ethoc_mdio_reset;
priv->mdio->priv = priv;
priv->mdio->irq = kmalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL);
@@ -1111,6 +1234,7 @@
netdev->netdev_ops = ðoc_netdev_ops;
netdev->watchdog_timeo = ETHOC_TIMEOUT;
netdev->features |= 0;
+ netdev->ethtool_ops = ðoc_ethtool_ops;
/* setup NAPI */
netif_napi_add(netdev, &priv->napi, ethoc_poll, 64);
@@ -1133,6 +1257,8 @@
kfree(priv->mdio->irq);
mdiobus_free(priv->mdio);
free:
+ if (priv->clk)
+ clk_disable_unprepare(priv->clk);
free_netdev(netdev);
out:
return ret;
@@ -1157,6 +1283,8 @@
kfree(priv->mdio->irq);
mdiobus_free(priv->mdio);
}
+ if (priv->clk)
+ clk_disable_unprepare(priv->clk);
unregister_netdev(netdev);
free_netdev(netdev);
}
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index c11ecbc..68069ea 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -940,11 +940,6 @@
return -EIO;
}
-static int ftgmac100_mdiobus_reset(struct mii_bus *bus)
-{
- return 0;
-}
-
/******************************************************************************
* struct ethtool_ops functions
*****************************************************************************/
@@ -1262,7 +1257,6 @@
priv->mii_bus->priv = netdev;
priv->mii_bus->read = ftgmac100_mdiobus_read;
priv->mii_bus->write = ftgmac100_mdiobus_write;
- priv->mii_bus->reset = ftgmac100_mdiobus_reset;
priv->mii_bus->irq = priv->phy_irq;
for (i = 0; i < PHY_MAX_ADDR; i++)
diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile
index 549ce13..71debd1 100644
--- a/drivers/net/ethernet/freescale/Makefile
+++ b/drivers/net/ethernet/freescale/Makefile
@@ -14,7 +14,6 @@
obj-$(CONFIG_GIANFAR) += gianfar_driver.o
obj-$(CONFIG_PTP_1588_CLOCK_GIANFAR) += gianfar_ptp.o
gianfar_driver-objs := gianfar.o \
- gianfar_ethtool.o \
- gianfar_sysfs.o
+ gianfar_ethtool.o
obj-$(CONFIG_UCC_GETH) += ucc_geth_driver.o
ucc_geth_driver-objs := ucc_geth.o ucc_geth_ethtool.o
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d4782b4..e19315e 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -338,7 +338,7 @@
/* Protocol checksum off-load for TCP and UDP. */
if (fec_enet_clear_csum(skb, ndev)) {
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -389,12 +389,6 @@
netdev_err(ndev, "Tx DMA memory map failed\n");
return NETDEV_TX_OK;
}
- /* Send it on its way. Tell FEC it's ready, interrupt when done,
- * it's the last BD of the frame, and to put the CRC on the end.
- */
- status |= (BD_ENET_TX_READY | BD_ENET_TX_INTR
- | BD_ENET_TX_LAST | BD_ENET_TX_TC);
- bdp->cbd_sc = status;
if (fep->bufdesc_ex) {
@@ -416,6 +410,13 @@
}
}
+ /* Send it on its way. Tell FEC it's ready, interrupt when done,
+ * it's the last BD of the frame, and to put the CRC on the end.
+ */
+ status |= (BD_ENET_TX_READY | BD_ENET_TX_INTR
+ | BD_ENET_TX_LAST | BD_ENET_TX_TC);
+ bdp->cbd_sc = status;
+
bdp_pre = fec_enet_get_prevdesc(bdp, fep);
if ((id_entry->driver_data & FEC_QUIRK_ERR006358) &&
!(bdp_pre->cbd_sc & BD_ENET_TX_READY)) {
@@ -527,13 +528,6 @@
/* Clear any outstanding interrupt. */
writel(0xffc00000, fep->hwp + FEC_IEVENT);
- /* Setup multicast filter. */
- set_multicast_list(ndev);
-#ifndef CONFIG_M5272
- writel(0, fep->hwp + FEC_HASH_TABLE_HIGH);
- writel(0, fep->hwp + FEC_HASH_TABLE_LOW);
-#endif
-
/* Set maximum receive buffer size. */
writel(PKT_MAXBLR_SIZE, fep->hwp + FEC_R_BUFF_SIZE);
@@ -654,6 +648,13 @@
writel(rcntl, fep->hwp + FEC_R_CNTRL);
+ /* Setup multicast filter. */
+ set_multicast_list(ndev);
+#ifndef CONFIG_M5272
+ writel(0, fep->hwp + FEC_HASH_TABLE_HIGH);
+ writel(0, fep->hwp + FEC_HASH_TABLE_LOW);
+#endif
+
if (id_entry->driver_data & FEC_QUIRK_ENET_MAC) {
/* enable ENET endian swap */
ecntl |= (1 << 8);
@@ -1254,11 +1255,6 @@
return 0;
}
-static int fec_enet_mdio_reset(struct mii_bus *bus)
-{
- return 0;
-}
-
static int fec_enet_mii_probe(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
@@ -1383,7 +1379,6 @@
fep->mii_bus->name = "fec_enet_mii_bus";
fep->mii_bus->read = fec_enet_mdio_read;
fep->mii_bus->write = fec_enet_mdio_write;
- fep->mii_bus->reset = fec_enet_mdio_reset;
snprintf(fep->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
pdev->name, fep->dev_id + 1);
fep->mii_bus->priv = fep;
@@ -1778,8 +1773,6 @@
struct fec_enet_private *fep = netdev_priv(ndev);
int ret;
- napi_enable(&fep->napi);
-
/* I should reset the ring buffers here, but I don't yet know
* a simple way to do that.
*/
@@ -1794,6 +1787,8 @@
fec_enet_free_buffers(ndev);
return ret;
}
+
+ napi_enable(&fep->napi);
phy_start(fep->phy_dev);
netif_start_queue(ndev);
fep->opened = 1;
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 89ccb5b..82386b2 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -372,6 +372,7 @@
fep->ptp_caps.n_alarm = 0;
fep->ptp_caps.n_ext_ts = 0;
fep->ptp_caps.n_per_out = 0;
+ fep->ptp_caps.n_pins = 0;
fep->ptp_caps.pps = 0;
fep->ptp_caps.adjfreq = fec_ptp_adjfreq;
fep->ptp_caps.adjtime = fec_ptp_adjtime;
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 62f042d..dc80db4 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -91,6 +91,9 @@
u16 pkt_len, sc;
int curidx;
+ if (budget <= 0)
+ return received;
+
/*
* First, grab all of the stats for the incoming packet.
* These get messed up if we get called due to a busy condition.
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
index 7e69c98..ebf5d64 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
@@ -95,12 +95,6 @@
}
-static int fs_enet_fec_mii_reset(struct mii_bus *bus)
-{
- /* nothing here - for now */
- return 0;
-}
-
static struct of_device_id fs_enet_mdio_fec_match[];
static int fs_enet_mdio_probe(struct platform_device *ofdev)
{
@@ -128,7 +122,6 @@
new_bus->name = "FEC MII Bus";
new_bus->read = &fs_enet_fec_mii_read;
new_bus->write = &fs_enet_fec_mii_write;
- new_bus->reset = &fs_enet_fec_mii_reset;
ret = of_address_to_resource(ofdev->dev.of_node, 0, &res);
if (ret)
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index ad5a5aa..9125d9a 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -9,7 +9,7 @@
* Maintainer: Kumar Gala
* Modifier: Sandeep Gopalpet <sandeep.kumar@freescale.com>
*
- * Copyright 2002-2009, 2011 Freescale Semiconductor, Inc.
+ * Copyright 2002-2009, 2011-2013 Freescale Semiconductor, Inc.
* Copyright 2007 MontaVista Software, Inc.
*
* This program is free software; you can redistribute it and/or modify it
@@ -121,7 +121,6 @@
static irqreturn_t gfar_transmit(int irq, void *dev_id);
static irqreturn_t gfar_interrupt(int irq, void *dev_id);
static void adjust_link(struct net_device *dev);
-static void init_registers(struct net_device *dev);
static int init_phy(struct net_device *dev);
static int gfar_probe(struct platform_device *ofdev);
static int gfar_remove(struct platform_device *ofdev);
@@ -129,8 +128,10 @@
static void gfar_set_multi(struct net_device *dev);
static void gfar_set_hash_for_addr(struct net_device *dev, u8 *addr);
static void gfar_configure_serdes(struct net_device *dev);
-static int gfar_poll(struct napi_struct *napi, int budget);
-static int gfar_poll_sq(struct napi_struct *napi, int budget);
+static int gfar_poll_rx(struct napi_struct *napi, int budget);
+static int gfar_poll_tx(struct napi_struct *napi, int budget);
+static int gfar_poll_rx_sq(struct napi_struct *napi, int budget);
+static int gfar_poll_tx_sq(struct napi_struct *napi, int budget);
#ifdef CONFIG_NET_POLL_CONTROLLER
static void gfar_netpoll(struct net_device *dev);
#endif
@@ -138,9 +139,7 @@
static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue);
static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb,
int amount_pull, struct napi_struct *napi);
-void gfar_halt(struct net_device *dev);
-static void gfar_halt_nodisable(struct net_device *dev);
-void gfar_start(struct net_device *dev);
+static void gfar_halt_nodisable(struct gfar_private *priv);
static void gfar_clear_exact_match(struct net_device *dev);
static void gfar_set_mac_for_addr(struct net_device *dev, int num,
const u8 *addr);
@@ -332,72 +331,76 @@
}
}
-static void gfar_init_mac(struct net_device *ndev)
+static void gfar_rx_buff_size_config(struct gfar_private *priv)
{
- struct gfar_private *priv = netdev_priv(ndev);
- struct gfar __iomem *regs = priv->gfargrp[0].regs;
- u32 rctrl = 0;
- u32 tctrl = 0;
- u32 attrs = 0;
-
- /* write the tx/rx base registers */
- gfar_init_tx_rx_base(priv);
-
- /* Configure the coalescing support */
- gfar_configure_coalescing_all(priv);
+ int frame_size = priv->ndev->mtu + ETH_HLEN;
/* set this when rx hw offload (TOE) functions are being used */
priv->uses_rxfcb = 0;
+ if (priv->ndev->features & (NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_RX))
+ priv->uses_rxfcb = 1;
+
+ if (priv->hwts_rx_en)
+ priv->uses_rxfcb = 1;
+
+ if (priv->uses_rxfcb)
+ frame_size += GMAC_FCB_LEN;
+
+ frame_size += priv->padding;
+
+ frame_size = (frame_size & ~(INCREMENTAL_BUFFER_SIZE - 1)) +
+ INCREMENTAL_BUFFER_SIZE;
+
+ priv->rx_buffer_size = frame_size;
+}
+
+static void gfar_mac_rx_config(struct gfar_private *priv)
+{
+ struct gfar __iomem *regs = priv->gfargrp[0].regs;
+ u32 rctrl = 0;
+
if (priv->rx_filer_enable) {
rctrl |= RCTRL_FILREN;
/* Program the RIR0 reg with the required distribution */
- gfar_write(®s->rir0, DEFAULT_RIR0);
+ if (priv->poll_mode == GFAR_SQ_POLLING)
+ gfar_write(®s->rir0, DEFAULT_2RXQ_RIR0);
+ else /* GFAR_MQ_POLLING */
+ gfar_write(®s->rir0, DEFAULT_8RXQ_RIR0);
}
/* Restore PROMISC mode */
- if (ndev->flags & IFF_PROMISC)
+ if (priv->ndev->flags & IFF_PROMISC)
rctrl |= RCTRL_PROM;
- if (ndev->features & NETIF_F_RXCSUM) {
+ if (priv->ndev->features & NETIF_F_RXCSUM)
rctrl |= RCTRL_CHECKSUMMING;
- priv->uses_rxfcb = 1;
- }
- if (priv->extended_hash) {
- rctrl |= RCTRL_EXTHASH;
-
- gfar_clear_exact_match(ndev);
- rctrl |= RCTRL_EMEN;
- }
+ if (priv->extended_hash)
+ rctrl |= RCTRL_EXTHASH | RCTRL_EMEN;
if (priv->padding) {
rctrl &= ~RCTRL_PAL_MASK;
rctrl |= RCTRL_PADDING(priv->padding);
}
- /* Insert receive time stamps into padding alignment bytes */
- if (priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER) {
- rctrl &= ~RCTRL_PAL_MASK;
- rctrl |= RCTRL_PADDING(8);
- priv->padding = 8;
- }
-
/* Enable HW time stamping if requested from user space */
- if (priv->hwts_rx_en) {
+ if (priv->hwts_rx_en)
rctrl |= RCTRL_PRSDEP_INIT | RCTRL_TS_ENABLE;
- priv->uses_rxfcb = 1;
- }
- if (ndev->features & NETIF_F_HW_VLAN_CTAG_RX) {
+ if (priv->ndev->features & NETIF_F_HW_VLAN_CTAG_RX)
rctrl |= RCTRL_VLEX | RCTRL_PRSDEP_INIT;
- priv->uses_rxfcb = 1;
- }
/* Init rctrl based on our settings */
gfar_write(®s->rctrl, rctrl);
+}
- if (ndev->features & NETIF_F_IP_CSUM)
+static void gfar_mac_tx_config(struct gfar_private *priv)
+{
+ struct gfar __iomem *regs = priv->gfargrp[0].regs;
+ u32 tctrl = 0;
+
+ if (priv->ndev->features & NETIF_F_IP_CSUM)
tctrl |= TCTRL_INIT_CSUM;
if (priv->prio_sched_en)
@@ -408,30 +411,51 @@
gfar_write(®s->tr47wt, DEFAULT_WRRS_WEIGHT);
}
+ if (priv->ndev->features & NETIF_F_HW_VLAN_CTAG_TX)
+ tctrl |= TCTRL_VLINS;
+
gfar_write(®s->tctrl, tctrl);
+}
- /* Set the extraction length and index */
- attrs = ATTRELI_EL(priv->rx_stash_size) |
- ATTRELI_EI(priv->rx_stash_index);
+static void gfar_configure_coalescing(struct gfar_private *priv,
+ unsigned long tx_mask, unsigned long rx_mask)
+{
+ struct gfar __iomem *regs = priv->gfargrp[0].regs;
+ u32 __iomem *baddr;
- gfar_write(®s->attreli, attrs);
+ if (priv->mode == MQ_MG_MODE) {
+ int i = 0;
- /* Start with defaults, and add stashing or locking
- * depending on the approprate variables
- */
- attrs = ATTR_INIT_SETTINGS;
+ baddr = ®s->txic0;
+ for_each_set_bit(i, &tx_mask, priv->num_tx_queues) {
+ gfar_write(baddr + i, 0);
+ if (likely(priv->tx_queue[i]->txcoalescing))
+ gfar_write(baddr + i, priv->tx_queue[i]->txic);
+ }
- if (priv->bd_stash_en)
- attrs |= ATTR_BDSTASH;
+ baddr = ®s->rxic0;
+ for_each_set_bit(i, &rx_mask, priv->num_rx_queues) {
+ gfar_write(baddr + i, 0);
+ if (likely(priv->rx_queue[i]->rxcoalescing))
+ gfar_write(baddr + i, priv->rx_queue[i]->rxic);
+ }
+ } else {
+ /* Backward compatible case -- even if we enable
+ * multiple queues, there's only single reg to program
+ */
+ gfar_write(®s->txic, 0);
+ if (likely(priv->tx_queue[0]->txcoalescing))
+ gfar_write(®s->txic, priv->tx_queue[0]->txic);
- if (priv->rx_stash_size != 0)
- attrs |= ATTR_BUFSTASH;
+ gfar_write(®s->rxic, 0);
+ if (unlikely(priv->rx_queue[0]->rxcoalescing))
+ gfar_write(®s->rxic, priv->rx_queue[0]->rxic);
+ }
+}
- gfar_write(®s->attr, attrs);
-
- gfar_write(®s->fifo_tx_thr, priv->fifo_threshold);
- gfar_write(®s->fifo_tx_starve, priv->fifo_starve);
- gfar_write(®s->fifo_tx_starve_shutoff, priv->fifo_starve_off);
+void gfar_configure_coalescing_all(struct gfar_private *priv)
+{
+ gfar_configure_coalescing(priv, 0xFF, 0xFF);
}
static struct net_device_stats *gfar_get_stats(struct net_device *dev)
@@ -479,12 +503,27 @@
#endif
};
-void lock_rx_qs(struct gfar_private *priv)
+static void gfar_ints_disable(struct gfar_private *priv)
{
int i;
+ for (i = 0; i < priv->num_grps; i++) {
+ struct gfar __iomem *regs = priv->gfargrp[i].regs;
+ /* Clear IEVENT */
+ gfar_write(®s->ievent, IEVENT_INIT_CLEAR);
- for (i = 0; i < priv->num_rx_queues; i++)
- spin_lock(&priv->rx_queue[i]->rxlock);
+ /* Initialize IMASK */
+ gfar_write(®s->imask, IMASK_INIT_CLEAR);
+ }
+}
+
+static void gfar_ints_enable(struct gfar_private *priv)
+{
+ int i;
+ for (i = 0; i < priv->num_grps; i++) {
+ struct gfar __iomem *regs = priv->gfargrp[i].regs;
+ /* Unmask the interrupts we look for */
+ gfar_write(®s->imask, IMASK_DEFAULT);
+ }
}
void lock_tx_qs(struct gfar_private *priv)
@@ -495,14 +534,6 @@
spin_lock(&priv->tx_queue[i]->txlock);
}
-void unlock_rx_qs(struct gfar_private *priv)
-{
- int i;
-
- for (i = 0; i < priv->num_rx_queues; i++)
- spin_unlock(&priv->rx_queue[i]->rxlock);
-}
-
void unlock_tx_qs(struct gfar_private *priv)
{
int i;
@@ -511,7 +542,42 @@
spin_unlock(&priv->tx_queue[i]->txlock);
}
-static void free_tx_pointers(struct gfar_private *priv)
+static int gfar_alloc_tx_queues(struct gfar_private *priv)
+{
+ int i;
+
+ for (i = 0; i < priv->num_tx_queues; i++) {
+ priv->tx_queue[i] = kzalloc(sizeof(struct gfar_priv_tx_q),
+ GFP_KERNEL);
+ if (!priv->tx_queue[i])
+ return -ENOMEM;
+
+ priv->tx_queue[i]->tx_skbuff = NULL;
+ priv->tx_queue[i]->qindex = i;
+ priv->tx_queue[i]->dev = priv->ndev;
+ spin_lock_init(&(priv->tx_queue[i]->txlock));
+ }
+ return 0;
+}
+
+static int gfar_alloc_rx_queues(struct gfar_private *priv)
+{
+ int i;
+
+ for (i = 0; i < priv->num_rx_queues; i++) {
+ priv->rx_queue[i] = kzalloc(sizeof(struct gfar_priv_rx_q),
+ GFP_KERNEL);
+ if (!priv->rx_queue[i])
+ return -ENOMEM;
+
+ priv->rx_queue[i]->rx_skbuff = NULL;
+ priv->rx_queue[i]->qindex = i;
+ priv->rx_queue[i]->dev = priv->ndev;
+ }
+ return 0;
+}
+
+static void gfar_free_tx_queues(struct gfar_private *priv)
{
int i;
@@ -519,7 +585,7 @@
kfree(priv->tx_queue[i]);
}
-static void free_rx_pointers(struct gfar_private *priv)
+static void gfar_free_rx_queues(struct gfar_private *priv)
{
int i;
@@ -553,23 +619,26 @@
{
int i;
- for (i = 0; i < priv->num_grps; i++)
- napi_disable(&priv->gfargrp[i].napi);
+ for (i = 0; i < priv->num_grps; i++) {
+ napi_disable(&priv->gfargrp[i].napi_rx);
+ napi_disable(&priv->gfargrp[i].napi_tx);
+ }
}
static void enable_napi(struct gfar_private *priv)
{
int i;
- for (i = 0; i < priv->num_grps; i++)
- napi_enable(&priv->gfargrp[i].napi);
+ for (i = 0; i < priv->num_grps; i++) {
+ napi_enable(&priv->gfargrp[i].napi_rx);
+ napi_enable(&priv->gfargrp[i].napi_tx);
+ }
}
static int gfar_parse_group(struct device_node *np,
struct gfar_private *priv, const char *model)
{
struct gfar_priv_grp *grp = &priv->gfargrp[priv->num_grps];
- u32 *queue_mask;
int i;
for (i = 0; i < GFAR_NUM_IRQS; i++) {
@@ -598,16 +667,52 @@
grp->priv = priv;
spin_lock_init(&grp->grplock);
if (priv->mode == MQ_MG_MODE) {
- queue_mask = (u32 *)of_get_property(np, "fsl,rx-bit-map", NULL);
- grp->rx_bit_map = queue_mask ?
- *queue_mask : (DEFAULT_MAPPING >> priv->num_grps);
- queue_mask = (u32 *)of_get_property(np, "fsl,tx-bit-map", NULL);
- grp->tx_bit_map = queue_mask ?
- *queue_mask : (DEFAULT_MAPPING >> priv->num_grps);
+ u32 *rxq_mask, *txq_mask;
+ rxq_mask = (u32 *)of_get_property(np, "fsl,rx-bit-map", NULL);
+ txq_mask = (u32 *)of_get_property(np, "fsl,tx-bit-map", NULL);
+
+ if (priv->poll_mode == GFAR_SQ_POLLING) {
+ /* One Q per interrupt group: Q0 to G0, Q1 to G1 */
+ grp->rx_bit_map = (DEFAULT_MAPPING >> priv->num_grps);
+ grp->tx_bit_map = (DEFAULT_MAPPING >> priv->num_grps);
+ } else { /* GFAR_MQ_POLLING */
+ grp->rx_bit_map = rxq_mask ?
+ *rxq_mask : (DEFAULT_MAPPING >> priv->num_grps);
+ grp->tx_bit_map = txq_mask ?
+ *txq_mask : (DEFAULT_MAPPING >> priv->num_grps);
+ }
} else {
grp->rx_bit_map = 0xFF;
grp->tx_bit_map = 0xFF;
}
+
+ /* bit_map's MSB is q0 (from q0 to q7) but, for_each_set_bit parses
+ * right to left, so we need to revert the 8 bits to get the q index
+ */
+ grp->rx_bit_map = bitrev8(grp->rx_bit_map);
+ grp->tx_bit_map = bitrev8(grp->tx_bit_map);
+
+ /* Calculate RSTAT, TSTAT, RQUEUE and TQUEUE values,
+ * also assign queues to groups
+ */
+ for_each_set_bit(i, &grp->rx_bit_map, priv->num_rx_queues) {
+ if (!grp->rx_queue)
+ grp->rx_queue = priv->rx_queue[i];
+ grp->num_rx_queues++;
+ grp->rstat |= (RSTAT_CLEAR_RHALT >> i);
+ priv->rqueue |= ((RQUEUE_EN0 | RQUEUE_EX0) >> i);
+ priv->rx_queue[i]->grp = grp;
+ }
+
+ for_each_set_bit(i, &grp->tx_bit_map, priv->num_tx_queues) {
+ if (!grp->tx_queue)
+ grp->tx_queue = priv->tx_queue[i];
+ grp->num_tx_queues++;
+ grp->tstat |= (TSTAT_CLEAR_THALT >> i);
+ priv->tqueue |= (TQUEUE_EN0 >> i);
+ priv->tx_queue[i]->grp = grp;
+ }
+
priv->num_grps++;
return 0;
@@ -628,13 +733,45 @@
const u32 *stash_idx;
unsigned int num_tx_qs, num_rx_qs;
u32 *tx_queues, *rx_queues;
+ unsigned short mode, poll_mode;
if (!np || !of_device_is_available(np))
return -ENODEV;
- /* parse the num of tx and rx queues */
+ if (of_device_is_compatible(np, "fsl,etsec2")) {
+ mode = MQ_MG_MODE;
+ poll_mode = GFAR_SQ_POLLING;
+ } else {
+ mode = SQ_SG_MODE;
+ poll_mode = GFAR_SQ_POLLING;
+ }
+
+ /* parse the num of HW tx and rx queues */
tx_queues = (u32 *)of_get_property(np, "fsl,num_tx_queues", NULL);
- num_tx_qs = tx_queues ? *tx_queues : 1;
+ rx_queues = (u32 *)of_get_property(np, "fsl,num_rx_queues", NULL);
+
+ if (mode == SQ_SG_MODE) {
+ num_tx_qs = 1;
+ num_rx_qs = 1;
+ } else { /* MQ_MG_MODE */
+ /* get the actual number of supported groups */
+ unsigned int num_grps = of_get_available_child_count(np);
+
+ if (num_grps == 0 || num_grps > MAXGROUPS) {
+ dev_err(&ofdev->dev, "Invalid # of int groups(%d)\n",
+ num_grps);
+ pr_err("Cannot do alloc_etherdev, aborting\n");
+ return -EINVAL;
+ }
+
+ if (poll_mode == GFAR_SQ_POLLING) {
+ num_tx_qs = num_grps; /* one txq per int group */
+ num_rx_qs = num_grps; /* one rxq per int group */
+ } else { /* GFAR_MQ_POLLING */
+ num_tx_qs = tx_queues ? *tx_queues : 1;
+ num_rx_qs = rx_queues ? *rx_queues : 1;
+ }
+ }
if (num_tx_qs > MAX_TX_QS) {
pr_err("num_tx_qs(=%d) greater than MAX_TX_QS(=%d)\n",
@@ -643,9 +780,6 @@
return -EINVAL;
}
- rx_queues = (u32 *)of_get_property(np, "fsl,num_rx_queues", NULL);
- num_rx_qs = rx_queues ? *rx_queues : 1;
-
if (num_rx_qs > MAX_RX_QS) {
pr_err("num_rx_qs(=%d) greater than MAX_RX_QS(=%d)\n",
num_rx_qs, MAX_RX_QS);
@@ -661,10 +795,20 @@
priv = netdev_priv(dev);
priv->ndev = dev;
+ priv->mode = mode;
+ priv->poll_mode = poll_mode;
+
priv->num_tx_queues = num_tx_qs;
netif_set_real_num_rx_queues(dev, num_rx_qs);
priv->num_rx_queues = num_rx_qs;
- priv->num_grps = 0x0;
+
+ err = gfar_alloc_tx_queues(priv);
+ if (err)
+ goto tx_alloc_failed;
+
+ err = gfar_alloc_rx_queues(priv);
+ if (err)
+ goto rx_alloc_failed;
/* Init Rx queue filer rule set linked list */
INIT_LIST_HEAD(&priv->rx_list.list);
@@ -677,52 +821,18 @@
priv->gfargrp[i].regs = NULL;
/* Parse and initialize group specific information */
- if (of_device_is_compatible(np, "fsl,etsec2")) {
- priv->mode = MQ_MG_MODE;
+ if (priv->mode == MQ_MG_MODE) {
for_each_child_of_node(np, child) {
err = gfar_parse_group(child, priv, model);
if (err)
goto err_grp_init;
}
- } else {
- priv->mode = SQ_SG_MODE;
+ } else { /* SQ_SG_MODE */
err = gfar_parse_group(np, priv, model);
if (err)
goto err_grp_init;
}
- for (i = 0; i < priv->num_tx_queues; i++)
- priv->tx_queue[i] = NULL;
- for (i = 0; i < priv->num_rx_queues; i++)
- priv->rx_queue[i] = NULL;
-
- for (i = 0; i < priv->num_tx_queues; i++) {
- priv->tx_queue[i] = kzalloc(sizeof(struct gfar_priv_tx_q),
- GFP_KERNEL);
- if (!priv->tx_queue[i]) {
- err = -ENOMEM;
- goto tx_alloc_failed;
- }
- priv->tx_queue[i]->tx_skbuff = NULL;
- priv->tx_queue[i]->qindex = i;
- priv->tx_queue[i]->dev = dev;
- spin_lock_init(&(priv->tx_queue[i]->txlock));
- }
-
- for (i = 0; i < priv->num_rx_queues; i++) {
- priv->rx_queue[i] = kzalloc(sizeof(struct gfar_priv_rx_q),
- GFP_KERNEL);
- if (!priv->rx_queue[i]) {
- err = -ENOMEM;
- goto rx_alloc_failed;
- }
- priv->rx_queue[i]->rx_skbuff = NULL;
- priv->rx_queue[i]->qindex = i;
- priv->rx_queue[i]->dev = dev;
- spin_lock_init(&(priv->rx_queue[i]->rxlock));
- }
-
-
stash = of_get_property(np, "bd-stash", NULL);
if (stash) {
@@ -749,17 +859,16 @@
memcpy(dev->dev_addr, mac_addr, ETH_ALEN);
if (model && !strcasecmp(model, "TSEC"))
- priv->device_flags = FSL_GIANFAR_DEV_HAS_GIGABIT |
+ priv->device_flags |= FSL_GIANFAR_DEV_HAS_GIGABIT |
FSL_GIANFAR_DEV_HAS_COALESCE |
FSL_GIANFAR_DEV_HAS_RMON |
FSL_GIANFAR_DEV_HAS_MULTI_INTR;
if (model && !strcasecmp(model, "eTSEC"))
- priv->device_flags = FSL_GIANFAR_DEV_HAS_GIGABIT |
+ priv->device_flags |= FSL_GIANFAR_DEV_HAS_GIGABIT |
FSL_GIANFAR_DEV_HAS_COALESCE |
FSL_GIANFAR_DEV_HAS_RMON |
FSL_GIANFAR_DEV_HAS_MULTI_INTR |
- FSL_GIANFAR_DEV_HAS_PADDING |
FSL_GIANFAR_DEV_HAS_CSUM |
FSL_GIANFAR_DEV_HAS_VLAN |
FSL_GIANFAR_DEV_HAS_MAGIC_PACKET |
@@ -784,12 +893,12 @@
return 0;
-rx_alloc_failed:
- free_rx_pointers(priv);
-tx_alloc_failed:
- free_tx_pointers(priv);
err_grp_init:
unmap_group_regs(priv);
+rx_alloc_failed:
+ gfar_free_rx_queues(priv);
+tx_alloc_failed:
+ gfar_free_tx_queues(priv);
free_gfar_dev(priv);
return err;
}
@@ -822,18 +931,16 @@
switch (config.rx_filter) {
case HWTSTAMP_FILTER_NONE:
if (priv->hwts_rx_en) {
- stop_gfar(netdev);
priv->hwts_rx_en = 0;
- startup_gfar(netdev);
+ reset_gfar(netdev);
}
break;
default:
if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER))
return -ERANGE;
if (!priv->hwts_rx_en) {
- stop_gfar(netdev);
priv->hwts_rx_en = 1;
- startup_gfar(netdev);
+ reset_gfar(netdev);
}
config.rx_filter = HWTSTAMP_FILTER_ALL;
break;
@@ -875,19 +982,6 @@
return phy_mii_ioctl(priv->phydev, rq, cmd);
}
-static unsigned int reverse_bitmap(unsigned int bit_map, unsigned int max_qs)
-{
- unsigned int new_bit_map = 0x0;
- int mask = 0x1 << (max_qs - 1), i;
-
- for (i = 0; i < max_qs; i++) {
- if (bit_map & mask)
- new_bit_map = new_bit_map + (1 << i);
- mask = mask >> 0x1;
- }
- return new_bit_map;
-}
-
static u32 cluster_entry_per_class(struct gfar_private *priv, u32 rqfar,
u32 class)
{
@@ -1005,99 +1099,140 @@
priv->errata);
}
-/* Set up the ethernet device structure, private data,
- * and anything else we need before we start
- */
-static int gfar_probe(struct platform_device *ofdev)
+void gfar_mac_reset(struct gfar_private *priv)
{
+ struct gfar __iomem *regs = priv->gfargrp[0].regs;
u32 tempval;
- struct net_device *dev = NULL;
- struct gfar_private *priv = NULL;
- struct gfar __iomem *regs = NULL;
- int err = 0, i, grp_idx = 0;
- u32 rstat = 0, tstat = 0, rqueue = 0, tqueue = 0;
- u32 isrg = 0;
- u32 __iomem *baddr;
-
- err = gfar_of_init(ofdev, &dev);
-
- if (err)
- return err;
-
- priv = netdev_priv(dev);
- priv->ndev = dev;
- priv->ofdev = ofdev;
- priv->dev = &ofdev->dev;
- SET_NETDEV_DEV(dev, &ofdev->dev);
-
- spin_lock_init(&priv->bflock);
- INIT_WORK(&priv->reset_task, gfar_reset_task);
-
- platform_set_drvdata(ofdev, priv);
- regs = priv->gfargrp[0].regs;
-
- gfar_detect_errata(priv);
-
- /* Stop the DMA engine now, in case it was running before
- * (The firmware could have used it, and left it running).
- */
- gfar_halt(dev);
/* Reset MAC layer */
gfar_write(®s->maccfg1, MACCFG1_SOFT_RESET);
/* We need to delay at least 3 TX clocks */
- udelay(2);
+ udelay(3);
- tempval = 0;
- if (!priv->pause_aneg_en && priv->tx_pause_en)
- tempval |= MACCFG1_TX_FLOW;
- if (!priv->pause_aneg_en && priv->rx_pause_en)
- tempval |= MACCFG1_RX_FLOW;
/* the soft reset bit is not self-resetting, so we need to
* clear it before resuming normal operation
*/
- gfar_write(®s->maccfg1, tempval);
+ gfar_write(®s->maccfg1, 0);
+
+ udelay(3);
+
+ /* Compute rx_buff_size based on config flags */
+ gfar_rx_buff_size_config(priv);
+
+ /* Initialize the max receive frame/buffer lengths */
+ gfar_write(®s->maxfrm, priv->rx_buffer_size);
+ gfar_write(®s->mrblr, priv->rx_buffer_size);
+
+ /* Initialize the Minimum Frame Length Register */
+ gfar_write(®s->minflr, MINFLR_INIT_SETTINGS);
/* Initialize MACCFG2. */
tempval = MACCFG2_INIT_SETTINGS;
- if (gfar_has_errata(priv, GFAR_ERRATA_74))
+
+ /* If the mtu is larger than the max size for standard
+ * ethernet frames (ie, a jumbo frame), then set maccfg2
+ * to allow huge frames, and to check the length
+ */
+ if (priv->rx_buffer_size > DEFAULT_RX_BUFFER_SIZE ||
+ gfar_has_errata(priv, GFAR_ERRATA_74))
tempval |= MACCFG2_HUGEFRAME | MACCFG2_LENGTHCHECK;
+
gfar_write(®s->maccfg2, tempval);
+ /* Clear mac addr hash registers */
+ gfar_write(®s->igaddr0, 0);
+ gfar_write(®s->igaddr1, 0);
+ gfar_write(®s->igaddr2, 0);
+ gfar_write(®s->igaddr3, 0);
+ gfar_write(®s->igaddr4, 0);
+ gfar_write(®s->igaddr5, 0);
+ gfar_write(®s->igaddr6, 0);
+ gfar_write(®s->igaddr7, 0);
+
+ gfar_write(®s->gaddr0, 0);
+ gfar_write(®s->gaddr1, 0);
+ gfar_write(®s->gaddr2, 0);
+ gfar_write(®s->gaddr3, 0);
+ gfar_write(®s->gaddr4, 0);
+ gfar_write(®s->gaddr5, 0);
+ gfar_write(®s->gaddr6, 0);
+ gfar_write(®s->gaddr7, 0);
+
+ if (priv->extended_hash)
+ gfar_clear_exact_match(priv->ndev);
+
+ gfar_mac_rx_config(priv);
+
+ gfar_mac_tx_config(priv);
+
+ gfar_set_mac_address(priv->ndev);
+
+ gfar_set_multi(priv->ndev);
+
+ /* clear ievent and imask before configuring coalescing */
+ gfar_ints_disable(priv);
+
+ /* Configure the coalescing support */
+ gfar_configure_coalescing_all(priv);
+}
+
+static void gfar_hw_init(struct gfar_private *priv)
+{
+ struct gfar __iomem *regs = priv->gfargrp[0].regs;
+ u32 attrs;
+
+ /* Stop the DMA engine now, in case it was running before
+ * (The firmware could have used it, and left it running).
+ */
+ gfar_halt(priv);
+
+ gfar_mac_reset(priv);
+
+ /* Zero out the rmon mib registers if it has them */
+ if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) {
+ memset_io(&(regs->rmon), 0, sizeof(struct rmon_mib));
+
+ /* Mask off the CAM interrupts */
+ gfar_write(®s->rmon.cam1, 0xffffffff);
+ gfar_write(®s->rmon.cam2, 0xffffffff);
+ }
+
/* Initialize ECNTRL */
gfar_write(®s->ecntrl, ECNTRL_INIT_SETTINGS);
- /* Set the dev->base_addr to the gfar reg region */
- dev->base_addr = (unsigned long) regs;
+ /* Set the extraction length and index */
+ attrs = ATTRELI_EL(priv->rx_stash_size) |
+ ATTRELI_EI(priv->rx_stash_index);
- /* Fill in the dev structure */
- dev->watchdog_timeo = TX_TIMEOUT;
- dev->mtu = 1500;
- dev->netdev_ops = &gfar_netdev_ops;
- dev->ethtool_ops = &gfar_ethtool_ops;
+ gfar_write(®s->attreli, attrs);
- /* Register for napi ...We are registering NAPI for each grp */
- if (priv->mode == SQ_SG_MODE)
- netif_napi_add(dev, &priv->gfargrp[0].napi, gfar_poll_sq,
- GFAR_DEV_WEIGHT);
- else
- for (i = 0; i < priv->num_grps; i++)
- netif_napi_add(dev, &priv->gfargrp[i].napi, gfar_poll,
- GFAR_DEV_WEIGHT);
+ /* Start with defaults, and add stashing
+ * depending on driver parameters
+ */
+ attrs = ATTR_INIT_SETTINGS;
- if (priv->device_flags & FSL_GIANFAR_DEV_HAS_CSUM) {
- dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG |
- NETIF_F_RXCSUM;
- dev->features |= NETIF_F_IP_CSUM | NETIF_F_SG |
- NETIF_F_RXCSUM | NETIF_F_HIGHDMA;
- }
+ if (priv->bd_stash_en)
+ attrs |= ATTR_BDSTASH;
- if (priv->device_flags & FSL_GIANFAR_DEV_HAS_VLAN) {
- dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX |
- NETIF_F_HW_VLAN_CTAG_RX;
- dev->features |= NETIF_F_HW_VLAN_CTAG_RX;
- }
+ if (priv->rx_stash_size != 0)
+ attrs |= ATTR_BUFSTASH;
+
+ gfar_write(®s->attr, attrs);
+
+ /* FIFO configs */
+ gfar_write(®s->fifo_tx_thr, DEFAULT_FIFO_TX_THR);
+ gfar_write(®s->fifo_tx_starve, DEFAULT_FIFO_TX_STARVE);
+ gfar_write(®s->fifo_tx_starve_shutoff, DEFAULT_FIFO_TX_STARVE_OFF);
+
+ /* Program the interrupt steering regs, only for MG devices */
+ if (priv->num_grps > 1)
+ gfar_write_isrg(priv);
+}
+
+static void __init gfar_init_addr_hash_table(struct gfar_private *priv)
+{
+ struct gfar __iomem *regs = priv->gfargrp[0].regs;
if (priv->device_flags & FSL_GIANFAR_DEV_HAS_EXTENDED_HASH) {
priv->extended_hash = 1;
@@ -1133,69 +1268,82 @@
priv->hash_regs[6] = ®s->gaddr6;
priv->hash_regs[7] = ®s->gaddr7;
}
+}
- if (priv->device_flags & FSL_GIANFAR_DEV_HAS_PADDING)
- priv->padding = DEFAULT_PADDING;
- else
- priv->padding = 0;
+/* Set up the ethernet device structure, private data,
+ * and anything else we need before we start
+ */
+static int gfar_probe(struct platform_device *ofdev)
+{
+ struct net_device *dev = NULL;
+ struct gfar_private *priv = NULL;
+ int err = 0, i;
+
+ err = gfar_of_init(ofdev, &dev);
+
+ if (err)
+ return err;
+
+ priv = netdev_priv(dev);
+ priv->ndev = dev;
+ priv->ofdev = ofdev;
+ priv->dev = &ofdev->dev;
+ SET_NETDEV_DEV(dev, &ofdev->dev);
+
+ spin_lock_init(&priv->bflock);
+ INIT_WORK(&priv->reset_task, gfar_reset_task);
+
+ platform_set_drvdata(ofdev, priv);
+
+ gfar_detect_errata(priv);
+
+ /* Set the dev->base_addr to the gfar reg region */
+ dev->base_addr = (unsigned long) priv->gfargrp[0].regs;
+
+ /* Fill in the dev structure */
+ dev->watchdog_timeo = TX_TIMEOUT;
+ dev->mtu = 1500;
+ dev->netdev_ops = &gfar_netdev_ops;
+ dev->ethtool_ops = &gfar_ethtool_ops;
+
+ /* Register for napi ...We are registering NAPI for each grp */
+ for (i = 0; i < priv->num_grps; i++) {
+ if (priv->poll_mode == GFAR_SQ_POLLING) {
+ netif_napi_add(dev, &priv->gfargrp[i].napi_rx,
+ gfar_poll_rx_sq, GFAR_DEV_WEIGHT);
+ netif_napi_add(dev, &priv->gfargrp[i].napi_tx,
+ gfar_poll_tx_sq, 2);
+ } else {
+ netif_napi_add(dev, &priv->gfargrp[i].napi_rx,
+ gfar_poll_rx, GFAR_DEV_WEIGHT);
+ netif_napi_add(dev, &priv->gfargrp[i].napi_tx,
+ gfar_poll_tx, 2);
+ }
+ }
+
+ if (priv->device_flags & FSL_GIANFAR_DEV_HAS_CSUM) {
+ dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG |
+ NETIF_F_RXCSUM;
+ dev->features |= NETIF_F_IP_CSUM | NETIF_F_SG |
+ NETIF_F_RXCSUM | NETIF_F_HIGHDMA;
+ }
+
+ if (priv->device_flags & FSL_GIANFAR_DEV_HAS_VLAN) {
+ dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX;
+ dev->features |= NETIF_F_HW_VLAN_CTAG_RX;
+ }
+
+ gfar_init_addr_hash_table(priv);
+
+ /* Insert receive time stamps into padding alignment bytes */
+ if (priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER)
+ priv->padding = 8;
if (dev->features & NETIF_F_IP_CSUM ||
priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER)
dev->needed_headroom = GMAC_FCB_LEN;
- /* Program the isrg regs only if number of grps > 1 */
- if (priv->num_grps > 1) {
- baddr = ®s->isrg0;
- for (i = 0; i < priv->num_grps; i++) {
- isrg |= (priv->gfargrp[i].rx_bit_map << ISRG_SHIFT_RX);
- isrg |= (priv->gfargrp[i].tx_bit_map << ISRG_SHIFT_TX);
- gfar_write(baddr, isrg);
- baddr++;
- isrg = 0x0;
- }
- }
-
- /* Need to reverse the bit maps as bit_map's MSB is q0
- * but, for_each_set_bit parses from right to left, which
- * basically reverses the queue numbers
- */
- for (i = 0; i< priv->num_grps; i++) {
- priv->gfargrp[i].tx_bit_map =
- reverse_bitmap(priv->gfargrp[i].tx_bit_map, MAX_TX_QS);
- priv->gfargrp[i].rx_bit_map =
- reverse_bitmap(priv->gfargrp[i].rx_bit_map, MAX_RX_QS);
- }
-
- /* Calculate RSTAT, TSTAT, RQUEUE and TQUEUE values,
- * also assign queues to groups
- */
- for (grp_idx = 0; grp_idx < priv->num_grps; grp_idx++) {
- priv->gfargrp[grp_idx].num_rx_queues = 0x0;
-
- for_each_set_bit(i, &priv->gfargrp[grp_idx].rx_bit_map,
- priv->num_rx_queues) {
- priv->gfargrp[grp_idx].num_rx_queues++;
- priv->rx_queue[i]->grp = &priv->gfargrp[grp_idx];
- rstat = rstat | (RSTAT_CLEAR_RHALT >> i);
- rqueue = rqueue | ((RQUEUE_EN0 | RQUEUE_EX0) >> i);
- }
- priv->gfargrp[grp_idx].num_tx_queues = 0x0;
-
- for_each_set_bit(i, &priv->gfargrp[grp_idx].tx_bit_map,
- priv->num_tx_queues) {
- priv->gfargrp[grp_idx].num_tx_queues++;
- priv->tx_queue[i]->grp = &priv->gfargrp[grp_idx];
- tstat = tstat | (TSTAT_CLEAR_THALT >> i);
- tqueue = tqueue | (TQUEUE_EN0 >> i);
- }
- priv->gfargrp[grp_idx].rstat = rstat;
- priv->gfargrp[grp_idx].tstat = tstat;
- rstat = tstat =0;
- }
-
- gfar_write(®s->rqueue, rqueue);
- gfar_write(®s->tqueue, tqueue);
-
priv->rx_buffer_size = DEFAULT_RX_BUFFER_SIZE;
/* Initializing some of the rx/tx queue level parameters */
@@ -1220,8 +1368,9 @@
if (priv->num_tx_queues == 1)
priv->prio_sched_en = 1;
- /* Carrier starts down, phylib will bring it up */
- netif_carrier_off(dev);
+ set_bit(GFAR_DOWN, &priv->state);
+
+ gfar_hw_init(priv);
err = register_netdev(dev);
@@ -1230,6 +1379,9 @@
goto register_fail;
}
+ /* Carrier starts down, phylib will bring it up */
+ netif_carrier_off(dev);
+
device_init_wakeup(&dev->dev,
priv->device_flags &
FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
@@ -1251,9 +1403,6 @@
/* Initialize the filer table */
gfar_init_filer_table(priv);
- /* Create all the sysfs files */
- gfar_init_sysfs(dev);
-
/* Print out the device info */
netdev_info(dev, "mac: %pM\n", dev->dev_addr);
@@ -1272,8 +1421,8 @@
register_fail:
unmap_group_regs(priv);
- free_tx_pointers(priv);
- free_rx_pointers(priv);
+ gfar_free_rx_queues(priv);
+ gfar_free_tx_queues(priv);
if (priv->phy_node)
of_node_put(priv->phy_node);
if (priv->tbi_node)
@@ -1293,6 +1442,8 @@
unregister_netdev(priv->ndev);
unmap_group_regs(priv);
+ gfar_free_rx_queues(priv);
+ gfar_free_tx_queues(priv);
free_gfar_dev(priv);
return 0;
@@ -1318,9 +1469,8 @@
local_irq_save(flags);
lock_tx_qs(priv);
- lock_rx_qs(priv);
- gfar_halt_nodisable(ndev);
+ gfar_halt_nodisable(priv);
/* Disable Tx, and Rx if wake-on-LAN is disabled. */
tempval = gfar_read(®s->maccfg1);
@@ -1332,7 +1482,6 @@
gfar_write(®s->maccfg1, tempval);
- unlock_rx_qs(priv);
unlock_tx_qs(priv);
local_irq_restore(flags);
@@ -1378,15 +1527,13 @@
*/
local_irq_save(flags);
lock_tx_qs(priv);
- lock_rx_qs(priv);
tempval = gfar_read(®s->maccfg2);
tempval &= ~MACCFG2_MPEN;
gfar_write(®s->maccfg2, tempval);
- gfar_start(ndev);
+ gfar_start(priv);
- unlock_rx_qs(priv);
unlock_tx_qs(priv);
local_irq_restore(flags);
@@ -1413,10 +1560,11 @@
return -ENOMEM;
}
- init_registers(ndev);
- gfar_set_mac_address(ndev);
- gfar_init_mac(ndev);
- gfar_start(ndev);
+ gfar_mac_reset(priv);
+
+ gfar_init_tx_rx_base(priv);
+
+ gfar_start(priv);
priv->oldlink = 0;
priv->oldspeed = 0;
@@ -1574,57 +1722,6 @@
BMCR_SPEED1000);
}
-static void init_registers(struct net_device *dev)
-{
- struct gfar_private *priv = netdev_priv(dev);
- struct gfar __iomem *regs = NULL;
- int i;
-
- for (i = 0; i < priv->num_grps; i++) {
- regs = priv->gfargrp[i].regs;
- /* Clear IEVENT */
- gfar_write(®s->ievent, IEVENT_INIT_CLEAR);
-
- /* Initialize IMASK */
- gfar_write(®s->imask, IMASK_INIT_CLEAR);
- }
-
- regs = priv->gfargrp[0].regs;
- /* Init hash registers to zero */
- gfar_write(®s->igaddr0, 0);
- gfar_write(®s->igaddr1, 0);
- gfar_write(®s->igaddr2, 0);
- gfar_write(®s->igaddr3, 0);
- gfar_write(®s->igaddr4, 0);
- gfar_write(®s->igaddr5, 0);
- gfar_write(®s->igaddr6, 0);
- gfar_write(®s->igaddr7, 0);
-
- gfar_write(®s->gaddr0, 0);
- gfar_write(®s->gaddr1, 0);
- gfar_write(®s->gaddr2, 0);
- gfar_write(®s->gaddr3, 0);
- gfar_write(®s->gaddr4, 0);
- gfar_write(®s->gaddr5, 0);
- gfar_write(®s->gaddr6, 0);
- gfar_write(®s->gaddr7, 0);
-
- /* Zero out the rmon mib registers if it has them */
- if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) {
- memset_io(&(regs->rmon), 0, sizeof (struct rmon_mib));
-
- /* Mask off the CAM interrupts */
- gfar_write(®s->rmon.cam1, 0xffffffff);
- gfar_write(®s->rmon.cam2, 0xffffffff);
- }
-
- /* Initialize the max receive buffer length */
- gfar_write(®s->mrblr, priv->rx_buffer_size);
-
- /* Initialize the Minimum Frame Length Register */
- gfar_write(®s->minflr, MINFLR_INIT_SETTINGS);
-}
-
static int __gfar_is_rx_idle(struct gfar_private *priv)
{
u32 res;
@@ -1648,23 +1745,13 @@
}
/* Halt the receive and transmit queues */
-static void gfar_halt_nodisable(struct net_device *dev)
+static void gfar_halt_nodisable(struct gfar_private *priv)
{
- struct gfar_private *priv = netdev_priv(dev);
- struct gfar __iomem *regs = NULL;
+ struct gfar __iomem *regs = priv->gfargrp[0].regs;
u32 tempval;
- int i;
- for (i = 0; i < priv->num_grps; i++) {
- regs = priv->gfargrp[i].regs;
- /* Mask all interrupts */
- gfar_write(®s->imask, IMASK_INIT_CLEAR);
+ gfar_ints_disable(priv);
- /* Clear all interrupts */
- gfar_write(®s->ievent, IEVENT_INIT_CLEAR);
- }
-
- regs = priv->gfargrp[0].regs;
/* Stop the DMA, and wait for it to stop */
tempval = gfar_read(®s->dmactrl);
if ((tempval & (DMACTRL_GRS | DMACTRL_GTS)) !=
@@ -1685,57 +1772,42 @@
}
/* Halt the receive and transmit queues */
-void gfar_halt(struct net_device *dev)
+void gfar_halt(struct gfar_private *priv)
{
- struct gfar_private *priv = netdev_priv(dev);
struct gfar __iomem *regs = priv->gfargrp[0].regs;
u32 tempval;
- gfar_halt_nodisable(dev);
+ /* Dissable the Rx/Tx hw queues */
+ gfar_write(®s->rqueue, 0);
+ gfar_write(®s->tqueue, 0);
- /* Disable Rx and Tx */
+ mdelay(10);
+
+ gfar_halt_nodisable(priv);
+
+ /* Disable Rx/Tx DMA */
tempval = gfar_read(®s->maccfg1);
tempval &= ~(MACCFG1_RX_EN | MACCFG1_TX_EN);
gfar_write(®s->maccfg1, tempval);
}
-static void free_grp_irqs(struct gfar_priv_grp *grp)
-{
- free_irq(gfar_irq(grp, TX)->irq, grp);
- free_irq(gfar_irq(grp, RX)->irq, grp);
- free_irq(gfar_irq(grp, ER)->irq, grp);
-}
-
void stop_gfar(struct net_device *dev)
{
struct gfar_private *priv = netdev_priv(dev);
- unsigned long flags;
- int i;
+
+ netif_tx_stop_all_queues(dev);
+
+ smp_mb__before_clear_bit();
+ set_bit(GFAR_DOWN, &priv->state);
+ smp_mb__after_clear_bit();
+
+ disable_napi(priv);
+
+ /* disable ints and gracefully shut down Rx/Tx DMA */
+ gfar_halt(priv);
phy_stop(priv->phydev);
-
- /* Lock it down */
- local_irq_save(flags);
- lock_tx_qs(priv);
- lock_rx_qs(priv);
-
- gfar_halt(dev);
-
- unlock_rx_qs(priv);
- unlock_tx_qs(priv);
- local_irq_restore(flags);
-
- /* Free the IRQs */
- if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) {
- for (i = 0; i < priv->num_grps; i++)
- free_grp_irqs(&priv->gfargrp[i]);
- } else {
- for (i = 0; i < priv->num_grps; i++)
- free_irq(gfar_irq(&priv->gfargrp[i], TX)->irq,
- &priv->gfargrp[i]);
- }
-
free_skb_resources(priv);
}
@@ -1825,17 +1897,15 @@
priv->tx_queue[0]->tx_bd_dma_base);
}
-void gfar_start(struct net_device *dev)
+void gfar_start(struct gfar_private *priv)
{
- struct gfar_private *priv = netdev_priv(dev);
struct gfar __iomem *regs = priv->gfargrp[0].regs;
u32 tempval;
int i = 0;
- /* Enable Rx and Tx in MACCFG1 */
- tempval = gfar_read(®s->maccfg1);
- tempval |= (MACCFG1_RX_EN | MACCFG1_TX_EN);
- gfar_write(®s->maccfg1, tempval);
+ /* Enable Rx/Tx hw queues */
+ gfar_write(®s->rqueue, priv->rqueue);
+ gfar_write(®s->tqueue, priv->tqueue);
/* Initialize DMACTRL to have WWR and WOP */
tempval = gfar_read(®s->dmactrl);
@@ -1852,52 +1922,23 @@
/* Clear THLT/RHLT, so that the DMA starts polling now */
gfar_write(®s->tstat, priv->gfargrp[i].tstat);
gfar_write(®s->rstat, priv->gfargrp[i].rstat);
- /* Unmask the interrupts we look for */
- gfar_write(®s->imask, IMASK_DEFAULT);
}
- dev->trans_start = jiffies; /* prevent tx timeout */
+ /* Enable Rx/Tx DMA */
+ tempval = gfar_read(®s->maccfg1);
+ tempval |= (MACCFG1_RX_EN | MACCFG1_TX_EN);
+ gfar_write(®s->maccfg1, tempval);
+
+ gfar_ints_enable(priv);
+
+ priv->ndev->trans_start = jiffies; /* prevent tx timeout */
}
-static void gfar_configure_coalescing(struct gfar_private *priv,
- unsigned long tx_mask, unsigned long rx_mask)
+static void free_grp_irqs(struct gfar_priv_grp *grp)
{
- struct gfar __iomem *regs = priv->gfargrp[0].regs;
- u32 __iomem *baddr;
-
- if (priv->mode == MQ_MG_MODE) {
- int i = 0;
-
- baddr = ®s->txic0;
- for_each_set_bit(i, &tx_mask, priv->num_tx_queues) {
- gfar_write(baddr + i, 0);
- if (likely(priv->tx_queue[i]->txcoalescing))
- gfar_write(baddr + i, priv->tx_queue[i]->txic);
- }
-
- baddr = ®s->rxic0;
- for_each_set_bit(i, &rx_mask, priv->num_rx_queues) {
- gfar_write(baddr + i, 0);
- if (likely(priv->rx_queue[i]->rxcoalescing))
- gfar_write(baddr + i, priv->rx_queue[i]->rxic);
- }
- } else {
- /* Backward compatible case -- even if we enable
- * multiple queues, there's only single reg to program
- */
- gfar_write(®s->txic, 0);
- if (likely(priv->tx_queue[0]->txcoalescing))
- gfar_write(®s->txic, priv->tx_queue[0]->txic);
-
- gfar_write(®s->rxic, 0);
- if (unlikely(priv->rx_queue[0]->rxcoalescing))
- gfar_write(®s->rxic, priv->rx_queue[0]->rxic);
- }
-}
-
-void gfar_configure_coalescing_all(struct gfar_private *priv)
-{
- gfar_configure_coalescing(priv, 0xFF, 0xFF);
+ free_irq(gfar_irq(grp, TX)->irq, grp);
+ free_irq(gfar_irq(grp, RX)->irq, grp);
+ free_irq(gfar_irq(grp, ER)->irq, grp);
}
static int register_grp_irqs(struct gfar_priv_grp *grp)
@@ -1956,46 +1997,65 @@
}
-/* Bring the controller up and running */
-int startup_gfar(struct net_device *ndev)
+static void gfar_free_irq(struct gfar_private *priv)
{
- struct gfar_private *priv = netdev_priv(ndev);
- struct gfar __iomem *regs = NULL;
- int err, i, j;
+ int i;
- for (i = 0; i < priv->num_grps; i++) {
- regs= priv->gfargrp[i].regs;
- gfar_write(®s->imask, IMASK_INIT_CLEAR);
+ /* Free the IRQs */
+ if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) {
+ for (i = 0; i < priv->num_grps; i++)
+ free_grp_irqs(&priv->gfargrp[i]);
+ } else {
+ for (i = 0; i < priv->num_grps; i++)
+ free_irq(gfar_irq(&priv->gfargrp[i], TX)->irq,
+ &priv->gfargrp[i]);
}
+}
- regs= priv->gfargrp[0].regs;
- err = gfar_alloc_skb_resources(ndev);
- if (err)
- return err;
-
- gfar_init_mac(ndev);
+static int gfar_request_irq(struct gfar_private *priv)
+{
+ int err, i, j;
for (i = 0; i < priv->num_grps; i++) {
err = register_grp_irqs(&priv->gfargrp[i]);
if (err) {
for (j = 0; j < i; j++)
free_grp_irqs(&priv->gfargrp[j]);
- goto irq_fail;
+ return err;
}
}
- /* Start the controller */
- gfar_start(ndev);
+ return 0;
+}
+
+/* Bring the controller up and running */
+int startup_gfar(struct net_device *ndev)
+{
+ struct gfar_private *priv = netdev_priv(ndev);
+ int err;
+
+ gfar_mac_reset(priv);
+
+ err = gfar_alloc_skb_resources(ndev);
+ if (err)
+ return err;
+
+ gfar_init_tx_rx_base(priv);
+
+ smp_mb__before_clear_bit();
+ clear_bit(GFAR_DOWN, &priv->state);
+ smp_mb__after_clear_bit();
+
+ /* Start Rx/Tx DMA and enable the interrupts */
+ gfar_start(priv);
phy_start(priv->phydev);
- gfar_configure_coalescing_all(priv);
+ enable_napi(priv);
+
+ netif_tx_wake_all_queues(ndev);
return 0;
-
-irq_fail:
- free_skb_resources(priv);
- return err;
}
/* Called when something needs to use the ethernet device
@@ -2006,27 +2066,17 @@
struct gfar_private *priv = netdev_priv(dev);
int err;
- enable_napi(priv);
-
- /* Initialize a bunch of registers */
- init_registers(dev);
-
- gfar_set_mac_address(dev);
-
err = init_phy(dev);
-
- if (err) {
- disable_napi(priv);
+ if (err)
return err;
- }
+
+ err = gfar_request_irq(priv);
+ if (err)
+ return err;
err = startup_gfar(dev);
- if (err) {
- disable_napi(priv);
+ if (err)
return err;
- }
-
- netif_tx_start_all_queues(dev);
device_set_wakeup_enable(&dev->dev, priv->wol_en);
@@ -2152,13 +2202,13 @@
skb_new = skb_realloc_headroom(skb, fcb_len);
if (!skb_new) {
dev->stats.tx_errors++;
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
if (skb->sk)
skb_set_owner_w(skb_new, skb->sk);
- consume_skb(skb);
+ dev_consume_skb_any(skb);
skb = skb_new;
}
@@ -2351,8 +2401,6 @@
{
struct gfar_private *priv = netdev_priv(dev);
- disable_napi(priv);
-
cancel_work_sync(&priv->reset_task);
stop_gfar(dev);
@@ -2360,7 +2408,7 @@
phy_disconnect(priv->phydev);
priv->phydev = NULL;
- netif_tx_stop_all_queues(dev);
+ gfar_free_irq(priv);
return 0;
}
@@ -2373,77 +2421,9 @@
return 0;
}
-/* Check if rx parser should be activated */
-void gfar_check_rx_parser_mode(struct gfar_private *priv)
-{
- struct gfar __iomem *regs;
- u32 tempval;
-
- regs = priv->gfargrp[0].regs;
-
- tempval = gfar_read(®s->rctrl);
- /* If parse is no longer required, then disable parser */
- if (tempval & RCTRL_REQ_PARSER) {
- tempval |= RCTRL_PRSDEP_INIT;
- priv->uses_rxfcb = 1;
- } else {
- tempval &= ~RCTRL_PRSDEP_INIT;
- priv->uses_rxfcb = 0;
- }
- gfar_write(®s->rctrl, tempval);
-}
-
-/* Enables and disables VLAN insertion/extraction */
-void gfar_vlan_mode(struct net_device *dev, netdev_features_t features)
-{
- struct gfar_private *priv = netdev_priv(dev);
- struct gfar __iomem *regs = NULL;
- unsigned long flags;
- u32 tempval;
-
- regs = priv->gfargrp[0].regs;
- local_irq_save(flags);
- lock_rx_qs(priv);
-
- if (features & NETIF_F_HW_VLAN_CTAG_TX) {
- /* Enable VLAN tag insertion */
- tempval = gfar_read(®s->tctrl);
- tempval |= TCTRL_VLINS;
- gfar_write(®s->tctrl, tempval);
- } else {
- /* Disable VLAN tag insertion */
- tempval = gfar_read(®s->tctrl);
- tempval &= ~TCTRL_VLINS;
- gfar_write(®s->tctrl, tempval);
- }
-
- if (features & NETIF_F_HW_VLAN_CTAG_RX) {
- /* Enable VLAN tag extraction */
- tempval = gfar_read(®s->rctrl);
- tempval |= (RCTRL_VLEX | RCTRL_PRSDEP_INIT);
- gfar_write(®s->rctrl, tempval);
- priv->uses_rxfcb = 1;
- } else {
- /* Disable VLAN tag extraction */
- tempval = gfar_read(®s->rctrl);
- tempval &= ~RCTRL_VLEX;
- gfar_write(®s->rctrl, tempval);
-
- gfar_check_rx_parser_mode(priv);
- }
-
- gfar_change_mtu(dev, dev->mtu);
-
- unlock_rx_qs(priv);
- local_irq_restore(flags);
-}
-
static int gfar_change_mtu(struct net_device *dev, int new_mtu)
{
- int tempsize, tempval;
struct gfar_private *priv = netdev_priv(dev);
- struct gfar __iomem *regs = priv->gfargrp[0].regs;
- int oldsize = priv->rx_buffer_size;
int frame_size = new_mtu + ETH_HLEN;
if ((frame_size < 64) || (frame_size > JUMBO_FRAME_SIZE)) {
@@ -2451,47 +2431,35 @@
return -EINVAL;
}
- if (priv->uses_rxfcb)
- frame_size += GMAC_FCB_LEN;
+ while (test_and_set_bit_lock(GFAR_RESETTING, &priv->state))
+ cpu_relax();
- frame_size += priv->padding;
-
- tempsize = (frame_size & ~(INCREMENTAL_BUFFER_SIZE - 1)) +
- INCREMENTAL_BUFFER_SIZE;
-
- /* Only stop and start the controller if it isn't already
- * stopped, and we changed something
- */
- if ((oldsize != tempsize) && (dev->flags & IFF_UP))
+ if (dev->flags & IFF_UP)
stop_gfar(dev);
- priv->rx_buffer_size = tempsize;
-
dev->mtu = new_mtu;
- gfar_write(®s->mrblr, priv->rx_buffer_size);
- gfar_write(®s->maxfrm, priv->rx_buffer_size);
-
- /* If the mtu is larger than the max size for standard
- * ethernet frames (ie, a jumbo frame), then set maccfg2
- * to allow huge frames, and to check the length
- */
- tempval = gfar_read(®s->maccfg2);
-
- if (priv->rx_buffer_size > DEFAULT_RX_BUFFER_SIZE ||
- gfar_has_errata(priv, GFAR_ERRATA_74))
- tempval |= (MACCFG2_HUGEFRAME | MACCFG2_LENGTHCHECK);
- else
- tempval &= ~(MACCFG2_HUGEFRAME | MACCFG2_LENGTHCHECK);
-
- gfar_write(®s->maccfg2, tempval);
-
- if ((oldsize != tempsize) && (dev->flags & IFF_UP))
+ if (dev->flags & IFF_UP)
startup_gfar(dev);
+ clear_bit_unlock(GFAR_RESETTING, &priv->state);
+
return 0;
}
+void reset_gfar(struct net_device *ndev)
+{
+ struct gfar_private *priv = netdev_priv(ndev);
+
+ while (test_and_set_bit_lock(GFAR_RESETTING, &priv->state))
+ cpu_relax();
+
+ stop_gfar(ndev);
+ startup_gfar(ndev);
+
+ clear_bit_unlock(GFAR_RESETTING, &priv->state);
+}
+
/* gfar_reset_task gets scheduled when a packet has not been
* transmitted after a set amount of time.
* For now, assume that clearing out all the structures, and
@@ -2501,16 +2469,7 @@
{
struct gfar_private *priv = container_of(work, struct gfar_private,
reset_task);
- struct net_device *dev = priv->ndev;
-
- if (dev->flags & IFF_UP) {
- netif_tx_stop_all_queues(dev);
- stop_gfar(dev);
- startup_gfar(dev);
- netif_tx_start_all_queues(dev);
- }
-
- netif_tx_schedule_all(dev);
+ reset_gfar(priv->ndev);
}
static void gfar_timeout(struct net_device *dev)
@@ -2623,8 +2582,10 @@
}
/* If we freed a buffer, we can restart transmission, if necessary */
- if (netif_tx_queue_stopped(txq) && tx_queue->num_txbdfree)
- netif_wake_subqueue(dev, tqi);
+ if (tx_queue->num_txbdfree &&
+ netif_tx_queue_stopped(txq) &&
+ !(test_bit(GFAR_DOWN, &priv->state)))
+ netif_wake_subqueue(priv->ndev, tqi);
/* Update dirty indicators */
tx_queue->skb_dirtytx = skb_dirtytx;
@@ -2633,31 +2594,6 @@
netdev_tx_completed_queue(txq, howmany, bytes_sent);
}
-static void gfar_schedule_cleanup(struct gfar_priv_grp *gfargrp)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&gfargrp->grplock, flags);
- if (napi_schedule_prep(&gfargrp->napi)) {
- gfar_write(&gfargrp->regs->imask, IMASK_RTX_DISABLED);
- __napi_schedule(&gfargrp->napi);
- } else {
- /* Clear IEVENT, so interrupts aren't called again
- * because of the packets that have already arrived.
- */
- gfar_write(&gfargrp->regs->ievent, IEVENT_RTX_MASK);
- }
- spin_unlock_irqrestore(&gfargrp->grplock, flags);
-
-}
-
-/* Interrupt Handler for Transmit complete */
-static irqreturn_t gfar_transmit(int irq, void *grp_id)
-{
- gfar_schedule_cleanup((struct gfar_priv_grp *)grp_id);
- return IRQ_HANDLED;
-}
-
static void gfar_new_rxbdp(struct gfar_priv_rx_q *rx_queue, struct rxbd8 *bdp,
struct sk_buff *skb)
{
@@ -2728,7 +2664,48 @@
irqreturn_t gfar_receive(int irq, void *grp_id)
{
- gfar_schedule_cleanup((struct gfar_priv_grp *)grp_id);
+ struct gfar_priv_grp *grp = (struct gfar_priv_grp *)grp_id;
+ unsigned long flags;
+ u32 imask;
+
+ if (likely(napi_schedule_prep(&grp->napi_rx))) {
+ spin_lock_irqsave(&grp->grplock, flags);
+ imask = gfar_read(&grp->regs->imask);
+ imask &= IMASK_RX_DISABLED;
+ gfar_write(&grp->regs->imask, imask);
+ spin_unlock_irqrestore(&grp->grplock, flags);
+ __napi_schedule(&grp->napi_rx);
+ } else {
+ /* Clear IEVENT, so interrupts aren't called again
+ * because of the packets that have already arrived.
+ */
+ gfar_write(&grp->regs->ievent, IEVENT_RX_MASK);
+ }
+
+ return IRQ_HANDLED;
+}
+
+/* Interrupt Handler for Transmit complete */
+static irqreturn_t gfar_transmit(int irq, void *grp_id)
+{
+ struct gfar_priv_grp *grp = (struct gfar_priv_grp *)grp_id;
+ unsigned long flags;
+ u32 imask;
+
+ if (likely(napi_schedule_prep(&grp->napi_tx))) {
+ spin_lock_irqsave(&grp->grplock, flags);
+ imask = gfar_read(&grp->regs->imask);
+ imask &= IMASK_TX_DISABLED;
+ gfar_write(&grp->regs->imask, imask);
+ spin_unlock_irqrestore(&grp->grplock, flags);
+ __napi_schedule(&grp->napi_tx);
+ } else {
+ /* Clear IEVENT, so interrupts aren't called again
+ * because of the packets that have already arrived.
+ */
+ gfar_write(&grp->regs->ievent, IEVENT_TX_MASK);
+ }
+
return IRQ_HANDLED;
}
@@ -2852,7 +2829,7 @@
rx_queue->stats.rx_bytes += pkt_len;
skb_record_rx_queue(skb, rx_queue->qindex);
gfar_process_frame(dev, skb, amount_pull,
- &rx_queue->grp->napi);
+ &rx_queue->grp->napi_rx);
} else {
netif_warn(priv, rx_err, dev, "Missing skb!\n");
@@ -2881,66 +2858,81 @@
return howmany;
}
-static int gfar_poll_sq(struct napi_struct *napi, int budget)
+static int gfar_poll_rx_sq(struct napi_struct *napi, int budget)
{
struct gfar_priv_grp *gfargrp =
- container_of(napi, struct gfar_priv_grp, napi);
+ container_of(napi, struct gfar_priv_grp, napi_rx);
struct gfar __iomem *regs = gfargrp->regs;
- struct gfar_priv_tx_q *tx_queue = gfargrp->priv->tx_queue[0];
- struct gfar_priv_rx_q *rx_queue = gfargrp->priv->rx_queue[0];
+ struct gfar_priv_rx_q *rx_queue = gfargrp->rx_queue;
int work_done = 0;
/* Clear IEVENT, so interrupts aren't called again
* because of the packets that have already arrived
*/
- gfar_write(®s->ievent, IEVENT_RTX_MASK);
-
- /* run Tx cleanup to completion */
- if (tx_queue->tx_skbuff[tx_queue->skb_dirtytx])
- gfar_clean_tx_ring(tx_queue);
+ gfar_write(®s->ievent, IEVENT_RX_MASK);
work_done = gfar_clean_rx_ring(rx_queue, budget);
if (work_done < budget) {
+ u32 imask;
napi_complete(napi);
/* Clear the halt bit in RSTAT */
gfar_write(®s->rstat, gfargrp->rstat);
- gfar_write(®s->imask, IMASK_DEFAULT);
-
- /* If we are coalescing interrupts, update the timer
- * Otherwise, clear it
- */
- gfar_write(®s->txic, 0);
- if (likely(tx_queue->txcoalescing))
- gfar_write(®s->txic, tx_queue->txic);
-
- gfar_write(®s->rxic, 0);
- if (unlikely(rx_queue->rxcoalescing))
- gfar_write(®s->rxic, rx_queue->rxic);
+ spin_lock_irq(&gfargrp->grplock);
+ imask = gfar_read(®s->imask);
+ imask |= IMASK_RX_DEFAULT;
+ gfar_write(®s->imask, imask);
+ spin_unlock_irq(&gfargrp->grplock);
}
return work_done;
}
-static int gfar_poll(struct napi_struct *napi, int budget)
+static int gfar_poll_tx_sq(struct napi_struct *napi, int budget)
{
struct gfar_priv_grp *gfargrp =
- container_of(napi, struct gfar_priv_grp, napi);
+ container_of(napi, struct gfar_priv_grp, napi_tx);
+ struct gfar __iomem *regs = gfargrp->regs;
+ struct gfar_priv_tx_q *tx_queue = gfargrp->tx_queue;
+ u32 imask;
+
+ /* Clear IEVENT, so interrupts aren't called again
+ * because of the packets that have already arrived
+ */
+ gfar_write(®s->ievent, IEVENT_TX_MASK);
+
+ /* run Tx cleanup to completion */
+ if (tx_queue->tx_skbuff[tx_queue->skb_dirtytx])
+ gfar_clean_tx_ring(tx_queue);
+
+ napi_complete(napi);
+
+ spin_lock_irq(&gfargrp->grplock);
+ imask = gfar_read(®s->imask);
+ imask |= IMASK_TX_DEFAULT;
+ gfar_write(®s->imask, imask);
+ spin_unlock_irq(&gfargrp->grplock);
+
+ return 0;
+}
+
+static int gfar_poll_rx(struct napi_struct *napi, int budget)
+{
+ struct gfar_priv_grp *gfargrp =
+ container_of(napi, struct gfar_priv_grp, napi_rx);
struct gfar_private *priv = gfargrp->priv;
struct gfar __iomem *regs = gfargrp->regs;
- struct gfar_priv_tx_q *tx_queue = NULL;
struct gfar_priv_rx_q *rx_queue = NULL;
int work_done = 0, work_done_per_q = 0;
int i, budget_per_q = 0;
- int has_tx_work = 0;
unsigned long rstat_rxf;
int num_act_queues;
/* Clear IEVENT, so interrupts aren't called again
* because of the packets that have already arrived
*/
- gfar_write(®s->ievent, IEVENT_RTX_MASK);
+ gfar_write(®s->ievent, IEVENT_RX_MASK);
rstat_rxf = gfar_read(®s->rstat) & RSTAT_RXF_MASK;
@@ -2948,15 +2940,6 @@
if (num_act_queues)
budget_per_q = budget/num_act_queues;
- for_each_set_bit(i, &gfargrp->tx_bit_map, priv->num_tx_queues) {
- tx_queue = priv->tx_queue[i];
- /* run Tx cleanup to completion */
- if (tx_queue->tx_skbuff[tx_queue->skb_dirtytx]) {
- gfar_clean_tx_ring(tx_queue);
- has_tx_work = 1;
- }
- }
-
for_each_set_bit(i, &gfargrp->rx_bit_map, priv->num_rx_queues) {
/* skip queue if not active */
if (!(rstat_rxf & (RSTAT_CLEAR_RXF0 >> i)))
@@ -2979,25 +2962,62 @@
}
}
- if (!num_act_queues && !has_tx_work) {
-
+ if (!num_act_queues) {
+ u32 imask;
napi_complete(napi);
/* Clear the halt bit in RSTAT */
gfar_write(®s->rstat, gfargrp->rstat);
- gfar_write(®s->imask, IMASK_DEFAULT);
-
- /* If we are coalescing interrupts, update the timer
- * Otherwise, clear it
- */
- gfar_configure_coalescing(priv, gfargrp->rx_bit_map,
- gfargrp->tx_bit_map);
+ spin_lock_irq(&gfargrp->grplock);
+ imask = gfar_read(®s->imask);
+ imask |= IMASK_RX_DEFAULT;
+ gfar_write(®s->imask, imask);
+ spin_unlock_irq(&gfargrp->grplock);
}
return work_done;
}
+static int gfar_poll_tx(struct napi_struct *napi, int budget)
+{
+ struct gfar_priv_grp *gfargrp =
+ container_of(napi, struct gfar_priv_grp, napi_tx);
+ struct gfar_private *priv = gfargrp->priv;
+ struct gfar __iomem *regs = gfargrp->regs;
+ struct gfar_priv_tx_q *tx_queue = NULL;
+ int has_tx_work = 0;
+ int i;
+
+ /* Clear IEVENT, so interrupts aren't called again
+ * because of the packets that have already arrived
+ */
+ gfar_write(®s->ievent, IEVENT_TX_MASK);
+
+ for_each_set_bit(i, &gfargrp->tx_bit_map, priv->num_tx_queues) {
+ tx_queue = priv->tx_queue[i];
+ /* run Tx cleanup to completion */
+ if (tx_queue->tx_skbuff[tx_queue->skb_dirtytx]) {
+ gfar_clean_tx_ring(tx_queue);
+ has_tx_work = 1;
+ }
+ }
+
+ if (!has_tx_work) {
+ u32 imask;
+ napi_complete(napi);
+
+ spin_lock_irq(&gfargrp->grplock);
+ imask = gfar_read(®s->imask);
+ imask |= IMASK_TX_DEFAULT;
+ gfar_write(®s->imask, imask);
+ spin_unlock_irq(&gfargrp->grplock);
+ }
+
+ return 0;
+}
+
+
#ifdef CONFIG_NET_POLL_CONTROLLER
/* Polling 'interrupt' - used by things like netconsole to send skbs
* without having to re-enable interrupts. It's not called while
@@ -3101,12 +3121,11 @@
{
struct gfar_private *priv = netdev_priv(dev);
struct gfar __iomem *regs = priv->gfargrp[0].regs;
- unsigned long flags;
struct phy_device *phydev = priv->phydev;
int new_state = 0;
- local_irq_save(flags);
- lock_tx_qs(priv);
+ if (test_bit(GFAR_RESETTING, &priv->state))
+ return;
if (phydev->link) {
u32 tempval1 = gfar_read(®s->maccfg1);
@@ -3178,8 +3197,6 @@
if (new_state && netif_msg_link(priv))
phy_print_status(phydev);
- unlock_tx_qs(priv);
- local_irq_restore(flags);
}
/* Update the hash table based on the current list of multicast
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index 52bb2b0..84632c5 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -9,7 +9,7 @@
* Maintainer: Kumar Gala
* Modifier: Sandeep Gopalpet <sandeep.kumar@freescale.com>
*
- * Copyright 2002-2009, 2011 Freescale Semiconductor, Inc.
+ * Copyright 2002-2009, 2011-2013 Freescale Semiconductor, Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
@@ -377,8 +377,11 @@
IMASK_RXFEN0 | IMASK_BSY | IMASK_EBERR | IMASK_BABR | \
IMASK_XFUN | IMASK_RXC | IMASK_BABT | IMASK_DPE \
| IMASK_PERR)
-#define IMASK_RTX_DISABLED ((~(IMASK_RXFEN0 | IMASK_TXFEN | IMASK_BSY)) \
- & IMASK_DEFAULT)
+#define IMASK_RX_DEFAULT (IMASK_RXFEN0 | IMASK_BSY)
+#define IMASK_TX_DEFAULT (IMASK_TXFEN | IMASK_TXBEN)
+
+#define IMASK_RX_DISABLED ((~(IMASK_RX_DEFAULT)) & IMASK_DEFAULT)
+#define IMASK_TX_DISABLED ((~(IMASK_TX_DEFAULT)) & IMASK_DEFAULT)
/* Fifo management */
#define FIFO_TX_THR_MASK 0x01ff
@@ -409,7 +412,9 @@
/* This default RIR value directly corresponds
* to the 3-bit hash value generated */
-#define DEFAULT_RIR0 0x05397700
+#define DEFAULT_8RXQ_RIR0 0x05397700
+/* Map even hash values to Q0, and odd ones to Q1 */
+#define DEFAULT_2RXQ_RIR0 0x04104100
/* RQFCR register bits */
#define RQFCR_GPI 0x80000000
@@ -880,7 +885,6 @@
#define FSL_GIANFAR_DEV_HAS_CSUM 0x00000010
#define FSL_GIANFAR_DEV_HAS_VLAN 0x00000020
#define FSL_GIANFAR_DEV_HAS_EXTENDED_HASH 0x00000040
-#define FSL_GIANFAR_DEV_HAS_PADDING 0x00000080
#define FSL_GIANFAR_DEV_HAS_MAGIC_PACKET 0x00000100
#define FSL_GIANFAR_DEV_HAS_BD_STASHING 0x00000200
#define FSL_GIANFAR_DEV_HAS_BUF_STASHING 0x00000400
@@ -892,8 +896,8 @@
#define DEFAULT_MAPPING 0xFF
#endif
-#define ISRG_SHIFT_TX 0x10
-#define ISRG_SHIFT_RX 0x18
+#define ISRG_RR0 0x80000000
+#define ISRG_TR0 0x00800000
/* The same driver can operate in two modes */
/* SQ_SG_MODE: Single Queue Single Group Mode
@@ -905,6 +909,22 @@
MQ_MG_MODE
};
+/* GFAR_SQ_POLLING: Single Queue NAPI polling mode
+ * The driver supports a single pair of RX/Tx queues
+ * per interrupt group (Rx/Tx int line). MQ_MG mode
+ * devices have 2 interrupt groups, so the device will
+ * have a total of 2 Tx and 2 Rx queues in this case.
+ * GFAR_MQ_POLLING: Multi Queue NAPI polling mode
+ * The driver supports all the 8 Rx and Tx HW queues
+ * each queue mapped by the Device Tree to one of
+ * the 2 interrupt groups. This mode implies significant
+ * processing overhead (CPU and controller level).
+ */
+enum gfar_poll_mode {
+ GFAR_SQ_POLLING = 0,
+ GFAR_MQ_POLLING
+};
+
/*
* Per TX queue stats
*/
@@ -966,7 +986,6 @@
/**
* struct gfar_priv_rx_q - per rx queue structure
- * @rxlock: per queue rx spin lock
* @rx_skbuff: skb pointers
* @skb_currx: currently use skb pointer
* @rx_bd_base: First rx buffer descriptor
@@ -979,8 +998,7 @@
*/
struct gfar_priv_rx_q {
- spinlock_t rxlock __attribute__ ((aligned (SMP_CACHE_BYTES)));
- struct sk_buff ** rx_skbuff;
+ struct sk_buff **rx_skbuff __aligned(SMP_CACHE_BYTES);
dma_addr_t rx_bd_dma_base;
struct rxbd8 *rx_bd_base;
struct rxbd8 *cur_rx;
@@ -1016,17 +1034,20 @@
*/
struct gfar_priv_grp {
- spinlock_t grplock __attribute__ ((aligned (SMP_CACHE_BYTES)));
- struct napi_struct napi;
- struct gfar_private *priv;
+ spinlock_t grplock __aligned(SMP_CACHE_BYTES);
+ struct napi_struct napi_rx;
+ struct napi_struct napi_tx;
struct gfar __iomem *regs;
- unsigned int rstat;
- unsigned long num_rx_queues;
- unsigned long rx_bit_map;
- /* cacheline 3 */
+ struct gfar_priv_tx_q *tx_queue;
+ struct gfar_priv_rx_q *rx_queue;
unsigned int tstat;
+ unsigned int rstat;
+
+ struct gfar_private *priv;
unsigned long num_tx_queues;
unsigned long tx_bit_map;
+ unsigned long num_rx_queues;
+ unsigned long rx_bit_map;
struct gfar_irqinfo *irqinfo[GFAR_NUM_IRQS];
};
@@ -1041,6 +1062,11 @@
GFAR_ERRATA_12 = 0x08, /* a.k.a errata eTSEC49 */
};
+enum gfar_dev_state {
+ GFAR_DOWN = 1,
+ GFAR_RESETTING
+};
+
/* Struct stolen almost completely (and shamelessly) from the FCC enet source
* (Ok, that's not so true anymore, but there is a family resemblance)
* The GFAR buffer descriptors track the ring buffers. The rx_bd_base
@@ -1051,8 +1077,6 @@
* the buffer descriptor determines the actual condition.
*/
struct gfar_private {
- unsigned int num_rx_queues;
-
struct device *dev;
struct net_device *ndev;
enum gfar_errata errata;
@@ -1060,6 +1084,7 @@
u16 uses_rxfcb;
u16 padding;
+ u32 device_flags;
/* HW time stamping enabled flag */
int hwts_rx_en;
@@ -1069,10 +1094,12 @@
struct gfar_priv_rx_q *rx_queue[MAX_RX_QS];
struct gfar_priv_grp gfargrp[MAXGROUPS];
- u32 device_flags;
+ unsigned long state;
- unsigned int mode;
+ unsigned short mode;
+ unsigned short poll_mode;
unsigned int num_tx_queues;
+ unsigned int num_rx_queues;
unsigned int num_grps;
/* Network Statistics */
@@ -1113,6 +1140,9 @@
unsigned int total_tx_ring_size;
unsigned int total_rx_ring_size;
+ u32 rqueue;
+ u32 tqueue;
+
/* RX per device parameters */
unsigned int rx_stash_size;
unsigned int rx_stash_index;
@@ -1127,11 +1157,6 @@
u32 __iomem *hash_regs[16];
int hash_width;
- /* global parameters */
- unsigned int fifo_threshold;
- unsigned int fifo_starve;
- unsigned int fifo_starve_off;
-
/*Filer table*/
unsigned int ftp_rqfpr[MAX_FILER_IDX + 1];
unsigned int ftp_rqfcr[MAX_FILER_IDX + 1];
@@ -1176,21 +1201,42 @@
*fpr = gfar_read(®s->rqfpr);
}
-void lock_rx_qs(struct gfar_private *priv);
-void lock_tx_qs(struct gfar_private *priv);
-void unlock_rx_qs(struct gfar_private *priv);
-void unlock_tx_qs(struct gfar_private *priv);
+static inline void gfar_write_isrg(struct gfar_private *priv)
+{
+ struct gfar __iomem *regs = priv->gfargrp[0].regs;
+ u32 __iomem *baddr = ®s->isrg0;
+ u32 isrg = 0;
+ int grp_idx, i;
+
+ for (grp_idx = 0; grp_idx < priv->num_grps; grp_idx++) {
+ struct gfar_priv_grp *grp = &priv->gfargrp[grp_idx];
+
+ for_each_set_bit(i, &grp->rx_bit_map, priv->num_rx_queues) {
+ isrg |= (ISRG_RR0 >> i);
+ }
+
+ for_each_set_bit(i, &grp->tx_bit_map, priv->num_tx_queues) {
+ isrg |= (ISRG_TR0 >> i);
+ }
+
+ gfar_write(baddr, isrg);
+
+ baddr++;
+ isrg = 0;
+ }
+}
+
irqreturn_t gfar_receive(int irq, void *dev_id);
int startup_gfar(struct net_device *dev);
void stop_gfar(struct net_device *dev);
-void gfar_halt(struct net_device *dev);
+void reset_gfar(struct net_device *dev);
+void gfar_mac_reset(struct gfar_private *priv);
+void gfar_halt(struct gfar_private *priv);
+void gfar_start(struct gfar_private *priv);
void gfar_phy_test(struct mii_bus *bus, struct phy_device *phydev, int enable,
u32 regnum, u32 read);
void gfar_configure_coalescing_all(struct gfar_private *priv);
-void gfar_init_sysfs(struct net_device *dev);
int gfar_set_features(struct net_device *dev, netdev_features_t features);
-void gfar_check_rx_parser_mode(struct gfar_private *priv);
-void gfar_vlan_mode(struct net_device *dev, netdev_features_t features);
extern const struct ethtool_ops gfar_ethtool_ops;
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 63d2344..891dbee 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -44,10 +44,6 @@
#include "gianfar.h"
-extern void gfar_start(struct net_device *dev);
-extern int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue,
- int rx_work_limit);
-
#define GFAR_MAX_COAL_USECS 0xffff
#define GFAR_MAX_COAL_FRAMES 0xff
static void gfar_fill_stats(struct net_device *dev, struct ethtool_stats *dummy,
@@ -364,25 +360,11 @@
struct ethtool_coalesce *cvals)
{
struct gfar_private *priv = netdev_priv(dev);
- int i = 0;
+ int i, err = 0;
if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_COALESCE))
return -EOPNOTSUPP;
- /* Set up rx coalescing */
- /* As of now, we will enable/disable coalescing for all
- * queues together in case of eTSEC2, this will be modified
- * along with the ethtool interface
- */
- if ((cvals->rx_coalesce_usecs == 0) ||
- (cvals->rx_max_coalesced_frames == 0)) {
- for (i = 0; i < priv->num_rx_queues; i++)
- priv->rx_queue[i]->rxcoalescing = 0;
- } else {
- for (i = 0; i < priv->num_rx_queues; i++)
- priv->rx_queue[i]->rxcoalescing = 1;
- }
-
if (NULL == priv->phydev)
return -ENODEV;
@@ -399,6 +381,32 @@
return -EINVAL;
}
+ /* Check the bounds of the values */
+ if (cvals->tx_coalesce_usecs > GFAR_MAX_COAL_USECS) {
+ netdev_info(dev, "Coalescing is limited to %d microseconds\n",
+ GFAR_MAX_COAL_USECS);
+ return -EINVAL;
+ }
+
+ if (cvals->tx_max_coalesced_frames > GFAR_MAX_COAL_FRAMES) {
+ netdev_info(dev, "Coalescing is limited to %d frames\n",
+ GFAR_MAX_COAL_FRAMES);
+ return -EINVAL;
+ }
+
+ while (test_and_set_bit_lock(GFAR_RESETTING, &priv->state))
+ cpu_relax();
+
+ /* Set up rx coalescing */
+ if ((cvals->rx_coalesce_usecs == 0) ||
+ (cvals->rx_max_coalesced_frames == 0)) {
+ for (i = 0; i < priv->num_rx_queues; i++)
+ priv->rx_queue[i]->rxcoalescing = 0;
+ } else {
+ for (i = 0; i < priv->num_rx_queues; i++)
+ priv->rx_queue[i]->rxcoalescing = 1;
+ }
+
for (i = 0; i < priv->num_rx_queues; i++) {
priv->rx_queue[i]->rxic = mk_ic_value(
cvals->rx_max_coalesced_frames,
@@ -415,28 +423,22 @@
priv->tx_queue[i]->txcoalescing = 1;
}
- /* Check the bounds of the values */
- if (cvals->tx_coalesce_usecs > GFAR_MAX_COAL_USECS) {
- netdev_info(dev, "Coalescing is limited to %d microseconds\n",
- GFAR_MAX_COAL_USECS);
- return -EINVAL;
- }
-
- if (cvals->tx_max_coalesced_frames > GFAR_MAX_COAL_FRAMES) {
- netdev_info(dev, "Coalescing is limited to %d frames\n",
- GFAR_MAX_COAL_FRAMES);
- return -EINVAL;
- }
-
for (i = 0; i < priv->num_tx_queues; i++) {
priv->tx_queue[i]->txic = mk_ic_value(
cvals->tx_max_coalesced_frames,
gfar_usecs2ticks(priv, cvals->tx_coalesce_usecs));
}
- gfar_configure_coalescing_all(priv);
+ if (dev->flags & IFF_UP) {
+ stop_gfar(dev);
+ err = startup_gfar(dev);
+ } else {
+ gfar_mac_reset(priv);
+ }
- return 0;
+ clear_bit_unlock(GFAR_RESETTING, &priv->state);
+
+ return err;
}
/* Fills in rvals with the current ring parameters. Currently,
@@ -467,15 +469,13 @@
}
/* Change the current ring parameters, stopping the controller if
- * necessary so that we don't mess things up while we're in
- * motion. We wait for the ring to be clean before reallocating
- * the rings.
+ * necessary so that we don't mess things up while we're in motion.
*/
static int gfar_sringparam(struct net_device *dev,
struct ethtool_ringparam *rvals)
{
struct gfar_private *priv = netdev_priv(dev);
- int err = 0, i = 0;
+ int err = 0, i;
if (rvals->rx_pending > GFAR_RX_MAX_RING_SIZE)
return -EINVAL;
@@ -493,44 +493,25 @@
return -EINVAL;
}
+ while (test_and_set_bit_lock(GFAR_RESETTING, &priv->state))
+ cpu_relax();
- if (dev->flags & IFF_UP) {
- unsigned long flags;
-
- /* Halt TX and RX, and process the frames which
- * have already been received
- */
- local_irq_save(flags);
- lock_tx_qs(priv);
- lock_rx_qs(priv);
-
- gfar_halt(dev);
-
- unlock_rx_qs(priv);
- unlock_tx_qs(priv);
- local_irq_restore(flags);
-
- for (i = 0; i < priv->num_rx_queues; i++)
- gfar_clean_rx_ring(priv->rx_queue[i],
- priv->rx_queue[i]->rx_ring_size);
-
- /* Now we take down the rings to rebuild them */
+ if (dev->flags & IFF_UP)
stop_gfar(dev);
- }
- /* Change the size */
- for (i = 0; i < priv->num_rx_queues; i++) {
+ /* Change the sizes */
+ for (i = 0; i < priv->num_rx_queues; i++)
priv->rx_queue[i]->rx_ring_size = rvals->rx_pending;
+
+ for (i = 0; i < priv->num_tx_queues; i++)
priv->tx_queue[i]->tx_ring_size = rvals->tx_pending;
- priv->tx_queue[i]->num_txbdfree =
- priv->tx_queue[i]->tx_ring_size;
- }
/* Rebuild the rings with the new size */
- if (dev->flags & IFF_UP) {
+ if (dev->flags & IFF_UP)
err = startup_gfar(dev);
- netif_tx_wake_all_queues(dev);
- }
+
+ clear_bit_unlock(GFAR_RESETTING, &priv->state);
+
return err;
}
@@ -608,43 +589,29 @@
int gfar_set_features(struct net_device *dev, netdev_features_t features)
{
- struct gfar_private *priv = netdev_priv(dev);
- unsigned long flags;
- int err = 0, i = 0;
netdev_features_t changed = dev->features ^ features;
+ struct gfar_private *priv = netdev_priv(dev);
+ int err = 0;
- if (changed & (NETIF_F_HW_VLAN_CTAG_TX|NETIF_F_HW_VLAN_CTAG_RX))
- gfar_vlan_mode(dev, features);
-
- if (!(changed & NETIF_F_RXCSUM))
+ if (!(changed & (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_RXCSUM)))
return 0;
+ while (test_and_set_bit_lock(GFAR_RESETTING, &priv->state))
+ cpu_relax();
+
+ dev->features = features;
+
if (dev->flags & IFF_UP) {
- /* Halt TX and RX, and process the frames which
- * have already been received
- */
- local_irq_save(flags);
- lock_tx_qs(priv);
- lock_rx_qs(priv);
-
- gfar_halt(dev);
-
- unlock_tx_qs(priv);
- unlock_rx_qs(priv);
- local_irq_restore(flags);
-
- for (i = 0; i < priv->num_rx_queues; i++)
- gfar_clean_rx_ring(priv->rx_queue[i],
- priv->rx_queue[i]->rx_ring_size);
-
/* Now we take down the rings to rebuild them */
stop_gfar(dev);
-
- dev->features = features;
-
err = startup_gfar(dev);
- netif_tx_wake_all_queues(dev);
+ } else {
+ gfar_mac_reset(priv);
}
+
+ clear_bit_unlock(GFAR_RESETTING, &priv->state);
+
return err;
}
@@ -1610,9 +1577,6 @@
if (tab->index > MAX_FILER_IDX - 1)
return -EBUSY;
- /* Avoid inconsistent filer table to be processed */
- lock_rx_qs(priv);
-
/* Fill regular entries */
for (; i < MAX_FILER_IDX - 1 && (tab->fe[i].ctrl | tab->fe[i].ctrl);
i++)
@@ -1625,8 +1589,6 @@
*/
gfar_write_filer(priv, i, 0x20, 0x0);
- unlock_rx_qs(priv);
-
return 0;
}
@@ -1831,6 +1793,9 @@
struct gfar_private *priv = netdev_priv(dev);
int ret = 0;
+ if (test_bit(GFAR_RESETTING, &priv->state))
+ return -EBUSY;
+
mutex_lock(&priv->rx_queue_access);
switch (cmd->cmd) {
diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c
index abc28da..bb56800 100644
--- a/drivers/net/ethernet/freescale/gianfar_ptp.c
+++ b/drivers/net/ethernet/freescale/gianfar_ptp.c
@@ -414,6 +414,7 @@
.n_alarm = 0,
.n_ext_ts = N_EXT_TS,
.n_per_out = 0,
+ .n_pins = 0,
.pps = 1,
.adjfreq = ptp_gianfar_adjfreq,
.adjtime = ptp_gianfar_adjtime,
diff --git a/drivers/net/ethernet/freescale/gianfar_sysfs.c b/drivers/net/ethernet/freescale/gianfar_sysfs.c
deleted file mode 100644
index e02dd13..0000000
--- a/drivers/net/ethernet/freescale/gianfar_sysfs.c
+++ /dev/null
@@ -1,340 +0,0 @@
-/*
- * drivers/net/ethernet/freescale/gianfar_sysfs.c
- *
- * Gianfar Ethernet Driver
- * This driver is designed for the non-CPM ethernet controllers
- * on the 85xx and 83xx family of integrated processors
- * Based on 8260_io/fcc_enet.c
- *
- * Author: Andy Fleming
- * Maintainer: Kumar Gala (galak@kernel.crashing.org)
- * Modifier: Sandeep Gopalpet <sandeep.kumar@freescale.com>
- *
- * Copyright 2002-2009 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- *
- * Sysfs file creation and management
- */
-
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/unistd.h>
-#include <linux/delay.h>
-#include <linux/etherdevice.h>
-#include <linux/spinlock.h>
-#include <linux/mm.h>
-#include <linux/device.h>
-
-#include <asm/uaccess.h>
-#include <linux/module.h>
-
-#include "gianfar.h"
-
-static ssize_t gfar_show_bd_stash(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct gfar_private *priv = netdev_priv(to_net_dev(dev));
-
- return sprintf(buf, "%s\n", priv->bd_stash_en ? "on" : "off");
-}
-
-static ssize_t gfar_set_bd_stash(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct gfar_private *priv = netdev_priv(to_net_dev(dev));
- struct gfar __iomem *regs = priv->gfargrp[0].regs;
- int new_setting = 0;
- u32 temp;
- unsigned long flags;
-
- if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_BD_STASHING))
- return count;
-
-
- /* Find out the new setting */
- if (!strncmp("on", buf, count - 1) || !strncmp("1", buf, count - 1))
- new_setting = 1;
- else if (!strncmp("off", buf, count - 1) ||
- !strncmp("0", buf, count - 1))
- new_setting = 0;
- else
- return count;
-
-
- local_irq_save(flags);
- lock_rx_qs(priv);
-
- /* Set the new stashing value */
- priv->bd_stash_en = new_setting;
-
- temp = gfar_read(®s->attr);
-
- if (new_setting)
- temp |= ATTR_BDSTASH;
- else
- temp &= ~(ATTR_BDSTASH);
-
- gfar_write(®s->attr, temp);
-
- unlock_rx_qs(priv);
- local_irq_restore(flags);
-
- return count;
-}
-
-static DEVICE_ATTR(bd_stash, 0644, gfar_show_bd_stash, gfar_set_bd_stash);
-
-static ssize_t gfar_show_rx_stash_size(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct gfar_private *priv = netdev_priv(to_net_dev(dev));
-
- return sprintf(buf, "%d\n", priv->rx_stash_size);
-}
-
-static ssize_t gfar_set_rx_stash_size(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct gfar_private *priv = netdev_priv(to_net_dev(dev));
- struct gfar __iomem *regs = priv->gfargrp[0].regs;
- unsigned int length = simple_strtoul(buf, NULL, 0);
- u32 temp;
- unsigned long flags;
-
- if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_BUF_STASHING))
- return count;
-
- local_irq_save(flags);
- lock_rx_qs(priv);
-
- if (length > priv->rx_buffer_size)
- goto out;
-
- if (length == priv->rx_stash_size)
- goto out;
-
- priv->rx_stash_size = length;
-
- temp = gfar_read(®s->attreli);
- temp &= ~ATTRELI_EL_MASK;
- temp |= ATTRELI_EL(length);
- gfar_write(®s->attreli, temp);
-
- /* Turn stashing on/off as appropriate */
- temp = gfar_read(®s->attr);
-
- if (length)
- temp |= ATTR_BUFSTASH;
- else
- temp &= ~(ATTR_BUFSTASH);
-
- gfar_write(®s->attr, temp);
-
-out:
- unlock_rx_qs(priv);
- local_irq_restore(flags);
-
- return count;
-}
-
-static DEVICE_ATTR(rx_stash_size, 0644, gfar_show_rx_stash_size,
- gfar_set_rx_stash_size);
-
-/* Stashing will only be enabled when rx_stash_size != 0 */
-static ssize_t gfar_show_rx_stash_index(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct gfar_private *priv = netdev_priv(to_net_dev(dev));
-
- return sprintf(buf, "%d\n", priv->rx_stash_index);
-}
-
-static ssize_t gfar_set_rx_stash_index(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct gfar_private *priv = netdev_priv(to_net_dev(dev));
- struct gfar __iomem *regs = priv->gfargrp[0].regs;
- unsigned short index = simple_strtoul(buf, NULL, 0);
- u32 temp;
- unsigned long flags;
-
- if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_BUF_STASHING))
- return count;
-
- local_irq_save(flags);
- lock_rx_qs(priv);
-
- if (index > priv->rx_stash_size)
- goto out;
-
- if (index == priv->rx_stash_index)
- goto out;
-
- priv->rx_stash_index = index;
-
- temp = gfar_read(®s->attreli);
- temp &= ~ATTRELI_EI_MASK;
- temp |= ATTRELI_EI(index);
- gfar_write(®s->attreli, temp);
-
-out:
- unlock_rx_qs(priv);
- local_irq_restore(flags);
-
- return count;
-}
-
-static DEVICE_ATTR(rx_stash_index, 0644, gfar_show_rx_stash_index,
- gfar_set_rx_stash_index);
-
-static ssize_t gfar_show_fifo_threshold(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct gfar_private *priv = netdev_priv(to_net_dev(dev));
-
- return sprintf(buf, "%d\n", priv->fifo_threshold);
-}
-
-static ssize_t gfar_set_fifo_threshold(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct gfar_private *priv = netdev_priv(to_net_dev(dev));
- struct gfar __iomem *regs = priv->gfargrp[0].regs;
- unsigned int length = simple_strtoul(buf, NULL, 0);
- u32 temp;
- unsigned long flags;
-
- if (length > GFAR_MAX_FIFO_THRESHOLD)
- return count;
-
- local_irq_save(flags);
- lock_tx_qs(priv);
-
- priv->fifo_threshold = length;
-
- temp = gfar_read(®s->fifo_tx_thr);
- temp &= ~FIFO_TX_THR_MASK;
- temp |= length;
- gfar_write(®s->fifo_tx_thr, temp);
-
- unlock_tx_qs(priv);
- local_irq_restore(flags);
-
- return count;
-}
-
-static DEVICE_ATTR(fifo_threshold, 0644, gfar_show_fifo_threshold,
- gfar_set_fifo_threshold);
-
-static ssize_t gfar_show_fifo_starve(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct gfar_private *priv = netdev_priv(to_net_dev(dev));
-
- return sprintf(buf, "%d\n", priv->fifo_starve);
-}
-
-static ssize_t gfar_set_fifo_starve(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct gfar_private *priv = netdev_priv(to_net_dev(dev));
- struct gfar __iomem *regs = priv->gfargrp[0].regs;
- unsigned int num = simple_strtoul(buf, NULL, 0);
- u32 temp;
- unsigned long flags;
-
- if (num > GFAR_MAX_FIFO_STARVE)
- return count;
-
- local_irq_save(flags);
- lock_tx_qs(priv);
-
- priv->fifo_starve = num;
-
- temp = gfar_read(®s->fifo_tx_starve);
- temp &= ~FIFO_TX_STARVE_MASK;
- temp |= num;
- gfar_write(®s->fifo_tx_starve, temp);
-
- unlock_tx_qs(priv);
- local_irq_restore(flags);
-
- return count;
-}
-
-static DEVICE_ATTR(fifo_starve, 0644, gfar_show_fifo_starve,
- gfar_set_fifo_starve);
-
-static ssize_t gfar_show_fifo_starve_off(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct gfar_private *priv = netdev_priv(to_net_dev(dev));
-
- return sprintf(buf, "%d\n", priv->fifo_starve_off);
-}
-
-static ssize_t gfar_set_fifo_starve_off(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct gfar_private *priv = netdev_priv(to_net_dev(dev));
- struct gfar __iomem *regs = priv->gfargrp[0].regs;
- unsigned int num = simple_strtoul(buf, NULL, 0);
- u32 temp;
- unsigned long flags;
-
- if (num > GFAR_MAX_FIFO_STARVE_OFF)
- return count;
-
- local_irq_save(flags);
- lock_tx_qs(priv);
-
- priv->fifo_starve_off = num;
-
- temp = gfar_read(®s->fifo_tx_starve_shutoff);
- temp &= ~FIFO_TX_STARVE_OFF_MASK;
- temp |= num;
- gfar_write(®s->fifo_tx_starve_shutoff, temp);
-
- unlock_tx_qs(priv);
- local_irq_restore(flags);
-
- return count;
-}
-
-static DEVICE_ATTR(fifo_starve_off, 0644, gfar_show_fifo_starve_off,
- gfar_set_fifo_starve_off);
-
-void gfar_init_sysfs(struct net_device *dev)
-{
- struct gfar_private *priv = netdev_priv(dev);
- int rc;
-
- /* Initialize the default values */
- priv->fifo_threshold = DEFAULT_FIFO_TX_THR;
- priv->fifo_starve = DEFAULT_FIFO_TX_STARVE;
- priv->fifo_starve_off = DEFAULT_FIFO_TX_STARVE_OFF;
-
- /* Create our sysfs files */
- rc = device_create_file(&dev->dev, &dev_attr_bd_stash);
- rc |= device_create_file(&dev->dev, &dev_attr_rx_stash_size);
- rc |= device_create_file(&dev->dev, &dev_attr_rx_stash_index);
- rc |= device_create_file(&dev->dev, &dev_attr_fifo_threshold);
- rc |= device_create_file(&dev->dev, &dev_attr_fifo_starve);
- rc |= device_create_file(&dev->dev, &dev_attr_fifo_starve_off);
- if (rc)
- dev_err(&dev->dev, "Error creating gianfar sysfs files\n");
-}
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 72291a8..c8299c3 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -3261,7 +3261,7 @@
dev->stats.tx_packets++;
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
ugeth->tx_skbuff[txQ][ugeth->skb_dirtytx[txQ]] = NULL;
ugeth->skb_dirtytx[txQ] =
diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c
index 17fca32..c984998 100644
--- a/drivers/net/ethernet/i825xx/lib82596.c
+++ b/drivers/net/ethernet/i825xx/lib82596.c
@@ -993,7 +993,7 @@
dev->name));
dev->stats.tx_dropped++;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
} else {
if (++lp->next_tx_cmd == TX_RING_SIZE)
lp->next_tx_cmd = 0;
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 7628e0f..538903b 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -490,7 +490,7 @@
skb_arr[index] = skb;
tmp_addr = ehea_map_vaddr(skb->data);
if (tmp_addr == -1) {
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
q_skba->os_skbs = fill_wqes - i;
ret = 0;
break;
@@ -856,7 +856,7 @@
index = EHEA_BMASK_GET(EHEA_WR_ID_INDEX, cqe->wr_id);
skb = pr->sq_skba.arr[index];
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
pr->sq_skba.arr[index] = NULL;
}
@@ -2044,7 +2044,7 @@
skb_copy_bits(skb, 0, imm_data, skb->len);
swqe->immediate_data_length = skb->len;
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
}
static int ehea_start_xmit(struct sk_buff *skb, struct net_device *dev)
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 4be9715..c912756 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -522,10 +522,21 @@
return rc;
}
+static u64 ibmveth_encode_mac_addr(u8 *mac)
+{
+ int i;
+ u64 encoded = 0;
+
+ for (i = 0; i < ETH_ALEN; i++)
+ encoded = (encoded << 8) | mac[i];
+
+ return encoded;
+}
+
static int ibmveth_open(struct net_device *netdev)
{
struct ibmveth_adapter *adapter = netdev_priv(netdev);
- u64 mac_address = 0;
+ u64 mac_address;
int rxq_entries = 1;
unsigned long lpar_rc;
int rc;
@@ -579,8 +590,7 @@
adapter->rx_queue.num_slots = rxq_entries;
adapter->rx_queue.toggle = 1;
- memcpy(&mac_address, netdev->dev_addr, netdev->addr_len);
- mac_address = mac_address >> 16;
+ mac_address = ibmveth_encode_mac_addr(netdev->dev_addr);
rxq_desc.fields.flags_len = IBMVETH_BUF_VALID |
adapter->rx_queue.queue_len;
@@ -1034,7 +1044,7 @@
DMA_TO_DEVICE);
out:
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
return NETDEV_TX_OK;
map_failed_frags:
@@ -1062,7 +1072,7 @@
unsigned long lpar_rc;
restart_poll:
- do {
+ while (frames_processed < budget) {
if (!ibmveth_rxq_pending_buffer(adapter))
break;
@@ -1111,7 +1121,7 @@
netdev->stats.rx_bytes += length;
frames_processed++;
}
- } while (frames_processed < budget);
+ }
ibmveth_replenish_task(adapter);
@@ -1183,8 +1193,8 @@
/* add the addresses to the filter table */
netdev_for_each_mc_addr(ha, netdev) {
/* add the multicast address to the filter table */
- unsigned long mcast_addr = 0;
- memcpy(((char *)&mcast_addr)+2, ha->addr, ETH_ALEN);
+ u64 mcast_addr;
+ mcast_addr = ibmveth_encode_mac_addr(ha->addr);
lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address,
IbmVethMcastAddFilter,
mcast_addr);
@@ -1372,9 +1382,6 @@
netif_napi_add(netdev, &adapter->napi, ibmveth_poll, 16);
- adapter->mac_addr = 0;
- memcpy(&adapter->mac_addr, mac_addr_p, ETH_ALEN);
-
netdev->irq = dev->irq;
netdev->netdev_ops = &ibmveth_netdev_ops;
netdev->ethtool_ops = &netdev_ethtool_ops;
@@ -1383,7 +1390,7 @@
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
netdev->features |= netdev->hw_features;
- memcpy(netdev->dev_addr, &adapter->mac_addr, netdev->addr_len);
+ memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN);
for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
struct kobject *kobj = &adapter->rx_buff_pool[i].kobj;
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 451ba79..1f37499 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -138,7 +138,6 @@
struct napi_struct napi;
struct net_device_stats stats;
unsigned int mcastFilterSize;
- unsigned long mac_addr;
void * buffer_list_addr;
void * filter_list_addr;
dma_addr_t buffer_list_dma;
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index cbaba44..b56461c 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -1778,9 +1778,9 @@
* testing, ie sending frames with bad CRC.
*/
if (unlikely(skb->no_fcs))
- cb->command |= __constant_cpu_to_le16(cb_tx_nc);
+ cb->command |= cpu_to_le16(cb_tx_nc);
else
- cb->command &= ~__constant_cpu_to_le16(cb_tx_nc);
+ cb->command &= ~cpu_to_le16(cb_tx_nc);
/* interrupt every 16 packets regardless of delay */
if ((nic->cbs_avail & ~15) == nic->cbs_avail)
@@ -3034,7 +3034,7 @@
*enable_wake = false;
}
- pci_disable_device(pdev);
+ pci_clear_master(pdev);
}
static int __e100_power_off(struct pci_dev *pdev, bool wake)
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
index ff2d806..a5f6b11 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
/* 80003ES2LAN Gigabit Ethernet Controller (Copper)
* 80003ES2LAN Gigabit Ethernet Controller (Serdes)
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.h b/drivers/net/ethernet/intel/e1000e/80003es2lan.h
index 90d363b..535a943 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.h
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.h
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#ifndef _E1000E_80003ES2LAN_H_
#define _E1000E_80003ES2LAN_H_
diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c
index 8fed74e..e0aa7f1 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.c
+++ b/drivers/net/ethernet/intel/e1000e/82571.c
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
/* 82571EB Gigabit Ethernet Controller
* 82571EB Gigabit Ethernet Controller (Copper)
diff --git a/drivers/net/ethernet/intel/e1000e/82571.h b/drivers/net/ethernet/intel/e1000e/82571.h
index 08e24dc..2e758f7 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.h
+++ b/drivers/net/ethernet/intel/e1000e/82571.h
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#ifndef _E1000E_82571_H_
#define _E1000E_82571_H_
diff --git a/drivers/net/ethernet/intel/e1000e/Makefile b/drivers/net/ethernet/intel/e1000e/Makefile
index c2dcfcc1..106de49 100644
--- a/drivers/net/ethernet/intel/e1000e/Makefile
+++ b/drivers/net/ethernet/intel/e1000e/Makefile
@@ -1,7 +1,7 @@
################################################################################
#
# Intel PRO/1000 Linux driver
-# Copyright(c) 1999 - 2013 Intel Corporation.
+# Copyright(c) 1999 - 2014 Intel Corporation.
#
# This program is free software; you can redistribute it and/or modify it
# under the terms and conditions of the GNU General Public License,
@@ -12,9 +12,8 @@
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
# more details.
#
-# You should have received a copy of the GNU General Public License along with
-# this program; if not, write to the Free Software Foundation, Inc.,
-# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, see <http://www.gnu.org/licenses/>.
#
# The full GNU General Public License is included in this distribution in
# the file called "COPYING".
diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index 351c94a..d18e892 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#ifndef _E1000_DEFINES_H_
#define _E1000_DEFINES_H_
@@ -35,9 +28,11 @@
/* Definitions for power management and wakeup registers */
/* Wake Up Control */
-#define E1000_WUC_APME 0x00000001 /* APM Enable */
-#define E1000_WUC_PME_EN 0x00000002 /* PME Enable */
-#define E1000_WUC_PHY_WAKE 0x00000100 /* if PHY supports wakeup */
+#define E1000_WUC_APME 0x00000001 /* APM Enable */
+#define E1000_WUC_PME_EN 0x00000002 /* PME Enable */
+#define E1000_WUC_PME_STATUS 0x00000004 /* PME Status */
+#define E1000_WUC_APMPME 0x00000008 /* Assert PME on APM Wakeup */
+#define E1000_WUC_PHY_WAKE 0x00000100 /* if PHY supports wakeup */
/* Wake Up Filter Control */
#define E1000_WUFC_LNKC 0x00000001 /* Link Status Change Wakeup Enable */
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 0150f7f..1471c54 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
/* Linux PRO/1000 Ethernet Driver main header file */
@@ -269,6 +262,7 @@
u32 tx_head_addr;
u32 tx_fifo_size;
u32 tx_dma_failed;
+ u32 tx_hwtstamp_timeouts;
/* Rx */
bool (*clean_rx) (struct e1000_ring *ring, int *work_done,
@@ -333,7 +327,6 @@
struct work_struct update_phy_task;
struct work_struct print_hang_task;
- bool idle_check;
int phy_hang_count;
u16 tx_ring_count;
@@ -342,6 +335,7 @@
struct hwtstamp_config hwtstamp_config;
struct delayed_work systim_overflow_work;
struct sk_buff *tx_hwtstamp_skb;
+ unsigned long tx_hwtstamp_start;
struct work_struct tx_hwtstamp_work;
spinlock_t systim_lock; /* protects SYSTIML/H regsters */
struct cyclecounter cc;
@@ -476,7 +470,7 @@
void e1000e_set_ethtool_ops(struct net_device *netdev);
int e1000e_up(struct e1000_adapter *adapter);
-void e1000e_down(struct e1000_adapter *adapter);
+void e1000e_down(struct e1000_adapter *adapter, bool reset);
void e1000e_reinit_locked(struct e1000_adapter *adapter);
void e1000e_reset(struct e1000_adapter *adapter);
void e1000e_power_up_phy(struct e1000_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index d14c8f5..cad250b 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
/* ethtool support for e1000 */
@@ -111,6 +104,7 @@
E1000_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared),
E1000_STAT("uncorr_ecc_errors", uncorr_errors),
E1000_STAT("corr_ecc_errors", corr_errors),
+ E1000_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts),
};
#define E1000_GLOBAL_STATS_LEN ARRAY_SIZE(e1000_gstrings_stats)
@@ -332,7 +326,7 @@
/* reset the link */
if (netif_running(adapter->netdev)) {
- e1000e_down(adapter);
+ e1000e_down(adapter, true);
e1000e_up(adapter);
} else {
e1000e_reset(adapter);
@@ -380,7 +374,7 @@
if (adapter->fc_autoneg == AUTONEG_ENABLE) {
hw->fc.requested_mode = e1000_fc_default;
if (netif_running(adapter->netdev)) {
- e1000e_down(adapter);
+ e1000e_down(adapter, true);
e1000e_up(adapter);
} else {
e1000e_reset(adapter);
@@ -726,7 +720,7 @@
pm_runtime_get_sync(netdev->dev.parent);
- e1000e_down(adapter);
+ e1000e_down(adapter, true);
/* We can't just free everything and then setup again, because the
* ISRs in MSI-X mode get passed pointers to the Tx and Rx ring
@@ -924,15 +918,21 @@
}
if (mac->type == e1000_pch2lan) {
/* SHRAH[0,1,2] different than previous */
- if (i == 7)
+ if (i == 1)
mask &= 0xFFF4FFFF;
/* SHRAH[3] different than SHRAH[0,1,2] */
- if (i == 10)
+ if (i == 4)
mask |= (1 << 30);
+ /* RAR[1-6] owned by management engine - skipping */
+ if (i > 0)
+ i += 6;
}
REG_PATTERN_TEST_ARRAY(E1000_RA, ((i << 1) + 1), mask,
0xFFFFFFFF);
+ /* reset index to actual value */
+ if ((mac->type == e1000_pch2lan) && (i > 6))
+ i -= 6;
}
for (i = 0; i < mac->mta_reg_count; i++)
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index b7f3843..6b3de5f 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#ifndef _E1000_HW_H_
#define _E1000_HW_H_
@@ -655,12 +648,20 @@
#define E1000_ICH8_SHADOW_RAM_WORDS 2048
+/* I218 PHY Ultra Low Power (ULP) states */
+enum e1000_ulp_state {
+ e1000_ulp_state_unknown,
+ e1000_ulp_state_off,
+ e1000_ulp_state_on,
+};
+
struct e1000_dev_spec_ich8lan {
bool kmrn_lock_loss_workaround_enabled;
struct e1000_shadow_ram shadow_ram[E1000_ICH8_SHADOW_RAM_WORDS];
bool nvm_k1_enabled;
bool eee_disable;
u16 eee_lp_ability;
+ enum e1000_ulp_state ulp_state;
};
struct e1000_hw {
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 42f0f67..9866f26 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
/* 82562G 10/100 Network Connection
* 82562G-2 10/100 Network Connection
@@ -53,6 +46,14 @@
* 82578DC Gigabit Network Connection
* 82579LM Gigabit Network Connection
* 82579V Gigabit Network Connection
+ * Ethernet Connection I217-LM
+ * Ethernet Connection I217-V
+ * Ethernet Connection I218-V
+ * Ethernet Connection I218-LM
+ * Ethernet Connection (2) I218-LM
+ * Ethernet Connection (2) I218-V
+ * Ethernet Connection (3) I218-LM
+ * Ethernet Connection (3) I218-V
*/
#include "e1000.h"
@@ -142,7 +143,9 @@
static void e1000_rar_set_pch_lpt(struct e1000_hw *hw, u8 *addr, u32 index);
static s32 e1000_k1_workaround_lv(struct e1000_hw *hw);
static void e1000_gate_hw_phy_config_ich8lan(struct e1000_hw *hw, bool gate);
+static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force);
static s32 e1000_setup_copper_link_pch_lpt(struct e1000_hw *hw);
+static s32 e1000_oem_bits_config_ich8lan(struct e1000_hw *hw, bool d0_state);
static inline u16 __er16flash(struct e1000_hw *hw, unsigned long reg)
{
@@ -239,6 +242,47 @@
}
/**
+ * e1000_toggle_lanphypc_pch_lpt - toggle the LANPHYPC pin value
+ * @hw: pointer to the HW structure
+ *
+ * Toggling the LANPHYPC pin value fully power-cycles the PHY and is
+ * used to reset the PHY to a quiescent state when necessary.
+ **/
+static void e1000_toggle_lanphypc_pch_lpt(struct e1000_hw *hw)
+{
+ u32 mac_reg;
+
+ /* Set Phy Config Counter to 50msec */
+ mac_reg = er32(FEXTNVM3);
+ mac_reg &= ~E1000_FEXTNVM3_PHY_CFG_COUNTER_MASK;
+ mac_reg |= E1000_FEXTNVM3_PHY_CFG_COUNTER_50MSEC;
+ ew32(FEXTNVM3, mac_reg);
+
+ /* Toggle LANPHYPC Value bit */
+ mac_reg = er32(CTRL);
+ mac_reg |= E1000_CTRL_LANPHYPC_OVERRIDE;
+ mac_reg &= ~E1000_CTRL_LANPHYPC_VALUE;
+ ew32(CTRL, mac_reg);
+ e1e_flush();
+ usleep_range(10, 20);
+ mac_reg &= ~E1000_CTRL_LANPHYPC_OVERRIDE;
+ ew32(CTRL, mac_reg);
+ e1e_flush();
+
+ if (hw->mac.type < e1000_pch_lpt) {
+ msleep(50);
+ } else {
+ u16 count = 20;
+
+ do {
+ usleep_range(5000, 10000);
+ } while (!(er32(CTRL_EXT) & E1000_CTRL_EXT_LPCD) && count--);
+
+ msleep(30);
+ }
+}
+
+/**
* e1000_init_phy_workarounds_pchlan - PHY initialization workarounds
* @hw: pointer to the HW structure
*
@@ -247,6 +291,7 @@
**/
static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
{
+ struct e1000_adapter *adapter = hw->adapter;
u32 mac_reg, fwsm = er32(FWSM);
s32 ret_val;
@@ -255,6 +300,12 @@
*/
e1000_gate_hw_phy_config_ich8lan(hw, true);
+ /* It is not possible to be certain of the current state of ULP
+ * so forcibly disable it.
+ */
+ hw->dev_spec.ich8lan.ulp_state = e1000_ulp_state_unknown;
+ e1000_disable_ulp_lpt_lp(hw, true);
+
ret_val = hw->phy.ops.acquire(hw);
if (ret_val) {
e_dbg("Failed to initialize PHY flow\n");
@@ -300,33 +351,9 @@
break;
}
- e_dbg("Toggling LANPHYPC\n");
-
- /* Set Phy Config Counter to 50msec */
- mac_reg = er32(FEXTNVM3);
- mac_reg &= ~E1000_FEXTNVM3_PHY_CFG_COUNTER_MASK;
- mac_reg |= E1000_FEXTNVM3_PHY_CFG_COUNTER_50MSEC;
- ew32(FEXTNVM3, mac_reg);
-
/* Toggle LANPHYPC Value bit */
- mac_reg = er32(CTRL);
- mac_reg |= E1000_CTRL_LANPHYPC_OVERRIDE;
- mac_reg &= ~E1000_CTRL_LANPHYPC_VALUE;
- ew32(CTRL, mac_reg);
- e1e_flush();
- usleep_range(10, 20);
- mac_reg &= ~E1000_CTRL_LANPHYPC_OVERRIDE;
- ew32(CTRL, mac_reg);
- e1e_flush();
- if (hw->mac.type < e1000_pch_lpt) {
- msleep(50);
- } else {
- u16 count = 20;
- do {
- usleep_range(5000, 10000);
- } while (!(er32(CTRL_EXT) &
- E1000_CTRL_EXT_LPCD) && count--);
- usleep_range(30000, 60000);
+ e1000_toggle_lanphypc_pch_lpt(hw);
+ if (hw->mac.type >= e1000_pch_lpt) {
if (e1000_phy_is_accessible_pchlan(hw))
break;
@@ -349,12 +376,31 @@
hw->phy.ops.release(hw);
if (!ret_val) {
+
+ /* Check to see if able to reset PHY. Print error if not */
+ if (hw->phy.ops.check_reset_block(hw)) {
+ e_err("Reset blocked by ME\n");
+ goto out;
+ }
+
/* Reset the PHY before any access to it. Doing so, ensures
* that the PHY is in a known good state before we read/write
* PHY registers. The generic reset is sufficient here,
* because we haven't determined the PHY type yet.
*/
ret_val = e1000e_phy_hw_reset_generic(hw);
+ if (ret_val)
+ goto out;
+
+ /* On a successful reset, possibly need to wait for the PHY
+ * to quiesce to an accessible state before returning control
+ * to the calling function. If the PHY does not quiesce, then
+ * return E1000E_BLK_PHY_RESET, as this is the condition that
+ * the PHY is in.
+ */
+ ret_val = hw->phy.ops.check_reset_block(hw);
+ if (ret_val)
+ e_err("ME blocked access to PHY after reset\n");
}
out:
@@ -724,8 +770,14 @@
* Enable/disable EEE based on setting in dev_spec structure, the duplex of
* the link and the EEE capabilities of the link partner. The LPI Control
* register bits will remain set only if/when link is up.
+ *
+ * EEE LPI must not be asserted earlier than one second after link is up.
+ * On 82579, EEE LPI should not be enabled until such time otherwise there
+ * can be link issues with some switches. Other devices can have EEE LPI
+ * enabled immediately upon link up since they have a timer in hardware which
+ * prevents LPI from being asserted too early.
**/
-static s32 e1000_set_eee_pchlan(struct e1000_hw *hw)
+s32 e1000_set_eee_pchlan(struct e1000_hw *hw)
{
struct e1000_dev_spec_ich8lan *dev_spec = &hw->dev_spec.ich8lan;
s32 ret_val;
@@ -979,6 +1031,253 @@
}
/**
+ * e1000_enable_ulp_lpt_lp - configure Ultra Low Power mode for LynxPoint-LP
+ * @hw: pointer to the HW structure
+ * @to_sx: boolean indicating a system power state transition to Sx
+ *
+ * When link is down, configure ULP mode to significantly reduce the power
+ * to the PHY. If on a Manageability Engine (ME) enabled system, tell the
+ * ME firmware to start the ULP configuration. If not on an ME enabled
+ * system, configure the ULP mode by software.
+ */
+s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx)
+{
+ u32 mac_reg;
+ s32 ret_val = 0;
+ u16 phy_reg;
+
+ if ((hw->mac.type < e1000_pch_lpt) ||
+ (hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPT_I217_LM) ||
+ (hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPT_I217_V) ||
+ (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_LM2) ||
+ (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_V2) ||
+ (hw->dev_spec.ich8lan.ulp_state == e1000_ulp_state_on))
+ return 0;
+
+ if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) {
+ /* Request ME configure ULP mode in the PHY */
+ mac_reg = er32(H2ME);
+ mac_reg |= E1000_H2ME_ULP | E1000_H2ME_ENFORCE_SETTINGS;
+ ew32(H2ME, mac_reg);
+
+ goto out;
+ }
+
+ if (!to_sx) {
+ int i = 0;
+
+ /* Poll up to 5 seconds for Cable Disconnected indication */
+ while (!(er32(FEXT) & E1000_FEXT_PHY_CABLE_DISCONNECTED)) {
+ /* Bail if link is re-acquired */
+ if (er32(STATUS) & E1000_STATUS_LU)
+ return -E1000_ERR_PHY;
+
+ if (i++ == 100)
+ break;
+
+ msleep(50);
+ }
+ e_dbg("CABLE_DISCONNECTED %s set after %dmsec\n",
+ (er32(FEXT) &
+ E1000_FEXT_PHY_CABLE_DISCONNECTED) ? "" : "not", i * 50);
+ }
+
+ ret_val = hw->phy.ops.acquire(hw);
+ if (ret_val)
+ goto out;
+
+ /* Force SMBus mode in PHY */
+ ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg);
+ if (ret_val)
+ goto release;
+ phy_reg |= CV_SMB_CTRL_FORCE_SMBUS;
+ e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg);
+
+ /* Force SMBus mode in MAC */
+ mac_reg = er32(CTRL_EXT);
+ mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS;
+ ew32(CTRL_EXT, mac_reg);
+
+ /* Set Inband ULP Exit, Reset to SMBus mode and
+ * Disable SMBus Release on PERST# in PHY
+ */
+ ret_val = e1000_read_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, &phy_reg);
+ if (ret_val)
+ goto release;
+ phy_reg |= (I218_ULP_CONFIG1_RESET_TO_SMBUS |
+ I218_ULP_CONFIG1_DISABLE_SMB_PERST);
+ if (to_sx) {
+ if (er32(WUFC) & E1000_WUFC_LNKC)
+ phy_reg |= I218_ULP_CONFIG1_WOL_HOST;
+
+ phy_reg |= I218_ULP_CONFIG1_STICKY_ULP;
+ } else {
+ phy_reg |= I218_ULP_CONFIG1_INBAND_EXIT;
+ }
+ e1000_write_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, phy_reg);
+
+ /* Set Disable SMBus Release on PERST# in MAC */
+ mac_reg = er32(FEXTNVM7);
+ mac_reg |= E1000_FEXTNVM7_DISABLE_SMB_PERST;
+ ew32(FEXTNVM7, mac_reg);
+
+ /* Commit ULP changes in PHY by starting auto ULP configuration */
+ phy_reg |= I218_ULP_CONFIG1_START;
+ e1000_write_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, phy_reg);
+release:
+ hw->phy.ops.release(hw);
+out:
+ if (ret_val)
+ e_dbg("Error in ULP enable flow: %d\n", ret_val);
+ else
+ hw->dev_spec.ich8lan.ulp_state = e1000_ulp_state_on;
+
+ return ret_val;
+}
+
+/**
+ * e1000_disable_ulp_lpt_lp - unconfigure Ultra Low Power mode for LynxPoint-LP
+ * @hw: pointer to the HW structure
+ * @force: boolean indicating whether or not to force disabling ULP
+ *
+ * Un-configure ULP mode when link is up, the system is transitioned from
+ * Sx or the driver is unloaded. If on a Manageability Engine (ME) enabled
+ * system, poll for an indication from ME that ULP has been un-configured.
+ * If not on an ME enabled system, un-configure the ULP mode by software.
+ *
+ * During nominal operation, this function is called when link is acquired
+ * to disable ULP mode (force=false); otherwise, for example when unloading
+ * the driver or during Sx->S0 transitions, this is called with force=true
+ * to forcibly disable ULP.
+ */
+static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force)
+{
+ s32 ret_val = 0;
+ u32 mac_reg;
+ u16 phy_reg;
+ int i = 0;
+
+ if ((hw->mac.type < e1000_pch_lpt) ||
+ (hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPT_I217_LM) ||
+ (hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPT_I217_V) ||
+ (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_LM2) ||
+ (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_V2) ||
+ (hw->dev_spec.ich8lan.ulp_state == e1000_ulp_state_off))
+ return 0;
+
+ if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) {
+ if (force) {
+ /* Request ME un-configure ULP mode in the PHY */
+ mac_reg = er32(H2ME);
+ mac_reg &= ~E1000_H2ME_ULP;
+ mac_reg |= E1000_H2ME_ENFORCE_SETTINGS;
+ ew32(H2ME, mac_reg);
+ }
+
+ /* Poll up to 100msec for ME to clear ULP_CFG_DONE */
+ while (er32(FWSM) & E1000_FWSM_ULP_CFG_DONE) {
+ if (i++ == 10) {
+ ret_val = -E1000_ERR_PHY;
+ goto out;
+ }
+
+ usleep_range(10000, 20000);
+ }
+ e_dbg("ULP_CONFIG_DONE cleared after %dmsec\n", i * 10);
+
+ if (force) {
+ mac_reg = er32(H2ME);
+ mac_reg &= ~E1000_H2ME_ENFORCE_SETTINGS;
+ ew32(H2ME, mac_reg);
+ } else {
+ /* Clear H2ME.ULP after ME ULP configuration */
+ mac_reg = er32(H2ME);
+ mac_reg &= ~E1000_H2ME_ULP;
+ ew32(H2ME, mac_reg);
+ }
+
+ goto out;
+ }
+
+ ret_val = hw->phy.ops.acquire(hw);
+ if (ret_val)
+ goto out;
+
+ if (force)
+ /* Toggle LANPHYPC Value bit */
+ e1000_toggle_lanphypc_pch_lpt(hw);
+
+ /* Unforce SMBus mode in PHY */
+ ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg);
+ if (ret_val) {
+ /* The MAC might be in PCIe mode, so temporarily force to
+ * SMBus mode in order to access the PHY.
+ */
+ mac_reg = er32(CTRL_EXT);
+ mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS;
+ ew32(CTRL_EXT, mac_reg);
+
+ msleep(50);
+
+ ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL,
+ &phy_reg);
+ if (ret_val)
+ goto release;
+ }
+ phy_reg &= ~CV_SMB_CTRL_FORCE_SMBUS;
+ e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg);
+
+ /* Unforce SMBus mode in MAC */
+ mac_reg = er32(CTRL_EXT);
+ mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS;
+ ew32(CTRL_EXT, mac_reg);
+
+ /* When ULP mode was previously entered, K1 was disabled by the
+ * hardware. Re-Enable K1 in the PHY when exiting ULP.
+ */
+ ret_val = e1000_read_phy_reg_hv_locked(hw, HV_PM_CTRL, &phy_reg);
+ if (ret_val)
+ goto release;
+ phy_reg |= HV_PM_CTRL_K1_ENABLE;
+ e1000_write_phy_reg_hv_locked(hw, HV_PM_CTRL, phy_reg);
+
+ /* Clear ULP enabled configuration */
+ ret_val = e1000_read_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, &phy_reg);
+ if (ret_val)
+ goto release;
+ phy_reg &= ~(I218_ULP_CONFIG1_IND |
+ I218_ULP_CONFIG1_STICKY_ULP |
+ I218_ULP_CONFIG1_RESET_TO_SMBUS |
+ I218_ULP_CONFIG1_WOL_HOST |
+ I218_ULP_CONFIG1_INBAND_EXIT |
+ I218_ULP_CONFIG1_DISABLE_SMB_PERST);
+ e1000_write_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, phy_reg);
+
+ /* Commit ULP changes by starting auto ULP configuration */
+ phy_reg |= I218_ULP_CONFIG1_START;
+ e1000_write_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, phy_reg);
+
+ /* Clear Disable SMBus Release on PERST# in MAC */
+ mac_reg = er32(FEXTNVM7);
+ mac_reg &= ~E1000_FEXTNVM7_DISABLE_SMB_PERST;
+ ew32(FEXTNVM7, mac_reg);
+
+release:
+ hw->phy.ops.release(hw);
+ if (force) {
+ e1000_phy_hw_reset(hw);
+ msleep(50);
+ }
+out:
+ if (ret_val)
+ e_dbg("Error in ULP disable flow: %d\n", ret_val);
+ else
+ hw->dev_spec.ich8lan.ulp_state = e1000_ulp_state_off;
+
+ return ret_val;
+}
+
+/**
* e1000_check_for_copper_link_ich8lan - Check for link (Copper)
* @hw: pointer to the HW structure
*
@@ -1106,9 +1405,11 @@
e1000e_check_downshift(hw);
/* Enable/Disable EEE after link up */
- ret_val = e1000_set_eee_pchlan(hw);
- if (ret_val)
- return ret_val;
+ if (hw->phy.type > e1000_phy_82579) {
+ ret_val = e1000_set_eee_pchlan(hw);
+ if (ret_val)
+ return ret_val;
+ }
/* If we are forcing speed/duplex, then we simply return since
* we have already determined whether we have link or not.
@@ -1374,7 +1675,7 @@
/* RAR[1-6] are owned by manageability. Skip those and program the
* next address into the SHRA register array.
*/
- if (index < (u32)(hw->mac.rar_entry_count - 6)) {
+ if (index < (u32)(hw->mac.rar_entry_count)) {
s32 ret_val;
ret_val = e1000_acquire_swflag_ich8lan(hw);
@@ -1484,11 +1785,13 @@
**/
static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw)
{
- u32 fwsm;
+ bool blocked = false;
+ int i = 0;
- fwsm = er32(FWSM);
-
- return (fwsm & E1000_ICH_FWSM_RSPCIPHY) ? 0 : E1000_BLK_PHY_RESET;
+ while ((blocked = !(er32(FWSM) & E1000_ICH_FWSM_RSPCIPHY)) &&
+ (i++ < 10))
+ usleep_range(10000, 20000);
+ return blocked ? E1000_BLK_PHY_RESET : 0;
}
/**
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h
index 217090d..bead50f 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.h
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#ifndef _E1000E_ICH8LAN_H_
#define _E1000E_ICH8LAN_H_
@@ -65,11 +58,16 @@
#define E1000_FWSM_WLOCK_MAC_MASK 0x0380
#define E1000_FWSM_WLOCK_MAC_SHIFT 7
+#define E1000_FWSM_ULP_CFG_DONE 0x00000400 /* Low power cfg done */
/* Shared Receive Address Registers */
#define E1000_SHRAL_PCH_LPT(_i) (0x05408 + ((_i) * 8))
#define E1000_SHRAH_PCH_LPT(_i) (0x0540C + ((_i) * 8))
+#define E1000_H2ME 0x05B50 /* Host to ME */
+#define E1000_H2ME_ULP 0x00000800 /* ULP Indication Bit */
+#define E1000_H2ME_ENFORCE_SETTINGS 0x00001000 /* Enforce Settings */
+
#define ID_LED_DEFAULT_ICH8LAN ((ID_LED_DEF1_DEF2 << 12) | \
(ID_LED_OFF1_OFF2 << 8) | \
(ID_LED_OFF1_ON2 << 4) | \
@@ -82,6 +80,9 @@
#define E1000_ICH8_LAN_INIT_TIMEOUT 1500
+/* FEXT register bit definition */
+#define E1000_FEXT_PHY_CABLE_DISCONNECTED 0x00000004
+
#define E1000_FEXTNVM_SW_CONFIG 1
#define E1000_FEXTNVM_SW_CONFIG_ICH8M (1 << 27) /* different on ICH8M */
@@ -95,10 +96,12 @@
#define E1000_FEXTNVM6_REQ_PLL_CLK 0x00000100
#define E1000_FEXTNVM6_ENABLE_K1_ENTRY_CONDITION 0x00000200
+#define E1000_FEXTNVM7_DISABLE_SMB_PERST 0x00000020
+
#define PCIE_ICH8_SNOOP_ALL PCIE_NO_SNOOP_ALL
#define E1000_ICH_RAR_ENTRIES 7
-#define E1000_PCH2_RAR_ENTRIES 11 /* RAR[0-6], SHRA[0-3] */
+#define E1000_PCH2_RAR_ENTRIES 5 /* RAR[0], SHRA[0-3] */
#define E1000_PCH_LPT_RAR_ENTRIES 12 /* RAR[0], SHRA[0-10] */
#define PHY_PAGE_SHIFT 5
@@ -161,6 +164,16 @@
#define CV_SMB_CTRL PHY_REG(769, 23)
#define CV_SMB_CTRL_FORCE_SMBUS 0x0001
+/* I218 Ultra Low Power Configuration 1 Register */
+#define I218_ULP_CONFIG1 PHY_REG(779, 16)
+#define I218_ULP_CONFIG1_START 0x0001 /* Start auto ULP config */
+#define I218_ULP_CONFIG1_IND 0x0004 /* Pwr up from ULP indication */
+#define I218_ULP_CONFIG1_STICKY_ULP 0x0010 /* Set sticky ULP mode */
+#define I218_ULP_CONFIG1_INBAND_EXIT 0x0020 /* Inband on ULP exit */
+#define I218_ULP_CONFIG1_WOL_HOST 0x0040 /* WoL Host on ULP exit */
+#define I218_ULP_CONFIG1_RESET_TO_SMBUS 0x0100 /* Reset to SMBus mode */
+#define I218_ULP_CONFIG1_DISABLE_SMB_PERST 0x1000 /* Disable on PERST# */
+
/* SMBus Address Phy Register */
#define HV_SMB_ADDR PHY_REG(768, 26)
#define HV_SMB_ADDR_MASK 0x007F
@@ -195,6 +208,7 @@
/* PHY Power Management Control */
#define HV_PM_CTRL PHY_REG(770, 17)
#define HV_PM_CTRL_PLL_STOP_IN_K1_GIGA 0x100
+#define HV_PM_CTRL_K1_ENABLE 0x4000
#define SW_FLAG_TIMEOUT 1000 /* SW Semaphore flag timeout in ms */
@@ -268,4 +282,6 @@
s32 e1000_lv_jumbo_workaround_ich8lan(struct e1000_hw *hw, bool enable);
s32 e1000_read_emi_reg_locked(struct e1000_hw *hw, u16 addr, u16 *data);
s32 e1000_write_emi_reg_locked(struct e1000_hw *hw, u16 addr, u16 data);
+s32 e1000_set_eee_pchlan(struct e1000_hw *hw);
+s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx);
#endif /* _E1000E_ICH8LAN_H_ */
diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c
index 2480c10..baa0a46 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.c
+++ b/drivers/net/ethernet/intel/e1000e/mac.c
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#include "e1000.h"
diff --git a/drivers/net/ethernet/intel/e1000e/mac.h b/drivers/net/ethernet/intel/e1000e/mac.h
index a61fee4..4e81c28 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.h
+++ b/drivers/net/ethernet/intel/e1000e/mac.h
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#ifndef _E1000E_MAC_H_
#define _E1000E_MAC_H_
diff --git a/drivers/net/ethernet/intel/e1000e/manage.c b/drivers/net/ethernet/intel/e1000e/manage.c
index e4b0f1e..cb37ff1 100644
--- a/drivers/net/ethernet/intel/e1000e/manage.c
+++ b/drivers/net/ethernet/intel/e1000e/manage.c
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#include "e1000.h"
diff --git a/drivers/net/ethernet/intel/e1000e/manage.h b/drivers/net/ethernet/intel/e1000e/manage.h
index 326897c..a8c27f9 100644
--- a/drivers/net/ethernet/intel/e1000e/manage.h
+++ b/drivers/net/ethernet/intel/e1000e/manage.h
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#ifndef _E1000E_MANAGE_H_
#define _E1000E_MANAGE_H_
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 6d91933..f1cce59 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -885,7 +878,7 @@
struct sk_buff *skb)
{
if (netdev->features & NETIF_F_RXHASH)
- skb->rxhash = le32_to_cpu(rss);
+ skb_set_hash(skb, le32_to_cpu(rss), PKT_HASH_TYPE_L3);
}
/**
@@ -1097,8 +1090,14 @@
adapter->tx_hang_recheck = true;
return;
}
- /* Real hang detected */
adapter->tx_hang_recheck = false;
+
+ if (er32(TDH(0)) == er32(TDT(0))) {
+ e_dbg("false hang detected, ignoring\n");
+ return;
+ }
+
+ /* Real hang detected */
netif_stop_queue(netdev);
e1e_rphy(hw, MII_BMSR, &phy_status);
@@ -1128,6 +1127,8 @@
eop, jiffies, eop_desc->upper.fields.status, er32(STATUS),
phy_status, phy_1000t_status, phy_ext_status, pci_status);
+ e1000e_dump(adapter);
+
/* Suggest workaround for known h/w issue */
if ((hw->mac.type == e1000_pchlan) && (er32(CTRL) & E1000_CTRL_TFCE))
e_err("Try turning off Tx pause (flow control) via ethtool\n");
@@ -1147,9 +1148,6 @@
tx_hwtstamp_work);
struct e1000_hw *hw = &adapter->hw;
- if (!adapter->tx_hwtstamp_skb)
- return;
-
if (er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID) {
struct skb_shared_hwtstamps shhwtstamps;
u64 txstmp;
@@ -1162,6 +1160,12 @@
skb_tstamp_tx(adapter->tx_hwtstamp_skb, &shhwtstamps);
dev_kfree_skb_any(adapter->tx_hwtstamp_skb);
adapter->tx_hwtstamp_skb = NULL;
+ } else if (time_after(jiffies, adapter->tx_hwtstamp_start
+ + adapter->tx_timeout_factor * HZ)) {
+ dev_kfree_skb_any(adapter->tx_hwtstamp_skb);
+ adapter->tx_hwtstamp_skb = NULL;
+ adapter->tx_hwtstamp_timeouts++;
+ e_warn("clearing Tx timestamp hang");
} else {
/* reschedule to check later */
schedule_work(&adapter->tx_hwtstamp_work);
@@ -1701,7 +1705,7 @@
adapter->flags2 &= ~FLAG2_IS_DISCARDING;
writel(0, rx_ring->head);
- if (rx_ring->adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
+ if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
e1000e_update_rdt_wa(rx_ring, 0);
else
writel(0, rx_ring->tail);
@@ -2038,13 +2042,16 @@
msix_entry),
GFP_KERNEL);
if (adapter->msix_entries) {
+ struct e1000_adapter *a = adapter;
+
for (i = 0; i < adapter->num_vectors; i++)
adapter->msix_entries[i].entry = i;
- err = pci_enable_msix(adapter->pdev,
- adapter->msix_entries,
- adapter->num_vectors);
- if (err == 0)
+ err = pci_enable_msix_range(a->pdev,
+ a->msix_entries,
+ a->num_vectors,
+ a->num_vectors);
+ if (err > 0)
return;
}
/* MSI-X failed, so fall through and try MSI */
@@ -2402,7 +2409,7 @@
tx_ring->next_to_clean = 0;
writel(0, tx_ring->head);
- if (tx_ring->adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
+ if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
e1000e_update_tdt_wa(tx_ring, 0);
else
writel(0, tx_ring->tail);
@@ -2894,7 +2901,7 @@
struct e1000_hw *hw = &adapter->hw;
struct e1000_ring *tx_ring = adapter->tx_ring;
u64 tdba;
- u32 tdlen, tarc;
+ u32 tdlen, tctl, tarc;
/* Setup the HW Tx Head and Tail descriptor pointers */
tdba = tx_ring->dma;
@@ -2931,6 +2938,12 @@
/* erratum work around: set txdctl the same for both queues */
ew32(TXDCTL(1), er32(TXDCTL(0)));
+ /* Program the Transmit Control Register */
+ tctl = er32(TCTL);
+ tctl &= ~E1000_TCTL_CT;
+ tctl |= E1000_TCTL_PSP | E1000_TCTL_RTLC |
+ (E1000_COLLISION_THRESHOLD << E1000_CT_SHIFT);
+
if (adapter->flags & FLAG_TARC_SPEED_MODE_BIT) {
tarc = er32(TARC(0));
/* set the speed mode bit, we'll clear it if we're not at
@@ -2961,6 +2974,8 @@
/* enable Report Status bit */
adapter->txd_cmd |= E1000_TXD_CMD_RS;
+ ew32(TCTL, tctl);
+
hw->mac.ops.config_collision_dist(hw);
}
@@ -3331,6 +3346,9 @@
struct e1000_hw *hw = &adapter->hw;
u32 rctl;
+ if (pm_runtime_suspended(netdev->dev.parent))
+ return;
+
/* Check for Promiscuous and All Multicast modes */
rctl = er32(RCTL);
@@ -3691,10 +3709,6 @@
*/
static void e1000_power_down_phy(struct e1000_adapter *adapter)
{
- /* WoL is enabled */
- if (adapter->wol)
- return;
-
if (adapter->hw.phy.ops.power_down)
adapter->hw.phy.ops.power_down(&adapter->hw);
}
@@ -3911,10 +3925,8 @@
}
if (!netif_running(adapter->netdev) &&
- !test_bit(__E1000_TESTING, &adapter->state)) {
+ !test_bit(__E1000_TESTING, &adapter->state))
e1000_power_down_phy(adapter);
- return;
- }
e1000_get_phy_info(hw);
@@ -3981,7 +3993,12 @@
static void e1000e_update_stats(struct e1000_adapter *adapter);
-void e1000e_down(struct e1000_adapter *adapter)
+/**
+ * e1000e_down - quiesce the device and optionally reset the hardware
+ * @adapter: board private structure
+ * @reset: boolean flag to reset the hardware or not
+ */
+void e1000e_down(struct e1000_adapter *adapter, bool reset)
{
struct net_device *netdev = adapter->netdev;
struct e1000_hw *hw = &adapter->hw;
@@ -4035,12 +4052,8 @@
e1000_lv_jumbo_workaround_ich8lan(hw, false))
e_dbg("failed to disable jumbo frame workaround mode\n");
- if (!pci_channel_offline(adapter->pdev))
+ if (reset && !pci_channel_offline(adapter->pdev))
e1000e_reset(adapter);
-
- /* TODO: for power management, we could drop the link and
- * pci_disable_device here.
- */
}
void e1000e_reinit_locked(struct e1000_adapter *adapter)
@@ -4048,7 +4061,7 @@
might_sleep();
while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
usleep_range(1000, 2000);
- e1000e_down(adapter);
+ e1000e_down(adapter, true);
e1000e_up(adapter);
clear_bit(__E1000_RESETTING, &adapter->state);
}
@@ -4326,7 +4339,6 @@
adapter->tx_hang_recheck = false;
netif_start_queue(netdev);
- adapter->idle_check = true;
hw->mac.get_link_status = true;
pm_runtime_put(&pdev->dev);
@@ -4376,14 +4388,15 @@
pm_runtime_get_sync(&pdev->dev);
if (!test_bit(__E1000_DOWN, &adapter->state)) {
- e1000e_down(adapter);
+ e1000e_down(adapter, true);
e1000_free_irq(adapter);
+
+ /* Link status message must follow this format */
+ pr_info("%s NIC Link is Down\n", adapter->netdev->name);
}
napi_disable(&adapter->napi);
- e1000_power_down_phy(adapter);
-
e1000e_free_tx_resources(adapter->tx_ring);
e1000e_free_rx_resources(adapter->rx_ring);
@@ -4460,11 +4473,16 @@
struct e1000_adapter *adapter = container_of(work,
struct e1000_adapter,
update_phy_task);
+ struct e1000_hw *hw = &adapter->hw;
if (test_bit(__E1000_DOWN, &adapter->state))
return;
- e1000_get_phy_info(&adapter->hw);
+ e1000_get_phy_info(hw);
+
+ /* Enable EEE on 82579 after link up */
+ if (hw->phy.type == e1000_phy_82579)
+ e1000_set_eee_pchlan(hw);
}
/**
@@ -4799,6 +4817,7 @@
if (adapter->phy_hang_count > 1) {
adapter->phy_hang_count = 0;
+ e_dbg("PHY appears hung - resetting\n");
schedule_work(&adapter->reset_task);
}
}
@@ -4957,15 +4976,11 @@
mod_timer(&adapter->phy_info_timer,
round_jiffies(jiffies + 2 * HZ));
- /* The link is lost so the controller stops DMA.
- * If there is queued Tx work that cannot be done
- * or if on an 8000ES2LAN which requires a Rx packet
- * buffer work-around on link down event, reset the
- * controller to flush the Tx/Rx packet buffers.
- * (Do the reset outside of interrupt context).
+ /* 8000ES2LAN requires a Rx packet buffer work-around
+ * on link down event; reset the controller to flush
+ * the Rx packet buffer.
*/
- if ((adapter->flags & FLAG_RX_NEEDS_RESTART) ||
- (e1000_desc_unused(tx_ring) + 1 < tx_ring->count))
+ if (adapter->flags & FLAG_RX_NEEDS_RESTART)
adapter->flags |= FLAG_RESTART_NOW;
else
pm_schedule_suspend(netdev->dev.parent,
@@ -4988,6 +5003,15 @@
adapter->gotc_old = adapter->stats.gotc;
spin_unlock(&adapter->stats64_lock);
+ /* If the link is lost the controller stops DMA, but
+ * if there is queued Tx work it cannot be done. So
+ * reset the controller to flush the Tx packet buffers.
+ */
+ if (!netif_carrier_ok(netdev) &&
+ (e1000_desc_unused(tx_ring) + 1 < tx_ring->count))
+ adapter->flags |= FLAG_RESTART_NOW;
+
+ /* If reset is necessary, do it outside of interrupt context. */
if (adapter->flags & FLAG_RESTART_NOW) {
schedule_work(&adapter->reset_task);
/* return immediately since reset is imminent */
@@ -5546,6 +5570,7 @@
skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
tx_flags |= E1000_TX_FLAGS_HWTSTAMP;
adapter->tx_hwtstamp_skb = skb_get(skb);
+ adapter->tx_hwtstamp_start = jiffies;
schedule_work(&adapter->tx_hwtstamp_work);
} else {
skb_tx_timestamp(skb);
@@ -5684,8 +5709,11 @@
adapter->max_frame_size = max_frame;
e_info("changing MTU from %d to %d\n", netdev->mtu, new_mtu);
netdev->mtu = new_mtu;
+
+ pm_runtime_get_sync(netdev->dev.parent);
+
if (netif_running(netdev))
- e1000e_down(adapter);
+ e1000e_down(adapter, true);
/* NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN
* means we reserve 2 more, this pushes us to allocate from the next
@@ -5711,6 +5739,8 @@
else
e1000e_reset(adapter);
+ pm_runtime_put_sync(netdev->dev.parent);
+
clear_bit(__E1000_RESETTING, &adapter->state);
return 0;
@@ -5852,7 +5882,7 @@
static int e1000_init_phy_wakeup(struct e1000_adapter *adapter, u32 wufc)
{
struct e1000_hw *hw = &adapter->hw;
- u32 i, mac_reg;
+ u32 i, mac_reg, wuc;
u16 phy_reg, wuc_enable;
int retval;
@@ -5899,13 +5929,18 @@
phy_reg |= BM_RCTL_RFCE;
hw->phy.ops.write_reg_page(&adapter->hw, BM_RCTL, phy_reg);
+ wuc = E1000_WUC_PME_EN;
+ if (wufc & (E1000_WUFC_MAG | E1000_WUFC_LNKC))
+ wuc |= E1000_WUC_APME;
+
/* enable PHY wakeup in MAC register */
ew32(WUFC, wufc);
- ew32(WUC, E1000_WUC_PHY_WAKE | E1000_WUC_PME_EN);
+ ew32(WUC, (E1000_WUC_PHY_WAKE | E1000_WUC_APMPME |
+ E1000_WUC_PME_STATUS | wuc));
/* configure and enable PHY wakeup in PHY registers */
hw->phy.ops.write_reg_page(&adapter->hw, BM_WUFC, wufc);
- hw->phy.ops.write_reg_page(&adapter->hw, BM_WUC, E1000_WUC_PME_EN);
+ hw->phy.ops.write_reg_page(&adapter->hw, BM_WUC, wuc);
/* activate PHY wakeup */
wuc_enable |= BM_WUC_ENABLE_BIT | BM_WUC_HOST_WU_BIT;
@@ -5918,15 +5953,10 @@
return retval;
}
-static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
+static int e1000e_pm_freeze(struct device *dev)
{
- struct net_device *netdev = pci_get_drvdata(pdev);
+ struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
struct e1000_adapter *adapter = netdev_priv(netdev);
- struct e1000_hw *hw = &adapter->hw;
- u32 ctrl, ctrl_ext, rctl, status;
- /* Runtime suspend should only enable wakeup for link changes */
- u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol;
- int retval = 0;
netif_device_detach(netdev);
@@ -5937,11 +5967,29 @@
usleep_range(10000, 20000);
WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
- e1000e_down(adapter);
+
+ /* Quiesce the device without resetting the hardware */
+ e1000e_down(adapter, false);
e1000_free_irq(adapter);
}
e1000e_reset_interrupt_capability(adapter);
+ /* Allow time for pending master requests to run */
+ e1000e_disable_pcie_master(&adapter->hw);
+
+ return 0;
+}
+
+static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
+{
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct e1000_adapter *adapter = netdev_priv(netdev);
+ struct e1000_hw *hw = &adapter->hw;
+ u32 ctrl, ctrl_ext, rctl, status;
+ /* Runtime suspend should only enable wakeup for link changes */
+ u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol;
+ int retval = 0;
+
status = er32(STATUS);
if (status & E1000_STATUS_LU)
wufc &= ~E1000_WUFC_LNKC;
@@ -5972,12 +6020,12 @@
ew32(CTRL_EXT, ctrl_ext);
}
+ if (!runtime)
+ e1000e_power_up_phy(adapter);
+
if (adapter->flags & FLAG_IS_ICH)
e1000_suspend_workarounds_ich8lan(&adapter->hw);
- /* Allow time for pending master requests to run */
- e1000e_disable_pcie_master(&adapter->hw);
-
if (adapter->flags2 & FLAG2_HAS_PHY_WAKEUP) {
/* enable wakeup by the PHY */
retval = e1000_init_phy_wakeup(adapter, wufc);
@@ -5991,10 +6039,23 @@
} else {
ew32(WUC, 0);
ew32(WUFC, 0);
+
+ e1000_power_down_phy(adapter);
}
- if (adapter->hw.phy.type == e1000_phy_igp_3)
+ if (adapter->hw.phy.type == e1000_phy_igp_3) {
e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw);
+ } else if (hw->mac.type == e1000_pch_lpt) {
+ if (!(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC)))
+ /* ULP does not support wake from unicast, multicast
+ * or broadcast.
+ */
+ retval = e1000_enable_ulp_lpt_lp(hw, !runtime);
+
+ if (retval)
+ return retval;
+ }
+
/* Release control of h/w to f/w. If f/w is AMT enabled, this
* would have already happened in close and is redundant.
@@ -6102,18 +6163,12 @@
}
#ifdef CONFIG_PM
-static bool e1000e_pm_ready(struct e1000_adapter *adapter)
-{
- return !!adapter->tx_ring->buffer_info;
-}
-
static int __e1000_resume(struct pci_dev *pdev)
{
struct net_device *netdev = pci_get_drvdata(pdev);
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
u16 aspm_disable_flag = 0;
- u32 err;
if (adapter->flags2 & FLAG2_DISABLE_ASPM_L0S)
aspm_disable_flag = PCIE_LINK_STATE_L0S;
@@ -6124,13 +6179,6 @@
pci_set_master(pdev);
- e1000e_set_interrupt_capability(adapter);
- if (netif_running(netdev)) {
- err = e1000_request_irq(adapter);
- if (err)
- return err;
- }
-
if (hw->mac.type >= e1000_pch2lan)
e1000_resume_workarounds_pchlan(&adapter->hw);
@@ -6169,11 +6217,6 @@
e1000_init_manageability_pt(adapter);
- if (netif_running(netdev))
- e1000e_up(adapter);
-
- netif_device_attach(netdev);
-
/* If the controller has AMT, do not set DRV_LOAD until the interface
* is up. For all other cases, let the f/w know that the h/w is now
* under the control of the driver.
@@ -6184,75 +6227,111 @@
return 0;
}
+static int e1000e_pm_thaw(struct device *dev)
+{
+ struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
+ struct e1000_adapter *adapter = netdev_priv(netdev);
+
+ e1000e_set_interrupt_capability(adapter);
+ if (netif_running(netdev)) {
+ u32 err = e1000_request_irq(adapter);
+
+ if (err)
+ return err;
+
+ e1000e_up(adapter);
+ }
+
+ netif_device_attach(netdev);
+
+ return 0;
+}
+
#ifdef CONFIG_PM_SLEEP
-static int e1000_suspend(struct device *dev)
+static int e1000e_pm_suspend(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
+ e1000e_pm_freeze(dev);
+
return __e1000_shutdown(pdev, false);
}
-static int e1000_resume(struct device *dev)
+static int e1000e_pm_resume(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
- struct net_device *netdev = pci_get_drvdata(pdev);
- struct e1000_adapter *adapter = netdev_priv(netdev);
+ int rc;
- if (e1000e_pm_ready(adapter))
- adapter->idle_check = true;
+ rc = __e1000_resume(pdev);
+ if (rc)
+ return rc;
- return __e1000_resume(pdev);
+ return e1000e_pm_thaw(dev);
}
#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_PM_RUNTIME
-static int e1000_runtime_suspend(struct device *dev)
+static int e1000e_pm_runtime_idle(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct net_device *netdev = pci_get_drvdata(pdev);
struct e1000_adapter *adapter = netdev_priv(netdev);
- if (!e1000e_pm_ready(adapter))
- return 0;
-
- return __e1000_shutdown(pdev, true);
-}
-
-static int e1000_idle(struct device *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct net_device *netdev = pci_get_drvdata(pdev);
- struct e1000_adapter *adapter = netdev_priv(netdev);
-
- if (!e1000e_pm_ready(adapter))
- return 0;
-
- if (adapter->idle_check) {
- adapter->idle_check = false;
- if (!e1000e_has_link(adapter))
- pm_schedule_suspend(dev, MSEC_PER_SEC);
- }
+ if (!e1000e_has_link(adapter))
+ pm_schedule_suspend(dev, 5 * MSEC_PER_SEC);
return -EBUSY;
}
-static int e1000_runtime_resume(struct device *dev)
+static int e1000e_pm_runtime_resume(struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct e1000_adapter *adapter = netdev_priv(netdev);
+ int rc;
+
+ rc = __e1000_resume(pdev);
+ if (rc)
+ return rc;
+
+ if (netdev->flags & IFF_UP)
+ rc = e1000e_up(adapter);
+
+ return rc;
+}
+
+static int e1000e_pm_runtime_suspend(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct net_device *netdev = pci_get_drvdata(pdev);
struct e1000_adapter *adapter = netdev_priv(netdev);
- if (!e1000e_pm_ready(adapter))
- return 0;
+ if (netdev->flags & IFF_UP) {
+ int count = E1000_CHECK_RESET_COUNT;
- adapter->idle_check = !dev->power.runtime_auto;
- return __e1000_resume(pdev);
+ while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
+ usleep_range(10000, 20000);
+
+ WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
+
+ /* Down the device without resetting the hardware */
+ e1000e_down(adapter, false);
+ }
+
+ if (__e1000_shutdown(pdev, true)) {
+ e1000e_pm_runtime_resume(dev);
+ return -EBUSY;
+ }
+
+ return 0;
}
#endif /* CONFIG_PM_RUNTIME */
#endif /* CONFIG_PM */
static void e1000_shutdown(struct pci_dev *pdev)
{
+ e1000e_pm_freeze(&pdev->dev);
+
__e1000_shutdown(pdev, false);
}
@@ -6338,7 +6417,7 @@
return PCI_ERS_RESULT_DISCONNECT;
if (netif_running(netdev))
- e1000e_down(adapter);
+ e1000e_down(adapter, true);
pci_disable_device(pdev);
/* Request a slot slot reset. */
@@ -6350,7 +6429,7 @@
* @pdev: Pointer to PCI device
*
* Restart the card from scratch, as if from a cold-boot. Implementation
- * resembles the first-half of the e1000_resume routine.
+ * resembles the first-half of the e1000e_pm_resume routine.
*/
static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev)
{
@@ -6397,7 +6476,7 @@
*
* This callback is called when the error recovery driver tells us that
* its OK to resume normal operation. Implementation resembles the
- * second-half of the e1000_resume routine.
+ * second-half of the e1000e_pm_resume routine.
*/
static void e1000_io_resume(struct pci_dev *pdev)
{
@@ -6902,9 +6981,6 @@
}
}
- if (!(netdev->flags & IFF_UP))
- e1000_power_down_phy(adapter);
-
/* Don't lie to e1000_close() down the road. */
if (!down)
clear_bit(__E1000_DOWN, &adapter->state);
@@ -7026,9 +7102,16 @@
MODULE_DEVICE_TABLE(pci, e1000_pci_tbl);
static const struct dev_pm_ops e1000_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(e1000_suspend, e1000_resume)
- SET_RUNTIME_PM_OPS(e1000_runtime_suspend, e1000_runtime_resume,
- e1000_idle)
+#ifdef CONFIG_PM_SLEEP
+ .suspend = e1000e_pm_suspend,
+ .resume = e1000e_pm_resume,
+ .freeze = e1000e_pm_freeze,
+ .thaw = e1000e_pm_thaw,
+ .poweroff = e1000e_pm_suspend,
+ .restore = e1000e_pm_resume,
+#endif
+ SET_RUNTIME_PM_OPS(e1000e_pm_runtime_suspend, e1000e_pm_runtime_resume,
+ e1000e_pm_runtime_idle)
};
/* PCI Device API Driver */
@@ -7055,7 +7138,7 @@
int ret;
pr_info("Intel(R) PRO/1000 Network Driver - %s\n",
e1000e_driver_version);
- pr_info("Copyright(c) 1999 - 2013 Intel Corporation.\n");
+ pr_info("Copyright(c) 1999 - 2014 Intel Corporation.\n");
ret = pci_register_driver(&e1000_driver);
return ret;
diff --git a/drivers/net/ethernet/intel/e1000e/nvm.c b/drivers/net/ethernet/intel/e1000e/nvm.c
index d70a039..a9a976f 100644
--- a/drivers/net/ethernet/intel/e1000e/nvm.c
+++ b/drivers/net/ethernet/intel/e1000e/nvm.c
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#include "e1000.h"
diff --git a/drivers/net/ethernet/intel/e1000e/nvm.h b/drivers/net/ethernet/intel/e1000e/nvm.h
index 45fc695..342bf69 100644
--- a/drivers/net/ethernet/intel/e1000e/nvm.h
+++ b/drivers/net/ethernet/intel/e1000e/nvm.h
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#ifndef _E1000E_NVM_H_
#define _E1000E_NVM_H_
diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c
index c16bd75..d0ac0f3 100644
--- a/drivers/net/ethernet/intel/e1000e/param.c
+++ b/drivers/net/ethernet/intel/e1000e/param.c
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#include <linux/netdevice.h>
#include <linux/module.h>
@@ -381,6 +374,12 @@
"%s set to dynamic mode\n", opt.name);
adapter->itr = 20000;
break;
+ case 2:
+ dev_info(&adapter->pdev->dev,
+ "%s Invalid mode - setting default\n",
+ opt.name);
+ adapter->itr_setting = opt.def;
+ /* fall-through */
case 3:
dev_info(&adapter->pdev->dev,
"%s set to dynamic conservative mode\n",
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index 20e71f4..00b3fc9 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#include "e1000.h"
diff --git a/drivers/net/ethernet/intel/e1000e/phy.h b/drivers/net/ethernet/intel/e1000e/phy.h
index f4f71b9..3841bcc 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.h
+++ b/drivers/net/ethernet/intel/e1000e/phy.h
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#ifndef _E1000E_PHY_H_
#define _E1000E_PHY_H_
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 065f8c8..fb1a914 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
/* PTP 1588 Hardware Clock (PHC)
* Derived from PTP Hardware Clock driver for Intel 82576 and 82580 (igb)
@@ -47,6 +40,7 @@
ptp_clock_info);
struct e1000_hw *hw = &adapter->hw;
bool neg_adj = false;
+ unsigned long flags;
u64 adjustment;
u32 timinca, incvalue;
s32 ret_val;
@@ -64,6 +58,8 @@
if (ret_val)
return ret_val;
+ spin_lock_irqsave(&adapter->systim_lock, flags);
+
incvalue = timinca & E1000_TIMINCA_INCVALUE_MASK;
adjustment = incvalue;
@@ -77,6 +73,8 @@
ew32(TIMINCA, timinca);
+ spin_unlock_irqrestore(&adapter->systim_lock, flags);
+
return 0;
}
@@ -191,6 +189,7 @@
.n_alarm = 0,
.n_ext_ts = 0,
.n_per_out = 0,
+ .n_pins = 0,
.pps = 0,
.adjfreq = e1000e_phc_adjfreq,
.adjtime = e1000e_phc_adjtime,
diff --git a/drivers/net/ethernet/intel/e1000e/regs.h b/drivers/net/ethernet/intel/e1000e/regs.h
index a7e6a3e..ea235bb 100644
--- a/drivers/net/ethernet/intel/e1000e/regs.h
+++ b/drivers/net/ethernet/intel/e1000e/regs.h
@@ -1,30 +1,23 @@
-/*******************************************************************************
-
- Intel PRO/1000 Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
-
- This program is free software; you can redistribute it and/or modify it
- under the terms and conditions of the GNU General Public License,
- version 2, as published by the Free Software Foundation.
-
- This program is distributed in the hope it will be useful, but WITHOUT
- ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- more details.
-
- You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
- The full GNU General Public License is included in this distribution in
- the file called "COPYING".
-
- Contact Information:
- Linux NICS <linux.nics@intel.com>
- e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
- Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel PRO/1000 Linux driver
+ * Copyright(c) 1999 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * Linux NICS <linux.nics@intel.com>
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
#ifndef _E1000E_REGS_H_
#define _E1000E_REGS_H_
@@ -39,6 +32,7 @@
#define E1000_SCTL 0x00024 /* SerDes Control - RW */
#define E1000_FCAL 0x00028 /* Flow Control Address Low - RW */
#define E1000_FCAH 0x0002C /* Flow Control Address High -RW */
+#define E1000_FEXT 0x0002C /* Future Extended - RW */
#define E1000_FEXTNVM 0x00028 /* Future Extended NVM - RW */
#define E1000_FEXTNVM3 0x0003C /* Future Extended NVM 3 - RW */
#define E1000_FEXTNVM4 0x00024 /* Future Extended NVM 4 - RW */
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 72dae4d..beb7b43 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -86,12 +86,12 @@
#define I40E_NVM_VERSION_LO_SHIFT 0
#define I40E_NVM_VERSION_LO_MASK (0xff << I40E_NVM_VERSION_LO_SHIFT)
-#define I40E_NVM_VERSION_HI_SHIFT 8
-#define I40E_NVM_VERSION_HI_MASK (0xff << I40E_NVM_VERSION_HI_SHIFT)
+#define I40E_NVM_VERSION_HI_SHIFT 12
+#define I40E_NVM_VERSION_HI_MASK (0xf << I40E_NVM_VERSION_HI_SHIFT)
/* The values in here are decimal coded as hex as is the case in the NVM map*/
#define I40E_CURRENT_NVM_VERSION_HI 0x2
-#define I40E_CURRENT_NVM_VERSION_LO 0x30
+#define I40E_CURRENT_NVM_VERSION_LO 0x40
/* magic for getting defines into strings */
#define STRINGIFY(foo) #foo
@@ -136,6 +136,7 @@
__I40E_EMP_RESET_REQUESTED,
__I40E_FILTER_OVERFLOW_PROMISC,
__I40E_SUSPENDED,
+ __I40E_BAD_EEPROM,
};
enum i40e_interrupt_policy {
@@ -152,8 +153,21 @@
};
#define I40E_DEFAULT_ATR_SAMPLE_RATE 20
-#define I40E_FDIR_MAX_RAW_PACKET_LOOKUP 512
-struct i40e_fdir_data {
+#define I40E_FDIR_MAX_RAW_PACKET_SIZE 512
+#define I40E_FDIR_BUFFER_FULL_MARGIN 10
+#define I40E_FDIR_BUFFER_HEAD_ROOM 200
+
+struct i40e_fdir_filter {
+ struct hlist_node fdir_node;
+ /* filter ipnut set */
+ u8 flow_type;
+ u8 ip4_proto;
+ __be32 dst_ip[4];
+ __be32 src_ip[4];
+ __be16 src_port;
+ __be16 dst_port;
+ __be32 sctp_v_tag;
+ /* filter control */
u16 q_index;
u8 flex_off;
u8 pctype;
@@ -162,7 +176,6 @@
u8 fd_status;
u16 cnt_index;
u32 fd_id;
- u8 *raw_packet;
};
#define I40E_ETH_P_LLDP 0x88cc
@@ -196,7 +209,7 @@
bool fc_autoneg_status;
u16 eeprom_version;
- u16 num_vmdq_vsis; /* num vmdq pools this pf has set up */
+ u16 num_vmdq_vsis; /* num vmdq vsis this pf has set up */
u16 num_vmdq_qps; /* num queue pairs per vmdq pool */
u16 num_vmdq_msix; /* num queue vectors per vmdq pool */
u16 num_req_vfs; /* num vfs requested for this vf */
@@ -210,6 +223,9 @@
u8 atr_sample_rate;
bool wol_en;
+ struct hlist_head fdir_filter_list;
+ u16 fdir_pf_active_filters;
+
#ifdef CONFIG_I40E_VXLAN
__be16 vxlan_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS];
u16 pending_vxlan_bitmap;
@@ -251,6 +267,9 @@
#define I40E_FLAG_VXLAN_FILTER_SYNC (u64)(1 << 27)
#endif
+ /* tracks features that get auto disabled by errors */
+ u64 auto_disable_flags;
+
bool stat_offsets_loaded;
struct i40e_hw_port_stats stats;
struct i40e_hw_port_stats stats_offsets;
@@ -477,10 +496,10 @@
"f%d.%d a%d.%d n%02x.%02x e%08x",
hw->aq.fw_maj_ver, hw->aq.fw_min_ver,
hw->aq.api_maj_ver, hw->aq.api_min_ver,
- (hw->nvm.version & I40E_NVM_VERSION_HI_MASK)
- >> I40E_NVM_VERSION_HI_SHIFT,
- (hw->nvm.version & I40E_NVM_VERSION_LO_MASK)
- >> I40E_NVM_VERSION_LO_SHIFT,
+ (hw->nvm.version & I40E_NVM_VERSION_HI_MASK) >>
+ I40E_NVM_VERSION_HI_SHIFT,
+ (hw->nvm.version & I40E_NVM_VERSION_LO_MASK) >>
+ I40E_NVM_VERSION_LO_SHIFT,
hw->nvm.eetrack);
return buf;
@@ -534,9 +553,13 @@
int i40e_fetch_switch_configuration(struct i40e_pf *pf,
bool printconfig);
-int i40e_program_fdir_filter(struct i40e_fdir_data *fdir_data,
+int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, u8 *raw_packet,
struct i40e_pf *pf, bool add);
-
+int i40e_add_del_fdir(struct i40e_vsi *vsi,
+ struct i40e_fdir_filter *input, bool add);
+void i40e_fdir_check_and_reenable(struct i40e_pf *pf);
+int i40e_get_current_fd_count(struct i40e_pf *pf);
+bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features);
void i40e_set_ethtool_ops(struct net_device *netdev);
struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
u8 *macaddr, s16 vlan,
@@ -575,6 +598,7 @@
void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf);
void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf);
int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
+int i40e_vsi_open(struct i40e_vsi *vsi);
void i40e_vlan_stripping_disable(struct i40e_vsi *vsi);
int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid);
int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index a50e6b3..ed3902b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -647,9 +647,8 @@
desc_cb = *desc;
cb_func(hw, &desc_cb);
}
- memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
- memset((void *)details, 0,
- sizeof(struct i40e_asq_cmd_details));
+ memset(desc, 0, sizeof(*desc));
+ memset(details, 0, sizeof(*details));
ntc++;
if (ntc == asq->count)
ntc = 0;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index e7f38b5..bb948dd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -162,6 +162,372 @@
return status;
}
+/* The i40e_ptype_lookup table is used to convert from the 8-bit ptype in the
+ * hardware to a bit-field that can be used by SW to more easily determine the
+ * packet type.
+ *
+ * Macros are used to shorten the table lines and make this table human
+ * readable.
+ *
+ * We store the PTYPE in the top byte of the bit field - this is just so that
+ * we can check that the table doesn't have a row missing, as the index into
+ * the table should be the PTYPE.
+ *
+ * Typical work flow:
+ *
+ * IF NOT i40e_ptype_lookup[ptype].known
+ * THEN
+ * Packet is unknown
+ * ELSE IF i40e_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP
+ * Use the rest of the fields to look at the tunnels, inner protocols, etc
+ * ELSE
+ * Use the enum i40e_rx_l2_ptype to decode the packet type
+ * ENDIF
+ */
+
+/* macro to make the table lines short */
+#define I40E_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
+ { PTYPE, \
+ 1, \
+ I40E_RX_PTYPE_OUTER_##OUTER_IP, \
+ I40E_RX_PTYPE_OUTER_##OUTER_IP_VER, \
+ I40E_RX_PTYPE_##OUTER_FRAG, \
+ I40E_RX_PTYPE_TUNNEL_##T, \
+ I40E_RX_PTYPE_TUNNEL_END_##TE, \
+ I40E_RX_PTYPE_##TEF, \
+ I40E_RX_PTYPE_INNER_PROT_##I, \
+ I40E_RX_PTYPE_PAYLOAD_LAYER_##PL }
+
+#define I40E_PTT_UNUSED_ENTRY(PTYPE) \
+ { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 }
+
+/* shorter macros makes the table fit but are terse */
+#define I40E_RX_PTYPE_NOF I40E_RX_PTYPE_NOT_FRAG
+#define I40E_RX_PTYPE_FRG I40E_RX_PTYPE_FRAG
+#define I40E_RX_PTYPE_INNER_PROT_TS I40E_RX_PTYPE_INNER_PROT_TIMESYNC
+
+/* Lookup table mapping the HW PTYPE to the bit field for decoding */
+struct i40e_rx_ptype_decoded i40e_ptype_lookup[] = {
+ /* L2 Packet types */
+ I40E_PTT_UNUSED_ENTRY(0),
+ I40E_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ I40E_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2),
+ I40E_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ I40E_PTT_UNUSED_ENTRY(4),
+ I40E_PTT_UNUSED_ENTRY(5),
+ I40E_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ I40E_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ I40E_PTT_UNUSED_ENTRY(8),
+ I40E_PTT_UNUSED_ENTRY(9),
+ I40E_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ I40E_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
+ I40E_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+
+ /* Non Tunneled IPv4 */
+ I40E_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(25),
+ I40E_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4),
+ I40E_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),
+ I40E_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),
+
+ /* IPv4 --> IPv4 */
+ I40E_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(32),
+ I40E_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv4 --> IPv6 */
+ I40E_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(39),
+ I40E_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT */
+ I40E_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
+
+ /* IPv4 --> GRE/NAT --> IPv4 */
+ I40E_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(47),
+ I40E_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT --> IPv6 */
+ I40E_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(54),
+ I40E_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT --> MAC */
+ I40E_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
+
+ /* IPv4 --> GRE/NAT --> MAC --> IPv4 */
+ I40E_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(62),
+ I40E_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT -> MAC --> IPv6 */
+ I40E_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(69),
+ I40E_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT --> MAC/VLAN */
+ I40E_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
+
+ /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */
+ I40E_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(77),
+ I40E_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */
+ I40E_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(84),
+ I40E_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+
+ /* Non Tunneled IPv6 */
+ I40E_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3),
+ I40E_PTT_UNUSED_ENTRY(91),
+ I40E_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4),
+ I40E_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),
+ I40E_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),
+
+ /* IPv6 --> IPv4 */
+ I40E_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(98),
+ I40E_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv6 --> IPv6 */
+ I40E_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(105),
+ I40E_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT */
+ I40E_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
+
+ /* IPv6 --> GRE/NAT -> IPv4 */
+ I40E_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(113),
+ I40E_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> IPv6 */
+ I40E_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(120),
+ I40E_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> MAC */
+ I40E_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
+
+ /* IPv6 --> GRE/NAT -> MAC -> IPv4 */
+ I40E_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(128),
+ I40E_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> MAC -> IPv6 */
+ I40E_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(135),
+ I40E_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> MAC/VLAN */
+ I40E_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
+
+ /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */
+ I40E_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(143),
+ I40E_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */
+ I40E_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(150),
+ I40E_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+
+ /* unused entries */
+ I40E_PTT_UNUSED_ENTRY(154),
+ I40E_PTT_UNUSED_ENTRY(155),
+ I40E_PTT_UNUSED_ENTRY(156),
+ I40E_PTT_UNUSED_ENTRY(157),
+ I40E_PTT_UNUSED_ENTRY(158),
+ I40E_PTT_UNUSED_ENTRY(159),
+
+ I40E_PTT_UNUSED_ENTRY(160),
+ I40E_PTT_UNUSED_ENTRY(161),
+ I40E_PTT_UNUSED_ENTRY(162),
+ I40E_PTT_UNUSED_ENTRY(163),
+ I40E_PTT_UNUSED_ENTRY(164),
+ I40E_PTT_UNUSED_ENTRY(165),
+ I40E_PTT_UNUSED_ENTRY(166),
+ I40E_PTT_UNUSED_ENTRY(167),
+ I40E_PTT_UNUSED_ENTRY(168),
+ I40E_PTT_UNUSED_ENTRY(169),
+
+ I40E_PTT_UNUSED_ENTRY(170),
+ I40E_PTT_UNUSED_ENTRY(171),
+ I40E_PTT_UNUSED_ENTRY(172),
+ I40E_PTT_UNUSED_ENTRY(173),
+ I40E_PTT_UNUSED_ENTRY(174),
+ I40E_PTT_UNUSED_ENTRY(175),
+ I40E_PTT_UNUSED_ENTRY(176),
+ I40E_PTT_UNUSED_ENTRY(177),
+ I40E_PTT_UNUSED_ENTRY(178),
+ I40E_PTT_UNUSED_ENTRY(179),
+
+ I40E_PTT_UNUSED_ENTRY(180),
+ I40E_PTT_UNUSED_ENTRY(181),
+ I40E_PTT_UNUSED_ENTRY(182),
+ I40E_PTT_UNUSED_ENTRY(183),
+ I40E_PTT_UNUSED_ENTRY(184),
+ I40E_PTT_UNUSED_ENTRY(185),
+ I40E_PTT_UNUSED_ENTRY(186),
+ I40E_PTT_UNUSED_ENTRY(187),
+ I40E_PTT_UNUSED_ENTRY(188),
+ I40E_PTT_UNUSED_ENTRY(189),
+
+ I40E_PTT_UNUSED_ENTRY(190),
+ I40E_PTT_UNUSED_ENTRY(191),
+ I40E_PTT_UNUSED_ENTRY(192),
+ I40E_PTT_UNUSED_ENTRY(193),
+ I40E_PTT_UNUSED_ENTRY(194),
+ I40E_PTT_UNUSED_ENTRY(195),
+ I40E_PTT_UNUSED_ENTRY(196),
+ I40E_PTT_UNUSED_ENTRY(197),
+ I40E_PTT_UNUSED_ENTRY(198),
+ I40E_PTT_UNUSED_ENTRY(199),
+
+ I40E_PTT_UNUSED_ENTRY(200),
+ I40E_PTT_UNUSED_ENTRY(201),
+ I40E_PTT_UNUSED_ENTRY(202),
+ I40E_PTT_UNUSED_ENTRY(203),
+ I40E_PTT_UNUSED_ENTRY(204),
+ I40E_PTT_UNUSED_ENTRY(205),
+ I40E_PTT_UNUSED_ENTRY(206),
+ I40E_PTT_UNUSED_ENTRY(207),
+ I40E_PTT_UNUSED_ENTRY(208),
+ I40E_PTT_UNUSED_ENTRY(209),
+
+ I40E_PTT_UNUSED_ENTRY(210),
+ I40E_PTT_UNUSED_ENTRY(211),
+ I40E_PTT_UNUSED_ENTRY(212),
+ I40E_PTT_UNUSED_ENTRY(213),
+ I40E_PTT_UNUSED_ENTRY(214),
+ I40E_PTT_UNUSED_ENTRY(215),
+ I40E_PTT_UNUSED_ENTRY(216),
+ I40E_PTT_UNUSED_ENTRY(217),
+ I40E_PTT_UNUSED_ENTRY(218),
+ I40E_PTT_UNUSED_ENTRY(219),
+
+ I40E_PTT_UNUSED_ENTRY(220),
+ I40E_PTT_UNUSED_ENTRY(221),
+ I40E_PTT_UNUSED_ENTRY(222),
+ I40E_PTT_UNUSED_ENTRY(223),
+ I40E_PTT_UNUSED_ENTRY(224),
+ I40E_PTT_UNUSED_ENTRY(225),
+ I40E_PTT_UNUSED_ENTRY(226),
+ I40E_PTT_UNUSED_ENTRY(227),
+ I40E_PTT_UNUSED_ENTRY(228),
+ I40E_PTT_UNUSED_ENTRY(229),
+
+ I40E_PTT_UNUSED_ENTRY(230),
+ I40E_PTT_UNUSED_ENTRY(231),
+ I40E_PTT_UNUSED_ENTRY(232),
+ I40E_PTT_UNUSED_ENTRY(233),
+ I40E_PTT_UNUSED_ENTRY(234),
+ I40E_PTT_UNUSED_ENTRY(235),
+ I40E_PTT_UNUSED_ENTRY(236),
+ I40E_PTT_UNUSED_ENTRY(237),
+ I40E_PTT_UNUSED_ENTRY(238),
+ I40E_PTT_UNUSED_ENTRY(239),
+
+ I40E_PTT_UNUSED_ENTRY(240),
+ I40E_PTT_UNUSED_ENTRY(241),
+ I40E_PTT_UNUSED_ENTRY(242),
+ I40E_PTT_UNUSED_ENTRY(243),
+ I40E_PTT_UNUSED_ENTRY(244),
+ I40E_PTT_UNUSED_ENTRY(245),
+ I40E_PTT_UNUSED_ENTRY(246),
+ I40E_PTT_UNUSED_ENTRY(247),
+ I40E_PTT_UNUSED_ENTRY(248),
+ I40E_PTT_UNUSED_ENTRY(249),
+
+ I40E_PTT_UNUSED_ENTRY(250),
+ I40E_PTT_UNUSED_ENTRY(251),
+ I40E_PTT_UNUSED_ENTRY(252),
+ I40E_PTT_UNUSED_ENTRY(253),
+ I40E_PTT_UNUSED_ENTRY(254),
+ I40E_PTT_UNUSED_ENTRY(255)
+};
+
+
/**
* i40e_init_shared_code - Initialize the shared code
* @hw: pointer to hardware structure
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 5073014..036570d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -332,6 +332,7 @@
u16 type;
u16 length;
u16 typelength;
+ u16 offset = 0;
if (!lldpmib || !dcbcfg)
return I40E_ERR_PARAM;
@@ -339,15 +340,17 @@
/* set to the start of LLDPDU */
lldpmib += ETH_HLEN;
tlv = (struct i40e_lldp_org_tlv *)lldpmib;
- while (tlv) {
+ while (1) {
typelength = ntohs(tlv->typelength);
type = (u16)((typelength & I40E_LLDP_TLV_TYPE_MASK) >>
I40E_LLDP_TLV_TYPE_SHIFT);
length = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >>
I40E_LLDP_TLV_LEN_SHIFT);
+ offset += sizeof(typelength) + length;
- if (type == I40E_TLV_TYPE_END)
- break;/* END TLV break out */
+ /* END TLV or beyond LLDPDU size */
+ if ((type == I40E_TLV_TYPE_END) || (offset > I40E_LLDPDU_SIZE))
+ break;
switch (type) {
case I40E_TLV_TYPE_ORG:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index da22c3f..3c37386 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -1011,10 +1011,12 @@
**/
static void i40e_dbg_cmd_fd_ctrl(struct i40e_pf *pf, u64 flag, bool enable)
{
- if (enable)
+ if (enable) {
pf->flags |= flag;
- else
+ } else {
pf->flags &= ~flag;
+ pf->auto_disable_flags |= flag;
+ }
dev_info(&pf->pdev->dev, "requesting a pf reset\n");
i40e_do_reset_safe(pf, (1 << __I40E_PF_RESET_REQUESTED));
}
@@ -1467,19 +1469,19 @@
pf->msg_enable);
}
} else if (strncmp(cmd_buf, "pfr", 3) == 0) {
- dev_info(&pf->pdev->dev, "forcing PFR\n");
+ dev_info(&pf->pdev->dev, "debugfs: forcing PFR\n");
i40e_do_reset_safe(pf, (1 << __I40E_PF_RESET_REQUESTED));
} else if (strncmp(cmd_buf, "corer", 5) == 0) {
- dev_info(&pf->pdev->dev, "forcing CoreR\n");
+ dev_info(&pf->pdev->dev, "debugfs: forcing CoreR\n");
i40e_do_reset_safe(pf, (1 << __I40E_CORE_RESET_REQUESTED));
} else if (strncmp(cmd_buf, "globr", 5) == 0) {
- dev_info(&pf->pdev->dev, "forcing GlobR\n");
+ dev_info(&pf->pdev->dev, "debugfs: forcing GlobR\n");
i40e_do_reset_safe(pf, (1 << __I40E_GLOBAL_RESET_REQUESTED));
} else if (strncmp(cmd_buf, "empr", 4) == 0) {
- dev_info(&pf->pdev->dev, "forcing EMPR\n");
+ dev_info(&pf->pdev->dev, "debugfs: forcing EMPR\n");
i40e_do_reset_safe(pf, (1 << __I40E_EMP_RESET_REQUESTED));
} else if (strncmp(cmd_buf, "read", 4) == 0) {
@@ -1663,28 +1665,36 @@
desc = NULL;
} else if ((strncmp(cmd_buf, "add fd_filter", 13) == 0) ||
(strncmp(cmd_buf, "rem fd_filter", 13) == 0)) {
- struct i40e_fdir_data fd_data;
+ struct i40e_fdir_filter fd_data;
u16 packet_len, i, j = 0;
char *asc_packet;
+ u8 *raw_packet;
bool add = false;
int ret;
- asc_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_LOOKUP,
+ if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
+ goto command_write_done;
+
+ if (strncmp(cmd_buf, "add", 3) == 0)
+ add = true;
+
+ if (add && (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED))
+ goto command_write_done;
+
+ asc_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_SIZE,
GFP_KERNEL);
if (!asc_packet)
goto command_write_done;
- fd_data.raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_LOOKUP,
- GFP_KERNEL);
+ raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_SIZE,
+ GFP_KERNEL);
- if (!fd_data.raw_packet) {
+ if (!raw_packet) {
kfree(asc_packet);
asc_packet = NULL;
goto command_write_done;
}
- if (strncmp(cmd_buf, "add", 3) == 0)
- add = true;
cnt = sscanf(&cmd_buf[13],
"%hx %2hhx %2hhx %hx %2hhx %2hhx %hx %x %hd %511s",
&fd_data.q_index,
@@ -1698,36 +1708,36 @@
cnt);
kfree(asc_packet);
asc_packet = NULL;
- kfree(fd_data.raw_packet);
+ kfree(raw_packet);
goto command_write_done;
}
/* fix packet length if user entered 0 */
if (packet_len == 0)
- packet_len = I40E_FDIR_MAX_RAW_PACKET_LOOKUP;
+ packet_len = I40E_FDIR_MAX_RAW_PACKET_SIZE;
/* make sure to check the max as well */
packet_len = min_t(u16,
- packet_len, I40E_FDIR_MAX_RAW_PACKET_LOOKUP);
+ packet_len, I40E_FDIR_MAX_RAW_PACKET_SIZE);
for (i = 0; i < packet_len; i++) {
sscanf(&asc_packet[j], "%2hhx ",
- &fd_data.raw_packet[i]);
+ &raw_packet[i]);
j += 3;
}
dev_info(&pf->pdev->dev, "FD raw packet dump\n");
print_hex_dump(KERN_INFO, "FD raw packet: ",
DUMP_PREFIX_OFFSET, 16, 1,
- fd_data.raw_packet, packet_len, true);
- ret = i40e_program_fdir_filter(&fd_data, pf, add);
+ raw_packet, packet_len, true);
+ ret = i40e_program_fdir_filter(&fd_data, raw_packet, pf, add);
if (!ret) {
dev_info(&pf->pdev->dev, "Filter command send Status : Success\n");
} else {
dev_info(&pf->pdev->dev,
"Filter command send failed %d\n", ret);
}
- kfree(fd_data.raw_packet);
- fd_data.raw_packet = NULL;
+ kfree(raw_packet);
+ raw_packet = NULL;
kfree(asc_packet);
asc_packet = NULL;
} else if (strncmp(cmd_buf, "fd-atr off", 10) == 0) {
@@ -2077,9 +2087,13 @@
if (!vsi) {
dev_info(&pf->pdev->dev,
"tx_timeout: VSI %d not found\n", vsi_seid);
- goto netdev_ops_write_done;
- }
- if (rtnl_trylock()) {
+ } else if (!vsi->netdev) {
+ dev_info(&pf->pdev->dev, "tx_timeout: no netdev for VSI %d\n",
+ vsi_seid);
+ } else if (test_bit(__I40E_DOWN, &vsi->state)) {
+ dev_info(&pf->pdev->dev, "tx_timeout: VSI %d not UP\n",
+ vsi_seid);
+ } else if (rtnl_trylock()) {
vsi->netdev->netdev_ops->ndo_tx_timeout(vsi->netdev);
rtnl_unlock();
dev_info(&pf->pdev->dev, "tx_timeout called\n");
@@ -2098,9 +2112,10 @@
if (!vsi) {
dev_info(&pf->pdev->dev,
"change_mtu: VSI %d not found\n", vsi_seid);
- goto netdev_ops_write_done;
- }
- if (rtnl_trylock()) {
+ } else if (!vsi->netdev) {
+ dev_info(&pf->pdev->dev, "change_mtu: no netdev for VSI %d\n",
+ vsi_seid);
+ } else if (rtnl_trylock()) {
vsi->netdev->netdev_ops->ndo_change_mtu(vsi->netdev,
mtu);
rtnl_unlock();
@@ -2119,9 +2134,10 @@
if (!vsi) {
dev_info(&pf->pdev->dev,
"set_rx_mode: VSI %d not found\n", vsi_seid);
- goto netdev_ops_write_done;
- }
- if (rtnl_trylock()) {
+ } else if (!vsi->netdev) {
+ dev_info(&pf->pdev->dev, "set_rx_mode: no netdev for VSI %d\n",
+ vsi_seid);
+ } else if (rtnl_trylock()) {
vsi->netdev->netdev_ops->ndo_set_rx_mode(vsi->netdev);
rtnl_unlock();
dev_info(&pf->pdev->dev, "set_rx_mode called\n");
@@ -2139,11 +2155,14 @@
if (!vsi) {
dev_info(&pf->pdev->dev, "napi: VSI %d not found\n",
vsi_seid);
- goto netdev_ops_write_done;
+ } else if (!vsi->netdev) {
+ dev_info(&pf->pdev->dev, "napi: no netdev for VSI %d\n",
+ vsi_seid);
+ } else {
+ for (i = 0; i < vsi->num_q_vectors; i++)
+ napi_schedule(&vsi->q_vectors[i]->napi);
+ dev_info(&pf->pdev->dev, "napi called\n");
}
- for (i = 0; i < vsi->num_q_vectors; i++)
- napi_schedule(&vsi->q_vectors[i]->napi);
- dev_info(&pf->pdev->dev, "napi called\n");
} else {
dev_info(&pf->pdev->dev, "unknown command '%s'\n",
i40e_dbg_netdev_ops_buf);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index b1d7d8c..aa123f4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -62,6 +62,9 @@
I40E_NETDEV_STAT(rx_crc_errors),
};
+static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
+ struct ethtool_rxnfc *cmd);
+
/* These PF_STATs might look like duplicates of some NETDEV_STATs,
* but they are separate. This device supports Virtualization, and
* as such might have several netdevs supporting VMDq and FCoE going
@@ -84,6 +87,7 @@
I40E_PF_STAT("illegal_bytes", stats.illegal_bytes),
I40E_PF_STAT("mac_local_faults", stats.mac_local_faults),
I40E_PF_STAT("mac_remote_faults", stats.mac_remote_faults),
+ I40E_PF_STAT("tx_timeout", tx_timeout_count),
I40E_PF_STAT("rx_length_errors", stats.rx_length_errors),
I40E_PF_STAT("link_xon_rx", stats.link_xon_rx),
I40E_PF_STAT("link_xoff_rx", stats.link_xoff_rx),
@@ -110,6 +114,11 @@
I40E_PF_STAT("VF_admin_queue_requests", vf_aq_requests),
I40E_PF_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts),
I40E_PF_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared),
+ /* LPI stats */
+ I40E_PF_STAT("tx_lpi_status", stats.tx_lpi_status),
+ I40E_PF_STAT("rx_lpi_status", stats.rx_lpi_status),
+ I40E_PF_STAT("tx_lpi_count", stats.tx_lpi_count),
+ I40E_PF_STAT("rx_lpi_count", stats.rx_lpi_count),
};
#define I40E_QUEUE_STATS_LEN(n) \
@@ -649,18 +658,18 @@
/* process Tx ring statistics */
do {
- start = u64_stats_fetch_begin_bh(&tx_ring->syncp);
+ start = u64_stats_fetch_begin_irq(&tx_ring->syncp);
data[i] = tx_ring->stats.packets;
data[i + 1] = tx_ring->stats.bytes;
- } while (u64_stats_fetch_retry_bh(&tx_ring->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&tx_ring->syncp, start));
/* Rx ring is the 2nd half of the queue pair */
rx_ring = &tx_ring[1];
do {
- start = u64_stats_fetch_begin_bh(&rx_ring->syncp);
+ start = u64_stats_fetch_begin_irq(&rx_ring->syncp);
data[i + 2] = rx_ring->stats.packets;
data[i + 3] = rx_ring->stats.bytes;
- } while (u64_stats_fetch_retry_bh(&rx_ring->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&rx_ring->syncp, start));
}
rcu_read_unlock();
if (vsi == pf->vsi[pf->lan_vsi]) {
@@ -1112,6 +1121,84 @@
}
/**
+ * i40e_get_ethtool_fdir_all - Populates the rule count of a command
+ * @pf: Pointer to the physical function struct
+ * @cmd: The command to get or set Rx flow classification rules
+ * @rule_locs: Array of used rule locations
+ *
+ * This function populates both the total and actual rule count of
+ * the ethtool flow classification command
+ *
+ * Returns 0 on success or -EMSGSIZE if entry not found
+ **/
+static int i40e_get_ethtool_fdir_all(struct i40e_pf *pf,
+ struct ethtool_rxnfc *cmd,
+ u32 *rule_locs)
+{
+ struct i40e_fdir_filter *rule;
+ struct hlist_node *node2;
+ int cnt = 0;
+
+ /* report total rule count */
+ cmd->data = pf->hw.fdir_shared_filter_count +
+ pf->fdir_pf_filter_count;
+
+ hlist_for_each_entry_safe(rule, node2,
+ &pf->fdir_filter_list, fdir_node) {
+ if (cnt == cmd->rule_cnt)
+ return -EMSGSIZE;
+
+ rule_locs[cnt] = rule->fd_id;
+ cnt++;
+ }
+
+ cmd->rule_cnt = cnt;
+
+ return 0;
+}
+
+/**
+ * i40e_get_ethtool_fdir_entry - Look up a filter based on Rx flow
+ * @pf: Pointer to the physical function struct
+ * @cmd: The command to get or set Rx flow classification rules
+ *
+ * This function looks up a filter based on the Rx flow classification
+ * command and fills the flow spec info for it if found
+ *
+ * Returns 0 on success or -EINVAL if filter not found
+ **/
+static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
+ struct ethtool_rxnfc *cmd)
+{
+ struct ethtool_rx_flow_spec *fsp =
+ (struct ethtool_rx_flow_spec *)&cmd->fs;
+ struct i40e_fdir_filter *rule = NULL;
+ struct hlist_node *node2;
+
+ /* report total rule count */
+ cmd->data = pf->hw.fdir_shared_filter_count +
+ pf->fdir_pf_filter_count;
+
+ hlist_for_each_entry_safe(rule, node2,
+ &pf->fdir_filter_list, fdir_node) {
+ if (fsp->location <= rule->fd_id)
+ break;
+ }
+
+ if (!rule || fsp->location != rule->fd_id)
+ return -EINVAL;
+
+ fsp->flow_type = rule->flow_type;
+ fsp->h_u.tcp_ip4_spec.psrc = rule->src_port;
+ fsp->h_u.tcp_ip4_spec.pdst = rule->dst_port;
+ fsp->h_u.tcp_ip4_spec.ip4src = rule->src_ip[0];
+ fsp->h_u.tcp_ip4_spec.ip4dst = rule->dst_ip[0];
+ fsp->ring_cookie = rule->q_index;
+
+ return 0;
+}
+
+/**
* i40e_get_rxnfc - command to get RX flow classification rules
* @netdev: network interface device structure
* @cmd: ethtool rxnfc command
@@ -1135,15 +1222,15 @@
ret = i40e_get_rss_hash_opts(pf, cmd);
break;
case ETHTOOL_GRXCLSRLCNT:
- cmd->rule_cnt = 10;
+ cmd->rule_cnt = pf->fdir_pf_active_filters;
ret = 0;
break;
case ETHTOOL_GRXCLSRULE:
- ret = 0;
+ ret = i40e_get_ethtool_fdir_entry(pf, cmd);
break;
case ETHTOOL_GRXCLSRLALL:
- cmd->data = 500;
- ret = 0;
+ ret = i40e_get_ethtool_fdir_all(pf, cmd, rule_locs);
+ break;
default:
break;
}
@@ -1274,289 +1361,182 @@
return 0;
}
-#define IP_HEADER_OFFSET 14
-#define I40E_UDPIP_DUMMY_PACKET_LEN 42
/**
- * i40e_add_del_fdir_udpv4 - Add/Remove UDPv4 Flow Director filters for
- * a specific flow spec
- * @vsi: pointer to the targeted VSI
- * @fd_data: the flow director data required from the FDir descriptor
- * @ethtool_rx_flow_spec: the flow spec
- * @add: true adds a filter, false removes it
+ * i40e_match_fdir_input_set - Match a new filter against an existing one
+ * @rule: The filter already added
+ * @input: The new filter to comapre against
*
- * Returns 0 if the filters were successfully added or removed
+ * Returns true if the two input set match
**/
-static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
- struct i40e_fdir_data *fd_data,
- struct ethtool_rx_flow_spec *fsp, bool add)
+static bool i40e_match_fdir_input_set(struct i40e_fdir_filter *rule,
+ struct i40e_fdir_filter *input)
{
+ if ((rule->dst_ip[0] != input->dst_ip[0]) ||
+ (rule->src_ip[0] != input->src_ip[0]) ||
+ (rule->dst_port != input->dst_port) ||
+ (rule->src_port != input->src_port))
+ return false;
+ return true;
+}
+
+/**
+ * i40e_update_ethtool_fdir_entry - Updates the fdir filter entry
+ * @vsi: Pointer to the targeted VSI
+ * @input: The filter to update or NULL to indicate deletion
+ * @sw_idx: Software index to the filter
+ * @cmd: The command to get or set Rx flow classification rules
+ *
+ * This function updates (or deletes) a Flow Director entry from
+ * the hlist of the corresponding PF
+ *
+ * Returns 0 on success
+ **/
+static int i40e_update_ethtool_fdir_entry(struct i40e_vsi *vsi,
+ struct i40e_fdir_filter *input,
+ u16 sw_idx,
+ struct ethtool_rxnfc *cmd)
+{
+ struct i40e_fdir_filter *rule, *parent;
struct i40e_pf *pf = vsi->back;
- struct udphdr *udp;
- struct iphdr *ip;
- bool err = false;
- int ret;
- int i;
- char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
- 0x45, 0, 0, 0x1c, 0, 0, 0x40, 0, 0x40, 0x11,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0};
+ struct hlist_node *node2;
+ int err = -EINVAL;
- memcpy(fd_data->raw_packet, packet, I40E_UDPIP_DUMMY_PACKET_LEN);
+ parent = NULL;
+ rule = NULL;
- ip = (struct iphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET);
- udp = (struct udphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET
- + sizeof(struct iphdr));
-
- ip->saddr = fsp->h_u.tcp_ip4_spec.ip4src;
- ip->daddr = fsp->h_u.tcp_ip4_spec.ip4dst;
- udp->source = fsp->h_u.tcp_ip4_spec.psrc;
- udp->dest = fsp->h_u.tcp_ip4_spec.pdst;
-
- for (i = I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP;
- i <= I40E_FILTER_PCTYPE_NONF_IPV4_UDP; i++) {
- fd_data->pctype = i;
- ret = i40e_program_fdir_filter(fd_data, pf, add);
-
- if (ret) {
- dev_info(&pf->pdev->dev,
- "Filter command send failed for PCTYPE %d (ret = %d)\n",
- fd_data->pctype, ret);
- err = true;
- } else {
- dev_info(&pf->pdev->dev,
- "Filter OK for PCTYPE %d (ret = %d)\n",
- fd_data->pctype, ret);
- }
+ hlist_for_each_entry_safe(rule, node2,
+ &pf->fdir_filter_list, fdir_node) {
+ /* hash found, or no matching entry */
+ if (rule->fd_id >= sw_idx)
+ break;
+ parent = rule;
}
- return err ? -EOPNOTSUPP : 0;
-}
-
-#define I40E_TCPIP_DUMMY_PACKET_LEN 54
-/**
- * i40e_add_del_fdir_tcpv4 - Add/Remove TCPv4 Flow Director filters for
- * a specific flow spec
- * @vsi: pointer to the targeted VSI
- * @fd_data: the flow director data required from the FDir descriptor
- * @ethtool_rx_flow_spec: the flow spec
- * @add: true adds a filter, false removes it
- *
- * Returns 0 if the filters were successfully added or removed
- **/
-static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
- struct i40e_fdir_data *fd_data,
- struct ethtool_rx_flow_spec *fsp, bool add)
-{
- struct i40e_pf *pf = vsi->back;
- struct tcphdr *tcp;
- struct iphdr *ip;
- bool err = false;
- int ret;
- /* Dummy packet */
- char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
- 0x45, 0, 0, 0x28, 0, 0, 0x40, 0, 0x40, 0x6,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0x80, 0x11, 0x0, 0x72, 0, 0, 0, 0};
-
- memcpy(fd_data->raw_packet, packet, I40E_TCPIP_DUMMY_PACKET_LEN);
-
- ip = (struct iphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET);
- tcp = (struct tcphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET
- + sizeof(struct iphdr));
-
- ip->daddr = fsp->h_u.tcp_ip4_spec.ip4dst;
- tcp->dest = fsp->h_u.tcp_ip4_spec.pdst;
- ip->saddr = fsp->h_u.tcp_ip4_spec.ip4src;
- tcp->source = fsp->h_u.tcp_ip4_spec.psrc;
-
- if (add) {
- if (pf->flags & I40E_FLAG_FD_ATR_ENABLED) {
- dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n");
- pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
- }
+ /* if there is an old rule occupying our place remove it */
+ if (rule && (rule->fd_id == sw_idx)) {
+ if (input && !i40e_match_fdir_input_set(rule, input))
+ err = i40e_add_del_fdir(vsi, rule, false);
+ else if (!input)
+ err = i40e_add_del_fdir(vsi, rule, false);
+ hlist_del(&rule->fdir_node);
+ kfree(rule);
+ pf->fdir_pf_active_filters--;
}
- fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN;
- ret = i40e_program_fdir_filter(fd_data, pf, add);
+ /* If no input this was a delete, err should be 0 if a rule was
+ * successfully found and removed from the list else -EINVAL
+ */
+ if (!input)
+ return err;
- if (ret) {
- dev_info(&pf->pdev->dev,
- "Filter command send failed for PCTYPE %d (ret = %d)\n",
- fd_data->pctype, ret);
- err = true;
- } else {
- dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d (ret = %d)\n",
- fd_data->pctype, ret);
- }
+ /* initialize node and set software index */
+ INIT_HLIST_NODE(&input->fdir_node);
- fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+ /* add filter to the list */
+ if (parent)
+ hlist_add_after(&parent->fdir_node, &input->fdir_node);
+ else
+ hlist_add_head(&input->fdir_node,
+ &pf->fdir_filter_list);
- ret = i40e_program_fdir_filter(fd_data, pf, add);
- if (ret) {
- dev_info(&pf->pdev->dev,
- "Filter command send failed for PCTYPE %d (ret = %d)\n",
- fd_data->pctype, ret);
- err = true;
- } else {
- dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d (ret = %d)\n",
- fd_data->pctype, ret);
- }
+ /* update counts */
+ pf->fdir_pf_active_filters++;
- return err ? -EOPNOTSUPP : 0;
+ return 0;
}
/**
- * i40e_add_del_fdir_sctpv4 - Add/Remove SCTPv4 Flow Director filters for
- * a specific flow spec
- * @vsi: pointer to the targeted VSI
- * @fd_data: the flow director data required from the FDir descriptor
- * @ethtool_rx_flow_spec: the flow spec
- * @add: true adds a filter, false removes it
+ * i40e_del_fdir_entry - Deletes a Flow Director filter entry
+ * @vsi: Pointer to the targeted VSI
+ * @cmd: The command to get or set Rx flow classification rules
*
- * Returns 0 if the filters were successfully added or removed
- **/
-static int i40e_add_del_fdir_sctpv4(struct i40e_vsi *vsi,
- struct i40e_fdir_data *fd_data,
- struct ethtool_rx_flow_spec *fsp, bool add)
-{
- return -EOPNOTSUPP;
-}
-
-#define I40E_IP_DUMMY_PACKET_LEN 34
-/**
- * i40e_add_del_fdir_ipv4 - Add/Remove IPv4 Flow Director filters for
- * a specific flow spec
- * @vsi: pointer to the targeted VSI
- * @fd_data: the flow director data required for the FDir descriptor
- * @fsp: the ethtool flow spec
- * @add: true adds a filter, false removes it
+ * The function removes a Flow Director filter entry from the
+ * hlist of the corresponding PF
*
- * Returns 0 if the filters were successfully added or removed
- **/
-static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
- struct i40e_fdir_data *fd_data,
- struct ethtool_rx_flow_spec *fsp, bool add)
+ * Returns 0 on success
+ */
+static int i40e_del_fdir_entry(struct i40e_vsi *vsi,
+ struct ethtool_rxnfc *cmd)
{
- struct i40e_pf *pf = vsi->back;
- struct iphdr *ip;
- bool err = false;
- int ret;
- int i;
- char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
- 0x45, 0, 0, 0x14, 0, 0, 0x40, 0, 0x40, 0x10,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
-
- memcpy(fd_data->raw_packet, packet, I40E_IP_DUMMY_PACKET_LEN);
- ip = (struct iphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET);
-
- ip->saddr = fsp->h_u.usr_ip4_spec.ip4src;
- ip->daddr = fsp->h_u.usr_ip4_spec.ip4dst;
- ip->protocol = fsp->h_u.usr_ip4_spec.proto;
-
- for (i = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
- i <= I40E_FILTER_PCTYPE_FRAG_IPV4; i++) {
- fd_data->pctype = i;
- ret = i40e_program_fdir_filter(fd_data, pf, add);
-
- if (ret) {
- dev_info(&pf->pdev->dev,
- "Filter command send failed for PCTYPE %d (ret = %d)\n",
- fd_data->pctype, ret);
- err = true;
- } else {
- dev_info(&pf->pdev->dev,
- "Filter OK for PCTYPE %d (ret = %d)\n",
- fd_data->pctype, ret);
- }
- }
-
- return err ? -EOPNOTSUPP : 0;
-}
-
-/**
- * i40e_add_del_fdir_ethtool - Add/Remove Flow Director filters for
- * a specific flow spec based on their protocol
- * @vsi: pointer to the targeted VSI
- * @cmd: command to get or set RX flow classification rules
- * @add: true adds a filter, false removes it
- *
- * Returns 0 if the filters were successfully added or removed
- **/
-static int i40e_add_del_fdir_ethtool(struct i40e_vsi *vsi,
- struct ethtool_rxnfc *cmd, bool add)
-{
- struct i40e_fdir_data fd_data;
- int ret = -EINVAL;
- struct i40e_pf *pf;
struct ethtool_rx_flow_spec *fsp =
(struct ethtool_rx_flow_spec *)&cmd->fs;
+ struct i40e_pf *pf = vsi->back;
+ int ret = 0;
+
+ ret = i40e_update_ethtool_fdir_entry(vsi, NULL, fsp->location, cmd);
+
+ i40e_fdir_check_and_reenable(pf);
+ return ret;
+}
+
+/**
+ * i40e_add_fdir_ethtool - Add/Remove Flow Director filters
+ * @vsi: pointer to the targeted VSI
+ * @cmd: command to get or set RX flow classification rules
+ *
+ * Add Flow Director filters for a specific flow spec based on their
+ * protocol. Returns 0 if the filters were successfully added.
+ **/
+static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
+ struct ethtool_rxnfc *cmd)
+{
+ struct ethtool_rx_flow_spec *fsp;
+ struct i40e_fdir_filter *input;
+ struct i40e_pf *pf;
+ int ret = -EINVAL;
if (!vsi)
return -EINVAL;
pf = vsi->back;
- if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) &&
- (fsp->ring_cookie >= vsi->num_queue_pairs))
+ if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
+ return -EOPNOTSUPP;
+
+ if (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)
+ return -ENOSPC;
+
+ fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+ if (fsp->location >= (pf->hw.func_caps.fd_filters_best_effort +
+ pf->hw.func_caps.fd_filters_guaranteed)) {
+ return -EINVAL;
+ }
+
+ if (fsp->ring_cookie >= vsi->num_queue_pairs)
return -EINVAL;
- /* Populate the Flow Director that we have at the moment
- * and allocate the raw packet buffer for the calling functions
- */
- fd_data.raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_LOOKUP,
- GFP_KERNEL);
+ input = kzalloc(sizeof(*input), GFP_KERNEL);
- if (!fd_data.raw_packet) {
- dev_info(&pf->pdev->dev, "Could not allocate memory\n");
+ if (!input)
return -ENOMEM;
- }
- fd_data.q_index = fsp->ring_cookie;
- fd_data.flex_off = 0;
- fd_data.pctype = 0;
- fd_data.dest_vsi = vsi->id;
- fd_data.dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX;
- fd_data.fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID;
- fd_data.cnt_index = 0;
- fd_data.fd_id = 0;
+ input->fd_id = fsp->location;
- switch (fsp->flow_type & ~FLOW_EXT) {
- case TCP_V4_FLOW:
- ret = i40e_add_del_fdir_tcpv4(vsi, &fd_data, fsp, add);
- break;
- case UDP_V4_FLOW:
- ret = i40e_add_del_fdir_udpv4(vsi, &fd_data, fsp, add);
- break;
- case SCTP_V4_FLOW:
- ret = i40e_add_del_fdir_sctpv4(vsi, &fd_data, fsp, add);
- break;
- case IPV4_FLOW:
- ret = i40e_add_del_fdir_ipv4(vsi, &fd_data, fsp, add);
- break;
- case IP_USER_FLOW:
- switch (fsp->h_u.usr_ip4_spec.proto) {
- case IPPROTO_TCP:
- ret = i40e_add_del_fdir_tcpv4(vsi, &fd_data, fsp, add);
- break;
- case IPPROTO_UDP:
- ret = i40e_add_del_fdir_udpv4(vsi, &fd_data, fsp, add);
- break;
- case IPPROTO_SCTP:
- ret = i40e_add_del_fdir_sctpv4(vsi, &fd_data, fsp, add);
- break;
- default:
- ret = i40e_add_del_fdir_ipv4(vsi, &fd_data, fsp, add);
- break;
- }
- break;
- default:
- dev_info(&pf->pdev->dev, "Could not specify spec type\n");
- ret = -EINVAL;
- }
+ if (fsp->ring_cookie == RX_CLS_FLOW_DISC)
+ input->dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET;
+ else
+ input->dest_ctl =
+ I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX;
- kfree(fd_data.raw_packet);
- fd_data.raw_packet = NULL;
+ input->q_index = fsp->ring_cookie;
+ input->flex_off = 0;
+ input->pctype = 0;
+ input->dest_vsi = vsi->id;
+ input->fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID;
+ input->cnt_index = 0;
+ input->flow_type = fsp->flow_type;
+ input->ip4_proto = fsp->h_u.usr_ip4_spec.proto;
+ input->src_port = fsp->h_u.tcp_ip4_spec.psrc;
+ input->dst_port = fsp->h_u.tcp_ip4_spec.pdst;
+ input->src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src;
+ input->dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst;
+
+ ret = i40e_add_del_fdir(vsi, input, true);
+ if (ret)
+ kfree(input);
+ else
+ i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL);
return ret;
}
@@ -1580,10 +1560,10 @@
ret = i40e_set_rss_hash_opt(pf, cmd);
break;
case ETHTOOL_SRXCLSRLINS:
- ret = i40e_add_del_fdir_ethtool(vsi, cmd, true);
+ ret = i40e_add_fdir_ethtool(vsi, cmd);
break;
case ETHTOOL_SRXCLSRLDEL:
- ret = i40e_add_del_fdir_ethtool(vsi, cmd, false);
+ ret = i40e_del_fdir_entry(vsi, cmd);
break;
default:
break;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index b901371..a1ec793 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -26,6 +26,7 @@
/* Local includes */
#include "i40e.h"
+#include "i40e_diag.h"
#ifdef CONFIG_I40E_VXLAN
#include <net/vxlan.h>
#endif
@@ -38,7 +39,7 @@
#define DRV_VERSION_MAJOR 0
#define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 30
+#define DRV_VERSION_BUILD 36
#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
__stringify(DRV_VERSION_MINOR) "." \
__stringify(DRV_VERSION_BUILD) DRV_KERN
@@ -305,6 +306,7 @@
break;
default:
netdev_err(netdev, "tx_timeout recovery unsuccessful\n");
+ set_bit(__I40E_DOWN, &vsi->state);
i40e_down(vsi);
break;
}
@@ -375,20 +377,20 @@
continue;
do {
- start = u64_stats_fetch_begin_bh(&tx_ring->syncp);
+ start = u64_stats_fetch_begin_irq(&tx_ring->syncp);
packets = tx_ring->stats.packets;
bytes = tx_ring->stats.bytes;
- } while (u64_stats_fetch_retry_bh(&tx_ring->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&tx_ring->syncp, start));
stats->tx_packets += packets;
stats->tx_bytes += bytes;
rx_ring = &tx_ring[1];
do {
- start = u64_stats_fetch_begin_bh(&rx_ring->syncp);
+ start = u64_stats_fetch_begin_irq(&rx_ring->syncp);
packets = rx_ring->stats.packets;
bytes = rx_ring->stats.bytes;
- } while (u64_stats_fetch_retry_bh(&rx_ring->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&rx_ring->syncp, start));
stats->rx_packets += packets;
stats->rx_bytes += bytes;
@@ -739,6 +741,7 @@
u32 rx_page, rx_buf;
u64 rx_p, rx_b;
u64 tx_p, tx_b;
+ u32 val;
int i;
u16 q;
@@ -769,10 +772,10 @@
p = ACCESS_ONCE(vsi->tx_rings[q]);
do {
- start = u64_stats_fetch_begin_bh(&p->syncp);
+ start = u64_stats_fetch_begin_irq(&p->syncp);
packets = p->stats.packets;
bytes = p->stats.bytes;
- } while (u64_stats_fetch_retry_bh(&p->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&p->syncp, start));
tx_b += bytes;
tx_p += packets;
tx_restart += p->tx_stats.restart_queue;
@@ -781,10 +784,10 @@
/* Rx queue is part of the same block as Tx queue */
p = &p[1];
do {
- start = u64_stats_fetch_begin_bh(&p->syncp);
+ start = u64_stats_fetch_begin_irq(&p->syncp);
packets = p->stats.packets;
bytes = p->stats.bytes;
- } while (u64_stats_fetch_retry_bh(&p->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&p->syncp, start));
rx_b += bytes;
rx_p += packets;
rx_buf += p->rx_stats.alloc_buff_failed;
@@ -971,6 +974,20 @@
i40e_stat_update32(hw, I40E_GLPRT_RJC(hw->port),
pf->stat_offsets_loaded,
&osd->rx_jabber, &nsd->rx_jabber);
+
+ val = rd32(hw, I40E_PRTPM_EEE_STAT);
+ nsd->tx_lpi_status =
+ (val & I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_MASK) >>
+ I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_SHIFT;
+ nsd->rx_lpi_status =
+ (val & I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_MASK) >>
+ I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_SHIFT;
+ i40e_stat_update32(hw, I40E_PRTPM_TLPIC,
+ pf->stat_offsets_loaded,
+ &osd->tx_lpi_count, &nsd->tx_lpi_count);
+ i40e_stat_update32(hw, I40E_PRTPM_RLPIC,
+ pf->stat_offsets_loaded,
+ &osd->rx_lpi_count, &nsd->rx_lpi_count);
}
pf->stat_offsets_loaded = true;
@@ -1964,11 +1981,14 @@
netdev_info(netdev, "adding %pM vid=%d\n", netdev->dev_addr, vid);
- /* If the network stack called us with vid = 0, we should
- * indicate to i40e_vsi_add_vlan() that we want to receive
- * any traffic (i.e. with any vlan tag, or untagged)
+ /* If the network stack called us with vid = 0 then
+ * it is asking to receive priority tagged packets with
+ * vlan id 0. Our HW receives them by default when configured
+ * to receive untagged packets so there is no need to add an
+ * extra filter for vlan 0 tagged packets.
*/
- ret = i40e_vsi_add_vlan(vsi, vid ? vid : I40E_VLAN_ANY);
+ if (vid)
+ ret = i40e_vsi_add_vlan(vsi, vid);
if (!ret && (vid < VLAN_N_VID))
set_bit(vid, vsi->active_vlans);
@@ -1981,7 +2001,7 @@
* @netdev: network interface to be adjusted
* @vid: vlan id to be removed
*
- * net_device_ops implementation for adding vlan ids
+ * net_device_ops implementation for removing vlan ids
**/
static int i40e_vlan_rx_kill_vid(struct net_device *netdev,
__always_unused __be16 proto, u16 vid)
@@ -2177,6 +2197,11 @@
tx_ctx.fd_ena = !!(vsi->back->flags & (I40E_FLAG_FD_SB_ENABLED |
I40E_FLAG_FD_ATR_ENABLED));
tx_ctx.timesync_ena = !!(vsi->back->flags & I40E_FLAG_PTP);
+ /* FDIR VSI tx ring can still use RS bit and writebacks */
+ if (vsi->type != I40E_VSI_FDIR)
+ tx_ctx.head_wb_ena = 1;
+ tx_ctx.head_wb_addr = ring->dma +
+ (ring->count * sizeof(struct i40e_tx_desc));
/* As part of VSI creation/update, FW allocates certain
* Tx arbitration queue sets for each TC enabled for
@@ -2420,6 +2445,28 @@
}
/**
+ * i40e_fdir_filter_restore - Restore the Sideband Flow Director filters
+ * @vsi: Pointer to the targeted VSI
+ *
+ * This function replays the hlist on the hw where all the SB Flow Director
+ * filters were saved.
+ **/
+static void i40e_fdir_filter_restore(struct i40e_vsi *vsi)
+{
+ struct i40e_fdir_filter *filter;
+ struct i40e_pf *pf = vsi->back;
+ struct hlist_node *node;
+
+ if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
+ return;
+
+ hlist_for_each_entry_safe(filter, node,
+ &pf->fdir_filter_list, fdir_node) {
+ i40e_add_del_fdir(vsi, filter, true);
+ }
+}
+
+/**
* i40e_vsi_configure - Set up the VSI for action
* @vsi: the VSI being configured
**/
@@ -2557,7 +2604,7 @@
/* FIRSTQ_INDX = 0, FIRSTQ_TYPE = 0 (rx) */
wr32(hw, I40E_PFINT_LNKLST0, 0);
- /* Associate the queue pair to the vector and enable the q int */
+ /* Associate the queue pair to the vector and enable the queue int */
val = I40E_QINT_RQCTL_CAUSE_ENA_MASK |
(I40E_RX_ITR << I40E_QINT_RQCTL_ITR_INDX_SHIFT) |
(I40E_QUEUE_TYPE_TX << I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT);
@@ -2831,12 +2878,14 @@
val = rd32(hw, I40E_GLGEN_RSTAT);
val = (val & I40E_GLGEN_RSTAT_RESET_TYPE_MASK)
>> I40E_GLGEN_RSTAT_RESET_TYPE_SHIFT;
- if (val == I40E_RESET_CORER)
+ if (val == I40E_RESET_CORER) {
pf->corer_count++;
- else if (val == I40E_RESET_GLOBR)
+ } else if (val == I40E_RESET_GLOBR) {
pf->globr_count++;
- else if (val == I40E_RESET_EMPR)
+ } else if (val == I40E_RESET_EMPR) {
pf->empr_count++;
+ set_bit(__I40E_EMP_RESET_REQUESTED, &pf->state);
+ }
}
if (icr0 & I40E_PFINT_ICR0_HMC_ERR_MASK) {
@@ -2866,8 +2915,7 @@
icr0_remaining);
if ((icr0_remaining & I40E_PFINT_ICR0_PE_CRITERR_MASK) ||
(icr0_remaining & I40E_PFINT_ICR0_PCI_EXCEPTION_MASK) ||
- (icr0_remaining & I40E_PFINT_ICR0_ECC_ERR_MASK) ||
- (icr0_remaining & I40E_PFINT_ICR0_MAL_DETECT_MASK)) {
+ (icr0_remaining & I40E_PFINT_ICR0_ECC_ERR_MASK)) {
dev_info(&pf->pdev->dev, "device will be reset\n");
set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
i40e_service_event_schedule(pf);
@@ -3107,13 +3155,13 @@
pf_q = vsi->base_queue;
for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
- j = 1000;
- do {
- usleep_range(1000, 2000);
+ for (j = 0; j < 50; j++) {
tx_reg = rd32(hw, I40E_QTX_ENA(pf_q));
- } while (j-- && ((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT)
- ^ (tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT)) & 1);
-
+ if (((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT) & 1) ==
+ ((tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT) & 1))
+ break;
+ usleep_range(1000, 2000);
+ }
/* Skip if the queue is already in the requested state */
if (enable && (tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
continue;
@@ -3123,8 +3171,7 @@
/* turn on/off the queue */
if (enable) {
wr32(hw, I40E_QTX_HEAD(pf_q), 0);
- tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK |
- I40E_QTX_ENA_QENA_STAT_MASK;
+ tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK;
} else {
tx_reg &= ~I40E_QTX_ENA_QENA_REQ_MASK;
}
@@ -3171,12 +3218,13 @@
pf_q = vsi->base_queue;
for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
- j = 1000;
- do {
- usleep_range(1000, 2000);
+ for (j = 0; j < 50; j++) {
rx_reg = rd32(hw, I40E_QRX_ENA(pf_q));
- } while (j-- && ((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT)
- ^ (rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT)) & 1);
+ if (((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT) & 1) ==
+ ((rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT) & 1))
+ break;
+ usleep_range(1000, 2000);
+ }
if (enable) {
/* is STAT set ? */
@@ -3190,11 +3238,9 @@
/* turn on/off the queue */
if (enable)
- rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK |
- I40E_QRX_ENA_QENA_STAT_MASK;
+ rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK;
else
- rx_reg &= ~(I40E_QRX_ENA_QENA_REQ_MASK |
- I40E_QRX_ENA_QENA_STAT_MASK);
+ rx_reg &= ~I40E_QRX_ENA_QENA_REQ_MASK;
wr32(hw, I40E_QRX_ENA(pf_q), rx_reg);
/* wait for the change to finish */
@@ -3732,8 +3778,8 @@
NULL);
if (aq_ret) {
dev_info(&vsi->back->pdev->dev,
- "%s: AQ command Config VSI BW allocation per TC failed = %d\n",
- __func__, vsi->back->hw.aq.asq_last_status);
+ "AQ command Config VSI BW allocation per TC failed = %d\n",
+ vsi->back->hw.aq.asq_last_status);
return -EINVAL;
}
@@ -4062,6 +4108,10 @@
} else if (vsi->netdev) {
netdev_info(vsi->netdev, "NIC Link is Down\n");
}
+
+ /* replay FDIR SB filters */
+ if (vsi->type == I40E_VSI_FDIR)
+ i40e_fdir_filter_restore(vsi);
i40e_service_event_schedule(pf);
return 0;
@@ -4208,15 +4258,40 @@
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
- char int_name[IFNAMSIZ];
int err;
- /* disallow open during test */
- if (test_bit(__I40E_TESTING, &pf->state))
+ /* disallow open during test or if eeprom is broken */
+ if (test_bit(__I40E_TESTING, &pf->state) ||
+ test_bit(__I40E_BAD_EEPROM, &pf->state))
return -EBUSY;
netif_carrier_off(netdev);
+ err = i40e_vsi_open(vsi);
+ if (err)
+ return err;
+
+#ifdef CONFIG_I40E_VXLAN
+ vxlan_get_rx_port(netdev);
+#endif
+
+ return 0;
+}
+
+/**
+ * i40e_vsi_open -
+ * @vsi: the VSI to open
+ *
+ * Finish initialization of the VSI.
+ *
+ * Returns 0 on success, negative value on failure
+ **/
+int i40e_vsi_open(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+ char int_name[IFNAMSIZ];
+ int err;
+
/* allocate descriptors */
err = i40e_vsi_setup_tx_resources(vsi);
if (err)
@@ -4229,18 +4304,22 @@
if (err)
goto err_setup_rx;
+ if (!vsi->netdev) {
+ err = EINVAL;
+ goto err_setup_rx;
+ }
snprintf(int_name, sizeof(int_name) - 1, "%s-%s",
- dev_driver_string(&pf->pdev->dev), netdev->name);
+ dev_driver_string(&pf->pdev->dev), vsi->netdev->name);
err = i40e_vsi_request_irq(vsi, int_name);
if (err)
goto err_setup_rx;
/* Notify the stack of the actual queue counts. */
- err = netif_set_real_num_tx_queues(netdev, vsi->num_queue_pairs);
+ err = netif_set_real_num_tx_queues(vsi->netdev, vsi->num_queue_pairs);
if (err)
goto err_set_queues;
- err = netif_set_real_num_rx_queues(netdev, vsi->num_queue_pairs);
+ err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_queue_pairs);
if (err)
goto err_set_queues;
@@ -4248,10 +4327,6 @@
if (err)
goto err_up_complete;
-#ifdef CONFIG_I40E_VXLAN
- vxlan_get_rx_port(netdev);
-#endif
-
return 0;
err_up_complete:
@@ -4269,6 +4344,26 @@
}
/**
+ * i40e_fdir_filter_exit - Cleans up the Flow Director accounting
+ * @pf: Pointer to pf
+ *
+ * This function destroys the hlist where all the Flow Director
+ * filters were saved.
+ **/
+static void i40e_fdir_filter_exit(struct i40e_pf *pf)
+{
+ struct i40e_fdir_filter *filter;
+ struct hlist_node *node2;
+
+ hlist_for_each_entry_safe(filter, node2,
+ &pf->fdir_filter_list, fdir_node) {
+ hlist_del(&filter->fdir_node);
+ kfree(filter);
+ }
+ pf->fdir_pf_active_filters = 0;
+}
+
+/**
* i40e_close - Disables a network interface
* @netdev: network interface device structure
*
@@ -4321,7 +4416,7 @@
* for the warning interrupt will deal with the shutdown
* and recovery of the switch setup.
*/
- dev_info(&pf->pdev->dev, "GlobalR requested\n");
+ dev_dbg(&pf->pdev->dev, "GlobalR requested\n");
val = rd32(&pf->hw, I40E_GLGEN_RTRIG);
val |= I40E_GLGEN_RTRIG_GLOBR_MASK;
wr32(&pf->hw, I40E_GLGEN_RTRIG, val);
@@ -4332,7 +4427,7 @@
*
* Same as Global Reset, except does *not* include the MAC/PHY
*/
- dev_info(&pf->pdev->dev, "CoreR requested\n");
+ dev_dbg(&pf->pdev->dev, "CoreR requested\n");
val = rd32(&pf->hw, I40E_GLGEN_RTRIG);
val |= I40E_GLGEN_RTRIG_CORER_MASK;
wr32(&pf->hw, I40E_GLGEN_RTRIG, val);
@@ -4366,7 +4461,7 @@
* the switch, since we need to do all the recovery as
* for the Core Reset.
*/
- dev_info(&pf->pdev->dev, "PFR requested\n");
+ dev_dbg(&pf->pdev->dev, "PFR requested\n");
i40e_handle_reset_warning(pf);
} else if (reset_flags & (1 << __I40E_REINIT_REQUESTED)) {
@@ -4415,18 +4510,18 @@
&old_cfg->etscfg.prioritytable,
sizeof(new_cfg->etscfg.prioritytable))) {
need_reconfig = true;
- dev_info(&pf->pdev->dev, "ETS UP2TC changed.\n");
+ dev_dbg(&pf->pdev->dev, "ETS UP2TC changed.\n");
}
if (memcmp(&new_cfg->etscfg.tcbwtable,
&old_cfg->etscfg.tcbwtable,
sizeof(new_cfg->etscfg.tcbwtable)))
- dev_info(&pf->pdev->dev, "ETS TC BW Table changed.\n");
+ dev_dbg(&pf->pdev->dev, "ETS TC BW Table changed.\n");
if (memcmp(&new_cfg->etscfg.tsatable,
&old_cfg->etscfg.tsatable,
sizeof(new_cfg->etscfg.tsatable)))
- dev_info(&pf->pdev->dev, "ETS TSA Table changed.\n");
+ dev_dbg(&pf->pdev->dev, "ETS TSA Table changed.\n");
}
/* Check if PFC configuration has changed */
@@ -4434,7 +4529,7 @@
&old_cfg->pfc,
sizeof(new_cfg->pfc))) {
need_reconfig = true;
- dev_info(&pf->pdev->dev, "PFC config change detected.\n");
+ dev_dbg(&pf->pdev->dev, "PFC config change detected.\n");
}
/* Check if APP Table has changed */
@@ -4442,7 +4537,7 @@
&old_cfg->app,
sizeof(new_cfg->app))) {
need_reconfig = true;
- dev_info(&pf->pdev->dev, "APP Table change detected.\n");
+ dev_dbg(&pf->pdev->dev, "APP Table change detected.\n");
}
return need_reconfig;
@@ -4492,7 +4587,7 @@
/* No change detected in DCBX configs */
if (!memcmp(&tmp_dcbx_cfg, dcbx_cfg, sizeof(tmp_dcbx_cfg))) {
- dev_info(&pf->pdev->dev, "No change detected in DCBX configuration.\n");
+ dev_dbg(&pf->pdev->dev, "No change detected in DCBX configuration.\n");
goto exit;
}
@@ -4550,8 +4645,8 @@
struct i40e_vf *vf;
u16 vf_id;
- dev_info(&pf->pdev->dev, "%s: Rx Queue Number = %d QTX_CTL=0x%08x\n",
- __func__, queue, qtx_ctl);
+ dev_dbg(&pf->pdev->dev, "overflow Rx Queue Number = %d QTX_CTL=0x%08x\n",
+ queue, qtx_ctl);
/* Queue belongs to VF, find the VF and issue VF reset */
if (((qtx_ctl & I40E_QTX_CTL_PFVF_Q_MASK)
@@ -4581,6 +4676,54 @@
}
/**
+ * i40e_get_current_fd_count - Get the count of FD filters programmed in the HW
+ * @pf: board private structure
+ **/
+int i40e_get_current_fd_count(struct i40e_pf *pf)
+{
+ int val, fcnt_prog;
+ val = rd32(&pf->hw, I40E_PFQF_FDSTAT);
+ fcnt_prog = (val & I40E_PFQF_FDSTAT_GUARANT_CNT_MASK) +
+ ((val & I40E_PFQF_FDSTAT_BEST_CNT_MASK) >>
+ I40E_PFQF_FDSTAT_BEST_CNT_SHIFT);
+ return fcnt_prog;
+}
+
+/**
+ * i40e_fdir_check_and_reenable - Function to reenabe FD ATR or SB if disabled
+ * @pf: board private structure
+ **/
+void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
+{
+ u32 fcnt_prog, fcnt_avail;
+
+ /* Check if, FD SB or ATR was auto disabled and if there is enough room
+ * to re-enable
+ */
+ if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
+ (pf->flags & I40E_FLAG_FD_SB_ENABLED))
+ return;
+ fcnt_prog = i40e_get_current_fd_count(pf);
+ fcnt_avail = pf->hw.fdir_shared_filter_count +
+ pf->fdir_pf_filter_count;
+ if (fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM)) {
+ if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
+ (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) {
+ pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED;
+ dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n");
+ }
+ }
+ /* Wait for some more space to be available to turn on ATR */
+ if (fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM * 2)) {
+ if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
+ (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) {
+ pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+ dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table now\n");
+ }
+ }
+}
+
+/**
* i40e_fdir_reinit_subtask - Worker thread to reinit FDIR filter table
* @pf: board private structure
**/
@@ -4589,11 +4732,14 @@
if (!(pf->flags & I40E_FLAG_FDIR_REQUIRES_REINIT))
return;
- pf->flags &= ~I40E_FLAG_FDIR_REQUIRES_REINIT;
-
/* if interface is down do nothing */
if (test_bit(__I40E_DOWN, &pf->state))
return;
+ i40e_fdir_check_and_reenable(pf);
+
+ if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
+ (pf->flags & I40E_FLAG_FD_SB_ENABLED))
+ pf->flags &= ~I40E_FLAG_FDIR_REQUIRES_REINIT;
}
/**
@@ -4903,7 +5049,7 @@
event.msg_size);
break;
case i40e_aqc_opc_lldp_update_mib:
- dev_info(&pf->pdev->dev, "ARQ: Update LLDP MIB event received\n");
+ dev_dbg(&pf->pdev->dev, "ARQ: Update LLDP MIB event received\n");
#ifdef CONFIG_I40E_DCB
rtnl_lock();
ret = i40e_handle_lldp_event(pf, &event);
@@ -4911,7 +5057,7 @@
#endif /* CONFIG_I40E_DCB */
break;
case i40e_aqc_opc_event_lan_overflow:
- dev_info(&pf->pdev->dev, "ARQ LAN queue overflow event received\n");
+ dev_dbg(&pf->pdev->dev, "ARQ LAN queue overflow event received\n");
i40e_handle_lan_overflow_event(pf, &event);
break;
case i40e_aqc_opc_send_msg_to_peer:
@@ -4936,6 +5082,31 @@
}
/**
+ * i40e_verify_eeprom - make sure eeprom is good to use
+ * @pf: board private structure
+ **/
+static void i40e_verify_eeprom(struct i40e_pf *pf)
+{
+ int err;
+
+ err = i40e_diag_eeprom_test(&pf->hw);
+ if (err) {
+ /* retry in case of garbage read */
+ err = i40e_diag_eeprom_test(&pf->hw);
+ if (err) {
+ dev_info(&pf->pdev->dev, "eeprom check failed (%d), Tx/Rx traffic disabled\n",
+ err);
+ set_bit(__I40E_BAD_EEPROM, &pf->state);
+ }
+ }
+
+ if (!err && test_bit(__I40E_BAD_EEPROM, &pf->state)) {
+ dev_info(&pf->pdev->dev, "eeprom check passed, Tx/Rx traffic enabled\n");
+ clear_bit(__I40E_BAD_EEPROM, &pf->state);
+ }
+}
+
+/**
* i40e_reconstitute_veb - rebuild the VEB and anything connected to it
* @veb: pointer to the VEB instance
*
@@ -5053,6 +5224,12 @@
/* increment MSI-X count because current FW skips one */
pf->hw.func_caps.num_msix_vectors++;
+ if (((pf->hw.aq.fw_maj_ver == 2) && (pf->hw.aq.fw_min_ver < 22)) ||
+ (pf->hw.aq.fw_maj_ver < 2)) {
+ pf->hw.func_caps.num_msix_vectors++;
+ pf->hw.func_caps.num_msix_vectors_vf++;
+ }
+
if (pf->hw.debug_mask & I40E_DEBUG_USER)
dev_info(&pf->pdev->dev,
"pf=%d, num_vfs=%d, msix_pf=%d, msix_vf=%d, fd_g=%d, fd_b=%d, pf_max_q=%d num_vsi=%d\n",
@@ -5132,9 +5309,9 @@
err = i40e_up_complete(vsi);
if (err)
goto err_up_complete;
+ clear_bit(__I40E_NEEDS_RESTART, &vsi->state);
}
- clear_bit(__I40E_NEEDS_RESTART, &vsi->state);
return;
err_up_complete:
@@ -5157,6 +5334,7 @@
{
int i;
+ i40e_fdir_filter_exit(pf);
for (i = 0; i < pf->hw.func_caps.num_vsis; i++) {
if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) {
i40e_vsi_release(pf->vsi[i]);
@@ -5181,7 +5359,7 @@
if (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state))
return 0;
- dev_info(&pf->pdev->dev, "Tearing down internal switch for reset\n");
+ dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n");
if (i40e_check_asq_alive(hw))
i40e_vc_notify_reset(pf);
@@ -5228,7 +5406,7 @@
if (test_bit(__I40E_DOWN, &pf->state))
goto end_core_reset;
- dev_info(&pf->pdev->dev, "Rebuilding internal switch\n");
+ dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n");
/* rebuild the basics for the AdminQ, HMC, and initial HW switch */
ret = i40e_init_adminq(&pf->hw);
@@ -5237,6 +5415,12 @@
goto end_core_reset;
}
+ /* re-verify the eeprom if we just had an EMP reset */
+ if (test_bit(__I40E_EMP_RESET_REQUESTED, &pf->state)) {
+ clear_bit(__I40E_EMP_RESET_REQUESTED, &pf->state);
+ i40e_verify_eeprom(pf);
+ }
+
ret = i40e_get_capabilities(pf);
if (ret) {
dev_info(&pf->pdev->dev, "i40e_get_capabilities failed, %d\n",
@@ -5278,7 +5462,7 @@
* try to recover minimal use by getting the basic PF VSI working.
*/
if (pf->vsi[pf->lan_vsi]->uplink_seid != pf->mac_seid) {
- dev_info(&pf->pdev->dev, "attempting to rebuild switch\n");
+ dev_dbg(&pf->pdev->dev, "attempting to rebuild switch\n");
/* find the one VEB connected to the MAC, and find orphans */
for (v = 0; v < I40E_MAX_VEB; v++) {
if (!pf->veb[v])
@@ -5331,6 +5515,11 @@
/* restart the VSIs that were rebuilt and running before the reset */
i40e_pf_unquiesce_all_vsi(pf);
+ if (pf->num_alloc_vfs) {
+ for (v = 0; v < pf->num_alloc_vfs; v++)
+ i40e_reset_vf(&pf->vf[v], true);
+ }
+
/* tell the firmware that we're starting */
dv.major_version = DRV_VERSION_MAJOR;
dv.minor_version = DRV_VERSION_MINOR;
@@ -5338,7 +5527,7 @@
dv.subbuild_version = 0;
i40e_aq_send_driver_version(&pf->hw, &dv, NULL);
- dev_info(&pf->pdev->dev, "PF reset done\n");
+ dev_info(&pf->pdev->dev, "reset complete\n");
end_core_reset:
clear_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state);
@@ -5387,7 +5576,7 @@
u8 queue = (reg & I40E_GL_MDET_TX_QUEUE_MASK)
>> I40E_GL_MDET_TX_QUEUE_SHIFT;
dev_info(&pf->pdev->dev,
- "Malicious Driver Detection TX event 0x%02x on q %d of function 0x%02x\n",
+ "Malicious Driver Detection event 0x%02x on TX queue %d of function 0x%02x\n",
event, queue, func);
wr32(hw, I40E_GL_MDET_TX, 0xffffffff);
mdd_detected = true;
@@ -5401,7 +5590,7 @@
u8 queue = (reg & I40E_GL_MDET_RX_QUEUE_MASK)
>> I40E_GL_MDET_RX_QUEUE_SHIFT;
dev_info(&pf->pdev->dev,
- "Malicious Driver Detection RX event 0x%02x on q %d of function 0x%02x\n",
+ "Malicious Driver Detection event 0x%02x on RX queue %d of function 0x%02x\n",
event, queue, func);
wr32(hw, I40E_GL_MDET_RX, 0xffffffff);
mdd_detected = true;
@@ -5850,37 +6039,16 @@
**/
static int i40e_reserve_msix_vectors(struct i40e_pf *pf, int vectors)
{
- int err = 0;
-
- pf->num_msix_entries = 0;
- while (vectors >= I40E_MIN_MSIX) {
- err = pci_enable_msix(pf->pdev, pf->msix_entries, vectors);
- if (err == 0) {
- /* good to go */
- pf->num_msix_entries = vectors;
- break;
- } else if (err < 0) {
- /* total failure */
- dev_info(&pf->pdev->dev,
- "MSI-X vector reservation failed: %d\n", err);
- vectors = 0;
- break;
- } else {
- /* err > 0 is the hint for retry */
- dev_info(&pf->pdev->dev,
- "MSI-X vectors wanted %d, retrying with %d\n",
- vectors, err);
- vectors = err;
- }
- }
-
- if (vectors > 0 && vectors < I40E_MIN_MSIX) {
+ vectors = pci_enable_msix_range(pf->pdev, pf->msix_entries,
+ I40E_MIN_MSIX, vectors);
+ if (vectors < 0) {
dev_info(&pf->pdev->dev,
- "Couldn't get enough vectors, only %d available\n",
- vectors);
+ "MSI-X vector reservation failed: %d\n", vectors);
vectors = 0;
}
+ pf->num_msix_entries = vectors;
+
return vectors;
}
@@ -5942,7 +6110,7 @@
} else if (vec == I40E_MIN_MSIX) {
/* Adjust for minimal MSIX use */
- dev_info(&pf->pdev->dev, "Features disabled, not enough MSIX vectors\n");
+ dev_info(&pf->pdev->dev, "Features disabled, not enough MSI-X vectors\n");
pf->flags &= ~I40E_FLAG_VMDQ_ENABLED;
pf->num_vmdq_vsis = 0;
pf->num_vmdq_qps = 0;
@@ -5978,13 +6146,13 @@
}
/**
- * i40e_alloc_q_vector - Allocate memory for a single interrupt vector
+ * i40e_vsi_alloc_q_vector - Allocate memory for a single interrupt vector
* @vsi: the VSI being configured
* @v_idx: index of the vector in the vsi struct
*
* We allocate one q_vector. If allocation fails we return -ENOMEM.
**/
-static int i40e_alloc_q_vector(struct i40e_vsi *vsi, int v_idx)
+static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx)
{
struct i40e_q_vector *q_vector;
@@ -6010,13 +6178,13 @@
}
/**
- * i40e_alloc_q_vectors - Allocate memory for interrupt vectors
+ * i40e_vsi_alloc_q_vectors - Allocate memory for interrupt vectors
* @vsi: the VSI being configured
*
* We allocate one q_vector per queue interrupt. If allocation fails we
* return -ENOMEM.
**/
-static int i40e_alloc_q_vectors(struct i40e_vsi *vsi)
+static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi)
{
struct i40e_pf *pf = vsi->back;
int v_idx, num_q_vectors;
@@ -6031,7 +6199,7 @@
return -EINVAL;
for (v_idx = 0; v_idx < num_q_vectors; v_idx++) {
- err = i40e_alloc_q_vector(vsi, v_idx);
+ err = i40e_vsi_alloc_q_vector(vsi, v_idx);
if (err)
goto err_out;
}
@@ -6071,7 +6239,7 @@
if (!(pf->flags & I40E_FLAG_MSIX_ENABLED) &&
(pf->flags & I40E_FLAG_MSI_ENABLED)) {
- dev_info(&pf->pdev->dev, "MSIX not available, trying MSI\n");
+ dev_info(&pf->pdev->dev, "MSI-X not available, trying MSI\n");
err = pci_enable_msi(pf->pdev);
if (err) {
dev_info(&pf->pdev->dev, "MSI init failed - %d\n", err);
@@ -6080,7 +6248,7 @@
}
if (!(pf->flags & (I40E_FLAG_MSIX_ENABLED | I40E_FLAG_MSI_ENABLED)))
- dev_info(&pf->pdev->dev, "MSIX and MSI not available, falling back to Legacy IRQ\n");
+ dev_info(&pf->pdev->dev, "MSI-X and MSI not available, falling back to Legacy IRQ\n");
/* track first vector for misc interrupts */
err = i40e_get_lump(pf, pf->irq_pile, 1, I40E_PILE_VALID_BIT-1);
@@ -6107,7 +6275,8 @@
i40e_intr, 0, pf->misc_int_name, pf);
if (err) {
dev_info(&pf->pdev->dev,
- "request_irq for msix_misc failed: %d\n", err);
+ "request_irq for %s failed: %d\n",
+ pf->misc_int_name, err);
return -EFAULT;
}
}
@@ -6258,15 +6427,11 @@
(pf->hw.func_caps.fd_filters_best_effort > 0)) {
pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
pf->atr_sample_rate = I40E_DEFAULT_ATR_SAMPLE_RATE;
- dev_info(&pf->pdev->dev,
- "Flow Director ATR mode Enabled\n");
if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) {
pf->flags |= I40E_FLAG_FD_SB_ENABLED;
- dev_info(&pf->pdev->dev,
- "Flow Director Side Band mode Enabled\n");
} else {
dev_info(&pf->pdev->dev,
- "Flow Director Side Band mode Disabled in MFP mode\n");
+ "Flow Director Sideband mode Disabled in MFP mode\n");
}
pf->fdir_pf_filter_count =
pf->hw.func_caps.fd_filters_guaranteed;
@@ -6287,9 +6452,6 @@
pf->num_req_vfs = min_t(int,
pf->hw.func_caps.num_vfs,
I40E_MAX_VF_COUNT);
- dev_info(&pf->pdev->dev,
- "Number of VFs being requested for PF[%d] = %d\n",
- pf->hw.pf_id, pf->num_req_vfs);
}
#endif /* CONFIG_PCI_IOV */
pf->eeprom_version = 0xDEAD;
@@ -6326,6 +6488,39 @@
}
/**
+ * i40e_set_ntuple - set the ntuple feature flag and take action
+ * @pf: board private structure to initialize
+ * @features: the feature set that the stack is suggesting
+ *
+ * returns a bool to indicate if reset needs to happen
+ **/
+bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
+{
+ bool need_reset = false;
+
+ /* Check if Flow Director n-tuple support was enabled or disabled. If
+ * the state changed, we need to reset.
+ */
+ if (features & NETIF_F_NTUPLE) {
+ /* Enable filters and mark for reset */
+ if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
+ need_reset = true;
+ pf->flags |= I40E_FLAG_FD_SB_ENABLED;
+ } else {
+ /* turn off filters, mark for reset and clear SW filter list */
+ if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
+ need_reset = true;
+ i40e_fdir_filter_exit(pf);
+ }
+ pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
+ /* if ATR was disabled it can be re-enabled. */
+ if (!(pf->flags & I40E_FLAG_FD_ATR_ENABLED))
+ pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
+ }
+ return need_reset;
+}
+
+/**
* i40e_set_features - set the netdev feature flags
* @netdev: ptr to the netdev being adjusted
* @features: the feature set that the stack is suggesting
@@ -6335,12 +6530,19 @@
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ bool need_reset;
if (features & NETIF_F_HW_VLAN_CTAG_RX)
i40e_vlan_stripping_enable(vsi);
else
i40e_vlan_stripping_disable(vsi);
+ need_reset = i40e_set_ntuple(pf, features);
+
+ if (need_reset)
+ i40e_do_reset(pf, (1 << __I40E_PF_RESET_REQUESTED));
+
return 0;
}
@@ -6464,6 +6666,7 @@
.ndo_set_vf_vlan = i40e_ndo_set_vf_port_vlan,
.ndo_set_vf_tx_rate = i40e_ndo_set_vf_bw,
.ndo_get_vf_config = i40e_ndo_get_vf_config,
+ .ndo_set_vf_link_state = i40e_ndo_set_vf_link_state,
#ifdef CONFIG_I40E_VXLAN
.ndo_add_vxlan_port = i40e_add_vxlan_port,
.ndo_del_vxlan_port = i40e_del_vxlan_port,
@@ -6495,10 +6698,9 @@
np = netdev_priv(netdev);
np->vsi = vsi;
- netdev->hw_enc_features = NETIF_F_IP_CSUM |
+ netdev->hw_enc_features |= NETIF_F_IP_CSUM |
NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_TSO |
- NETIF_F_SG;
+ NETIF_F_TSO;
netdev->features = NETIF_F_SG |
NETIF_F_IP_CSUM |
@@ -6512,6 +6714,7 @@
NETIF_F_TSO |
NETIF_F_TSO6 |
NETIF_F_RXCSUM |
+ NETIF_F_NTUPLE |
NETIF_F_RXHASH |
0;
@@ -6771,8 +6974,6 @@
if (vsi->netdev) {
/* results in a call to i40e_close() */
unregister_netdev(vsi->netdev);
- free_netdev(vsi->netdev);
- vsi->netdev = NULL;
}
} else {
if (!test_and_set_bit(__I40E_DOWN, &vsi->state))
@@ -6791,6 +6992,10 @@
i40e_vsi_delete(vsi);
i40e_vsi_free_q_vectors(vsi);
+ if (vsi->netdev) {
+ free_netdev(vsi->netdev);
+ vsi->netdev = NULL;
+ }
i40e_vsi_clear_rings(vsi);
i40e_vsi_clear(vsi);
@@ -6845,13 +7050,12 @@
}
if (vsi->base_vector) {
- dev_info(&pf->pdev->dev,
- "VSI %d has non-zero base vector %d\n",
+ dev_info(&pf->pdev->dev, "VSI %d has non-zero base vector %d\n",
vsi->seid, vsi->base_vector);
return -EEXIST;
}
- ret = i40e_alloc_q_vectors(vsi);
+ ret = i40e_vsi_alloc_q_vectors(vsi);
if (ret) {
dev_info(&pf->pdev->dev,
"failed to allocate %d q_vector for VSI %d, ret=%d\n",
@@ -6865,7 +7069,7 @@
vsi->num_q_vectors, vsi->idx);
if (vsi->base_vector < 0) {
dev_info(&pf->pdev->dev,
- "failed to get q tracking for VSI %d, err=%d\n",
+ "failed to get queue tracking for VSI %d, err=%d\n",
vsi->seid, vsi->base_vector);
i40e_vsi_free_q_vectors(vsi);
ret = -ENOENT;
@@ -7822,6 +8026,44 @@
return 0;
}
+#define INFO_STRING_LEN 255
+static void i40e_print_features(struct i40e_pf *pf)
+{
+ struct i40e_hw *hw = &pf->hw;
+ char *buf, *string;
+
+ string = kzalloc(INFO_STRING_LEN, GFP_KERNEL);
+ if (!string) {
+ dev_err(&pf->pdev->dev, "Features string allocation failed\n");
+ return;
+ }
+
+ buf = string;
+
+ buf += sprintf(string, "Features: PF-id[%d] ", hw->pf_id);
+#ifdef CONFIG_PCI_IOV
+ buf += sprintf(buf, "VFs: %d ", pf->num_req_vfs);
+#endif
+ buf += sprintf(buf, "VSIs: %d QP: %d ", pf->hw.func_caps.num_vsis,
+ pf->vsi[pf->lan_vsi]->num_queue_pairs);
+
+ if (pf->flags & I40E_FLAG_RSS_ENABLED)
+ buf += sprintf(buf, "RSS ");
+ buf += sprintf(buf, "FDir ");
+ if (pf->flags & I40E_FLAG_FD_ATR_ENABLED)
+ buf += sprintf(buf, "ATR ");
+ if (pf->flags & I40E_FLAG_FD_SB_ENABLED)
+ buf += sprintf(buf, "NTUPLE ");
+ if (pf->flags & I40E_FLAG_DCB_ENABLED)
+ buf += sprintf(buf, "DCB ");
+ if (pf->flags & I40E_FLAG_PTP)
+ buf += sprintf(buf, "PTP ");
+
+ BUG_ON(buf > (string + INFO_STRING_LEN));
+ dev_info(&pf->pdev->dev, "%s\n", string);
+ kfree(string);
+}
+
/**
* i40e_probe - Device initialization routine
* @pdev: PCI device information struct
@@ -7848,16 +8090,12 @@
return err;
/* set up for high or low dma */
- if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64))) {
- /* coherent mask for the same size will always succeed if
- * dma_set_mask does
- */
- dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
- } else if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) {
- dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
- } else {
- dev_err(&pdev->dev, "DMA configuration failed: %d\n", err);
- err = -EIO;
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+ if (err)
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+ if (err) {
+ dev_err(&pdev->dev,
+ "DMA configuration failed: 0x%x\n", err);
goto err_dma;
}
@@ -7946,13 +8184,6 @@
err = i40e_init_adminq(hw);
dev_info(&pdev->dev, "%s\n", i40e_fw_version_str(hw));
- if (((hw->nvm.version & I40E_NVM_VERSION_HI_MASK)
- >> I40E_NVM_VERSION_HI_SHIFT) != I40E_CURRENT_NVM_VERSION_HI) {
- dev_info(&pdev->dev,
- "warning: NVM version not supported, supported version: %02x.%02x\n",
- I40E_CURRENT_NVM_VERSION_HI,
- I40E_CURRENT_NVM_VERSION_LO);
- }
if (err) {
dev_info(&pdev->dev,
"init_adminq failed: %d expecting API %02x.%02x\n",
@@ -7961,6 +8192,8 @@
goto err_pf_reset;
}
+ i40e_verify_eeprom(pf);
+
i40e_clear_pxe_mode(hw);
err = i40e_get_capabilities(pf);
if (err)
@@ -8062,7 +8295,8 @@
/* prep for VF support */
if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
- (pf->flags & I40E_FLAG_MSIX_ENABLED)) {
+ (pf->flags & I40E_FLAG_MSIX_ENABLED) &&
+ !test_bit(__I40E_BAD_EEPROM, &pf->state)) {
u32 val;
/* disable link interrupts for VFs */
@@ -8070,6 +8304,16 @@
val &= ~I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_MASK;
wr32(hw, I40E_PFGEN_PORTMDIO_NUM, val);
i40e_flush(hw);
+
+ if (pci_num_vf(pdev)) {
+ dev_info(&pdev->dev,
+ "Active VFs found, allocating resources.\n");
+ err = i40e_alloc_vfs(pf, pci_num_vf(pdev));
+ if (err)
+ dev_info(&pdev->dev,
+ "Error %d allocating resources for existing VFs\n",
+ err);
+ }
}
pfs_found++;
@@ -8092,7 +8336,7 @@
i40e_set_pci_config_data(hw, link_status);
- dev_info(&pdev->dev, "PCI Express: %s %s\n",
+ dev_info(&pdev->dev, "PCI-Express: %s %s\n",
(hw->bus.speed == i40e_bus_speed_8000 ? "Speed 8.0GT/s" :
hw->bus.speed == i40e_bus_speed_5000 ? "Speed 5.0GT/s" :
hw->bus.speed == i40e_bus_speed_2500 ? "Speed 2.5GT/s" :
@@ -8109,6 +8353,9 @@
dev_warn(&pdev->dev, "Please move the device to a different PCI-e link with more lanes and/or higher transfer rate.\n");
}
+ /* print a string summarizing features */
+ i40e_print_features(pf);
+
return 0;
/* Unwind what we've done if something failed in the setup */
@@ -8165,16 +8412,16 @@
i40e_ptp_stop(pf);
- if (pf->flags & I40E_FLAG_SRIOV_ENABLED) {
- i40e_free_vfs(pf);
- pf->flags &= ~I40E_FLAG_SRIOV_ENABLED;
- }
-
/* no more scheduling of any task */
set_bit(__I40E_DOWN, &pf->state);
del_timer_sync(&pf->service_timer);
cancel_work_sync(&pf->service_task);
+ if (pf->flags & I40E_FLAG_SRIOV_ENABLED) {
+ i40e_free_vfs(pf);
+ pf->flags &= ~I40E_FLAG_SRIOV_ENABLED;
+ }
+
i40e_fdir_teardown(pf);
/* If there is a switch structure or any orphans, remove them.
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 73f95b0..262bdf1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -27,14 +27,14 @@
#include "i40e_prototype.h"
/**
- * i40e_init_nvm_ops - Initialize NVM function pointers.
- * @hw: pointer to the HW structure.
+ * i40e_init_nvm_ops - Initialize NVM function pointers
+ * @hw: pointer to the HW structure
*
- * Setups the function pointers and the NVM info structure. Should be called
- * once per NVM initialization, e.g. inside the i40e_init_shared_code().
- * Please notice that the NVM term is used here (& in all methods covered
- * in this file) as an equivalent of the FLASH part mapped into the SR.
- * We are accessing FLASH always thru the Shadow RAM.
+ * Setup the function pointers and the NVM info structure. Should be called
+ * once per NVM initialization, e.g. inside the i40e_init_shared_code().
+ * Please notice that the NVM term is used here (& in all methods covered
+ * in this file) as an equivalent of the FLASH part mapped into the SR.
+ * We are accessing FLASH always thru the Shadow RAM.
**/
i40e_status i40e_init_nvm(struct i40e_hw *hw)
{
@@ -49,16 +49,16 @@
gens = rd32(hw, I40E_GLNVM_GENS);
sr_size = ((gens & I40E_GLNVM_GENS_SR_SIZE_MASK) >>
I40E_GLNVM_GENS_SR_SIZE_SHIFT);
- /* Switching to words (sr_size contains power of 2KB). */
+ /* Switching to words (sr_size contains power of 2KB) */
nvm->sr_size = (1 << sr_size) * I40E_SR_WORDS_IN_1KB;
- /* Check if we are in the normal or blank NVM programming mode. */
+ /* Check if we are in the normal or blank NVM programming mode */
fla = rd32(hw, I40E_GLNVM_FLA);
- if (fla & I40E_GLNVM_FLA_LOCKED_MASK) { /* Normal programming mode. */
- /* Max NVM timeout. */
+ if (fla & I40E_GLNVM_FLA_LOCKED_MASK) { /* Normal programming mode */
+ /* Max NVM timeout */
nvm->timeout = I40E_MAX_NVM_TIMEOUT;
nvm->blank_nvm_mode = false;
- } else { /* Blank programming mode. */
+ } else { /* Blank programming mode */
nvm->blank_nvm_mode = true;
ret_code = I40E_ERR_NVM_BLANK_MODE;
hw_dbg(hw, "NVM init error: unsupported blank mode.\n");
@@ -68,12 +68,12 @@
}
/**
- * i40e_acquire_nvm - Generic request for acquiring the NVM ownership.
- * @hw: pointer to the HW structure.
- * @access: NVM access type (read or write).
+ * i40e_acquire_nvm - Generic request for acquiring the NVM ownership
+ * @hw: pointer to the HW structure
+ * @access: NVM access type (read or write)
*
- * This function will request NVM ownership for reading
- * via the proper Admin Command.
+ * This function will request NVM ownership for reading
+ * via the proper Admin Command.
**/
i40e_status i40e_acquire_nvm(struct i40e_hw *hw,
enum i40e_aq_resource_access_type access)
@@ -87,20 +87,20 @@
ret_code = i40e_aq_request_resource(hw, I40E_NVM_RESOURCE_ID, access,
0, &time, NULL);
- /* Reading the Global Device Timer. */
+ /* Reading the Global Device Timer */
gtime = rd32(hw, I40E_GLVFGEN_TIMER);
- /* Store the timeout. */
+ /* Store the timeout */
hw->nvm.hw_semaphore_timeout = I40E_MS_TO_GTIME(time) + gtime;
if (ret_code) {
- /* Set the polling timeout. */
+ /* Set the polling timeout */
if (time > I40E_MAX_NVM_TIMEOUT)
timeout = I40E_MS_TO_GTIME(I40E_MAX_NVM_TIMEOUT)
+ gtime;
else
timeout = hw->nvm.hw_semaphore_timeout;
- /* Poll until the current NVM owner timeouts. */
+ /* Poll until the current NVM owner timeouts */
while (gtime < timeout) {
usleep_range(10000, 20000);
ret_code = i40e_aq_request_resource(hw,
@@ -128,10 +128,10 @@
}
/**
- * i40e_release_nvm - Generic request for releasing the NVM ownership.
- * @hw: pointer to the HW structure.
+ * i40e_release_nvm - Generic request for releasing the NVM ownership
+ * @hw: pointer to the HW structure
*
- * This function will release NVM resource via the proper Admin Command.
+ * This function will release NVM resource via the proper Admin Command.
**/
void i40e_release_nvm(struct i40e_hw *hw)
{
@@ -140,17 +140,17 @@
}
/**
- * i40e_poll_sr_srctl_done_bit - Polls the GLNVM_SRCTL done bit.
- * @hw: pointer to the HW structure.
+ * i40e_poll_sr_srctl_done_bit - Polls the GLNVM_SRCTL done bit
+ * @hw: pointer to the HW structure
*
- * Polls the SRCTL Shadow RAM register done bit.
+ * Polls the SRCTL Shadow RAM register done bit.
**/
static i40e_status i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw)
{
i40e_status ret_code = I40E_ERR_TIMEOUT;
u32 srctl, wait_cnt;
- /* Poll the I40E_GLNVM_SRCTL until the done bit is set. */
+ /* Poll the I40E_GLNVM_SRCTL until the done bit is set */
for (wait_cnt = 0; wait_cnt < I40E_SRRD_SRCTL_ATTEMPTS; wait_cnt++) {
srctl = rd32(hw, I40E_GLNVM_SRCTL);
if (srctl & I40E_GLNVM_SRCTL_DONE_MASK) {
@@ -165,12 +165,12 @@
}
/**
- * i40e_read_nvm_word - Reads Shadow RAM
- * @hw: pointer to the HW structure.
- * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF).
- * @data: word read from the Shadow RAM.
+ * i40e_read_nvm_word - Reads Shadow RAM
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
+ * @data: word read from the Shadow RAM
*
- * Reads 16 bit word from the Shadow RAM using the GLNVM_SRCTL register.
+ * Reads one 16 bit word from the Shadow RAM using the GLNVM_SRCTL register.
**/
i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
u16 *data)
@@ -184,15 +184,15 @@
goto read_nvm_exit;
}
- /* Poll the done bit first. */
+ /* Poll the done bit first */
ret_code = i40e_poll_sr_srctl_done_bit(hw);
if (!ret_code) {
- /* Write the address and start reading. */
+ /* Write the address and start reading */
sr_reg = (u32)(offset << I40E_GLNVM_SRCTL_ADDR_SHIFT) |
(1 << I40E_GLNVM_SRCTL_START_SHIFT);
wr32(hw, I40E_GLNVM_SRCTL, sr_reg);
- /* Poll I40E_GLNVM_SRCTL until the done bit is set. */
+ /* Poll I40E_GLNVM_SRCTL until the done bit is set */
ret_code = i40e_poll_sr_srctl_done_bit(hw);
if (!ret_code) {
sr_reg = rd32(hw, I40E_GLNVM_SRDATA);
@@ -210,16 +210,15 @@
}
/**
- * i40e_read_nvm_buffer - Reads Shadow RAM buffer.
- * @hw: pointer to the HW structure.
- * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF).
- * @words: number of words to read (in) &
- * number of words read before the NVM ownership timeout (out).
- * @data: words read from the Shadow RAM.
+ * i40e_read_nvm_buffer - Reads Shadow RAM buffer
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF).
+ * @words: (in) number of words to read; (out) number of words actually read
+ * @data: words read from the Shadow RAM
*
- * Reads 16 bit words (data buffer) from the SR using the i40e_read_nvm_srrd()
- * method. The buffer read is preceded by the NVM ownership take
- * and followed by the release.
+ * Reads 16 bit words (data buffer) from the SR using the i40e_read_nvm_srrd()
+ * method. The buffer read is preceded by the NVM ownership take
+ * and followed by the release.
**/
i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset,
u16 *words, u16 *data)
@@ -227,7 +226,7 @@
i40e_status ret_code = 0;
u16 index, word;
- /* Loop thru the selected region. */
+ /* Loop thru the selected region */
for (word = 0; word < *words; word++) {
index = offset + word;
ret_code = i40e_read_nvm_word(hw, index, &data[word]);
@@ -235,21 +234,21 @@
break;
}
- /* Update the number of words read from the Shadow RAM. */
+ /* Update the number of words read from the Shadow RAM */
*words = word;
return ret_code;
}
/**
- * i40e_calc_nvm_checksum - Calculates and returns the checksum
- * @hw: pointer to hardware structure
- * @checksum: pointer to the checksum
+ * i40e_calc_nvm_checksum - Calculates and returns the checksum
+ * @hw: pointer to hardware structure
+ * @checksum: pointer to the checksum
*
- * This function calculate SW Checksum that covers the whole 64kB shadow RAM
- * except the VPD and PCIe ALT Auto-load modules. The structure and size of VPD
- * is customer specific and unknown. Therefore, this function skips all maximum
- * possible size of VPD (1kB).
+ * This function calculates SW Checksum that covers the whole 64kB shadow RAM
+ * except the VPD and PCIe ALT Auto-load modules. The structure and size of VPD
+ * is customer specific and unknown. Therefore, this function skips all maximum
+ * possible size of VPD (1kB).
**/
static i40e_status i40e_calc_nvm_checksum(struct i40e_hw *hw,
u16 *checksum)
@@ -311,12 +310,12 @@
}
/**
- * i40e_validate_nvm_checksum - Validate EEPROM checksum
- * @hw: pointer to hardware structure
- * @checksum: calculated checksum
+ * i40e_validate_nvm_checksum - Validate EEPROM checksum
+ * @hw: pointer to hardware structure
+ * @checksum: calculated checksum
*
- * Performs checksum calculation and validates the NVM SW checksum. If the
- * caller does not need checksum, the value can be NULL.
+ * Performs checksum calculation and validates the NVM SW checksum. If the
+ * caller does not need checksum, the value can be NULL.
**/
i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw,
u16 *checksum)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index ed91f93..9cd57e6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -231,6 +231,13 @@
u16 *checksum);
void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status);
+extern struct i40e_rx_ptype_decoded i40e_ptype_lookup[];
+
+static inline struct i40e_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype)
+{
+ return i40e_ptype_lookup[ptype];
+}
+
/* prototype for functions used for SW locks */
/* i40e_common for VF drivers*/
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index d4bb482..a329aac 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -25,6 +25,7 @@
******************************************************************************/
#include "i40e.h"
+#include "i40e_prototype.h"
static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
u32 td_tag)
@@ -39,11 +40,12 @@
#define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS)
/**
* i40e_program_fdir_filter - Program a Flow Director filter
- * @fdir_input: Packet data that will be filter parameters
+ * @fdir_data: Packet data that will be filter parameters
+ * @raw_packet: the pre-allocated packet buffer for FDir
* @pf: The pf pointer
* @add: True for add/update, False for remove
**/
-int i40e_program_fdir_filter(struct i40e_fdir_data *fdir_data,
+int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, u8 *raw_packet,
struct i40e_pf *pf, bool add)
{
struct i40e_filter_program_desc *fdir_desc;
@@ -68,8 +70,8 @@
tx_ring = vsi->tx_rings[0];
dev = tx_ring->dev;
- dma = dma_map_single(dev, fdir_data->raw_packet,
- I40E_FDIR_MAX_RAW_PACKET_LOOKUP, DMA_TO_DEVICE);
+ dma = dma_map_single(dev, raw_packet,
+ I40E_FDIR_MAX_RAW_PACKET_SIZE, DMA_TO_DEVICE);
if (dma_mapping_error(dev, dma))
goto dma_fail;
@@ -132,14 +134,14 @@
tx_ring->next_to_use = (i + 1 < tx_ring->count) ? i + 1 : 0;
/* record length, and DMA address */
- dma_unmap_len_set(tx_buf, len, I40E_FDIR_MAX_RAW_PACKET_LOOKUP);
+ dma_unmap_len_set(tx_buf, len, I40E_FDIR_MAX_RAW_PACKET_SIZE);
dma_unmap_addr_set(tx_buf, dma, dma);
tx_desc->buffer_addr = cpu_to_le64(dma);
td_cmd = I40E_TXD_CMD | I40E_TX_DESC_CMD_DUMMY;
tx_desc->cmd_type_offset_bsz =
- build_ctob(td_cmd, 0, I40E_FDIR_MAX_RAW_PACKET_LOOKUP, 0);
+ build_ctob(td_cmd, 0, I40E_FDIR_MAX_RAW_PACKET_SIZE, 0);
/* set the timestamp */
tx_buf->time_stamp = jiffies;
@@ -161,26 +163,329 @@
return -1;
}
+#define IP_HEADER_OFFSET 14
+#define I40E_UDPIP_DUMMY_PACKET_LEN 42
+/**
+ * i40e_add_del_fdir_udpv4 - Add/Remove UDPv4 filters
+ * @vsi: pointer to the targeted VSI
+ * @fd_data: the flow director data required for the FDir descriptor
+ * @raw_packet: the pre-allocated packet buffer for FDir
+ * @add: true adds a filter, false removes it
+ *
+ * Returns 0 if the filters were successfully added or removed
+ **/
+static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
+ struct i40e_fdir_filter *fd_data,
+ u8 *raw_packet, bool add)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct udphdr *udp;
+ struct iphdr *ip;
+ bool err = false;
+ int ret;
+ int i;
+ static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
+ 0x45, 0, 0, 0x1c, 0, 0, 0x40, 0, 0x40, 0x11, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+
+ memcpy(raw_packet, packet, I40E_UDPIP_DUMMY_PACKET_LEN);
+
+ ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET);
+ udp = (struct udphdr *)(raw_packet + IP_HEADER_OFFSET
+ + sizeof(struct iphdr));
+
+ ip->daddr = fd_data->dst_ip[0];
+ udp->dest = fd_data->dst_port;
+ ip->saddr = fd_data->src_ip[0];
+ udp->source = fd_data->src_port;
+
+ for (i = I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP;
+ i <= I40E_FILTER_PCTYPE_NONF_IPV4_UDP; i++) {
+ fd_data->pctype = i;
+ ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
+
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Filter command send failed for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ err = true;
+ } else {
+ dev_info(&pf->pdev->dev,
+ "Filter OK for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ }
+ }
+
+ return err ? -EOPNOTSUPP : 0;
+}
+
+#define I40E_TCPIP_DUMMY_PACKET_LEN 54
+/**
+ * i40e_add_del_fdir_tcpv4 - Add/Remove TCPv4 filters
+ * @vsi: pointer to the targeted VSI
+ * @fd_data: the flow director data required for the FDir descriptor
+ * @raw_packet: the pre-allocated packet buffer for FDir
+ * @add: true adds a filter, false removes it
+ *
+ * Returns 0 if the filters were successfully added or removed
+ **/
+static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
+ struct i40e_fdir_filter *fd_data,
+ u8 *raw_packet, bool add)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct tcphdr *tcp;
+ struct iphdr *ip;
+ bool err = false;
+ int ret;
+ /* Dummy packet */
+ static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
+ 0x45, 0, 0, 0x28, 0, 0, 0x40, 0, 0x40, 0x6, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x80, 0x11,
+ 0x0, 0x72, 0, 0, 0, 0};
+
+ memcpy(raw_packet, packet, I40E_TCPIP_DUMMY_PACKET_LEN);
+
+ ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET);
+ tcp = (struct tcphdr *)(raw_packet + IP_HEADER_OFFSET
+ + sizeof(struct iphdr));
+
+ ip->daddr = fd_data->dst_ip[0];
+ tcp->dest = fd_data->dst_port;
+ ip->saddr = fd_data->src_ip[0];
+ tcp->source = fd_data->src_port;
+
+ if (add) {
+ if (pf->flags & I40E_FLAG_FD_ATR_ENABLED) {
+ dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n");
+ pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+ }
+ }
+
+ fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN;
+ ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
+
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Filter command send failed for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ err = true;
+ } else {
+ dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ }
+
+ fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+
+ ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Filter command send failed for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ err = true;
+ } else {
+ dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ }
+
+ return err ? -EOPNOTSUPP : 0;
+}
+
+/**
+ * i40e_add_del_fdir_sctpv4 - Add/Remove SCTPv4 Flow Director filters for
+ * a specific flow spec
+ * @vsi: pointer to the targeted VSI
+ * @fd_data: the flow director data required for the FDir descriptor
+ * @raw_packet: the pre-allocated packet buffer for FDir
+ * @add: true adds a filter, false removes it
+ *
+ * Returns 0 if the filters were successfully added or removed
+ **/
+static int i40e_add_del_fdir_sctpv4(struct i40e_vsi *vsi,
+ struct i40e_fdir_filter *fd_data,
+ u8 *raw_packet, bool add)
+{
+ return -EOPNOTSUPP;
+}
+
+#define I40E_IP_DUMMY_PACKET_LEN 34
+/**
+ * i40e_add_del_fdir_ipv4 - Add/Remove IPv4 Flow Director filters for
+ * a specific flow spec
+ * @vsi: pointer to the targeted VSI
+ * @fd_data: the flow director data required for the FDir descriptor
+ * @raw_packet: the pre-allocated packet buffer for FDir
+ * @add: true adds a filter, false removes it
+ *
+ * Returns 0 if the filters were successfully added or removed
+ **/
+static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi,
+ struct i40e_fdir_filter *fd_data,
+ u8 *raw_packet, bool add)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct iphdr *ip;
+ bool err = false;
+ int ret;
+ int i;
+ static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
+ 0x45, 0, 0, 0x14, 0, 0, 0x40, 0, 0x40, 0x10, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0};
+
+ memcpy(raw_packet, packet, I40E_IP_DUMMY_PACKET_LEN);
+ ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET);
+
+ ip->saddr = fd_data->src_ip[0];
+ ip->daddr = fd_data->dst_ip[0];
+ ip->protocol = 0;
+
+ for (i = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
+ i <= I40E_FILTER_PCTYPE_FRAG_IPV4; i++) {
+ fd_data->pctype = i;
+ ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
+
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Filter command send failed for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ err = true;
+ } else {
+ dev_info(&pf->pdev->dev,
+ "Filter OK for PCTYPE %d (ret = %d)\n",
+ fd_data->pctype, ret);
+ }
+ }
+
+ return err ? -EOPNOTSUPP : 0;
+}
+
+/**
+ * i40e_add_del_fdir - Build raw packets to add/del fdir filter
+ * @vsi: pointer to the targeted VSI
+ * @cmd: command to get or set RX flow classification rules
+ * @add: true adds a filter, false removes it
+ *
+ **/
+int i40e_add_del_fdir(struct i40e_vsi *vsi,
+ struct i40e_fdir_filter *input, bool add)
+{
+ struct i40e_pf *pf = vsi->back;
+ u8 *raw_packet;
+ int ret;
+
+ /* Populate the Flow Director that we have at the moment
+ * and allocate the raw packet buffer for the calling functions
+ */
+ raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_SIZE, GFP_KERNEL);
+ if (!raw_packet)
+ return -ENOMEM;
+
+ switch (input->flow_type & ~FLOW_EXT) {
+ case TCP_V4_FLOW:
+ ret = i40e_add_del_fdir_tcpv4(vsi, input, raw_packet,
+ add);
+ break;
+ case UDP_V4_FLOW:
+ ret = i40e_add_del_fdir_udpv4(vsi, input, raw_packet,
+ add);
+ break;
+ case SCTP_V4_FLOW:
+ ret = i40e_add_del_fdir_sctpv4(vsi, input, raw_packet,
+ add);
+ break;
+ case IPV4_FLOW:
+ ret = i40e_add_del_fdir_ipv4(vsi, input, raw_packet,
+ add);
+ break;
+ case IP_USER_FLOW:
+ switch (input->ip4_proto) {
+ case IPPROTO_TCP:
+ ret = i40e_add_del_fdir_tcpv4(vsi, input,
+ raw_packet, add);
+ break;
+ case IPPROTO_UDP:
+ ret = i40e_add_del_fdir_udpv4(vsi, input,
+ raw_packet, add);
+ break;
+ case IPPROTO_SCTP:
+ ret = i40e_add_del_fdir_sctpv4(vsi, input,
+ raw_packet, add);
+ break;
+ default:
+ ret = i40e_add_del_fdir_ipv4(vsi, input,
+ raw_packet, add);
+ break;
+ }
+ break;
+ default:
+ dev_info(&pf->pdev->dev, "Could not specify spec type %d",
+ input->flow_type);
+ ret = -EINVAL;
+ }
+
+ kfree(raw_packet);
+ return ret;
+}
+
/**
* i40e_fd_handle_status - check the Programming Status for FD
* @rx_ring: the Rx ring for this descriptor
- * @qw: the descriptor data
+ * @rx_desc: the Rx descriptor for programming Status, not a packet descriptor.
* @prog_id: the id originally used for programming
*
* This is used to verify if the FD programming or invalidation
* requested by SW to the HW is successful or not and take actions accordingly.
**/
-static void i40e_fd_handle_status(struct i40e_ring *rx_ring, u32 qw, u8 prog_id)
+static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
+ union i40e_rx_desc *rx_desc, u8 prog_id)
{
- struct pci_dev *pdev = rx_ring->vsi->back->pdev;
+ struct i40e_pf *pf = rx_ring->vsi->back;
+ struct pci_dev *pdev = pf->pdev;
+ u32 fcnt_prog, fcnt_avail;
u32 error;
+ u64 qw;
+ qw = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
error = (qw & I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK) >>
I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT;
- /* for now just print the Status */
- dev_info(&pdev->dev, "FD programming id %02x, Status %08x\n",
- prog_id, error);
+ if (error == (0x1 << I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT)) {
+ dev_warn(&pdev->dev, "ntuple filter loc = %d, could not be added\n",
+ rx_desc->wb.qword0.hi_dword.fd_id);
+
+ /* filter programming failed most likely due to table full */
+ fcnt_prog = i40e_get_current_fd_count(pf);
+ fcnt_avail = pf->hw.fdir_shared_filter_count +
+ pf->fdir_pf_filter_count;
+
+ /* If ATR is running fcnt_prog can quickly change,
+ * if we are very close to full, it makes sense to disable
+ * FD ATR/SB and then re-enable it when there is room.
+ */
+ if (fcnt_prog >= (fcnt_avail - I40E_FDIR_BUFFER_FULL_MARGIN)) {
+ /* Turn off ATR first */
+ if (pf->flags | I40E_FLAG_FD_ATR_ENABLED) {
+ pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+ dev_warn(&pdev->dev, "FD filter space full, ATR for further flows will be turned off\n");
+ pf->auto_disable_flags |=
+ I40E_FLAG_FD_ATR_ENABLED;
+ pf->flags |= I40E_FLAG_FDIR_REQUIRES_REINIT;
+ } else if (pf->flags | I40E_FLAG_FD_SB_ENABLED) {
+ pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
+ dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n");
+ pf->auto_disable_flags |=
+ I40E_FLAG_FD_SB_ENABLED;
+ pf->flags |= I40E_FLAG_FDIR_REQUIRES_REINIT;
+ }
+ } else {
+ dev_info(&pdev->dev, "FD filter programming error");
+ }
+ } else if (error ==
+ (0x1 << I40E_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT)) {
+ if (I40E_DEBUG_FD & pf->hw.debug_mask)
+ dev_info(&pdev->dev, "ntuple filter loc = %d, could not be removed\n",
+ rx_desc->wb.qword0.hi_dword.fd_id);
+ }
}
/**
@@ -315,6 +620,20 @@
}
/**
+ * i40e_get_head - Retrieve head from head writeback
+ * @tx_ring: tx ring to fetch head of
+ *
+ * Returns value of Tx ring head based on value stored
+ * in head write-back location
+ **/
+static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
+{
+ void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count;
+
+ return le32_to_cpu(*(volatile __le32 *)head);
+}
+
+/**
* i40e_clean_tx_irq - Reclaim resources after transmit completes
* @tx_ring: tx ring to clean
* @budget: how many cleans we're allowed
@@ -325,6 +644,7 @@
{
u16 i = tx_ring->next_to_clean;
struct i40e_tx_buffer *tx_buf;
+ struct i40e_tx_desc *tx_head;
struct i40e_tx_desc *tx_desc;
unsigned int total_packets = 0;
unsigned int total_bytes = 0;
@@ -333,6 +653,8 @@
tx_desc = I40E_TX_DESC(tx_ring, i);
i -= tx_ring->count;
+ tx_head = I40E_TX_DESC(tx_ring, i40e_get_head(tx_ring));
+
do {
struct i40e_tx_desc *eop_desc = tx_buf->next_to_watch;
@@ -343,9 +665,8 @@
/* prevent any other reads prior to eop_desc */
read_barrier_depends();
- /* if the descriptor isn't done, no work yet to do */
- if (!(eop_desc->cmd_type_offset_bsz &
- cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE)))
+ /* we have caught up to head, no work left to do */
+ if (tx_head == tx_desc)
break;
/* clear next_to_watch to prevent false hangs */
@@ -577,7 +898,7 @@
I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT;
if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS)
- i40e_fd_handle_status(rx_ring, qw, id);
+ i40e_fd_handle_status(rx_ring, rx_desc, id);
}
/**
@@ -601,6 +922,10 @@
/* round up to nearest 4K */
tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc);
+ /* add u32 for head writeback, align after this takes care of
+ * guaranteeing this is at least one cache line in size
+ */
+ tx_ring->size += sizeof(u32);
tx_ring->size = ALIGN(tx_ring->size, 4096);
tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
&tx_ring->dma, GFP_KERNEL);
@@ -892,7 +1217,7 @@
rx_status & (1 << I40E_RX_DESC_STATUS_L3L4P_SHIFT)))
return;
- /* likely incorrect csum if alternate IP extention headers found */
+ /* likely incorrect csum if alternate IP extension headers found */
if (rx_status & (1 << I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT))
return;
@@ -956,6 +1281,29 @@
}
/**
+ * i40e_ptype_to_hash - get a hash type
+ * @ptype: the ptype value from the descriptor
+ *
+ * Returns a hash type to be used by skb_set_hash
+ **/
+static inline enum pkt_hash_types i40e_ptype_to_hash(u8 ptype)
+{
+ struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype);
+
+ if (!decoded.known)
+ return PKT_HASH_TYPE_NONE;
+
+ if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
+ decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4)
+ return PKT_HASH_TYPE_L4;
+ else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
+ decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3)
+ return PKT_HASH_TYPE_L3;
+ else
+ return PKT_HASH_TYPE_L2;
+}
+
+/**
* i40e_clean_rx_irq - Reclaim resources after receive completes
* @rx_ring: rx ring to clean
* @budget: how many cleans we're allowed
@@ -972,8 +1320,11 @@
u16 i = rx_ring->next_to_clean;
union i40e_rx_desc *rx_desc;
u32 rx_error, rx_status;
+ u8 rx_ptype;
u64 qword;
- u16 rx_ptype;
+
+ if (budget <= 0)
+ return 0;
rx_desc = I40E_RX_DESC(rx_ring, i);
qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
@@ -1087,7 +1438,8 @@
goto next_desc;
}
- skb->rxhash = i40e_rx_hash(rx_ring, rx_desc);
+ skb_set_hash(skb, i40e_rx_hash(rx_ring, rx_desc),
+ i40e_ptype_to_hash(rx_ptype));
if (unlikely(rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK)) {
i40e_ptp_rx_hwtstamp(vsi->back, skb, (rx_status &
I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >>
@@ -1246,8 +1598,6 @@
if (!tx_ring->atr_sample_rate)
return;
- tx_ring->atr_count++;
-
/* snag network header to get L4 type and address */
hdr.network = skb_network_header(skb);
@@ -1269,8 +1619,17 @@
th = (struct tcphdr *)(hdr.network + hlen);
- /* sample on all syn/fin packets or once every atr sample rate */
- if (!th->fin && !th->syn && (tx_ring->atr_count < tx_ring->atr_sample_rate))
+ /* Due to lack of space, no more new filters can be programmed */
+ if (th->syn && (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+ return;
+
+ tx_ring->atr_count++;
+
+ /* sample on all syn/fin/rst packets or once every atr sample rate */
+ if (!th->fin &&
+ !th->syn &&
+ !th->rst &&
+ (tx_ring->atr_count < tx_ring->atr_sample_rate))
return;
tx_ring->atr_count = 0;
@@ -1294,7 +1653,7 @@
dtype_cmd = I40E_TX_DESC_DTYPE_FILTER_PROG;
- dtype_cmd |= th->fin ?
+ dtype_cmd |= (th->fin || th->rst) ?
(I40E_FILTER_PROGRAM_DESC_PCMD_REMOVE <<
I40E_TXD_FLTR_QW1_PCMD_SHIFT) :
(I40E_FILTER_PROGRAM_DESC_PCMD_ADD_UPDATE <<
@@ -1596,7 +1955,8 @@
struct i40e_tx_context_desc *context_desc;
int i = tx_ring->next_to_use;
- if (!cd_type_cmd_tso_mss && !cd_tunneling && !cd_l2tag2)
+ if ((cd_type_cmd_tso_mss == I40E_TX_DESC_DTYPE_CONTEXT) &&
+ !cd_tunneling && !cd_l2tag2)
return;
/* grab the next descriptor */
@@ -1707,9 +2067,23 @@
tx_bi = &tx_ring->tx_bi[i];
}
- tx_desc->cmd_type_offset_bsz =
- build_ctob(td_cmd, td_offset, size, td_tag) |
- cpu_to_le64((u64)I40E_TXD_CMD << I40E_TXD_QW1_CMD_SHIFT);
+ /* Place RS bit on last descriptor of any packet that spans across the
+ * 4th descriptor (WB_STRIDE aka 0x3) in a 64B cacheline.
+ */
+#define WB_STRIDE 0x3
+ if (((i & WB_STRIDE) != WB_STRIDE) &&
+ (first <= &tx_ring->tx_bi[i]) &&
+ (first >= &tx_ring->tx_bi[i & ~WB_STRIDE])) {
+ tx_desc->cmd_type_offset_bsz =
+ build_ctob(td_cmd, td_offset, size, td_tag) |
+ cpu_to_le64((u64)I40E_TX_DESC_CMD_EOP <<
+ I40E_TXD_QW1_CMD_SHIFT);
+ } else {
+ tx_desc->cmd_type_offset_bsz =
+ build_ctob(td_cmd, td_offset, size, td_tag) |
+ cpu_to_le64((u64)I40E_TXD_CMD <<
+ I40E_TXD_QW1_CMD_SHIFT);
+ }
netdev_tx_sent_queue(netdev_get_tx_queue(tx_ring->netdev,
tx_ring->queue_index),
@@ -1812,7 +2186,7 @@
/* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD,
* + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD,
- * + 2 desc gap to keep tail from touching head,
+ * + 4 desc gap to avoid the cache line where head is,
* + 1 desc for context descriptor,
* otherwise try next time
*/
@@ -1823,7 +2197,7 @@
count += skb_shinfo(skb)->nr_frags;
#endif
count += TXD_USE_COUNT(skb_headlen(skb));
- if (i40e_maybe_stop_tx(tx_ring, count + 3)) {
+ if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) {
tx_ring->tx_stats.tx_busy++;
return 0;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 181a825..71a968f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -91,6 +91,7 @@
I40E_DEBUG_FLOW = 0x00000200,
I40E_DEBUG_DCB = 0x00000400,
I40E_DEBUG_DIAG = 0x00000800,
+ I40E_DEBUG_FD = 0x00001000,
I40E_DEBUG_AQ_MESSAGE = 0x01000000,
I40E_DEBUG_AQ_DESCRIPTOR = 0x02000000,
@@ -458,6 +459,10 @@
union {
__le32 rss; /* RSS Hash */
__le32 fcoe_param; /* FCoE DDP Context id */
+ /* Flow director filter id in case of
+ * Programming status desc WB
+ */
+ __le32 fd_id;
} hi_dword;
} qword0;
struct {
@@ -698,7 +703,7 @@
enum i40e_rx_prog_status_desc_error_bits {
/* Note: These are predefined bit offsets */
I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT = 0,
- I40E_RX_PROG_STATUS_DESC_NO_FD_QUOTA_SHIFT = 1,
+ I40E_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT = 1,
I40E_RX_PROG_STATUS_DESC_FCOE_TBL_FULL_SHIFT = 2,
I40E_RX_PROG_STATUS_DESC_FCOE_CONFLICT_SHIFT = 3
};
@@ -1010,6 +1015,11 @@
u64 tx_size_big; /* ptc9522 */
u64 mac_short_packet_dropped; /* mspdc */
u64 checksum_error; /* xec */
+ /* EEE LPI */
+ bool tx_lpi_status;
+ bool rx_lpi_status;
+ u64 tx_lpi_count; /* etlpic */
+ u64 rx_lpi_count; /* erlpic */
};
/* Checksum and Shadow RAM pointers */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index b9d1c1c..02c11a7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -69,7 +69,7 @@
{
struct i40e_pf *pf = vf->pf;
- return vector_id <= pf->hw.func_caps.num_msix_vectors_vf;
+ return vector_id < pf->hw.func_caps.num_msix_vectors_vf;
}
/***********************vf resource mgmt routines*****************/
@@ -126,8 +126,8 @@
reg_idx = I40E_VPINT_LNKLST0(vf->vf_id);
else
reg_idx = I40E_VPINT_LNKLSTN(
- (pf->hw.func_caps.num_msix_vectors_vf
- * vf->vf_id) + (vector_id - 1));
+ ((pf->hw.func_caps.num_msix_vectors_vf - 1) * vf->vf_id) +
+ (vector_id - 1));
if (vecmap->rxq_map == 0 && vecmap->txq_map == 0) {
/* Special case - No queues mapped on this vector */
@@ -230,6 +230,9 @@
tx_ctx.qlen = info->ring_len;
tx_ctx.rdylist = le16_to_cpu(pf->vsi[vsi_idx]->info.qs_handle[0]);
tx_ctx.rdylist_act = 0;
+ tx_ctx.head_wb_ena = 1;
+ tx_ctx.head_wb_addr = info->dma_ring_addr +
+ (info->ring_len * sizeof(struct i40e_tx_desc));
/* clear the context in the HMC */
ret = i40e_clear_lan_tx_queue_context(hw, pf_queue_id);
@@ -408,18 +411,10 @@
"Could not allocate VF broadcast filter\n");
}
- if (!f) {
- dev_err(&pf->pdev->dev, "Unable to add ucast filter\n");
- ret = -ENOMEM;
- goto error_alloc_vsi_res;
- }
-
/* program mac filter */
ret = i40e_sync_vsi_filters(vsi);
- if (ret) {
+ if (ret)
dev_err(&pf->pdev->dev, "Unable to program ucast filters\n");
- goto error_alloc_vsi_res;
- }
error_alloc_vsi_res:
return ret;
@@ -514,7 +509,8 @@
vf->lan_vsi_index = 0;
vf->lan_vsi_id = 0;
}
- msix_vf = pf->hw.func_caps.num_msix_vectors_vf + 1;
+ msix_vf = pf->hw.func_caps.num_msix_vectors_vf;
+
/* disable interrupts so the VF starts in a known state */
for (i = 0; i < msix_vf; i++) {
/* format is same for both registers */
@@ -679,9 +675,9 @@
complete_reset:
/* reallocate vf resources to reset the VSI state */
i40e_free_vf_res(vf);
- mdelay(10);
i40e_alloc_vf_res(vf);
i40e_enable_vf_mappings(vf);
+ set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states);
/* tell the VF the reset is done */
wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE);
@@ -847,7 +843,7 @@
*
* allocate vf resources
**/
-static int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
+int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
{
struct i40e_vf *vfs;
int i, ret = 0;
@@ -855,16 +851,18 @@
/* Disable interrupt 0 so we don't try to handle the VFLR. */
i40e_irq_dynamic_disable_icr0(pf);
- ret = pci_enable_sriov(pf->pdev, num_alloc_vfs);
- if (ret) {
- dev_err(&pf->pdev->dev,
- "pci_enable_sriov failed with error %d!\n", ret);
- pf->num_alloc_vfs = 0;
- goto err_iov;
+ /* Check to see if we're just allocating resources for extant VFs */
+ if (pci_num_vf(pf->pdev) != num_alloc_vfs) {
+ ret = pci_enable_sriov(pf->pdev, num_alloc_vfs);
+ if (ret) {
+ dev_err(&pf->pdev->dev,
+ "Failed to enable SR-IOV, error %d.\n", ret);
+ pf->num_alloc_vfs = 0;
+ goto err_iov;
+ }
}
-
/* allocate memory */
- vfs = kzalloc(num_alloc_vfs * sizeof(struct i40e_vf), GFP_KERNEL);
+ vfs = kcalloc(num_alloc_vfs, sizeof(struct i40e_vf), GFP_KERNEL);
if (!vfs) {
ret = -ENOMEM;
goto err_alloc;
@@ -1776,7 +1774,7 @@
u32 v_retval, u8 *msg, u16 msglen)
{
struct i40e_hw *hw = &pf->hw;
- int local_vf_id = vf_id - hw->func_caps.vf_base_id;
+ unsigned int local_vf_id = vf_id - hw->func_caps.vf_base_id;
struct i40e_vf *vf;
int ret;
@@ -1873,7 +1871,8 @@
/* clear the bit in GLGEN_VFLRSTAT */
wr32(hw, I40E_GLGEN_VFLRSTAT(reg_idx), (1 << bit_idx));
- i40e_reset_vf(vf, true);
+ if (!test_bit(__I40E_DOWN, &pf->state))
+ i40e_reset_vf(vf, true);
}
}
@@ -1924,15 +1923,28 @@
void i40e_vc_notify_link_state(struct i40e_pf *pf)
{
struct i40e_virtchnl_pf_event pfe;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_vf *vf = pf->vf;
+ struct i40e_link_status *ls = &pf->hw.phy.link_info;
+ int i;
pfe.event = I40E_VIRTCHNL_EVENT_LINK_CHANGE;
pfe.severity = I40E_PF_EVENT_SEVERITY_INFO;
- pfe.event_data.link_event.link_status =
- pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP;
- pfe.event_data.link_event.link_speed = pf->hw.phy.link_info.link_speed;
-
- i40e_vc_vf_broadcast(pf, I40E_VIRTCHNL_OP_EVENT, I40E_SUCCESS,
- (u8 *)&pfe, sizeof(struct i40e_virtchnl_pf_event));
+ for (i = 0; i < pf->num_alloc_vfs; i++) {
+ if (vf->link_forced) {
+ pfe.event_data.link_event.link_status = vf->link_up;
+ pfe.event_data.link_event.link_speed =
+ (vf->link_up ? I40E_LINK_SPEED_40GB : 0);
+ } else {
+ pfe.event_data.link_event.link_status =
+ ls->link_info & I40E_AQ_LINK_UP;
+ pfe.event_data.link_event.link_speed = ls->link_speed;
+ }
+ i40e_aq_send_msg_to_vf(hw, vf->vf_id, I40E_VIRTCHNL_OP_EVENT,
+ 0, (u8 *)&pfe, sizeof(pfe),
+ NULL);
+ vf++;
+ }
}
/**
@@ -2197,3 +2209,64 @@
error_param:
return ret;
}
+
+/**
+ * i40e_ndo_set_vf_link_state
+ * @netdev: network interface device structure
+ * @vf_id: vf identifier
+ * @link: required link state
+ *
+ * Set the link state of a specified VF, regardless of physical link state
+ **/
+int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_pf *pf = np->vsi->back;
+ struct i40e_virtchnl_pf_event pfe;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_vf *vf;
+ int ret = 0;
+
+ /* validate the request */
+ if (vf_id >= pf->num_alloc_vfs) {
+ dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
+ ret = -EINVAL;
+ goto error_out;
+ }
+
+ vf = &pf->vf[vf_id];
+
+ pfe.event = I40E_VIRTCHNL_EVENT_LINK_CHANGE;
+ pfe.severity = I40E_PF_EVENT_SEVERITY_INFO;
+
+ switch (link) {
+ case IFLA_VF_LINK_STATE_AUTO:
+ vf->link_forced = false;
+ pfe.event_data.link_event.link_status =
+ pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP;
+ pfe.event_data.link_event.link_speed =
+ pf->hw.phy.link_info.link_speed;
+ break;
+ case IFLA_VF_LINK_STATE_ENABLE:
+ vf->link_forced = true;
+ vf->link_up = true;
+ pfe.event_data.link_event.link_status = true;
+ pfe.event_data.link_event.link_speed = I40E_LINK_SPEED_40GB;
+ break;
+ case IFLA_VF_LINK_STATE_DISABLE:
+ vf->link_forced = true;
+ vf->link_up = false;
+ pfe.event_data.link_event.link_status = false;
+ pfe.event_data.link_event.link_speed = 0;
+ break;
+ default:
+ ret = -EINVAL;
+ goto error_out;
+ }
+ /* Notify the VF of its new link state */
+ i40e_aq_send_msg_to_vf(hw, vf->vf_id, I40E_VIRTCHNL_OP_EVENT,
+ 0, (u8 *)&pfe, sizeof(pfe), NULL);
+
+error_out:
+ return ret;
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index cc1feee..389c47f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -98,10 +98,13 @@
unsigned long vf_caps; /* vf's adv. capabilities */
unsigned long vf_states; /* vf's runtime states */
+ bool link_forced;
+ bool link_up; /* only valid if vf link is forced */
};
void i40e_free_vfs(struct i40e_pf *pf);
int i40e_pci_sriov_configure(struct pci_dev *dev, int num_vfs);
+int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs);
int i40e_vc_process_vf_msg(struct i40e_pf *pf, u16 vf_id, u32 v_opcode,
u32 v_retval, u8 *msg, u16 msglen);
int i40e_vc_process_vflr_event(struct i40e_pf *pf);
@@ -115,6 +118,8 @@
int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int tx_rate);
int i40e_ndo_get_vf_config(struct net_device *netdev,
int vf_id, struct ifla_vf_info *ivi);
+int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link);
+
void i40e_vc_notify_link_state(struct i40e_pf *pf);
void i40e_vc_notify_reset(struct i40e_pf *pf);
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index f7cea1b..97662b6 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -1229,7 +1229,7 @@
#define I40E_AQC_ADD_CLOUD_TNL_TYPE_NGE 2
#define I40E_AQC_ADD_CLOUD_TNL_TYPE_IP 3
- __le32 tenant_id ;
+ __le32 tenant_id;
u8 reserved[4];
__le16 queue_number;
#define I40E_AQC_ADD_CLOUD_QUEUE_SHIFT 0
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index 7b13953..c688a0f 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -160,6 +160,372 @@
}
+/* The i40evf_ptype_lookup table is used to convert from the 8-bit ptype in the
+ * hardware to a bit-field that can be used by SW to more easily determine the
+ * packet type.
+ *
+ * Macros are used to shorten the table lines and make this table human
+ * readable.
+ *
+ * We store the PTYPE in the top byte of the bit field - this is just so that
+ * we can check that the table doesn't have a row missing, as the index into
+ * the table should be the PTYPE.
+ *
+ * Typical work flow:
+ *
+ * IF NOT i40evf_ptype_lookup[ptype].known
+ * THEN
+ * Packet is unknown
+ * ELSE IF i40evf_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP
+ * Use the rest of the fields to look at the tunnels, inner protocols, etc
+ * ELSE
+ * Use the enum i40e_rx_l2_ptype to decode the packet type
+ * ENDIF
+ */
+
+/* macro to make the table lines short */
+#define I40E_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
+ { PTYPE, \
+ 1, \
+ I40E_RX_PTYPE_OUTER_##OUTER_IP, \
+ I40E_RX_PTYPE_OUTER_##OUTER_IP_VER, \
+ I40E_RX_PTYPE_##OUTER_FRAG, \
+ I40E_RX_PTYPE_TUNNEL_##T, \
+ I40E_RX_PTYPE_TUNNEL_END_##TE, \
+ I40E_RX_PTYPE_##TEF, \
+ I40E_RX_PTYPE_INNER_PROT_##I, \
+ I40E_RX_PTYPE_PAYLOAD_LAYER_##PL }
+
+#define I40E_PTT_UNUSED_ENTRY(PTYPE) \
+ { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 }
+
+/* shorter macros makes the table fit but are terse */
+#define I40E_RX_PTYPE_NOF I40E_RX_PTYPE_NOT_FRAG
+#define I40E_RX_PTYPE_FRG I40E_RX_PTYPE_FRAG
+#define I40E_RX_PTYPE_INNER_PROT_TS I40E_RX_PTYPE_INNER_PROT_TIMESYNC
+
+/* Lookup table mapping the HW PTYPE to the bit field for decoding */
+struct i40e_rx_ptype_decoded i40evf_ptype_lookup[] = {
+ /* L2 Packet types */
+ I40E_PTT_UNUSED_ENTRY(0),
+ I40E_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ I40E_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2),
+ I40E_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ I40E_PTT_UNUSED_ENTRY(4),
+ I40E_PTT_UNUSED_ENTRY(5),
+ I40E_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ I40E_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ I40E_PTT_UNUSED_ENTRY(8),
+ I40E_PTT_UNUSED_ENTRY(9),
+ I40E_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
+ I40E_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
+ I40E_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3),
+
+ /* Non Tunneled IPv4 */
+ I40E_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(25),
+ I40E_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4),
+ I40E_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),
+ I40E_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),
+
+ /* IPv4 --> IPv4 */
+ I40E_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(32),
+ I40E_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv4 --> IPv6 */
+ I40E_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(39),
+ I40E_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT */
+ I40E_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
+
+ /* IPv4 --> GRE/NAT --> IPv4 */
+ I40E_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(47),
+ I40E_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT --> IPv6 */
+ I40E_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(54),
+ I40E_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT --> MAC */
+ I40E_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
+
+ /* IPv4 --> GRE/NAT --> MAC --> IPv4 */
+ I40E_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(62),
+ I40E_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT -> MAC --> IPv6 */
+ I40E_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(69),
+ I40E_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv4 --> GRE/NAT --> MAC/VLAN */
+ I40E_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
+
+ /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */
+ I40E_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(77),
+ I40E_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */
+ I40E_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(84),
+ I40E_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+
+ /* Non Tunneled IPv6 */
+ I40E_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),
+ I40E_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3),
+ I40E_PTT_UNUSED_ENTRY(91),
+ I40E_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4),
+ I40E_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),
+ I40E_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),
+
+ /* IPv6 --> IPv4 */
+ I40E_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(98),
+ I40E_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv6 --> IPv6 */
+ I40E_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(105),
+ I40E_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT */
+ I40E_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
+
+ /* IPv6 --> GRE/NAT -> IPv4 */
+ I40E_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(113),
+ I40E_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> IPv6 */
+ I40E_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(120),
+ I40E_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> MAC */
+ I40E_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
+
+ /* IPv6 --> GRE/NAT -> MAC -> IPv4 */
+ I40E_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(128),
+ I40E_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> MAC -> IPv6 */
+ I40E_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(135),
+ I40E_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> MAC/VLAN */
+ I40E_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
+
+ /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */
+ I40E_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
+ I40E_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
+ I40E_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(143),
+ I40E_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4),
+ I40E_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
+ I40E_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
+
+ /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */
+ I40E_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
+ I40E_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
+ I40E_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4),
+ I40E_PTT_UNUSED_ENTRY(150),
+ I40E_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4),
+ I40E_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
+ I40E_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+
+ /* unused entries */
+ I40E_PTT_UNUSED_ENTRY(154),
+ I40E_PTT_UNUSED_ENTRY(155),
+ I40E_PTT_UNUSED_ENTRY(156),
+ I40E_PTT_UNUSED_ENTRY(157),
+ I40E_PTT_UNUSED_ENTRY(158),
+ I40E_PTT_UNUSED_ENTRY(159),
+
+ I40E_PTT_UNUSED_ENTRY(160),
+ I40E_PTT_UNUSED_ENTRY(161),
+ I40E_PTT_UNUSED_ENTRY(162),
+ I40E_PTT_UNUSED_ENTRY(163),
+ I40E_PTT_UNUSED_ENTRY(164),
+ I40E_PTT_UNUSED_ENTRY(165),
+ I40E_PTT_UNUSED_ENTRY(166),
+ I40E_PTT_UNUSED_ENTRY(167),
+ I40E_PTT_UNUSED_ENTRY(168),
+ I40E_PTT_UNUSED_ENTRY(169),
+
+ I40E_PTT_UNUSED_ENTRY(170),
+ I40E_PTT_UNUSED_ENTRY(171),
+ I40E_PTT_UNUSED_ENTRY(172),
+ I40E_PTT_UNUSED_ENTRY(173),
+ I40E_PTT_UNUSED_ENTRY(174),
+ I40E_PTT_UNUSED_ENTRY(175),
+ I40E_PTT_UNUSED_ENTRY(176),
+ I40E_PTT_UNUSED_ENTRY(177),
+ I40E_PTT_UNUSED_ENTRY(178),
+ I40E_PTT_UNUSED_ENTRY(179),
+
+ I40E_PTT_UNUSED_ENTRY(180),
+ I40E_PTT_UNUSED_ENTRY(181),
+ I40E_PTT_UNUSED_ENTRY(182),
+ I40E_PTT_UNUSED_ENTRY(183),
+ I40E_PTT_UNUSED_ENTRY(184),
+ I40E_PTT_UNUSED_ENTRY(185),
+ I40E_PTT_UNUSED_ENTRY(186),
+ I40E_PTT_UNUSED_ENTRY(187),
+ I40E_PTT_UNUSED_ENTRY(188),
+ I40E_PTT_UNUSED_ENTRY(189),
+
+ I40E_PTT_UNUSED_ENTRY(190),
+ I40E_PTT_UNUSED_ENTRY(191),
+ I40E_PTT_UNUSED_ENTRY(192),
+ I40E_PTT_UNUSED_ENTRY(193),
+ I40E_PTT_UNUSED_ENTRY(194),
+ I40E_PTT_UNUSED_ENTRY(195),
+ I40E_PTT_UNUSED_ENTRY(196),
+ I40E_PTT_UNUSED_ENTRY(197),
+ I40E_PTT_UNUSED_ENTRY(198),
+ I40E_PTT_UNUSED_ENTRY(199),
+
+ I40E_PTT_UNUSED_ENTRY(200),
+ I40E_PTT_UNUSED_ENTRY(201),
+ I40E_PTT_UNUSED_ENTRY(202),
+ I40E_PTT_UNUSED_ENTRY(203),
+ I40E_PTT_UNUSED_ENTRY(204),
+ I40E_PTT_UNUSED_ENTRY(205),
+ I40E_PTT_UNUSED_ENTRY(206),
+ I40E_PTT_UNUSED_ENTRY(207),
+ I40E_PTT_UNUSED_ENTRY(208),
+ I40E_PTT_UNUSED_ENTRY(209),
+
+ I40E_PTT_UNUSED_ENTRY(210),
+ I40E_PTT_UNUSED_ENTRY(211),
+ I40E_PTT_UNUSED_ENTRY(212),
+ I40E_PTT_UNUSED_ENTRY(213),
+ I40E_PTT_UNUSED_ENTRY(214),
+ I40E_PTT_UNUSED_ENTRY(215),
+ I40E_PTT_UNUSED_ENTRY(216),
+ I40E_PTT_UNUSED_ENTRY(217),
+ I40E_PTT_UNUSED_ENTRY(218),
+ I40E_PTT_UNUSED_ENTRY(219),
+
+ I40E_PTT_UNUSED_ENTRY(220),
+ I40E_PTT_UNUSED_ENTRY(221),
+ I40E_PTT_UNUSED_ENTRY(222),
+ I40E_PTT_UNUSED_ENTRY(223),
+ I40E_PTT_UNUSED_ENTRY(224),
+ I40E_PTT_UNUSED_ENTRY(225),
+ I40E_PTT_UNUSED_ENTRY(226),
+ I40E_PTT_UNUSED_ENTRY(227),
+ I40E_PTT_UNUSED_ENTRY(228),
+ I40E_PTT_UNUSED_ENTRY(229),
+
+ I40E_PTT_UNUSED_ENTRY(230),
+ I40E_PTT_UNUSED_ENTRY(231),
+ I40E_PTT_UNUSED_ENTRY(232),
+ I40E_PTT_UNUSED_ENTRY(233),
+ I40E_PTT_UNUSED_ENTRY(234),
+ I40E_PTT_UNUSED_ENTRY(235),
+ I40E_PTT_UNUSED_ENTRY(236),
+ I40E_PTT_UNUSED_ENTRY(237),
+ I40E_PTT_UNUSED_ENTRY(238),
+ I40E_PTT_UNUSED_ENTRY(239),
+
+ I40E_PTT_UNUSED_ENTRY(240),
+ I40E_PTT_UNUSED_ENTRY(241),
+ I40E_PTT_UNUSED_ENTRY(242),
+ I40E_PTT_UNUSED_ENTRY(243),
+ I40E_PTT_UNUSED_ENTRY(244),
+ I40E_PTT_UNUSED_ENTRY(245),
+ I40E_PTT_UNUSED_ENTRY(246),
+ I40E_PTT_UNUSED_ENTRY(247),
+ I40E_PTT_UNUSED_ENTRY(248),
+ I40E_PTT_UNUSED_ENTRY(249),
+
+ I40E_PTT_UNUSED_ENTRY(250),
+ I40E_PTT_UNUSED_ENTRY(251),
+ I40E_PTT_UNUSED_ENTRY(252),
+ I40E_PTT_UNUSED_ENTRY(253),
+ I40E_PTT_UNUSED_ENTRY(254),
+ I40E_PTT_UNUSED_ENTRY(255)
+};
+
+
/**
* i40e_aq_send_msg_to_pf
* @hw: pointer to the hardware structure
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
index 7841573..97ab8c2 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
@@ -63,6 +63,13 @@
i40e_status i40e_set_mac_type(struct i40e_hw *hw);
+extern struct i40e_rx_ptype_decoded i40evf_ptype_lookup[];
+
+static inline struct i40e_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype)
+{
+ return i40evf_ptype_lookup[ptype];
+}
+
/* prototype for functions used for SW locks */
/* i40e_common for VF drivers*/
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index ffdb01d..53be5f4 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1,7 +1,7 @@
/*******************************************************************************
*
* Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -24,6 +24,7 @@
#include <linux/prefetch.h>
#include "i40evf.h"
+#include "i40e_prototype.h"
static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
u32 td_tag)
@@ -169,6 +170,20 @@
}
/**
+ * i40e_get_head - Retrieve head from head writeback
+ * @tx_ring: tx ring to fetch head of
+ *
+ * Returns value of Tx ring head based on value stored
+ * in head write-back location
+ **/
+static inline u32 i40e_get_head(struct i40e_ring *tx_ring)
+{
+ void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count;
+
+ return le32_to_cpu(*(volatile __le32 *)head);
+}
+
+/**
* i40e_clean_tx_irq - Reclaim resources after transmit completes
* @tx_ring: tx ring to clean
* @budget: how many cleans we're allowed
@@ -179,6 +194,7 @@
{
u16 i = tx_ring->next_to_clean;
struct i40e_tx_buffer *tx_buf;
+ struct i40e_tx_desc *tx_head;
struct i40e_tx_desc *tx_desc;
unsigned int total_packets = 0;
unsigned int total_bytes = 0;
@@ -187,6 +203,8 @@
tx_desc = I40E_TX_DESC(tx_ring, i);
i -= tx_ring->count;
+ tx_head = I40E_TX_DESC(tx_ring, i40e_get_head(tx_ring));
+
do {
struct i40e_tx_desc *eop_desc = tx_buf->next_to_watch;
@@ -197,9 +215,8 @@
/* prevent any other reads prior to eop_desc */
read_barrier_depends();
- /* if the descriptor isn't done, no work yet to do */
- if (!(eop_desc->cmd_type_offset_bsz &
- cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE)))
+ /* we have caught up to head, no work left to do */
+ if (tx_head == tx_desc)
break;
/* clear next_to_watch to prevent false hangs */
@@ -431,6 +448,10 @@
/* round up to nearest 4K */
tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc);
+ /* add u32 for head writeback, align after this takes care of
+ * guaranteeing this is at least one cache line in size
+ */
+ tx_ring->size += sizeof(u32);
tx_ring->size = ALIGN(tx_ring->size, 4096);
tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
&tx_ring->dma, GFP_KERNEL);
@@ -722,7 +743,7 @@
rx_status & (1 << I40E_RX_DESC_STATUS_L3L4P_SHIFT)))
return;
- /* likely incorrect csum if alternate IP extention headers found */
+ /* likely incorrect csum if alternate IP extension headers found */
if (rx_status & (1 << I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT))
return;
@@ -786,6 +807,29 @@
}
/**
+ * i40e_ptype_to_hash - get a hash type
+ * @ptype: the ptype value from the descriptor
+ *
+ * Returns a hash type to be used by skb_set_hash
+ **/
+static inline enum pkt_hash_types i40e_ptype_to_hash(u8 ptype)
+{
+ struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype);
+
+ if (!decoded.known)
+ return PKT_HASH_TYPE_NONE;
+
+ if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
+ decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4)
+ return PKT_HASH_TYPE_L4;
+ else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
+ decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3)
+ return PKT_HASH_TYPE_L3;
+ else
+ return PKT_HASH_TYPE_L2;
+}
+
+/**
* i40e_clean_rx_irq - Reclaim resources after receive completes
* @rx_ring: rx ring to clean
* @budget: how many cleans we're allowed
@@ -802,13 +846,13 @@
u16 i = rx_ring->next_to_clean;
union i40e_rx_desc *rx_desc;
u32 rx_error, rx_status;
+ u8 rx_ptype;
u64 qword;
- u16 rx_ptype;
rx_desc = I40E_RX_DESC(rx_ring, i);
qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
- rx_status = (qword & I40E_RXD_QW1_STATUS_MASK)
- >> I40E_RXD_QW1_STATUS_SHIFT;
+ rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >>
+ I40E_RXD_QW1_STATUS_SHIFT;
while (rx_status & (1 << I40E_RX_DESC_STATUS_DD_SHIFT)) {
union i40e_rx_desc *next_rxd;
@@ -912,7 +956,8 @@
goto next_desc;
}
- skb->rxhash = i40e_rx_hash(rx_ring, rx_desc);
+ skb_set_hash(skb, i40e_rx_hash(rx_ring, rx_desc),
+ i40e_ptype_to_hash(rx_ptype));
/* probably a little skewed due to removing CRC */
total_rx_bytes += skb->len;
total_rx_packets++;
@@ -1241,7 +1286,8 @@
struct i40e_tx_context_desc *context_desc;
int i = tx_ring->next_to_use;
- if (!cd_type_cmd_tso_mss && !cd_tunneling && !cd_l2tag2)
+ if ((cd_type_cmd_tso_mss == I40E_TX_DESC_DTYPE_CONTEXT) &&
+ !cd_tunneling && !cd_l2tag2)
return;
/* grab the next descriptor */
@@ -1352,9 +1398,23 @@
tx_bi = &tx_ring->tx_bi[i];
}
- tx_desc->cmd_type_offset_bsz =
- build_ctob(td_cmd, td_offset, size, td_tag) |
- cpu_to_le64((u64)I40E_TXD_CMD << I40E_TXD_QW1_CMD_SHIFT);
+ /* Place RS bit on last descriptor of any packet that spans across the
+ * 4th descriptor (WB_STRIDE aka 0x3) in a 64B cacheline.
+ */
+#define WB_STRIDE 0x3
+ if (((i & WB_STRIDE) != WB_STRIDE) &&
+ (first <= &tx_ring->tx_bi[i]) &&
+ (first >= &tx_ring->tx_bi[i & ~WB_STRIDE])) {
+ tx_desc->cmd_type_offset_bsz =
+ build_ctob(td_cmd, td_offset, size, td_tag) |
+ cpu_to_le64((u64)I40E_TX_DESC_CMD_EOP <<
+ I40E_TXD_QW1_CMD_SHIFT);
+ } else {
+ tx_desc->cmd_type_offset_bsz =
+ build_ctob(td_cmd, td_offset, size, td_tag) |
+ cpu_to_le64((u64)I40E_TXD_CMD <<
+ I40E_TXD_QW1_CMD_SHIFT);
+ }
netdev_tx_sent_queue(netdev_get_tx_queue(tx_ring->netdev,
tx_ring->queue_index),
@@ -1457,7 +1517,7 @@
/* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD,
* + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD,
- * + 2 desc gap to keep tail from touching head,
+ * + 4 desc gap to avoid the cache line where head is,
* + 1 desc for context descriptor,
* otherwise try next time
*/
@@ -1468,7 +1528,7 @@
count += skb_shinfo(skb)->nr_frags;
#endif
count += TXD_USE_COUNT(skb_headlen(skb));
- if (i40e_maybe_stop_tx(tx_ring, count + 3)) {
+ if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) {
tx_ring->tx_stats.tx_busy++;
return 0;
}
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index 3bffac0..4673b33 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -1,7 +1,7 @@
/*******************************************************************************
*
* Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -64,8 +64,6 @@
struct i40e_hw;
typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *);
-#define ETH_ALEN 6
-
/* Data type manipulation macros. */
#define I40E_DESC_UNUSED(R) \
@@ -90,6 +88,7 @@
I40E_DEBUG_FLOW = 0x00000200,
I40E_DEBUG_DCB = 0x00000400,
I40E_DEBUG_DIAG = 0x00000800,
+ I40E_DEBUG_FD = 0x00001000,
I40E_DEBUG_AQ_MESSAGE = 0x01000000,
I40E_DEBUG_AQ_DESCRIPTOR = 0x02000000,
@@ -466,6 +465,10 @@
union {
__le32 rss; /* RSS Hash */
__le32 fcoe_param; /* FCoE DDP Context id */
+ /* Flow director filter id in case of
+ * Programming status desc WB
+ */
+ __le32 fd_id;
} hi_dword;
} qword0;
struct {
@@ -706,7 +709,7 @@
enum i40e_rx_prog_status_desc_error_bits {
/* Note: These are predefined bit offsets */
I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT = 0,
- I40E_RX_PROG_STATUS_DESC_NO_FD_QUOTA_SHIFT = 1,
+ I40E_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT = 1,
I40E_RX_PROG_STATUS_DESC_FCOE_TBL_FULL_SHIFT = 2,
I40E_RX_PROG_STATUS_DESC_FCOE_CONFLICT_SHIFT = 3
};
@@ -1018,6 +1021,11 @@
u64 tx_size_big; /* ptc9522 */
u64 mac_short_packet_dropped; /* mspdc */
u64 checksum_error; /* xec */
+ /* EEE LPI */
+ bool tx_lpi_status;
+ bool rx_lpi_status;
+ u64 tx_lpi_count; /* etlpic */
+ u64 rx_lpi_count; /* erlpic */
};
/* Checksum and Shadow RAM pointers */
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index ff6529b..807807d 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -1,7 +1,7 @@
/*******************************************************************************
*
* Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -38,8 +38,6 @@
#include <linux/ipv6.h>
#include <net/ip6_checksum.h>
#include <net/udp.h>
-#include <linux/sctp.h>
-
#include "i40e_type.h"
#include "i40e_virtchnl.h"
@@ -164,15 +162,14 @@
/* Driver state. The order of these is important! */
enum i40evf_state_t {
__I40EVF_STARTUP, /* driver loaded, probe complete */
- __I40EVF_FAILED, /* PF communication failed. Fatal. */
__I40EVF_REMOVE, /* driver is being unloaded */
__I40EVF_INIT_VERSION_CHECK, /* aq msg sent, awaiting reply */
__I40EVF_INIT_GET_RESOURCES, /* aq msg sent, awaiting reply */
__I40EVF_INIT_SW, /* got resources, setting up structs */
+ __I40EVF_RESETTING, /* in reset */
/* Below here, watchdog is running */
__I40EVF_DOWN, /* ready, can be opened */
__I40EVF_TESTING, /* in ethtool self-test */
- __I40EVF_RESETTING, /* in reset */
__I40EVF_RUNNING, /* opened, working */
};
@@ -185,47 +182,25 @@
/* board specific private data structure */
struct i40evf_adapter {
struct timer_list watchdog_timer;
- struct vlan_group *vlgrp;
struct work_struct reset_task;
struct work_struct adminq_task;
struct delayed_work init_task;
struct i40e_q_vector *q_vector[MAX_MSIX_Q_VECTORS];
struct list_head vlan_filter_list;
- char name[MAX_MSIX_COUNT][IFNAMSIZ + 9];
-
- /* Interrupt Throttle Rate */
- u32 itr_setting;
- u16 eitr_low;
- u16 eitr_high;
+ char misc_vector_name[IFNAMSIZ + 9];
/* TX */
struct i40e_ring *tx_rings[I40E_MAX_VSI_QP];
- u64 restart_queue;
- u64 hw_csum_tx_good;
- u64 lsc_int;
- u64 hw_tso_ctxt;
- u64 hw_tso6_ctxt;
u32 tx_timeout_count;
struct list_head mac_filter_list;
-#ifdef DEBUG
- bool detect_tx_hung;
-#endif /* DEBUG */
/* RX */
struct i40e_ring *rx_rings[I40E_MAX_VSI_QP];
- int txd_count;
- int rxd_count;
u64 hw_csum_rx_error;
- u64 hw_rx_no_dma_resources;
- u64 hw_csum_rx_good;
- u64 non_eop_descs;
int num_msix_vectors;
struct msix_entry *msix_entries;
- u64 rx_hdr_split;
-
- u32 init_state;
- volatile unsigned long flags;
+ u32 flags;
#define I40EVF_FLAG_RX_CSUM_ENABLED (u32)(1)
#define I40EVF_FLAG_RX_1BUF_CAPABLE (u32)(1 << 1)
#define I40EVF_FLAG_RX_PS_CAPABLE (u32)(1 << 2)
@@ -234,6 +209,9 @@
#define I40EVF_FLAG_IMIR_ENABLED (u32)(1 << 5)
#define I40EVF_FLAG_MQ_CAPABLE (u32)(1 << 6)
#define I40EVF_FLAG_NEED_LINK_UPDATE (u32)(1 << 7)
+#define I40EVF_FLAG_PF_COMMS_FAILED (u32)(1 << 8)
+#define I40EVF_FLAG_RESET_PENDING (u32)(1 << 9)
+#define I40EVF_FLAG_RESET_NEEDED (u32)(1 << 10)
/* duplcates for common code */
#define I40E_FLAG_FDIR_ATR_ENABLED 0
#define I40E_FLAG_DCB_ENABLED 0
@@ -251,21 +229,19 @@
#define I40EVF_FLAG_AQ_CONFIGURE_QUEUES (u32)(1 << 6)
#define I40EVF_FLAG_AQ_MAP_VECTORS (u32)(1 << 7)
#define I40EVF_FLAG_AQ_HANDLE_RESET (u32)(1 << 8)
+
/* OS defined structs */
struct net_device *netdev;
struct pci_dev *pdev;
struct net_device_stats net_stats;
- /* structs defined in i40e_vf.h */
- struct i40e_hw hw;
+ struct i40e_hw hw; /* defined in i40e_type.h */
enum i40evf_state_t state;
volatile unsigned long crit_section;
- u64 tx_busy;
struct work_struct watchdog_task;
bool netdev_registered;
- bool dev_closed;
bool link_up;
enum i40e_virtchnl_ops current_op;
struct i40e_virtchnl_vf_resource *vf_res; /* incl. all VSIs */
@@ -276,11 +252,6 @@
u32 aq_wait_count;
};
-struct i40evf_info {
- enum i40e_mac_type mac;
- unsigned int flags;
-};
-
/* needed by i40evf_ethtool.c */
extern char i40evf_driver_name[];
@@ -315,6 +286,7 @@
void i40evf_del_vlans(struct i40evf_adapter *adapter);
void i40evf_set_promiscuous(struct i40evf_adapter *adapter, int flags);
void i40evf_request_stats(struct i40evf_adapter *adapter);
+void i40evf_request_reset(struct i40evf_adapter *adapter);
void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
enum i40e_virtchnl_ops v_opcode,
i40e_status v_retval, u8 *msg, u16 msglen);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index b0b1f4b..8b0db1c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -1,7 +1,7 @@
/*******************************************************************************
*
* Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -241,6 +241,7 @@
{
struct i40evf_adapter *adapter = netdev_priv(netdev);
u32 new_rx_count, new_tx_count;
+ int i;
if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
return -EINVAL;
@@ -256,12 +257,14 @@
new_rx_count = ALIGN(new_rx_count, I40EVF_REQ_DESCRIPTOR_MULTIPLE);
/* if nothing to do return success */
- if ((new_tx_count == adapter->txd_count) &&
- (new_rx_count == adapter->rxd_count))
+ if ((new_tx_count == adapter->tx_rings[0]->count) &&
+ (new_rx_count == adapter->rx_rings[0]->count))
return 0;
- adapter->txd_count = new_tx_count;
- adapter->rxd_count = new_rx_count;
+ for (i = 0; i < adapter->vsi_res->num_queue_pairs; i++) {
+ adapter->tx_rings[0]->count = new_tx_count;
+ adapter->rx_rings[0]->count = new_rx_count;
+ }
if (netif_running(netdev))
i40evf_reinit_locked(adapter);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index f5caf44..51c84c1 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -1,7 +1,7 @@
/*******************************************************************************
*
* Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -31,10 +31,10 @@
static const char i40evf_driver_string[] =
"Intel(R) XL710 X710 Virtual Function Network Driver";
-#define DRV_VERSION "0.9.11"
+#define DRV_VERSION "0.9.16"
const char i40evf_driver_version[] = DRV_VERSION;
static const char i40evf_copyright[] =
- "Copyright (c) 2013 Intel Corporation.";
+ "Copyright (c) 2013 - 2014 Intel Corporation.";
/* i40evf_pci_tbl - PCI Device ID Table
*
@@ -167,9 +167,11 @@
struct i40evf_adapter *adapter = netdev_priv(netdev);
adapter->tx_timeout_count++;
-
- /* Do the reset outside of interrupt context */
- schedule_work(&adapter->reset_task);
+ dev_info(&adapter->pdev->dev, "TX timeout detected.\n");
+ if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING)) {
+ adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
+ schedule_work(&adapter->reset_task);
+ }
}
/**
@@ -211,6 +213,9 @@
int i;
struct i40e_hw *hw = &adapter->hw;
+ if (!adapter->msix_entries)
+ return;
+
for (i = 1; i < adapter->num_msix_vectors; i++) {
wr32(hw, I40E_VFINT_DYN_CTLN1(i - 1), 0);
synchronize_irq(adapter->msix_entries[i].vector);
@@ -511,12 +516,14 @@
struct net_device *netdev = adapter->netdev;
int err;
- sprintf(adapter->name[0], "i40evf:mbx");
+ sprintf(adapter->misc_vector_name, "i40evf:mbx");
err = request_irq(adapter->msix_entries[0].vector,
- &i40evf_msix_aq, 0, adapter->name[0], netdev);
+ &i40evf_msix_aq, 0,
+ adapter->misc_vector_name, netdev);
if (err) {
dev_err(&adapter->pdev->dev,
- "request_irq for msix_aq failed: %d\n", err);
+ "request_irq for %s failed: %d\n",
+ adapter->misc_vector_name, err);
free_irq(adapter->msix_entries[0].vector, netdev);
}
return err;
@@ -963,16 +970,23 @@
struct net_device *netdev = adapter->netdev;
struct i40evf_mac_filter *f;
- /* remove all MAC filters from the VSI */
+ /* remove all MAC filters */
list_for_each_entry(f, &adapter->mac_filter_list, list) {
f->remove = true;
}
- adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER;
- /* disable receives */
- adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES;
- mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
- msleep(20);
-
+ /* remove all VLAN filters */
+ list_for_each_entry(f, &adapter->vlan_filter_list, list) {
+ f->remove = true;
+ }
+ if (!(adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) &&
+ adapter->state != __I40EVF_RESETTING) {
+ adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER;
+ adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER;
+ /* disable receives */
+ adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES;
+ mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
+ msleep(20);
+ }
netif_tx_disable(netdev);
netif_tx_stop_all_queues(netdev);
@@ -1124,8 +1138,8 @@
* than CPU's. So let's be conservative and only ask for
* (roughly) twice the number of vectors as there are CPU's.
*/
- v_budget = min(pairs, (int)(num_online_cpus() * 2)) + NONQ_VECS;
- v_budget = min(v_budget, (int)adapter->vf_res->max_vectors + 1);
+ v_budget = min_t(int, pairs, (int)(num_online_cpus() * 2)) + NONQ_VECS;
+ v_budget = min_t(int, v_budget, (int)adapter->vf_res->max_vectors);
/* A failure in MSI-X entry allocation isn't fatal, but it does
* mean we disable MSI-X capabilities of the adapter.
@@ -1291,19 +1305,47 @@
watchdog_task);
struct i40e_hw *hw = &adapter->hw;
- if (adapter->state < __I40EVF_DOWN)
- goto watchdog_done;
-
if (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section))
+ goto restart_watchdog;
+
+ if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) {
+ dev_info(&adapter->pdev->dev, "Checking for redemption\n");
+ if ((rd32(hw, I40E_VFGEN_RSTAT) & 0x3) == I40E_VFR_VFACTIVE) {
+ /* A chance for redemption! */
+ dev_err(&adapter->pdev->dev, "Hardware came out of reset. Attempting reinit.\n");
+ adapter->state = __I40EVF_STARTUP;
+ adapter->flags &= ~I40EVF_FLAG_PF_COMMS_FAILED;
+ schedule_delayed_work(&adapter->init_task, 10);
+ clear_bit(__I40EVF_IN_CRITICAL_TASK,
+ &adapter->crit_section);
+ /* Don't reschedule the watchdog, since we've restarted
+ * the init task. When init_task contacts the PF and
+ * gets everything set up again, it'll restart the
+ * watchdog for us. Down, boy. Sit. Stay. Woof.
+ */
+ return;
+ }
+ adapter->aq_pending = 0;
+ adapter->aq_required = 0;
+ adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN;
+ goto watchdog_done;
+ }
+
+ if ((adapter->state < __I40EVF_DOWN) ||
+ (adapter->flags & I40EVF_FLAG_RESET_PENDING))
goto watchdog_done;
- /* check for unannounced reset */
- if ((adapter->state != __I40EVF_RESETTING) &&
+ /* check for reset */
+ if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING) &&
(rd32(hw, I40E_VFGEN_RSTAT) & 0x3) != I40E_VFR_VFACTIVE) {
adapter->state = __I40EVF_RESETTING;
+ adapter->flags |= I40EVF_FLAG_RESET_PENDING;
+ dev_err(&adapter->pdev->dev, "Hardware reset detected.\n");
+ dev_info(&adapter->pdev->dev, "Scheduling reset task\n");
schedule_work(&adapter->reset_task);
- dev_info(&adapter->pdev->dev, "%s: hardware reset detected\n",
- __func__);
+ adapter->aq_pending = 0;
+ adapter->aq_required = 0;
+ adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN;
goto watchdog_done;
}
@@ -1358,16 +1400,25 @@
i40evf_irq_enable(adapter, true);
i40evf_fire_sw_int(adapter, 0xFF);
+
watchdog_done:
+ clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
+restart_watchdog:
if (adapter->aq_required)
mod_timer(&adapter->watchdog_timer,
jiffies + msecs_to_jiffies(20));
else
mod_timer(&adapter->watchdog_timer, jiffies + (HZ * 2));
- clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
schedule_work(&adapter->adminq_task);
}
+static int next_queue(struct i40evf_adapter *adapter, int j)
+{
+ j += 1;
+
+ return j >= adapter->vsi_res->num_queue_pairs ? 0 : j;
+}
+
/**
* i40evf_configure_rss - Prepare for RSS if used
* @adapter: board private structure
@@ -1398,19 +1449,19 @@
wr32(hw, I40E_VFQF_HENA(1), (u32)(hena >> 32));
/* Populate the LUT with max no. of queues in round robin fashion */
- for (i = 0, j = 0; i < I40E_VFQF_HLUT_MAX_INDEX; i++, j++) {
- if (j == adapter->vsi_res->num_queue_pairs)
- j = 0;
- /* lut = 4-byte sliding window of 4 lut entries */
- lut = (lut << 8) | (j &
- ((0x1 << 8) - 1));
- /* On i = 3, we have 4 entries in lut; write to the register */
- if ((i & 3) == 3)
- wr32(hw, I40E_VFQF_HLUT(i >> 2), lut);
+ j = adapter->vsi_res->num_queue_pairs;
+ for (i = 0; i <= I40E_VFQF_HLUT_MAX_INDEX; i++) {
+ lut = next_queue(adapter, j);
+ lut |= next_queue(adapter, j) << 8;
+ lut |= next_queue(adapter, j) << 16;
+ lut |= next_queue(adapter, j) << 24;
+ wr32(hw, I40E_VFQF_HLUT(i), lut);
}
i40e_flush(hw);
}
+#define I40EVF_RESET_WAIT_MS 100
+#define I40EVF_RESET_WAIT_COUNT 200
/**
* i40evf_reset_task - Call-back task to handle hardware reset
* @work: pointer to work_struct
@@ -1421,8 +1472,9 @@
**/
static void i40evf_reset_task(struct work_struct *work)
{
- struct i40evf_adapter *adapter =
- container_of(work, struct i40evf_adapter, reset_task);
+ struct i40evf_adapter *adapter = container_of(work,
+ struct i40evf_adapter,
+ reset_task);
struct i40e_hw *hw = &adapter->hw;
int i = 0, err;
uint32_t rstat_val;
@@ -1431,21 +1483,61 @@
&adapter->crit_section))
udelay(500);
- /* wait until the reset is complete */
- for (i = 0; i < 20; i++) {
+ if (adapter->flags & I40EVF_FLAG_RESET_NEEDED) {
+ dev_info(&adapter->pdev->dev, "Requesting reset from PF\n");
+ i40evf_request_reset(adapter);
+ }
+
+ /* poll until we see the reset actually happen */
+ for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) {
rstat_val = rd32(hw, I40E_VFGEN_RSTAT) &
I40E_VFGEN_RSTAT_VFR_STATE_MASK;
- if (rstat_val == I40E_VFR_COMPLETED)
+ if (rstat_val != I40E_VFR_VFACTIVE) {
+ dev_info(&adapter->pdev->dev, "Reset now occurring\n");
break;
- else
- mdelay(100);
+ } else {
+ msleep(I40EVF_RESET_WAIT_MS);
+ }
}
- if (i == 20) {
+ if (i == I40EVF_RESET_WAIT_COUNT) {
+ dev_err(&adapter->pdev->dev, "Reset was not detected\n");
+ adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
+ goto continue_reset; /* act like the reset happened */
+ }
+
+ /* wait until the reset is complete and the PF is responding to us */
+ for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) {
+ rstat_val = rd32(hw, I40E_VFGEN_RSTAT) &
+ I40E_VFGEN_RSTAT_VFR_STATE_MASK;
+ if (rstat_val == I40E_VFR_VFACTIVE) {
+ dev_info(&adapter->pdev->dev, "Reset is complete. Reinitializing.\n");
+ break;
+ } else {
+ msleep(I40EVF_RESET_WAIT_MS);
+ }
+ }
+ if (i == I40EVF_RESET_WAIT_COUNT) {
/* reset never finished */
- dev_info(&adapter->pdev->dev, "%s: reset never finished: %x\n",
- __func__, rstat_val);
- /* carry on anyway */
+ dev_err(&adapter->pdev->dev, "Reset never finished (%x). PF driver is dead, and so am I.\n",
+ rstat_val);
+ adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED;
+
+ if (netif_running(adapter->netdev))
+ i40evf_close(adapter->netdev);
+
+ i40evf_free_misc_irq(adapter);
+ i40evf_reset_interrupt_capability(adapter);
+ i40evf_free_queues(adapter);
+ kfree(adapter->vf_res);
+ i40evf_shutdown_adminq(hw);
+ adapter->netdev->flags &= ~IFF_UP;
+ clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
+ return; /* Do not attempt to reinit. It's dead, Jim. */
}
+
+continue_reset:
+ adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
+
i40evf_down(adapter);
adapter->state = __I40EVF_RESETTING;
@@ -1505,6 +1597,9 @@
i40e_status ret;
u16 pending;
+ if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED)
+ return;
+
event.msg_size = I40EVF_MAX_AQ_BUF_SIZE;
event.msg_buf = kzalloc(event.msg_size, GFP_KERNEL);
if (!event.msg_buf) {
@@ -1636,6 +1731,10 @@
struct i40evf_adapter *adapter = netdev_priv(netdev);
int err;
+ if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) {
+ dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n");
+ return -EIO;
+ }
if (adapter->state != __I40EVF_DOWN)
return -EBUSY;
@@ -1690,8 +1789,12 @@
{
struct i40evf_adapter *adapter = netdev_priv(netdev);
+ if (adapter->state <= __I40EVF_DOWN)
+ return 0;
+
/* signal that we are down to the interrupt handler */
adapter->state = __I40EVF_DOWN;
+
set_bit(__I40E_DOWN, &adapter->vsi.state);
i40evf_down(adapter);
@@ -1842,16 +1945,18 @@
switch (adapter->state) {
case __I40EVF_STARTUP:
/* driver loaded, probe complete */
+ adapter->flags &= ~I40EVF_FLAG_PF_COMMS_FAILED;
+ adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
err = i40e_set_mac_type(hw);
if (err) {
- dev_info(&pdev->dev, "%s: set_mac_type failed: %d\n",
- __func__, err);
+ dev_err(&pdev->dev, "Failed to set MAC type (%d)\n",
+ err);
goto err;
}
err = i40evf_check_reset_complete(hw);
if (err) {
- dev_info(&pdev->dev, "%s: device is still in reset (%d).\n",
- __func__, err);
+ dev_err(&pdev->dev, "Device is still in reset (%d)\n",
+ err);
goto err;
}
hw->aq.num_arq_entries = I40EVF_AQ_LEN;
@@ -1861,14 +1966,13 @@
err = i40evf_init_adminq(hw);
if (err) {
- dev_info(&pdev->dev, "%s: init_adminq failed: %d\n",
- __func__, err);
+ dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n",
+ err);
goto err;
}
err = i40evf_send_api_ver(adapter);
if (err) {
- dev_info(&pdev->dev, "%s: unable to send to PF (%d)\n",
- __func__, err);
+ dev_err(&pdev->dev, "Unable to send to PF (%d)\n", err);
i40evf_shutdown_adminq(hw);
goto err;
}
@@ -1876,19 +1980,21 @@
goto restart;
break;
case __I40EVF_INIT_VERSION_CHECK:
- if (!i40evf_asq_done(hw))
+ if (!i40evf_asq_done(hw)) {
+ dev_err(&pdev->dev, "Admin queue command never completed.\n");
goto err;
+ }
/* aq msg sent, awaiting reply */
err = i40evf_verify_api_ver(adapter);
if (err) {
- dev_err(&pdev->dev, "Unable to verify API version, error %d\n",
+ dev_err(&pdev->dev, "Unable to verify API version (%d)\n",
err);
goto err;
}
err = i40evf_send_vf_config_msg(adapter);
if (err) {
- dev_err(&pdev->dev, "Unable send config request, error %d\n",
+ dev_err(&pdev->dev, "Unable send config request (%d)\n",
err);
goto err;
}
@@ -1902,18 +2008,15 @@
(I40E_MAX_VF_VSI *
sizeof(struct i40e_virtchnl_vsi_resource));
adapter->vf_res = kzalloc(bufsz, GFP_KERNEL);
- if (!adapter->vf_res) {
- dev_err(&pdev->dev, "%s: unable to allocate memory\n",
- __func__);
+ if (!adapter->vf_res)
goto err;
- }
}
err = i40evf_get_vf_config(adapter);
if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK)
goto restart;
if (err) {
- dev_info(&pdev->dev, "%s: unable to get VF config (%d)\n",
- __func__, err);
+ dev_err(&pdev->dev, "Unable to get VF config (%d)\n",
+ err);
goto err_alloc;
}
adapter->state = __I40EVF_INIT_SW;
@@ -1927,25 +2030,23 @@
adapter->vsi_res = &adapter->vf_res->vsi_res[i];
}
if (!adapter->vsi_res) {
- dev_info(&pdev->dev, "%s: no LAN VSI found\n", __func__);
+ dev_err(&pdev->dev, "No LAN VSI found\n");
goto err_alloc;
}
adapter->flags |= I40EVF_FLAG_RX_CSUM_ENABLED;
- adapter->txd_count = I40EVF_DEFAULT_TXD;
- adapter->rxd_count = I40EVF_DEFAULT_RXD;
-
netdev->netdev_ops = &i40evf_netdev_ops;
i40evf_set_ethtool_ops(netdev);
netdev->watchdog_timeo = 5 * HZ;
-
- netdev->features |= NETIF_F_SG |
+ netdev->features |= NETIF_F_HIGHDMA |
+ NETIF_F_SG |
NETIF_F_IP_CSUM |
NETIF_F_SCTP_CSUM |
NETIF_F_IPV6_CSUM |
NETIF_F_TSO |
NETIF_F_TSO6 |
+ NETIF_F_RXCSUM |
NETIF_F_GRO;
if (adapter->vf_res->vf_offload_flags
@@ -1956,11 +2057,13 @@
NETIF_F_HW_VLAN_CTAG_FILTER;
}
- /* The HW MAC address was set and/or determined in sw_init */
+ /* copy netdev features into list of user selectable features */
+ netdev->hw_features |= netdev->features;
+ netdev->hw_features &= ~NETIF_F_RXCSUM;
+
if (!is_valid_ether_addr(adapter->hw.mac.addr)) {
- dev_info(&pdev->dev,
- "Invalid MAC address %pMAC, using random\n",
- adapter->hw.mac.addr);
+ dev_info(&pdev->dev, "Invalid MAC address %pMAC, using random\n",
+ adapter->hw.mac.addr);
random_ether_addr(adapter->hw.mac.addr);
}
memcpy(netdev->dev_addr, adapter->hw.mac.addr, netdev->addr_len);
@@ -1994,8 +2097,6 @@
netif_carrier_off(netdev);
- strcpy(netdev->name, "eth%d");
-
adapter->vsi.id = adapter->vsi_res->vsi_id;
adapter->vsi.seid = adapter->vsi_res->vsi_id; /* dummy */
adapter->vsi.back = adapter;
@@ -2005,9 +2106,11 @@
adapter->vsi.tx_itr_setting = I40E_ITR_DYNAMIC;
adapter->vsi.netdev = adapter->netdev;
- err = register_netdev(netdev);
- if (err)
- goto err_register;
+ if (!adapter->netdev_registered) {
+ err = register_netdev(netdev);
+ if (err)
+ goto err_register;
+ }
adapter->netdev_registered = true;
@@ -2031,7 +2134,6 @@
i40evf_free_misc_irq(adapter);
err_sw_init:
i40evf_reset_interrupt_capability(adapter);
- adapter->state = __I40EVF_FAILED;
err_alloc:
kfree(adapter->vf_res);
adapter->vf_res = NULL;
@@ -2039,9 +2141,7 @@
/* Things went into the weeds, so try again later */
if (++adapter->aq_wait_count > I40EVF_AQ_MAX_ERR) {
dev_err(&pdev->dev, "Failed to communicate with PF; giving up.\n");
- if (hw->aq.asq.count)
- i40evf_shutdown_adminq(hw); /* ignore error */
- adapter->state = __I40EVF_FAILED;
+ adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED;
return; /* do not reschedule */
}
schedule_delayed_work(&adapter->init_task, HZ * 3);
@@ -2084,25 +2184,18 @@
struct net_device *netdev;
struct i40evf_adapter *adapter = NULL;
struct i40e_hw *hw = NULL;
- int err, pci_using_dac;
+ int err;
err = pci_enable_device(pdev);
if (err)
return err;
- if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64))) {
- pci_using_dac = true;
- /* coherent mask for the same size will always succeed if
- * dma_set_mask does
- */
- dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
- } else if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) {
- pci_using_dac = false;
- dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
- } else {
- dev_err(&pdev->dev, "%s: DMA configuration failed: %d\n",
- __func__, err);
- err = -EIO;
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+ if (err)
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+ if (err) {
+ dev_err(&pdev->dev,
+ "DMA configuration failed: 0x%x\n", err);
goto err_dma;
}
@@ -2128,8 +2221,6 @@
pci_set_drvdata(pdev, netdev);
adapter = netdev_priv(netdev);
- if (pci_using_dac)
- netdev->features |= NETIF_F_HIGHDMA;
adapter->netdev = netdev;
adapter->pdev = pdev;
@@ -2271,6 +2362,7 @@
struct i40e_hw *hw = &adapter->hw;
cancel_delayed_work_sync(&adapter->init_task);
+ cancel_work_sync(&adapter->reset_task);
if (adapter->netdev_registered) {
unregister_netdev(netdev);
@@ -2278,17 +2370,15 @@
}
adapter->state = __I40EVF_REMOVE;
- if (adapter->num_msix_vectors) {
+ if (adapter->msix_entries) {
i40evf_misc_irq_disable(adapter);
- del_timer_sync(&adapter->watchdog_timer);
-
- flush_scheduled_work();
-
i40evf_free_misc_irq(adapter);
-
i40evf_reset_interrupt_capability(adapter);
}
+ del_timer_sync(&adapter->watchdog_timer);
+ flush_scheduled_work();
+
if (hw->aq.asq.count)
i40evf_shutdown_adminq(hw);
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index e6978d7..e294f01 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -1,7 +1,7 @@
/*******************************************************************************
*
* Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -43,6 +43,9 @@
struct i40e_hw *hw = &adapter->hw;
i40e_status err;
+ if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED)
+ return 0; /* nothing to see here, move along */
+
err = i40e_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL);
if (err)
dev_err(&adapter->pdev->dev, "Unable to send opcode %d to PF, error %d, aq status %d\n",
@@ -651,6 +654,18 @@
/* if the request failed, don't lock out others */
adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN;
}
+/**
+ * i40evf_request_reset
+ * @adapter: adapter structure
+ *
+ * Request that the PF reset this VF. No response is expected.
+ **/
+void i40evf_request_reset(struct i40evf_adapter *adapter)
+{
+ /* Don't check CURRENT_OP - this is always higher priority */
+ i40evf_send_pf_msg(adapter, I40E_VIRTCHNL_OP_RESET_VF, NULL, 0);
+ adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN;
+}
/**
* i40evf_virtchnl_completion
@@ -689,10 +704,12 @@
}
break;
case I40E_VIRTCHNL_EVENT_RESET_IMPENDING:
- adapter->state = __I40EVF_RESETTING;
- schedule_work(&adapter->reset_task);
- dev_info(&adapter->pdev->dev,
- "%s: hardware reset pending\n", __func__);
+ dev_info(&adapter->pdev->dev, "PF reset warning received\n");
+ if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING)) {
+ adapter->flags |= I40EVF_FLAG_RESET_PENDING;
+ dev_info(&adapter->pdev->dev, "Scheduling reset task\n");
+ schedule_work(&adapter->reset_task);
+ }
break;
default:
dev_err(&adapter->pdev->dev,
diff --git a/drivers/net/ethernet/intel/igb/Makefile b/drivers/net/ethernet/intel/igb/Makefile
index f19700e..5bcb2de 100644
--- a/drivers/net/ethernet/intel/igb/Makefile
+++ b/drivers/net/ethernet/intel/igb/Makefile
@@ -1,7 +1,7 @@
################################################################################
#
# Intel 82575 PCI-Express Ethernet Linux driver
-# Copyright(c) 1999 - 2013 Intel Corporation.
+# Copyright(c) 1999 - 2014 Intel Corporation.
#
# This program is free software; you can redistribute it and/or modify it
# under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
# more details.
#
# You should have received a copy of the GNU General Public License along with
-# this program; if not, write to the Free Software Foundation, Inc.,
-# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+# this program; if not, see <http://www.gnu.org/licenses/>.
#
# The full GNU General Public License is included in this distribution in
# the file called "COPYING".
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 06df692..fa36fe1 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
@@ -77,8 +76,6 @@
static const u16 e1000_82580_rxpbs_table[] =
{ 36, 72, 144, 1, 2, 4, 8, 16,
35, 70, 140 };
-#define E1000_82580_RXPBS_TABLE_SIZE \
- (sizeof(e1000_82580_rxpbs_table)/sizeof(u16))
/**
* igb_sgmii_uses_mdio_82575 - Determine if I2C pins are for external MDIO
@@ -2308,7 +2305,7 @@
{
u16 ret_val = 0;
- if (data < E1000_82580_RXPBS_TABLE_SIZE)
+ if (data < ARRAY_SIZE(e1000_82580_rxpbs_table))
ret_val = e1000_82580_rxpbs_table[data];
return ret_val;
@@ -2714,13 +2711,14 @@
E1000_EMC_DIODE3_THERM_LIMIT
};
+#ifdef CONFIG_IGB_HWMON
/**
* igb_get_thermal_sensor_data_generic - Gathers thermal sensor data
* @hw: pointer to hardware structure
*
* Updates the temperatures in mac.thermal_sensor_data
**/
-s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw)
+static s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw)
{
s32 status = E1000_SUCCESS;
u16 ets_offset;
@@ -2774,7 +2772,7 @@
* Sets the thermal sensor thresholds according to the NVM map
* and save off the threshold and location values into mac.thermal_sensor_data
**/
-s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *hw)
+static s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *hw)
{
s32 status = E1000_SUCCESS;
u16 ets_offset;
@@ -2836,6 +2834,7 @@
return status;
}
+#endif
static struct e1000_mac_operations e1000_mac_ops_82575 = {
.init_hw = igb_init_hw_82575,
.check_for_link = igb_check_for_link_82575,
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.h b/drivers/net/ethernet/intel/igb/e1000_82575.h
index 8c24377..09d78be 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.h
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
@@ -231,6 +230,10 @@
#define E1000_VMOLR_STRVLAN 0x40000000 /* Vlan stripping enable */
#define E1000_VMOLR_STRCRC 0x80000000 /* CRC stripping enable */
+#define E1000_DVMOLR_HIDEVLAN 0x20000000 /* Hide vlan enable */
+#define E1000_DVMOLR_STRVLAN 0x40000000 /* Vlan stripping enable */
+#define E1000_DVMOLR_STRCRC 0x80000000 /* CRC stripping enable */
+
#define E1000_VLVF_ARRAY_SIZE 32
#define E1000_VLVF_VLANID_MASK 0x00000FFF
#define E1000_VLVF_POOLSEL_SHIFT 12
@@ -266,8 +269,7 @@
s32 igb_read_emi_reg(struct e1000_hw *, u16 addr, u16 *data);
s32 igb_set_eee_i350(struct e1000_hw *);
s32 igb_set_eee_i354(struct e1000_hw *);
-s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *);
-s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw);
+s32 igb_get_eee_status_i354(struct e1000_hw *hw, bool *status);
#define E1000_I2C_THERMAL_SENSOR_ADDR 0xF8
#define E1000_EMC_INTERNAL_DATA 0x00
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 0571b97..b05bf92 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
@@ -44,7 +43,11 @@
#define E1000_WUFC_BC 0x00000010 /* Broadcast Wakeup Enable */
/* Extended Device Control */
+#define E1000_CTRL_EXT_SDP2_DATA 0x00000040 /* Value of SW Defineable Pin 2 */
#define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* Value of SW Defineable Pin 3 */
+#define E1000_CTRL_EXT_SDP2_DIR 0x00000400 /* SDP2 Data direction */
+#define E1000_CTRL_EXT_SDP3_DIR 0x00000800 /* SDP3 Data direction */
+
/* Physical Func Reset Done Indication */
#define E1000_CTRL_EXT_PFRSTD 0x00004000
#define E1000_CTRL_EXT_LINK_MODE_MASK 0x00C00000
@@ -191,7 +194,8 @@
/* enable link status from external LINK_0 and LINK_1 pins */
#define E1000_CTRL_SWDPIN0 0x00040000 /* SWDPIN 0 value */
#define E1000_CTRL_SWDPIN1 0x00080000 /* SWDPIN 1 value */
-#define E1000_CTRL_SWDPIO0 0x00400000 /* SWDPIN 0 Input or output */
+#define E1000_CTRL_SDP0_DIR 0x00400000 /* SDP0 Data direction */
+#define E1000_CTRL_SDP1_DIR 0x00800000 /* SDP1 Data direction */
#define E1000_CTRL_RST 0x04000000 /* Global reset */
#define E1000_CTRL_RFCE 0x08000000 /* Receive Flow Control enable */
#define E1000_CTRL_TFCE 0x10000000 /* Transmit flow control enable */
@@ -529,8 +533,67 @@
#define E1000_TIMINCA_16NS_SHIFT 24
-#define E1000_TSICR_TXTS 0x00000002
-#define E1000_TSIM_TXTS 0x00000002
+/* Time Sync Interrupt Cause/Mask Register Bits */
+
+#define TSINTR_SYS_WRAP (1 << 0) /* SYSTIM Wrap around. */
+#define TSINTR_TXTS (1 << 1) /* Transmit Timestamp. */
+#define TSINTR_RXTS (1 << 2) /* Receive Timestamp. */
+#define TSINTR_TT0 (1 << 3) /* Target Time 0 Trigger. */
+#define TSINTR_TT1 (1 << 4) /* Target Time 1 Trigger. */
+#define TSINTR_AUTT0 (1 << 5) /* Auxiliary Timestamp 0 Taken. */
+#define TSINTR_AUTT1 (1 << 6) /* Auxiliary Timestamp 1 Taken. */
+#define TSINTR_TADJ (1 << 7) /* Time Adjust Done. */
+
+#define TSYNC_INTERRUPTS TSINTR_TXTS
+#define E1000_TSICR_TXTS TSINTR_TXTS
+
+/* TSAUXC Configuration Bits */
+#define TSAUXC_EN_TT0 (1 << 0) /* Enable target time 0. */
+#define TSAUXC_EN_TT1 (1 << 1) /* Enable target time 1. */
+#define TSAUXC_EN_CLK0 (1 << 2) /* Enable Configurable Frequency Clock 0. */
+#define TSAUXC_SAMP_AUT0 (1 << 3) /* Latch SYSTIML/H into AUXSTMPL/0. */
+#define TSAUXC_ST0 (1 << 4) /* Start Clock 0 Toggle on Target Time 0. */
+#define TSAUXC_EN_CLK1 (1 << 5) /* Enable Configurable Frequency Clock 1. */
+#define TSAUXC_SAMP_AUT1 (1 << 6) /* Latch SYSTIML/H into AUXSTMPL/1. */
+#define TSAUXC_ST1 (1 << 7) /* Start Clock 1 Toggle on Target Time 1. */
+#define TSAUXC_EN_TS0 (1 << 8) /* Enable hardware timestamp 0. */
+#define TSAUXC_AUTT0 (1 << 9) /* Auxiliary Timestamp Taken. */
+#define TSAUXC_EN_TS1 (1 << 10) /* Enable hardware timestamp 0. */
+#define TSAUXC_AUTT1 (1 << 11) /* Auxiliary Timestamp Taken. */
+#define TSAUXC_PLSG (1 << 17) /* Generate a pulse. */
+#define TSAUXC_DISABLE (1 << 31) /* Disable SYSTIM Count Operation. */
+
+/* SDP Configuration Bits */
+#define AUX0_SEL_SDP0 (0 << 0) /* Assign SDP0 to auxiliary time stamp 0. */
+#define AUX0_SEL_SDP1 (1 << 0) /* Assign SDP1 to auxiliary time stamp 0. */
+#define AUX0_SEL_SDP2 (2 << 0) /* Assign SDP2 to auxiliary time stamp 0. */
+#define AUX0_SEL_SDP3 (3 << 0) /* Assign SDP3 to auxiliary time stamp 0. */
+#define AUX0_TS_SDP_EN (1 << 2) /* Enable auxiliary time stamp trigger 0. */
+#define AUX1_SEL_SDP0 (0 << 3) /* Assign SDP0 to auxiliary time stamp 1. */
+#define AUX1_SEL_SDP1 (1 << 3) /* Assign SDP1 to auxiliary time stamp 1. */
+#define AUX1_SEL_SDP2 (2 << 3) /* Assign SDP2 to auxiliary time stamp 1. */
+#define AUX1_SEL_SDP3 (3 << 3) /* Assign SDP3 to auxiliary time stamp 1. */
+#define AUX1_TS_SDP_EN (1 << 5) /* Enable auxiliary time stamp trigger 1. */
+#define TS_SDP0_SEL_TT0 (0 << 6) /* Target time 0 is output on SDP0. */
+#define TS_SDP0_SEL_TT1 (1 << 6) /* Target time 1 is output on SDP0. */
+#define TS_SDP0_SEL_FC0 (2 << 6) /* Freq clock 0 is output on SDP0. */
+#define TS_SDP0_SEL_FC1 (3 << 6) /* Freq clock 1 is output on SDP0. */
+#define TS_SDP0_EN (1 << 8) /* SDP0 is assigned to Tsync. */
+#define TS_SDP1_SEL_TT0 (0 << 9) /* Target time 0 is output on SDP1. */
+#define TS_SDP1_SEL_TT1 (1 << 9) /* Target time 1 is output on SDP1. */
+#define TS_SDP1_SEL_FC0 (2 << 9) /* Freq clock 0 is output on SDP1. */
+#define TS_SDP1_SEL_FC1 (3 << 9) /* Freq clock 1 is output on SDP1. */
+#define TS_SDP1_EN (1 << 11) /* SDP1 is assigned to Tsync. */
+#define TS_SDP2_SEL_TT0 (0 << 12) /* Target time 0 is output on SDP2. */
+#define TS_SDP2_SEL_TT1 (1 << 12) /* Target time 1 is output on SDP2. */
+#define TS_SDP2_SEL_FC0 (2 << 12) /* Freq clock 0 is output on SDP2. */
+#define TS_SDP2_SEL_FC1 (3 << 12) /* Freq clock 1 is output on SDP2. */
+#define TS_SDP2_EN (1 << 14) /* SDP2 is assigned to Tsync. */
+#define TS_SDP3_SEL_TT0 (0 << 15) /* Target time 0 is output on SDP3. */
+#define TS_SDP3_SEL_TT1 (1 << 15) /* Target time 1 is output on SDP3. */
+#define TS_SDP3_SEL_FC0 (2 << 15) /* Freq clock 0 is output on SDP3. */
+#define TS_SDP3_SEL_FC1 (3 << 15) /* Freq clock 1 is output on SDP3. */
+#define TS_SDP3_EN (1 << 17) /* SDP3 is assigned to Tsync. */
#define E1000_MDICNFG_EXT_MDIO 0x80000000 /* MDI ext/int destination */
#define E1000_MDICNFG_COM_MDIO 0x40000000 /* MDI shared w/ lan 0 */
diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h
index ab99e2b..10741d1 100644
--- a/drivers/net/ethernet/intel/igb/e1000_hw.h
+++ b/drivers/net/ethernet/intel/igb/e1000_hw.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c
index 0c03933..db96339 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.c
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
@@ -35,6 +34,8 @@
#include "e1000_hw.h"
#include "e1000_i210.h"
+static s32 igb_update_flash_i210(struct e1000_hw *hw);
+
/**
* igb_get_hw_semaphore_i210 - Acquire hardware semaphore
* @hw: pointer to the HW structure
@@ -111,7 +112,7 @@
* Return successful if access grant bit set, else clear the request for
* EEPROM access and return -E1000_ERR_NVM (-1).
**/
-s32 igb_acquire_nvm_i210(struct e1000_hw *hw)
+static s32 igb_acquire_nvm_i210(struct e1000_hw *hw)
{
return igb_acquire_swfw_sync_i210(hw, E1000_SWFW_EEP_SM);
}
@@ -123,7 +124,7 @@
* Stop any current commands to the EEPROM and clear the EEPROM request bit,
* then release the semaphores acquired.
**/
-void igb_release_nvm_i210(struct e1000_hw *hw)
+static void igb_release_nvm_i210(struct e1000_hw *hw)
{
igb_release_swfw_sync_i210(hw, E1000_SWFW_EEP_SM);
}
@@ -206,8 +207,8 @@
* Reads a 16 bit word from the Shadow Ram using the EERD register.
* Uses necessary synchronization semaphores.
**/
-s32 igb_read_nvm_srrd_i210(struct e1000_hw *hw, u16 offset, u16 words,
- u16 *data)
+static s32 igb_read_nvm_srrd_i210(struct e1000_hw *hw, u16 offset, u16 words,
+ u16 *data)
{
s32 status = E1000_SUCCESS;
u16 i, count;
@@ -306,8 +307,8 @@
* If error code is returned, data and Shadow RAM may be inconsistent - buffer
* partially written.
**/
-s32 igb_write_nvm_srwr_i210(struct e1000_hw *hw, u16 offset, u16 words,
- u16 *data)
+static s32 igb_write_nvm_srwr_i210(struct e1000_hw *hw, u16 offset, u16 words,
+ u16 *data)
{
s32 status = E1000_SUCCESS;
u16 i, count;
@@ -555,7 +556,7 @@
* Calculates the EEPROM checksum by reading/adding each word of the EEPROM
* and then verifies that the sum of the EEPROM is equal to 0xBABA.
**/
-s32 igb_validate_nvm_checksum_i210(struct e1000_hw *hw)
+static s32 igb_validate_nvm_checksum_i210(struct e1000_hw *hw)
{
s32 status = E1000_SUCCESS;
s32 (*read_op_ptr)(struct e1000_hw *, u16, u16, u16 *);
@@ -590,7 +591,7 @@
* up to the checksum. Then calculates the EEPROM checksum and writes the
* value to the EEPROM. Next commit EEPROM data onto the Flash.
**/
-s32 igb_update_nvm_checksum_i210(struct e1000_hw *hw)
+static s32 igb_update_nvm_checksum_i210(struct e1000_hw *hw)
{
s32 ret_val = E1000_SUCCESS;
u16 checksum = 0;
@@ -684,7 +685,7 @@
* @hw: pointer to the HW structure
*
**/
-s32 igb_update_flash_i210(struct e1000_hw *hw)
+static s32 igb_update_flash_i210(struct e1000_hw *hw)
{
s32 ret_val = E1000_SUCCESS;
u32 flup;
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.h b/drivers/net/ethernet/intel/igb/e1000_i210.h
index 2d91371..907fe99 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.h
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
@@ -28,17 +27,8 @@
#ifndef _E1000_I210_H_
#define _E1000_I210_H_
-s32 igb_update_flash_i210(struct e1000_hw *hw);
-s32 igb_update_nvm_checksum_i210(struct e1000_hw *hw);
-s32 igb_validate_nvm_checksum_i210(struct e1000_hw *hw);
-s32 igb_write_nvm_srwr_i210(struct e1000_hw *hw, u16 offset, u16 words,
- u16 *data);
-s32 igb_read_nvm_srrd_i210(struct e1000_hw *hw, u16 offset, u16 words,
- u16 *data);
s32 igb_acquire_swfw_sync_i210(struct e1000_hw *hw, u16 mask);
void igb_release_swfw_sync_i210(struct e1000_hw *hw, u16 mask);
-s32 igb_acquire_nvm_i210(struct e1000_hw *hw);
-void igb_release_nvm_i210(struct e1000_hw *hw);
s32 igb_valid_led_default_i210(struct e1000_hw *hw, u16 *data);
s32 igb_read_invm_version(struct e1000_hw *hw,
struct e1000_fw_version *invm_ver);
diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c
index 298f0ed..5910a93 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mac.c
+++ b/drivers/net/ethernet/intel/igb/e1000_mac.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.h b/drivers/net/ethernet/intel/igb/e1000_mac.h
index e4cbe8e..99299ba 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mac.h
+++ b/drivers/net/ethernet/intel/igb/e1000_mac.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.c b/drivers/net/ethernet/intel/igb/e1000_mbx.c
index dac1447..d5b1217 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mbx.c
+++ b/drivers/net/ethernet/intel/igb/e1000_mbx.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.h b/drivers/net/ethernet/intel/igb/e1000_mbx.h
index de9bba4..f52f551 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mbx.h
+++ b/drivers/net/ethernet/intel/igb/e1000_mbx.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.c b/drivers/net/ethernet/intel/igb/e1000_nvm.c
index a7db7f3..9abf829 100644
--- a/drivers/net/ethernet/intel/igb/e1000_nvm.c
+++ b/drivers/net/ethernet/intel/igb/e1000_nvm.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.h b/drivers/net/ethernet/intel/igb/e1000_nvm.h
index 433b741..5b10117 100644
--- a/drivers/net/ethernet/intel/igb/e1000_nvm.h
+++ b/drivers/net/ethernet/intel/igb/e1000_nvm.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index ad2b74d..4009bba 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
@@ -394,77 +393,6 @@
}
/**
- * e1000_write_sfp_data_byte - Writes SFP module data.
- * @hw: pointer to the HW structure
- * @offset: byte location offset to write to
- * @data: data to write
- *
- * Writes one byte to SFP module data stored
- * in SFP resided EEPROM memory or SFP diagnostic area.
- * Function should be called with
- * E1000_I2CCMD_SFP_DATA_ADDR(<byte offset>) for SFP module database access
- * E1000_I2CCMD_SFP_DIAG_ADDR(<byte offset>) for SFP diagnostics parameters
- * access
- **/
-s32 e1000_write_sfp_data_byte(struct e1000_hw *hw, u16 offset, u8 data)
-{
- u32 i = 0;
- u32 i2ccmd = 0;
- u32 data_local = 0;
-
- if (offset > E1000_I2CCMD_SFP_DIAG_ADDR(255)) {
- hw_dbg("I2CCMD command address exceeds upper limit\n");
- return -E1000_ERR_PHY;
- }
- /* The programming interface is 16 bits wide
- * so we need to read the whole word first
- * then update appropriate byte lane and write
- * the updated word back.
- */
- /* Set up Op-code, EEPROM Address,in the I2CCMD
- * register. The MAC will take care of interfacing
- * with an EEPROM to write the data given.
- */
- i2ccmd = ((offset << E1000_I2CCMD_REG_ADDR_SHIFT) |
- E1000_I2CCMD_OPCODE_READ);
- /* Set a command to read single word */
- wr32(E1000_I2CCMD, i2ccmd);
- for (i = 0; i < E1000_I2CCMD_PHY_TIMEOUT; i++) {
- udelay(50);
- /* Poll the ready bit to see if lastly
- * launched I2C operation completed
- */
- i2ccmd = rd32(E1000_I2CCMD);
- if (i2ccmd & E1000_I2CCMD_READY) {
- /* Check if this is READ or WRITE phase */
- if ((i2ccmd & E1000_I2CCMD_OPCODE_READ) ==
- E1000_I2CCMD_OPCODE_READ) {
- /* Write the selected byte
- * lane and update whole word
- */
- data_local = i2ccmd & 0xFF00;
- data_local |= data;
- i2ccmd = ((offset <<
- E1000_I2CCMD_REG_ADDR_SHIFT) |
- E1000_I2CCMD_OPCODE_WRITE | data_local);
- wr32(E1000_I2CCMD, i2ccmd);
- } else {
- break;
- }
- }
- }
- if (!(i2ccmd & E1000_I2CCMD_READY)) {
- hw_dbg("I2CCMD Write did not complete\n");
- return -E1000_ERR_PHY;
- }
- if (i2ccmd & E1000_I2CCMD_ERROR) {
- hw_dbg("I2CCMD Error bit set\n");
- return -E1000_ERR_PHY;
- }
- return 0;
-}
-
-/**
* igb_read_phy_reg_igp - Read igp PHY register
* @hw: pointer to the HW structure
* @offset: register offset to be read
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.h b/drivers/net/ethernet/intel/igb/e1000_phy.h
index 6a0873f..4c2c36c 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.h
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
@@ -70,7 +69,6 @@
s32 igb_read_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 *data);
s32 igb_write_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 data);
s32 igb_read_sfp_data_byte(struct e1000_hw *hw, u16 offset, u8 *data);
-s32 e1000_write_sfp_data_byte(struct e1000_hw *hw, u16 offset, u8 data);
s32 igb_copper_link_setup_82580(struct e1000_hw *hw);
s32 igb_get_phy_info_82580(struct e1000_hw *hw);
s32 igb_phy_force_speed_duplex_82580(struct e1000_hw *hw);
diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h
index 82632c6..bdb246e 100644
--- a/drivers/net/ethernet/intel/igb/e1000_regs.h
+++ b/drivers/net/ethernet/intel/igb/e1000_regs.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
@@ -41,6 +40,7 @@
#define E1000_FCT 0x00030 /* Flow Control Type - RW */
#define E1000_CONNSW 0x00034 /* Copper/Fiber switch control - RW */
#define E1000_VET 0x00038 /* VLAN Ether Type - RW */
+#define E1000_TSSDP 0x0003C /* Time Sync SDP Configuration Register - RW */
#define E1000_ICR 0x000C0 /* Interrupt Cause Read - R/clr */
#define E1000_ITR 0x000C4 /* Interrupt Throttling Rate - RW */
#define E1000_ICS 0x000C8 /* Interrupt Cause Set - WO */
@@ -102,6 +102,14 @@
#define E1000_SYSTIMH 0x0B604 /* System time register High - RO */
#define E1000_TIMINCA 0x0B608 /* Increment attributes register - RW */
#define E1000_TSAUXC 0x0B640 /* Timesync Auxiliary Control register */
+#define E1000_TRGTTIML0 0x0B644 /* Target Time Register 0 Low - RW */
+#define E1000_TRGTTIMH0 0x0B648 /* Target Time Register 0 High - RW */
+#define E1000_TRGTTIML1 0x0B64C /* Target Time Register 1 Low - RW */
+#define E1000_TRGTTIMH1 0x0B650 /* Target Time Register 1 High - RW */
+#define E1000_AUXSTMPL0 0x0B65C /* Auxiliary Time Stamp 0 Register Low - RO */
+#define E1000_AUXSTMPH0 0x0B660 /* Auxiliary Time Stamp 0 Register High - RO */
+#define E1000_AUXSTMPL1 0x0B664 /* Auxiliary Time Stamp 1 Register Low - RO */
+#define E1000_AUXSTMPH1 0x0B668 /* Auxiliary Time Stamp 1 Register High - RO */
#define E1000_SYSTIMR 0x0B6F8 /* System time register Residue */
#define E1000_TSICR 0x0B66C /* Interrupt Cause Register */
#define E1000_TSIM 0x0B674 /* Interrupt Mask Register */
@@ -349,16 +357,30 @@
#define E1000_P2VMAILBOX(_n) (0x00C00 + (4 * (_n)))
#define E1000_VMBMEM(_n) (0x00800 + (64 * (_n)))
#define E1000_VMOLR(_n) (0x05AD0 + (4 * (_n)))
+#define E1000_DVMOLR(_n) (0x0C038 + (64 * (_n)))
#define E1000_VLVF(_n) (0x05D00 + (4 * (_n))) /* VLAN Virtual Machine
* Filter - RW */
#define E1000_VMVIR(_n) (0x03700 + (4 * (_n)))
-#define wr32(reg, value) (writel(value, hw->hw_addr + reg))
-#define rd32(reg) (readl(hw->hw_addr + reg))
+struct e1000_hw;
+
+u32 igb_rd32(struct e1000_hw *hw, u32 reg);
+
+/* write operations, indexed using DWORDS */
+#define wr32(reg, val) \
+do { \
+ u8 __iomem *hw_addr = ACCESS_ONCE((hw)->hw_addr); \
+ if (!E1000_REMOVED(hw_addr)) \
+ writel((val), &hw_addr[(reg)]); \
+} while (0)
+
+#define rd32(reg) (igb_rd32(hw, reg))
+
#define wrfl() ((void)rd32(E1000_STATUS))
#define array_wr32(reg, offset, value) \
- (writel(value, hw->hw_addr + reg + ((offset) << 2)))
+ wr32((reg) + ((offset) << 2), (value))
+
#define array_rd32(reg, offset) \
(readl(hw->hw_addr + reg + ((offset) << 2)))
@@ -397,4 +419,6 @@
#define E1000_INVM_DATA_REG(_n) (0x12120 + 4*(_n))
#define E1000_INVM_SIZE 64 /* Number of INVM Data Registers */
+#define E1000_REMOVED(h) unlikely(!(h))
+
#endif
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index ccf472f..7fbe1e9 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
@@ -42,6 +41,7 @@
#include <linux/i2c.h>
#include <linux/i2c-algo-bit.h>
#include <linux/pci.h>
+#include <linux/mdio.h>
struct igb_adapter;
@@ -434,6 +434,7 @@
struct delayed_work ptp_overflow_work;
struct work_struct ptp_tx_work;
struct sk_buff *ptp_tx_skb;
+ struct hwtstamp_config tstamp_config;
unsigned long ptp_tx_start;
unsigned long last_rx_ptp_check;
spinlock_t tmreg_lock;
@@ -456,6 +457,7 @@
unsigned long link_check_timeout;
int copper_tries;
struct e1000_info ei;
+ u16 eee_advert;
};
#define IGB_FLAG_HAS_MSI (1 << 0)
@@ -472,6 +474,7 @@
#define IGB_FLAG_MAS_CAPABLE (1 << 11)
#define IGB_FLAG_MAS_ENABLE (1 << 12)
#define IGB_FLAG_HAS_MSIX (1 << 13)
+#define IGB_FLAG_EEE (1 << 14)
/* Media Auto Sense */
#define IGB_MAS_ENABLE_0 0X0001
@@ -489,7 +492,8 @@
enum e1000_state_t {
__IGB_TESTING,
__IGB_RESETTING,
- __IGB_DOWN
+ __IGB_DOWN,
+ __IGB_PTP_TX_IN_PROGRESS,
};
enum igb_boards {
@@ -525,9 +529,7 @@
void igb_ptp_init(struct igb_adapter *adapter);
void igb_ptp_stop(struct igb_adapter *adapter);
void igb_ptp_reset(struct igb_adapter *adapter);
-void igb_ptp_tx_work(struct work_struct *work);
void igb_ptp_rx_hang(struct igb_adapter *adapter);
-void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter);
void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb);
void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, unsigned char *va,
struct sk_buff *skb);
@@ -545,8 +547,8 @@
rx_ring->last_rx_timestamp = jiffies;
}
-int igb_ptp_hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr,
- int cmd);
+int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
+int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
#ifdef CONFIG_IGB_HWMON
void igb_sysfs_exit(struct igb_adapter *adapter);
int igb_sysfs_init(struct igb_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 1df0237..e5570ac 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
@@ -2274,15 +2273,15 @@
ring = adapter->tx_ring[j];
do {
- start = u64_stats_fetch_begin_bh(&ring->tx_syncp);
+ start = u64_stats_fetch_begin_irq(&ring->tx_syncp);
data[i] = ring->tx_stats.packets;
data[i+1] = ring->tx_stats.bytes;
data[i+2] = ring->tx_stats.restart_queue;
- } while (u64_stats_fetch_retry_bh(&ring->tx_syncp, start));
+ } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start));
do {
- start = u64_stats_fetch_begin_bh(&ring->tx_syncp2);
+ start = u64_stats_fetch_begin_irq(&ring->tx_syncp2);
restart2 = ring->tx_stats.restart_queue2;
- } while (u64_stats_fetch_retry_bh(&ring->tx_syncp2, start));
+ } while (u64_stats_fetch_retry_irq(&ring->tx_syncp2, start));
data[i+2] += restart2;
i += IGB_TX_QUEUE_STATS_LEN;
@@ -2290,13 +2289,13 @@
for (j = 0; j < adapter->num_rx_queues; j++) {
ring = adapter->rx_ring[j];
do {
- start = u64_stats_fetch_begin_bh(&ring->rx_syncp);
+ start = u64_stats_fetch_begin_irq(&ring->rx_syncp);
data[i] = ring->rx_stats.packets;
data[i+1] = ring->rx_stats.bytes;
data[i+2] = ring->rx_stats.drops;
data[i+3] = ring->rx_stats.csum_err;
data[i+4] = ring->rx_stats.alloc_failed;
- } while (u64_stats_fetch_retry_bh(&ring->rx_syncp, start));
+ } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start));
i += IGB_RX_QUEUE_STATS_LEN;
}
spin_unlock(&adapter->stats64_lock);
@@ -2354,6 +2353,11 @@
{
struct igb_adapter *adapter = netdev_priv(dev);
+ if (adapter->ptp_clock)
+ info->phc_index = ptp_clock_index(adapter->ptp_clock);
+ else
+ info->phc_index = -1;
+
switch (adapter->hw.mac.type) {
case e1000_82575:
info->so_timestamping =
@@ -2375,11 +2379,6 @@
SOF_TIMESTAMPING_RX_HARDWARE |
SOF_TIMESTAMPING_RAW_HARDWARE;
- if (adapter->ptp_clock)
- info->phc_index = ptp_clock_index(adapter->ptp_clock);
- else
- info->phc_index = -1;
-
info->tx_types =
(1 << HWTSTAMP_TX_OFF) |
(1 << HWTSTAMP_TX_ON);
@@ -2588,7 +2587,7 @@
{
struct igb_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
- u32 ipcnfg, eeer, ret_val;
+ u32 ret_val;
u16 phy_data;
if ((hw->mac.type < e1000_i350) ||
@@ -2597,16 +2596,25 @@
edata->supported = (SUPPORTED_1000baseT_Full |
SUPPORTED_100baseT_Full);
+ if (!hw->dev_spec._82575.eee_disable)
+ edata->advertised =
+ mmd_eee_adv_to_ethtool_adv_t(adapter->eee_advert);
- ipcnfg = rd32(E1000_IPCNFG);
- eeer = rd32(E1000_EEER);
+ /* The IPCNFG and EEER registers are not supported on I354. */
+ if (hw->mac.type == e1000_i354) {
+ igb_get_eee_status_i354(hw, (bool *)&edata->eee_active);
+ } else {
+ u32 eeer;
- /* EEE status on negotiated link */
- if (ipcnfg & E1000_IPCNFG_EEE_1G_AN)
- edata->advertised = ADVERTISED_1000baseT_Full;
+ eeer = rd32(E1000_EEER);
- if (ipcnfg & E1000_IPCNFG_EEE_100M_AN)
- edata->advertised |= ADVERTISED_100baseT_Full;
+ /* EEE status on negotiated link */
+ if (eeer & E1000_EEER_EEE_NEG)
+ edata->eee_active = true;
+
+ if (eeer & E1000_EEER_TX_LPI_EN)
+ edata->tx_lpi_enabled = true;
+ }
/* EEE Link Partner Advertised */
switch (hw->mac.type) {
@@ -2617,8 +2625,8 @@
return -ENODATA;
edata->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(phy_data);
-
break;
+ case e1000_i354:
case e1000_i210:
case e1000_i211:
ret_val = igb_read_xmdio_reg(hw, E1000_EEE_LP_ADV_ADDR_I210,
@@ -2634,12 +2642,10 @@
break;
}
- if (eeer & E1000_EEER_EEE_NEG)
- edata->eee_active = true;
-
edata->eee_enabled = !hw->dev_spec._82575.eee_disable;
- if (eeer & E1000_EEER_TX_LPI_EN)
+ if ((hw->mac.type == e1000_i354) &&
+ (edata->eee_enabled))
edata->tx_lpi_enabled = true;
/* Report correct negotiated EEE status for devices that
@@ -2687,9 +2693,10 @@
return -EINVAL;
}
- if (eee_curr.advertised != edata->advertised) {
+ if (edata->advertised &
+ ~(ADVERTISE_100_FULL | ADVERTISE_1000_FULL)) {
dev_err(&adapter->pdev->dev,
- "Setting EEE Advertisement is not supported\n");
+ "EEE Advertisement supports only 100Tx and or 100T full duplex\n");
return -EINVAL;
}
@@ -2699,9 +2706,14 @@
return -EINVAL;
}
+ adapter->eee_advert = ethtool_adv_to_mmd_eee_adv_t(edata->advertised);
if (hw->dev_spec._82575.eee_disable != !edata->eee_enabled) {
hw->dev_spec._82575.eee_disable = !edata->eee_enabled;
- igb_set_eee_i350(hw);
+ adapter->flags |= IGB_FLAG_EEE;
+ if (hw->mac.type == e1000_i350)
+ igb_set_eee_i350(hw);
+ else
+ igb_set_eee_i354(hw);
/* reset link */
if (netif_running(netdev))
@@ -2779,9 +2791,11 @@
/* Read EEPROM block, SFF-8079/SFF-8472, word at a time */
for (i = 0; i < last_word - first_word + 1; i++) {
status = igb_read_phy_reg_i2c(hw, first_word + i, &dataword[i]);
- if (status != E1000_SUCCESS)
+ if (status != E1000_SUCCESS) {
/* Error occurred while reading module */
+ kfree(dataword);
return -EIO;
+ }
be16_to_cpus(&dataword[i]);
}
diff --git a/drivers/net/ethernet/intel/igb/igb_hwmon.c b/drivers/net/ethernet/intel/igb/igb_hwmon.c
index e0af5bc..8333f67 100644
--- a/drivers/net/ethernet/intel/igb/igb_hwmon.c
+++ b/drivers/net/ethernet/intel/igb/igb_hwmon.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 46d31a4..55fc559 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) Gigabit Ethernet Linux driver
- Copyright(c) 2007-2013 Intel Corporation.
+ Copyright(c) 2007-2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -13,8 +13,7 @@
more details.
You should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc.,
- 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ this program; if not, see <http://www.gnu.org/licenses/>.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
@@ -70,7 +69,7 @@
static const char igb_driver_string[] =
"Intel(R) Gigabit Ethernet Network Driver";
static const char igb_copyright[] =
- "Copyright (c) 2007-2013 Intel Corporation.";
+ "Copyright (c) 2007-2014 Intel Corporation.";
static const struct e1000_info *igb_info_tbl[] = {
[board_82575] = &e1000_82575_info,
@@ -752,6 +751,28 @@
}
}
+u32 igb_rd32(struct e1000_hw *hw, u32 reg)
+{
+ struct igb_adapter *igb = container_of(hw, struct igb_adapter, hw);
+ u8 __iomem *hw_addr = ACCESS_ONCE(hw->hw_addr);
+ u32 value = 0;
+
+ if (E1000_REMOVED(hw_addr))
+ return ~value;
+
+ value = readl(&hw_addr[reg]);
+
+ /* reads should not return all F's */
+ if (!(~value) && (!reg || !(~readl(hw_addr)))) {
+ struct net_device *netdev = igb->netdev;
+ hw->hw_addr = NULL;
+ netif_device_detach(netdev);
+ netdev_err(netdev, "PCIe link lost, device now detached\n");
+ }
+
+ return value;
+}
+
/**
* igb_write_ivar - configure ivar for given MSI-X vector
* @hw: pointer to the HW structure
@@ -1014,6 +1035,12 @@
{
struct igb_q_vector *q_vector = adapter->q_vector[v_idx];
+ /* Coming from igb_set_interrupt_capability, the vectors are not yet
+ * allocated. So, q_vector is NULL so we should stop here.
+ */
+ if (!q_vector)
+ return;
+
if (q_vector->tx.ring)
adapter->tx_ring[q_vector->tx.ring->queue_index] = NULL;
@@ -1111,16 +1138,18 @@
for (i = 0; i < numvecs; i++)
adapter->msix_entries[i].entry = i;
- err = pci_enable_msix(adapter->pdev,
- adapter->msix_entries,
- numvecs);
- if (err == 0)
+ err = pci_enable_msix_range(adapter->pdev,
+ adapter->msix_entries,
+ numvecs,
+ numvecs);
+ if (err > 0)
return;
igb_reset_interrupt_capability(adapter);
/* If we can't do MSI-X, try MSI */
msi_only:
+ adapter->flags &= ~IGB_FLAG_HAS_MSIX;
#ifdef CONFIG_PCI_IOV
/* disable SR-IOV for non MSI-X configurations */
if (adapter->vf_data) {
@@ -1726,6 +1755,10 @@
hw->mac.get_link_status = 1;
schedule_work(&adapter->watchdog_task);
+ if ((adapter->flags & IGB_FLAG_EEE) &&
+ (!hw->dev_spec._82575.eee_disable))
+ adapter->eee_advert = MDIO_EEE_100TX | MDIO_EEE_1000T;
+
return 0;
}
@@ -1974,6 +2007,21 @@
}
}
#endif
+ /* Re-establish EEE setting */
+ if (hw->phy.media_type == e1000_media_type_copper) {
+ switch (mac->type) {
+ case e1000_i350:
+ case e1000_i210:
+ case e1000_i211:
+ igb_set_eee_i350(hw);
+ break;
+ case e1000_i354:
+ igb_set_eee_i354(hw);
+ break;
+ default:
+ break;
+ }
+ }
if (!netif_running(adapter->netdev))
igb_power_down_link(adapter);
@@ -2560,23 +2608,36 @@
(adapter->flags & IGB_FLAG_HAS_MSIX) ? "MSI-X" :
(adapter->flags & IGB_FLAG_HAS_MSI) ? "MSI" : "legacy",
adapter->num_rx_queues, adapter->num_tx_queues);
- switch (hw->mac.type) {
- case e1000_i350:
- case e1000_i210:
- case e1000_i211:
- igb_set_eee_i350(hw);
- break;
- case e1000_i354:
- if (hw->phy.media_type == e1000_media_type_copper) {
+ if (hw->phy.media_type == e1000_media_type_copper) {
+ switch (hw->mac.type) {
+ case e1000_i350:
+ case e1000_i210:
+ case e1000_i211:
+ /* Enable EEE for internal copper PHY devices */
+ err = igb_set_eee_i350(hw);
+ if ((!err) &&
+ (!hw->dev_spec._82575.eee_disable)) {
+ adapter->eee_advert =
+ MDIO_EEE_100TX | MDIO_EEE_1000T;
+ adapter->flags |= IGB_FLAG_EEE;
+ }
+ break;
+ case e1000_i354:
if ((rd32(E1000_CTRL_EXT) &
- E1000_CTRL_EXT_LINK_MODE_SGMII))
- igb_set_eee_i354(hw);
+ E1000_CTRL_EXT_LINK_MODE_SGMII)) {
+ err = igb_set_eee_i354(hw);
+ if ((!err) &&
+ (!hw->dev_spec._82575.eee_disable)) {
+ adapter->eee_advert =
+ MDIO_EEE_100TX | MDIO_EEE_1000T;
+ adapter->flags |= IGB_FLAG_EEE;
+ }
+ }
+ break;
+ default:
+ break;
}
- break;
- default:
- break;
}
-
pm_runtime_put_noidle(&pdev->dev);
return 0;
@@ -3510,6 +3571,13 @@
vmolr = rd32(E1000_VMOLR(vfn));
vmolr |= E1000_VMOLR_STRVLAN; /* Strip vlan tags */
+ if (hw->mac.type == e1000_i350) {
+ u32 dvmolr;
+
+ dvmolr = rd32(E1000_DVMOLR(vfn));
+ dvmolr |= E1000_DVMOLR_STRVLAN;
+ wr32(E1000_DVMOLR(vfn), dvmolr);
+ }
if (aupe)
vmolr |= E1000_VMOLR_AUPE; /* Accept untagged packets */
else
@@ -4158,6 +4226,15 @@
(ctrl & E1000_CTRL_RFCE) ? "RX" :
(ctrl & E1000_CTRL_TFCE) ? "TX" : "None");
+ /* disable EEE if enabled */
+ if ((adapter->flags & IGB_FLAG_EEE) &&
+ (adapter->link_duplex == HALF_DUPLEX)) {
+ dev_info(&adapter->pdev->dev,
+ "EEE Disabled: unsupported at half duplex. Re-enable using ethtool when at full duplex.\n");
+ adapter->hw.dev_spec._82575.eee_disable = true;
+ adapter->flags &= ~IGB_FLAG_EEE;
+ }
+
/* check if SmartSpeed worked */
igb_check_downshift(hw);
if (phy->speed_downgraded)
@@ -4306,8 +4383,7 @@
* were determined based on theoretical maximum wire speed and testing
* data, in order to minimize response time while increasing bulk
* throughput.
- * This functionality is controlled by the InterruptThrottleRate module
- * parameter (see igb_param.c)
+ * This functionality is controlled by ethtool's coalescing settings.
* NOTE: This function is called only when operating in a multiqueue
* receive environment.
**/
@@ -4381,8 +4457,7 @@
* based on theoretical maximum wire speed and thresholds were set based
* on testing data as well as attempting to minimize response time
* while increasing bulk throughput.
- * this functionality is controlled by the InterruptThrottleRate module
- * parameter (see igb_param.c)
+ * This functionality is controlled by ethtool's coalescing settings.
* NOTE: These calculations are only valid when operating in a single-
* queue environment.
**/
@@ -4546,7 +4621,7 @@
/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
type_tucmd = E1000_ADVTXD_TUCMD_L4T_TCP;
- if (first->protocol == __constant_htons(ETH_P_IP)) {
+ if (first->protocol == htons(ETH_P_IP)) {
struct iphdr *iph = ip_hdr(skb);
iph->tot_len = 0;
iph->check = 0;
@@ -4602,12 +4677,12 @@
} else {
u8 l4_hdr = 0;
switch (first->protocol) {
- case __constant_htons(ETH_P_IP):
+ case htons(ETH_P_IP):
vlan_macip_lens |= skb_network_header_len(skb);
type_tucmd |= E1000_ADVTXD_TUCMD_IPV4;
l4_hdr = ip_hdr(skb)->protocol;
break;
- case __constant_htons(ETH_P_IPV6):
+ case htons(ETH_P_IPV6):
vlan_macip_lens |= skb_network_header_len(skb);
l4_hdr = ipv6_hdr(skb)->nexthdr;
break;
@@ -4905,12 +4980,11 @@
first->bytecount = skb->len;
first->gso_segs = 1;
- skb_tx_timestamp(skb);
-
if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
struct igb_adapter *adapter = netdev_priv(tx_ring->netdev);
- if (!(adapter->ptp_tx_skb)) {
+ if (!test_and_set_bit_lock(__IGB_PTP_TX_IN_PROGRESS,
+ &adapter->state)) {
skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
tx_flags |= IGB_TX_FLAGS_TSTAMP;
@@ -4921,6 +4995,8 @@
}
}
+ skb_tx_timestamp(skb);
+
if (vlan_tx_tag_present(skb)) {
tx_flags |= IGB_TX_FLAGS_VLAN;
tx_flags |= (vlan_tx_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT);
@@ -5127,10 +5203,10 @@
}
do {
- start = u64_stats_fetch_begin_bh(&ring->rx_syncp);
+ start = u64_stats_fetch_begin_irq(&ring->rx_syncp);
_bytes = ring->rx_stats.bytes;
_packets = ring->rx_stats.packets;
- } while (u64_stats_fetch_retry_bh(&ring->rx_syncp, start));
+ } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start));
bytes += _bytes;
packets += _packets;
}
@@ -5143,10 +5219,10 @@
for (i = 0; i < adapter->num_tx_queues; i++) {
struct igb_ring *ring = adapter->tx_ring[i];
do {
- start = u64_stats_fetch_begin_bh(&ring->tx_syncp);
+ start = u64_stats_fetch_begin_irq(&ring->tx_syncp);
_bytes = ring->tx_stats.bytes;
_packets = ring->tx_stats.packets;
- } while (u64_stats_fetch_retry_bh(&ring->tx_syncp, start));
+ } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start));
bytes += _bytes;
packets += _packets;
}
@@ -6620,7 +6696,9 @@
struct sk_buff *skb)
{
if (ring->netdev->features & NETIF_F_RXHASH)
- skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
+ skb_set_hash(skb,
+ le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
+ PKT_HASH_TYPE_L3);
}
/**
@@ -6690,7 +6768,7 @@
hdr.network += ETH_HLEN;
/* handle any vlan tag if present */
- if (protocol == __constant_htons(ETH_P_8021Q)) {
+ if (protocol == htons(ETH_P_8021Q)) {
if ((hdr.network - data) > (max_len - VLAN_HLEN))
return max_len;
@@ -6699,7 +6777,7 @@
}
/* handle L3 protocols */
- if (protocol == __constant_htons(ETH_P_IP)) {
+ if (protocol == htons(ETH_P_IP)) {
if ((hdr.network - data) > (max_len - sizeof(struct iphdr)))
return max_len;
@@ -6713,7 +6791,7 @@
/* record next protocol if header is present */
if (!(hdr.ipv4->frag_off & htons(IP_OFFSET)))
nexthdr = hdr.ipv4->protocol;
- } else if (protocol == __constant_htons(ETH_P_IPV6)) {
+ } else if (protocol == htons(ETH_P_IPV6)) {
if ((hdr.network - data) > (max_len - sizeof(struct ipv6hdr)))
return max_len;
@@ -6903,7 +6981,7 @@
unsigned int total_bytes = 0, total_packets = 0;
u16 cleaned_count = igb_desc_unused(rx_ring);
- do {
+ while (likely(total_packets < budget)) {
union e1000_adv_rx_desc *rx_desc;
/* return some buffers to hardware, one at a time is too slow */
@@ -6955,7 +7033,7 @@
/* update budget accounting */
total_packets++;
- } while (likely(total_packets < budget));
+ }
/* place incomplete frames back on ring for completion */
rx_ring->skb = skb;
@@ -7114,8 +7192,10 @@
case SIOCGMIIREG:
case SIOCSMIIREG:
return igb_mii_ioctl(netdev, ifr, cmd);
+ case SIOCGHWTSTAMP:
+ return igb_ptp_get_ts_config(netdev, ifr);
case SIOCSHWTSTAMP:
- return igb_ptp_hwtstamp_ioctl(netdev, ifr, cmd);
+ return igb_ptp_set_ts_config(netdev, ifr);
default:
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index 5a54e3d..2cca8fd 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -12,9 +12,8 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/module.h>
#include <linux/device.h>
@@ -75,6 +74,8 @@
#define INCVALUE_82576 (16 << IGB_82576_TSYNC_SHIFT)
#define IGB_NBITS_82580 40
+static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter);
+
/* SYSTIM read access for the 82576 */
static cycle_t igb_ptp_read_82576(const struct cyclecounter *cc)
{
@@ -372,7 +373,7 @@
* This work function polls the TSYNCTXCTL valid bit to determine when a
* timestamp has been taken for the current stored skb.
**/
-void igb_ptp_tx_work(struct work_struct *work)
+static void igb_ptp_tx_work(struct work_struct *work)
{
struct igb_adapter *adapter = container_of(work, struct igb_adapter,
ptp_tx_work);
@@ -386,6 +387,7 @@
IGB_PTP_TX_TIMEOUT)) {
dev_kfree_skb_any(adapter->ptp_tx_skb);
adapter->ptp_tx_skb = NULL;
+ clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state);
adapter->tx_hwtstamp_timeouts++;
dev_warn(&adapter->pdev->dev, "clearing Tx timestamp hang");
return;
@@ -466,7 +468,7 @@
* available, then it must have been for this skb here because we only
* allow only one such packet into the queue.
**/
-void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
+static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
{
struct e1000_hw *hw = &adapter->hw;
struct skb_shared_hwtstamps shhwtstamps;
@@ -479,6 +481,7 @@
skb_tstamp_tx(adapter->ptp_tx_skb, &shhwtstamps);
dev_kfree_skb_any(adapter->ptp_tx_skb);
adapter->ptp_tx_skb = NULL;
+ clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state);
}
/**
@@ -540,10 +543,26 @@
}
/**
- * igb_ptp_hwtstamp_ioctl - control hardware time stamping
+ * igb_ptp_get_ts_config - get hardware time stamping config
* @netdev:
* @ifreq:
- * @cmd:
+ *
+ * Get the hwtstamp_config settings to return to the user. Rather than attempt
+ * to deconstruct the settings from the registers, just return a shadow copy
+ * of the last known settings.
+ **/
+int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr)
+{
+ struct igb_adapter *adapter = netdev_priv(netdev);
+ struct hwtstamp_config *config = &adapter->tstamp_config;
+
+ return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
+ -EFAULT : 0;
+}
+/**
+ * igb_ptp_set_ts_config - control hardware time stamping
+ * @netdev:
+ * @ifreq:
*
* Outgoing time stamping can be enabled and disabled. Play nice and
* disable it when requested, although it shouldn't case any overhead
@@ -557,12 +576,11 @@
* not supported, with the exception of "all V2 events regardless of
* level 2 or 4".
**/
-int igb_ptp_hwtstamp_ioctl(struct net_device *netdev,
- struct ifreq *ifr, int cmd)
+int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr)
{
struct igb_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
- struct hwtstamp_config config;
+ struct hwtstamp_config *config = &adapter->tstamp_config;
u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED;
u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED;
u32 tsync_rx_cfg = 0;
@@ -570,14 +588,14 @@
bool is_l2 = false;
u32 regval;
- if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+ if (copy_from_user(config, ifr->ifr_data, sizeof(*config)))
return -EFAULT;
/* reserved for future extensions */
- if (config.flags)
+ if (config->flags)
return -EINVAL;
- switch (config.tx_type) {
+ switch (config->tx_type) {
case HWTSTAMP_TX_OFF:
tsync_tx_ctl = 0;
case HWTSTAMP_TX_ON:
@@ -586,7 +604,7 @@
return -ERANGE;
}
- switch (config.rx_filter) {
+ switch (config->rx_filter) {
case HWTSTAMP_FILTER_NONE:
tsync_rx_ctl = 0;
break;
@@ -610,7 +628,7 @@
case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_EVENT_V2;
- config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+ config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
is_l2 = true;
is_l4 = true;
break;
@@ -621,12 +639,12 @@
*/
if (hw->mac.type != e1000_82576) {
tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL;
- config.rx_filter = HWTSTAMP_FILTER_ALL;
+ config->rx_filter = HWTSTAMP_FILTER_ALL;
break;
}
/* fall through */
default:
- config.rx_filter = HWTSTAMP_FILTER_NONE;
+ config->rx_filter = HWTSTAMP_FILTER_NONE;
return -ERANGE;
}
@@ -643,7 +661,7 @@
if ((hw->mac.type >= e1000_82580) && tsync_rx_ctl) {
tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED;
tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL;
- config.rx_filter = HWTSTAMP_FILTER_ALL;
+ config->rx_filter = HWTSTAMP_FILTER_ALL;
is_l2 = true;
is_l4 = true;
@@ -707,7 +725,7 @@
regval = rd32(E1000_RXSTMPL);
regval = rd32(E1000_RXSTMPH);
- return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
+ return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
-EFAULT : 0;
}
@@ -798,7 +816,7 @@
/* Initialize the time sync interrupts for devices that support it. */
if (hw->mac.type >= e1000_82580) {
- wr32(E1000_TSIM, E1000_TSIM_TXTS);
+ wr32(E1000_TSIM, TSYNC_INTERRUPTS);
wr32(E1000_IMS, E1000_IMS_TS);
}
@@ -841,6 +859,7 @@
if (adapter->ptp_tx_skb) {
dev_kfree_skb_any(adapter->ptp_tx_skb);
adapter->ptp_tx_skb = NULL;
+ clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state);
}
if (adapter->ptp_clock) {
@@ -864,6 +883,9 @@
if (!(adapter->flags & IGB_FLAG_PTP))
return;
+ /* reset the tstamp_config */
+ memset(&adapter->tstamp_config, 0, sizeof(adapter->tstamp_config));
+
switch (adapter->hw.mac.type) {
case e1000_82576:
/* Dial the nominal frequency. */
@@ -876,7 +898,7 @@
case e1000_i211:
/* Enable the timer functions and interrupts. */
wr32(E1000_TSAUXC, 0x0);
- wr32(E1000_TSIM, E1000_TSIM_TXTS);
+ wr32(E1000_TSIM, TSYNC_INTERRUPTS);
wr32(E1000_IMS, E1000_IMS_TS);
break;
default:
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 675435f..b7ab03a 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -1043,11 +1043,11 @@
for (i = 0; i < 3; i++)
adapter->msix_entries[i].entry = i;
- err = pci_enable_msix(adapter->pdev,
- adapter->msix_entries, 3);
+ err = pci_enable_msix_range(adapter->pdev,
+ adapter->msix_entries, 3, 3);
}
- if (err) {
+ if (err < 0) {
/* MSI-X failed */
dev_err(&adapter->pdev->dev,
"Failed to initialize MSI-X interrupts.\n");
@@ -2014,12 +2014,12 @@
if (skb->ip_summed == CHECKSUM_PARTIAL) {
switch (skb->protocol) {
- case __constant_htons(ETH_P_IP):
+ case htons(ETH_P_IP):
tu_cmd |= E1000_ADVTXD_TUCMD_IPV4;
if (ip_hdr(skb)->protocol == IPPROTO_TCP)
tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
break;
- case __constant_htons(ETH_P_IPV6):
+ case htons(ETH_P_IPV6):
if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
break;
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index 57e390c..f42c201 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -1521,12 +1521,12 @@
int tso;
if (test_bit(__IXGB_DOWN, &adapter->flags)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
if (skb->len <= 0) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -1543,7 +1543,7 @@
tso = ixgb_tso(adapter, skb);
if (tso < 0) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 0186ea2..2fff0fc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -765,6 +766,7 @@
struct ptp_clock_info ptp_caps;
struct work_struct ptp_tx_work;
struct sk_buff *ptp_tx_skb;
+ struct hwtstamp_config tstamp_config;
unsigned long ptp_tx_start;
unsigned long last_overflow_check;
unsigned long last_rx_ptp_check;
@@ -884,7 +886,6 @@
u16 soft_id);
void ixgbe_atr_compute_perfect_hash_82599(union ixgbe_atr_input *input,
union ixgbe_atr_input *mask);
-bool ixgbe_verify_lesm_fw_enabled_82599(struct ixgbe_hw *hw);
void ixgbe_set_rx_mode(struct net_device *netdev);
#ifdef CONFIG_IXGBE_DCB
void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter);
@@ -958,8 +959,8 @@
rx_ring->last_rx_timestamp = jiffies;
}
-int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter, struct ifreq *ifr,
- int cmd);
+int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr);
+int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr);
void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter);
void ixgbe_ptp_reset(struct ixgbe_adapter *adapter);
void ixgbe_ptp_check_pps_event(struct ixgbe_adapter *adapter, u32 eicr);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
index a26f3fe..4c78ea8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -57,10 +58,12 @@
**/
static void ixgbe_set_pcie_completion_timeout(struct ixgbe_hw *hw)
{
- struct ixgbe_adapter *adapter = hw->back;
u32 gcr = IXGBE_READ_REG(hw, IXGBE_GCR);
u16 pcie_devctl2;
+ if (ixgbe_removed(hw->hw_addr))
+ return;
+
/* only take action if timeout value is defaulted to 0 */
if (gcr & IXGBE_GCR_CMPL_TMOUT_MASK)
goto out;
@@ -79,11 +82,9 @@
* directly in order to set the completion timeout value for
* 16ms to 55ms
*/
- pci_read_config_word(adapter->pdev,
- IXGBE_PCI_DEVICE_CONTROL2, &pcie_devctl2);
+ pcie_devctl2 = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_CONTROL2);
pcie_devctl2 |= IXGBE_PCI_DEVICE_CONTROL2_16ms;
- pci_write_config_word(adapter->pdev,
- IXGBE_PCI_DEVICE_CONTROL2, pcie_devctl2);
+ ixgbe_write_pci_cfg_word(hw, IXGBE_PCI_DEVICE_CONTROL2, pcie_devctl2);
out:
/* disable completion timeout resend */
gcr &= ~IXGBE_GCR_CMPL_TMOUT_RESEND;
@@ -100,6 +101,7 @@
mac->mcft_size = IXGBE_82598_MC_TBL_SIZE;
mac->vft_size = IXGBE_82598_VFT_TBL_SIZE;
mac->num_rar_entries = IXGBE_82598_RAR_ENTRIES;
+ mac->rx_pb_size = IXGBE_82598_RX_PB_SIZE;
mac->max_rx_queues = IXGBE_82598_MAX_RX_QUEUES;
mac->max_tx_queues = IXGBE_82598_MAX_TX_QUEUES;
mac->max_msix_vectors = ixgbe_get_pcie_msix_count_generic(hw);
@@ -201,8 +203,6 @@
IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval);
}
- hw->mac.rx_pb_size = IXGBE_82598_RX_PB_SIZE;
-
/* set the completion timeout for interface */
if (ret_val == 0)
ixgbe_set_pcie_completion_timeout(hw);
@@ -1237,14 +1237,14 @@
}
/**
- * ixgbe_set_rxpba_82598 - Configure packet buffers
+ * ixgbe_set_rxpba_82598 - Initialize RX packet buffer
* @hw: pointer to hardware structure
- * @dcb_config: pointer to ixgbe_dcb_config structure
- *
- * Configure packet buffers.
- */
-static void ixgbe_set_rxpba_82598(struct ixgbe_hw *hw, int num_pb, u32 headroom,
- int strategy)
+ * @num_pb: number of packet buffers to allocate
+ * @headroom: reserve n KB of headroom
+ * @strategy: packet buffer allocation strategy
+ **/
+static void ixgbe_set_rxpba_82598(struct ixgbe_hw *hw, int num_pb,
+ u32 headroom, int strategy)
{
u32 rxpktsize = IXGBE_RXPBSIZE_64KB;
u8 i = 0;
@@ -1315,7 +1315,8 @@
.release_swfw_sync = &ixgbe_release_swfw_sync,
.get_thermal_sensor_data = NULL,
.init_thermal_sensor_thresh = NULL,
- .mng_fw_enabled = NULL,
+ .prot_autoc_read = &prot_autoc_read_generic,
+ .prot_autoc_write = &prot_autoc_write_generic,
};
static struct ixgbe_eeprom_operations eeprom_ops_82598 = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index edda681..f32b3dd 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -63,8 +64,10 @@
u8 dev_addr, u8 *data);
static s32 ixgbe_write_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset,
u8 dev_addr, u8 data);
+static s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw);
+static bool ixgbe_verify_lesm_fw_enabled_82599(struct ixgbe_hw *hw);
-static bool ixgbe_mng_enabled(struct ixgbe_hw *hw)
+bool ixgbe_mng_enabled(struct ixgbe_hw *hw)
{
u32 fwsm, manc, factps;
@@ -91,7 +94,7 @@
* and MNG not enabled
*/
if ((mac->ops.get_media_type(hw) == ixgbe_media_type_fiber) &&
- !hw->mng_fw_enabled) {
+ !ixgbe_mng_enabled(hw)) {
mac->ops.disable_tx_laser =
&ixgbe_disable_tx_laser_multispeed_fiber;
mac->ops.enable_tx_laser =
@@ -122,7 +125,6 @@
{
s32 ret_val = 0;
u16 list_offset, data_offset, data_value;
- bool got_lock = false;
if (hw->phy.sfp_type != ixgbe_sfp_type_unknown) {
ixgbe_init_mac_link_ops_82599(hw);
@@ -160,30 +162,10 @@
usleep_range(hw->eeprom.semaphore_delay * 1000,
hw->eeprom.semaphore_delay * 2000);
- /* Need SW/FW semaphore around AUTOC writes if LESM on,
- * likewise reset_pipeline requires lock as it also writes
- * AUTOC.
- */
- if (ixgbe_verify_lesm_fw_enabled_82599(hw)) {
- ret_val = hw->mac.ops.acquire_swfw_sync(hw,
- IXGBE_GSSR_MAC_CSR_SM);
- if (ret_val)
- goto setup_sfp_out;
-
- got_lock = true;
- }
-
/* Restart DSP and set SFI mode */
- IXGBE_WRITE_REG(hw, IXGBE_AUTOC, ((hw->mac.orig_autoc) |
- IXGBE_AUTOC_LMS_10G_SERIAL));
- hw->mac.cached_autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC);
- ret_val = ixgbe_reset_pipeline_82599(hw);
-
- if (got_lock) {
- hw->mac.ops.release_swfw_sync(hw,
- IXGBE_GSSR_MAC_CSR_SM);
- got_lock = false;
- }
+ ret_val = hw->mac.ops.prot_autoc_write(hw,
+ hw->mac.orig_autoc | IXGBE_AUTOC_LMS_10G_SERIAL,
+ false);
if (ret_val) {
hw_dbg(hw, " sfp module setup not complete\n");
@@ -207,6 +189,81 @@
return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE;
}
+/**
+ * prot_autoc_read_82599 - Hides MAC differences needed for AUTOC read
+ * @hw: pointer to hardware structure
+ * @locked: Return the if we locked for this read.
+ * @reg_val: Value we read from AUTOC
+ *
+ * For this part (82599) we need to wrap read-modify-writes with a possible
+ * FW/SW lock. It is assumed this lock will be freed with the next
+ * prot_autoc_write_82599(). Note, that locked can only be true in cases
+ * where this function doesn't return an error.
+ **/
+static s32 prot_autoc_read_82599(struct ixgbe_hw *hw, bool *locked,
+ u32 *reg_val)
+{
+ s32 ret_val;
+
+ *locked = false;
+ /* If LESM is on then we need to hold the SW/FW semaphore. */
+ if (ixgbe_verify_lesm_fw_enabled_82599(hw)) {
+ ret_val = hw->mac.ops.acquire_swfw_sync(hw,
+ IXGBE_GSSR_MAC_CSR_SM);
+ if (ret_val)
+ return IXGBE_ERR_SWFW_SYNC;
+
+ *locked = true;
+ }
+
+ *reg_val = IXGBE_READ_REG(hw, IXGBE_AUTOC);
+ return 0;
+}
+
+/**
+ * prot_autoc_write_82599 - Hides MAC differences needed for AUTOC write
+ * @hw: pointer to hardware structure
+ * @reg_val: value to write to AUTOC
+ * @locked: bool to indicate whether the SW/FW lock was already taken by
+ * previous proc_autoc_read_82599.
+ *
+ * This part (82599) may need to hold a the SW/FW lock around all writes to
+ * AUTOC. Likewise after a write we need to do a pipeline reset.
+ **/
+static s32 prot_autoc_write_82599(struct ixgbe_hw *hw, u32 autoc, bool locked)
+{
+ s32 ret_val = 0;
+
+ /* Blocked by MNG FW so bail */
+ if (ixgbe_check_reset_blocked(hw))
+ goto out;
+
+ /* We only need to get the lock if:
+ * - We didn't do it already (in the read part of a read-modify-write)
+ * - LESM is enabled.
+ */
+ if (!locked && ixgbe_verify_lesm_fw_enabled_82599(hw)) {
+ ret_val = hw->mac.ops.acquire_swfw_sync(hw,
+ IXGBE_GSSR_MAC_CSR_SM);
+ if (ret_val)
+ return IXGBE_ERR_SWFW_SYNC;
+
+ locked = true;
+ }
+
+ IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc);
+ ret_val = ixgbe_reset_pipeline_82599(hw);
+
+out:
+ /* Free the SW/FW semaphore as we either grabbed it here or
+ * already had it when this function was called.
+ */
+ if (locked)
+ hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM);
+
+ return ret_val;
+}
+
static s32 ixgbe_get_invariants_82599(struct ixgbe_hw *hw)
{
struct ixgbe_mac_info *mac = &hw->mac;
@@ -216,6 +273,7 @@
mac->mcft_size = IXGBE_82599_MC_TBL_SIZE;
mac->vft_size = IXGBE_82599_VFT_TBL_SIZE;
mac->num_rar_entries = IXGBE_82599_RAR_ENTRIES;
+ mac->rx_pb_size = IXGBE_82599_RX_PB_SIZE;
mac->max_rx_queues = IXGBE_82599_MAX_RX_QUEUES;
mac->max_tx_queues = IXGBE_82599_MAX_TX_QUEUES;
mac->max_msix_vectors = ixgbe_get_pcie_msix_count_generic(hw);
@@ -456,12 +514,20 @@
*
* Disables link, should be called during D3 power down sequence.
*
- */
+ **/
static void ixgbe_stop_mac_link_on_d3_82599(struct ixgbe_hw *hw)
{
- u32 autoc2_reg;
+ u32 autoc2_reg, fwsm;
+ u16 ee_ctrl_2 = 0;
- if (!hw->mng_fw_enabled && !hw->wol_enabled) {
+ hw->eeprom.ops.read(hw, IXGBE_EEPROM_CTRL_2, &ee_ctrl_2);
+
+ /* Check to see if MNG FW could be enabled */
+ fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM);
+
+ if (((fwsm & IXGBE_FWSM_MODE_MASK) != IXGBE_FWSM_FW_MODE_PT) &&
+ !hw->wol_enabled &&
+ ee_ctrl_2 & IXGBE_EEPROM_CCD_BIT) {
autoc2_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC2);
autoc2_reg |= IXGBE_AUTOC2_LINK_DISABLE_ON_D3_MASK;
IXGBE_WRITE_REG(hw, IXGBE_AUTOC2, autoc2_reg);
@@ -542,6 +608,10 @@
{
u32 esdp_reg = IXGBE_READ_REG(hw, IXGBE_ESDP);
+ /* Blocked by MNG FW so bail */
+ if (ixgbe_check_reset_blocked(hw))
+ return;
+
/* Disable tx laser; allow 100us to go dark per spec */
esdp_reg |= IXGBE_ESDP_SDP3;
IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg);
@@ -582,6 +652,10 @@
**/
static void ixgbe_flap_tx_laser_multispeed_fiber(struct ixgbe_hw *hw)
{
+ /* Blocked by MNG FW so bail */
+ if (ixgbe_check_reset_blocked(hw))
+ return;
+
if (hw->mac.autotry_restart) {
ixgbe_disable_tx_laser_multispeed_fiber(hw);
ixgbe_enable_tx_laser_multispeed_fiber(hw);
@@ -590,75 +664,6 @@
}
/**
- * ixgbe_set_fiber_fixed_speed - Set module link speed for fixed fiber
- * @hw: pointer to hardware structure
- * @speed: link speed to set
- *
- * We set the module speed differently for fixed fiber. For other
- * multi-speed devices we don't have an error value so here if we
- * detect an error we just log it and exit.
- */
-static void ixgbe_set_fiber_fixed_speed(struct ixgbe_hw *hw,
- ixgbe_link_speed speed)
-{
- s32 status;
- u8 rs, eeprom_data;
-
- switch (speed) {
- case IXGBE_LINK_SPEED_10GB_FULL:
- /* one bit mask same as setting on */
- rs = IXGBE_SFF_SOFT_RS_SELECT_10G;
- break;
- case IXGBE_LINK_SPEED_1GB_FULL:
- rs = IXGBE_SFF_SOFT_RS_SELECT_1G;
- break;
- default:
- hw_dbg(hw, "Invalid fixed module speed\n");
- return;
- }
-
- /* Set RS0 */
- status = hw->phy.ops.read_i2c_byte(hw, IXGBE_SFF_SFF_8472_OSCB,
- IXGBE_I2C_EEPROM_DEV_ADDR2,
- &eeprom_data);
- if (status) {
- hw_dbg(hw, "Failed to read Rx Rate Select RS0\n");
- goto out;
- }
-
- eeprom_data = (eeprom_data & ~IXGBE_SFF_SOFT_RS_SELECT_MASK) | rs;
-
- status = hw->phy.ops.write_i2c_byte(hw, IXGBE_SFF_SFF_8472_OSCB,
- IXGBE_I2C_EEPROM_DEV_ADDR2,
- eeprom_data);
- if (status) {
- hw_dbg(hw, "Failed to write Rx Rate Select RS0\n");
- goto out;
- }
-
- /* Set RS1 */
- status = hw->phy.ops.read_i2c_byte(hw, IXGBE_SFF_SFF_8472_ESCB,
- IXGBE_I2C_EEPROM_DEV_ADDR2,
- &eeprom_data);
- if (status) {
- hw_dbg(hw, "Failed to read Rx Rate Select RS1\n");
- goto out;
- }
-
- eeprom_data = (eeprom_data & ~IXGBE_SFF_SOFT_RS_SELECT_MASK) & rs;
-
- status = hw->phy.ops.write_i2c_byte(hw, IXGBE_SFF_SFF_8472_ESCB,
- IXGBE_I2C_EEPROM_DEV_ADDR2,
- eeprom_data);
- if (status) {
- hw_dbg(hw, "Failed to write Rx Rate Select RS1\n");
- goto out;
- }
-out:
- return;
-}
-
-/**
* ixgbe_setup_mac_link_multispeed_fiber - Set MAC link speed
* @hw: pointer to hardware structure
* @speed: new link speed
@@ -768,10 +773,6 @@
/* Set the module link speed */
switch (hw->phy.media_type) {
- case ixgbe_media_type_fiber_fixed:
- ixgbe_set_fiber_fixed_speed(hw,
- IXGBE_LINK_SPEED_1GB_FULL);
- break;
case ixgbe_media_type_fiber:
esdp_reg &= ~IXGBE_ESDP_SDP5;
esdp_reg |= IXGBE_ESDP_SDP5_DIR;
@@ -941,8 +942,7 @@
out:
if (link_up && (link_speed == IXGBE_LINK_SPEED_1GB_FULL))
- hw_dbg(hw, "Smartspeed has downgraded the link speed from "
- "the maximum advertised\n");
+ hw_dbg(hw, "Smartspeed has downgraded the link speed from the maximum advertised\n");
return status;
}
@@ -958,16 +958,19 @@
ixgbe_link_speed speed,
bool autoneg_wait_to_complete)
{
- s32 status = 0;
- u32 autoc, pma_pmd_1g, link_mode, start_autoc;
- u32 autoc2 = IXGBE_READ_REG(hw, IXGBE_AUTOC2);
- u32 orig_autoc = 0;
- u32 pma_pmd_10g_serial = autoc2 & IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_MASK;
- u32 links_reg;
- u32 i;
- ixgbe_link_speed link_capabilities = IXGBE_LINK_SPEED_UNKNOWN;
- bool got_lock = false;
bool autoneg = false;
+ s32 status = 0;
+ u32 pma_pmd_1g, link_mode, links_reg, i;
+ u32 autoc2 = IXGBE_READ_REG(hw, IXGBE_AUTOC2);
+ u32 pma_pmd_10g_serial = autoc2 & IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_MASK;
+ ixgbe_link_speed link_capabilities = IXGBE_LINK_SPEED_UNKNOWN;
+
+ /* holds the value of AUTOC register at this current point in time */
+ u32 current_autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC);
+ /* holds the cached value of AUTOC register */
+ u32 orig_autoc = 0;
+ /* temporary variable used for comparison purposes */
+ u32 autoc = current_autoc;
/* Check to see if speed passed in is supported. */
status = hw->mac.ops.get_link_capabilities(hw, &link_capabilities,
@@ -984,12 +987,10 @@
/* Use stored value (EEPROM defaults) of AUTOC to find KR/KX4 support*/
if (hw->mac.orig_link_settings_stored)
- autoc = hw->mac.orig_autoc;
+ orig_autoc = hw->mac.orig_autoc;
else
- autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC);
+ orig_autoc = autoc;
- orig_autoc = autoc;
- start_autoc = hw->mac.cached_autoc;
link_mode = autoc & IXGBE_AUTOC_LMS_MASK;
pma_pmd_1g = autoc & IXGBE_AUTOC_1G_PMA_PMD_MASK;
@@ -1029,28 +1030,11 @@
}
}
- if (autoc != start_autoc) {
- /* Need SW/FW semaphore around AUTOC writes if LESM is on,
- * likewise reset_pipeline requires us to hold this lock as
- * it also writes to AUTOC.
- */
- if (ixgbe_verify_lesm_fw_enabled_82599(hw)) {
- status = hw->mac.ops.acquire_swfw_sync(hw,
- IXGBE_GSSR_MAC_CSR_SM);
- if (status != 0)
- goto out;
-
- got_lock = true;
- }
-
+ if (autoc != current_autoc) {
/* Restart link */
- IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc);
- hw->mac.cached_autoc = autoc;
- ixgbe_reset_pipeline_82599(hw);
-
- if (got_lock)
- hw->mac.ops.release_swfw_sync(hw,
- IXGBE_GSSR_MAC_CSR_SM);
+ status = hw->mac.ops.prot_autoc_write(hw, autoc, false);
+ if (status)
+ goto out;
/* Only poll for autoneg to complete if specified to do so */
if (autoneg_wait_to_complete) {
@@ -1068,8 +1052,7 @@
if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) {
status =
IXGBE_ERR_AUTONEG_NOT_COMPLETE;
- hw_dbg(hw, "Autoneg did not "
- "complete.\n");
+ hw_dbg(hw, "Autoneg did not complete.\n");
}
}
}
@@ -1117,7 +1100,7 @@
{
ixgbe_link_speed link_speed;
s32 status;
- u32 ctrl, i, autoc2;
+ u32 ctrl, i, autoc, autoc2;
u32 curr_lms;
bool link_up = false;
@@ -1151,11 +1134,7 @@
hw->phy.ops.reset(hw);
/* remember AUTOC from before we reset */
- if (hw->mac.cached_autoc)
- curr_lms = hw->mac.cached_autoc & IXGBE_AUTOC_LMS_MASK;
- else
- curr_lms = IXGBE_READ_REG(hw, IXGBE_AUTOC) &
- IXGBE_AUTOC_LMS_MASK;
+ curr_lms = IXGBE_READ_REG(hw, IXGBE_AUTOC) & IXGBE_AUTOC_LMS_MASK;
mac_reset_top:
/*
@@ -1205,7 +1184,7 @@
* stored off yet. Otherwise restore the stored original
* values since the reset operation sets back to defaults.
*/
- hw->mac.cached_autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC);
+ autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC);
autoc2 = IXGBE_READ_REG(hw, IXGBE_AUTOC2);
/* Enable link if disabled in NVM */
@@ -1216,7 +1195,7 @@
}
if (hw->mac.orig_link_settings_stored == false) {
- hw->mac.orig_autoc = hw->mac.cached_autoc;
+ hw->mac.orig_autoc = autoc;
hw->mac.orig_autoc2 = autoc2;
hw->mac.orig_link_settings_stored = true;
} else {
@@ -1227,34 +1206,18 @@
* Likewise if we support WoL we don't want change the
* LMS state either.
*/
- if ((hw->phy.multispeed_fiber && hw->mng_fw_enabled) ||
+ if ((hw->phy.multispeed_fiber && ixgbe_mng_enabled(hw)) ||
hw->wol_enabled)
hw->mac.orig_autoc =
(hw->mac.orig_autoc & ~IXGBE_AUTOC_LMS_MASK) |
curr_lms;
- if (hw->mac.cached_autoc != hw->mac.orig_autoc) {
- /* Need SW/FW semaphore around AUTOC writes if LESM is
- * on, likewise reset_pipeline requires us to hold
- * this lock as it also writes to AUTOC.
- */
- bool got_lock = false;
- if (ixgbe_verify_lesm_fw_enabled_82599(hw)) {
- status = hw->mac.ops.acquire_swfw_sync(hw,
- IXGBE_GSSR_MAC_CSR_SM);
- if (status)
- goto reset_hw_out;
-
- got_lock = true;
- }
-
- IXGBE_WRITE_REG(hw, IXGBE_AUTOC, hw->mac.orig_autoc);
- hw->mac.cached_autoc = hw->mac.orig_autoc;
- ixgbe_reset_pipeline_82599(hw);
-
- if (got_lock)
- hw->mac.ops.release_swfw_sync(hw,
- IXGBE_GSSR_MAC_CSR_SM);
+ if (autoc != hw->mac.orig_autoc) {
+ status = hw->mac.ops.prot_autoc_write(hw,
+ hw->mac.orig_autoc,
+ false);
+ if (status)
+ goto reset_hw_out;
}
if ((autoc2 & IXGBE_AUTOC2_UPPER_MASK) !=
@@ -1634,35 +1597,20 @@
{
u32 hi_hash_dword, lo_hash_dword, flow_vm_vlan;
- u32 bucket_hash = 0;
+ u32 bucket_hash = 0, hi_dword = 0;
+ int i;
/* Apply masks to input data */
- input->dword_stream[0] &= input_mask->dword_stream[0];
- input->dword_stream[1] &= input_mask->dword_stream[1];
- input->dword_stream[2] &= input_mask->dword_stream[2];
- input->dword_stream[3] &= input_mask->dword_stream[3];
- input->dword_stream[4] &= input_mask->dword_stream[4];
- input->dword_stream[5] &= input_mask->dword_stream[5];
- input->dword_stream[6] &= input_mask->dword_stream[6];
- input->dword_stream[7] &= input_mask->dword_stream[7];
- input->dword_stream[8] &= input_mask->dword_stream[8];
- input->dword_stream[9] &= input_mask->dword_stream[9];
- input->dword_stream[10] &= input_mask->dword_stream[10];
+ for (i = 0; i <= 10; i++)
+ input->dword_stream[i] &= input_mask->dword_stream[i];
/* record the flow_vm_vlan bits as they are a key part to the hash */
flow_vm_vlan = ntohl(input->dword_stream[0]);
/* generate common hash dword */
- hi_hash_dword = ntohl(input->dword_stream[1] ^
- input->dword_stream[2] ^
- input->dword_stream[3] ^
- input->dword_stream[4] ^
- input->dword_stream[5] ^
- input->dword_stream[6] ^
- input->dword_stream[7] ^
- input->dword_stream[8] ^
- input->dword_stream[9] ^
- input->dword_stream[10]);
+ for (i = 1; i <= 10; i++)
+ hi_dword ^= input->dword_stream[i];
+ hi_hash_dword = ntohl(hi_dword);
/* low dword is word swapped version of common */
lo_hash_dword = (hi_hash_dword >> 16) | (hi_hash_dword << 16);
@@ -1681,21 +1629,8 @@
lo_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan << 16);
/* Process remaining 30 bit of the key */
- IXGBE_COMPUTE_BKT_HASH_ITERATION(1);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(2);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(3);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(4);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(5);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(6);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(7);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(8);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(9);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(10);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(11);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(12);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(13);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(14);
- IXGBE_COMPUTE_BKT_HASH_ITERATION(15);
+ for (i = 1; i <= 15; i++)
+ IXGBE_COMPUTE_BKT_HASH_ITERATION(i);
/*
* Limit hash to 13 bits since max bucket count is 8K.
@@ -2001,7 +1936,6 @@
/* We need to run link autotry after the driver loads */
hw->mac.autotry_restart = true;
- hw->mac.rx_pb_size = IXGBE_82599_RX_PB_SIZE;
if (ret_val == 0)
ret_val = ixgbe_verify_fw_version_82599(hw);
@@ -2260,7 +2194,7 @@
* Returns true if the LESM FW module is present and enabled. Otherwise
* returns false. Smart Speed must be disabled if LESM FW module is enabled.
**/
-bool ixgbe_verify_lesm_fw_enabled_82599(struct ixgbe_hw *hw)
+static bool ixgbe_verify_lesm_fw_enabled_82599(struct ixgbe_hw *hw)
{
bool lesm_enabled = false;
u16 fw_offset, fw_lesm_param_offset, fw_lesm_state;
@@ -2366,7 +2300,7 @@
* full pipeline reset. Note - We must hold the SW/FW semaphore before writing
* to AUTOC, so this function assumes the semaphore is held.
**/
-s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw)
+static s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw)
{
s32 ret_val;
u32 anlp1_reg = 0;
@@ -2380,11 +2314,12 @@
IXGBE_WRITE_FLUSH(hw);
}
- autoc_reg = hw->mac.cached_autoc;
+ autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC);
autoc_reg |= IXGBE_AUTOC_AN_RESTART;
/* Write AUTOC register with toggled LMS[2] bit and Restart_AN */
- IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg ^ IXGBE_AUTOC_LMS_1G_AN);
+ IXGBE_WRITE_REG(hw, IXGBE_AUTOC,
+ autoc_reg ^ (0x4 << IXGBE_AUTOC_LMS_SHIFT));
/* Wait for AN to leave state 0 */
for (i = 0; i < 10; i++) {
@@ -2565,7 +2500,8 @@
.release_swfw_sync = &ixgbe_release_swfw_sync,
.get_thermal_sensor_data = &ixgbe_get_thermal_sensor_data_generic,
.init_thermal_sensor_thresh = &ixgbe_init_thermal_sensor_thresh_generic,
- .mng_fw_enabled = &ixgbe_mng_enabled,
+ .prot_autoc_read = &prot_autoc_read_82599,
+ .prot_autoc_write = &prot_autoc_write_82599,
};
static struct ixgbe_eeprom_operations eeprom_ops_82599 = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index b5c434b..24fba39 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -72,7 +73,6 @@
bool link_up;
switch (hw->phy.media_type) {
- case ixgbe_media_type_fiber_fixed:
case ixgbe_media_type_fiber:
hw->mac.ops.check_link(hw, &speed, &link_up, false);
/* if link is down, assume supported */
@@ -114,7 +114,7 @@
s32 ret_val = 0;
u32 reg = 0, reg_bp = 0;
u16 reg_cu = 0;
- bool got_lock = false;
+ bool locked = false;
/*
* Validate the requested mode. Strict IEEE mode does not allow
@@ -139,11 +139,16 @@
* we link at 10G, the 1G advertisement is harmless and vice versa.
*/
switch (hw->phy.media_type) {
- case ixgbe_media_type_fiber_fixed:
- case ixgbe_media_type_fiber:
case ixgbe_media_type_backplane:
+ /* some MAC's need RMW protection on AUTOC */
+ ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, ®_bp);
+ if (ret_val)
+ goto out;
+
+ /* only backplane uses autoc so fall though */
+ case ixgbe_media_type_fiber:
reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA);
- reg_bp = IXGBE_READ_REG(hw, IXGBE_AUTOC);
+
break;
case ixgbe_media_type_copper:
hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE,
@@ -240,27 +245,12 @@
* LESM is on, likewise reset_pipeline requries the lock as
* it also writes AUTOC.
*/
- if ((hw->mac.type == ixgbe_mac_82599EB) &&
- ixgbe_verify_lesm_fw_enabled_82599(hw)) {
- ret_val = hw->mac.ops.acquire_swfw_sync(hw,
- IXGBE_GSSR_MAC_CSR_SM);
- if (ret_val)
- goto out;
-
- got_lock = true;
- }
-
- IXGBE_WRITE_REG(hw, IXGBE_AUTOC, reg_bp);
-
- if (hw->mac.type == ixgbe_mac_82599EB)
- ixgbe_reset_pipeline_82599(hw);
-
- if (got_lock)
- hw->mac.ops.release_swfw_sync(hw,
- IXGBE_GSSR_MAC_CSR_SM);
+ ret_val = hw->mac.ops.prot_autoc_write(hw, reg_bp, locked);
+ if (ret_val)
+ goto out;
} else if ((hw->phy.media_type == ixgbe_media_type_copper) &&
- ixgbe_device_supports_autoneg_fc(hw)) {
+ ixgbe_device_supports_autoneg_fc(hw)) {
hw->phy.ops.write_reg(hw, MDIO_AN_ADVERTISE,
MDIO_MMD_AN, reg_cu);
}
@@ -656,20 +646,17 @@
**/
s32 ixgbe_get_bus_info_generic(struct ixgbe_hw *hw)
{
- struct ixgbe_adapter *adapter = hw->back;
- struct ixgbe_mac_info *mac = &hw->mac;
u16 link_status;
hw->bus.type = ixgbe_bus_type_pci_express;
/* Get the negotiated link width and speed from PCI config space */
- pci_read_config_word(adapter->pdev, IXGBE_PCI_LINK_STATUS,
- &link_status);
+ link_status = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_LINK_STATUS);
hw->bus.width = ixgbe_convert_bus_width(link_status);
hw->bus.speed = ixgbe_convert_bus_speed(link_status);
- mac->ops.set_lan_id(hw);
+ hw->mac.ops.set_lan_id(hw);
return 0;
}
@@ -2406,7 +2393,6 @@
switch (hw->phy.media_type) {
/* Autoneg flow control on fiber adapters */
- case ixgbe_media_type_fiber_fixed:
case ixgbe_media_type_fiber:
if (speed == IXGBE_LINK_SPEED_1GB_FULL)
ret_val = ixgbe_fc_autoneg_fiber(hw);
@@ -2437,6 +2423,53 @@
}
/**
+ * ixgbe_pcie_timeout_poll - Return number of times to poll for completion
+ * @hw: pointer to hardware structure
+ *
+ * System-wide timeout range is encoded in PCIe Device Control2 register.
+ *
+ * Add 10% to specified maximum and return the number of times to poll for
+ * completion timeout, in units of 100 microsec. Never return less than
+ * 800 = 80 millisec.
+ **/
+static u32 ixgbe_pcie_timeout_poll(struct ixgbe_hw *hw)
+{
+ s16 devctl2;
+ u32 pollcnt;
+
+ devctl2 = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_CONTROL2);
+ devctl2 &= IXGBE_PCIDEVCTRL2_TIMEO_MASK;
+
+ switch (devctl2) {
+ case IXGBE_PCIDEVCTRL2_65_130ms:
+ pollcnt = 1300; /* 130 millisec */
+ break;
+ case IXGBE_PCIDEVCTRL2_260_520ms:
+ pollcnt = 5200; /* 520 millisec */
+ break;
+ case IXGBE_PCIDEVCTRL2_1_2s:
+ pollcnt = 20000; /* 2 sec */
+ break;
+ case IXGBE_PCIDEVCTRL2_4_8s:
+ pollcnt = 80000; /* 8 sec */
+ break;
+ case IXGBE_PCIDEVCTRL2_17_34s:
+ pollcnt = 34000; /* 34 sec */
+ break;
+ case IXGBE_PCIDEVCTRL2_50_100us: /* 100 microsecs */
+ case IXGBE_PCIDEVCTRL2_1_2ms: /* 2 millisecs */
+ case IXGBE_PCIDEVCTRL2_16_32ms: /* 32 millisec */
+ case IXGBE_PCIDEVCTRL2_16_32ms_def: /* 32 millisec default */
+ default:
+ pollcnt = 800; /* 80 millisec minimum */
+ break;
+ }
+
+ /* add 10% to spec maximum */
+ return (pollcnt * 11) / 10;
+}
+
+/**
* ixgbe_disable_pcie_master - Disable PCI-express master access
* @hw: pointer to hardware structure
*
@@ -2447,16 +2480,16 @@
**/
static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw)
{
- struct ixgbe_adapter *adapter = hw->back;
s32 status = 0;
- u32 i;
+ u32 i, poll;
u16 value;
/* Always set this bit to ensure any future transactions are blocked */
IXGBE_WRITE_REG(hw, IXGBE_CTRL, IXGBE_CTRL_GIO_DIS);
/* Exit if master requests are blocked */
- if (!(IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_GIO))
+ if (!(IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_GIO) ||
+ ixgbe_removed(hw->hw_addr))
goto out;
/* Poll for master request bit to clear */
@@ -2481,10 +2514,12 @@
* Before proceeding, make sure that the PCIe block does not have
* transactions pending.
*/
- for (i = 0; i < IXGBE_PCI_MASTER_DISABLE_TIMEOUT; i++) {
+ poll = ixgbe_pcie_timeout_poll(hw);
+ for (i = 0; i < poll; i++) {
udelay(100);
- pci_read_config_word(adapter->pdev, IXGBE_PCI_DEVICE_STATUS,
- &value);
+ value = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_STATUS);
+ if (ixgbe_removed(hw->hw_addr))
+ goto out;
if (!(value & IXGBE_PCI_DEVICE_STATUS_TRANSACTION_PENDING))
goto out;
}
@@ -2564,6 +2599,35 @@
}
/**
+ * prot_autoc_read_generic - Hides MAC differences needed for AUTOC read
+ * @hw: pointer to hardware structure
+ * @reg_val: Value we read from AUTOC
+ * @locked: bool to indicate whether the SW/FW lock should be taken. Never
+ * true in this the generic case.
+ *
+ * The default case requires no protection so just to the register read.
+ **/
+s32 prot_autoc_read_generic(struct ixgbe_hw *hw, bool *locked, u32 *reg_val)
+{
+ *locked = false;
+ *reg_val = IXGBE_READ_REG(hw, IXGBE_AUTOC);
+ return 0;
+}
+
+/**
+ * prot_autoc_write_generic - Hides MAC differences needed for AUTOC write
+ * @hw: pointer to hardware structure
+ * @reg_val: value to write to AUTOC
+ * @locked: bool to indicate whether the SW/FW lock was already taken by
+ * previous read.
+ **/
+s32 prot_autoc_write_generic(struct ixgbe_hw *hw, u32 reg_val, bool locked)
+{
+ IXGBE_WRITE_REG(hw, IXGBE_AUTOC, reg_val);
+ return 0;
+}
+
+/**
* ixgbe_disable_rx_buff_generic - Stops the receive data path
* @hw: pointer to hardware structure
*
@@ -2641,6 +2705,7 @@
u32 autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC);
u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL);
s32 ret_val = 0;
+ bool locked = false;
/*
* Link must be up to auto-blink the LEDs;
@@ -2649,28 +2714,19 @@
hw->mac.ops.check_link(hw, &speed, &link_up, false);
if (!link_up) {
- /* Need the SW/FW semaphore around AUTOC writes if 82599 and
- * LESM is on.
- */
- bool got_lock = false;
+ ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, &autoc_reg);
+ if (ret_val)
+ goto out;
- if ((hw->mac.type == ixgbe_mac_82599EB) &&
- ixgbe_verify_lesm_fw_enabled_82599(hw)) {
- ret_val = hw->mac.ops.acquire_swfw_sync(hw,
- IXGBE_GSSR_MAC_CSR_SM);
- if (ret_val)
- goto out;
-
- got_lock = true;
- }
autoc_reg |= IXGBE_AUTOC_AN_RESTART;
autoc_reg |= IXGBE_AUTOC_FLU;
- IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg);
+
+ ret_val = hw->mac.ops.prot_autoc_write(hw, autoc_reg, locked);
+ if (ret_val)
+ goto out;
+
IXGBE_WRITE_FLUSH(hw);
- if (got_lock)
- hw->mac.ops.release_swfw_sync(hw,
- IXGBE_GSSR_MAC_CSR_SM);
usleep_range(10000, 20000);
}
@@ -2690,33 +2746,21 @@
**/
s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index)
{
- u32 autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC);
+ u32 autoc_reg = 0;
u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL);
s32 ret_val = 0;
- bool got_lock = false;
+ bool locked = false;
- /* Need the SW/FW semaphore around AUTOC writes if 82599 and
- * LESM is on.
- */
- if ((hw->mac.type == ixgbe_mac_82599EB) &&
- ixgbe_verify_lesm_fw_enabled_82599(hw)) {
- ret_val = hw->mac.ops.acquire_swfw_sync(hw,
- IXGBE_GSSR_MAC_CSR_SM);
- if (ret_val)
- goto out;
-
- got_lock = true;
- }
+ ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, &autoc_reg);
+ if (ret_val)
+ goto out;
autoc_reg &= ~IXGBE_AUTOC_FLU;
autoc_reg |= IXGBE_AUTOC_AN_RESTART;
- IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg);
- if (hw->mac.type == ixgbe_mac_82599EB)
- ixgbe_reset_pipeline_82599(hw);
-
- if (got_lock)
- hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM);
+ ret_val = hw->mac.ops.prot_autoc_write(hw, autoc_reg, locked);
+ if (ret_val)
+ goto out;
led_reg &= ~IXGBE_LED_MODE_MASK(index);
led_reg &= ~IXGBE_LED_BLINK(index);
@@ -2817,7 +2861,6 @@
**/
u16 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw)
{
- struct ixgbe_adapter *adapter = hw->back;
u16 msix_count = 1;
u16 max_msix_count;
u16 pcie_offset;
@@ -2836,7 +2879,9 @@
return msix_count;
}
- pci_read_config_word(adapter->pdev, pcie_offset, &msix_count);
+ msix_count = ixgbe_read_pci_cfg_word(hw, pcie_offset);
+ if (ixgbe_removed(hw->hw_addr))
+ msix_count = 0;
msix_count &= IXGBE_PCIE_MSIX_TBL_SZ_MASK;
/* MSI-X count is zero-based in HW */
@@ -2868,6 +2913,9 @@
mpsar_lo = IXGBE_READ_REG(hw, IXGBE_MPSAR_LO(rar));
mpsar_hi = IXGBE_READ_REG(hw, IXGBE_MPSAR_HI(rar));
+ if (ixgbe_removed(hw->hw_addr))
+ goto done;
+
if (!mpsar_lo && !mpsar_hi)
goto done;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
index f2e3919..f12c40f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -98,6 +99,10 @@
bool *link_up, bool link_up_wait_to_complete);
s32 ixgbe_get_wwn_prefix_generic(struct ixgbe_hw *hw, u16 *wwnn_prefix,
u16 *wwpn_prefix);
+
+s32 prot_autoc_read_generic(struct ixgbe_hw *hw, bool *, u32 *reg_val);
+s32 prot_autoc_write_generic(struct ixgbe_hw *hw, u32 reg_val, bool locked);
+
s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index);
s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index);
void ixgbe_set_mac_anti_spoofing(struct ixgbe_hw *hw, bool enable, int pf);
@@ -106,10 +111,10 @@
s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min,
u8 build, u8 ver);
void ixgbe_clear_tx_pending(struct ixgbe_hw *hw);
+bool ixgbe_mng_enabled(struct ixgbe_hw *hw);
void ixgbe_set_rxpba_generic(struct ixgbe_hw *hw, int num_pb,
u32 headroom, int strategy);
-s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw);
#define IXGBE_I2C_THERMAL_SENSOR_ADDR 0xF8
#define IXGBE_EMC_INTERNAL_DATA 0x00
@@ -125,6 +130,11 @@
s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw);
#define IXGBE_FAILED_READ_REG 0xffffffffU
+#define IXGBE_FAILED_READ_CFG_DWORD 0xffffffffU
+#define IXGBE_FAILED_READ_CFG_WORD 0xffffU
+
+u16 ixgbe_read_pci_cfg_word(struct ixgbe_hw *hw, u32 reg);
+void ixgbe_write_pci_cfg_word(struct ixgbe_hw *hw, u32 reg, u16 value);
static inline bool ixgbe_removed(void __iomem *addr)
{
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c
index 05e23b8..bdb99b3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h
index d71d9ce..d5a1e3d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
index c5933f6..472b0f4 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 0433070..6c55c14 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -1127,10 +1128,10 @@
}
do {
- start = u64_stats_fetch_begin_bh(&ring->syncp);
+ start = u64_stats_fetch_begin_irq(&ring->syncp);
data[i] = ring->stats.packets;
data[i+1] = ring->stats.bytes;
- } while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&ring->syncp, start));
i += 2;
#ifdef BP_EXTENDED_STATS
data[i] = ring->stats.yields;
@@ -1155,10 +1156,10 @@
}
do {
- start = u64_stats_fetch_begin_bh(&ring->syncp);
+ start = u64_stats_fetch_begin_irq(&ring->syncp);
data[i] = ring->stats.packets;
data[i+1] = ring->stats.bytes;
- } while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&ring->syncp, start));
i += 2;
#ifdef BP_EXTENDED_STATS
data[i] = ring->stats.yields;
@@ -1247,6 +1248,11 @@
struct ixgbe_hw *hw = &adapter->hw;
bool link_up;
u32 link_speed = 0;
+
+ if (ixgbe_removed(hw->hw_addr)) {
+ *data = 1;
+ return 1;
+ }
*data = 0;
hw->mac.ops.check_link(hw, &link_speed, &link_up, true);
@@ -1969,6 +1975,7 @@
data[1] = 1;
data[2] = 1;
data[3] = 1;
+ data[4] = 1;
eth_test->flags |= ETH_TEST_FL_FAILED;
return;
}
@@ -1988,6 +1995,7 @@
data[1] = 1;
data[2] = 1;
data[3] = 1;
+ data[4] = 1;
eth_test->flags |= ETH_TEST_FL_FAILED;
clear_bit(__IXGBE_TESTING,
&adapter->state);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
index f58db45..25a3dfe 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -407,13 +408,13 @@
switch (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_FCSTAT)) {
/* return 0 to bypass going to ULD for DDPed data */
- case __constant_cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_DDP):
+ case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_DDP):
/* update length of DDPed data */
ddp->len = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
rc = 0;
break;
/* unmap the sg list when FCPRSP is received */
- case __constant_cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_FCPRSP):
+ case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_FCPRSP):
dma_unmap_sg(&adapter->pdev->dev, ddp->sgl,
ddp->sgc, DMA_FROM_DEVICE);
ddp->err = ddp_err;
@@ -421,14 +422,14 @@
ddp->sgc = 0;
/* fall through */
/* if DDP length is present pass it through to ULD */
- case __constant_cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_NODDP):
+ case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_NODDP):
/* update length of DDPed data */
ddp->len = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
if (ddp->len)
rc = ddp->len;
break;
/* no match will return as an error */
- case __constant_cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_NOMTCH):
+ case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_NOMTCH):
default:
break;
}
@@ -585,7 +586,7 @@
struct dma_pool *pool;
char pool_name[32];
- snprintf(pool_name, 32, "ixgbe_fcoe_ddp_%d", cpu);
+ snprintf(pool_name, 32, "ixgbe_fcoe_ddp_%u", cpu);
pool = dma_pool_create(pool_name, dev, IXGBE_FCPTR_MAX,
IXGBE_FCPTR_ALIGN, PAGE_SIZE);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h
index 3a02759..b16cc78 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index 32e3eaa..2067d39 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -698,7 +699,7 @@
static void ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter,
int vectors)
{
- int err, vector_threshold;
+ int vector_threshold;
/* We'll want at least 2 (vector_threshold):
* 1) TxQ[0] + RxQ[0] handler
@@ -712,18 +713,10 @@
* Right now, we simply care about how many we'll get; we'll
* set them up later while requesting irq's.
*/
- while (vectors >= vector_threshold) {
- err = pci_enable_msix(adapter->pdev, adapter->msix_entries,
- vectors);
- if (!err) /* Success in acquiring all requested vectors. */
- break;
- else if (err < 0)
- vectors = 0; /* Nasty failure, quit now */
- else /* err == number of vectors we should try again with */
- vectors = err;
- }
+ vectors = pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
+ vector_threshold, vectors);
- if (vectors < vector_threshold) {
+ if (vectors < 0) {
/* Can't allocate enough MSI-X interrupts? Oh well.
* This just means we'll go with either a single MSI
* vector or fall back to legacy interrupts.
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 6d4ada7..9e5a366 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -67,7 +68,7 @@
#define DRV_VERSION "3.19.1-k"
const char ixgbe_driver_version[] = DRV_VERSION;
static const char ixgbe_copyright[] =
- "Copyright (c) 1999-2013 Intel Corporation.";
+ "Copyright (c) 1999-2014 Intel Corporation.";
static const struct ixgbe_info *ixgbe_info_tbl[] = {
[board_82598] = &ixgbe_82598_info,
@@ -151,6 +152,8 @@
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);
+static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev);
+
static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter,
u32 reg, u16 *value)
{
@@ -169,6 +172,9 @@
return -1;
pcie_capability_read_word(parent_dev, reg, value);
+ if (*value == IXGBE_FAILED_READ_CFG_WORD &&
+ ixgbe_check_cfg_remove(&adapter->hw, parent_dev))
+ return -1;
return 0;
}
@@ -313,6 +319,57 @@
ixgbe_remove_adapter(hw);
}
+static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev)
+{
+ u16 value;
+
+ pci_read_config_word(pdev, PCI_VENDOR_ID, &value);
+ if (value == IXGBE_FAILED_READ_CFG_WORD) {
+ ixgbe_remove_adapter(hw);
+ return true;
+ }
+ return false;
+}
+
+u16 ixgbe_read_pci_cfg_word(struct ixgbe_hw *hw, u32 reg)
+{
+ struct ixgbe_adapter *adapter = hw->back;
+ u16 value;
+
+ if (ixgbe_removed(hw->hw_addr))
+ return IXGBE_FAILED_READ_CFG_WORD;
+ pci_read_config_word(adapter->pdev, reg, &value);
+ if (value == IXGBE_FAILED_READ_CFG_WORD &&
+ ixgbe_check_cfg_remove(hw, adapter->pdev))
+ return IXGBE_FAILED_READ_CFG_WORD;
+ return value;
+}
+
+#ifdef CONFIG_PCI_IOV
+static u32 ixgbe_read_pci_cfg_dword(struct ixgbe_hw *hw, u32 reg)
+{
+ struct ixgbe_adapter *adapter = hw->back;
+ u32 value;
+
+ if (ixgbe_removed(hw->hw_addr))
+ return IXGBE_FAILED_READ_CFG_DWORD;
+ pci_read_config_dword(adapter->pdev, reg, &value);
+ if (value == IXGBE_FAILED_READ_CFG_DWORD &&
+ ixgbe_check_cfg_remove(hw, adapter->pdev))
+ return IXGBE_FAILED_READ_CFG_DWORD;
+ return value;
+}
+#endif /* CONFIG_PCI_IOV */
+
+void ixgbe_write_pci_cfg_word(struct ixgbe_hw *hw, u32 reg, u16 value)
+{
+ struct ixgbe_adapter *adapter = hw->back;
+
+ if (ixgbe_removed(hw->hw_addr))
+ return;
+ pci_write_config_word(adapter->pdev, reg, value);
+}
+
static void ixgbe_service_event_complete(struct ixgbe_adapter *adapter)
{
BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state));
@@ -1264,7 +1321,9 @@
struct sk_buff *skb)
{
if (ring->netdev->features & NETIF_F_RXHASH)
- skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
+ skb_set_hash(skb,
+ le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
+ PKT_HASH_TYPE_L3);
}
#ifdef IXGBE_FCOE
@@ -1480,7 +1539,7 @@
hdr.network += ETH_HLEN;
/* handle any vlan tag if present */
- if (protocol == __constant_htons(ETH_P_8021Q)) {
+ if (protocol == htons(ETH_P_8021Q)) {
if ((hdr.network - data) > (max_len - VLAN_HLEN))
return max_len;
@@ -1489,7 +1548,7 @@
}
/* handle L3 protocols */
- if (protocol == __constant_htons(ETH_P_IP)) {
+ if (protocol == htons(ETH_P_IP)) {
if ((hdr.network - data) > (max_len - sizeof(struct iphdr)))
return max_len;
@@ -1503,7 +1562,7 @@
/* record next protocol if header is present */
if (!(hdr.ipv4->frag_off & htons(IP_OFFSET)))
nexthdr = hdr.ipv4->protocol;
- } else if (protocol == __constant_htons(ETH_P_IPV6)) {
+ } else if (protocol == htons(ETH_P_IPV6)) {
if ((hdr.network - data) > (max_len - sizeof(struct ipv6hdr)))
return max_len;
@@ -1511,7 +1570,7 @@
nexthdr = hdr.ipv6->nexthdr;
hlen = sizeof(struct ipv6hdr);
#ifdef IXGBE_FCOE
- } else if (protocol == __constant_htons(ETH_P_FCOE)) {
+ } else if (protocol == htons(ETH_P_FCOE)) {
if ((hdr.network - data) > (max_len - FCOE_HEADER_LEN))
return max_len;
hlen = FCOE_HEADER_LEN;
@@ -2026,7 +2085,7 @@
#endif /* IXGBE_FCOE */
u16 cleaned_count = ixgbe_desc_unused(rx_ring);
- do {
+ while (likely(total_rx_packets < budget)) {
union ixgbe_adv_rx_desc *rx_desc;
struct sk_buff *skb;
@@ -2101,7 +2160,7 @@
/* update budget accounting */
total_rx_packets++;
- } while (likely(total_rx_packets < budget));
+ }
u64_stats_update_begin(&rx_ring->syncp);
rx_ring->stats.packets += total_rx_packets;
@@ -2630,9 +2689,12 @@
switch (hw->mac.type) {
case ixgbe_mac_82599EB:
case ixgbe_mac_X540:
- if (eicr & IXGBE_EICR_ECC)
- e_info(link, "Received unrecoverable ECC Err, please "
- "reboot\n");
+ if (eicr & IXGBE_EICR_ECC) {
+ e_info(link, "Received ECC Err, initiating reset\n");
+ adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED;
+ ixgbe_service_event_schedule(adapter);
+ IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_ECC);
+ }
/* Handle Flow Director Full threshold interrupt */
if (eicr & IXGBE_EICR_FLOW_DIR) {
int reinit_count = 0;
@@ -2846,9 +2908,12 @@
ixgbe_check_sfp_event(adapter, eicr);
/* Fall through */
case ixgbe_mac_X540:
- if (eicr & IXGBE_EICR_ECC)
- e_info(link, "Received unrecoverable ECC err, please "
- "reboot\n");
+ if (eicr & IXGBE_EICR_ECC) {
+ e_info(link, "Received ECC Err, initiating reset\n");
+ adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED;
+ ixgbe_service_event_schedule(adapter);
+ IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_ECC);
+ }
ixgbe_check_overtemp_event(adapter, eicr);
break;
default:
@@ -4590,8 +4655,6 @@
static void ixgbe_up_complete(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
- struct net_device *upper;
- struct list_head *iter;
int err;
u32 ctrl_ext;
@@ -4633,19 +4696,6 @@
e_crit(drv, "Fan has stopped, replace the adapter\n");
}
- /* enable transmits */
- netif_tx_start_all_queues(adapter->netdev);
-
- /* enable any upper devices */
- netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
- if (netif_is_macvlan(upper)) {
- struct macvlan_dev *vlan = netdev_priv(upper);
-
- if (vlan->fwd_priv)
- netif_tx_start_all_queues(upper);
- }
- }
-
/* bring the link up in the watchdog, this could race with our first
* link up interrupt but shouldn't be a problem */
adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
@@ -5502,6 +5552,7 @@
struct net_device *netdev = adapter->netdev;
u32 err;
+ adapter->hw.hw_addr = adapter->io_addr;
pci_set_power_state(pdev, PCI_D0);
pci_restore_state(pdev);
/*
@@ -6016,6 +6067,8 @@
{
struct net_device *netdev = adapter->netdev;
struct ixgbe_hw *hw = &adapter->hw;
+ struct net_device *upper;
+ struct list_head *iter;
u32 link_speed = adapter->link_speed;
bool flow_rx, flow_tx;
@@ -6067,6 +6120,21 @@
netif_carrier_on(netdev);
ixgbe_check_vf_rate_limit(adapter);
+ /* enable transmits */
+ netif_tx_wake_all_queues(adapter->netdev);
+
+ /* enable any upper devices */
+ rtnl_lock();
+ netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
+ if (netif_is_macvlan(upper)) {
+ struct macvlan_dev *vlan = netdev_priv(upper);
+
+ if (vlan->fwd_priv)
+ netif_tx_wake_all_queues(upper);
+ }
+ }
+ rtnl_unlock();
+
/* update the default user priority for VFs */
ixgbe_update_default_up(adapter);
@@ -6454,7 +6522,7 @@
/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP;
- if (first->protocol == __constant_htons(ETH_P_IP)) {
+ if (first->protocol == htons(ETH_P_IP)) {
struct iphdr *iph = ip_hdr(skb);
iph->tot_len = 0;
iph->check = 0;
@@ -6514,12 +6582,12 @@
} else {
u8 l4_hdr = 0;
switch (first->protocol) {
- case __constant_htons(ETH_P_IP):
+ case htons(ETH_P_IP):
vlan_macip_lens |= skb_network_header_len(skb);
type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4;
l4_hdr = ip_hdr(skb)->protocol;
break;
- case __constant_htons(ETH_P_IPV6):
+ case htons(ETH_P_IPV6):
vlan_macip_lens |= skb_network_header_len(skb);
l4_hdr = ipv6_hdr(skb)->nexthdr;
break;
@@ -6794,9 +6862,9 @@
hdr.network = skb_network_header(first->skb);
/* Currently only IPv4/IPv6 with TCP is supported */
- if ((first->protocol != __constant_htons(ETH_P_IPV6) ||
+ if ((first->protocol != htons(ETH_P_IPV6) ||
hdr.ipv6->nexthdr != IPPROTO_TCP) &&
- (first->protocol != __constant_htons(ETH_P_IP) ||
+ (first->protocol != htons(ETH_P_IP) ||
hdr.ipv4->protocol != IPPROTO_TCP))
return;
@@ -6829,12 +6897,12 @@
* and write the value to source port portion of compressed dword
*/
if (first->tx_flags & (IXGBE_TX_FLAGS_SW_VLAN | IXGBE_TX_FLAGS_HW_VLAN))
- common.port.src ^= th->dest ^ __constant_htons(ETH_P_8021Q);
+ common.port.src ^= th->dest ^ htons(ETH_P_8021Q);
else
common.port.src ^= th->dest ^ first->protocol;
common.port.dst ^= th->source;
- if (first->protocol == __constant_htons(ETH_P_IP)) {
+ if (first->protocol == htons(ETH_P_IP)) {
input.formatted.flow_type = IXGBE_ATR_FLOW_TYPE_TCPV4;
common.ip ^= hdr.ipv4->saddr ^ hdr.ipv4->daddr;
} else {
@@ -6881,7 +6949,7 @@
}
static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv, select_queue_fallback_t fallback)
{
struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
#ifdef IXGBE_FCOE
@@ -6900,14 +6968,14 @@
* or FIP and we have FCoE enabled on the adapter
*/
switch (vlan_get_protocol(skb)) {
- case __constant_htons(ETH_P_FCOE):
- case __constant_htons(ETH_P_FIP):
+ case htons(ETH_P_FCOE):
+ case htons(ETH_P_FIP):
adapter = netdev_priv(dev);
if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
break;
default:
- return __netdev_pick_tx(dev, skb);
+ return fallback(dev, skb);
}
f = &adapter->ring_feature[RING_F_FCOE];
@@ -6920,7 +6988,7 @@
return txq + f->offset;
#else
- return __netdev_pick_tx(dev, skb);
+ return fallback(dev, skb);
#endif
}
@@ -6962,7 +7030,7 @@
tx_flags |= vlan_tx_tag_get(skb) << IXGBE_TX_FLAGS_VLAN_SHIFT;
tx_flags |= IXGBE_TX_FLAGS_HW_VLAN;
/* else if it is a SW VLAN check the next protocol and store the tag */
- } else if (protocol == __constant_htons(ETH_P_8021Q)) {
+ } else if (protocol == htons(ETH_P_8021Q)) {
struct vlan_hdr *vhdr, _vhdr;
vhdr = skb_header_pointer(skb, ETH_HLEN, sizeof(_vhdr), &_vhdr);
if (!vhdr)
@@ -7021,7 +7089,7 @@
#ifdef IXGBE_FCOE
/* setup tx offload for FCoE */
- if ((protocol == __constant_htons(ETH_P_FCOE)) &&
+ if ((protocol == htons(ETH_P_FCOE)) &&
(tx_ring->netdev->features & (NETIF_F_FSO | NETIF_F_FCOE_CRC))) {
tso = ixgbe_fso(tx_ring, first, &hdr_len);
if (tso < 0)
@@ -7143,7 +7211,9 @@
switch (cmd) {
case SIOCSHWTSTAMP:
- return ixgbe_ptp_hwtstamp_ioctl(adapter, req, cmd);
+ return ixgbe_ptp_set_ts_config(adapter, req);
+ case SIOCGHWTSTAMP:
+ return ixgbe_ptp_get_ts_config(adapter, req);
default:
return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd);
}
@@ -7234,10 +7304,10 @@
if (ring) {
do {
- start = u64_stats_fetch_begin_bh(&ring->syncp);
+ start = u64_stats_fetch_begin_irq(&ring->syncp);
packets = ring->stats.packets;
bytes = ring->stats.bytes;
- } while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&ring->syncp, start));
stats->rx_packets += packets;
stats->rx_bytes += bytes;
}
@@ -7250,10 +7320,10 @@
if (ring) {
do {
- start = u64_stats_fetch_begin_bh(&ring->syncp);
+ start = u64_stats_fetch_begin_irq(&ring->syncp);
packets = ring->stats.packets;
bytes = ring->stats.bytes;
- } while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&ring->syncp, start));
stats->tx_packets += packets;
stats->tx_bytes += bytes;
}
@@ -7792,6 +7862,7 @@
case IXGBE_DEV_ID_82599_SFP:
/* Only these subdevices could supports WOL */
switch (subdevice_id) {
+ case IXGBE_SUBDEV_ID_82599_SFP_WOL0:
case IXGBE_SUBDEV_ID_82599_560FLR:
/* only support first port */
if (hw->bus.func != 0)
@@ -7969,10 +8040,6 @@
if (err)
goto err_sw_init;
- /* Cache if MNG FW is up so we don't have to read the REG later */
- if (hw->mac.ops.mng_fw_enabled)
- hw->mng_fw_enabled = hw->mac.ops.mng_fw_enabled(hw);
-
/* Make it possible the adapter to be woken up via WOL */
switch (adapter->hw.mac.type) {
case ixgbe_mac_82599EB:
@@ -8223,7 +8290,7 @@
ixgbe_dbg_adapter_init(adapter);
/* Need link setup for MNG FW, else wait for IXGBE_UP */
- if (hw->mng_fw_enabled && hw->mac.ops.setup_link)
+ if (ixgbe_mng_enabled(hw) && hw->mac.ops.setup_link)
hw->mac.ops.setup_link(hw,
IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL,
true);
@@ -8331,6 +8398,7 @@
struct net_device *netdev = adapter->netdev;
#ifdef CONFIG_PCI_IOV
+ struct ixgbe_hw *hw = &adapter->hw;
struct pci_dev *bdev, *vfdev;
u32 dw0, dw1, dw2, dw3;
int vf, pos;
@@ -8351,10 +8419,12 @@
if (!pos)
goto skip_bad_vf_detection;
- pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG, &dw0);
- pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG + 4, &dw1);
- pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG + 8, &dw2);
- pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG + 12, &dw3);
+ dw0 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG);
+ dw1 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 4);
+ dw2 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 8);
+ dw3 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 12);
+ if (ixgbe_removed(hw->hw_addr))
+ goto skip_bad_vf_detection;
req_id = dw1 >> 16;
/* On the 82599 if bit 7 of the requestor ID is set then it's a VF */
@@ -8446,6 +8516,7 @@
e_err(probe, "Cannot re-enable PCI device after reset.\n");
result = PCI_ERS_RESULT_DISCONNECT;
} else {
+ adapter->hw.hw_addr = adapter->io_addr;
pci_set_master(pdev);
pci_restore_state(pdev);
pci_save_state(pdev);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
index cc3101a..f5c6af2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
index e44ff47..a9b9ad6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 132557c..ad51c12 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -98,6 +99,32 @@
}
/**
+ * ixgbe_check_reset_blocked - check status of MNG FW veto bit
+ * @hw: pointer to the hardware structure
+ *
+ * This function checks the MMNGC.MNG_VETO bit to see if there are
+ * any constraints on link from manageability. For MAC's that don't
+ * have this bit just return false since the link can not be blocked
+ * via this method.
+ **/
+s32 ixgbe_check_reset_blocked(struct ixgbe_hw *hw)
+{
+ u32 mmngc;
+
+ /* If we don't have this bit, it can't be blocking */
+ if (hw->mac.type == ixgbe_mac_82598EB)
+ return false;
+
+ mmngc = IXGBE_READ_REG(hw, IXGBE_MMNGC);
+ if (mmngc & IXGBE_MMNGC_MNG_VETO) {
+ hw_dbg(hw, "MNG_VETO bit detected.\n");
+ return true;
+ }
+
+ return false;
+}
+
+/**
* ixgbe_get_phy_id - Get the phy type
* @hw: pointer to hardware structure
*
@@ -172,6 +199,10 @@
(IXGBE_ERR_OVERTEMP == hw->phy.ops.check_overtemp(hw)))
goto out;
+ /* Blocked by MNG FW so bail */
+ if (ixgbe_check_reset_blocked(hw))
+ goto out;
+
/*
* Perform soft PHY reset to the PHY_XS.
* This will cause a soft reset to the PHY
@@ -476,6 +507,10 @@
autoneg_reg);
}
+ /* Blocked by MNG FW so don't reset PHY */
+ if (ixgbe_check_reset_blocked(hw))
+ return status;
+
/* Restart PHY autonegotiation and wait for completion */
hw->phy.ops.read_reg(hw, MDIO_CTRL1,
MDIO_MMD_AN, &autoneg_reg);
@@ -682,6 +717,10 @@
autoneg_reg);
}
+ /* Blocked by MNG FW so don't reset PHY */
+ if (ixgbe_check_reset_blocked(hw))
+ return status;
+
/* Restart PHY autonegotiation and wait for completion */
hw->phy.ops.read_reg(hw, MDIO_CTRL1,
MDIO_MMD_AN, &autoneg_reg);
@@ -759,6 +798,10 @@
s32 ret_val = 0;
u32 i;
+ /* Blocked by MNG FW so bail */
+ if (ixgbe_check_reset_blocked(hw))
+ goto out;
+
hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_PHYXS, &phy_data);
/* reset the PHY and poll for completion */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
index fffcbdd..4a456c9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -65,9 +66,6 @@
#define IXGBE_SFF_1GBASET_CAPABLE 0x8
#define IXGBE_SFF_10GBASESR_CAPABLE 0x10
#define IXGBE_SFF_10GBASELR_CAPABLE 0x20
-#define IXGBE_SFF_SOFT_RS_SELECT_MASK 0x8
-#define IXGBE_SFF_SOFT_RS_SELECT_10G 0x8
-#define IXGBE_SFF_SOFT_RS_SELECT_1G 0x0
#define IXGBE_SFF_ADDRESSING_MODE 0x4
#define IXGBE_SFF_QSFP_DA_ACTIVE_CABLE 0x1
#define IXGBE_SFF_QSFP_DA_PASSIVE_CABLE 0x8
@@ -79,7 +77,6 @@
#define IXGBE_I2C_EEPROM_STATUS_PASS 0x1
#define IXGBE_I2C_EEPROM_STATUS_FAIL 0x2
#define IXGBE_I2C_EEPROM_STATUS_IN_PROGRESS 0x3
-
/* Flow control defines */
#define IXGBE_TAF_SYM_PAUSE 0x400
#define IXGBE_TAF_ASM_PAUSE 0x800
@@ -131,6 +128,7 @@
s32 ixgbe_get_copper_link_capabilities_generic(struct ixgbe_hw *hw,
ixgbe_link_speed *speed,
bool *autoneg);
+s32 ixgbe_check_reset_blocked(struct ixgbe_hw *hw);
/* PHY specific */
s32 ixgbe_check_phy_link_tnx(struct ixgbe_hw *hw,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index 5184e2a..44ac9ae 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -576,14 +577,21 @@
shhwtstamps->hwtstamp = ns_to_ktime(ns);
}
+int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
+{
+ struct hwtstamp_config *config = &adapter->tstamp_config;
+
+ return copy_to_user(ifr->ifr_data, config,
+ sizeof(*config)) ? -EFAULT : 0;
+}
+
/**
- * ixgbe_ptp_hwtstamp_ioctl - control hardware time stamping
+ * ixgbe_ptp_set_ts_config - control hardware time stamping
* @adapter: pointer to adapter struct
* @ifreq: ioctl data
- * @cmd: particular ioctl requested
*
* Outgoing time stamping can be enabled and disabled. Play nice and
- * disable it when requested, although it shouldn't case any overhead
+ * disable it when requested, although it shouldn't cause any overhead
* when no packet needs it. At most one packet in the queue may be
* marked for time stamping, otherwise it would be impossible to tell
* for sure to which packet the hardware time stamp belongs.
@@ -599,8 +607,7 @@
* Event mode. This more accurately tells the user what the hardware is going
* to do anyways.
*/
-int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter,
- struct ifreq *ifr, int cmd)
+int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
{
struct ixgbe_hw *hw = &adapter->hw;
struct hwtstamp_config config;
@@ -702,6 +709,10 @@
regval = IXGBE_READ_REG(hw, IXGBE_TXSTMPH);
regval = IXGBE_READ_REG(hw, IXGBE_RXSTMPH);
+ /* save these settings for future reference */
+ memcpy(&adapter->tstamp_config, &config,
+ sizeof(adapter->tstamp_config));
+
return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
-EFAULT : 0;
}
@@ -809,6 +820,9 @@
IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0x00000000);
IXGBE_WRITE_FLUSH(hw);
+ /* Reset the saved tstamp_config */
+ memset(&adapter->tstamp_config, 0, sizeof(adapter->tstamp_config));
+
ixgbe_ptp_start_cyclecounter(adapter);
spin_lock_irqsave(&adapter->tmreg_lock, flags);
@@ -840,7 +854,9 @@
switch (adapter->hw.mac.type) {
case ixgbe_mac_X540:
- snprintf(adapter->ptp_caps.name, 16, "%s", netdev->name);
+ snprintf(adapter->ptp_caps.name,
+ sizeof(adapter->ptp_caps.name),
+ "%s", netdev->name);
adapter->ptp_caps.owner = THIS_MODULE;
adapter->ptp_caps.max_adj = 250000000;
adapter->ptp_caps.n_alarm = 0;
@@ -854,7 +870,9 @@
adapter->ptp_caps.enable = ixgbe_ptp_enable;
break;
case ixgbe_mac_82599EB:
- snprintf(adapter->ptp_caps.name, 16, "%s", netdev->name);
+ snprintf(adapter->ptp_caps.name,
+ sizeof(adapter->ptp_caps.name),
+ "%s", netdev->name);
adapter->ptp_caps.owner = THIS_MODULE;
adapter->ptp_caps.max_adj = 250000000;
adapter->ptp_caps.n_alarm = 0;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index dff0977..e6c68d3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
index 8bd2919..139eadd 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c
index e74ae36..ef6df3d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 0d39cfc..8a6ff24 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2013 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -54,6 +55,7 @@
#define IXGBE_DEV_ID_82599_BACKPLANE_FCOE 0x152a
#define IXGBE_DEV_ID_82599_SFP_FCOE 0x1529
#define IXGBE_SUBDEV_ID_82599_SFP 0x11A9
+#define IXGBE_SUBDEV_ID_82599_SFP_WOL0 0x1071
#define IXGBE_SUBDEV_ID_82599_RNDC 0x1F72
#define IXGBE_SUBDEV_ID_82599_560FLR 0x17D0
#define IXGBE_SUBDEV_ID_82599_SP_560FLR 0x211B
@@ -1609,6 +1611,9 @@
#define IXGBE_MACC_FS 0x00040000
#define IXGBE_MAC_RX2TX_LPBK 0x00000002
+/* Veto Bit definiton */
+#define IXGBE_MMNGC_MNG_VETO 0x00000001
+
/* LINKS Bit Masks */
#define IXGBE_LINKS_KX_AN_COMP 0x80000000
#define IXGBE_LINKS_UP 0x40000000
@@ -1788,6 +1793,9 @@
#define IXGBE_EEPROM_RD_BUFFER_MAX_COUNT 512 /* EEPROM words # read in burst */
#define IXGBE_EEPROM_WR_BUFFER_MAX_COUNT 256 /* EEPROM words # wr in burst */
+#define IXGBE_EEPROM_CTRL_2 1 /* EEPROM CTRL word 2 */
+#define IXGBE_EEPROM_CCD_BIT 2 /* EEPROM Core Clock Disable bit */
+
#ifndef IXGBE_EEPROM_GRANT_ATTEMPTS
#define IXGBE_EEPROM_GRANT_ATTEMPTS 1000 /* EEPROM # attempts to gain grant */
#endif
@@ -1853,8 +1861,19 @@
#define IXGBE_PCI_HEADER_TYPE_MULTIFUNC 0x80
#define IXGBE_PCI_DEVICE_CONTROL2_16ms 0x0005
+#define IXGBE_PCIDEVCTRL2_TIMEO_MASK 0xf
+#define IXGBE_PCIDEVCTRL2_16_32ms_def 0x0
+#define IXGBE_PCIDEVCTRL2_50_100us 0x1
+#define IXGBE_PCIDEVCTRL2_1_2ms 0x2
+#define IXGBE_PCIDEVCTRL2_16_32ms 0x5
+#define IXGBE_PCIDEVCTRL2_65_130ms 0x6
+#define IXGBE_PCIDEVCTRL2_260_520ms 0x9
+#define IXGBE_PCIDEVCTRL2_1_2s 0xa
+#define IXGBE_PCIDEVCTRL2_4_8s 0xd
+#define IXGBE_PCIDEVCTRL2_17_34s 0xe
+
/* Number of 100 microseconds we wait for PCI Express master disable */
-#define IXGBE_PCI_MASTER_DISABLE_TIMEOUT 800
+#define IXGBE_PCI_MASTER_DISABLE_TIMEOUT 800
/* RAH */
#define IXGBE_RAH_VIND_MASK 0x003C0000
@@ -2645,7 +2664,6 @@
enum ixgbe_media_type {
ixgbe_media_type_unknown = 0,
ixgbe_media_type_fiber,
- ixgbe_media_type_fiber_fixed,
ixgbe_media_type_fiber_qsfp,
ixgbe_media_type_fiber_lco,
ixgbe_media_type_copper,
@@ -2858,6 +2876,8 @@
s32 (*enable_rx_dma)(struct ixgbe_hw *, u32);
s32 (*acquire_swfw_sync)(struct ixgbe_hw *, u16);
void (*release_swfw_sync)(struct ixgbe_hw *, u16);
+ s32 (*prot_autoc_read)(struct ixgbe_hw *, bool *, u32 *);
+ s32 (*prot_autoc_write)(struct ixgbe_hw *, u32, bool);
/* Link */
void (*disable_tx_laser)(struct ixgbe_hw *);
@@ -2901,7 +2921,6 @@
s32 (*set_fw_drv_ver)(struct ixgbe_hw *, u8, u8, u8, u8);
s32 (*get_thermal_sensor_data)(struct ixgbe_hw *);
s32 (*init_thermal_sensor_thresh)(struct ixgbe_hw *hw);
- bool (*mng_fw_enabled)(struct ixgbe_hw *hw);
};
struct ixgbe_phy_operations {
@@ -2957,7 +2976,6 @@
u32 max_tx_queues;
u32 max_rx_queues;
u32 orig_autoc;
- u32 cached_autoc;
u32 orig_autoc2;
bool orig_link_settings_stored;
bool autotry_restart;
@@ -3033,7 +3051,6 @@
bool adapter_stopped;
bool force_full_reset;
bool allow_unsupported_sfp;
- bool mng_fw_enabled;
bool wol_enabled;
};
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
index 24b80a6..188a597 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
@@ -20,6 +20,7 @@
the file called "COPYING".
Contact Information:
+ Linux NICS <linux.nics@intel.com>
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
@@ -61,6 +62,7 @@
mac->mcft_size = IXGBE_X540_MC_TBL_SIZE;
mac->vft_size = IXGBE_X540_VFT_TBL_SIZE;
mac->num_rar_entries = IXGBE_X540_RAR_ENTRIES;
+ mac->rx_pb_size = IXGBE_X540_RX_PB_SIZE;
mac->max_rx_queues = IXGBE_X540_MAX_RX_QUEUES;
mac->max_tx_queues = IXGBE_X540_MAX_TX_QUEUES;
mac->max_msix_vectors = ixgbe_get_pcie_msix_count_generic(hw);
@@ -187,7 +189,6 @@
goto out;
ret_val = ixgbe_start_hw_gen2(hw);
- hw->mac.rx_pb_size = IXGBE_X540_RX_PB_SIZE;
out:
return ret_val;
}
@@ -854,7 +855,8 @@
.enable_rx_buff = &ixgbe_enable_rx_buff_generic,
.get_thermal_sensor_data = NULL,
.init_thermal_sensor_thresh = NULL,
- .mng_fw_enabled = NULL,
+ .prot_autoc_read = &prot_autoc_read_generic,
+ .prot_autoc_write = &prot_autoc_write_generic,
};
static struct ixgbe_eeprom_operations eeprom_ops_X540 = {
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index f68b78c..b2d0023 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2012 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -530,41 +530,55 @@
0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF
};
-#define REG_PATTERN_TEST(R, M, W) \
-{ \
- u32 pat, val, before; \
- for (pat = 0; pat < ARRAY_SIZE(register_test_patterns); pat++) { \
- before = readl(adapter->hw.hw_addr + R); \
- writel((register_test_patterns[pat] & W), \
- (adapter->hw.hw_addr + R)); \
- val = readl(adapter->hw.hw_addr + R); \
- if (val != (register_test_patterns[pat] & W & M)) { \
- hw_dbg(&adapter->hw, \
- "pattern test reg %04X failed: got " \
- "0x%08X expected 0x%08X\n", \
- R, val, (register_test_patterns[pat] & W & M)); \
- *data = R; \
- writel(before, adapter->hw.hw_addr + R); \
- return 1; \
- } \
- writel(before, adapter->hw.hw_addr + R); \
- } \
+static bool reg_pattern_test(struct ixgbevf_adapter *adapter, u64 *data,
+ int reg, u32 mask, u32 write)
+{
+ u32 pat, val, before;
+
+ if (IXGBE_REMOVED(adapter->hw.hw_addr)) {
+ *data = 1;
+ return true;
+ }
+ for (pat = 0; pat < ARRAY_SIZE(register_test_patterns); pat++) {
+ before = ixgbe_read_reg(&adapter->hw, reg);
+ ixgbe_write_reg(&adapter->hw, reg,
+ register_test_patterns[pat] & write);
+ val = ixgbe_read_reg(&adapter->hw, reg);
+ if (val != (register_test_patterns[pat] & write & mask)) {
+ hw_dbg(&adapter->hw,
+ "pattern test reg %04X failed: got 0x%08X expected 0x%08X\n",
+ reg, val,
+ register_test_patterns[pat] & write & mask);
+ *data = reg;
+ ixgbe_write_reg(&adapter->hw, reg, before);
+ return true;
+ }
+ ixgbe_write_reg(&adapter->hw, reg, before);
+ }
+ return false;
}
-#define REG_SET_AND_CHECK(R, M, W) \
-{ \
- u32 val, before; \
- before = readl(adapter->hw.hw_addr + R); \
- writel((W & M), (adapter->hw.hw_addr + R)); \
- val = readl(adapter->hw.hw_addr + R); \
- if ((W & M) != (val & M)) { \
- pr_err("set/check reg %04X test failed: got 0x%08X expected " \
- "0x%08X\n", R, (val & M), (W & M)); \
- *data = R; \
- writel(before, (adapter->hw.hw_addr + R)); \
- return 1; \
- } \
- writel(before, (adapter->hw.hw_addr + R)); \
+static bool reg_set_and_check(struct ixgbevf_adapter *adapter, u64 *data,
+ int reg, u32 mask, u32 write)
+{
+ u32 val, before;
+
+ if (IXGBE_REMOVED(adapter->hw.hw_addr)) {
+ *data = 1;
+ return true;
+ }
+ before = ixgbe_read_reg(&adapter->hw, reg);
+ ixgbe_write_reg(&adapter->hw, reg, write & mask);
+ val = ixgbe_read_reg(&adapter->hw, reg);
+ if ((write & mask) != (val & mask)) {
+ pr_err("set/check reg %04X test failed: got 0x%08X expected 0x%08X\n",
+ reg, (val & mask), write & mask);
+ *data = reg;
+ ixgbe_write_reg(&adapter->hw, reg, before);
+ return true;
+ }
+ ixgbe_write_reg(&adapter->hw, reg, before);
+ return false;
}
static int ixgbevf_reg_test(struct ixgbevf_adapter *adapter, u64 *data)
@@ -572,6 +586,12 @@
const struct ixgbevf_reg_test *test;
u32 i;
+ if (IXGBE_REMOVED(adapter->hw.hw_addr)) {
+ dev_err(&adapter->pdev->dev,
+ "Adapter removed - register test blocked\n");
+ *data = 1;
+ return 1;
+ }
test = reg_test_vf;
/*
@@ -580,38 +600,47 @@
*/
while (test->reg) {
for (i = 0; i < test->array_len; i++) {
+ bool b = false;
+
switch (test->test_type) {
case PATTERN_TEST:
- REG_PATTERN_TEST(test->reg + (i * 0x40),
- test->mask,
- test->write);
+ b = reg_pattern_test(adapter, data,
+ test->reg + (i * 0x40),
+ test->mask,
+ test->write);
break;
case SET_READ_TEST:
- REG_SET_AND_CHECK(test->reg + (i * 0x40),
- test->mask,
- test->write);
+ b = reg_set_and_check(adapter, data,
+ test->reg + (i * 0x40),
+ test->mask,
+ test->write);
break;
case WRITE_NO_TEST:
- writel(test->write,
- (adapter->hw.hw_addr + test->reg)
- + (i * 0x40));
+ ixgbe_write_reg(&adapter->hw,
+ test->reg + (i * 0x40),
+ test->write);
break;
case TABLE32_TEST:
- REG_PATTERN_TEST(test->reg + (i * 4),
- test->mask,
- test->write);
+ b = reg_pattern_test(adapter, data,
+ test->reg + (i * 4),
+ test->mask,
+ test->write);
break;
case TABLE64_TEST_LO:
- REG_PATTERN_TEST(test->reg + (i * 8),
- test->mask,
- test->write);
+ b = reg_pattern_test(adapter, data,
+ test->reg + (i * 8),
+ test->mask,
+ test->write);
break;
case TABLE64_TEST_HI:
- REG_PATTERN_TEST((test->reg + 4) + (i * 8),
- test->mask,
- test->write);
+ b = reg_pattern_test(adapter, data,
+ test->reg + 4 + (i * 8),
+ test->mask,
+ test->write);
break;
}
+ if (b)
+ return 1;
}
test++;
}
@@ -626,6 +655,14 @@
struct ixgbevf_adapter *adapter = netdev_priv(netdev);
bool if_running = netif_running(netdev);
+ if (IXGBE_REMOVED(adapter->hw.hw_addr)) {
+ dev_err(&adapter->pdev->dev,
+ "Adapter removed - test blocked\n");
+ data[0] = 1;
+ data[1] = 1;
+ eth_test->flags |= ETH_TEST_FL_FAILED;
+ return;
+ }
set_bit(__IXGBEVF_TESTING, &adapter->state);
if (eth_test->flags == ETH_TEST_FL_OFFLINE) {
/* Offline tests */
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index 5482932..a08bd7c 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2012 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -315,6 +315,11 @@
return ((ntc > ntu) ? 0 : ring->count) + ntc - ntu - 1;
}
+static inline void ixgbevf_write_tail(struct ixgbevf_ring *ring, u32 value)
+{
+ writel(value, ring->tail);
+}
+
#define IXGBEVF_RX_DESC(R, i) \
(&(((union ixgbe_adv_rx_desc *)((R)->desc))[i]))
#define IXGBEVF_TX_DESC(R, i) \
@@ -401,6 +406,7 @@
u64 bp_tx_missed;
#endif
+ u8 __iomem *io_addr; /* Mainly for iounmap use */
u32 link_speed;
bool link_up;
@@ -412,7 +418,8 @@
enum ixbgevf_state_t {
__IXGBEVF_TESTING,
__IXGBEVF_RESETTING,
- __IXGBEVF_DOWN
+ __IXGBEVF_DOWN,
+ __IXGBEVF_REMOVING,
};
struct ixgbevf_cb {
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 9df2898..a50e892 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2012 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -99,6 +99,49 @@
static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector);
static void ixgbevf_free_all_rx_resources(struct ixgbevf_adapter *adapter);
+static void ixgbevf_remove_adapter(struct ixgbe_hw *hw)
+{
+ struct ixgbevf_adapter *adapter = hw->back;
+
+ if (!hw->hw_addr)
+ return;
+ hw->hw_addr = NULL;
+ dev_err(&adapter->pdev->dev, "Adapter removed\n");
+ schedule_work(&adapter->watchdog_task);
+}
+
+static void ixgbevf_check_remove(struct ixgbe_hw *hw, u32 reg)
+{
+ u32 value;
+
+ /* The following check not only optimizes a bit by not
+ * performing a read on the status register when the
+ * register just read was a status register read that
+ * returned IXGBE_FAILED_READ_REG. It also blocks any
+ * potential recursion.
+ */
+ if (reg == IXGBE_VFSTATUS) {
+ ixgbevf_remove_adapter(hw);
+ return;
+ }
+ value = ixgbe_read_reg(hw, IXGBE_VFSTATUS);
+ if (value == IXGBE_FAILED_READ_REG)
+ ixgbevf_remove_adapter(hw);
+}
+
+u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg)
+{
+ u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr);
+ u32 value;
+
+ if (IXGBE_REMOVED(reg_addr))
+ return IXGBE_FAILED_READ_REG;
+ value = readl(reg_addr + reg);
+ if (unlikely(value == IXGBE_FAILED_READ_REG))
+ ixgbevf_check_remove(hw, reg);
+ return value;
+}
+
static inline void ixgbevf_release_rx_desc(struct ixgbevf_ring *rx_ring,
u32 val)
{
@@ -111,7 +154,7 @@
* such as IA-64).
*/
wmb();
- writel(val, rx_ring->tail);
+ ixgbevf_write_tail(rx_ring, val);
}
/**
@@ -516,7 +559,8 @@
/* Workaround hardware that can't do proper VEPA multicast
* source pruning.
*/
- if ((skb->pkt_type & (PACKET_BROADCAST | PACKET_MULTICAST)) &&
+ if ((skb->pkt_type == PACKET_BROADCAST ||
+ skb->pkt_type == PACKET_MULTICAST) &&
ether_addr_equal(rx_ring->netdev->dev_addr,
eth_hdr(skb)->h_source)) {
dev_kfree_skb_irq(skb);
@@ -607,7 +651,8 @@
napi_complete(napi);
if (adapter->rx_itr_setting & 1)
ixgbevf_set_itr(q_vector);
- if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
+ if (!test_bit(__IXGBEVF_DOWN, &adapter->state) &&
+ !test_bit(__IXGBEVF_REMOVING, &adapter->state))
ixgbevf_irq_enable_queues(adapter,
1 << q_vector->v_idx);
@@ -832,7 +877,8 @@
hw->mac.get_link_status = 1;
- if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
+ if (!test_bit(__IXGBEVF_DOWN, &adapter->state) &&
+ !test_bit(__IXGBEVF_REMOVING, &adapter->state))
mod_timer(&adapter->watchdog_timer, jiffies);
IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_other);
@@ -1136,7 +1182,7 @@
/* reset head and tail pointers */
IXGBE_WRITE_REG(hw, IXGBE_VFTDH(reg_idx), 0);
IXGBE_WRITE_REG(hw, IXGBE_VFTDT(reg_idx), 0);
- ring->tail = hw->hw_addr + IXGBE_VFTDT(reg_idx);
+ ring->tail = adapter->io_addr + IXGBE_VFTDT(reg_idx);
/* reset ntu and ntc to place SW in sync with hardwdare */
ring->next_to_clean = 0;
@@ -1256,6 +1302,8 @@
u32 rxdctl;
u8 reg_idx = ring->reg_idx;
+ if (IXGBE_REMOVED(hw->hw_addr))
+ return;
rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx));
rxdctl &= ~IXGBE_RXDCTL_ENABLE;
@@ -1281,6 +1329,8 @@
u32 rxdctl;
u8 reg_idx = ring->reg_idx;
+ if (IXGBE_REMOVED(hw->hw_addr))
+ return;
do {
usleep_range(1000, 2000);
rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx));
@@ -1315,7 +1365,7 @@
/* reset head and tail pointers */
IXGBE_WRITE_REG(hw, IXGBE_VFRDH(reg_idx), 0);
IXGBE_WRITE_REG(hw, IXGBE_VFRDT(reg_idx), 0);
- ring->tail = hw->hw_addr + IXGBE_VFRDT(reg_idx);
+ ring->tail = adapter->io_addr + IXGBE_VFRDT(reg_idx);
/* reset ntu and ntc to place SW in sync with hardwdare */
ring->next_to_clean = 0;
@@ -1617,6 +1667,7 @@
spin_unlock_bh(&adapter->mbx_lock);
+ smp_mb__before_clear_bit();
clear_bit(__IXGBEVF_DOWN, &adapter->state);
ixgbevf_napi_enable_all(adapter);
@@ -1741,7 +1792,8 @@
int i;
/* signal that we are down to the interrupt handler */
- set_bit(__IXGBEVF_DOWN, &adapter->state);
+ if (test_and_set_bit(__IXGBEVF_DOWN, &adapter->state))
+ return; /* do nothing if already down */
/* disable all enabled rx queues */
for (i = 0; i < adapter->num_rx_queues; i++)
@@ -1817,7 +1869,6 @@
static int ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter,
int vectors)
{
- int err = 0;
int vector_threshold;
/* We'll want at least 2 (vector_threshold):
@@ -1831,33 +1882,24 @@
* Right now, we simply care about how many we'll get; we'll
* set them up later while requesting irq's.
*/
- while (vectors >= vector_threshold) {
- err = pci_enable_msix(adapter->pdev, adapter->msix_entries,
- vectors);
- if (!err || err < 0) /* Success or a nasty failure. */
- break;
- else /* err == number of vectors we should try again with */
- vectors = err;
- }
+ vectors = pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
+ vector_threshold, vectors);
- if (vectors < vector_threshold)
- err = -ENOMEM;
-
- if (err) {
+ if (vectors < 0) {
dev_err(&adapter->pdev->dev,
"Unable to allocate MSI-X interrupts\n");
kfree(adapter->msix_entries);
adapter->msix_entries = NULL;
- } else {
- /*
- * Adjust for only the vectors we'll use, which is minimum
- * of max_msix_q_vectors + NON_Q_VECTORS, or the number of
- * vectors we were allocated.
- */
- adapter->num_msix_vectors = vectors;
+ return vectors;
}
- return err;
+ /* Adjust for only the vectors we'll use, which is minimum
+ * of max_msix_q_vectors + NON_Q_VECTORS, or the number of
+ * vectors we were allocated.
+ */
+ adapter->num_msix_vectors = vectors;
+
+ return 0;
}
/**
@@ -2338,6 +2380,7 @@
/* If we're already down or resetting, just bail */
if (test_bit(__IXGBEVF_DOWN, &adapter->state) ||
+ test_bit(__IXGBEVF_REMOVING, &adapter->state) ||
test_bit(__IXGBEVF_RESETTING, &adapter->state))
return;
@@ -2361,6 +2404,14 @@
bool link_up = adapter->link_up;
s32 need_reset;
+ if (IXGBE_REMOVED(hw->hw_addr)) {
+ if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) {
+ rtnl_lock();
+ ixgbevf_down(adapter);
+ rtnl_unlock();
+ }
+ return;
+ }
ixgbevf_queue_reset_subtask(adapter);
adapter->flags |= IXGBE_FLAG_IN_WATCHDOG_TASK;
@@ -2422,7 +2473,8 @@
pf_has_reset:
/* Reset the timer */
- if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
+ if (!test_bit(__IXGBEVF_DOWN, &adapter->state) &&
+ !test_bit(__IXGBEVF_REMOVING, &adapter->state))
mod_timer(&adapter->watchdog_timer,
round_jiffies(jiffies + (2 * HZ)));
@@ -2787,6 +2839,9 @@
u32 vlan_macip_lens, type_tucmd;
u32 mss_l4len_idx, l4len;
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ return 0;
+
if (!skb_is_gso(skb))
return 0;
@@ -2857,12 +2912,12 @@
if (skb->ip_summed == CHECKSUM_PARTIAL) {
u8 l4_hdr = 0;
switch (skb->protocol) {
- case __constant_htons(ETH_P_IP):
+ case htons(ETH_P_IP):
vlan_macip_lens |= skb_network_header_len(skb);
type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4;
l4_hdr = ip_hdr(skb)->protocol;
break;
- case __constant_htons(ETH_P_IPV6):
+ case htons(ETH_P_IPV6):
vlan_macip_lens |= skb_network_header_len(skb);
l4_hdr = ipv6_hdr(skb)->nexthdr;
break;
@@ -3060,7 +3115,7 @@
tx_ring->next_to_use = i;
/* notify HW of packet */
- writel(i, tx_ring->tail);
+ ixgbevf_write_tail(tx_ring, i);
return;
dma_error:
@@ -3165,7 +3220,7 @@
tso = ixgbevf_tso(tx_ring, first, &hdr_len);
if (tso < 0)
goto out_drop;
- else
+ else if (!tso)
ixgbevf_tx_csum(tx_ring, first);
ixgbevf_tx_map(tx_ring, first, hdr_len);
@@ -3286,7 +3341,6 @@
struct ixgbevf_adapter *adapter = netdev_priv(netdev);
u32 err;
- pci_set_power_state(pdev, PCI_D0);
pci_restore_state(pdev);
/*
* pci_restore_state clears dev->state_saved so call
@@ -3344,10 +3398,10 @@
for (i = 0; i < adapter->num_rx_queues; i++) {
ring = adapter->rx_ring[i];
do {
- start = u64_stats_fetch_begin_bh(&ring->syncp);
+ start = u64_stats_fetch_begin_irq(&ring->syncp);
bytes = ring->stats.bytes;
packets = ring->stats.packets;
- } while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&ring->syncp, start));
stats->rx_bytes += bytes;
stats->rx_packets += packets;
}
@@ -3355,10 +3409,10 @@
for (i = 0; i < adapter->num_tx_queues; i++) {
ring = adapter->tx_ring[i];
do {
- start = u64_stats_fetch_begin_bh(&ring->syncp);
+ start = u64_stats_fetch_begin_irq(&ring->syncp);
bytes = ring->stats.bytes;
packets = ring->stats.packets;
- } while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&ring->syncp, start));
stats->tx_bytes += bytes;
stats->tx_packets += packets;
}
@@ -3460,6 +3514,7 @@
hw->hw_addr = ioremap(pci_resource_start(pdev, 0),
pci_resource_len(pdev, 0));
+ adapter->io_addr = hw->hw_addr;
if (!hw->hw_addr) {
err = -EIO;
goto err_ioremap;
@@ -3545,7 +3600,7 @@
ixgbevf_clear_interrupt_scheme(adapter);
err_sw_init:
ixgbevf_reset_interrupt_capability(adapter);
- iounmap(hw->hw_addr);
+ iounmap(adapter->io_addr);
err_ioremap:
free_netdev(netdev);
err_alloc_etherdev:
@@ -3570,7 +3625,7 @@
struct net_device *netdev = pci_get_drvdata(pdev);
struct ixgbevf_adapter *adapter = netdev_priv(netdev);
- set_bit(__IXGBEVF_DOWN, &adapter->state);
+ set_bit(__IXGBEVF_REMOVING, &adapter->state);
del_timer_sync(&adapter->watchdog_timer);
@@ -3583,7 +3638,7 @@
ixgbevf_clear_interrupt_scheme(adapter);
ixgbevf_reset_interrupt_capability(adapter);
- iounmap(adapter->hw.hw_addr);
+ iounmap(adapter->io_addr);
pci_release_regions(pdev);
hw_dbg(&adapter->hw, "Remove complete\n");
diff --git a/drivers/net/ethernet/intel/ixgbevf/regs.h b/drivers/net/ethernet/intel/ixgbevf/regs.h
index debd8c0..09dd8f6 100644
--- a/drivers/net/ethernet/intel/ixgbevf/regs.h
+++ b/drivers/net/ethernet/intel/ixgbevf/regs.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2012 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -70,16 +70,6 @@
#define IXGBE_VFGOTC_MSB 0x02024
#define IXGBE_VFMPRC 0x01034
-#define IXGBE_WRITE_REG(a, reg, value) writel((value), ((a)->hw_addr + (reg)))
-
-#define IXGBE_READ_REG(a, reg) readl((a)->hw_addr + (reg))
-
-#define IXGBE_WRITE_REG_ARRAY(a, reg, offset, value) ( \
- writel((value), ((a)->hw_addr + (reg) + ((offset) << 2))))
-
-#define IXGBE_READ_REG_ARRAY(a, reg, offset) ( \
- readl((a)->hw_addr + (reg) + ((offset) << 2)))
-
#define IXGBE_WRITE_FLUSH(a) (IXGBE_READ_REG(a, IXGBE_VFSTATUS))
#endif /* _IXGBEVF_REGS_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h
index 7b1f502..096d33a 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2012 Intel Corporation.
+ Copyright(c) 1999 - 2014 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -172,6 +172,37 @@
const struct ixgbe_mac_operations *mac_ops;
};
+#define IXGBE_FAILED_READ_REG 0xffffffffU
+
+#define IXGBE_REMOVED(a) unlikely(!(a))
+
+static inline void ixgbe_write_reg(struct ixgbe_hw *hw, u32 reg, u32 value)
+{
+ u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr);
+
+ if (IXGBE_REMOVED(reg_addr))
+ return;
+ writel(value, reg_addr + reg);
+}
+#define IXGBE_WRITE_REG(h, r, v) ixgbe_write_reg(h, r, v)
+
+u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg);
+#define IXGBE_READ_REG(h, r) ixgbe_read_reg(h, r)
+
+static inline void ixgbe_write_reg_array(struct ixgbe_hw *hw, u32 reg,
+ u32 offset, u32 value)
+{
+ ixgbe_write_reg(hw, reg + (offset << 2), value);
+}
+#define IXGBE_WRITE_REG_ARRAY(h, r, o, v) ixgbe_write_reg_array(h, r, o, v)
+
+static inline u32 ixgbe_read_reg_array(struct ixgbe_hw *hw, u32 reg,
+ u32 offset)
+{
+ return ixgbe_read_reg(hw, reg + (offset << 2));
+}
+#define IXGBE_READ_REG_ARRAY(h, r, o) ixgbe_read_reg_array(h, r, o)
+
void ixgbevf_rlpml_set_vf(struct ixgbe_hw *hw, u16 max_size);
int ixgbevf_negotiate_api_version(struct ixgbe_hw *hw, int api);
int ixgbevf_get_queues(struct ixgbe_hw *hw, unsigned int *num_tcs,
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index f5685c0..b0c6050 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -2054,19 +2054,6 @@
}
static int
-jme_expand_header(struct jme_adapter *jme, struct sk_buff *skb)
-{
- if (unlikely(skb_shinfo(skb)->gso_size &&
- skb_header_cloned(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) {
- dev_kfree_skb(skb);
- return -1;
- }
-
- return 0;
-}
-
-static int
jme_tx_tso(struct sk_buff *skb, __le16 *mss, u8 *flags)
{
*mss = cpu_to_le16(skb_shinfo(skb)->gso_size << TXDESC_MSS_SHIFT);
@@ -2225,7 +2212,8 @@
struct jme_adapter *jme = netdev_priv(netdev);
int idx;
- if (unlikely(jme_expand_header(jme, skb))) {
+ if (unlikely(skb_is_gso(skb) && skb_cow_head(skb, 0))) {
+ dev_kfree_skb_any(skb);
++(NET_STAT(jme).tx_dropped);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 8f9266c..fd4b6ae 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -619,7 +619,7 @@
static u16
ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv, select_queue_fallback_t fallback)
{
/* we are currently only using the first queue */
return 0;
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index 6300fd2..68e6a66 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -43,12 +43,12 @@
This driver is used by the MV643XX_ETH and MVNETA drivers.
config MVNETA
- tristate "Marvell Armada 370/XP network interface support"
- depends on MACH_ARMADA_370_XP
+ tristate "Marvell Armada 370/38x/XP network interface support"
+ depends on PLAT_ORION
select MVMDIO
---help---
This driver supports the network interface units in the
- Marvell ARMADA XP and ARMADA 370 SoC family.
+ Marvell ARMADA XP, ARMADA 370 and ARMADA 38x SoC family.
Note that this driver is distinct from the mv643xx_eth
driver, which should be used for the older Marvell SoCs
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index a2565ce..b7b8d74 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -730,7 +730,7 @@
unlikely(tag_bytes & ~12)) {
if (skb_checksum_help(skb) == 0)
goto no_csum;
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return 1;
}
@@ -819,7 +819,7 @@
if (txq->tx_ring_size - txq->tx_desc_count < MAX_SKB_FRAGS + 1) {
if (net_ratelimit())
netdev_err(dev, "tx queue full?!\n");
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index fd409d7..b161a52 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -167,11 +167,6 @@
return ret;
}
-static int orion_mdio_reset(struct mii_bus *bus)
-{
- return 0;
-}
-
static irqreturn_t orion_mdio_err_irq(int irq, void *dev_id)
{
struct orion_mdio_dev *dev = dev_id;
@@ -209,7 +204,6 @@
bus->name = "orion_mdio_bus";
bus->read = orion_mdio_read;
bus->write = orion_mdio_write;
- bus->reset = orion_mdio_reset;
snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii",
dev_name(&pdev->dev));
bus->parent = &pdev->dev;
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index f418f4f..d04b1c3 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -22,6 +22,7 @@
#include <linux/interrupt.h>
#include <net/ip.h>
#include <net/ipv6.h>
+#include <linux/io.h>
#include <linux/of.h>
#include <linux/of_irq.h>
#include <linux/of_mdio.h>
@@ -88,8 +89,9 @@
#define MVNETA_TX_IN_PRGRS BIT(1)
#define MVNETA_TX_FIFO_EMPTY BIT(8)
#define MVNETA_RX_MIN_FRAME_SIZE 0x247c
-#define MVNETA_SGMII_SERDES_CFG 0x24A0
+#define MVNETA_SERDES_CFG 0x24A0
#define MVNETA_SGMII_SERDES_PROTO 0x0cc7
+#define MVNETA_RGMII_SERDES_PROTO 0x0667
#define MVNETA_TYPE_PRIO 0x24bc
#define MVNETA_FORCE_UNI BIT(21)
#define MVNETA_TXQ_CMD_1 0x24e4
@@ -161,7 +163,7 @@
#define MVNETA_GMAC_MAX_RX_SIZE_MASK 0x7ffc
#define MVNETA_GMAC0_PORT_ENABLE BIT(0)
#define MVNETA_GMAC_CTRL_2 0x2c08
-#define MVNETA_GMAC2_PSC_ENABLE BIT(3)
+#define MVNETA_GMAC2_PCS_ENABLE BIT(3)
#define MVNETA_GMAC2_PORT_RGMII BIT(4)
#define MVNETA_GMAC2_PORT_RESET BIT(6)
#define MVNETA_GMAC_STATUS 0x2c10
@@ -508,12 +510,12 @@
cpu_stats = per_cpu_ptr(pp->stats, cpu);
do {
- start = u64_stats_fetch_begin_bh(&cpu_stats->syncp);
+ start = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
rx_packets = cpu_stats->rx_packets;
rx_bytes = cpu_stats->rx_bytes;
tx_packets = cpu_stats->tx_packets;
tx_bytes = cpu_stats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&cpu_stats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start));
stats->rx_packets += rx_packets;
stats->rx_bytes += rx_bytes;
@@ -710,35 +712,6 @@
mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
}
-
-
-/* Sets the RGMII Enable bit (RGMIIEn) in port MAC control register */
-static void mvneta_gmac_rgmii_set(struct mvneta_port *pp, int enable)
-{
- u32 val;
-
- val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
-
- if (enable)
- val |= MVNETA_GMAC2_PORT_RGMII;
- else
- val &= ~MVNETA_GMAC2_PORT_RGMII;
-
- mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
-}
-
-/* Config SGMII port */
-static void mvneta_port_sgmii_config(struct mvneta_port *pp)
-{
- u32 val;
-
- val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
- val |= MVNETA_GMAC2_PSC_ENABLE;
- mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
-
- mvreg_write(pp, MVNETA_SGMII_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
-}
-
/* Start the Ethernet port RX and TX activity */
static void mvneta_port_up(struct mvneta_port *pp)
{
@@ -2756,12 +2729,15 @@
mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0);
if (phy_mode == PHY_INTERFACE_MODE_SGMII)
- mvneta_port_sgmii_config(pp);
+ mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
+ else
+ mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_RGMII_SERDES_PROTO);
- mvneta_gmac_rgmii_set(pp, 1);
+ val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+
+ val |= MVNETA_GMAC2_PCS_ENABLE | MVNETA_GMAC2_PORT_RGMII;
/* Cancel Port Reset */
- val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
val &= ~MVNETA_GMAC2_PORT_RESET;
mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
@@ -2774,6 +2750,7 @@
static int mvneta_probe(struct platform_device *pdev)
{
const struct mbus_dram_target_info *dram_target_info;
+ struct resource *res;
struct device_node *dn = pdev->dev.of_node;
struct device_node *phy_node;
u32 phy_addr;
@@ -2784,7 +2761,6 @@
const char *mac_from;
int phy_mode;
int err;
- int cpu;
/* Our multiqueue support is not complete, so for now, only
* allow the usage of the first RX queue
@@ -2838,23 +2814,18 @@
clk_prepare_enable(pp->clk);
- pp->base = of_iomap(dn, 0);
- if (pp->base == NULL) {
- err = -ENOMEM;
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ pp->base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(pp->base)) {
+ err = PTR_ERR(pp->base);
goto err_clk;
}
/* Alloc per-cpu stats */
- pp->stats = alloc_percpu(struct mvneta_pcpu_stats);
+ pp->stats = netdev_alloc_pcpu_stats(struct mvneta_pcpu_stats);
if (!pp->stats) {
err = -ENOMEM;
- goto err_unmap;
- }
-
- for_each_possible_cpu(cpu) {
- struct mvneta_pcpu_stats *stats;
- stats = per_cpu_ptr(pp->stats, cpu);
- u64_stats_init(&stats->syncp);
+ goto err_clk;
}
dt_mac_addr = of_get_mac_address(dn);
@@ -2913,8 +2884,6 @@
mvneta_deinit(pp);
err_free_stats:
free_percpu(pp->stats);
-err_unmap:
- iounmap(pp->base);
err_clk:
clk_disable_unprepare(pp->clk);
err_free_irq:
@@ -2934,7 +2903,6 @@
mvneta_deinit(pp);
clk_disable_unprepare(pp->clk);
free_percpu(pp->stats);
- iounmap(pp->base);
irq_dispose_mapping(dev->irq);
free_netdev(dev);
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 5978461..7f81ae6 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -2845,7 +2845,7 @@
mapping_error:
if (net_ratelimit())
dev_warn(&hw->pdev->dev, "%s: tx mapping error\n", dev->name);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -3172,7 +3172,7 @@
pkts_compl++;
bytes_compl += e->skb->len;
- dev_kfree_skb(e->skb);
+ dev_consume_skb_any(e->skb);
}
}
netdev_completed_queue(dev, pkts_compl, bytes_compl);
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 55a37ae..b811064 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -44,6 +44,8 @@
#include <linux/prefetch.h>
#include <linux/debugfs.h>
#include <linux/mii.h>
+#include <linux/of_device.h>
+#include <linux/of_net.h>
#include <asm/irq.h>
@@ -2000,7 +2002,7 @@
mapping_error:
if (net_ratelimit())
dev_warn(&hw->pdev->dev, "%s: tx mapping error\n", dev->name);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -2733,6 +2735,9 @@
unsigned int total_bytes[2] = { 0 };
unsigned int total_packets[2] = { 0 };
+ if (to_do <= 0)
+ return work_done;
+
rmb();
do {
struct sky2_port *sky2;
@@ -3906,19 +3911,19 @@
u64 _bytes, _packets;
do {
- start = u64_stats_fetch_begin_bh(&sky2->rx_stats.syncp);
+ start = u64_stats_fetch_begin_irq(&sky2->rx_stats.syncp);
_bytes = sky2->rx_stats.bytes;
_packets = sky2->rx_stats.packets;
- } while (u64_stats_fetch_retry_bh(&sky2->rx_stats.syncp, start));
+ } while (u64_stats_fetch_retry_irq(&sky2->rx_stats.syncp, start));
stats->rx_packets = _packets;
stats->rx_bytes = _bytes;
do {
- start = u64_stats_fetch_begin_bh(&sky2->tx_stats.syncp);
+ start = u64_stats_fetch_begin_irq(&sky2->tx_stats.syncp);
_bytes = sky2->tx_stats.bytes;
_packets = sky2->tx_stats.packets;
- } while (u64_stats_fetch_retry_bh(&sky2->tx_stats.syncp, start));
+ } while (u64_stats_fetch_retry_irq(&sky2->tx_stats.syncp, start));
stats->tx_packets = _packets;
stats->tx_bytes = _bytes;
@@ -4748,6 +4753,7 @@
{
struct sky2_port *sky2;
struct net_device *dev = alloc_etherdev(sizeof(*sky2));
+ const void *iap;
if (!dev)
return NULL;
@@ -4805,8 +4811,16 @@
dev->features |= dev->hw_features;
- /* read the mac address */
- memcpy_fromio(dev->dev_addr, hw->regs + B2_MAC_1 + port * 8, ETH_ALEN);
+ /* try to get mac address in the following order:
+ * 1) from device tree data
+ * 2) from internal registers set by bootloader
+ */
+ iap = of_get_mac_address(hw->pdev->dev.of_node);
+ if (iap)
+ memcpy(dev->dev_addr, iap, ETH_ALEN);
+ else
+ memcpy_fromio(dev->dev_addr, hw->regs + B2_MAC_1 + port * 8,
+ ETH_ALEN);
return dev;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig
index 563495d..1a6e188 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig
@@ -3,7 +3,7 @@
#
config MLX4_EN
- tristate "Mellanox Technologies 10Gbit Ethernet support"
+ tristate "Mellanox Technologies 1/10/40Gbit Ethernet support"
depends on PCI
select MLX4_CORE
select PTP_1588_CLOCK
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 0d02fba..78099ea 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -800,16 +800,7 @@
vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
}
-static int MLX4_CMD_UPDATE_QP_wrapper(struct mlx4_dev *dev, int slave,
- struct mlx4_vhcr *vhcr,
- struct mlx4_cmd_mailbox *inbox,
- struct mlx4_cmd_mailbox *outbox,
- struct mlx4_cmd_info *cmd)
-{
- return -EPERM;
-}
-
-static int MLX4_CMD_GET_OP_REQ_wrapper(struct mlx4_dev *dev, int slave,
+static int mlx4_CMD_EPERM_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
@@ -964,6 +955,15 @@
.wrapper = NULL
},
{
+ .opcode = MLX4_CMD_CONFIG_DEV,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_CMD_EPERM_wrapper
+ },
+ {
.opcode = MLX4_CMD_ALLOC_RES,
.has_inbox = false,
.has_outbox = false,
@@ -1258,7 +1258,7 @@
.out_is_imm = false,
.encode_slave_id = false,
.verify = NULL,
- .wrapper = MLX4_CMD_UPDATE_QP_wrapper
+ .wrapper = mlx4_CMD_EPERM_wrapper
},
{
.opcode = MLX4_CMD_GET_OP_REQ,
@@ -1267,7 +1267,7 @@
.out_is_imm = false,
.encode_slave_id = false,
.verify = NULL,
- .wrapper = MLX4_CMD_GET_OP_REQ_wrapper,
+ .wrapper = mlx4_CMD_EPERM_wrapper,
},
{
.opcode = MLX4_CMD_CONF_SPECIAL_QP,
@@ -1378,7 +1378,7 @@
.out_is_imm = false,
.encode_slave_id = false,
.verify = NULL,
- .wrapper = mlx4_FLOW_STEERING_IB_UC_QP_RANGE_wrapper
+ .wrapper = mlx4_CMD_EPERM_wrapper
},
};
@@ -1643,8 +1643,16 @@
int port, err;
struct mlx4_vport_state *vp_admin;
struct mlx4_vport_oper_state *vp_oper;
+ struct mlx4_active_ports actv_ports = mlx4_get_active_ports(
+ &priv->dev, slave);
+ int min_port = find_first_bit(actv_ports.ports,
+ priv->dev.caps.num_ports) + 1;
+ int max_port = min_port - 1 +
+ bitmap_weight(actv_ports.ports, priv->dev.caps.num_ports);
- for (port = 1; port <= MLX4_MAX_PORTS; port++) {
+ for (port = min_port; port <= max_port; port++) {
+ if (!test_bit(port - 1, actv_ports.ports))
+ continue;
vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
vp_admin = &priv->mfunc.master.vf_admin[slave].vport[port];
vp_oper->state = *vp_admin;
@@ -1685,8 +1693,17 @@
{
int port;
struct mlx4_vport_oper_state *vp_oper;
+ struct mlx4_active_ports actv_ports = mlx4_get_active_ports(
+ &priv->dev, slave);
+ int min_port = find_first_bit(actv_ports.ports,
+ priv->dev.caps.num_ports) + 1;
+ int max_port = min_port - 1 +
+ bitmap_weight(actv_ports.ports, priv->dev.caps.num_ports);
- for (port = 1; port <= MLX4_MAX_PORTS; port++) {
+
+ for (port = min_port; port <= max_port; port++) {
+ if (!test_bit(port - 1, actv_ports.ports))
+ continue;
vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
if (NO_INDX != vp_oper->vlan_idx) {
__mlx4_unregister_vlan(&priv->dev,
@@ -2234,6 +2251,112 @@
return vf+1;
}
+int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave)
+{
+ if (slave < 1 || slave > dev->num_vfs) {
+ mlx4_err(dev,
+ "Bad slave number:%d (number of activated slaves: %lu)\n",
+ slave, dev->num_slaves);
+ return -EINVAL;
+ }
+ return slave - 1;
+}
+
+struct mlx4_active_ports mlx4_get_active_ports(struct mlx4_dev *dev, int slave)
+{
+ struct mlx4_active_ports actv_ports;
+ int vf;
+
+ bitmap_zero(actv_ports.ports, MLX4_MAX_PORTS);
+
+ if (slave == 0) {
+ bitmap_fill(actv_ports.ports, dev->caps.num_ports);
+ return actv_ports;
+ }
+
+ vf = mlx4_get_vf_indx(dev, slave);
+ if (vf < 0)
+ return actv_ports;
+
+ bitmap_set(actv_ports.ports, dev->dev_vfs[vf].min_port - 1,
+ min((int)dev->dev_vfs[mlx4_get_vf_indx(dev, slave)].n_ports,
+ dev->caps.num_ports));
+
+ return actv_ports;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_active_ports);
+
+int mlx4_slave_convert_port(struct mlx4_dev *dev, int slave, int port)
+{
+ unsigned n;
+ struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave);
+ unsigned m = bitmap_weight(actv_ports.ports, dev->caps.num_ports);
+
+ if (port <= 0 || port > m)
+ return -EINVAL;
+
+ n = find_first_bit(actv_ports.ports, dev->caps.num_ports);
+ if (port <= n)
+ port = n + 1;
+
+ return port;
+}
+EXPORT_SYMBOL_GPL(mlx4_slave_convert_port);
+
+int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port)
+{
+ struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave);
+ if (test_bit(port - 1, actv_ports.ports))
+ return port -
+ find_first_bit(actv_ports.ports, dev->caps.num_ports);
+
+ return -1;
+}
+EXPORT_SYMBOL_GPL(mlx4_phys_to_slave_port);
+
+struct mlx4_slaves_pport mlx4_phys_to_slaves_pport(struct mlx4_dev *dev,
+ int port)
+{
+ unsigned i;
+ struct mlx4_slaves_pport slaves_pport;
+
+ bitmap_zero(slaves_pport.slaves, MLX4_MFUNC_MAX);
+
+ if (port <= 0 || port > dev->caps.num_ports)
+ return slaves_pport;
+
+ for (i = 0; i < dev->num_vfs + 1; i++) {
+ struct mlx4_active_ports actv_ports =
+ mlx4_get_active_ports(dev, i);
+ if (test_bit(port - 1, actv_ports.ports))
+ set_bit(i, slaves_pport.slaves);
+ }
+
+ return slaves_pport;
+}
+EXPORT_SYMBOL_GPL(mlx4_phys_to_slaves_pport);
+
+struct mlx4_slaves_pport mlx4_phys_to_slaves_pport_actv(
+ struct mlx4_dev *dev,
+ const struct mlx4_active_ports *crit_ports)
+{
+ unsigned i;
+ struct mlx4_slaves_pport slaves_pport;
+
+ bitmap_zero(slaves_pport.slaves, MLX4_MFUNC_MAX);
+
+ for (i = 0; i < dev->num_vfs + 1; i++) {
+ struct mlx4_active_ports actv_ports =
+ mlx4_get_active_ports(dev, i);
+ if (bitmap_equal(crit_ports->ports, actv_ports.ports,
+ dev->caps.num_ports))
+ set_bit(i, slaves_pport.slaves);
+ }
+
+ return slaves_pport;
+}
+EXPORT_SYMBOL_GPL(mlx4_phys_to_slaves_pport_actv);
+
int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac)
{
struct mlx4_priv *priv = mlx4_priv(dev);
@@ -2289,6 +2412,30 @@
}
EXPORT_SYMBOL_GPL(mlx4_set_vf_vlan);
+ /* mlx4_get_slave_default_vlan -
+ * return true if VST ( default vlan)
+ * if VST, will return vlan & qos (if not NULL)
+ */
+bool mlx4_get_slave_default_vlan(struct mlx4_dev *dev, int port, int slave,
+ u16 *vlan, u8 *qos)
+{
+ struct mlx4_vport_oper_state *vp_oper;
+ struct mlx4_priv *priv;
+
+ priv = mlx4_priv(dev);
+ vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
+
+ if (MLX4_VGT != vp_oper->state.default_vlan) {
+ if (vlan)
+ *vlan = vp_oper->state.default_vlan;
+ if (qos)
+ *qos = vp_oper->state.default_qos;
+ return true;
+ }
+ return false;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_slave_default_vlan);
+
int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting)
{
struct mlx4_priv *priv = mlx4_priv(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index abaf6bb..57dda95 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -276,6 +276,7 @@
.n_alarm = 0,
.n_ext_ts = 0,
.n_per_out = 0,
+ .n_pins = 0,
.pps = 0,
.adjfreq = mlx4_en_phc_adjfreq,
.adjtime = mlx4_en_phc_adjtime,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
index b4881b6..c95ca25 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -62,7 +62,7 @@
int has_ets_tc = 0;
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
- if (ets->prio_tc[i] > MLX4_EN_NUM_UP) {
+ if (ets->prio_tc[i] >= MLX4_EN_NUM_UP) {
en_err(priv, "Bad priority in UP <=> TC mapping. TC: %d, UP: %d\n",
i, ets->prio_tc[i]);
return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index d357bf5..0c59d4f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -72,6 +72,12 @@
MLX4_EN_PARM_INT(pfcrx, 0, "Priority based Flow Control policy on RX[7:0]."
" Per priority bit mask");
+MLX4_EN_PARM_INT(inline_thold, MAX_INLINE,
+ "Threshold for using inline data (range: 17-104, default: 104)");
+
+#define MAX_PFC_TX 0xff
+#define MAX_PFC_RX 0xff
+
int en_print(const char *level, const struct mlx4_en_priv *priv,
const char *format, ...)
{
@@ -140,6 +146,7 @@
params->prof[i].tx_ring_num = params->num_tx_rings_p_up *
MLX4_EN_NUM_UP;
params->prof[i].rss_rings = 0;
+ params->prof[i].inline_thold = inline_thold;
}
return 0;
@@ -274,19 +281,8 @@
if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
mlx4_en_init_timestamp(mdev);
- mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
- if (!dev->caps.comp_pool) {
- mdev->profile.prof[i].rx_ring_num =
- rounddown_pow_of_two(max_t(int, MIN_RX_RINGS,
- min_t(int,
- dev->caps.num_comp_vectors,
- DEF_RX_RINGS)));
- } else {
- mdev->profile.prof[i].rx_ring_num = rounddown_pow_of_two(
- min_t(int, dev->caps.comp_pool/
- dev->caps.num_ports - 1 , MAX_MSIX_P_PORT - 1));
- }
- }
+ /* Set default number of RX rings*/
+ mlx4_en_set_num_rx_rings(mdev);
/* Create our own workqueue for reset/multicast tasks
* Note: we cannot use the shared workqueue because of deadlocks caused
@@ -336,8 +332,31 @@
.protocol = MLX4_PROT_ETH,
};
+static void mlx4_en_verify_params(void)
+{
+ if (pfctx > MAX_PFC_TX) {
+ pr_warn("mlx4_en: WARNING: illegal module parameter pfctx 0x%x - should be in range 0-0x%x, will be changed to default (0)\n",
+ pfctx, MAX_PFC_TX);
+ pfctx = 0;
+ }
+
+ if (pfcrx > MAX_PFC_RX) {
+ pr_warn("mlx4_en: WARNING: illegal module parameter pfcrx 0x%x - should be in range 0-0x%x, will be changed to default (0)\n",
+ pfcrx, MAX_PFC_RX);
+ pfcrx = 0;
+ }
+
+ if (inline_thold < MIN_PKT_LEN || inline_thold > MAX_INLINE) {
+ pr_warn("mlx4_en: WARNING: illegal module parameter inline_thold %d - should be in range %d-%d, will be changed to default (%d)\n",
+ inline_thold, MIN_PKT_LEN, MAX_INLINE, MAX_INLINE);
+ inline_thold = MAX_INLINE;
+ }
+}
+
static int __init mlx4_en_init(void)
{
+ mlx4_en_verify_params();
+
return mlx4_register_interface(&mlx4_en_interface);
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index fad4531..82d7eb5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -39,6 +39,7 @@
#include <linux/hash.h>
#include <net/ip.h>
#include <net/busy_poll.h>
+#include <net/vxlan.h>
#include <linux/mlx4/driver.h>
#include <linux/mlx4/device.h>
@@ -603,7 +604,7 @@
int err = 0;
u64 reg_id;
int *qpn = &priv->base_qpn;
- u64 mac = mlx4_en_mac_to_u64(priv->dev->dev_addr);
+ u64 mac = mlx4_mac_to_u64(priv->dev->dev_addr);
en_dbg(DRV, priv, "Registering MAC: %pM for adding\n",
priv->dev->dev_addr);
@@ -672,7 +673,7 @@
u64 mac;
if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) {
- mac = mlx4_en_mac_to_u64(priv->dev->dev_addr);
+ mac = mlx4_mac_to_u64(priv->dev->dev_addr);
en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n",
priv->dev->dev_addr);
mlx4_unregister_mac(dev, priv->port, mac);
@@ -685,7 +686,7 @@
for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) {
bucket = &priv->mac_hash[i];
hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
- mac = mlx4_en_mac_to_u64(entry->mac);
+ mac = mlx4_mac_to_u64(entry->mac);
en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n",
entry->mac);
mlx4_en_uc_steer_release(priv, entry->mac,
@@ -715,14 +716,14 @@
struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_dev *dev = mdev->dev;
int err = 0;
- u64 new_mac_u64 = mlx4_en_mac_to_u64(new_mac);
+ u64 new_mac_u64 = mlx4_mac_to_u64(new_mac);
if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) {
struct hlist_head *bucket;
unsigned int mac_hash;
struct mlx4_mac_entry *entry;
struct hlist_node *tmp;
- u64 prev_mac_u64 = mlx4_en_mac_to_u64(prev_mac);
+ u64 prev_mac_u64 = mlx4_mac_to_u64(prev_mac);
bucket = &priv->mac_hash[prev_mac[MLX4_EN_MAC_HASH_IDX]];
hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
@@ -742,6 +743,14 @@
err = mlx4_en_uc_steer_add(priv, new_mac,
&qpn,
&entry->reg_id);
+ if (err)
+ return err;
+ if (priv->tunnel_reg_id) {
+ mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id);
+ priv->tunnel_reg_id = 0;
+ }
+ err = mlx4_en_tunnel_steer_add(priv, new_mac, qpn,
+ &priv->tunnel_reg_id);
return err;
}
}
@@ -751,18 +760,6 @@
return __mlx4_replace_mac(dev, priv->port, qpn, new_mac_u64);
}
-u64 mlx4_en_mac_to_u64(u8 *addr)
-{
- u64 mac = 0;
- int i;
-
- for (i = 0; i < ETH_ALEN; i++) {
- mac <<= 8;
- mac |= addr[i];
- }
- return mac;
-}
-
static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv)
{
int err = 0;
@@ -1081,7 +1078,7 @@
mlx4_en_cache_mclist(dev);
netif_addr_unlock_bh(dev);
list_for_each_entry(mclist, &priv->mc_list, list) {
- mcast_addr = mlx4_en_mac_to_u64(mclist->addr);
+ mcast_addr = mlx4_mac_to_u64(mclist->addr);
mlx4_SET_MCAST_FLTR(mdev->dev, priv->port,
mcast_addr, 0, MLX4_MCAST_CONFIG);
}
@@ -1173,7 +1170,7 @@
found = true;
if (!found) {
- mac = mlx4_en_mac_to_u64(entry->mac);
+ mac = mlx4_mac_to_u64(entry->mac);
mlx4_en_uc_steer_release(priv, entry->mac,
priv->base_qpn,
entry->reg_id);
@@ -1216,7 +1213,7 @@
priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
break;
}
- mac = mlx4_en_mac_to_u64(ha->addr);
+ mac = mlx4_mac_to_u64(ha->addr);
memcpy(entry->mac, ha->addr, ETH_ALEN);
err = mlx4_register_mac(mdev->dev, priv->port, mac);
if (err < 0) {
@@ -1669,7 +1666,7 @@
}
if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
- err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC);
+ err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC, 1);
if (err) {
en_err(priv, "Failed setting port L2 tunnel configuration, err %d\n",
err);
@@ -1701,6 +1698,8 @@
mlx4_set_stats_bitmap(mdev->dev, &priv->stats_bitmap);
+ if (priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS)
+ vxlan_get_rx_port(dev);
priv->port_up = true;
netif_tx_start_all_queues(dev);
netif_device_attach(dev);
@@ -1792,6 +1791,8 @@
mc_list[5] = priv->port;
mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp,
mc_list, MLX4_PROT_ETH, mclist->reg_id);
+ if (mclist->tunnel_reg_id)
+ mlx4_flow_detach(mdev->dev, mclist->tunnel_reg_id);
}
mlx4_en_clear_list(dev);
list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) {
@@ -2206,7 +2207,7 @@
{
struct mlx4_en_priv *en_priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = en_priv->mdev;
- u64 mac_u64 = mlx4_en_mac_to_u64(mac);
+ u64 mac_u64 = mlx4_mac_to_u64(mac);
if (!is_valid_ether_addr(mac))
return -EINVAL;
@@ -2266,6 +2267,81 @@
return 0;
}
+static void mlx4_en_add_vxlan_offloads(struct work_struct *work)
+{
+ int ret;
+ struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
+ vxlan_add_task);
+
+ ret = mlx4_config_vxlan_port(priv->mdev->dev, priv->vxlan_port);
+ if (ret)
+ goto out;
+
+ ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port,
+ VXLAN_STEER_BY_OUTER_MAC, 1);
+out:
+ if (ret)
+ en_err(priv, "failed setting L2 tunnel configuration ret %d\n", ret);
+}
+
+static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
+{
+ int ret;
+ struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
+ vxlan_del_task);
+
+ ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port,
+ VXLAN_STEER_BY_OUTER_MAC, 0);
+ if (ret)
+ en_err(priv, "failed setting L2 tunnel configuration ret %d\n", ret);
+
+ priv->vxlan_port = 0;
+}
+
+static void mlx4_en_add_vxlan_port(struct net_device *dev,
+ sa_family_t sa_family, __be16 port)
+{
+ struct mlx4_en_priv *priv = netdev_priv(dev);
+ __be16 current_port;
+
+ if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS))
+ return;
+
+ if (sa_family == AF_INET6)
+ return;
+
+ current_port = priv->vxlan_port;
+ if (current_port && current_port != port) {
+ en_warn(priv, "vxlan port %d configured, can't add port %d\n",
+ ntohs(current_port), ntohs(port));
+ return;
+ }
+
+ priv->vxlan_port = port;
+ queue_work(priv->mdev->workqueue, &priv->vxlan_add_task);
+}
+
+static void mlx4_en_del_vxlan_port(struct net_device *dev,
+ sa_family_t sa_family, __be16 port)
+{
+ struct mlx4_en_priv *priv = netdev_priv(dev);
+ __be16 current_port;
+
+ if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+ return;
+
+ if (sa_family == AF_INET6)
+ return;
+
+ current_port = priv->vxlan_port;
+ if (current_port != port) {
+ en_dbg(DRV, priv, "vxlan port %d isn't configured, ignoring\n", ntohs(port));
+ return;
+ }
+
+ queue_work(priv->mdev->workqueue, &priv->vxlan_del_task);
+}
+
static const struct net_device_ops mlx4_netdev_ops = {
.ndo_open = mlx4_en_open,
.ndo_stop = mlx4_en_close,
@@ -2292,6 +2368,8 @@
.ndo_busy_poll = mlx4_en_low_latency_recv,
#endif
.ndo_get_phys_port_id = mlx4_en_get_phys_port_id,
+ .ndo_add_vxlan_port = mlx4_en_add_vxlan_port,
+ .ndo_del_vxlan_port = mlx4_en_del_vxlan_port,
};
static const struct net_device_ops mlx4_netdev_ops_master = {
@@ -2341,7 +2419,7 @@
netif_set_real_num_rx_queues(dev, prof->rx_ring_num);
SET_NETDEV_DEV(dev, &mdev->dev->pdev->dev);
- dev->dev_id = port - 1;
+ dev->dev_port = port - 1;
/*
* Initialize driver private data
@@ -2383,6 +2461,8 @@
INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate);
INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats);
INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task);
+ INIT_WORK(&priv->vxlan_add_task, mlx4_en_add_vxlan_offloads);
+ INIT_WORK(&priv->vxlan_del_task, mlx4_en_del_vxlan_offloads);
#ifdef CONFIG_MLX4_EN_DCB
if (!mlx4_is_slave(priv->mdev->dev)) {
if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_SET_ETH_SCHED) {
@@ -2407,7 +2487,7 @@
if (mlx4_is_slave(priv->mdev->dev)) {
eth_hw_addr_random(dev);
en_warn(priv, "Assigned random MAC address %pM\n", dev->dev_addr);
- mac_u64 = mlx4_en_mac_to_u64(dev->dev_addr);
+ mac_u64 = mlx4_mac_to_u64(dev->dev_addr);
mdev->dev->caps.def_mac[priv->port] = mac_u64;
} else {
en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n",
@@ -2516,7 +2596,7 @@
}
if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
- err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC);
+ err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC, 1);
if (err) {
en_err(priv, "Failed setting port L2 tunnel configuration, err %d\n",
err);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index dae1a1f..c2cfb05 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -148,10 +148,16 @@
stats->tx_packets = 0;
stats->tx_bytes = 0;
priv->port_stats.tx_chksum_offload = 0;
+ priv->port_stats.queue_stopped = 0;
+ priv->port_stats.wake_queue = 0;
+
for (i = 0; i < priv->tx_ring_num; i++) {
stats->tx_packets += priv->tx_ring[i]->packets;
stats->tx_bytes += priv->tx_ring[i]->bytes;
priv->port_stats.tx_chksum_offload += priv->tx_ring[i]->tx_csum;
+ priv->port_stats.queue_stopped +=
+ priv->tx_ring[i]->queue_stopped;
+ priv->port_stats.wake_queue += priv->tx_ring[i]->wake_queue;
}
stats->rx_errors = be64_to_cpu(mlx4_en_stats->PCS) +
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 890922c..ba049ae 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -318,6 +318,31 @@
}
}
+void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev)
+{
+ int i;
+ int num_of_eqs;
+ int num_rx_rings;
+ struct mlx4_dev *dev = mdev->dev;
+
+ mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
+ if (!dev->caps.comp_pool)
+ num_of_eqs = max_t(int, MIN_RX_RINGS,
+ min_t(int,
+ dev->caps.num_comp_vectors,
+ DEF_RX_RINGS));
+ else
+ num_of_eqs = min_t(int, MAX_MSIX_P_PORT,
+ dev->caps.comp_pool/
+ dev->caps.num_ports) - 1;
+
+ num_rx_rings = min_t(int, num_of_eqs,
+ netif_get_num_default_rss_queues());
+ mdev->profile.prof[i].rx_ring_num =
+ rounddown_pow_of_two(num_rx_rings);
+ }
+}
+
int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring **pring,
u32 size, u16 stride, int node)
@@ -636,6 +661,9 @@
if (!priv->port_up)
return 0;
+ if (budget <= 0)
+ return polled;
+
/* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx
* descriptor offset can be deduced from the CQE index instead of
* reading 'cqe->index' */
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
index c11d063..03e5f6a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
@@ -129,8 +129,10 @@
if (mlx4_en_QUERY_PORT(priv->mdev, priv->port))
return -ENOMEM;
- /* The device currently only supports 10G speed */
- if (priv->port_state.link_speed != SPEED_10000)
+ /* The device supports 1G, 10G and 40G speeds */
+ if (priv->port_state.link_speed != 1000 &&
+ priv->port_state.link_speed != 10000 &&
+ priv->port_state.link_speed != 40000)
return priv->port_state.link_speed;
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 8e8a7eb..dd1f6d3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -44,16 +44,6 @@
#include "mlx4_en.h"
-enum {
- MAX_INLINE = 104, /* 128 - 16 - 4 - 4 */
- MAX_BF = 256,
-};
-
-static int inline_thold __read_mostly = MAX_INLINE;
-
-module_param_named(inline_thold, inline_thold, int, 0444);
-MODULE_PARM_DESC(inline_thold, "threshold for using inline data");
-
int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring **pring, int qpn, u32 size,
u16 stride, int node, int queue_index)
@@ -75,8 +65,7 @@
ring->size = size;
ring->size_mask = size - 1;
ring->stride = stride;
-
- inline_thold = min(inline_thold, MAX_INLINE);
+ ring->inline_thold = priv->prof->inline_thold;
tmp = size * sizeof(struct mlx4_en_tx_info);
ring->tx_info = vmalloc_node(tmp, node);
@@ -325,7 +314,7 @@
}
}
}
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return tx_info->nr_txbb;
}
@@ -456,7 +445,7 @@
*/
if (netif_tx_queue_stopped(ring->tx_queue) && txbbs_skipped > 0) {
netif_tx_wake_queue(ring->tx_queue);
- priv->port_stats.wake_queue++;
+ ring->wake_queue++;
}
return done;
}
@@ -520,7 +509,7 @@
return ring->buf + index * TXBB_SIZE;
}
-static int is_inline(struct sk_buff *skb, void **pfrag)
+static int is_inline(int inline_thold, struct sk_buff *skb, void **pfrag)
{
void *ptr;
@@ -580,7 +569,7 @@
}
} else {
*lso_header_size = 0;
- if (!is_inline(skb, NULL))
+ if (!is_inline(priv->prof->inline_thold, skb, NULL))
real_size = CTRL_SIZE + (skb_shinfo(skb)->nr_frags + 1) * DS_SIZE;
else
real_size = inline_size(skb);
@@ -596,7 +585,13 @@
int spc = MLX4_INLINE_ALIGN - CTRL_SIZE - sizeof *inl;
if (skb->len <= spc) {
- inl->byte_count = cpu_to_be32(1 << 31 | skb->len);
+ if (likely(skb->len >= MIN_PKT_LEN)) {
+ inl->byte_count = cpu_to_be32(1 << 31 | skb->len);
+ } else {
+ inl->byte_count = cpu_to_be32(1 << 31 | MIN_PKT_LEN);
+ memset(((void *)(inl + 1)) + skb->len, 0,
+ MIN_PKT_LEN - skb->len);
+ }
skb_copy_from_linear_data(skb, inl + 1, skb_headlen(skb));
if (skb_shinfo(skb)->nr_frags)
memcpy(((void *)(inl + 1)) + skb_headlen(skb), fragptr,
@@ -629,7 +624,7 @@
}
u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv, select_queue_fallback_t fallback)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
u16 rings_p_up = priv->num_tx_rings_p_up;
@@ -641,7 +636,7 @@
if (vlan_tx_tag_present(skb))
up = vlan_tx_tag_get(skb) >> VLAN_PRIO_SHIFT;
- return __netdev_pick_tx(dev, skb) % rings_p_up + up * rings_p_up;
+ return fallback(dev, skb) % rings_p_up + up * rings_p_up;
}
static void mlx4_bf_copy(void __iomem *dst, unsigned long *src, unsigned bytecnt)
@@ -696,7 +691,7 @@
ring->size - HEADROOM - MAX_DESC_TXBBS)) {
/* every full Tx ring stops queue */
netif_tx_stop_queue(ring->tx_queue);
- priv->port_stats.queue_stopped++;
+ ring->queue_stopped++;
/* If queue was emptied after the if, and before the
* stop_queue - need to wake the queue, or else it will remain
@@ -709,7 +704,7 @@
if (unlikely(((int)(ring->prod - ring->cons)) <=
ring->size - HEADROOM - MAX_DESC_TXBBS)) {
netif_tx_wake_queue(ring->tx_queue);
- priv->port_stats.wake_queue++;
+ ring->wake_queue++;
} else {
return NETDEV_TX_BUSY;
}
@@ -747,11 +742,11 @@
tx_info->data_offset = (void *)data - (void *)tx_desc;
tx_info->linear = (lso_header_size < skb_headlen(skb) &&
- !is_inline(skb, NULL)) ? 1 : 0;
+ !is_inline(ring->inline_thold, skb, NULL)) ? 1 : 0;
data += skb_shinfo(skb)->nr_frags + tx_info->linear - 1;
- if (is_inline(skb, &fragptr)) {
+ if (is_inline(ring->inline_thold, skb, &fragptr)) {
tx_info->inl = 1;
} else {
/* Map fragments */
@@ -881,7 +876,8 @@
skb_tx_timestamp(skb);
if (ring->bf_enabled && desc_size <= MAX_BF && !bounce && !vlan_tx_tag_present(skb)) {
- *(__be32 *) (&tx_desc->ctrl.vlan_tag) |= cpu_to_be32(ring->doorbell_qpn);
+ tx_desc->ctrl.bf_qpn |= cpu_to_be32(ring->doorbell_qpn);
+
op_own |= htonl((bf_index & 0xffff) << 8);
/* Ensure new descirptor hits memory
* before setting ownership of this descriptor to HW */
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 8992b38..d501a2b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -271,7 +271,10 @@
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_slave_state *s_state = priv->mfunc.master.slave_state;
- if (slave >= dev->num_slaves || port > MLX4_MAX_PORTS) {
+ struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave);
+
+ if (slave >= dev->num_slaves || port > dev->caps.num_ports ||
+ port <= 0 || !test_bit(port - 1, actv_ports.ports)) {
pr_err("%s: Error: asking for slave:%d, port:%d\n",
__func__, slave, port);
return SLAVE_PORT_DOWN;
@@ -285,8 +288,10 @@
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_slave_state *s_state = priv->mfunc.master.slave_state;
+ struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave);
- if (slave >= dev->num_slaves || port > MLX4_MAX_PORTS || port == 0) {
+ if (slave >= dev->num_slaves || port > dev->caps.num_ports ||
+ port <= 0 || !test_bit(port - 1, actv_ports.ports)) {
pr_err("%s: Error: asking for slave:%d, port:%d\n",
__func__, slave, port);
return -1;
@@ -300,9 +305,13 @@
{
int i;
enum slave_port_gen_event gen_event;
+ struct mlx4_slaves_pport slaves_pport = mlx4_phys_to_slaves_pport(dev,
+ port);
- for (i = 0; i < dev->num_slaves; i++)
- set_and_calc_slave_port_state(dev, i, port, event, &gen_event);
+ for (i = 0; i < dev->num_vfs + 1; i++)
+ if (test_bit(i, slaves_pport.slaves))
+ set_and_calc_slave_port_state(dev, i, port,
+ event, &gen_event);
}
/**************************************************************************
The function get as input the new event to that port,
@@ -321,12 +330,14 @@
struct mlx4_slave_state *ctx = NULL;
unsigned long flags;
int ret = -1;
+ struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave);
enum slave_port_state cur_state =
mlx4_get_slave_port_state(dev, slave, port);
*gen_event = SLAVE_PORT_GEN_EVENT_NONE;
- if (slave >= dev->num_slaves || port > MLX4_MAX_PORTS || port == 0) {
+ if (slave >= dev->num_slaves || port > dev->caps.num_ports ||
+ port <= 0 || !test_bit(port - 1, actv_ports.ports)) {
pr_err("%s: Error: asking for slave:%d, port:%d\n",
__func__, slave, port);
return ret;
@@ -542,15 +553,19 @@
be64_to_cpu(eqe->event.cmd.out_param));
break;
- case MLX4_EVENT_TYPE_PORT_CHANGE:
+ case MLX4_EVENT_TYPE_PORT_CHANGE: {
+ struct mlx4_slaves_pport slaves_port;
port = be32_to_cpu(eqe->event.port_change.port) >> 28;
+ slaves_port = mlx4_phys_to_slaves_pport(dev, port);
if (eqe->subtype == MLX4_PORT_CHANGE_SUBTYPE_DOWN) {
mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_DOWN,
port);
mlx4_priv(dev)->sense.do_sense_port[port] = 1;
if (!mlx4_is_master(dev))
break;
- for (i = 0; i < dev->num_slaves; i++) {
+ for (i = 0; i < dev->num_vfs + 1; i++) {
+ if (!test_bit(i, slaves_port.slaves))
+ continue;
if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH) {
if (i == mlx4_master_func_num(dev))
continue;
@@ -558,8 +573,13 @@
" to slave: %d, port:%d\n",
__func__, i, port);
s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
- if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state)
+ if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
+ eqe->event.port_change.port =
+ cpu_to_be32(
+ (be32_to_cpu(eqe->event.port_change.port) & 0xFFFFFFF)
+ | (mlx4_phys_to_slave_port(dev, i, port) << 28));
mlx4_slave_event(dev, i, eqe);
+ }
} else { /* IB port */
set_and_calc_slave_port_state(dev, i, port,
MLX4_PORT_STATE_DEV_EVENT_PORT_DOWN,
@@ -580,12 +600,19 @@
if (!mlx4_is_master(dev))
break;
if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH)
- for (i = 0; i < dev->num_slaves; i++) {
+ for (i = 0; i < dev->num_vfs + 1; i++) {
+ if (!test_bit(i, slaves_port.slaves))
+ continue;
if (i == mlx4_master_func_num(dev))
continue;
s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
- if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state)
+ if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
+ eqe->event.port_change.port =
+ cpu_to_be32(
+ (be32_to_cpu(eqe->event.port_change.port) & 0xFFFFFFF)
+ | (mlx4_phys_to_slave_port(dev, i, port) << 28));
mlx4_slave_event(dev, i, eqe);
+ }
}
else /* IB port */
/* port-up event will be sent to a slave when the
@@ -594,6 +621,7 @@
set_all_slave_state(dev, port, MLX4_DEV_EVENT_PORT_UP);
}
break;
+ }
case MLX4_EVENT_TYPE_CQ_ERROR:
mlx4_warn(dev, "CQ %s on CQN %06x\n",
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 91b69ff..d16a4d1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -129,13 +129,14 @@
[0] = "RSS support",
[1] = "RSS Toeplitz Hash Function support",
[2] = "RSS XOR Hash Function support",
- [3] = "Device manage flow steering support",
+ [3] = "Device managed flow steering support",
[4] = "Automatic MAC reassignment support",
[5] = "Time stamping support",
[6] = "VST (control vlan insertion/stripping) support",
[7] = "FSM (MAC anti-spoofing) support",
[8] = "Dynamic QP updates support",
- [9] = "TCP/IP offloads/flow-steering for VXLAN support"
+ [9] = "Device managed flow steering IPoIB support",
+ [10] = "TCP/IP offloads/flow-steering for VXLAN support"
};
int i;
@@ -224,13 +225,25 @@
#define QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID 0x80
if (vhcr->op_modifier == 1) {
+ struct mlx4_active_ports actv_ports =
+ mlx4_get_active_ports(dev, slave);
+ int converted_port = mlx4_slave_convert_port(
+ dev, slave, vhcr->in_modifier);
+
+ if (converted_port < 0)
+ return -EINVAL;
+
+ vhcr->in_modifier = converted_port;
/* Set nic_info bit to mark new fields support */
field = QUERY_FUNC_CAP_FLAGS1_NIC_INFO;
MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS1_OFFSET);
- field = vhcr->in_modifier; /* phys-port = logical-port */
+ /* phys-port = logical-port */
+ field = vhcr->in_modifier -
+ find_first_bit(actv_ports.ports, dev->caps.num_ports);
MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_PHYS_PORT_OFFSET);
+ field = vhcr->in_modifier;
/* size is now the QP number */
size = dev->phys_caps.base_tunnel_sqpn + 8 * slave + field - 1;
MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP0_TUNNEL);
@@ -248,12 +261,16 @@
QUERY_FUNC_CAP_PHYS_PORT_ID);
} else if (vhcr->op_modifier == 0) {
+ struct mlx4_active_ports actv_ports =
+ mlx4_get_active_ports(dev, slave);
/* enable rdma and ethernet interfaces, and new quota locations */
field = (QUERY_FUNC_CAP_FLAG_ETH | QUERY_FUNC_CAP_FLAG_RDMA |
QUERY_FUNC_CAP_FLAG_QUOTAS);
MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS_OFFSET);
- field = dev->caps.num_ports;
+ field = min(
+ bitmap_weight(actv_ports.ports, dev->caps.num_ports),
+ dev->caps.num_ports);
MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_NUM_PORTS_OFFSET);
size = dev->caps.function_caps; /* set PF behaviours */
@@ -839,6 +856,10 @@
int err = 0;
u8 field;
u32 bmme_flags;
+ int real_port;
+ int slave_port;
+ int first_port;
+ struct mlx4_active_ports actv_ports;
err = mlx4_cmd_box(dev, 0, outbox->dma, 0, 0, MLX4_CMD_QUERY_DEV_CAP,
MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
@@ -851,15 +872,33 @@
MLX4_GET(flags, outbox->buf, QUERY_DEV_CAP_EXT_FLAGS_OFFSET);
flags |= MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV;
flags &= ~MLX4_DEV_CAP_FLAG_MEM_WINDOW;
+ actv_ports = mlx4_get_active_ports(dev, slave);
+ first_port = find_first_bit(actv_ports.ports, dev->caps.num_ports);
+ for (slave_port = 0, real_port = first_port;
+ real_port < first_port +
+ bitmap_weight(actv_ports.ports, dev->caps.num_ports);
+ ++real_port, ++slave_port) {
+ if (flags & (MLX4_DEV_CAP_FLAG_WOL_PORT1 << real_port))
+ flags |= MLX4_DEV_CAP_FLAG_WOL_PORT1 << slave_port;
+ else
+ flags &= ~(MLX4_DEV_CAP_FLAG_WOL_PORT1 << slave_port);
+ }
+ for (; slave_port < dev->caps.num_ports; ++slave_port)
+ flags &= ~(MLX4_DEV_CAP_FLAG_WOL_PORT1 << slave_port);
MLX4_PUT(outbox->buf, flags, QUERY_DEV_CAP_EXT_FLAGS_OFFSET);
+ MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_VL_PORT_OFFSET);
+ field &= ~0x0F;
+ field |= bitmap_weight(actv_ports.ports, dev->caps.num_ports) & 0x0F;
+ MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_VL_PORT_OFFSET);
+
/* For guests, disable timestamp */
MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET);
field &= 0x7f;
MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET);
/* For guests, disable vxlan tunneling */
- MLX4_GET(field, outbox, QUERY_DEV_CAP_VXLAN);
+ MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_VXLAN);
field &= 0xf7;
MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_VXLAN);
@@ -869,7 +908,7 @@
MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_BF_OFFSET);
/* For guests, disable mw type 2 */
- MLX4_GET(bmme_flags, outbox, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
+ MLX4_GET(bmme_flags, outbox->buf, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
bmme_flags &= ~MLX4_BMME_FLAG_TYPE_2_WIN;
MLX4_PUT(outbox->buf, bmme_flags, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
@@ -883,7 +922,7 @@
}
/* turn off ipoib managed steering for guests */
- MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
+ MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
field &= ~0x80;
MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
@@ -902,12 +941,20 @@
u16 short_field;
int err;
int admin_link_state;
+ int port = mlx4_slave_convert_port(dev, slave,
+ vhcr->in_modifier & 0xFF);
#define MLX4_VF_PORT_NO_LINK_SENSE_MASK 0xE0
#define MLX4_PORT_LINK_UP_MASK 0x80
#define QUERY_PORT_CUR_MAX_PKEY_OFFSET 0x0c
#define QUERY_PORT_CUR_MAX_GID_OFFSET 0x0e
+ if (port < 0)
+ return -EINVAL;
+
+ vhcr->in_modifier = (vhcr->in_modifier & ~0xFF) |
+ (port & 0xFF);
+
err = mlx4_cmd_box(dev, 0, outbox->dma, vhcr->in_modifier, 0,
MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
MLX4_CMD_NATIVE);
@@ -934,7 +981,10 @@
MLX4_PUT(outbox->buf, port_type,
QUERY_PORT_SUPPORTED_TYPE_OFFSET);
- short_field = 1; /* slave max gids */
+ if (dev->caps.port_type[vhcr->in_modifier] == MLX4_PORT_TYPE_ETH)
+ short_field = mlx4_get_slave_num_gids(dev, slave, port);
+ else
+ short_field = 1; /* slave max gids */
MLX4_PUT(outbox->buf, short_field,
QUERY_PORT_CUR_MAX_GID_OFFSET);
@@ -1584,9 +1634,12 @@
struct mlx4_cmd_info *cmd)
{
struct mlx4_priv *priv = mlx4_priv(dev);
- int port = vhcr->in_modifier;
+ int port = mlx4_slave_convert_port(dev, slave, vhcr->in_modifier);
int err;
+ if (port < 0)
+ return -EINVAL;
+
if (priv->mfunc.master.slave_state[slave].init_port_mask & (1 << port))
return 0;
@@ -1676,9 +1729,12 @@
struct mlx4_cmd_info *cmd)
{
struct mlx4_priv *priv = mlx4_priv(dev);
- int port = vhcr->in_modifier;
+ int port = mlx4_slave_convert_port(dev, slave, vhcr->in_modifier);
int err;
+ if (port < 0)
+ return -EINVAL;
+
if (!(priv->mfunc.master.slave_state[slave].init_port_mask &
(1 << port)))
return 0;
@@ -1723,6 +1779,46 @@
MLX4_CMD_NATIVE);
}
+struct mlx4_config_dev {
+ __be32 update_flags;
+ __be32 rsdv1[3];
+ __be16 vxlan_udp_dport;
+ __be16 rsvd2;
+};
+
+#define MLX4_VXLAN_UDP_DPORT (1 << 0)
+
+static int mlx4_CONFIG_DEV(struct mlx4_dev *dev, struct mlx4_config_dev *config_dev)
+{
+ int err;
+ struct mlx4_cmd_mailbox *mailbox;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+
+ memcpy(mailbox->buf, config_dev, sizeof(*config_dev));
+
+ err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_CONFIG_DEV,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+}
+
+int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port)
+{
+ struct mlx4_config_dev config_dev;
+
+ memset(&config_dev, 0, sizeof(config_dev));
+ config_dev.update_flags = cpu_to_be32(MLX4_VXLAN_UDP_DPORT);
+ config_dev.vxlan_udp_dport = udp_port;
+
+ return mlx4_CONFIG_DEV(dev, &config_dev);
+}
+EXPORT_SYMBOL_GPL(mlx4_config_vxlan_port);
+
+
int mlx4_SET_ICM_SIZE(struct mlx4_dev *dev, u64 icm_size, u64 *aux_pages)
{
int ret = mlx4_cmd_imm(dev, icm_size, aux_pages, 0, 0,
@@ -1890,7 +1986,8 @@
err = EINVAL;
break;
}
- err = mlx4_cmd(dev, 0, ((u32) err | cpu_to_be32(token) << 16),
+ err = mlx4_cmd(dev, 0, ((u32) err |
+ (__force u32)cpu_to_be32(token) << 16),
1, MLX4_CMD_GET_OP_REQ, MLX4_CMD_TIME_CLASS_A,
MLX4_CMD_NATIVE);
if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index d711158..f0ae95f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -41,7 +41,6 @@
#include <linux/slab.h>
#include <linux/io-mapping.h>
#include <linux/delay.h>
-#include <linux/netdevice.h>
#include <linux/kmod.h>
#include <linux/mlx4/device.h>
@@ -78,13 +77,17 @@
#endif /* CONFIG_PCI_MSI */
-static int num_vfs;
-module_param(num_vfs, int, 0444);
-MODULE_PARM_DESC(num_vfs, "enable #num_vfs functions if num_vfs > 0");
+static uint8_t num_vfs[3] = {0, 0, 0};
+static int num_vfs_argc = 3;
+module_param_array(num_vfs, byte , &num_vfs_argc, 0444);
+MODULE_PARM_DESC(num_vfs, "enable #num_vfs functions if num_vfs > 0\n"
+ "num_vfs=port1,port2,port1+2");
-static int probe_vf;
-module_param(probe_vf, int, 0644);
-MODULE_PARM_DESC(probe_vf, "number of vfs to probe by pf driver (num_vfs > 0)");
+static uint8_t probe_vf[3] = {0, 0, 0};
+static int probe_vfs_argc = 3;
+module_param_array(probe_vf, byte, &probe_vfs_argc, 0444);
+MODULE_PARM_DESC(probe_vf, "number of vfs to probe by pf driver (num_vfs > 0)\n"
+ "probe_vf=port1,port2,port1+2");
int mlx4_log_num_mgm_entry_size = MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE;
module_param_named(log_num_mgm_entry_size,
@@ -150,6 +153,8 @@
struct pci_dev *pdev;
};
+static atomic_t pf_loading = ATOMIC_INIT(0);
+
int mlx4_check_port_params(struct mlx4_dev *dev,
enum mlx4_port_type *port_type)
{
@@ -749,7 +754,7 @@
has_eth_port = true;
}
- if (has_ib_port)
+ if (has_ib_port || (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
request_module_nowait(IB_DRV_NAME);
if (has_eth_port)
request_module_nowait(EN_DRV_NAME);
@@ -1407,6 +1412,11 @@
u32 slave_read;
u32 cmd_channel_ver;
+ if (atomic_read(&pf_loading)) {
+ mlx4_warn(dev, "PF is not ready. Deferring probe\n");
+ return -EPROBE_DEFER;
+ }
+
mutex_lock(&priv->cmd.slave_cmd_mutex);
priv->cmd.max_cmds = 1;
mlx4_warn(dev, "Sending reset\n");
@@ -1463,7 +1473,11 @@
int i;
for (i = 1; i <= dev->caps.num_ports; i++) {
- dev->caps.gid_table_len[i] = 1;
+ if (dev->caps.port_type[i] == MLX4_PORT_TYPE_ETH)
+ dev->caps.gid_table_len[i] =
+ mlx4_get_slave_num_gids(dev, 0, i);
+ else
+ dev->caps.gid_table_len[i] = 1;
dev->caps.pkey_table_len[i] =
dev->phys_caps.pkey_phys_table_len[i] - 1;
}
@@ -1488,7 +1502,7 @@
if (mlx4_log_num_mgm_entry_size == -1 &&
dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN &&
(!mlx4_is_mfunc(dev) ||
- (dev_cap->fs_max_num_qp_per_entry >= (num_vfs + 1))) &&
+ (dev_cap->fs_max_num_qp_per_entry >= (dev->num_vfs + 1))) &&
choose_log_fs_mgm_entry_size(dev_cap->fs_max_num_qp_per_entry) >=
MLX4_MIN_MGM_LOG_ENTRY_SIZE) {
dev->oper_log_mgm_entry_size =
@@ -1974,9 +1988,8 @@
struct mlx4_priv *priv = mlx4_priv(dev);
struct msix_entry *entries;
int nreq = min_t(int, dev->caps.num_ports *
- min_t(int, netif_get_num_default_rss_queues() + 1,
+ min_t(int, num_online_cpus() + 1,
MAX_MSIX_P_PORT) + MSIX_LEGACY_SZ, MAX_MSIX);
- int err;
int i;
if (msi_x) {
@@ -1990,23 +2003,13 @@
for (i = 0; i < nreq; ++i)
entries[i].entry = i;
- retry:
- err = pci_enable_msix(dev->pdev, entries, nreq);
- if (err) {
- /* Try again if at least 2 vectors are available */
- if (err > 1) {
- mlx4_info(dev, "Requested %d vectors, "
- "but only %d MSI-X vectors available, "
- "trying again\n", nreq, err);
- nreq = err;
- goto retry;
- }
+ nreq = pci_enable_msix_range(dev->pdev, entries, 2, nreq);
+
+ if (nreq < 0) {
kfree(entries);
goto no_msi;
- }
-
- if (nreq <
- MSIX_LEGACY_SZ + dev->caps.num_ports * MIN_MSIX_P_PORT) {
+ } else if (nreq < MSIX_LEGACY_SZ +
+ dev->caps.num_ports * MIN_MSIX_P_PORT) {
/*Working in legacy mode , all EQ's shared*/
dev->caps.comp_pool = 0;
dev->caps.num_comp_vectors = nreq - 1;
@@ -2194,6 +2197,13 @@
struct mlx4_dev *dev;
int err;
int port;
+ int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0};
+ int prb_vf[MLX4_MAX_PORTS + 1] = {0, 0, 0};
+ const int param_map[MLX4_MAX_PORTS + 1][MLX4_MAX_PORTS + 1] = {
+ {2, 0, 0}, {0, 1, 2}, {0, 1, 2} };
+ unsigned total_vfs = 0;
+ int sriov_initialized = 0;
+ unsigned int i;
pr_info(DRV_NAME ": Initializing %s\n", pci_name(pdev));
@@ -2208,17 +2218,40 @@
* per port, we must limit the number of VFs to 63 (since their are
* 128 MACs)
*/
- if (num_vfs >= MLX4_MAX_NUM_VF) {
+ for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) && i < num_vfs_argc;
+ total_vfs += nvfs[param_map[num_vfs_argc - 1][i]], i++) {
+ nvfs[param_map[num_vfs_argc - 1][i]] = num_vfs[i];
+ if (nvfs[i] < 0) {
+ dev_err(&pdev->dev, "num_vfs module parameter cannot be negative\n");
+ return -EINVAL;
+ }
+ }
+ for (i = 0; i < sizeof(prb_vf)/sizeof(prb_vf[0]) && i < probe_vfs_argc;
+ i++) {
+ prb_vf[param_map[probe_vfs_argc - 1][i]] = probe_vf[i];
+ if (prb_vf[i] < 0 || prb_vf[i] > nvfs[i]) {
+ dev_err(&pdev->dev, "probe_vf module parameter cannot be negative or greater than num_vfs\n");
+ return -EINVAL;
+ }
+ }
+ if (total_vfs >= MLX4_MAX_NUM_VF) {
dev_err(&pdev->dev,
"Requested more VF's (%d) than allowed (%d)\n",
- num_vfs, MLX4_MAX_NUM_VF - 1);
+ total_vfs, MLX4_MAX_NUM_VF - 1);
return -EINVAL;
}
- if (num_vfs < 0) {
- pr_err("num_vfs module parameter cannot be negative\n");
- return -EINVAL;
+ for (i = 0; i < MLX4_MAX_PORTS; i++) {
+ if (nvfs[i] + nvfs[2] >= MLX4_MAX_NUM_VF_P_PORT) {
+ dev_err(&pdev->dev,
+ "Requested more VF's (%d) for port (%d) than allowed (%d)\n",
+ nvfs[i] + nvfs[2], i + 1,
+ MLX4_MAX_NUM_VF_P_PORT - 1);
+ return -EINVAL;
+ }
}
+
+
/*
* Check for BARs.
*/
@@ -2293,11 +2326,23 @@
if (pci_dev_data & MLX4_PCI_DEV_IS_VF) {
/* When acting as pf, we normally skip vfs unless explicitly
* requested to probe them. */
- if (num_vfs && extended_func_num(pdev) > probe_vf) {
- mlx4_warn(dev, "Skipping virtual function:%d\n",
- extended_func_num(pdev));
- err = -ENODEV;
- goto err_free_dev;
+ if (total_vfs) {
+ unsigned vfs_offset = 0;
+ for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) &&
+ vfs_offset + nvfs[i] < extended_func_num(pdev);
+ vfs_offset += nvfs[i], i++)
+ ;
+ if (i == sizeof(nvfs)/sizeof(nvfs[0])) {
+ err = -ENODEV;
+ goto err_free_dev;
+ }
+ if ((extended_func_num(pdev) - vfs_offset)
+ > prb_vf[i]) {
+ mlx4_warn(dev, "Skipping virtual function:%d\n",
+ extended_func_num(pdev));
+ err = -ENODEV;
+ goto err_free_dev;
+ }
}
mlx4_warn(dev, "Detected virtual function - running in slave mode\n");
dev->flags |= MLX4_FLAG_SLAVE;
@@ -2317,18 +2362,30 @@
}
}
- if (num_vfs) {
- mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n", num_vfs);
- err = pci_enable_sriov(pdev, num_vfs);
- if (err) {
- mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d).\n",
- err);
+ if (total_vfs) {
+ mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n",
+ total_vfs);
+ dev->dev_vfs = kzalloc(
+ total_vfs * sizeof(*dev->dev_vfs),
+ GFP_KERNEL);
+ if (NULL == dev->dev_vfs) {
+ mlx4_err(dev, "Failed to allocate memory for VFs\n");
err = 0;
} else {
- mlx4_warn(dev, "Running in master mode\n");
- dev->flags |= MLX4_FLAG_SRIOV |
- MLX4_FLAG_MASTER;
- dev->num_vfs = num_vfs;
+ atomic_inc(&pf_loading);
+ err = pci_enable_sriov(pdev, total_vfs);
+ atomic_dec(&pf_loading);
+ if (err) {
+ mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d).\n",
+ err);
+ err = 0;
+ } else {
+ mlx4_warn(dev, "Running in master mode\n");
+ dev->flags |= MLX4_FLAG_SRIOV |
+ MLX4_FLAG_MASTER;
+ dev->num_vfs = total_vfs;
+ sriov_initialized = 1;
+ }
}
}
@@ -2393,12 +2450,37 @@
/* In master functions, the communication channel must be initialized
* after obtaining its address from fw */
if (mlx4_is_master(dev)) {
+ unsigned sum = 0;
err = mlx4_multi_func_init(dev);
if (err) {
mlx4_err(dev, "Failed to init master mfunc"
"interface, aborting.\n");
goto err_close;
}
+ if (sriov_initialized) {
+ int ib_ports = 0;
+ mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
+ ib_ports++;
+
+ if (ib_ports &&
+ (num_vfs_argc > 1 || probe_vfs_argc > 1)) {
+ mlx4_err(dev,
+ "Invalid syntax of num_vfs/probe_vfs "
+ "with IB port. Single port VFs syntax"
+ " is only supported when all ports "
+ "are configured as ethernet\n");
+ goto err_close;
+ }
+ for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]); i++) {
+ unsigned j;
+ for (j = 0; j < nvfs[i]; ++sum, ++j) {
+ dev->dev_vfs[sum].min_port =
+ i < 2 ? i + 1 : 1;
+ dev->dev_vfs[sum].n_ports = i < 2 ? 1 :
+ dev->caps.num_ports;
+ }
+ }
+ }
}
err = mlx4_alloc_eq_table(dev);
@@ -2506,6 +2588,8 @@
if (!mlx4_is_slave(dev))
mlx4_free_ownership(dev);
+ kfree(priv->dev.dev_vfs);
+
err_free_dev:
kfree(priv);
@@ -2592,6 +2676,7 @@
kfree(dev->caps.qp0_proxy);
kfree(dev->caps.qp1_tunnel);
kfree(dev->caps.qp1_proxy);
+ kfree(dev->dev_vfs);
kfree(priv);
pci_release_regions(pdev);
@@ -2670,7 +2755,11 @@
static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
{
- int ret = __mlx4_init_one(pdev, 0);
+ const struct pci_device_id *id;
+ int ret;
+
+ id = pci_match_id(mlx4_pci_table, pdev);
+ ret = __mlx4_init_one(pdev, id->driver_data);
return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
}
@@ -2684,6 +2773,7 @@
.name = DRV_NAME,
.id_table = mlx4_pci_table,
.probe = mlx4_init_one,
+ .shutdown = mlx4_remove_one,
.remove = mlx4_remove_one,
.err_handler = &mlx4_err_handler,
};
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index db7dc0b..80ccb4e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -1387,9 +1387,12 @@
struct mlx4_cmd_info *cmd)
{
u32 qpn = (u32) vhcr->in_param & 0xffffffff;
- u8 port = vhcr->in_param >> 62;
+ int port = mlx4_slave_convert_port(dev, slave, vhcr->in_param >> 62);
enum mlx4_steer_type steer = vhcr->in_modifier;
+ if (port < 0)
+ return -EINVAL;
+
/* Promiscuous unicast is not allowed in mfunc */
if (mlx4_is_mfunc(dev) && steer == MLX4_UC_STEER)
return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 6b65f77..cf8be41 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -51,8 +51,8 @@
#define DRV_NAME "mlx4_core"
#define PFX DRV_NAME ": "
-#define DRV_VERSION "1.1"
-#define DRV_RELDATE "Dec, 2011"
+#define DRV_VERSION "2.2-1"
+#define DRV_RELDATE "Feb, 2014"
#define MLX4_FS_UDP_UC_EN (1 << 1)
#define MLX4_FS_TCP_UC_EN (1 << 2)
@@ -788,6 +788,10 @@
MLX4_USE_RR = 1,
};
+struct mlx4_roce_gid_entry {
+ u8 raw[16];
+};
+
struct mlx4_priv {
struct mlx4_dev dev;
@@ -834,6 +838,7 @@
int fs_hash_mode;
u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS];
__be64 slave_node_guids[MLX4_MFUNC_MAX];
+ struct mlx4_roce_gid_entry roce_gids[MLX4_MAX_PORTS][MLX4_ROCE_MAX_GIDS];
atomic_t opreq_count;
struct work_struct opreq_task;
@@ -1242,11 +1247,6 @@
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
-int mlx4_FLOW_STEERING_IB_UC_QP_RANGE_wrapper(struct mlx4_dev *dev, int slave,
- struct mlx4_vhcr *vhcr,
- struct mlx4_cmd_mailbox *inbox,
- struct mlx4_cmd_mailbox *outbox,
- struct mlx4_cmd_info *cmd);
int mlx4_get_mgm_entry_size(struct mlx4_dev *dev);
int mlx4_get_qp_per_mgm(struct mlx4_dev *dev);
@@ -1282,4 +1282,8 @@
void mlx4_init_quotas(struct mlx4_dev *dev);
+int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port);
+/* Returns the VF index of slave */
+int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave);
+
#endif /* MLX4_H */
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 3af04c3..36fc2a2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -57,8 +57,8 @@
#include "en_port.h"
#define DRV_NAME "mlx4_en"
-#define DRV_VERSION "2.0"
-#define DRV_RELDATE "Dec 2011"
+#define DRV_VERSION "2.2-1"
+#define DRV_RELDATE "Feb 2014"
#define MLX4_EN_MSG_LEVEL (NETIF_MSG_LINK | NETIF_MSG_IFDOWN)
@@ -187,6 +187,13 @@
#define GET_AVG_PERF_COUNTER(cnt) (0)
#endif /* MLX4_EN_PERF_STAT */
+/* Constants for TX flow */
+enum {
+ MAX_INLINE = 104, /* 128 - 16 - 4 - 4 */
+ MAX_BF = 256,
+ MIN_PKT_LEN = 17,
+};
+
/*
* Configurables
*/
@@ -267,10 +274,13 @@
unsigned long bytes;
unsigned long packets;
unsigned long tx_csum;
+ unsigned long queue_stopped;
+ unsigned long wake_queue;
struct mlx4_bf bf;
bool bf_enabled;
struct netdev_queue *tx_queue;
int hwtstamp_tx_type;
+ int inline_thold;
};
struct mlx4_en_rx_desc {
@@ -346,6 +356,7 @@
u8 tx_pause;
u8 tx_ppp;
int rss_rings;
+ int inline_thold;
};
struct mlx4_en_profile {
@@ -548,6 +559,8 @@
struct work_struct linkstate_task;
struct delayed_work stats_task;
struct delayed_work service_task;
+ struct work_struct vxlan_add_task;
+ struct work_struct vxlan_del_task;
struct mlx4_en_perf_stats pstats;
struct mlx4_en_pkt_stats pkstats;
struct mlx4_en_port_stats port_stats;
@@ -574,6 +587,7 @@
struct hlist_head filter_hash[1 << MLX4_EN_FILTER_HASH_SHIFT];
#endif
u64 tunnel_reg_id;
+ __be16 vxlan_port;
};
enum mlx4_en_wol {
@@ -723,7 +737,7 @@
void mlx4_en_tx_irq(struct mlx4_cq *mcq);
u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv);
+ void *accel_priv, select_queue_fallback_t fallback);
netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
@@ -737,7 +751,7 @@
int cq, int user_prio);
void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring *ring);
-
+void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev);
int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring **pring,
u32 size, u16 stride, int node);
@@ -786,7 +800,6 @@
#define MLX4_EN_NUM_SELF_TEST 5
void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf);
-u64 mlx4_en_mac_to_u64(u8 *addr);
void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev);
/*
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index a58bcbf..cfcad26 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -505,6 +505,84 @@
mlx4_free_cmd_mailbox(dev, outmailbox);
return err;
}
+static struct mlx4_roce_gid_entry zgid_entry;
+
+int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port)
+{
+ int vfs;
+ int slave_gid = slave;
+ unsigned i;
+ struct mlx4_slaves_pport slaves_pport;
+ struct mlx4_active_ports actv_ports;
+ unsigned max_port_p_one;
+
+ if (slave == 0)
+ return MLX4_ROCE_PF_GIDS;
+
+ /* Slave is a VF */
+ slaves_pport = mlx4_phys_to_slaves_pport(dev, port);
+ actv_ports = mlx4_get_active_ports(dev, slave);
+ max_port_p_one = find_first_bit(actv_ports.ports, dev->caps.num_ports) +
+ bitmap_weight(actv_ports.ports, dev->caps.num_ports) + 1;
+
+ for (i = 1; i < max_port_p_one; i++) {
+ struct mlx4_active_ports exclusive_ports;
+ struct mlx4_slaves_pport slaves_pport_actv;
+ bitmap_zero(exclusive_ports.ports, dev->caps.num_ports);
+ set_bit(i - 1, exclusive_ports.ports);
+ if (i == port)
+ continue;
+ slaves_pport_actv = mlx4_phys_to_slaves_pport_actv(
+ dev, &exclusive_ports);
+ slave_gid -= bitmap_weight(slaves_pport_actv.slaves,
+ dev->num_vfs + 1);
+ }
+ vfs = bitmap_weight(slaves_pport.slaves, dev->num_vfs + 1) - 1;
+ if (slave_gid <= ((MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) % vfs))
+ return ((MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) / vfs) + 1;
+ return (MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) / vfs;
+}
+
+int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port)
+{
+ int gids;
+ unsigned i;
+ int slave_gid = slave;
+ int vfs;
+
+ struct mlx4_slaves_pport slaves_pport;
+ struct mlx4_active_ports actv_ports;
+ unsigned max_port_p_one;
+
+ if (slave == 0)
+ return 0;
+
+ slaves_pport = mlx4_phys_to_slaves_pport(dev, port);
+ actv_ports = mlx4_get_active_ports(dev, slave);
+ max_port_p_one = find_first_bit(actv_ports.ports, dev->caps.num_ports) +
+ bitmap_weight(actv_ports.ports, dev->caps.num_ports) + 1;
+
+ for (i = 1; i < max_port_p_one; i++) {
+ struct mlx4_active_ports exclusive_ports;
+ struct mlx4_slaves_pport slaves_pport_actv;
+ bitmap_zero(exclusive_ports.ports, dev->caps.num_ports);
+ set_bit(i - 1, exclusive_ports.ports);
+ if (i == port)
+ continue;
+ slaves_pport_actv = mlx4_phys_to_slaves_pport_actv(
+ dev, &exclusive_ports);
+ slave_gid -= bitmap_weight(slaves_pport_actv.slaves,
+ dev->num_vfs + 1);
+ }
+ gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS;
+ vfs = bitmap_weight(slaves_pport.slaves, dev->num_vfs + 1) - 1;
+ if (slave_gid <= gids % vfs)
+ return MLX4_ROCE_PF_GIDS + ((gids / vfs) + 1) * (slave_gid - 1);
+
+ return MLX4_ROCE_PF_GIDS + (gids % vfs) +
+ ((gids / vfs) * (slave_gid - 1));
+}
+EXPORT_SYMBOL_GPL(mlx4_get_base_gid_ix);
static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
u8 op_mod, struct mlx4_cmd_mailbox *inbox)
@@ -515,14 +593,18 @@
struct mlx4_slave_state *slave_st = &master->slave_state[slave];
struct mlx4_set_port_rqp_calc_context *qpn_context;
struct mlx4_set_port_general_context *gen_context;
+ struct mlx4_roce_gid_entry *gid_entry_tbl, *gid_entry_mbox, *gid_entry_mb1;
int reset_qkey_viols;
int port;
int is_eth;
+ int num_gids;
+ int base;
u32 in_modifier;
u32 promisc;
u16 mtu, prev_mtu;
int err;
- int i;
+ int i, j;
+ int offset;
__be32 agg_cap_mask;
__be32 slave_cap_mask;
__be32 new_cap_mask;
@@ -535,7 +617,8 @@
/* Slaves cannot perform SET_PORT operations except changing MTU */
if (is_eth) {
if (slave != dev->caps.function &&
- in_modifier != MLX4_SET_PORT_GENERAL) {
+ in_modifier != MLX4_SET_PORT_GENERAL &&
+ in_modifier != MLX4_SET_PORT_GID_TABLE) {
mlx4_warn(dev, "denying SET_PORT for slave:%d\n",
slave);
return -EINVAL;
@@ -581,6 +664,67 @@
gen_context->mtu = cpu_to_be16(master->max_mtu[port]);
break;
+ case MLX4_SET_PORT_GID_TABLE:
+ /* change to MULTIPLE entries: number of guest's gids
+ * need a FOR-loop here over number of gids the guest has.
+ * 1. Check no duplicates in gids passed by slave
+ */
+ num_gids = mlx4_get_slave_num_gids(dev, slave, port);
+ base = mlx4_get_base_gid_ix(dev, slave, port);
+ gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf);
+ for (i = 0; i < num_gids; gid_entry_mbox++, i++) {
+ if (!memcmp(gid_entry_mbox->raw, zgid_entry.raw,
+ sizeof(zgid_entry)))
+ continue;
+ gid_entry_mb1 = gid_entry_mbox + 1;
+ for (j = i + 1; j < num_gids; gid_entry_mb1++, j++) {
+ if (!memcmp(gid_entry_mb1->raw,
+ zgid_entry.raw, sizeof(zgid_entry)))
+ continue;
+ if (!memcmp(gid_entry_mb1->raw, gid_entry_mbox->raw,
+ sizeof(gid_entry_mbox->raw))) {
+ /* found duplicate */
+ return -EINVAL;
+ }
+ }
+ }
+
+ /* 2. Check that do not have duplicates in OTHER
+ * entries in the port GID table
+ */
+ for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) {
+ if (i >= base && i < base + num_gids)
+ continue; /* don't compare to slave's current gids */
+ gid_entry_tbl = &priv->roce_gids[port - 1][i];
+ if (!memcmp(gid_entry_tbl->raw, zgid_entry.raw, sizeof(zgid_entry)))
+ continue;
+ gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf);
+ for (j = 0; j < num_gids; gid_entry_mbox++, j++) {
+ if (!memcmp(gid_entry_mbox->raw, zgid_entry.raw,
+ sizeof(zgid_entry)))
+ continue;
+ if (!memcmp(gid_entry_mbox->raw, gid_entry_tbl->raw,
+ sizeof(gid_entry_tbl->raw))) {
+ /* found duplicate */
+ mlx4_warn(dev, "requested gid entry for slave:%d "
+ "is a duplicate of gid at index %d\n",
+ slave, i);
+ return -EINVAL;
+ }
+ }
+ }
+
+ /* insert slave GIDs with memcpy, starting at slave's base index */
+ gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf);
+ for (i = 0, offset = base; i < num_gids; gid_entry_mbox++, offset++, i++)
+ memcpy(priv->roce_gids[port - 1][offset].raw, gid_entry_mbox->raw, 16);
+
+ /* Now, copy roce port gids table to current mailbox for passing to FW */
+ gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf);
+ for (i = 0; i < MLX4_ROCE_MAX_GIDS; gid_entry_mbox++, i++)
+ memcpy(gid_entry_mbox->raw, priv->roce_gids[port - 1][i].raw, 16);
+
+ break;
}
return mlx4_cmd(dev, inbox->dma, in_mod, op_mod,
MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
@@ -646,6 +790,15 @@
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd)
{
+ int port = mlx4_slave_convert_port(
+ dev, slave, vhcr->in_modifier & 0xFF);
+
+ if (port < 0)
+ return -EINVAL;
+
+ vhcr->in_modifier = (vhcr->in_modifier & ~0xFF) |
+ (port & 0xFF);
+
return mlx4_common_set_port(dev, slave, vhcr->in_modifier,
vhcr->op_modifier, inbox);
}
@@ -835,7 +988,7 @@
u8 steering;
};
-int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering)
+int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering, int enable)
{
int err;
u32 in_mod;
@@ -849,7 +1002,8 @@
memset(context, 0, sizeof(*context));
context->modify_flags = VXLAN_ENABLE_MODIFY | VXLAN_STEERING_MODIFY;
- context->enable_flags = VXLAN_ENABLE;
+ if (enable)
+ context->enable_flags = VXLAN_ENABLE;
context->steering = steering;
in_mod = MLX4_SET_PORT_VXLAN << 8 | port;
@@ -927,3 +1081,108 @@
*stats_bitmap |= MLX4_STATS_ERROR_COUNTERS_MASK;
}
EXPORT_SYMBOL(mlx4_set_stats_bitmap);
+
+int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
+ int *slave_id)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ int i, found_ix = -1;
+ int vf_gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS;
+ struct mlx4_slaves_pport slaves_pport;
+ unsigned num_vfs;
+ int slave_gid;
+
+ if (!mlx4_is_mfunc(dev))
+ return -EINVAL;
+
+ slaves_pport = mlx4_phys_to_slaves_pport(dev, port);
+ num_vfs = bitmap_weight(slaves_pport.slaves, dev->num_vfs + 1) - 1;
+
+ for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) {
+ if (!memcmp(priv->roce_gids[port - 1][i].raw, gid, 16)) {
+ found_ix = i;
+ break;
+ }
+ }
+
+ if (found_ix >= 0) {
+ if (found_ix < MLX4_ROCE_PF_GIDS)
+ slave_gid = 0;
+ else if (found_ix < MLX4_ROCE_PF_GIDS + (vf_gids % num_vfs) *
+ (vf_gids / num_vfs + 1))
+ slave_gid = ((found_ix - MLX4_ROCE_PF_GIDS) /
+ (vf_gids / num_vfs + 1)) + 1;
+ else
+ slave_gid =
+ ((found_ix - MLX4_ROCE_PF_GIDS -
+ ((vf_gids % num_vfs) * ((vf_gids / num_vfs + 1)))) /
+ (vf_gids / num_vfs)) + vf_gids % num_vfs + 1;
+
+ if (slave_gid) {
+ struct mlx4_active_ports exclusive_ports;
+ struct mlx4_active_ports actv_ports;
+ struct mlx4_slaves_pport slaves_pport_actv;
+ unsigned max_port_p_one;
+ int num_slaves_before = 1;
+
+ for (i = 1; i < port; i++) {
+ bitmap_zero(exclusive_ports.ports, dev->caps.num_ports);
+ set_bit(i, exclusive_ports.ports);
+ slaves_pport_actv =
+ mlx4_phys_to_slaves_pport_actv(
+ dev, &exclusive_ports);
+ num_slaves_before += bitmap_weight(
+ slaves_pport_actv.slaves,
+ dev->num_vfs + 1);
+ }
+
+ if (slave_gid < num_slaves_before) {
+ bitmap_zero(exclusive_ports.ports, dev->caps.num_ports);
+ set_bit(port - 1, exclusive_ports.ports);
+ slaves_pport_actv =
+ mlx4_phys_to_slaves_pport_actv(
+ dev, &exclusive_ports);
+ slave_gid += bitmap_weight(
+ slaves_pport_actv.slaves,
+ dev->num_vfs + 1) -
+ num_slaves_before;
+ }
+ actv_ports = mlx4_get_active_ports(dev, slave_gid);
+ max_port_p_one = find_first_bit(
+ actv_ports.ports, dev->caps.num_ports) +
+ bitmap_weight(actv_ports.ports,
+ dev->caps.num_ports) + 1;
+
+ for (i = 1; i < max_port_p_one; i++) {
+ if (i == port)
+ continue;
+ bitmap_zero(exclusive_ports.ports,
+ dev->caps.num_ports);
+ set_bit(i - 1, exclusive_ports.ports);
+ slaves_pport_actv =
+ mlx4_phys_to_slaves_pport_actv(
+ dev, &exclusive_ports);
+ slave_gid += bitmap_weight(
+ slaves_pport_actv.slaves,
+ dev->num_vfs + 1);
+ }
+ }
+ *slave_id = slave_gid;
+ }
+
+ return (found_ix >= 0) ? 0 : -EINVAL;
+}
+EXPORT_SYMBOL(mlx4_get_slave_from_roce_gid);
+
+int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id,
+ u8 *gid)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+
+ if (!mlx4_is_master(dev))
+ return -EINVAL;
+
+ memcpy(gid, priv->roce_gids[port - 1][slave_id].raw, 16);
+ return 0;
+}
+EXPORT_SYMBOL(mlx4_get_roce_gid_from_slave);
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 57428a0..3b5f53e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -52,6 +52,8 @@
struct mac_res {
struct list_head list;
u64 mac;
+ int ref_count;
+ u8 smac_index;
u8 port;
};
@@ -219,6 +221,11 @@
int qpn;
};
+static int mlx4_is_eth(struct mlx4_dev *dev, int port)
+{
+ return dev->caps.port_mask[port] == MLX4_PORT_TYPE_IB ? 0 : 1;
+}
+
static void *res_tracker_lookup(struct rb_root *root, u64 res_id)
{
struct rb_node *node = root->rb_node;
@@ -461,6 +468,8 @@
spin_lock_init(&res_alloc->alloc_lock);
for (t = 0; t < dev->num_vfs + 1; t++) {
+ struct mlx4_active_ports actv_ports =
+ mlx4_get_active_ports(dev, t);
switch (i) {
case RES_QP:
initialize_res_quotas(dev, res_alloc, RES_QP,
@@ -490,10 +499,27 @@
break;
case RES_MAC:
if (t == mlx4_master_func_num(dev)) {
- res_alloc->quota[t] = MLX4_MAX_MAC_NUM;
+ int max_vfs_pport = 0;
+ /* Calculate the max vfs per port for */
+ /* both ports. */
+ for (j = 0; j < dev->caps.num_ports;
+ j++) {
+ struct mlx4_slaves_pport slaves_pport =
+ mlx4_phys_to_slaves_pport(dev, j + 1);
+ unsigned current_slaves =
+ bitmap_weight(slaves_pport.slaves,
+ dev->caps.num_ports) - 1;
+ if (max_vfs_pport < current_slaves)
+ max_vfs_pport =
+ current_slaves;
+ }
+ res_alloc->quota[t] =
+ MLX4_MAX_MAC_NUM -
+ 2 * max_vfs_pport;
res_alloc->guaranteed[t] = 2;
for (j = 0; j < MLX4_MAX_PORTS; j++)
- res_alloc->res_port_free[j] = MLX4_MAX_MAC_NUM;
+ res_alloc->res_port_free[j] =
+ MLX4_MAX_MAC_NUM;
} else {
res_alloc->quota[t] = MLX4_MAX_MAC_NUM;
res_alloc->guaranteed[t] = 2;
@@ -521,9 +547,10 @@
break;
}
if (i == RES_MAC || i == RES_VLAN) {
- for (j = 0; j < MLX4_MAX_PORTS; j++)
- res_alloc->res_port_rsvd[j] +=
- res_alloc->guaranteed[t];
+ for (j = 0; j < dev->caps.num_ports; j++)
+ if (test_bit(j, actv_ports.ports))
+ res_alloc->res_port_rsvd[j] +=
+ res_alloc->guaranteed[t];
} else {
res_alloc->res_reserved += res_alloc->guaranteed[t];
}
@@ -600,15 +627,37 @@
struct mlx4_qp_context *qp_ctx = inbox->buf + 8;
enum mlx4_qp_optpar optpar = be32_to_cpu(*(__be32 *) inbox->buf);
u32 ts = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff;
+ int port;
- if (MLX4_QP_ST_UD == ts)
- qp_ctx->pri_path.mgid_index = 0x80 | slave;
+ if (MLX4_QP_ST_UD == ts) {
+ port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
+ if (mlx4_is_eth(dev, port))
+ qp_ctx->pri_path.mgid_index =
+ mlx4_get_base_gid_ix(dev, slave, port) | 0x80;
+ else
+ qp_ctx->pri_path.mgid_index = slave | 0x80;
- if (MLX4_QP_ST_RC == ts || MLX4_QP_ST_UC == ts) {
- if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH)
- qp_ctx->pri_path.mgid_index = slave & 0x7F;
- if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH)
- qp_ctx->alt_path.mgid_index = slave & 0x7F;
+ } else if (MLX4_QP_ST_RC == ts || MLX4_QP_ST_XRC == ts || MLX4_QP_ST_UC == ts) {
+ if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) {
+ port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
+ if (mlx4_is_eth(dev, port)) {
+ qp_ctx->pri_path.mgid_index +=
+ mlx4_get_base_gid_ix(dev, slave, port);
+ qp_ctx->pri_path.mgid_index &= 0x7f;
+ } else {
+ qp_ctx->pri_path.mgid_index = slave & 0x7F;
+ }
+ }
+ if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) {
+ port = (qp_ctx->alt_path.sched_queue >> 6 & 1) + 1;
+ if (mlx4_is_eth(dev, port)) {
+ qp_ctx->alt_path.mgid_index +=
+ mlx4_get_base_gid_ix(dev, slave, port);
+ qp_ctx->alt_path.mgid_index &= 0x7f;
+ } else {
+ qp_ctx->alt_path.mgid_index = slave & 0x7F;
+ }
+ }
}
}
@@ -619,7 +668,6 @@
struct mlx4_qp_context *qpc = inbox->buf + 8;
struct mlx4_vport_oper_state *vp_oper;
struct mlx4_priv *priv;
- u32 qp_type;
int port;
port = (qpc->pri_path.sched_queue & 0x40) ? 2 : 1;
@@ -627,12 +675,6 @@
vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
if (MLX4_VGT != vp_oper->state.default_vlan) {
- qp_type = (be32_to_cpu(qpc->flags) >> 16) & 0xff;
- if (MLX4_QP_ST_RC == qp_type ||
- (MLX4_QP_ST_UD == qp_type &&
- !mlx4_is_qp_reserved(dev, qpn)))
- return -EINVAL;
-
/* the reserved QPs (special, proxy, tunnel)
* do not operate over vlans
*/
@@ -1659,11 +1701,39 @@
return err;
}
-static int mac_add_to_slave(struct mlx4_dev *dev, int slave, u64 mac, int port)
+static int mac_find_smac_ix_in_slave(struct mlx4_dev *dev, int slave, int port,
+ u8 smac_index, u64 *mac)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
- struct mac_res *res;
+ struct list_head *mac_list =
+ &tracker->slave_list[slave].res_list[RES_MAC];
+ struct mac_res *res, *tmp;
+
+ list_for_each_entry_safe(res, tmp, mac_list, list) {
+ if (res->smac_index == smac_index && res->port == (u8) port) {
+ *mac = res->mac;
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
+static int mac_add_to_slave(struct mlx4_dev *dev, int slave, u64 mac, int port, u8 smac_index)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+ struct list_head *mac_list =
+ &tracker->slave_list[slave].res_list[RES_MAC];
+ struct mac_res *res, *tmp;
+
+ list_for_each_entry_safe(res, tmp, mac_list, list) {
+ if (res->mac == mac && res->port == (u8) port) {
+ /* mac found. update ref count */
+ ++res->ref_count;
+ return 0;
+ }
+ }
if (mlx4_grant_resource(dev, slave, RES_MAC, 1, port))
return -EINVAL;
@@ -1674,6 +1744,8 @@
}
res->mac = mac;
res->port = (u8) port;
+ res->smac_index = smac_index;
+ res->ref_count = 1;
list_add_tail(&res->list,
&tracker->slave_list[slave].res_list[RES_MAC]);
return 0;
@@ -1690,9 +1762,11 @@
list_for_each_entry_safe(res, tmp, mac_list, list) {
if (res->mac == mac && res->port == (u8) port) {
- list_del(&res->list);
- mlx4_release_resource(dev, slave, RES_MAC, 1, port);
- kfree(res);
+ if (!--res->ref_count) {
+ list_del(&res->list);
+ mlx4_release_resource(dev, slave, RES_MAC, 1, port);
+ kfree(res);
+ }
break;
}
}
@@ -1705,10 +1779,13 @@
struct list_head *mac_list =
&tracker->slave_list[slave].res_list[RES_MAC];
struct mac_res *res, *tmp;
+ int i;
list_for_each_entry_safe(res, tmp, mac_list, list) {
list_del(&res->list);
- __mlx4_unregister_mac(dev, res->port, res->mac);
+ /* dereference the mac the num times the slave referenced it */
+ for (i = 0; i < res->ref_count; i++)
+ __mlx4_unregister_mac(dev, res->port, res->mac);
mlx4_release_resource(dev, slave, RES_MAC, 1, res->port);
kfree(res);
}
@@ -1720,21 +1797,28 @@
int err = -EINVAL;
int port;
u64 mac;
+ u8 smac_index;
if (op != RES_OP_RESERVE_AND_MAP)
return err;
port = !in_port ? get_param_l(out_param) : in_port;
+ port = mlx4_slave_convert_port(
+ dev, slave, port);
+
+ if (port < 0)
+ return -EINVAL;
mac = in_param;
err = __mlx4_register_mac(dev, port, mac);
if (err >= 0) {
+ smac_index = err;
set_param_l(out_param, err);
err = 0;
}
if (!err) {
- err = mac_add_to_slave(dev, slave, mac, port);
+ err = mac_add_to_slave(dev, slave, mac, port, smac_index);
if (err)
__mlx4_unregister_mac(dev, port, mac);
}
@@ -1831,6 +1915,11 @@
if (!port || op != RES_OP_RESERVE_AND_MAP)
return -EINVAL;
+ port = mlx4_slave_convert_port(
+ dev, slave, port);
+
+ if (port < 0)
+ return -EINVAL;
/* upstream kernels had NOP for reg/unreg vlan. Continue this. */
if (!in_port && port > 0 && port <= dev->caps.num_ports) {
slave_state[slave].old_vlan_api = true;
@@ -2128,6 +2217,11 @@
switch (op) {
case RES_OP_RESERVE_AND_MAP:
port = !in_port ? get_param_l(out_param) : in_port;
+ port = mlx4_slave_convert_port(
+ dev, slave, port);
+
+ if (port < 0)
+ return -EINVAL;
mac_del_from_slave(dev, slave, in_param, port);
__mlx4_unregister_mac(dev, port, in_param);
break;
@@ -2147,6 +2241,11 @@
struct mlx4_slave_state *slave_state = priv->mfunc.master.slave_state;
int err = 0;
+ port = mlx4_slave_convert_port(
+ dev, slave, port);
+
+ if (port < 0)
+ return -EINVAL;
switch (op) {
case RES_OP_RESERVE_AND_MAP:
if (slave_state[slave].old_vlan_api)
@@ -2734,6 +2833,8 @@
u32 qp_type;
struct mlx4_qp_context *qp_ctx;
enum mlx4_qp_optpar optpar;
+ int port;
+ int num_gids;
qp_ctx = inbox->buf + 8;
qp_type = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff;
@@ -2741,6 +2842,7 @@
switch (qp_type) {
case MLX4_QP_ST_RC:
+ case MLX4_QP_ST_XRC:
case MLX4_QP_ST_UC:
switch (transition) {
case QP_TRANS_INIT2RTR:
@@ -2749,13 +2851,24 @@
case QP_TRANS_SQD2SQD:
case QP_TRANS_SQD2RTS:
if (slave != mlx4_master_func_num(dev))
- /* slaves have only gid index 0 */
- if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH)
- if (qp_ctx->pri_path.mgid_index)
+ if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) {
+ port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
+ if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB)
+ num_gids = mlx4_get_slave_num_gids(dev, slave, port);
+ else
+ num_gids = 1;
+ if (qp_ctx->pri_path.mgid_index >= num_gids)
return -EINVAL;
- if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH)
- if (qp_ctx->alt_path.mgid_index)
+ }
+ if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) {
+ port = (qp_ctx->alt_path.sched_queue >> 6 & 1) + 1;
+ if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB)
+ num_gids = mlx4_get_slave_num_gids(dev, slave, port);
+ else
+ num_gids = 1;
+ if (qp_ctx->alt_path.mgid_index >= num_gids)
return -EINVAL;
+ }
break;
default:
break;
@@ -3268,6 +3381,58 @@
return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
}
+static int adjust_qp_sched_queue(struct mlx4_dev *dev, int slave,
+ struct mlx4_qp_context *qpc,
+ struct mlx4_cmd_mailbox *inbox)
+{
+ enum mlx4_qp_optpar optpar = be32_to_cpu(*(__be32 *)inbox->buf);
+ u8 pri_sched_queue;
+ int port = mlx4_slave_convert_port(
+ dev, slave, (qpc->pri_path.sched_queue >> 6 & 1) + 1) - 1;
+
+ if (port < 0)
+ return -EINVAL;
+
+ pri_sched_queue = (qpc->pri_path.sched_queue & ~(1 << 6)) |
+ ((port & 1) << 6);
+
+ if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH ||
+ mlx4_is_eth(dev, port + 1)) {
+ qpc->pri_path.sched_queue = pri_sched_queue;
+ }
+
+ if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) {
+ port = mlx4_slave_convert_port(
+ dev, slave, (qpc->alt_path.sched_queue >> 6 & 1)
+ + 1) - 1;
+ if (port < 0)
+ return -EINVAL;
+ qpc->alt_path.sched_queue =
+ (qpc->alt_path.sched_queue & ~(1 << 6)) |
+ (port & 1) << 6;
+ }
+ return 0;
+}
+
+static int roce_verify_mac(struct mlx4_dev *dev, int slave,
+ struct mlx4_qp_context *qpc,
+ struct mlx4_cmd_mailbox *inbox)
+{
+ u64 mac;
+ int port;
+ u32 ts = (be32_to_cpu(qpc->flags) >> 16) & 0xff;
+ u8 sched = *(u8 *)(inbox->buf + 64);
+ u8 smac_ix;
+
+ port = (sched >> 6 & 1) + 1;
+ if (mlx4_is_eth(dev, port) && (ts != MLX4_QP_ST_MLX)) {
+ smac_ix = qpc->pri_path.grh_mylmc & 0x7f;
+ if (mac_find_smac_ix_in_slave(dev, slave, port, smac_ix, &mac))
+ return -ENOENT;
+ }
+ return 0;
+}
+
int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
@@ -3286,10 +3451,16 @@
u8 orig_vlan_index = qpc->pri_path.vlan_index;
u8 orig_feup = qpc->pri_path.feup;
+ err = adjust_qp_sched_queue(dev, slave, qpc, inbox);
+ if (err)
+ return err;
err = verify_qp_parameters(dev, inbox, QP_TRANS_INIT2RTR, slave);
if (err)
return err;
+ if (roce_verify_mac(dev, slave, qpc, inbox))
+ return -EINVAL;
+
update_pkey_index(dev, slave, inbox);
update_gid(dev, inbox, (u8)slave);
adjust_proxy_tun_qkey(dev, vhcr, qpc);
@@ -3334,6 +3505,9 @@
int err;
struct mlx4_qp_context *context = inbox->buf + 8;
+ err = adjust_qp_sched_queue(dev, slave, context, inbox);
+ if (err)
+ return err;
err = verify_qp_parameters(dev, inbox, QP_TRANS_RTR2RTS, slave);
if (err)
return err;
@@ -3353,6 +3527,9 @@
int err;
struct mlx4_qp_context *context = inbox->buf + 8;
+ err = adjust_qp_sched_queue(dev, slave, context, inbox);
+ if (err)
+ return err;
err = verify_qp_parameters(dev, inbox, QP_TRANS_RTS2RTS, slave);
if (err)
return err;
@@ -3371,6 +3548,9 @@
struct mlx4_cmd_info *cmd)
{
struct mlx4_qp_context *context = inbox->buf + 8;
+ int err = adjust_qp_sched_queue(dev, slave, context, inbox);
+ if (err)
+ return err;
adjust_proxy_tun_qkey(dev, vhcr, context);
return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
}
@@ -3384,6 +3564,9 @@
int err;
struct mlx4_qp_context *context = inbox->buf + 8;
+ err = adjust_qp_sched_queue(dev, slave, context, inbox);
+ if (err)
+ return err;
err = verify_qp_parameters(dev, inbox, QP_TRANS_SQD2SQD, slave);
if (err)
return err;
@@ -3403,6 +3586,9 @@
int err;
struct mlx4_qp_context *context = inbox->buf + 8;
+ err = adjust_qp_sched_queue(dev, slave, context, inbox);
+ if (err)
+ return err;
err = verify_qp_parameters(dev, inbox, QP_TRANS_SQD2RTS, slave);
if (err)
return err;
@@ -3506,16 +3692,26 @@
return err;
}
-static int qp_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
- int block_loopback, enum mlx4_protocol prot,
+static int qp_attach(struct mlx4_dev *dev, int slave, struct mlx4_qp *qp,
+ u8 gid[16], int block_loopback, enum mlx4_protocol prot,
enum mlx4_steer_type type, u64 *reg_id)
{
switch (dev->caps.steering_mode) {
- case MLX4_STEERING_MODE_DEVICE_MANAGED:
- return mlx4_trans_to_dmfs_attach(dev, qp, gid, gid[5],
+ case MLX4_STEERING_MODE_DEVICE_MANAGED: {
+ int port = mlx4_slave_convert_port(dev, slave, gid[5]);
+ if (port < 0)
+ return port;
+ return mlx4_trans_to_dmfs_attach(dev, qp, gid, port,
block_loopback, prot,
reg_id);
+ }
case MLX4_STEERING_MODE_B0:
+ if (prot == MLX4_PROT_ETH) {
+ int port = mlx4_slave_convert_port(dev, slave, gid[5]);
+ if (port < 0)
+ return port;
+ gid[5] = port;
+ }
return mlx4_qp_attach_common(dev, qp, gid,
block_loopback, prot, type);
default:
@@ -3523,9 +3719,9 @@
}
}
-static int qp_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
- enum mlx4_protocol prot, enum mlx4_steer_type type,
- u64 reg_id)
+static int qp_detach(struct mlx4_dev *dev, struct mlx4_qp *qp,
+ u8 gid[16], enum mlx4_protocol prot,
+ enum mlx4_steer_type type, u64 reg_id)
{
switch (dev->caps.steering_mode) {
case MLX4_STEERING_MODE_DEVICE_MANAGED:
@@ -3562,7 +3758,7 @@
qp.qpn = qpn;
if (attach) {
- err = qp_attach(dev, &qp, gid, block_loopback, prot,
+ err = qp_attach(dev, slave, &qp, gid, block_loopback, prot,
type, ®_id);
if (err) {
pr_err("Fail to attach rule to qp 0x%x\n", qpn);
@@ -3698,6 +3894,9 @@
return -EOPNOTSUPP;
ctrl = (struct mlx4_net_trans_rule_hw_ctrl *)inbox->buf;
+ ctrl->port = mlx4_slave_convert_port(dev, slave, ctrl->port);
+ if (ctrl->port <= 0)
+ return -EINVAL;
qpn = be32_to_cpu(ctrl->qpn) & 0xffffff;
err = get_res(dev, slave, qpn, RES_QP, &rqp);
if (err) {
@@ -3816,16 +4015,6 @@
return err;
}
-int mlx4_FLOW_STEERING_IB_UC_QP_RANGE_wrapper(struct mlx4_dev *dev, int slave,
- struct mlx4_vhcr *vhcr,
- struct mlx4_cmd_mailbox *inbox,
- struct mlx4_cmd_mailbox *outbox,
- struct mlx4_cmd_info *cmd)
-{
- return -EPERM;
-}
-
-
static void detach_qp(struct mlx4_dev *dev, int slave, struct res_qp *rqp)
{
struct res_gid *rgid;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 157fe8d..8ff57e8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -4,5 +4,5 @@
config MLX5_CORE
tristate
- depends on PCI && X86
+ depends on PCI
default n
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a064f06..77ac95f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -46,8 +46,8 @@
#include "mlx5_core.h"
#define DRIVER_NAME "mlx5_core"
-#define DRIVER_VERSION "1.0"
-#define DRIVER_RELDATE "June 2013"
+#define DRIVER_VERSION "2.2-1"
+#define DRIVER_RELDATE "Feb 2014"
MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
MODULE_DESCRIPTION("Mellanox ConnectX-IB HCA core library");
@@ -116,7 +116,6 @@
struct mlx5_eq_table *table = &dev->priv.eq_table;
int num_eqs = 1 << dev->caps.log_max_eq;
int nvec;
- int err;
int i;
nvec = dev->caps.num_ports * num_online_cpus() + MLX5_EQ_VEC_COMP_BASE;
@@ -131,17 +130,12 @@
for (i = 0; i < nvec; i++)
table->msix_arr[i].entry = i;
-retry:
- table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE;
- err = pci_enable_msix(dev->pdev, table->msix_arr, nvec);
- if (err <= 0) {
- return err;
- } else if (err > 2) {
- nvec = err;
- goto retry;
- }
+ nvec = pci_enable_msix_range(dev->pdev, table->msix_arr,
+ MLX5_EQ_VEC_COMP_BASE, nvec);
+ if (nvec < 0)
+ return nvec;
- mlx5_core_dbg(dev, "received %d MSI vectors out of %d requested\n", err, nvec);
+ table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE;
return 0;
}
@@ -537,7 +531,6 @@
return 0;
- mlx5_health_cleanup();
err_debug:
mlx5_unregister_debugfs();
return err;
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index 727b546a..e0c92e0 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -23,6 +23,7 @@
#include <linux/crc32.h>
#include <linux/mii.h>
#include <linux/eeprom_93cx6.h>
+#include <linux/regulator/consumer.h>
#include <linux/spi/spi.h>
@@ -83,6 +84,7 @@
* @rc_rxqcr: Cached copy of KS_RXQCR.
* @eeprom_size: Companion eeprom size in Bytes, 0 if no eeprom
* @eeprom: 93CX6 EEPROM state for accessing on-board EEPROM.
+ * @vdd_reg: Optional regulator supplying the chip
*
* The @lock ensures that the chip is protected when certain operations are
* in progress. When the read or write packet transfer is in progress, most
@@ -130,6 +132,7 @@
struct spi_transfer spi_xfer2[2];
struct eeprom_93cx6 eeprom;
+ struct regulator *vdd_reg;
};
static int msg_enable;
@@ -1414,6 +1417,21 @@
ks->spidev = spi;
ks->tx_space = 6144;
+ ks->vdd_reg = regulator_get_optional(&spi->dev, "vdd");
+ if (IS_ERR(ks->vdd_reg)) {
+ ret = PTR_ERR(ks->vdd_reg);
+ if (ret == -EPROBE_DEFER)
+ goto err_reg;
+ } else {
+ ret = regulator_enable(ks->vdd_reg);
+ if (ret) {
+ dev_err(&spi->dev, "regulator enable fail: %d\n",
+ ret);
+ goto err_reg_en;
+ }
+ }
+
+
mutex_init(&ks->lock);
spin_lock_init(&ks->statelock);
@@ -1508,8 +1526,14 @@
err_netdev:
free_irq(ndev->irq, ks);
-err_id:
err_irq:
+err_id:
+ if (!IS_ERR(ks->vdd_reg))
+ regulator_disable(ks->vdd_reg);
+err_reg_en:
+ if (!IS_ERR(ks->vdd_reg))
+ regulator_put(ks->vdd_reg);
+err_reg:
free_netdev(ndev);
return ret;
}
@@ -1523,6 +1547,10 @@
unregister_netdev(priv->netdev);
free_irq(spi->irq, priv);
+ if (!IS_ERR(priv->vdd_reg)) {
+ regulator_disable(priv->vdd_reg);
+ regulator_put(priv->vdd_reg);
+ }
free_netdev(priv->netdev);
return 0;
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index ce84dc2..14ac0e2 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -4832,7 +4832,7 @@
skb->csum = old->csum;
skb_set_network_header(skb, ETH_HLEN);
- dev_kfree_skb(old);
+ dev_consume_skb_any(old);
}
/**
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 68026f7..130f6b2 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -2329,16 +2329,14 @@
status = 0;
if (myri10ge_msi) {
if (mgp->num_slices > 1) {
- status =
- pci_enable_msix(pdev, mgp->msix_vectors,
- mgp->num_slices);
- if (status == 0) {
- mgp->msix_enabled = 1;
- } else {
+ status = pci_enable_msix_range(pdev, mgp->msix_vectors,
+ mgp->num_slices, mgp->num_slices);
+ if (status < 0) {
dev_err(&pdev->dev,
"Error %d setting up MSI-X\n", status);
return status;
}
+ mgp->msix_enabled = 1;
}
if (mgp->msix_enabled == 0) {
status = pci_enable_msi(pdev);
@@ -3895,32 +3893,34 @@
mgp->msix_vectors = kcalloc(mgp->num_slices, sizeof(*mgp->msix_vectors),
GFP_KERNEL);
if (mgp->msix_vectors == NULL)
- goto disable_msix;
+ goto no_msix;
for (i = 0; i < mgp->num_slices; i++) {
mgp->msix_vectors[i].entry = i;
}
while (mgp->num_slices > 1) {
- /* make sure it is a power of two */
- while (!is_power_of_2(mgp->num_slices))
- mgp->num_slices--;
+ mgp->num_slices = rounddown_pow_of_two(mgp->num_slices);
if (mgp->num_slices == 1)
- goto disable_msix;
- status = pci_enable_msix(pdev, mgp->msix_vectors,
- mgp->num_slices);
- if (status == 0) {
- pci_disable_msix(pdev);
+ goto no_msix;
+ status = pci_enable_msix_range(pdev,
+ mgp->msix_vectors,
+ mgp->num_slices,
+ mgp->num_slices);
+ if (status < 0)
+ goto no_msix;
+
+ pci_disable_msix(pdev);
+
+ if (status == mgp->num_slices) {
if (old_allocated)
kfree(old_fw);
return;
- }
- if (status > 0)
+ } else {
mgp->num_slices = status;
- else
- goto disable_msix;
+ }
}
-disable_msix:
+no_msix:
if (mgp->msix_vectors != NULL) {
kfree(mgp->msix_vectors);
mgp->msix_vectors = NULL;
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 9eeddbd..a2844ff 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -2914,6 +2914,9 @@
struct RxD1 *rxdp1;
struct RxD3 *rxdp3;
+ if (budget <= 0)
+ return napi_pkts;
+
get_info = ring_data->rx_curr_get_info;
get_block = get_info.block_index;
memcpy(&put_info, &ring_data->rx_curr_put_info, sizeof(put_info));
@@ -3792,9 +3795,10 @@
writeq(rx_mat, &bar0->rx_mat);
readq(&bar0->rx_mat);
- ret = pci_enable_msix(nic->pdev, nic->entries, nic->num_entries);
+ ret = pci_enable_msix_range(nic->pdev, nic->entries,
+ nic->num_entries, nic->num_entries);
/* We fail init if error or we get less vectors than min required */
- if (ret) {
+ if (ret < 0) {
DBG_PRINT(ERR_DBG, "Enabling MSI-X failed\n");
kfree(nic->entries);
swstats->mem_freed += nic->num_entries *
@@ -4045,7 +4049,7 @@
if (!is_s2io_card_up(sp)) {
DBG_PRINT(TX_DBG, "%s: Card going down for reset\n",
dev->name);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -4118,7 +4122,7 @@
((put_off+1) == queue_len ? 0 : (put_off+1)) == get_off) {
DBG_PRINT(TX_DBG, "Error in xmit, No free TXDs.\n");
s2io_stop_tx_queue(sp, fifo->fifo_no);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
spin_unlock_irqrestore(&fifo->tx_lock, flags);
return NETDEV_TX_OK;
}
@@ -4240,7 +4244,7 @@
swstats->pci_map_fail_cnt++;
s2io_stop_tx_queue(sp, fifo->fifo_no);
swstats->mem_freed += skb->truesize;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
spin_unlock_irqrestore(&fifo->tx_lock, flags);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index 1ded50ca..d107bcb 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -368,6 +368,9 @@
vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
ring->ndev->name, __func__, __LINE__);
+ if (ring->budget <= 0)
+ goto out;
+
do {
prefetch((char *)dtr + L1_CACHE_BYTES);
rx_priv = vxge_hw_ring_rxd_private_get(dtr);
@@ -525,6 +528,7 @@
if (first_dtr)
vxge_hw_ring_rxd_post_post_wmb(ringh, first_dtr);
+out:
vxge_debug_entryexit(VXGE_TRACE,
"%s:%d Exiting...",
__func__, __LINE__);
@@ -726,9 +730,6 @@
int vpath_idx = 0;
enum vxge_hw_status status = VXGE_HW_OK;
struct vxge_vpath *vpath = NULL;
- struct __vxge_hw_device *hldev;
-
- hldev = pci_get_drvdata(vdev->pdev);
mac_address = (u8 *)&mac_addr;
memcpy(mac_address, mac_header, ETH_ALEN);
@@ -823,7 +824,7 @@
if (unlikely(skb->len <= 0)) {
vxge_debug_tx(VXGE_ERR,
"%s: Buffer has no data..", dev->name);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -832,7 +833,7 @@
if (unlikely(!is_vxge_card_up(vdev))) {
vxge_debug_tx(VXGE_ERR,
"%s: vdev not initialized", dev->name);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -842,7 +843,7 @@
vxge_debug_tx(VXGE_ERR,
"%s: Failed to store the mac address",
dev->name);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
}
@@ -989,7 +990,7 @@
vxge_hw_fifo_txdl_free(fifo_hw, dtr);
_exit0:
netif_tx_stop_queue(fifo->txq);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -2352,12 +2353,18 @@
vdev->vxge_entries[j].entry = VXGE_ALARM_MSIX_ID;
vdev->vxge_entries[j].in_use = 0;
- ret = pci_enable_msix(vdev->pdev, vdev->entries, vdev->intr_cnt);
- if (ret > 0) {
+ ret = pci_enable_msix_range(vdev->pdev,
+ vdev->entries, 3, vdev->intr_cnt);
+ if (ret < 0) {
+ ret = -ENODEV;
+ goto enable_msix_failed;
+ } else if (ret < vdev->intr_cnt) {
+ pci_disable_msix(vdev->pdev);
+
vxge_debug_init(VXGE_ERR,
"%s: MSI-X enable failed for %d vectors, ret: %d",
VXGE_DRIVER_NAME, vdev->intr_cnt, ret);
- if ((max_config_vpath != VXGE_USE_DEFAULT) || (ret < 3)) {
+ if (max_config_vpath != VXGE_USE_DEFAULT) {
ret = -ENODEV;
goto enable_msix_failed;
}
@@ -2371,9 +2378,6 @@
vxge_close_vpaths(vdev, temp);
vdev->no_of_vpath = temp;
goto start;
- } else if (ret < 0) {
- ret = -ENODEV;
- goto enable_msix_failed;
}
return 0;
@@ -2443,9 +2447,6 @@
static void vxge_rem_isr(struct vxgedev *vdev)
{
- struct __vxge_hw_device *hldev;
- hldev = pci_get_drvdata(vdev->pdev);
-
#ifdef CONFIG_PCI_MSI
if (vdev->config.intr_type == MSI_X) {
vxge_rem_msix_isr(vdev);
@@ -3137,12 +3138,12 @@
u64 packets, bytes, multicast;
do {
- start = u64_stats_fetch_begin_bh(&rxstats->syncp);
+ start = u64_stats_fetch_begin_irq(&rxstats->syncp);
packets = rxstats->rx_frms;
multicast = rxstats->rx_mcast;
bytes = rxstats->rx_bytes;
- } while (u64_stats_fetch_retry_bh(&rxstats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&rxstats->syncp, start));
net_stats->rx_packets += packets;
net_stats->rx_bytes += bytes;
@@ -3152,11 +3153,11 @@
net_stats->rx_dropped += rxstats->rx_dropped;
do {
- start = u64_stats_fetch_begin_bh(&txstats->syncp);
+ start = u64_stats_fetch_begin_irq(&txstats->syncp);
packets = txstats->tx_frms;
bytes = txstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&txstats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&txstats->syncp, start));
net_stats->tx_packets += packets;
net_stats->tx_bytes += bytes;
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 70cf97f..fddb464 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -1753,19 +1753,19 @@
/* software stats */
do {
- syncp_start = u64_stats_fetch_begin_bh(&np->swstats_rx_syncp);
+ syncp_start = u64_stats_fetch_begin_irq(&np->swstats_rx_syncp);
storage->rx_packets = np->stat_rx_packets;
storage->rx_bytes = np->stat_rx_bytes;
storage->rx_dropped = np->stat_rx_dropped;
storage->rx_missed_errors = np->stat_rx_missed_errors;
- } while (u64_stats_fetch_retry_bh(&np->swstats_rx_syncp, syncp_start));
+ } while (u64_stats_fetch_retry_irq(&np->swstats_rx_syncp, syncp_start));
do {
- syncp_start = u64_stats_fetch_begin_bh(&np->swstats_tx_syncp);
+ syncp_start = u64_stats_fetch_begin_irq(&np->swstats_tx_syncp);
storage->tx_packets = np->stat_tx_packets;
storage->tx_bytes = np->stat_tx_bytes;
storage->tx_dropped = np->stat_tx_dropped;
- } while (u64_stats_fetch_retry_bh(&np->swstats_tx_syncp, syncp_start));
+ } while (u64_stats_fetch_retry_irq(&np->swstats_tx_syncp, syncp_start));
/* If the nic supports hw counters then retrieve latest values */
if (np->driver_data & DEV_HAS_STATISTICS_V123) {
@@ -2231,7 +2231,7 @@
if (pci_dma_mapping_error(np->pci_dev,
np->put_tx_ctx->dma)) {
/* on DMA mapping error - drop the packet */
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
u64_stats_update_begin(&np->swstats_tx_syncp);
np->stat_tx_dropped++;
u64_stats_update_end(&np->swstats_tx_syncp);
@@ -2277,7 +2277,7 @@
if (unlikely(tmp_tx_ctx++ == np->last_tx_ctx))
tmp_tx_ctx = np->first_tx_ctx;
} while (tmp_tx_ctx != np->put_tx_ctx);
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
np->put_tx_ctx = start_tx_ctx;
u64_stats_update_begin(&np->swstats_tx_syncp);
np->stat_tx_dropped++;
@@ -2380,7 +2380,7 @@
if (pci_dma_mapping_error(np->pci_dev,
np->put_tx_ctx->dma)) {
/* on DMA mapping error - drop the packet */
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
u64_stats_update_begin(&np->swstats_tx_syncp);
np->stat_tx_dropped++;
u64_stats_update_end(&np->swstats_tx_syncp);
@@ -2427,7 +2427,7 @@
if (unlikely(tmp_tx_ctx++ == np->last_tx_ctx))
tmp_tx_ctx = np->first_tx_ctx;
} while (tmp_tx_ctx != np->put_tx_ctx);
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
np->put_tx_ctx = start_tx_ctx;
u64_stats_update_begin(&np->swstats_tx_syncp);
np->stat_tx_dropped++;
@@ -3930,7 +3930,7 @@
{
struct fe_priv *np = get_nvpriv(dev);
u8 __iomem *base = get_hwbase(dev);
- int ret = 1;
+ int ret;
int i;
irqreturn_t (*handler)(int foo, void *data);
@@ -3946,14 +3946,18 @@
if (np->msi_flags & NV_MSI_X_CAPABLE) {
for (i = 0; i < (np->msi_flags & NV_MSI_X_VECTORS_MASK); i++)
np->msi_x_entry[i].entry = i;
- ret = pci_enable_msix(np->pci_dev, np->msi_x_entry, (np->msi_flags & NV_MSI_X_VECTORS_MASK));
- if (ret == 0) {
+ ret = pci_enable_msix_range(np->pci_dev,
+ np->msi_x_entry,
+ np->msi_flags & NV_MSI_X_VECTORS_MASK,
+ np->msi_flags & NV_MSI_X_VECTORS_MASK);
+ if (ret > 0) {
np->msi_flags |= NV_MSI_X_ENABLED;
if (optimization_mode == NV_OPTIMIZATION_MODE_THROUGHPUT && !intr_test) {
/* Request irq for rx handling */
sprintf(np->name_rx, "%s-rx", dev->name);
- if (request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector,
- nv_nic_irq_rx, IRQF_SHARED, np->name_rx, dev) != 0) {
+ ret = request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector,
+ nv_nic_irq_rx, IRQF_SHARED, np->name_rx, dev);
+ if (ret) {
netdev_info(dev,
"request_irq failed for rx %d\n",
ret);
@@ -3963,8 +3967,9 @@
}
/* Request irq for tx handling */
sprintf(np->name_tx, "%s-tx", dev->name);
- if (request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector,
- nv_nic_irq_tx, IRQF_SHARED, np->name_tx, dev) != 0) {
+ ret = request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector,
+ nv_nic_irq_tx, IRQF_SHARED, np->name_tx, dev);
+ if (ret) {
netdev_info(dev,
"request_irq failed for tx %d\n",
ret);
@@ -3974,8 +3979,9 @@
}
/* Request irq for link and timer handling */
sprintf(np->name_other, "%s-other", dev->name);
- if (request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector,
- nv_nic_irq_other, IRQF_SHARED, np->name_other, dev) != 0) {
+ ret = request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector,
+ nv_nic_irq_other, IRQF_SHARED, np->name_other, dev);
+ if (ret) {
netdev_info(dev,
"request_irq failed for link %d\n",
ret);
@@ -3991,7 +3997,9 @@
set_msix_vector_map(dev, NV_MSI_X_VECTOR_OTHER, NVREG_IRQ_OTHER);
} else {
/* Request irq for all interrupts */
- if (request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector, handler, IRQF_SHARED, dev->name, dev) != 0) {
+ ret = request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector,
+ handler, IRQF_SHARED, dev->name, dev);
+ if (ret) {
netdev_info(dev,
"request_irq failed %d\n",
ret);
@@ -4005,13 +4013,15 @@
writel(0, base + NvRegMSIXMap1);
}
netdev_info(dev, "MSI-X enabled\n");
+ return 0;
}
}
- if (ret != 0 && np->msi_flags & NV_MSI_CAPABLE) {
+ if (np->msi_flags & NV_MSI_CAPABLE) {
ret = pci_enable_msi(np->pci_dev);
if (ret == 0) {
np->msi_flags |= NV_MSI_ENABLED;
- if (request_irq(np->pci_dev->irq, handler, IRQF_SHARED, dev->name, dev) != 0) {
+ ret = request_irq(np->pci_dev->irq, handler, IRQF_SHARED, dev->name, dev);
+ if (ret) {
netdev_info(dev, "request_irq failed %d\n",
ret);
pci_disable_msi(np->pci_dev);
@@ -4025,13 +4035,12 @@
/* enable msi vector 0 */
writel(NVREG_MSI_VECTOR_0_ENABLED, base + NvRegMSIIrqMask);
netdev_info(dev, "MSI enabled\n");
+ return 0;
}
}
- if (ret != 0) {
- if (request_irq(np->pci_dev->irq, handler, IRQF_SHARED, dev->name, dev) != 0)
- goto out_err;
- }
+ if (request_irq(np->pci_dev->irq, handler, IRQF_SHARED, dev->name, dev) != 0)
+ goto out_err;
return 0;
out_free_tx:
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 464e910..73e6683 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -120,10 +120,6 @@
int data);
static void pch_gbe_set_multi(struct net_device *netdev);
-static struct sock_filter ptp_filter[] = {
- PTP_FILTER
-};
-
static int pch_ptp_match(struct sk_buff *skb, u16 uid_hi, u32 uid_lo, u16 seqid)
{
u8 *data = skb->data;
@@ -131,7 +127,7 @@
u16 *hi, *id;
u32 lo;
- if (sk_run_filter(skb, ptp_filter) == PTP_CLASS_NONE)
+ if (ptp_classify_raw(skb) == PTP_CLASS_NONE)
return 0;
offset = ETH_HLEN + IPV4_HLEN(data) + UDP_HLEN;
@@ -2635,11 +2631,6 @@
adapter->ptp_pdev = pci_get_bus_and_slot(adapter->pdev->bus->number,
PCI_DEVFN(12, 4));
- if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter))) {
- dev_err(&pdev->dev, "Bad ptp filter\n");
- ret = -EINVAL;
- goto err_free_netdev;
- }
netdev->netdev_ops = &pch_gbe_netdev_ops;
netdev->watchdog_timeo = PCH_GBE_WATCHDOG_PERIOD;
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 70849de..f09c35d 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -643,8 +643,9 @@
if (adapter->msix_supported) {
netxen_init_msix_entries(adapter, num_msix);
- err = pci_enable_msix(pdev, adapter->msix_entries, num_msix);
- if (err == 0) {
+ err = pci_enable_msix_range(pdev, adapter->msix_entries,
+ num_msix, num_msix);
+ if (err > 0) {
adapter->flags |= NETXEN_NIC_MSIX_ENABLED;
netxen_set_msix_bit(pdev, 1);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index f19f81c..b9039b5 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -38,8 +38,8 @@
#define _QLCNIC_LINUX_MAJOR 5
#define _QLCNIC_LINUX_MINOR 3
-#define _QLCNIC_LINUX_SUBVERSION 55
-#define QLCNIC_LINUX_VERSIONID "5.3.55"
+#define _QLCNIC_LINUX_SUBVERSION 57
+#define QLCNIC_LINUX_VERSIONID "5.3.57"
#define QLCNIC_DRV_IDC_VER 0x01
#define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\
(_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION))
@@ -169,11 +169,20 @@
__le64 addr_buffer2;
- __le16 reference_handle;
+ __le16 encap_descr; /* 15:10 offset of outer L3 header,
+ * 9:6 number of 32bit words in outer L3 header,
+ * 5 offload outer L4 checksum,
+ * 4 offload outer L3 checksum,
+ * 3 Inner L4 type, TCP=0, UDP=1,
+ * 2 Inner L3 type, IPv4=0, IPv6=1,
+ * 1 Outer L3 type,IPv4=0, IPv6=1,
+ * 0 type of encapsulation, GRE=0, VXLAN=1
+ */
__le16 mss;
u8 port_ctxid; /* 7:4 ctxid 3:0 port */
- u8 total_hdr_length; /* LSO only : MAC+IP+TCP Hdr size */
- __le16 conn_id; /* IPSec offoad only */
+ u8 hdr_length; /* LSO only : MAC+IP+TCP Hdr size */
+ u8 outer_hdr_length; /* Encapsulation only */
+ u8 rsvd1;
__le64 addr_buffer3;
__le64 addr_buffer1;
@@ -183,7 +192,9 @@
__le64 addr_buffer4;
u8 eth_addr[ETH_ALEN];
- __le16 vlan_TCI;
+ __le16 vlan_TCI; /* In case of encapsulation,
+ * this is for outer VLAN
+ */
} __attribute__ ((aligned(64)));
@@ -394,7 +405,7 @@
u32 timer_out;
};
-struct qlcnic_dump_template_hdr {
+struct qlcnic_83xx_dump_template_hdr {
u32 type;
u32 offset;
u32 size;
@@ -411,15 +422,42 @@
u32 rsvd[0];
};
+struct qlcnic_82xx_dump_template_hdr {
+ u32 type;
+ u32 offset;
+ u32 size;
+ u32 cap_mask;
+ u32 num_entries;
+ u32 version;
+ u32 timestamp;
+ u32 checksum;
+ u32 drv_cap_mask;
+ u32 sys_info[3];
+ u32 saved_state[16];
+ u32 cap_sizes[8];
+ u32 rsvd[7];
+ u32 capabilities;
+ u32 rsvd1[0];
+};
+
struct qlcnic_fw_dump {
u8 clr; /* flag to indicate if dump is cleared */
bool enable; /* enable/disable dump */
u32 size; /* total size of the dump */
+ u32 cap_mask; /* Current capture mask */
void *data; /* dump data area */
- struct qlcnic_dump_template_hdr *tmpl_hdr;
+ void *tmpl_hdr;
dma_addr_t phys_addr;
void *dma_buffer;
bool use_pex_dma;
+ /* Read only elements which are common between 82xx and 83xx
+ * template header. Update these values immediately after we read
+ * template header from Firmware
+ */
+ u32 tmpl_hdr_size;
+ u32 version;
+ u32 num_entries;
+ u32 offset;
};
/*
@@ -497,6 +535,7 @@
u8 extend_lb_time;
u8 phys_port_id[ETH_ALEN];
u8 lb_mode;
+ u16 vxlan_port;
};
struct qlcnic_adapter_stats {
@@ -511,6 +550,9 @@
u64 txbytes;
u64 lrobytes;
u64 lso_frames;
+ u64 encap_lso_frames;
+ u64 encap_tx_csummed;
+ u64 encap_rx_csummed;
u64 xmit_on;
u64 xmit_off;
u64 skb_alloc_failure;
@@ -872,6 +914,10 @@
#define QLCNIC_FW_CAPABILITY_2_BEACON BIT_7
#define QLCNIC_FW_CAPABILITY_2_PER_PORT_ESWITCH_CFG BIT_9
+#define QLCNIC_83XX_FW_CAPAB_ENCAP_RX_OFFLOAD BIT_0
+#define QLCNIC_83XX_FW_CAPAB_ENCAP_TX_OFFLOAD BIT_1
+#define QLCNIC_83XX_FW_CAPAB_ENCAP_CKO_OFFLOAD BIT_4
+
/* module types */
#define LINKEVENT_MODULE_NOT_PRESENT 1
#define LINKEVENT_MODULE_OPTICAL_UNKNOWN 2
@@ -965,6 +1011,8 @@
#define QLCNIC_APP_CHANGED_FLAGS 0x20000
#define QLCNIC_HAS_PHYS_PORT_ID 0x40000
#define QLCNIC_TSS_RSS 0x80000
+#define QLCNIC_ADD_VXLAN_PORT 0x100000
+#define QLCNIC_DEL_VXLAN_PORT 0x200000
#define QLCNIC_IS_MSI_FAMILY(adapter) \
((adapter)->flags & (QLCNIC_MSI_ENABLED | QLCNIC_MSIX_ENABLED))
@@ -1769,10 +1817,28 @@
struct qlcnic_host_tx_ring *);
void (*disable_tx_intr) (struct qlcnic_adapter *,
struct qlcnic_host_tx_ring *);
+ u32 (*get_saved_state)(void *, u32);
+ void (*set_saved_state)(void *, u32, u32);
+ void (*cache_tmpl_hdr_values)(struct qlcnic_fw_dump *);
+ u32 (*get_cap_size)(void *, int);
+ void (*set_sys_info)(void *, int, u32);
+ void (*store_cap_mask)(void *, u32);
};
extern struct qlcnic_nic_template qlcnic_vf_ops;
+static inline bool qlcnic_encap_tx_offload(struct qlcnic_adapter *adapter)
+{
+ return adapter->ahw->extra_capability[0] &
+ QLCNIC_83XX_FW_CAPAB_ENCAP_TX_OFFLOAD;
+}
+
+static inline bool qlcnic_encap_rx_offload(struct qlcnic_adapter *adapter)
+{
+ return adapter->ahw->extra_capability[0] &
+ QLCNIC_83XX_FW_CAPAB_ENCAP_RX_OFFLOAD;
+}
+
static inline int qlcnic_start_firmware(struct qlcnic_adapter *adapter)
{
return adapter->nic_ops->start_firmware(adapter);
@@ -2007,6 +2073,42 @@
adapter->ahw->hw_ops->read_phys_port_id(adapter);
}
+static inline u32 qlcnic_get_saved_state(struct qlcnic_adapter *adapter,
+ void *t_hdr, u32 index)
+{
+ return adapter->ahw->hw_ops->get_saved_state(t_hdr, index);
+}
+
+static inline void qlcnic_set_saved_state(struct qlcnic_adapter *adapter,
+ void *t_hdr, u32 index, u32 value)
+{
+ adapter->ahw->hw_ops->set_saved_state(t_hdr, index, value);
+}
+
+static inline void qlcnic_cache_tmpl_hdr_values(struct qlcnic_adapter *adapter,
+ struct qlcnic_fw_dump *fw_dump)
+{
+ adapter->ahw->hw_ops->cache_tmpl_hdr_values(fw_dump);
+}
+
+static inline u32 qlcnic_get_cap_size(struct qlcnic_adapter *adapter,
+ void *tmpl_hdr, int index)
+{
+ return adapter->ahw->hw_ops->get_cap_size(tmpl_hdr, index);
+}
+
+static inline void qlcnic_set_sys_info(struct qlcnic_adapter *adapter,
+ void *tmpl_hdr, int idx, u32 value)
+{
+ adapter->ahw->hw_ops->set_sys_info(tmpl_hdr, idx, value);
+}
+
+static inline void qlcnic_store_cap_mask(struct qlcnic_adapter *adapter,
+ void *tmpl_hdr, u32 mask)
+{
+ adapter->ahw->hw_ops->store_cap_mask(tmpl_hdr, mask);
+}
+
static inline void qlcnic_dev_request_reset(struct qlcnic_adapter *adapter,
u32 key)
{
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 4146664..b7cffb4 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -77,7 +77,7 @@
{QLCNIC_CMD_GET_PORT_CONFIG, 2, 2},
{QLCNIC_CMD_GET_LINK_STATUS, 2, 4},
{QLCNIC_CMD_IDC_ACK, 5, 1},
- {QLCNIC_CMD_INIT_NIC_FUNC, 2, 1},
+ {QLCNIC_CMD_INIT_NIC_FUNC, 3, 1},
{QLCNIC_CMD_STOP_NIC_FUNC, 2, 1},
{QLCNIC_CMD_SET_LED_CONFIG, 5, 1},
{QLCNIC_CMD_GET_LED_CONFIG, 1, 5},
@@ -87,6 +87,7 @@
{QLCNIC_CMD_BC_EVENT_SETUP, 2, 1},
{QLCNIC_CMD_DCB_QUERY_CAP, 1, 2},
{QLCNIC_CMD_DCB_QUERY_PARAM, 1, 50},
+ {QLCNIC_CMD_SET_INGRESS_ENCAP, 2, 1},
};
const u32 qlcnic_83xx_ext_reg_tbl[] = {
@@ -203,7 +204,12 @@
.disable_sds_intr = qlcnic_83xx_disable_sds_intr,
.enable_tx_intr = qlcnic_83xx_enable_tx_intr,
.disable_tx_intr = qlcnic_83xx_disable_tx_intr,
-
+ .get_saved_state = qlcnic_83xx_get_saved_state,
+ .set_saved_state = qlcnic_83xx_set_saved_state,
+ .cache_tmpl_hdr_values = qlcnic_83xx_cache_tmpl_hdr_values,
+ .get_cap_size = qlcnic_83xx_get_cap_size,
+ .set_sys_info = qlcnic_83xx_set_sys_info,
+ .store_cap_mask = qlcnic_83xx_store_cap_mask,
};
static struct qlcnic_nic_template qlcnic_83xx_ops = {
@@ -340,6 +346,7 @@
if (qlcnic_sriov_vf_check(adapter))
return -EINVAL;
num_msix = 1;
+ adapter->drv_sds_rings = QLCNIC_SINGLE_RING;
adapter->drv_tx_rings = QLCNIC_SINGLE_RING;
}
}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
index f92485c..88d809c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
@@ -308,6 +308,8 @@
#define QLC_83XX_IDC_FLASH_PARAM_ADDR 0x3e8020
struct qlcnic_adapter;
+struct qlcnic_fw_dump;
+
struct qlc_83xx_idc {
int (*state_entry) (struct qlcnic_adapter *);
u64 sec_counter;
@@ -526,8 +528,9 @@
};
/* Initialize/Stop NIC command bit definitions */
-#define QLC_REGISTER_DCB_AEN BIT_1
#define QLC_REGISTER_LB_IDC BIT_0
+#define QLC_REGISTER_DCB_AEN BIT_1
+#define QLC_83XX_MULTI_TENANCY_INFO BIT_29
#define QLC_INIT_FW_RESOURCES BIT_31
/* 83xx funcitons */
@@ -650,4 +653,10 @@
void qlcnic_83xx_aer_stop_poll_work(struct qlcnic_adapter *);
int qlcnic_83xx_aer_reset(struct qlcnic_adapter *);
void qlcnic_83xx_aer_start_poll_work(struct qlcnic_adapter *);
+u32 qlcnic_83xx_get_saved_state(void *, u32);
+void qlcnic_83xx_set_saved_state(void *, u32, u32);
+void qlcnic_83xx_cache_tmpl_hdr_values(struct qlcnic_fw_dump *);
+u32 qlcnic_83xx_get_cap_size(void *, int);
+void qlcnic_83xx_set_sys_info(void *, int, u32);
+void qlcnic_83xx_store_cap_mask(void *, u32);
#endif
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index 90a2dda..2d91975 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -1020,10 +1020,97 @@
return 0;
}
+#define QLC_83XX_ENCAP_TYPE_VXLAN BIT_1
+#define QLC_83XX_MATCH_ENCAP_ID BIT_2
+#define QLC_83XX_SET_VXLAN_UDP_DPORT BIT_3
+#define QLC_83XX_VXLAN_UDP_DPORT(PORT) ((PORT & 0xffff) << 16)
+
+#define QLCNIC_ENABLE_INGRESS_ENCAP_PARSING 1
+#define QLCNIC_DISABLE_INGRESS_ENCAP_PARSING 0
+
+static int qlcnic_set_vxlan_port(struct qlcnic_adapter *adapter)
+{
+ u16 port = adapter->ahw->vxlan_port;
+ struct qlcnic_cmd_args cmd;
+ int ret = 0;
+
+ memset(&cmd, 0, sizeof(cmd));
+
+ ret = qlcnic_alloc_mbx_args(&cmd, adapter,
+ QLCNIC_CMD_INIT_NIC_FUNC);
+ if (ret)
+ return ret;
+
+ cmd.req.arg[1] = QLC_83XX_MULTI_TENANCY_INFO;
+ cmd.req.arg[2] = QLC_83XX_ENCAP_TYPE_VXLAN |
+ QLC_83XX_SET_VXLAN_UDP_DPORT |
+ QLC_83XX_VXLAN_UDP_DPORT(port);
+
+ ret = qlcnic_issue_cmd(adapter, &cmd);
+ if (ret)
+ netdev_err(adapter->netdev,
+ "Failed to set VXLAN port %d in adapter\n",
+ port);
+
+ qlcnic_free_mbx_args(&cmd);
+
+ return ret;
+}
+
+static int qlcnic_set_vxlan_parsing(struct qlcnic_adapter *adapter,
+ bool state)
+{
+ u16 vxlan_port = adapter->ahw->vxlan_port;
+ struct qlcnic_cmd_args cmd;
+ int ret = 0;
+
+ memset(&cmd, 0, sizeof(cmd));
+
+ ret = qlcnic_alloc_mbx_args(&cmd, adapter,
+ QLCNIC_CMD_SET_INGRESS_ENCAP);
+ if (ret)
+ return ret;
+
+ cmd.req.arg[1] = state ? QLCNIC_ENABLE_INGRESS_ENCAP_PARSING :
+ QLCNIC_DISABLE_INGRESS_ENCAP_PARSING;
+
+ ret = qlcnic_issue_cmd(adapter, &cmd);
+ if (ret)
+ netdev_err(adapter->netdev,
+ "Failed to %s VXLAN parsing for port %d\n",
+ state ? "enable" : "disable", vxlan_port);
+ else
+ netdev_info(adapter->netdev,
+ "%s VXLAN parsing for port %d\n",
+ state ? "Enabled" : "Disabled", vxlan_port);
+
+ qlcnic_free_mbx_args(&cmd);
+
+ return ret;
+}
+
static void qlcnic_83xx_periodic_tasks(struct qlcnic_adapter *adapter)
{
+ struct qlcnic_hardware_context *ahw = adapter->ahw;
+
if (adapter->fhash.fnum)
qlcnic_prune_lb_filters(adapter);
+
+ if (adapter->flags & QLCNIC_ADD_VXLAN_PORT) {
+ if (qlcnic_set_vxlan_port(adapter))
+ return;
+
+ if (qlcnic_set_vxlan_parsing(adapter, true))
+ return;
+
+ adapter->flags &= ~QLCNIC_ADD_VXLAN_PORT;
+ } else if (adapter->flags & QLCNIC_DEL_VXLAN_PORT) {
+ if (qlcnic_set_vxlan_parsing(adapter, false))
+ return;
+
+ ahw->vxlan_port = 0;
+ adapter->flags &= ~QLCNIC_DEL_VXLAN_PORT;
+ }
}
/**
@@ -1301,7 +1388,7 @@
addr = (u64)dest;
ret = qlcnic_83xx_ms_mem_write128(adapter, addr,
- (u32 *)p_cache, size / 16);
+ p_cache, size / 16);
if (ret) {
dev_err(&adapter->pdev->dev, "MS memory write failed\n");
release_firmware(fw);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c
index 77f1bce..7d4f549 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c
@@ -807,7 +807,7 @@
!type->tc_param_valid)
return;
- if (tc < 0 || (tc > QLC_DCB_MAX_TC))
+ if (tc < 0 || (tc >= QLC_DCB_MAX_TC))
return;
tc_cfg = &type->tc_cfg[tc];
@@ -843,7 +843,7 @@
!type->tc_param_valid)
return;
- if (pgid < 0 || pgid > QLC_DCB_MAX_PG)
+ if (pgid < 0 || pgid >= QLC_DCB_MAX_PG)
return;
pgcfg = &type->pg_cfg[pgid];
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index acee1a5..5bacf52 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -47,6 +47,12 @@
{"lro_pkts", QLC_SIZEOF(stats.lro_pkts), QLC_OFF(stats.lro_pkts)},
{"lrobytes", QLC_SIZEOF(stats.lrobytes), QLC_OFF(stats.lrobytes)},
{"lso_frames", QLC_SIZEOF(stats.lso_frames), QLC_OFF(stats.lso_frames)},
+ {"encap_lso_frames", QLC_SIZEOF(stats.encap_lso_frames),
+ QLC_OFF(stats.encap_lso_frames)},
+ {"encap_tx_csummed", QLC_SIZEOF(stats.encap_tx_csummed),
+ QLC_OFF(stats.encap_tx_csummed)},
+ {"encap_rx_csummed", QLC_SIZEOF(stats.encap_rx_csummed),
+ QLC_OFF(stats.encap_rx_csummed)},
{"skb_alloc_failure", QLC_SIZEOF(stats.skb_alloc_failure),
QLC_OFF(stats.skb_alloc_failure)},
{"mac_filter_limit_overrun", QLC_SIZEOF(stats.mac_filter_limit_overrun),
@@ -1639,14 +1645,14 @@
}
if (fw_dump->clr)
- dump->len = fw_dump->tmpl_hdr->size + fw_dump->size;
+ dump->len = fw_dump->tmpl_hdr_size + fw_dump->size;
else
dump->len = 0;
if (!qlcnic_check_fw_dump_state(adapter))
dump->flag = ETH_FW_DUMP_DISABLE;
else
- dump->flag = fw_dump->tmpl_hdr->drv_cap_mask;
+ dump->flag = fw_dump->cap_mask;
dump->version = adapter->fw_version;
return 0;
@@ -1671,9 +1677,10 @@
netdev_info(netdev, "Dump not available\n");
return -EINVAL;
}
+
/* Copy template header first */
- copy_sz = fw_dump->tmpl_hdr->size;
- hdr_ptr = (u32 *) fw_dump->tmpl_hdr;
+ copy_sz = fw_dump->tmpl_hdr_size;
+ hdr_ptr = (u32 *)fw_dump->tmpl_hdr;
data = buffer;
for (i = 0; i < copy_sz/sizeof(u32); i++)
*data++ = cpu_to_le32(*hdr_ptr++);
@@ -1681,7 +1688,7 @@
/* Copy captured dump data */
memcpy(buffer + copy_sz, fw_dump->data, fw_dump->size);
dump->len = copy_sz + fw_dump->size;
- dump->flag = fw_dump->tmpl_hdr->drv_cap_mask;
+ dump->flag = fw_dump->cap_mask;
/* Free dump area once data has been captured */
vfree(fw_dump->data);
@@ -1703,7 +1710,11 @@
return -EOPNOTSUPP;
}
- fw_dump->tmpl_hdr->drv_cap_mask = mask;
+ fw_dump->cap_mask = mask;
+
+ /* Store new capture mask in template header as well*/
+ qlcnic_store_cap_mask(adapter, fw_dump->tmpl_hdr, mask);
+
netdev_info(netdev, "Driver mask changed to: 0x%x\n", mask);
return 0;
}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
index 03d18a0..9f3adf4 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
@@ -317,9 +317,7 @@
int
qlcnic_pcie_sem_lock(struct qlcnic_adapter *adapter, int sem, u32 id_reg)
{
- int timeout = 0;
- int err = 0;
- u32 done = 0;
+ int timeout = 0, err = 0, done = 0;
while (!done) {
done = QLCRD32(adapter, QLCNIC_PCIE_REG(PCIE_SEM_LOCK(sem)),
@@ -327,10 +325,20 @@
if (done == 1)
break;
if (++timeout >= QLCNIC_PCIE_SEM_TIMEOUT) {
- dev_err(&adapter->pdev->dev,
- "Failed to acquire sem=%d lock; holdby=%d\n",
- sem,
- id_reg ? QLCRD32(adapter, id_reg, &err) : -1);
+ if (id_reg) {
+ done = QLCRD32(adapter, id_reg, &err);
+ if (done != -1)
+ dev_err(&adapter->pdev->dev,
+ "Failed to acquire sem=%d lock held by=%d\n",
+ sem, done);
+ else
+ dev_err(&adapter->pdev->dev,
+ "Failed to acquire sem=%d lock",
+ sem);
+ } else {
+ dev_err(&adapter->pdev->dev,
+ "Failed to acquire sem=%d lock", sem);
+ }
return -EIO;
}
msleep(1);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
index 63d7561..cbe2399 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
@@ -98,6 +98,7 @@
#define QLCNIC_CMD_GET_LINK_EVENT 0x48
#define QLCNIC_CMD_CONFIGURE_MAC_RX_MODE 0x49
#define QLCNIC_CMD_CONFIGURE_HW_LRO 0x4A
+#define QLCNIC_CMD_SET_INGRESS_ENCAP 0x4E
#define QLCNIC_CMD_INIT_NIC_FUNC 0x60
#define QLCNIC_CMD_STOP_NIC_FUNC 0x61
#define QLCNIC_CMD_IDC_ACK 0x63
@@ -161,6 +162,7 @@
struct qlcnic_host_tx_ring;
struct qlcnic_hardware_context;
struct qlcnic_adapter;
+struct qlcnic_fw_dump;
int qlcnic_82xx_hw_read_wx_2M(struct qlcnic_adapter *adapter, ulong, int *);
int qlcnic_82xx_hw_write_wx_2M(struct qlcnic_adapter *, ulong, u32);
@@ -213,4 +215,11 @@
int qlcnic_82xx_resume(struct qlcnic_adapter *);
void qlcnic_clr_all_drv_state(struct qlcnic_adapter *adapter, u8 failed);
void qlcnic_fw_poll_work(struct work_struct *work);
+
+u32 qlcnic_82xx_get_saved_state(void *, u32);
+void qlcnic_82xx_set_saved_state(void *, u32, u32);
+void qlcnic_82xx_cache_tmpl_hdr_values(struct qlcnic_fw_dump *);
+u32 qlcnic_82xx_get_cap_size(void *, int);
+void qlcnic_82xx_set_sys_info(void *, int, u32);
+void qlcnic_82xx_store_cap_mask(void *, u32);
#endif /* __QLCNIC_HW_H_ */
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 54ebf30..173b3d1 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -13,16 +13,19 @@
#include "qlcnic.h"
-#define TX_ETHER_PKT 0x01
-#define TX_TCP_PKT 0x02
-#define TX_UDP_PKT 0x03
-#define TX_IP_PKT 0x04
-#define TX_TCP_LSO 0x05
-#define TX_TCP_LSO6 0x06
-#define TX_TCPV6_PKT 0x0b
-#define TX_UDPV6_PKT 0x0c
-#define FLAGS_VLAN_TAGGED 0x10
-#define FLAGS_VLAN_OOB 0x40
+#define QLCNIC_TX_ETHER_PKT 0x01
+#define QLCNIC_TX_TCP_PKT 0x02
+#define QLCNIC_TX_UDP_PKT 0x03
+#define QLCNIC_TX_IP_PKT 0x04
+#define QLCNIC_TX_TCP_LSO 0x05
+#define QLCNIC_TX_TCP_LSO6 0x06
+#define QLCNIC_TX_ENCAP_PKT 0x07
+#define QLCNIC_TX_ENCAP_LSO 0x08
+#define QLCNIC_TX_TCPV6_PKT 0x0b
+#define QLCNIC_TX_UDPV6_PKT 0x0c
+
+#define QLCNIC_FLAGS_VLAN_TAGGED 0x10
+#define QLCNIC_FLAGS_VLAN_OOB 0x40
#define qlcnic_set_tx_vlan_tci(cmd_desc, v) \
(cmd_desc)->vlan_TCI = cpu_to_le16(v);
@@ -364,6 +367,101 @@
spin_unlock(&adapter->mac_learn_lock);
}
+#define QLCNIC_ENCAP_VXLAN_PKT BIT_0
+#define QLCNIC_ENCAP_OUTER_L3_IP6 BIT_1
+#define QLCNIC_ENCAP_INNER_L3_IP6 BIT_2
+#define QLCNIC_ENCAP_INNER_L4_UDP BIT_3
+#define QLCNIC_ENCAP_DO_L3_CSUM BIT_4
+#define QLCNIC_ENCAP_DO_L4_CSUM BIT_5
+
+static int qlcnic_tx_encap_pkt(struct qlcnic_adapter *adapter,
+ struct cmd_desc_type0 *first_desc,
+ struct sk_buff *skb,
+ struct qlcnic_host_tx_ring *tx_ring)
+{
+ u8 opcode = 0, inner_hdr_len = 0, outer_hdr_len = 0, total_hdr_len = 0;
+ int copied, copy_len, descr_size;
+ u32 producer = tx_ring->producer;
+ struct cmd_desc_type0 *hwdesc;
+ u16 flags = 0, encap_descr = 0;
+
+ opcode = QLCNIC_TX_ETHER_PKT;
+ encap_descr = QLCNIC_ENCAP_VXLAN_PKT;
+
+ if (skb_is_gso(skb)) {
+ inner_hdr_len = skb_inner_transport_header(skb) +
+ inner_tcp_hdrlen(skb) -
+ skb_inner_mac_header(skb);
+
+ /* VXLAN header size = 8 */
+ outer_hdr_len = skb_transport_offset(skb) + 8 +
+ sizeof(struct udphdr);
+ first_desc->outer_hdr_length = outer_hdr_len;
+ total_hdr_len = inner_hdr_len + outer_hdr_len;
+ encap_descr |= QLCNIC_ENCAP_DO_L3_CSUM |
+ QLCNIC_ENCAP_DO_L4_CSUM;
+ first_desc->mss = cpu_to_le16(skb_shinfo(skb)->gso_size);
+ first_desc->hdr_length = inner_hdr_len;
+
+ /* Copy inner and outer headers in Tx descriptor(s)
+ * If total_hdr_len > cmd_desc_type0, use multiple
+ * descriptors
+ */
+ copied = 0;
+ descr_size = (int)sizeof(struct cmd_desc_type0);
+ while (copied < total_hdr_len) {
+ copy_len = min(descr_size, (total_hdr_len - copied));
+ hwdesc = &tx_ring->desc_head[producer];
+ tx_ring->cmd_buf_arr[producer].skb = NULL;
+ skb_copy_from_linear_data_offset(skb, copied,
+ (char *)hwdesc,
+ copy_len);
+ copied += copy_len;
+ producer = get_next_index(producer, tx_ring->num_desc);
+ }
+
+ tx_ring->producer = producer;
+
+ /* Make sure updated tx_ring->producer is visible
+ * for qlcnic_tx_avail()
+ */
+ smp_mb();
+ adapter->stats.encap_lso_frames++;
+
+ opcode = QLCNIC_TX_ENCAP_LSO;
+ } else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ if (inner_ip_hdr(skb)->version == 6) {
+ if (inner_ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)
+ encap_descr |= QLCNIC_ENCAP_INNER_L4_UDP;
+ } else {
+ if (inner_ip_hdr(skb)->protocol == IPPROTO_UDP)
+ encap_descr |= QLCNIC_ENCAP_INNER_L4_UDP;
+ }
+
+ adapter->stats.encap_tx_csummed++;
+ opcode = QLCNIC_TX_ENCAP_PKT;
+ }
+
+ /* Prepare first 16 bits of byte offset 16 of Tx descriptor */
+ if (ip_hdr(skb)->version == 6)
+ encap_descr |= QLCNIC_ENCAP_OUTER_L3_IP6;
+
+ /* outer IP header's size in 32bit words size*/
+ encap_descr |= (skb_network_header_len(skb) >> 2) << 6;
+
+ /* outer IP header offset */
+ encap_descr |= skb_network_offset(skb) << 10;
+ first_desc->encap_descr = cpu_to_le16(encap_descr);
+
+ first_desc->tcp_hdr_offset = skb_inner_transport_header(skb) -
+ skb->data;
+ first_desc->ip_hdr_offset = skb_inner_network_offset(skb);
+
+ qlcnic_set_tx_flags_opcode(first_desc, flags, opcode);
+
+ return 0;
+}
+
static int qlcnic_tx_pkt(struct qlcnic_adapter *adapter,
struct cmd_desc_type0 *first_desc, struct sk_buff *skb,
struct qlcnic_host_tx_ring *tx_ring)
@@ -378,11 +476,11 @@
if (protocol == ETH_P_8021Q) {
vh = (struct vlan_ethhdr *)skb->data;
- flags = FLAGS_VLAN_TAGGED;
+ flags = QLCNIC_FLAGS_VLAN_TAGGED;
vlan_tci = ntohs(vh->h_vlan_TCI);
protocol = ntohs(vh->h_vlan_encapsulated_proto);
} else if (vlan_tx_tag_present(skb)) {
- flags = FLAGS_VLAN_OOB;
+ flags = QLCNIC_FLAGS_VLAN_OOB;
vlan_tci = vlan_tx_tag_get(skb);
}
if (unlikely(adapter->tx_pvid)) {
@@ -391,7 +489,7 @@
if (vlan_tci && (adapter->flags & QLCNIC_TAGGING_ENABLED))
goto set_flags;
- flags = FLAGS_VLAN_OOB;
+ flags = QLCNIC_FLAGS_VLAN_OOB;
vlan_tci = adapter->tx_pvid;
}
set_flags:
@@ -402,25 +500,26 @@
flags |= BIT_0;
memcpy(&first_desc->eth_addr, skb->data, ETH_ALEN);
}
- opcode = TX_ETHER_PKT;
+ opcode = QLCNIC_TX_ETHER_PKT;
if (skb_is_gso(skb)) {
hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
first_desc->mss = cpu_to_le16(skb_shinfo(skb)->gso_size);
- first_desc->total_hdr_length = hdr_len;
- opcode = (protocol == ETH_P_IPV6) ? TX_TCP_LSO6 : TX_TCP_LSO;
+ first_desc->hdr_length = hdr_len;
+ opcode = (protocol == ETH_P_IPV6) ? QLCNIC_TX_TCP_LSO6 :
+ QLCNIC_TX_TCP_LSO;
/* For LSO, we need to copy the MAC/IP/TCP headers into
* the descriptor ring */
copied = 0;
offset = 2;
- if (flags & FLAGS_VLAN_OOB) {
- first_desc->total_hdr_length += VLAN_HLEN;
+ if (flags & QLCNIC_FLAGS_VLAN_OOB) {
+ first_desc->hdr_length += VLAN_HLEN;
first_desc->tcp_hdr_offset = VLAN_HLEN;
first_desc->ip_hdr_offset = VLAN_HLEN;
/* Only in case of TSO on vlan device */
- flags |= FLAGS_VLAN_TAGGED;
+ flags |= QLCNIC_FLAGS_VLAN_TAGGED;
/* Create a TSO vlan header template for firmware */
hwdesc = &tx_ring->desc_head[producer];
@@ -464,16 +563,16 @@
l4proto = ip_hdr(skb)->protocol;
if (l4proto == IPPROTO_TCP)
- opcode = TX_TCP_PKT;
+ opcode = QLCNIC_TX_TCP_PKT;
else if (l4proto == IPPROTO_UDP)
- opcode = TX_UDP_PKT;
+ opcode = QLCNIC_TX_UDP_PKT;
} else if (protocol == ETH_P_IPV6) {
l4proto = ipv6_hdr(skb)->nexthdr;
if (l4proto == IPPROTO_TCP)
- opcode = TX_TCPV6_PKT;
+ opcode = QLCNIC_TX_TCPV6_PKT;
else if (l4proto == IPPROTO_UDP)
- opcode = TX_UDPV6_PKT;
+ opcode = QLCNIC_TX_UDPV6_PKT;
}
}
first_desc->tcp_hdr_offset += skb_transport_offset(skb);
@@ -563,6 +662,8 @@
struct ethhdr *phdr;
int i, k, frag_count, delta = 0;
u32 producer, num_txd;
+ u16 protocol;
+ bool l4_is_udp = false;
if (!test_bit(__QLCNIC_DEV_UP, &adapter->state)) {
netif_tx_stop_all_queues(netdev);
@@ -653,8 +754,23 @@
tx_ring->producer = get_next_index(producer, num_txd);
smp_mb();
- if (unlikely(qlcnic_tx_pkt(adapter, first_desc, skb, tx_ring)))
- goto unwind_buff;
+ protocol = ntohs(skb->protocol);
+ if (protocol == ETH_P_IP)
+ l4_is_udp = ip_hdr(skb)->protocol == IPPROTO_UDP;
+ else if (protocol == ETH_P_IPV6)
+ l4_is_udp = ipv6_hdr(skb)->nexthdr == IPPROTO_UDP;
+
+ /* Check if it is a VXLAN packet */
+ if (!skb->encapsulation || !l4_is_udp ||
+ !qlcnic_encap_tx_offload(adapter)) {
+ if (unlikely(qlcnic_tx_pkt(adapter, first_desc, skb,
+ tx_ring)))
+ goto unwind_buff;
+ } else {
+ if (unlikely(qlcnic_tx_encap_pkt(adapter, first_desc,
+ skb, tx_ring)))
+ goto unwind_buff;
+ }
if (adapter->drv_mac_learn)
qlcnic_send_filter(adapter, first_desc, skb);
@@ -1587,6 +1703,13 @@
return (sts_data & QLC_83XX_NORMAL_LB_PKT) ? 1 : 0;
}
+#define QLCNIC_ENCAP_LENGTH_MASK 0x7f
+
+static inline u8 qlcnic_encap_length(u64 sts_data)
+{
+ return sts_data & QLCNIC_ENCAP_LENGTH_MASK;
+}
+
static struct qlcnic_rx_buffer *
qlcnic_83xx_process_rcv(struct qlcnic_adapter *adapter,
struct qlcnic_host_sds_ring *sds_ring,
@@ -1637,6 +1760,12 @@
skb->protocol = eth_type_trans(skb, netdev);
+ if (qlcnic_encap_length(sts_data[1]) &&
+ skb->ip_summed == CHECKSUM_UNNECESSARY) {
+ skb->encapsulation = 1;
+ adapter->stats.encap_rx_csummed++;
+ }
+
if (vid != 0xffff)
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index ba78c74..79be451 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -21,6 +21,7 @@
#include <linux/aer.h>
#include <linux/log2.h>
#include <linux/pci.h>
+#include <net/vxlan.h>
MODULE_DESCRIPTION("QLogic 1/10 GbE Converged/Intelligent Ethernet Driver");
MODULE_LICENSE("GPL");
@@ -90,7 +91,6 @@
static void qlcnic_82xx_set_mac_filter_count(struct qlcnic_adapter *);
static pci_ers_result_t qlcnic_82xx_io_error_detected(struct pci_dev *,
pci_channel_state_t);
-
static u32 qlcnic_vlan_tx_check(struct qlcnic_adapter *adapter)
{
struct qlcnic_hardware_context *ahw = adapter->ahw;
@@ -462,6 +462,35 @@
return 0;
}
+static void qlcnic_add_vxlan_port(struct net_device *netdev,
+ sa_family_t sa_family, __be16 port)
+{
+ struct qlcnic_adapter *adapter = netdev_priv(netdev);
+ struct qlcnic_hardware_context *ahw = adapter->ahw;
+
+ /* Adapter supports only one VXLAN port. Use very first port
+ * for enabling offload
+ */
+ if (!qlcnic_encap_rx_offload(adapter) || ahw->vxlan_port)
+ return;
+
+ ahw->vxlan_port = ntohs(port);
+ adapter->flags |= QLCNIC_ADD_VXLAN_PORT;
+}
+
+static void qlcnic_del_vxlan_port(struct net_device *netdev,
+ sa_family_t sa_family, __be16 port)
+{
+ struct qlcnic_adapter *adapter = netdev_priv(netdev);
+ struct qlcnic_hardware_context *ahw = adapter->ahw;
+
+ if (!qlcnic_encap_rx_offload(adapter) || !ahw->vxlan_port ||
+ (ahw->vxlan_port != ntohs(port)))
+ return;
+
+ adapter->flags |= QLCNIC_DEL_VXLAN_PORT;
+}
+
static const struct net_device_ops qlcnic_netdev_ops = {
.ndo_open = qlcnic_open,
.ndo_stop = qlcnic_close,
@@ -480,6 +509,8 @@
.ndo_fdb_del = qlcnic_fdb_del,
.ndo_fdb_dump = qlcnic_fdb_dump,
.ndo_get_phys_port_id = qlcnic_get_phys_port_id,
+ .ndo_add_vxlan_port = qlcnic_add_vxlan_port,
+ .ndo_del_vxlan_port = qlcnic_del_vxlan_port,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = qlcnic_poll_controller,
#endif
@@ -561,6 +592,12 @@
.disable_sds_intr = qlcnic_82xx_disable_sds_intr,
.enable_tx_intr = qlcnic_82xx_enable_tx_intr,
.disable_tx_intr = qlcnic_82xx_disable_tx_intr,
+ .get_saved_state = qlcnic_82xx_get_saved_state,
+ .set_saved_state = qlcnic_82xx_set_saved_state,
+ .cache_tmpl_hdr_values = qlcnic_82xx_cache_tmpl_hdr_values,
+ .get_cap_size = qlcnic_82xx_get_cap_size,
+ .set_sys_info = qlcnic_82xx_set_sys_info,
+ .store_cap_mask = qlcnic_82xx_store_cap_mask,
};
static int qlcnic_check_multi_tx_capability(struct qlcnic_adapter *adapter)
@@ -684,7 +721,7 @@
int qlcnic_enable_msix(struct qlcnic_adapter *adapter, u32 num_msix)
{
struct pci_dev *pdev = adapter->pdev;
- int err = -1, vector;
+ int err, vector;
if (!adapter->msix_entries) {
adapter->msix_entries = kcalloc(num_msix,
@@ -701,13 +738,17 @@
for (vector = 0; vector < num_msix; vector++)
adapter->msix_entries[vector].entry = vector;
- err = pci_enable_msix(pdev, adapter->msix_entries, num_msix);
- if (err == 0) {
+ err = pci_enable_msix_range(pdev,
+ adapter->msix_entries, 1, num_msix);
+
+ if (err == num_msix) {
adapter->flags |= QLCNIC_MSIX_ENABLED;
adapter->ahw->num_msix = num_msix;
dev_info(&pdev->dev, "using msi-x interrupts\n");
- return err;
+ return 0;
} else if (err > 0) {
+ pci_disable_msix(pdev);
+
dev_info(&pdev->dev,
"Unable to allocate %d MSI-X vectors, Available vectors %d\n",
num_msix, err);
@@ -715,12 +756,12 @@
if (qlcnic_82xx_check(adapter)) {
num_msix = rounddown_pow_of_two(err);
if (err < QLCNIC_82XX_MINIMUM_VECTOR)
- return -EIO;
+ return -ENOSPC;
} else {
num_msix = rounddown_pow_of_two(err - 1);
num_msix += 1;
if (err < QLCNIC_83XX_MINIMUM_VECTOR)
- return -EIO;
+ return -ENOSPC;
}
if (qlcnic_82xx_check(adapter) &&
@@ -747,7 +788,7 @@
}
}
- return err;
+ return -EIO;
}
static int qlcnic_82xx_calculate_msix_vector(struct qlcnic_adapter *adapter)
@@ -816,9 +857,10 @@
if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) {
qlcnic_disable_multi_tx(adapter);
+ adapter->drv_sds_rings = QLCNIC_SINGLE_RING;
err = qlcnic_enable_msi_legacy(adapter);
- if (!err)
+ if (err)
return err;
}
}
@@ -1933,6 +1975,9 @@
qlcnic_create_sysfs_entries(adapter);
+ if (qlcnic_encap_rx_offload(adapter))
+ vxlan_get_rx_port(netdev);
+
adapter->is_up = QLCNIC_ADAPTER_UP_MAGIC;
return 0;
@@ -2195,6 +2240,19 @@
if (adapter->ahw->capabilities & QLCNIC_FW_CAPABILITY_HW_LRO)
netdev->features |= NETIF_F_LRO;
+ if (qlcnic_encap_tx_offload(adapter)) {
+ netdev->features |= NETIF_F_GSO_UDP_TUNNEL;
+
+ /* encapsulation Tx offload supported by Adapter */
+ netdev->hw_enc_features = NETIF_F_IP_CSUM |
+ NETIF_F_GSO_UDP_TUNNEL |
+ NETIF_F_TSO |
+ NETIF_F_TSO6;
+ }
+
+ if (qlcnic_encap_rx_offload(adapter))
+ netdev->hw_enc_features |= NETIF_F_RXCSUM;
+
netdev->hw_features = netdev->features;
netdev->priv_flags |= IFF_UNICAST_FLT;
netdev->irq = adapter->msix_entries[0].vector;
@@ -2441,8 +2499,8 @@
if (err) {
switch (err) {
case -ENOTRECOVERABLE:
- dev_err(&pdev->dev, "Adapter initialization failed due to a faulty hardware. Please reboot\n");
- dev_err(&pdev->dev, "If reboot doesn't help, please replace the adapter with new one and return the faulty adapter for repair\n");
+ dev_err(&pdev->dev, "Adapter initialization failed due to a faulty hardware\n");
+ dev_err(&pdev->dev, "Please replace the adapter with new one and return the faulty adapter for repair\n");
goto err_out_free_hw;
case -ENOMEM:
dev_err(&pdev->dev, "Adapter initialization failed. Please reboot\n");
@@ -3863,7 +3921,7 @@
strcpy(buf, "Tx");
}
- if (!qlcnic_use_msi_x && !qlcnic_use_msi) {
+ if (!QLCNIC_IS_MSI_FAMILY(adapter)) {
netdev_err(netdev, "No RSS/TSS support in INT-x mode\n");
return -EINVAL;
}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
index 7763962..37b979b 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
@@ -211,6 +211,107 @@
QLCNIC_DUMP_RDEND = 255
};
+inline u32 qlcnic_82xx_get_saved_state(void *t_hdr, u32 index)
+{
+ struct qlcnic_82xx_dump_template_hdr *hdr = t_hdr;
+
+ return hdr->saved_state[index];
+}
+
+inline void qlcnic_82xx_set_saved_state(void *t_hdr, u32 index,
+ u32 value)
+{
+ struct qlcnic_82xx_dump_template_hdr *hdr = t_hdr;
+
+ hdr->saved_state[index] = value;
+}
+
+void qlcnic_82xx_cache_tmpl_hdr_values(struct qlcnic_fw_dump *fw_dump)
+{
+ struct qlcnic_82xx_dump_template_hdr *hdr;
+
+ hdr = fw_dump->tmpl_hdr;
+ fw_dump->tmpl_hdr_size = hdr->size;
+ fw_dump->version = hdr->version;
+ fw_dump->num_entries = hdr->num_entries;
+ fw_dump->offset = hdr->offset;
+
+ hdr->drv_cap_mask = hdr->cap_mask;
+ fw_dump->cap_mask = hdr->cap_mask;
+}
+
+inline u32 qlcnic_82xx_get_cap_size(void *t_hdr, int index)
+{
+ struct qlcnic_82xx_dump_template_hdr *hdr = t_hdr;
+
+ return hdr->cap_sizes[index];
+}
+
+void qlcnic_82xx_set_sys_info(void *t_hdr, int idx, u32 value)
+{
+ struct qlcnic_82xx_dump_template_hdr *hdr = t_hdr;
+
+ hdr->sys_info[idx] = value;
+}
+
+void qlcnic_82xx_store_cap_mask(void *tmpl_hdr, u32 mask)
+{
+ struct qlcnic_82xx_dump_template_hdr *hdr = tmpl_hdr;
+
+ hdr->drv_cap_mask = mask;
+}
+
+inline u32 qlcnic_83xx_get_saved_state(void *t_hdr, u32 index)
+{
+ struct qlcnic_83xx_dump_template_hdr *hdr = t_hdr;
+
+ return hdr->saved_state[index];
+}
+
+inline void qlcnic_83xx_set_saved_state(void *t_hdr, u32 index,
+ u32 value)
+{
+ struct qlcnic_83xx_dump_template_hdr *hdr = t_hdr;
+
+ hdr->saved_state[index] = value;
+}
+
+void qlcnic_83xx_cache_tmpl_hdr_values(struct qlcnic_fw_dump *fw_dump)
+{
+ struct qlcnic_83xx_dump_template_hdr *hdr;
+
+ hdr = fw_dump->tmpl_hdr;
+ fw_dump->tmpl_hdr_size = hdr->size;
+ fw_dump->version = hdr->version;
+ fw_dump->num_entries = hdr->num_entries;
+ fw_dump->offset = hdr->offset;
+
+ hdr->drv_cap_mask = hdr->cap_mask;
+ fw_dump->cap_mask = hdr->cap_mask;
+}
+
+inline u32 qlcnic_83xx_get_cap_size(void *t_hdr, int index)
+{
+ struct qlcnic_83xx_dump_template_hdr *hdr = t_hdr;
+
+ return hdr->cap_sizes[index];
+}
+
+void qlcnic_83xx_set_sys_info(void *t_hdr, int idx, u32 value)
+{
+ struct qlcnic_83xx_dump_template_hdr *hdr = t_hdr;
+
+ hdr->sys_info[idx] = value;
+}
+
+void qlcnic_83xx_store_cap_mask(void *tmpl_hdr, u32 mask)
+{
+ struct qlcnic_83xx_dump_template_hdr *hdr;
+
+ hdr = tmpl_hdr;
+ hdr->drv_cap_mask = mask;
+}
+
struct qlcnic_dump_operations {
enum qlcnic_minidump_opcode opcode;
u32 (*handler)(struct qlcnic_adapter *, struct qlcnic_dump_entry *,
@@ -238,11 +339,11 @@
static u32 qlcnic_dump_ctrl(struct qlcnic_adapter *adapter,
struct qlcnic_dump_entry *entry, __le32 *buffer)
{
- int i, k, timeout = 0;
- u32 addr, data;
- u8 no_ops;
+ void *hdr = adapter->ahw->fw_dump.tmpl_hdr;
struct __ctrl *ctr = &entry->region.ctrl;
- struct qlcnic_dump_template_hdr *t_hdr = adapter->ahw->fw_dump.tmpl_hdr;
+ int i, k, timeout = 0;
+ u32 addr, data, temp;
+ u8 no_ops;
addr = ctr->addr;
no_ops = ctr->no_ops;
@@ -285,29 +386,42 @@
}
break;
case QLCNIC_DUMP_RD_SAVE:
- if (ctr->index_a)
- addr = t_hdr->saved_state[ctr->index_a];
+ temp = ctr->index_a;
+ if (temp)
+ addr = qlcnic_get_saved_state(adapter,
+ hdr,
+ temp);
data = qlcnic_ind_rd(adapter, addr);
- t_hdr->saved_state[ctr->index_v] = data;
+ qlcnic_set_saved_state(adapter, hdr,
+ ctr->index_v, data);
break;
case QLCNIC_DUMP_WRT_SAVED:
- if (ctr->index_v)
- data = t_hdr->saved_state[ctr->index_v];
+ temp = ctr->index_v;
+ if (temp)
+ data = qlcnic_get_saved_state(adapter,
+ hdr,
+ temp);
else
data = ctr->val1;
- if (ctr->index_a)
- addr = t_hdr->saved_state[ctr->index_a];
+
+ temp = ctr->index_a;
+ if (temp)
+ addr = qlcnic_get_saved_state(adapter,
+ hdr,
+ temp);
qlcnic_ind_wr(adapter, addr, data);
break;
case QLCNIC_DUMP_MOD_SAVE_ST:
- data = t_hdr->saved_state[ctr->index_v];
+ data = qlcnic_get_saved_state(adapter, hdr,
+ ctr->index_v);
data <<= ctr->shl_val;
data >>= ctr->shr_val;
if (ctr->val2)
data &= ctr->val2;
data |= ctr->val3;
data += ctr->val1;
- t_hdr->saved_state[ctr->index_v] = data;
+ qlcnic_set_saved_state(adapter, hdr,
+ ctr->index_v, data);
break;
default:
dev_info(&adapter->pdev->dev,
@@ -544,7 +658,7 @@
static int qlcnic_start_pex_dma(struct qlcnic_adapter *adapter,
struct __mem *mem)
{
- struct qlcnic_dump_template_hdr *tmpl_hdr;
+ struct qlcnic_83xx_dump_template_hdr *tmpl_hdr;
struct device *dev = &adapter->pdev->dev;
u32 dma_no, dma_base_addr, temp_addr;
int i, ret, dma_sts;
@@ -596,7 +710,7 @@
struct qlcnic_fw_dump *fw_dump = &adapter->ahw->fw_dump;
u32 temp, dma_base_addr, size = 0, read_size = 0;
struct qlcnic_pex_dma_descriptor *dma_descr;
- struct qlcnic_dump_template_hdr *tmpl_hdr;
+ struct qlcnic_83xx_dump_template_hdr *tmpl_hdr;
struct device *dev = &adapter->pdev->dev;
dma_addr_t dma_phys_addr;
void *dma_buffer;
@@ -938,8 +1052,8 @@
qlcnic_fw_flash_get_minidump_temp_size(struct qlcnic_adapter *adapter,
struct qlcnic_cmd_args *cmd)
{
- struct qlcnic_dump_template_hdr tmp_hdr;
- u32 size = sizeof(struct qlcnic_dump_template_hdr) / sizeof(u32);
+ struct qlcnic_83xx_dump_template_hdr tmp_hdr;
+ u32 size = sizeof(tmp_hdr) / sizeof(u32);
int ret = 0;
if (qlcnic_82xx_check(adapter))
@@ -1027,17 +1141,19 @@
return err;
}
+#define QLCNIC_TEMPLATE_VERSION (0x20001)
+
int qlcnic_fw_cmd_get_minidump_temp(struct qlcnic_adapter *adapter)
{
- int err;
- u32 temp_size = 0;
- u32 version, csum, *tmp_buf;
struct qlcnic_hardware_context *ahw;
- struct qlcnic_dump_template_hdr *tmpl_hdr;
+ struct qlcnic_fw_dump *fw_dump;
+ u32 version, csum, *tmp_buf;
u8 use_flash_temp = 0;
+ u32 temp_size = 0;
+ int err;
ahw = adapter->ahw;
-
+ fw_dump = &ahw->fw_dump;
err = qlcnic_fw_get_minidump_temp_size(adapter, &version, &temp_size,
&use_flash_temp);
if (err) {
@@ -1046,11 +1162,11 @@
return -EIO;
}
- ahw->fw_dump.tmpl_hdr = vzalloc(temp_size);
- if (!ahw->fw_dump.tmpl_hdr)
+ fw_dump->tmpl_hdr = vzalloc(temp_size);
+ if (!fw_dump->tmpl_hdr)
return -ENOMEM;
- tmp_buf = (u32 *)ahw->fw_dump.tmpl_hdr;
+ tmp_buf = (u32 *)fw_dump->tmpl_hdr;
if (use_flash_temp)
goto flash_temp;
@@ -1065,8 +1181,8 @@
dev_err(&adapter->pdev->dev,
"Failed to get minidump template header %d\n",
err);
- vfree(ahw->fw_dump.tmpl_hdr);
- ahw->fw_dump.tmpl_hdr = NULL;
+ vfree(fw_dump->tmpl_hdr);
+ fw_dump->tmpl_hdr = NULL;
return -EIO;
}
}
@@ -1076,21 +1192,22 @@
if (csum) {
dev_err(&adapter->pdev->dev,
"Template header checksum validation failed\n");
- vfree(ahw->fw_dump.tmpl_hdr);
- ahw->fw_dump.tmpl_hdr = NULL;
+ vfree(fw_dump->tmpl_hdr);
+ fw_dump->tmpl_hdr = NULL;
return -EIO;
}
- tmpl_hdr = ahw->fw_dump.tmpl_hdr;
- tmpl_hdr->drv_cap_mask = tmpl_hdr->cap_mask;
+ qlcnic_cache_tmpl_hdr_values(adapter, fw_dump);
+
dev_info(&adapter->pdev->dev,
"Default minidump capture mask 0x%x\n",
- tmpl_hdr->cap_mask);
+ fw_dump->cap_mask);
- if ((tmpl_hdr->version & 0xfffff) >= 0x20001)
- ahw->fw_dump.use_pex_dma = true;
+ if (qlcnic_83xx_check(adapter) &&
+ (fw_dump->version & 0xfffff) >= QLCNIC_TEMPLATE_VERSION)
+ fw_dump->use_pex_dma = true;
else
- ahw->fw_dump.use_pex_dma = false;
+ fw_dump->use_pex_dma = false;
qlcnic_enable_fw_dump_state(adapter);
@@ -1099,21 +1216,22 @@
int qlcnic_dump_fw(struct qlcnic_adapter *adapter)
{
- __le32 *buffer;
- u32 ocm_window;
- char mesg[64];
- char *msg[] = {mesg, NULL};
- int i, k, ops_cnt, ops_index, dump_size = 0;
- u32 entry_offset, dump, no_entries, buf_offset = 0;
- struct qlcnic_dump_entry *entry;
struct qlcnic_fw_dump *fw_dump = &adapter->ahw->fw_dump;
- struct qlcnic_dump_template_hdr *tmpl_hdr = fw_dump->tmpl_hdr;
static const struct qlcnic_dump_operations *fw_dump_ops;
+ struct qlcnic_83xx_dump_template_hdr *hdr_83xx;
+ u32 entry_offset, dump, no_entries, buf_offset = 0;
+ int i, k, ops_cnt, ops_index, dump_size = 0;
struct device *dev = &adapter->pdev->dev;
struct qlcnic_hardware_context *ahw;
- void *temp_buffer;
+ struct qlcnic_dump_entry *entry;
+ void *temp_buffer, *tmpl_hdr;
+ u32 ocm_window;
+ __le32 *buffer;
+ char mesg[64];
+ char *msg[] = {mesg, NULL};
ahw = adapter->ahw;
+ tmpl_hdr = fw_dump->tmpl_hdr;
/* Return if we don't have firmware dump template header */
if (!tmpl_hdr)
@@ -1133,8 +1251,9 @@
netif_info(adapter->ahw, drv, adapter->netdev, "Take FW dump\n");
/* Calculate the size for dump data area only */
for (i = 2, k = 1; (i & QLCNIC_DUMP_MASK_MAX); i <<= 1, k++)
- if (i & tmpl_hdr->drv_cap_mask)
- dump_size += tmpl_hdr->cap_sizes[k];
+ if (i & fw_dump->cap_mask)
+ dump_size += qlcnic_get_cap_size(adapter, tmpl_hdr, k);
+
if (!dump_size)
return -EIO;
@@ -1144,10 +1263,10 @@
buffer = fw_dump->data;
fw_dump->size = dump_size;
- no_entries = tmpl_hdr->num_entries;
- entry_offset = tmpl_hdr->offset;
- tmpl_hdr->sys_info[0] = QLCNIC_DRIVER_VERSION;
- tmpl_hdr->sys_info[1] = adapter->fw_version;
+ no_entries = fw_dump->num_entries;
+ entry_offset = fw_dump->offset;
+ qlcnic_set_sys_info(adapter, tmpl_hdr, 0, QLCNIC_DRIVER_VERSION);
+ qlcnic_set_sys_info(adapter, tmpl_hdr, 1, adapter->fw_version);
if (fw_dump->use_pex_dma) {
temp_buffer = dma_alloc_coherent(dev, QLC_PEX_DMA_READ_SIZE,
@@ -1163,16 +1282,17 @@
ops_cnt = ARRAY_SIZE(qlcnic_fw_dump_ops);
fw_dump_ops = qlcnic_fw_dump_ops;
} else {
+ hdr_83xx = tmpl_hdr;
ops_cnt = ARRAY_SIZE(qlcnic_83xx_fw_dump_ops);
fw_dump_ops = qlcnic_83xx_fw_dump_ops;
- ocm_window = tmpl_hdr->ocm_wnd_reg[adapter->ahw->pci_func];
- tmpl_hdr->saved_state[QLC_83XX_OCM_INDEX] = ocm_window;
- tmpl_hdr->saved_state[QLC_83XX_PCI_INDEX] = ahw->pci_func;
+ ocm_window = hdr_83xx->ocm_wnd_reg[ahw->pci_func];
+ hdr_83xx->saved_state[QLC_83XX_OCM_INDEX] = ocm_window;
+ hdr_83xx->saved_state[QLC_83XX_PCI_INDEX] = ahw->pci_func;
}
for (i = 0; i < no_entries; i++) {
- entry = (void *)tmpl_hdr + entry_offset;
- if (!(entry->hdr.mask & tmpl_hdr->drv_cap_mask)) {
+ entry = tmpl_hdr + entry_offset;
+ if (!(entry->hdr.mask & fw_dump->cap_mask)) {
entry->hdr.flags |= QLCNIC_DUMP_SKIP;
entry_offset += entry->hdr.offset;
continue;
@@ -1209,8 +1329,9 @@
fw_dump->clr = 1;
snprintf(mesg, sizeof(mesg), "FW_DUMP=%s", adapter->netdev->name);
- dev_info(dev, "%s: Dump data %d bytes captured, template header size %d bytes\n",
- adapter->netdev->name, fw_dump->size, tmpl_hdr->size);
+ netdev_info(adapter->netdev,
+ "Dump data %d bytes captured, template header size %d bytes\n",
+ fw_dump->size, fw_dump->tmpl_hdr_size);
/* Send a udev event to notify availability of FW dump */
kobject_uevent_env(&dev->kobj, KOBJ_CHANGE, msg);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index 09acf15..14f748c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -13,10 +13,9 @@
#define QLC_VF_MIN_TX_RATE 100
#define QLC_VF_MAX_TX_RATE 9999
#define QLC_MAC_OPCODE_MASK 0x7
-#define QLC_MAC_STAR_ADD 6
-#define QLC_MAC_STAR_DEL 7
#define QLC_VF_FLOOD_BIT BIT_16
#define QLC_FLOOD_MODE 0x5
+#define QLC_SRIOV_ALLOW_VLAN0 BIT_19
static int qlcnic_sriov_pf_get_vport_handle(struct qlcnic_adapter *, u8);
@@ -337,8 +336,11 @@
return err;
cmd.req.arg[1] = 0x4;
- if (enable)
+ if (enable) {
cmd.req.arg[1] |= BIT_16;
+ if (qlcnic_84xx_check(adapter))
+ cmd.req.arg[1] |= QLC_SRIOV_ALLOW_VLAN0;
+ }
err = qlcnic_issue_cmd(adapter, &cmd);
if (err)
@@ -1206,13 +1208,6 @@
struct qlcnic_vport *vp = vf->vp;
u8 op, new_op;
- if (((cmd->req.arg[1] & QLC_MAC_OPCODE_MASK) == QLC_MAC_STAR_ADD) ||
- ((cmd->req.arg[1] & QLC_MAC_OPCODE_MASK) == QLC_MAC_STAR_DEL)) {
- netdev_err(adapter->netdev, "MAC + any VLAN filter not allowed from VF %d\n",
- vf->pci_func);
- return -EINVAL;
- }
-
if (!(cmd->req.arg[1] & BIT_8))
return -EINVAL;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
index 3d64113..448d156 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
@@ -350,33 +350,15 @@
return size;
}
-static u32 qlcnic_get_pci_func_count(struct qlcnic_adapter *adapter)
-{
- struct qlcnic_hardware_context *ahw = adapter->ahw;
- u32 count = 0;
-
- if (!(adapter->flags & QLCNIC_ESWITCH_ENABLED))
- return ahw->total_nic_func;
-
- if (ahw->total_pci_func <= QLC_DEFAULT_VNIC_COUNT)
- count = QLC_DEFAULT_VNIC_COUNT;
- else
- count = ahw->max_vnic_func;
-
- return count;
-}
-
int qlcnic_is_valid_nic_func(struct qlcnic_adapter *adapter, u8 pci_func)
{
- u32 pci_func_count = qlcnic_get_pci_func_count(adapter);
int i;
- for (i = 0; i < pci_func_count; i++) {
+ for (i = 0; i < adapter->ahw->max_vnic_func; i++) {
if (adapter->npars[i].pci_func == pci_func)
return i;
}
-
- return -1;
+ return -EINVAL;
}
static int validate_pm_config(struct qlcnic_adapter *adapter,
@@ -464,23 +446,21 @@
{
struct device *dev = container_of(kobj, struct device, kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
- u32 pci_func_count = qlcnic_get_pci_func_count(adapter);
struct qlcnic_pm_func_cfg *pm_cfg;
- int i, pm_cfg_size;
u8 pci_func;
+ u32 count;
+ int i;
- pm_cfg_size = pci_func_count * sizeof(*pm_cfg);
- if (size != pm_cfg_size)
- return QL_STATUS_INVALID_PARAM;
-
- memset(buf, 0, pm_cfg_size);
+ memset(buf, 0, size);
pm_cfg = (struct qlcnic_pm_func_cfg *)buf;
-
- for (i = 0; i < pci_func_count; i++) {
+ count = size / sizeof(struct qlcnic_pm_func_cfg);
+ for (i = 0; i < adapter->ahw->total_nic_func; i++) {
pci_func = adapter->npars[i].pci_func;
- if (!adapter->npars[i].active)
+ if (pci_func >= count) {
+ dev_dbg(dev, "%s: Total nic functions[%d], App sent function count[%d]\n",
+ __func__, adapter->ahw->total_nic_func, count);
continue;
-
+ }
if (!adapter->npars[i].eswitch_status)
continue;
@@ -494,7 +474,6 @@
static int validate_esw_config(struct qlcnic_adapter *adapter,
struct qlcnic_esw_func_cfg *esw_cfg, int count)
{
- u32 pci_func_count = qlcnic_get_pci_func_count(adapter);
struct qlcnic_hardware_context *ahw = adapter->ahw;
int i, ret;
u32 op_mode;
@@ -507,7 +486,7 @@
for (i = 0; i < count; i++) {
pci_func = esw_cfg[i].pci_func;
- if (pci_func >= pci_func_count)
+ if (pci_func >= ahw->max_vnic_func)
return QL_STATUS_INVALID_PARAM;
if (adapter->ahw->op_mode == QLCNIC_MGMT_FUNC)
@@ -642,23 +621,21 @@
{
struct device *dev = container_of(kobj, struct device, kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
- u32 pci_func_count = qlcnic_get_pci_func_count(adapter);
struct qlcnic_esw_func_cfg *esw_cfg;
- size_t esw_cfg_size;
- u8 i, pci_func;
+ u8 pci_func;
+ u32 count;
+ int i;
- esw_cfg_size = pci_func_count * sizeof(*esw_cfg);
- if (size != esw_cfg_size)
- return QL_STATUS_INVALID_PARAM;
-
- memset(buf, 0, esw_cfg_size);
+ memset(buf, 0, size);
esw_cfg = (struct qlcnic_esw_func_cfg *)buf;
-
- for (i = 0; i < pci_func_count; i++) {
+ count = size / sizeof(struct qlcnic_esw_func_cfg);
+ for (i = 0; i < adapter->ahw->total_nic_func; i++) {
pci_func = adapter->npars[i].pci_func;
- if (!adapter->npars[i].active)
+ if (pci_func >= count) {
+ dev_dbg(dev, "%s: Total nic functions[%d], App sent function count[%d]\n",
+ __func__, adapter->ahw->total_nic_func, count);
continue;
-
+ }
if (!adapter->npars[i].eswitch_status)
continue;
@@ -741,23 +718,24 @@
{
struct device *dev = container_of(kobj, struct device, kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
- u32 pci_func_count = qlcnic_get_pci_func_count(adapter);
struct qlcnic_npar_func_cfg *np_cfg;
struct qlcnic_info nic_info;
- size_t np_cfg_size;
int i, ret;
-
- np_cfg_size = pci_func_count * sizeof(*np_cfg);
- if (size != np_cfg_size)
- return QL_STATUS_INVALID_PARAM;
+ u32 count;
memset(&nic_info, 0, sizeof(struct qlcnic_info));
- memset(buf, 0, np_cfg_size);
+ memset(buf, 0, size);
np_cfg = (struct qlcnic_npar_func_cfg *)buf;
- for (i = 0; i < pci_func_count; i++) {
+ count = size / sizeof(struct qlcnic_npar_func_cfg);
+ for (i = 0; i < adapter->ahw->total_nic_func; i++) {
if (qlcnic_is_valid_nic_func(adapter, i) < 0)
continue;
+ if (adapter->npars[i].pci_func >= count) {
+ dev_dbg(dev, "%s: Total nic functions[%d], App sent function count[%d]\n",
+ __func__, adapter->ahw->total_nic_func, count);
+ continue;
+ }
ret = qlcnic_get_nic_info(adapter, &nic_info, i);
if (ret)
return ret;
@@ -783,7 +761,6 @@
{
struct device *dev = container_of(kobj, struct device, kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
- u32 pci_func_count = qlcnic_get_pci_func_count(adapter);
struct qlcnic_esw_statistics port_stats;
int ret;
@@ -793,7 +770,7 @@
if (size != sizeof(struct qlcnic_esw_statistics))
return QL_STATUS_INVALID_PARAM;
- if (offset >= pci_func_count)
+ if (offset >= adapter->ahw->max_vnic_func)
return QL_STATUS_INVALID_PARAM;
memset(&port_stats, 0, size);
@@ -884,13 +861,12 @@
struct device *dev = container_of(kobj, struct device, kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
- u32 pci_func_count = qlcnic_get_pci_func_count(adapter);
int ret;
if (qlcnic_83xx_check(adapter))
return QLC_STATUS_UNSUPPORTED_CMD;
- if (offset >= pci_func_count)
+ if (offset >= adapter->ahw->max_vnic_func)
return QL_STATUS_INVALID_PARAM;
ret = qlcnic_clear_esw_stats(adapter, QLCNIC_STATS_PORT, offset,
@@ -914,17 +890,12 @@
{
struct device *dev = container_of(kobj, struct device, kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
- u32 pci_func_count = qlcnic_get_pci_func_count(adapter);
struct qlcnic_pci_func_cfg *pci_cfg;
struct qlcnic_pci_info *pci_info;
- size_t pci_cfg_sz;
int i, ret;
+ u32 count;
- pci_cfg_sz = pci_func_count * sizeof(*pci_cfg);
- if (size != pci_cfg_sz)
- return QL_STATUS_INVALID_PARAM;
-
- pci_info = kcalloc(pci_func_count, sizeof(*pci_info), GFP_KERNEL);
+ pci_info = kcalloc(size, sizeof(*pci_info), GFP_KERNEL);
if (!pci_info)
return -ENOMEM;
@@ -935,7 +906,8 @@
}
pci_cfg = (struct qlcnic_pci_func_cfg *)buf;
- for (i = 0; i < pci_func_count; i++) {
+ count = size / sizeof(struct qlcnic_pci_func_cfg);
+ for (i = 0; i < count; i++) {
pci_cfg[i].pci_func = pci_info[i].id;
pci_cfg[i].func_type = pci_info[i].type;
pci_cfg[i].func_state = 0;
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index ce2cfdd..0a1d76ac 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -2556,11 +2556,10 @@
if (skb_is_gso(skb)) {
int err;
- if (skb_header_cloned(skb)) {
- err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (err)
- return err;
- }
+
+ err = skb_cow_head(skb, 0);
+ if (err < 0)
+ return err;
mac_iocb_ptr->opcode = OPCODE_OB_MAC_TSO_IOCB;
mac_iocb_ptr->flags3 |= OB_MAC_TSO_IOCB_IC;
@@ -3331,24 +3330,16 @@
for (i = 0; i < qdev->intr_count; i++)
qdev->msi_x_entry[i].entry = i;
- /* Loop to get our vectors. We start with
- * what we want and settle for what we get.
- */
- do {
- err = pci_enable_msix(qdev->pdev,
- qdev->msi_x_entry, qdev->intr_count);
- if (err > 0)
- qdev->intr_count = err;
- } while (err > 0);
-
+ err = pci_enable_msix_range(qdev->pdev, qdev->msi_x_entry,
+ 1, qdev->intr_count);
if (err < 0) {
kfree(qdev->msi_x_entry);
qdev->msi_x_entry = NULL;
netif_warn(qdev, ifup, qdev->ndev,
"MSI-X Enable failed, trying MSI.\n");
- qdev->intr_count = 1;
qlge_irq_type = MSI_IRQ;
- } else if (err == 0) {
+ } else {
+ qdev->intr_count = err;
set_bit(QL_MSIX_ENABLED, &qdev->flags);
netif_info(qdev, ifup, qdev->ndev,
"MSI-X Enabled, got %d vectors.\n",
@@ -4765,7 +4756,9 @@
ndev->features = ndev->hw_features;
ndev->vlan_features = ndev->hw_features;
/* vlan gets same features (except vlan filter) */
- ndev->vlan_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+ ndev->vlan_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER |
+ NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX);
if (test_bit(QL_DMA64, &qdev->flags))
ndev->features |= NETIF_F_HIGHDMA;
diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c
index 819b74c..cd045ec 100644
--- a/drivers/net/ethernet/rdc/r6040.c
+++ b/drivers/net/ethernet/rdc/r6040.c
@@ -270,11 +270,6 @@
return r6040_phy_write(ioaddr, phy_addr, reg, value);
}
-static int r6040_mdiobus_reset(struct mii_bus *bus)
-{
- return 0;
-}
-
static void r6040_free_txbufs(struct net_device *dev)
{
struct r6040_private *lp = netdev_priv(dev);
@@ -1191,7 +1186,6 @@
lp->mii_bus->priv = dev;
lp->mii_bus->read = r6040_mdiobus_read;
lp->mii_bus->write = r6040_mdiobus_write;
- lp->mii_bus->reset = r6040_mdiobus_reset;
lp->mii_bus->name = "r6040_eth_mii";
snprintf(lp->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
dev_name(&pdev->dev), card_idx);
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index 737c1a8..2bc728e 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -476,7 +476,7 @@
rx = 0;
cpw16(IntrStatus, cp_rx_intr_mask);
- while (1) {
+ while (rx < budget) {
u32 status, len;
dma_addr_t mapping, new_mapping;
struct sk_buff *skb, *new_skb;
@@ -554,9 +554,6 @@
else
desc->opts1 = cpu_to_le32(DescOwn | cp->rx_buf_sz);
rx_tail = NEXT_RX(rx_tail);
-
- if (rx >= budget)
- break;
}
cp->rx_tail = rx_tail;
@@ -899,7 +896,7 @@
return NETDEV_TX_OK;
out_dma_error:
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
cp->dev->stats.tx_dropped++;
goto out_unlock;
}
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index da5972e..2e5df14 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -1717,9 +1717,9 @@
if (len < ETH_ZLEN)
memset(tp->tx_buf[entry], 0, ETH_ZLEN);
skb_copy_and_csum_dev(skb, tp->tx_buf[entry]);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
} else {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
@@ -2522,16 +2522,16 @@
netdev_stats_to_stats64(stats, &dev->stats);
do {
- start = u64_stats_fetch_begin_bh(&tp->rx_stats.syncp);
+ start = u64_stats_fetch_begin_irq(&tp->rx_stats.syncp);
stats->rx_packets = tp->rx_stats.packets;
stats->rx_bytes = tp->rx_stats.bytes;
- } while (u64_stats_fetch_retry_bh(&tp->rx_stats.syncp, start));
+ } while (u64_stats_fetch_retry_irq(&tp->rx_stats.syncp, start));
do {
- start = u64_stats_fetch_begin_bh(&tp->tx_stats.syncp);
+ start = u64_stats_fetch_begin_irq(&tp->tx_stats.syncp);
stats->tx_packets = tp->tx_stats.packets;
stats->tx_bytes = tp->tx_stats.bytes;
- } while (u64_stats_fetch_retry_bh(&tp->tx_stats.syncp, start));
+ } while (u64_stats_fetch_retry_irq(&tp->tx_stats.syncp, start));
return stats;
}
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 91a67ae..aa1c079 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -209,7 +209,7 @@
[RTL_GIGA_MAC_VER_16] =
_R("RTL8101e", RTL_TD_0, NULL, JUMBO_1K, true),
[RTL_GIGA_MAC_VER_17] =
- _R("RTL8168b/8111b", RTL_TD_1, NULL, JUMBO_4K, false),
+ _R("RTL8168b/8111b", RTL_TD_0, NULL, JUMBO_4K, false),
[RTL_GIGA_MAC_VER_18] =
_R("RTL8168cp/8111cp", RTL_TD_1, NULL, JUMBO_6K, false),
[RTL_GIGA_MAC_VER_19] =
@@ -5834,7 +5834,7 @@
tp->TxDescArray + entry);
if (skb) {
tp->dev->stats.tx_dropped++;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
tx_skb->skb = NULL;
}
}
@@ -6059,7 +6059,7 @@
err_dma_1:
rtl8169_unmap_tx_skb(d, tp->tx_skb + entry, txd);
err_dma_0:
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
err_update_stats:
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
@@ -6142,7 +6142,7 @@
tp->tx_stats.packets++;
tp->tx_stats.bytes += tx_skb->skb->len;
u64_stats_update_end(&tp->tx_stats.syncp);
- dev_kfree_skb(tx_skb->skb);
+ dev_kfree_skb_any(tx_skb->skb);
tx_skb->skb = NULL;
}
dirty_tx++;
@@ -6590,17 +6590,17 @@
rtl8169_rx_missed(dev, ioaddr);
do {
- start = u64_stats_fetch_begin_bh(&tp->rx_stats.syncp);
+ start = u64_stats_fetch_begin_irq(&tp->rx_stats.syncp);
stats->rx_packets = tp->rx_stats.packets;
stats->rx_bytes = tp->rx_stats.bytes;
- } while (u64_stats_fetch_retry_bh(&tp->rx_stats.syncp, start));
+ } while (u64_stats_fetch_retry_irq(&tp->rx_stats.syncp, start));
do {
- start = u64_stats_fetch_begin_bh(&tp->tx_stats.syncp);
+ start = u64_stats_fetch_begin_irq(&tp->tx_stats.syncp);
stats->tx_packets = tp->tx_stats.packets;
stats->tx_bytes = tp->tx_stats.bytes;
- } while (u64_stats_fetch_retry_bh(&tp->tx_stats.syncp, start));
+ } while (u64_stats_fetch_retry_irq(&tp->tx_stats.syncp, start));
stats->rx_dropped = dev->stats.rx_dropped;
stats->tx_dropped = dev->stats.tx_dropped;
@@ -7118,6 +7118,8 @@
}
mutex_init(&tp->wk.mutex);
+ u64_stats_init(&tp->rx_stats.syncp);
+ u64_stats_init(&tp->tx_stats.syncp);
/* Get MAC address */
for (i = 0; i < ETH_ALEN; i++)
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 040cb94..6a9509c 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1,8 +1,9 @@
/* SuperH Ethernet device driver
*
* Copyright (C) 2006-2012 Nobuhiro Iwamatsu
- * Copyright (C) 2008-2013 Renesas Solutions Corp.
- * Copyright (C) 2013 Cogent Embedded, Inc.
+ * Copyright (C) 2008-2014 Renesas Solutions Corp.
+ * Copyright (C) 2013-2014 Cogent Embedded, Inc.
+ * Copyright (C) 2014 Codethink Limited
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
@@ -27,6 +28,10 @@
#include <linux/platform_device.h>
#include <linux/mdio-bitbang.h>
#include <linux/netdevice.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/of_net.h>
#include <linux/phy.h>
#include <linux/cache.h>
#include <linux/io.h>
@@ -36,6 +41,7 @@
#include <linux/if_vlan.h>
#include <linux/clk.h>
#include <linux/sh_eth.h>
+#include <linux/of_mdio.h>
#include "sh_eth.h"
@@ -394,7 +400,8 @@
value = 0x0;
break;
default:
- pr_warn("PHY interface mode was not setup. Set to MII.\n");
+ netdev_warn(ndev,
+ "PHY interface mode was not setup. Set to MII.\n");
value = 0x1;
break;
}
@@ -848,7 +855,7 @@
cnt--;
}
if (cnt <= 0) {
- pr_err("Device reset failed\n");
+ netdev_err(ndev, "Device reset failed\n");
ret = -ETIMEDOUT;
}
return ret;
@@ -866,7 +873,7 @@
ret = sh_eth_check_reset(ndev);
if (ret)
- goto out;
+ return ret;
/* Table Init */
sh_eth_write(ndev, 0x0, TDLAR);
@@ -893,7 +900,6 @@
EDMR);
}
-out:
return ret;
}
@@ -1257,7 +1263,7 @@
/* Soft Reset */
ret = sh_eth_reset(ndev);
if (ret)
- goto out;
+ return ret;
if (mdp->cd->rmiimode)
sh_eth_write(ndev, 0x1, RMIIMODE);
@@ -1336,7 +1342,6 @@
netif_start_queue(ndev);
}
-out:
return ret;
}
@@ -1550,8 +1555,7 @@
/* Unused write back interrupt */
if (intr_status & EESR_TABT) { /* Transmit Abort int */
ndev->stats.tx_aborted_errors++;
- if (netif_msg_tx_err(mdp))
- dev_err(&ndev->dev, "Transmit Abort\n");
+ netif_err(mdp, tx_err, ndev, "Transmit Abort\n");
}
}
@@ -1560,45 +1564,38 @@
if (intr_status & EESR_RFRMER) {
/* Receive Frame Overflow int */
ndev->stats.rx_frame_errors++;
- if (netif_msg_rx_err(mdp))
- dev_err(&ndev->dev, "Receive Abort\n");
+ netif_err(mdp, rx_err, ndev, "Receive Abort\n");
}
}
if (intr_status & EESR_TDE) {
/* Transmit Descriptor Empty int */
ndev->stats.tx_fifo_errors++;
- if (netif_msg_tx_err(mdp))
- dev_err(&ndev->dev, "Transmit Descriptor Empty\n");
+ netif_err(mdp, tx_err, ndev, "Transmit Descriptor Empty\n");
}
if (intr_status & EESR_TFE) {
/* FIFO under flow */
ndev->stats.tx_fifo_errors++;
- if (netif_msg_tx_err(mdp))
- dev_err(&ndev->dev, "Transmit FIFO Under flow\n");
+ netif_err(mdp, tx_err, ndev, "Transmit FIFO Under flow\n");
}
if (intr_status & EESR_RDE) {
/* Receive Descriptor Empty int */
ndev->stats.rx_over_errors++;
-
- if (netif_msg_rx_err(mdp))
- dev_err(&ndev->dev, "Receive Descriptor Empty\n");
+ netif_err(mdp, rx_err, ndev, "Receive Descriptor Empty\n");
}
if (intr_status & EESR_RFE) {
/* Receive FIFO Overflow int */
ndev->stats.rx_fifo_errors++;
- if (netif_msg_rx_err(mdp))
- dev_err(&ndev->dev, "Receive FIFO Overflow\n");
+ netif_err(mdp, rx_err, ndev, "Receive FIFO Overflow\n");
}
if (!mdp->cd->no_ade && (intr_status & EESR_ADE)) {
/* Address Error */
ndev->stats.tx_fifo_errors++;
- if (netif_msg_tx_err(mdp))
- dev_err(&ndev->dev, "Address Error\n");
+ netif_err(mdp, tx_err, ndev, "Address Error\n");
}
mask = EESR_TWB | EESR_TABT | EESR_ADE | EESR_TDE | EESR_TFE;
@@ -1609,9 +1606,9 @@
u32 edtrr = sh_eth_read(ndev, EDTRR);
/* dmesg */
- dev_err(&ndev->dev, "TX error. status=%8.8x cur_tx=%8.8x dirty_tx=%8.8x state=%8.8x EDTRR=%8.8x.\n",
- intr_status, mdp->cur_tx, mdp->dirty_tx,
- (u32)ndev->state, edtrr);
+ netdev_err(ndev, "TX error. status=%8.8x cur_tx=%8.8x dirty_tx=%8.8x state=%8.8x EDTRR=%8.8x.\n",
+ intr_status, mdp->cur_tx, mdp->dirty_tx,
+ (u32)ndev->state, edtrr);
/* dirty buffer free */
sh_eth_txfree(ndev);
@@ -1656,9 +1653,9 @@
EESIPR);
__napi_schedule(&mdp->napi);
} else {
- dev_warn(&ndev->dev,
- "ignoring interrupt, status 0x%08lx, mask 0x%08lx.\n",
- intr_status, intr_enable);
+ netdev_warn(ndev,
+ "ignoring interrupt, status 0x%08lx, mask 0x%08lx.\n",
+ intr_status, intr_enable);
}
}
@@ -1757,27 +1754,42 @@
/* PHY init function */
static int sh_eth_phy_init(struct net_device *ndev)
{
+ struct device_node *np = ndev->dev.parent->of_node;
struct sh_eth_private *mdp = netdev_priv(ndev);
- char phy_id[MII_BUS_ID_SIZE + 3];
struct phy_device *phydev = NULL;
- snprintf(phy_id, sizeof(phy_id), PHY_ID_FMT,
- mdp->mii_bus->id, mdp->phy_id);
-
mdp->link = 0;
mdp->speed = 0;
mdp->duplex = -1;
/* Try connect to PHY */
- phydev = phy_connect(ndev, phy_id, sh_eth_adjust_link,
- mdp->phy_interface);
+ if (np) {
+ struct device_node *pn;
+
+ pn = of_parse_phandle(np, "phy-handle", 0);
+ phydev = of_phy_connect(ndev, pn,
+ sh_eth_adjust_link, 0,
+ mdp->phy_interface);
+
+ if (!phydev)
+ phydev = ERR_PTR(-ENOENT);
+ } else {
+ char phy_id[MII_BUS_ID_SIZE + 3];
+
+ snprintf(phy_id, sizeof(phy_id), PHY_ID_FMT,
+ mdp->mii_bus->id, mdp->phy_id);
+
+ phydev = phy_connect(ndev, phy_id, sh_eth_adjust_link,
+ mdp->phy_interface);
+ }
+
if (IS_ERR(phydev)) {
- dev_err(&ndev->dev, "phy_connect failed\n");
+ netdev_err(ndev, "failed to connect PHY\n");
return PTR_ERR(phydev);
}
- dev_info(&ndev->dev, "attached PHY %d (IRQ %d) to driver %s\n",
- phydev->addr, phydev->irq, phydev->drv->name);
+ netdev_info(ndev, "attached PHY %d (IRQ %d) to driver %s\n",
+ phydev->addr, phydev->irq, phydev->drv->name);
mdp->phydev = phydev;
@@ -1958,12 +1970,12 @@
ret = sh_eth_ring_init(ndev);
if (ret < 0) {
- dev_err(&ndev->dev, "%s: sh_eth_ring_init failed.\n", __func__);
+ netdev_err(ndev, "%s: sh_eth_ring_init failed.\n", __func__);
return ret;
}
ret = sh_eth_dev_init(ndev, false);
if (ret < 0) {
- dev_err(&ndev->dev, "%s: sh_eth_dev_init failed.\n", __func__);
+ netdev_err(ndev, "%s: sh_eth_dev_init failed.\n", __func__);
return ret;
}
@@ -2004,7 +2016,7 @@
ret = request_irq(ndev->irq, sh_eth_interrupt,
mdp->cd->irq_flags, ndev->name, ndev);
if (ret) {
- dev_err(&ndev->dev, "Can not assign IRQ number\n");
+ netdev_err(ndev, "Can not assign IRQ number\n");
goto out_napi_off;
}
@@ -2042,10 +2054,9 @@
netif_stop_queue(ndev);
- if (netif_msg_timer(mdp)) {
- dev_err(&ndev->dev, "%s: transmit timed out, status %8.8x, resetting...\n",
- ndev->name, (int)sh_eth_read(ndev, EESR));
- }
+ netif_err(mdp, timer, ndev,
+ "transmit timed out, status %8.8x, resetting...\n",
+ (int)sh_eth_read(ndev, EESR));
/* tx_errors count up */
ndev->stats.tx_errors++;
@@ -2080,8 +2091,7 @@
spin_lock_irqsave(&mdp->lock, flags);
if ((mdp->cur_tx - mdp->dirty_tx) >= (mdp->num_tx_ring - 4)) {
if (!sh_eth_txfree(ndev)) {
- if (netif_msg_tx_queued(mdp))
- dev_warn(&ndev->dev, "TxFD exhausted.\n");
+ netif_warn(mdp, tx_queued, ndev, "TxFD exhausted.\n");
netif_stop_queue(ndev);
spin_unlock_irqrestore(&mdp->lock, flags);
return NETDEV_TX_BUSY;
@@ -2098,8 +2108,8 @@
skb->len + 2);
txdesc->addr = dma_map_single(&ndev->dev, skb->data, skb->len,
DMA_TO_DEVICE);
- if (skb->len < ETHERSMALL)
- txdesc->buffer_length = ETHERSMALL;
+ if (skb->len < ETH_ZLEN)
+ txdesc->buffer_length = ETH_ZLEN;
else
txdesc->buffer_length = skb->len;
@@ -2251,7 +2261,7 @@
udelay(10);
timeout--;
if (timeout <= 0) {
- dev_err(&ndev->dev, "%s: timeout\n", __func__);
+ netdev_err(ndev, "%s: timeout\n", __func__);
return -ETIMEDOUT;
}
}
@@ -2571,37 +2581,30 @@
}
/* MDIO bus release function */
-static int sh_mdio_release(struct net_device *ndev)
+static int sh_mdio_release(struct sh_eth_private *mdp)
{
- struct mii_bus *bus = dev_get_drvdata(&ndev->dev);
-
/* unregister mdio bus */
- mdiobus_unregister(bus);
-
- /* remove mdio bus info from net_device */
- dev_set_drvdata(&ndev->dev, NULL);
+ mdiobus_unregister(mdp->mii_bus);
/* free bitbang info */
- free_mdio_bitbang(bus);
+ free_mdio_bitbang(mdp->mii_bus);
return 0;
}
/* MDIO bus init function */
-static int sh_mdio_init(struct net_device *ndev, int id,
+static int sh_mdio_init(struct sh_eth_private *mdp,
struct sh_eth_plat_data *pd)
{
int ret, i;
struct bb_info *bitbang;
- struct sh_eth_private *mdp = netdev_priv(ndev);
+ struct platform_device *pdev = mdp->pdev;
+ struct device *dev = &mdp->pdev->dev;
/* create bit control struct for PHY */
- bitbang = devm_kzalloc(&ndev->dev, sizeof(struct bb_info),
- GFP_KERNEL);
- if (!bitbang) {
- ret = -ENOMEM;
- goto out;
- }
+ bitbang = devm_kzalloc(dev, sizeof(struct bb_info), GFP_KERNEL);
+ if (!bitbang)
+ return -ENOMEM;
/* bitbang init */
bitbang->addr = mdp->addr + mdp->reg_offset[PIR];
@@ -2614,44 +2617,42 @@
/* MII controller setting */
mdp->mii_bus = alloc_mdio_bitbang(&bitbang->ctrl);
- if (!mdp->mii_bus) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!mdp->mii_bus)
+ return -ENOMEM;
/* Hook up MII support for ethtool */
mdp->mii_bus->name = "sh_mii";
- mdp->mii_bus->parent = &ndev->dev;
+ mdp->mii_bus->parent = dev;
snprintf(mdp->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
- mdp->pdev->name, id);
+ pdev->name, pdev->id);
/* PHY IRQ */
- mdp->mii_bus->irq = devm_kzalloc(&ndev->dev,
- sizeof(int) * PHY_MAX_ADDR,
+ mdp->mii_bus->irq = devm_kzalloc(dev, sizeof(int) * PHY_MAX_ADDR,
GFP_KERNEL);
if (!mdp->mii_bus->irq) {
ret = -ENOMEM;
goto out_free_bus;
}
- for (i = 0; i < PHY_MAX_ADDR; i++)
- mdp->mii_bus->irq[i] = PHY_POLL;
- if (pd->phy_irq > 0)
- mdp->mii_bus->irq[pd->phy] = pd->phy_irq;
+ /* register MDIO bus */
+ if (dev->of_node) {
+ ret = of_mdiobus_register(mdp->mii_bus, dev->of_node);
+ } else {
+ for (i = 0; i < PHY_MAX_ADDR; i++)
+ mdp->mii_bus->irq[i] = PHY_POLL;
+ if (pd->phy_irq > 0)
+ mdp->mii_bus->irq[pd->phy] = pd->phy_irq;
- /* register mdio bus */
- ret = mdiobus_register(mdp->mii_bus);
+ ret = mdiobus_register(mdp->mii_bus);
+ }
+
if (ret)
goto out_free_bus;
- dev_set_drvdata(&ndev->dev, mdp->mii_bus);
-
return 0;
out_free_bus:
free_mdio_bitbang(mdp->mii_bus);
-
-out:
return ret;
}
@@ -2676,7 +2677,6 @@
reg_offset = sh_eth_offset_fast_sh3_sh2;
break;
default:
- pr_err("Unknown register type (%d)\n", register_type);
break;
}
@@ -2710,6 +2710,48 @@
.ndo_change_mtu = eth_change_mtu,
};
+#ifdef CONFIG_OF
+static struct sh_eth_plat_data *sh_eth_parse_dt(struct device *dev)
+{
+ struct device_node *np = dev->of_node;
+ struct sh_eth_plat_data *pdata;
+ const char *mac_addr;
+
+ pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+ if (!pdata)
+ return NULL;
+
+ pdata->phy_interface = of_get_phy_mode(np);
+
+ mac_addr = of_get_mac_address(np);
+ if (mac_addr)
+ memcpy(pdata->mac_addr, mac_addr, ETH_ALEN);
+
+ pdata->no_ether_link =
+ of_property_read_bool(np, "renesas,no-ether-link");
+ pdata->ether_link_active_low =
+ of_property_read_bool(np, "renesas,ether-link-active-low");
+
+ return pdata;
+}
+
+static const struct of_device_id sh_eth_match_table[] = {
+ { .compatible = "renesas,gether-r8a7740", .data = &r8a7740_data },
+ { .compatible = "renesas,ether-r8a7778", .data = &r8a777x_data },
+ { .compatible = "renesas,ether-r8a7779", .data = &r8a777x_data },
+ { .compatible = "renesas,ether-r8a7790", .data = &r8a779x_data },
+ { .compatible = "renesas,ether-r8a7791", .data = &r8a779x_data },
+ { .compatible = "renesas,ether-r7s72100", .data = &r7s72100_data },
+ { }
+};
+MODULE_DEVICE_TABLE(of, sh_eth_match_table);
+#else
+static inline struct sh_eth_plat_data *sh_eth_parse_dt(struct device *dev)
+{
+ return NULL;
+}
+#endif
+
static int sh_eth_drv_probe(struct platform_device *pdev)
{
int ret, devno = 0;
@@ -2723,15 +2765,15 @@
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (unlikely(res == NULL)) {
dev_err(&pdev->dev, "invalid resource\n");
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
ndev = alloc_etherdev(sizeof(struct sh_eth_private));
- if (!ndev) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!ndev)
+ return -ENOMEM;
+
+ pm_runtime_enable(&pdev->dev);
+ pm_runtime_get_sync(&pdev->dev);
/* The sh Ether-specific entries in the device structure. */
ndev->base_addr = res->start;
@@ -2760,9 +2802,9 @@
spin_lock_init(&mdp->lock);
mdp->pdev = pdev;
- pm_runtime_enable(&pdev->dev);
- pm_runtime_resume(&pdev->dev);
+ if (pdev->dev.of_node)
+ pd = sh_eth_parse_dt(&pdev->dev);
if (!pd) {
dev_err(&pdev->dev, "no platform data\n");
ret = -EINVAL;
@@ -2778,8 +2820,22 @@
mdp->ether_link_active_low = pd->ether_link_active_low;
/* set cpu data */
- mdp->cd = (struct sh_eth_cpu_data *)id->driver_data;
+ if (id) {
+ mdp->cd = (struct sh_eth_cpu_data *)id->driver_data;
+ } else {
+ const struct of_device_id *match;
+
+ match = of_match_device(of_match_ptr(sh_eth_match_table),
+ &pdev->dev);
+ mdp->cd = (struct sh_eth_cpu_data *)match->data;
+ }
mdp->reg_offset = sh_eth_get_register_offset(mdp->cd->register_type);
+ if (!mdp->reg_offset) {
+ dev_err(&pdev->dev, "Unknown register type (%d)\n",
+ mdp->cd->register_type);
+ ret = -EINVAL;
+ goto out_release;
+ }
sh_eth_set_default_cpu_data(mdp->cd);
/* set function */
@@ -2825,6 +2881,13 @@
}
}
+ /* MDIO bus init */
+ ret = sh_mdio_init(mdp, pd);
+ if (ret) {
+ dev_err(&ndev->dev, "failed to initialise MDIO\n");
+ goto out_release;
+ }
+
netif_napi_add(ndev, &mdp->napi, sh_eth_poll, 64);
/* network device register */
@@ -2832,31 +2895,26 @@
if (ret)
goto out_napi_del;
- /* mdio bus init */
- ret = sh_mdio_init(ndev, pdev->id, pd);
- if (ret)
- goto out_unregister;
-
/* print device information */
- pr_info("Base address at 0x%x, %pM, IRQ %d.\n",
- (u32)ndev->base_addr, ndev->dev_addr, ndev->irq);
+ netdev_info(ndev, "Base address at 0x%x, %pM, IRQ %d.\n",
+ (u32)ndev->base_addr, ndev->dev_addr, ndev->irq);
+ pm_runtime_put(&pdev->dev);
platform_set_drvdata(pdev, ndev);
return ret;
-out_unregister:
- unregister_netdev(ndev);
-
out_napi_del:
netif_napi_del(&mdp->napi);
+ sh_mdio_release(mdp);
out_release:
/* net_dev free */
if (ndev)
free_netdev(ndev);
-out:
+ pm_runtime_put(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
return ret;
}
@@ -2865,9 +2923,9 @@
struct net_device *ndev = platform_get_drvdata(pdev);
struct sh_eth_private *mdp = netdev_priv(ndev);
- sh_mdio_release(ndev);
unregister_netdev(ndev);
netif_napi_del(&mdp->napi);
+ sh_mdio_release(mdp);
pm_runtime_disable(&pdev->dev);
free_netdev(ndev);
@@ -2920,6 +2978,7 @@
.driver = {
.name = CARDNAME,
.pm = SH_ETH_PM_OPS,
+ .of_match_table = of_match_ptr(sh_eth_match_table),
},
};
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index 6075915..d55e37c 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -27,8 +27,7 @@
#define RX_RING_MIN 64
#define TX_RING_MAX 1024
#define RX_RING_MAX 1024
-#define ETHERSMALL 60
-#define PKT_BUF_SZ 1538
+#define PKT_BUF_SZ 1538
#define SH_ETH_TSU_TIMEOUT_MS 500
#define SH_ETH_TSU_CAM_ENTRIES 32
diff --git a/drivers/net/ethernet/samsung/Kconfig b/drivers/net/ethernet/samsung/Kconfig
new file mode 100644
index 0000000..7902341
--- /dev/null
+++ b/drivers/net/ethernet/samsung/Kconfig
@@ -0,0 +1,16 @@
+#
+# Samsung Ethernet device configuration
+#
+
+config NET_VENDOR_SAMSUNG
+ bool "Samsung Ethernet device"
+ default y
+ ---help---
+ This is the driver for the SXGBE 10G Ethernet IP block found on Samsung
+ platforms.
+
+if NET_VENDOR_SAMSUNG
+
+source "drivers/net/ethernet/samsung/sxgbe/Kconfig"
+
+endif # NET_VENDOR_SAMSUNG
diff --git a/drivers/net/ethernet/samsung/Makefile b/drivers/net/ethernet/samsung/Makefile
new file mode 100644
index 0000000..1773c29
--- /dev/null
+++ b/drivers/net/ethernet/samsung/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Samsung Ethernet device drivers.
+#
+
+obj-$(CONFIG_SXGBE_ETH) += sxgbe/
diff --git a/drivers/net/ethernet/samsung/sxgbe/Kconfig b/drivers/net/ethernet/samsung/sxgbe/Kconfig
new file mode 100644
index 0000000..d79288c
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/Kconfig
@@ -0,0 +1,9 @@
+config SXGBE_ETH
+ tristate "Samsung 10G/2.5G/1G SXGBE Ethernet driver"
+ depends on HAS_IOMEM && HAS_DMA
+ select PHYLIB
+ select CRC32
+ select PTP_1588_CLOCK
+ ---help---
+ This is the driver for the SXGBE 10G Ethernet IP block found on Samsung
+ platforms.
diff --git a/drivers/net/ethernet/samsung/sxgbe/Makefile b/drivers/net/ethernet/samsung/sxgbe/Makefile
new file mode 100644
index 0000000..dcc80b9
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/Makefile
@@ -0,0 +1,4 @@
+obj-$(CONFIG_SXGBE_ETH) += samsung-sxgbe.o
+samsung-sxgbe-objs:= sxgbe_platform.o sxgbe_main.o sxgbe_desc.o \
+ sxgbe_dma.o sxgbe_core.o sxgbe_mtl.o sxgbe_mdio.o \
+ sxgbe_ethtool.o sxgbe_xpcs.o $(samsung-sxgbe-y)
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h
new file mode 100644
index 0000000..6203c7d
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h
@@ -0,0 +1,535 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __SXGBE_COMMON_H__
+#define __SXGBE_COMMON_H__
+
+/* forward references */
+struct sxgbe_desc_ops;
+struct sxgbe_dma_ops;
+struct sxgbe_mtl_ops;
+
+#define SXGBE_RESOURCE_NAME "sam_sxgbeeth"
+#define DRV_MODULE_VERSION "November_2013"
+
+/* MAX HW feature words */
+#define SXGBE_HW_WORDS 3
+
+#define SXGBE_RX_COE_NONE 0
+
+/* CSR Frequency Access Defines*/
+#define SXGBE_CSR_F_150M 150000000
+#define SXGBE_CSR_F_250M 250000000
+#define SXGBE_CSR_F_300M 300000000
+#define SXGBE_CSR_F_350M 350000000
+#define SXGBE_CSR_F_400M 400000000
+#define SXGBE_CSR_F_500M 500000000
+
+/* pause time */
+#define SXGBE_PAUSE_TIME 0x200
+
+/* tx queues */
+#define SXGBE_TX_QUEUES 8
+#define SXGBE_RX_QUEUES 16
+
+/* Calculated based how much time does it take to fill 256KB Rx memory
+ * at 10Gb speed at 156MHz clock rate and considered little less then
+ * the actual value.
+ */
+#define SXGBE_MAX_DMA_RIWT 0x70
+#define SXGBE_MIN_DMA_RIWT 0x01
+
+/* Tx coalesce parameters */
+#define SXGBE_COAL_TX_TIMER 40000
+#define SXGBE_MAX_COAL_TX_TICK 100000
+#define SXGBE_TX_MAX_FRAMES 512
+#define SXGBE_TX_FRAMES 128
+
+/* SXGBE TX FIFO is 8K, Rx FIFO is 16K */
+#define BUF_SIZE_16KiB 16384
+#define BUF_SIZE_8KiB 8192
+#define BUF_SIZE_4KiB 4096
+#define BUF_SIZE_2KiB 2048
+
+#define SXGBE_DEFAULT_LIT_LS 0x3E8
+#define SXGBE_DEFAULT_TWT_LS 0x0
+
+/* Flow Control defines */
+#define SXGBE_FLOW_OFF 0
+#define SXGBE_FLOW_RX 1
+#define SXGBE_FLOW_TX 2
+#define SXGBE_FLOW_AUTO (SXGBE_FLOW_TX | SXGBE_FLOW_RX)
+
+#define SF_DMA_MODE 1 /* DMA STORE-AND-FORWARD Operation Mode */
+
+/* errors */
+#define RX_GMII_ERR 0x01
+#define RX_WATCHDOG_ERR 0x02
+#define RX_CRC_ERR 0x03
+#define RX_GAINT_ERR 0x04
+#define RX_IP_HDR_ERR 0x05
+#define RX_PAYLOAD_ERR 0x06
+#define RX_OVERFLOW_ERR 0x07
+
+/* pkt type */
+#define RX_LEN_PKT 0x00
+#define RX_MACCTL_PKT 0x01
+#define RX_DCBCTL_PKT 0x02
+#define RX_ARP_PKT 0x03
+#define RX_OAM_PKT 0x04
+#define RX_UNTAG_PKT 0x05
+#define RX_OTHER_PKT 0x07
+#define RX_SVLAN_PKT 0x08
+#define RX_CVLAN_PKT 0x09
+#define RX_DVLAN_OCVLAN_ICVLAN_PKT 0x0A
+#define RX_DVLAN_OSVLAN_ISVLAN_PKT 0x0B
+#define RX_DVLAN_OSVLAN_ICVLAN_PKT 0x0C
+#define RX_DVLAN_OCVLAN_ISVLAN_PKT 0x0D
+
+#define RX_NOT_IP_PKT 0x00
+#define RX_IPV4_TCP_PKT 0x01
+#define RX_IPV4_UDP_PKT 0x02
+#define RX_IPV4_ICMP_PKT 0x03
+#define RX_IPV4_UNKNOWN_PKT 0x07
+#define RX_IPV6_TCP_PKT 0x09
+#define RX_IPV6_UDP_PKT 0x0A
+#define RX_IPV6_ICMP_PKT 0x0B
+#define RX_IPV6_UNKNOWN_PKT 0x0F
+
+#define RX_NO_PTP 0x00
+#define RX_PTP_SYNC 0x01
+#define RX_PTP_FOLLOW_UP 0x02
+#define RX_PTP_DELAY_REQ 0x03
+#define RX_PTP_DELAY_RESP 0x04
+#define RX_PTP_PDELAY_REQ 0x05
+#define RX_PTP_PDELAY_RESP 0x06
+#define RX_PTP_PDELAY_FOLLOW_UP 0x07
+#define RX_PTP_ANNOUNCE 0x08
+#define RX_PTP_MGMT 0x09
+#define RX_PTP_SIGNAL 0x0A
+#define RX_PTP_RESV_MSG 0x0F
+
+/* EEE-LPI mode flags*/
+#define TX_ENTRY_LPI_MODE 0x10
+#define TX_EXIT_LPI_MODE 0x20
+#define RX_ENTRY_LPI_MODE 0x40
+#define RX_EXIT_LPI_MODE 0x80
+
+/* EEE-LPI Interrupt status flag */
+#define LPI_INT_STATUS BIT(5)
+
+/* EEE-LPI Default timer values */
+#define LPI_LINK_STATUS_TIMER 0x3E8
+#define LPI_MAC_WAIT_TIMER 0x00
+
+/* EEE-LPI Control and status definitions */
+#define LPI_CTRL_STATUS_TXA BIT(19)
+#define LPI_CTRL_STATUS_PLSDIS BIT(18)
+#define LPI_CTRL_STATUS_PLS BIT(17)
+#define LPI_CTRL_STATUS_LPIEN BIT(16)
+#define LPI_CTRL_STATUS_TXRSTP BIT(11)
+#define LPI_CTRL_STATUS_RXRSTP BIT(10)
+#define LPI_CTRL_STATUS_RLPIST BIT(9)
+#define LPI_CTRL_STATUS_TLPIST BIT(8)
+#define LPI_CTRL_STATUS_RLPIEX BIT(3)
+#define LPI_CTRL_STATUS_RLPIEN BIT(2)
+#define LPI_CTRL_STATUS_TLPIEX BIT(1)
+#define LPI_CTRL_STATUS_TLPIEN BIT(0)
+
+enum dma_irq_status {
+ tx_hard_error = BIT(0),
+ tx_bump_tc = BIT(1),
+ handle_tx = BIT(2),
+ rx_hard_error = BIT(3),
+ rx_bump_tc = BIT(4),
+ handle_rx = BIT(5),
+};
+
+#define NETIF_F_HW_VLAN_ALL (NETIF_F_HW_VLAN_CTAG_RX | \
+ NETIF_F_HW_VLAN_STAG_RX | \
+ NETIF_F_HW_VLAN_CTAG_TX | \
+ NETIF_F_HW_VLAN_STAG_TX | \
+ NETIF_F_HW_VLAN_CTAG_FILTER | \
+ NETIF_F_HW_VLAN_STAG_FILTER)
+
+/* MMC control defines */
+#define SXGBE_MMC_CTRL_CNT_FRZ 0x00000008
+
+/* SXGBE HW ADDR regs */
+#define SXGBE_ADDR_HIGH(reg) (((reg > 15) ? 0x00000800 : 0x00000040) + \
+ (reg * 8))
+#define SXGBE_ADDR_LOW(reg) (((reg > 15) ? 0x00000804 : 0x00000044) + \
+ (reg * 8))
+#define SXGBE_MAX_PERFECT_ADDRESSES 32 /* Maximum unicast perfect filtering */
+#define SXGBE_FRAME_FILTER 0x00000004 /* Frame Filter */
+
+/* SXGBE Frame Filter defines */
+#define SXGBE_FRAME_FILTER_PR 0x00000001 /* Promiscuous Mode */
+#define SXGBE_FRAME_FILTER_HUC 0x00000002 /* Hash Unicast */
+#define SXGBE_FRAME_FILTER_HMC 0x00000004 /* Hash Multicast */
+#define SXGBE_FRAME_FILTER_DAIF 0x00000008 /* DA Inverse Filtering */
+#define SXGBE_FRAME_FILTER_PM 0x00000010 /* Pass all multicast */
+#define SXGBE_FRAME_FILTER_DBF 0x00000020 /* Disable Broadcast frames */
+#define SXGBE_FRAME_FILTER_SAIF 0x00000100 /* Inverse Filtering */
+#define SXGBE_FRAME_FILTER_SAF 0x00000200 /* Source Address Filter */
+#define SXGBE_FRAME_FILTER_HPF 0x00000400 /* Hash or perfect Filter */
+#define SXGBE_FRAME_FILTER_RA 0x80000000 /* Receive all mode */
+
+#define SXGBE_HASH_TABLE_SIZE 64
+#define SXGBE_HASH_HIGH 0x00000008 /* Multicast Hash Table High */
+#define SXGBE_HASH_LOW 0x0000000c /* Multicast Hash Table Low */
+
+#define SXGBE_HI_REG_AE 0x80000000
+
+/* Minimum and maximum MTU */
+#define MIN_MTU 68
+#define MAX_MTU 9000
+
+#define SXGBE_FOR_EACH_QUEUE(max_queues, queue_num) \
+ for (queue_num = 0; queue_num < max_queues; queue_num++)
+
+#define DRV_VERSION "1.0.0"
+
+#define SXGBE_MAX_RX_CHANNELS 16
+#define SXGBE_MAX_TX_CHANNELS 16
+
+#define START_MAC_REG_OFFSET 0x0000
+#define MAX_MAC_REG_OFFSET 0x0DFC
+#define START_MTL_REG_OFFSET 0x1000
+#define MAX_MTL_REG_OFFSET 0x18FC
+#define START_DMA_REG_OFFSET 0x3000
+#define MAX_DMA_REG_OFFSET 0x38FC
+
+#define REG_SPACE_SIZE 0x2000
+
+/* sxgbe statistics counters */
+struct sxgbe_extra_stats {
+ /* TX/RX IRQ events */
+ unsigned long tx_underflow_irq;
+ unsigned long tx_process_stopped_irq;
+ unsigned long tx_ctxt_desc_err;
+ unsigned long tx_threshold;
+ unsigned long rx_threshold;
+ unsigned long tx_pkt_n;
+ unsigned long rx_pkt_n;
+ unsigned long normal_irq_n;
+ unsigned long tx_normal_irq_n;
+ unsigned long rx_normal_irq_n;
+ unsigned long napi_poll;
+ unsigned long tx_clean;
+ unsigned long tx_reset_ic_bit;
+ unsigned long rx_process_stopped_irq;
+ unsigned long rx_underflow_irq;
+
+ /* Bus access errors */
+ unsigned long fatal_bus_error_irq;
+ unsigned long tx_read_transfer_err;
+ unsigned long tx_write_transfer_err;
+ unsigned long tx_desc_access_err;
+ unsigned long tx_buffer_access_err;
+ unsigned long tx_data_transfer_err;
+ unsigned long rx_read_transfer_err;
+ unsigned long rx_write_transfer_err;
+ unsigned long rx_desc_access_err;
+ unsigned long rx_buffer_access_err;
+ unsigned long rx_data_transfer_err;
+
+ /* EEE-LPI stats */
+ unsigned long tx_lpi_entry_n;
+ unsigned long tx_lpi_exit_n;
+ unsigned long rx_lpi_entry_n;
+ unsigned long rx_lpi_exit_n;
+ unsigned long eee_wakeup_error_n;
+
+ /* RX specific */
+ /* L2 error */
+ unsigned long rx_code_gmii_err;
+ unsigned long rx_watchdog_err;
+ unsigned long rx_crc_err;
+ unsigned long rx_gaint_pkt_err;
+ unsigned long ip_hdr_err;
+ unsigned long ip_payload_err;
+ unsigned long overflow_error;
+
+ /* L2 Pkt type */
+ unsigned long len_pkt;
+ unsigned long mac_ctl_pkt;
+ unsigned long dcb_ctl_pkt;
+ unsigned long arp_pkt;
+ unsigned long oam_pkt;
+ unsigned long untag_okt;
+ unsigned long other_pkt;
+ unsigned long svlan_tag_pkt;
+ unsigned long cvlan_tag_pkt;
+ unsigned long dvlan_ocvlan_icvlan_pkt;
+ unsigned long dvlan_osvlan_isvlan_pkt;
+ unsigned long dvlan_osvlan_icvlan_pkt;
+ unsigned long dvan_ocvlan_icvlan_pkt;
+
+ /* L3/L4 Pkt type */
+ unsigned long not_ip_pkt;
+ unsigned long ip4_tcp_pkt;
+ unsigned long ip4_udp_pkt;
+ unsigned long ip4_icmp_pkt;
+ unsigned long ip4_unknown_pkt;
+ unsigned long ip6_tcp_pkt;
+ unsigned long ip6_udp_pkt;
+ unsigned long ip6_icmp_pkt;
+ unsigned long ip6_unknown_pkt;
+
+ /* Filter specific */
+ unsigned long vlan_filter_match;
+ unsigned long sa_filter_fail;
+ unsigned long da_filter_fail;
+ unsigned long hash_filter_pass;
+ unsigned long l3_filter_match;
+ unsigned long l4_filter_match;
+
+ /* RX context specific */
+ unsigned long timestamp_dropped;
+ unsigned long rx_msg_type_no_ptp;
+ unsigned long rx_ptp_type_sync;
+ unsigned long rx_ptp_type_follow_up;
+ unsigned long rx_ptp_type_delay_req;
+ unsigned long rx_ptp_type_delay_resp;
+ unsigned long rx_ptp_type_pdelay_req;
+ unsigned long rx_ptp_type_pdelay_resp;
+ unsigned long rx_ptp_type_pdelay_follow_up;
+ unsigned long rx_ptp_announce;
+ unsigned long rx_ptp_mgmt;
+ unsigned long rx_ptp_signal;
+ unsigned long rx_ptp_resv_msg_type;
+};
+
+struct mac_link {
+ int port;
+ int duplex;
+ int speed;
+};
+
+struct mii_regs {
+ unsigned int addr; /* MII Address */
+ unsigned int data; /* MII Data */
+};
+
+struct sxgbe_core_ops {
+ /* MAC core initialization */
+ void (*core_init)(void __iomem *ioaddr);
+ /* Dump MAC registers */
+ void (*dump_regs)(void __iomem *ioaddr);
+ /* Handle extra events on specific interrupts hw dependent */
+ int (*host_irq_status)(void __iomem *ioaddr,
+ struct sxgbe_extra_stats *x);
+ /* Set power management mode (e.g. magic frame) */
+ void (*pmt)(void __iomem *ioaddr, unsigned long mode);
+ /* Set/Get Unicast MAC addresses */
+ void (*set_umac_addr)(void __iomem *ioaddr, unsigned char *addr,
+ unsigned int reg_n);
+ void (*get_umac_addr)(void __iomem *ioaddr, unsigned char *addr,
+ unsigned int reg_n);
+ void (*enable_rx)(void __iomem *ioaddr, bool enable);
+ void (*enable_tx)(void __iomem *ioaddr, bool enable);
+
+ /* controller version specific operations */
+ int (*get_controller_version)(void __iomem *ioaddr);
+
+ /* If supported then get the optional core features */
+ unsigned int (*get_hw_feature)(void __iomem *ioaddr,
+ unsigned char feature_index);
+ /* adjust SXGBE speed */
+ void (*set_speed)(void __iomem *ioaddr, unsigned char speed);
+
+ /* EEE-LPI specific operations */
+ void (*set_eee_mode)(void __iomem *ioaddr);
+ void (*reset_eee_mode)(void __iomem *ioaddr);
+ void (*set_eee_timer)(void __iomem *ioaddr, const int ls,
+ const int tw);
+ void (*set_eee_pls)(void __iomem *ioaddr, const int link);
+
+ /* Enable disable checksum offload operations */
+ void (*enable_rx_csum)(void __iomem *ioaddr);
+ void (*disable_rx_csum)(void __iomem *ioaddr);
+};
+
+const struct sxgbe_core_ops *sxgbe_get_core_ops(void);
+
+struct sxgbe_ops {
+ const struct sxgbe_core_ops *mac;
+ const struct sxgbe_desc_ops *desc;
+ const struct sxgbe_dma_ops *dma;
+ const struct sxgbe_mtl_ops *mtl;
+ struct mii_regs mii; /* MII register Addresses */
+ struct mac_link link;
+ unsigned int ctrl_uid;
+ unsigned int ctrl_id;
+};
+
+/* SXGBE private data structures */
+struct sxgbe_tx_queue {
+ unsigned int irq_no;
+ struct sxgbe_priv_data *priv_ptr;
+ struct sxgbe_tx_norm_desc *dma_tx;
+ dma_addr_t dma_tx_phy;
+ dma_addr_t *tx_skbuff_dma;
+ struct sk_buff **tx_skbuff;
+ struct timer_list txtimer;
+ spinlock_t tx_lock; /* lock for tx queues */
+ unsigned int cur_tx;
+ unsigned int dirty_tx;
+ u32 tx_count_frames;
+ u32 tx_coal_frames;
+ u32 tx_coal_timer;
+ int hwts_tx_en;
+ u16 prev_mss;
+ u8 queue_no;
+};
+
+struct sxgbe_rx_queue {
+ struct sxgbe_priv_data *priv_ptr;
+ struct sxgbe_rx_norm_desc *dma_rx;
+ struct sk_buff **rx_skbuff;
+ unsigned int cur_rx;
+ unsigned int dirty_rx;
+ unsigned int irq_no;
+ u32 rx_riwt;
+ dma_addr_t *rx_skbuff_dma;
+ dma_addr_t dma_rx_phy;
+ u8 queue_no;
+};
+
+/* SXGBE HW capabilities */
+struct sxgbe_hw_features {
+ /****** CAP [0] *******/
+ unsigned int pmt_remote_wake_up;
+ unsigned int pmt_magic_frame;
+ /* IEEE 1588-2008 */
+ unsigned int atime_stamp;
+
+ unsigned int eee;
+
+ unsigned int tx_csum_offload;
+ unsigned int rx_csum_offload;
+ unsigned int multi_macaddr;
+ unsigned int tstamp_srcselect;
+ unsigned int sa_vlan_insert;
+
+ /****** CAP [1] *******/
+ unsigned int rxfifo_size;
+ unsigned int txfifo_size;
+ unsigned int atstmap_hword;
+ unsigned int dcb_enable;
+ unsigned int splithead_enable;
+ unsigned int tcpseg_offload;
+ unsigned int debug_mem;
+ unsigned int rss_enable;
+ unsigned int hash_tsize;
+ unsigned int l3l4_filer_size;
+
+ /* This value is in bytes and
+ * as mentioned in HW features
+ * of SXGBE data book
+ */
+ unsigned int rx_mtl_qsize;
+ unsigned int tx_mtl_qsize;
+
+ /****** CAP [2] *******/
+ /* TX and RX number of channels */
+ unsigned int rx_mtl_queues;
+ unsigned int tx_mtl_queues;
+ unsigned int rx_dma_channels;
+ unsigned int tx_dma_channels;
+ unsigned int pps_output_count;
+ unsigned int aux_input_count;
+};
+
+struct sxgbe_priv_data {
+ /* DMA descriptos */
+ struct sxgbe_tx_queue *txq[SXGBE_TX_QUEUES];
+ struct sxgbe_rx_queue *rxq[SXGBE_RX_QUEUES];
+ u8 cur_rx_qnum;
+
+ unsigned int dma_tx_size;
+ unsigned int dma_rx_size;
+ unsigned int dma_buf_sz;
+ u32 rx_riwt;
+
+ struct napi_struct napi;
+
+ void __iomem *ioaddr;
+ struct net_device *dev;
+ struct device *device;
+ struct sxgbe_ops *hw; /* sxgbe specific ops */
+ int no_csum_insertion;
+ int irq;
+ int rxcsum_insertion;
+ spinlock_t stats_lock; /* lock for tx/rx statatics */
+
+ struct phy_device *phydev;
+ int oldlink;
+ int speed;
+ int oldduplex;
+ struct mii_bus *mii;
+ int mii_irq[PHY_MAX_ADDR];
+ u8 rx_pause;
+ u8 tx_pause;
+
+ struct sxgbe_extra_stats xstats;
+ struct sxgbe_plat_data *plat;
+ struct sxgbe_hw_features hw_cap;
+
+ u32 msg_enable;
+
+ struct clk *sxgbe_clk;
+ int clk_csr;
+ unsigned int mode;
+ unsigned int default_addend;
+
+ /* advanced time stamp support */
+ u32 adv_ts;
+ int use_riwt;
+ struct ptp_clock *ptp_clock;
+
+ /* tc control */
+ int tx_tc;
+ int rx_tc;
+ /* EEE-LPI specific members */
+ struct timer_list eee_ctrl_timer;
+ bool tx_path_in_lpi_mode;
+ int lpi_irq;
+ int eee_enabled;
+ int eee_active;
+ int tx_lpi_timer;
+};
+
+/* Function prototypes */
+struct sxgbe_priv_data *sxgbe_drv_probe(struct device *device,
+ struct sxgbe_plat_data *plat_dat,
+ void __iomem *addr);
+int sxgbe_drv_remove(struct net_device *ndev);
+void sxgbe_set_ethtool_ops(struct net_device *netdev);
+int sxgbe_mdio_unregister(struct net_device *ndev);
+int sxgbe_mdio_register(struct net_device *ndev);
+int sxgbe_register_platform(void);
+void sxgbe_unregister_platform(void);
+
+#ifdef CONFIG_PM
+int sxgbe_suspend(struct net_device *ndev);
+int sxgbe_resume(struct net_device *ndev);
+int sxgbe_freeze(struct net_device *ndev);
+int sxgbe_restore(struct net_device *ndev);
+#endif /* CONFIG_PM */
+
+const struct sxgbe_mtl_ops *sxgbe_get_mtl_ops(void);
+
+void sxgbe_disable_eee_mode(struct sxgbe_priv_data * const priv);
+bool sxgbe_eee_init(struct sxgbe_priv_data * const priv);
+#endif /* __SXGBE_COMMON_H__ */
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c
new file mode 100644
index 0000000..66d4a74
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c
@@ -0,0 +1,262 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/export.h>
+#include <linux/io.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_reg.h"
+
+/* MAC core initialization */
+static void sxgbe_core_init(void __iomem *ioaddr)
+{
+ u32 regval;
+
+ /* TX configuration */
+ regval = readl(ioaddr + SXGBE_CORE_TX_CONFIG_REG);
+ /* Other configurable parameters IFP, IPG, ISR, ISM
+ * needs to be set if needed
+ */
+ regval |= SXGBE_TX_JABBER_DISABLE;
+ writel(regval, ioaddr + SXGBE_CORE_TX_CONFIG_REG);
+
+ /* RX configuration */
+ regval = readl(ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+ /* Other configurable parameters CST, SPEN, USP, GPSLCE
+ * WD, LM, S2KP, HDSMS, GPSL, ELEN, ARPEN needs to be
+ * set if needed
+ */
+ regval |= SXGBE_RX_JUMBPKT_ENABLE | SXGBE_RX_ACS_ENABLE;
+ writel(regval, ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+}
+
+/* Dump MAC registers */
+static void sxgbe_core_dump_regs(void __iomem *ioaddr)
+{
+}
+
+static int sxgbe_get_lpi_status(void __iomem *ioaddr, const u32 irq_status)
+{
+ int status = 0;
+ int lpi_status;
+
+ /* Reading this register shall clear all the LPI status bits */
+ lpi_status = readl(ioaddr + SXGBE_CORE_LPI_CTRL_STATUS);
+
+ if (lpi_status & LPI_CTRL_STATUS_TLPIEN)
+ status |= TX_ENTRY_LPI_MODE;
+ if (lpi_status & LPI_CTRL_STATUS_TLPIEX)
+ status |= TX_EXIT_LPI_MODE;
+ if (lpi_status & LPI_CTRL_STATUS_RLPIEN)
+ status |= RX_ENTRY_LPI_MODE;
+ if (lpi_status & LPI_CTRL_STATUS_RLPIEX)
+ status |= RX_EXIT_LPI_MODE;
+
+ return status;
+}
+
+/* Handle extra events on specific interrupts hw dependent */
+static int sxgbe_core_host_irq_status(void __iomem *ioaddr,
+ struct sxgbe_extra_stats *x)
+{
+ int irq_status, status = 0;
+
+ irq_status = readl(ioaddr + SXGBE_CORE_INT_STATUS_REG);
+
+ if (unlikely(irq_status & LPI_INT_STATUS))
+ status |= sxgbe_get_lpi_status(ioaddr, irq_status);
+
+ return status;
+}
+
+/* Set power management mode (e.g. magic frame) */
+static void sxgbe_core_pmt(void __iomem *ioaddr, unsigned long mode)
+{
+}
+
+/* Set/Get Unicast MAC addresses */
+static void sxgbe_core_set_umac_addr(void __iomem *ioaddr, unsigned char *addr,
+ unsigned int reg_n)
+{
+ u32 high_word, low_word;
+
+ high_word = (addr[5] << 8) || (addr[4]);
+ low_word = ((addr[3] << 24) || (addr[2] << 16) ||
+ (addr[1] << 8) || (addr[0]));
+ writel(high_word, ioaddr + SXGBE_CORE_ADD_HIGHOFFSET(reg_n));
+ writel(low_word, ioaddr + SXGBE_CORE_ADD_LOWOFFSET(reg_n));
+}
+
+static void sxgbe_core_get_umac_addr(void __iomem *ioaddr, unsigned char *addr,
+ unsigned int reg_n)
+{
+ u32 high_word, low_word;
+
+ high_word = readl(ioaddr + SXGBE_CORE_ADD_HIGHOFFSET(reg_n));
+ low_word = readl(ioaddr + SXGBE_CORE_ADD_LOWOFFSET(reg_n));
+
+ /* extract and assign address */
+ addr[5] = (high_word & 0x0000FF00) >> 8;
+ addr[4] = (high_word & 0x000000FF);
+ addr[3] = (low_word & 0xFF000000) >> 24;
+ addr[2] = (low_word & 0x00FF0000) >> 16;
+ addr[1] = (low_word & 0x0000FF00) >> 8;
+ addr[0] = (low_word & 0x000000FF);
+}
+
+static void sxgbe_enable_tx(void __iomem *ioaddr, bool enable)
+{
+ u32 tx_config;
+
+ tx_config = readl(ioaddr + SXGBE_CORE_TX_CONFIG_REG);
+ tx_config &= ~SXGBE_TX_ENABLE;
+
+ if (enable)
+ tx_config |= SXGBE_TX_ENABLE;
+ writel(tx_config, ioaddr + SXGBE_CORE_TX_CONFIG_REG);
+}
+
+static void sxgbe_enable_rx(void __iomem *ioaddr, bool enable)
+{
+ u32 rx_config;
+
+ rx_config = readl(ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+ rx_config &= ~SXGBE_RX_ENABLE;
+
+ if (enable)
+ rx_config |= SXGBE_RX_ENABLE;
+ writel(rx_config, ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+}
+
+static int sxgbe_get_controller_version(void __iomem *ioaddr)
+{
+ return readl(ioaddr + SXGBE_CORE_VERSION_REG);
+}
+
+/* If supported then get the optional core features */
+static unsigned int sxgbe_get_hw_feature(void __iomem *ioaddr,
+ unsigned char feature_index)
+{
+ return readl(ioaddr + (SXGBE_CORE_HW_FEA_REG(feature_index)));
+}
+
+static void sxgbe_core_set_speed(void __iomem *ioaddr, unsigned char speed)
+{
+ u32 tx_cfg = readl(ioaddr + SXGBE_CORE_TX_CONFIG_REG);
+
+ /* clear the speed bits */
+ tx_cfg &= ~0x60000000;
+ tx_cfg |= (speed << SXGBE_SPEED_LSHIFT);
+
+ /* set the speed */
+ writel(tx_cfg, ioaddr + SXGBE_CORE_TX_CONFIG_REG);
+}
+
+static void sxgbe_set_eee_mode(void __iomem *ioaddr)
+{
+ u32 ctrl;
+
+ /* Enable the LPI mode for transmit path with Tx automate bit set.
+ * When Tx Automate bit is set, MAC internally handles the entry
+ * to LPI mode after all outstanding and pending packets are
+ * transmitted.
+ */
+ ctrl = readl(ioaddr + SXGBE_CORE_LPI_CTRL_STATUS);
+ ctrl |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_TXA;
+ writel(ctrl, ioaddr + SXGBE_CORE_LPI_CTRL_STATUS);
+}
+
+static void sxgbe_reset_eee_mode(void __iomem *ioaddr)
+{
+ u32 ctrl;
+
+ ctrl = readl(ioaddr + SXGBE_CORE_LPI_CTRL_STATUS);
+ ctrl &= ~(LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_TXA);
+ writel(ctrl, ioaddr + SXGBE_CORE_LPI_CTRL_STATUS);
+}
+
+static void sxgbe_set_eee_pls(void __iomem *ioaddr, const int link)
+{
+ u32 ctrl;
+
+ ctrl = readl(ioaddr + SXGBE_CORE_LPI_CTRL_STATUS);
+
+ /* If the PHY link status is UP then set PLS */
+ if (link)
+ ctrl |= LPI_CTRL_STATUS_PLS;
+ else
+ ctrl &= ~LPI_CTRL_STATUS_PLS;
+
+ writel(ctrl, ioaddr + SXGBE_CORE_LPI_CTRL_STATUS);
+}
+
+static void sxgbe_set_eee_timer(void __iomem *ioaddr,
+ const int ls, const int tw)
+{
+ int value = ((tw & 0xffff)) | ((ls & 0x7ff) << 16);
+
+ /* Program the timers in the LPI timer control register:
+ * LS: minimum time (ms) for which the link
+ * status from PHY should be ok before transmitting
+ * the LPI pattern.
+ * TW: minimum time (us) for which the core waits
+ * after it has stopped transmitting the LPI pattern.
+ */
+ writel(value, ioaddr + SXGBE_CORE_LPI_TIMER_CTRL);
+}
+
+static void sxgbe_enable_rx_csum(void __iomem *ioaddr)
+{
+ u32 ctrl;
+
+ ctrl = readl(ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+ ctrl |= SXGBE_RX_CSUMOFFLOAD_ENABLE;
+ writel(ctrl, ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+}
+
+static void sxgbe_disable_rx_csum(void __iomem *ioaddr)
+{
+ u32 ctrl;
+
+ ctrl = readl(ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+ ctrl &= ~SXGBE_RX_CSUMOFFLOAD_ENABLE;
+ writel(ctrl, ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+}
+
+const struct sxgbe_core_ops core_ops = {
+ .core_init = sxgbe_core_init,
+ .dump_regs = sxgbe_core_dump_regs,
+ .host_irq_status = sxgbe_core_host_irq_status,
+ .pmt = sxgbe_core_pmt,
+ .set_umac_addr = sxgbe_core_set_umac_addr,
+ .get_umac_addr = sxgbe_core_get_umac_addr,
+ .enable_rx = sxgbe_enable_rx,
+ .enable_tx = sxgbe_enable_tx,
+ .get_controller_version = sxgbe_get_controller_version,
+ .get_hw_feature = sxgbe_get_hw_feature,
+ .set_speed = sxgbe_core_set_speed,
+ .set_eee_mode = sxgbe_set_eee_mode,
+ .reset_eee_mode = sxgbe_reset_eee_mode,
+ .set_eee_timer = sxgbe_set_eee_timer,
+ .set_eee_pls = sxgbe_set_eee_pls,
+ .enable_rx_csum = sxgbe_enable_rx_csum,
+ .disable_rx_csum = sxgbe_disable_rx_csum,
+};
+
+const struct sxgbe_core_ops *sxgbe_get_core_ops(void)
+{
+ return &core_ops;
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.c
new file mode 100644
index 0000000..e896dbb
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.c
@@ -0,0 +1,515 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/bitops.h>
+#include <linux/export.h>
+#include <linux/io.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_dma.h"
+#include "sxgbe_desc.h"
+
+/* DMA TX descriptor ring initialization */
+static void sxgbe_init_tx_desc(struct sxgbe_tx_norm_desc *p)
+{
+ p->tdes23.tx_rd_des23.own_bit = 0;
+}
+
+static void sxgbe_tx_desc_enable_tse(struct sxgbe_tx_norm_desc *p, u8 is_tse,
+ u32 total_hdr_len, u32 tcp_hdr_len,
+ u32 tcp_payload_len)
+{
+ p->tdes23.tx_rd_des23.tse_bit = is_tse;
+ p->tdes23.tx_rd_des23.buf1_size = total_hdr_len;
+ p->tdes23.tx_rd_des23.tcp_hdr_len = tcp_hdr_len / 4;
+ p->tdes23.tx_rd_des23.tx_pkt_len.tcp_payload_len = tcp_payload_len;
+}
+
+/* Assign buffer lengths for descriptor */
+static void sxgbe_prepare_tx_desc(struct sxgbe_tx_norm_desc *p, u8 is_fd,
+ int buf1_len, int pkt_len, int cksum)
+{
+ p->tdes23.tx_rd_des23.first_desc = is_fd;
+ p->tdes23.tx_rd_des23.buf1_size = buf1_len;
+
+ p->tdes23.tx_rd_des23.tx_pkt_len.cksum_pktlen.total_pkt_len = pkt_len;
+
+ if (cksum)
+ p->tdes23.tx_rd_des23.tx_pkt_len.cksum_pktlen.cksum_ctl = cic_full;
+}
+
+/* Set VLAN control information */
+static void sxgbe_tx_vlanctl_desc(struct sxgbe_tx_norm_desc *p, int vlan_ctl)
+{
+ p->tdes23.tx_rd_des23.vlan_tag_ctl = vlan_ctl;
+}
+
+/* Set the owner of Normal descriptor */
+static void sxgbe_set_tx_owner(struct sxgbe_tx_norm_desc *p)
+{
+ p->tdes23.tx_rd_des23.own_bit = 1;
+}
+
+/* Get the owner of Normal descriptor */
+static int sxgbe_get_tx_owner(struct sxgbe_tx_norm_desc *p)
+{
+ return p->tdes23.tx_rd_des23.own_bit;
+}
+
+/* Invoked by the xmit function to close the tx descriptor */
+static void sxgbe_close_tx_desc(struct sxgbe_tx_norm_desc *p)
+{
+ p->tdes23.tx_rd_des23.last_desc = 1;
+ p->tdes23.tx_rd_des23.int_on_com = 1;
+}
+
+/* Clean the tx descriptor as soon as the tx irq is received */
+static void sxgbe_release_tx_desc(struct sxgbe_tx_norm_desc *p)
+{
+ memset(p, 0, sizeof(*p));
+}
+
+/* Clear interrupt on tx frame completion. When this bit is
+ * set an interrupt happens as soon as the frame is transmitted
+ */
+static void sxgbe_clear_tx_ic(struct sxgbe_tx_norm_desc *p)
+{
+ p->tdes23.tx_rd_des23.int_on_com = 0;
+}
+
+/* Last tx segment reports the transmit status */
+static int sxgbe_get_tx_ls(struct sxgbe_tx_norm_desc *p)
+{
+ return p->tdes23.tx_rd_des23.last_desc;
+}
+
+/* Get the buffer size from the descriptor */
+static int sxgbe_get_tx_len(struct sxgbe_tx_norm_desc *p)
+{
+ return p->tdes23.tx_rd_des23.buf1_size;
+}
+
+/* Set tx timestamp enable bit */
+static void sxgbe_tx_enable_tstamp(struct sxgbe_tx_norm_desc *p)
+{
+ p->tdes23.tx_rd_des23.timestmp_enable = 1;
+}
+
+/* get tx timestamp status */
+static int sxgbe_get_tx_timestamp_status(struct sxgbe_tx_norm_desc *p)
+{
+ return p->tdes23.tx_rd_des23.timestmp_enable;
+}
+
+/* TX Context Descripto Specific */
+static void sxgbe_tx_ctxt_desc_set_ctxt(struct sxgbe_tx_ctxt_desc *p)
+{
+ p->ctxt_bit = 1;
+}
+
+/* Set the owner of TX context descriptor */
+static void sxgbe_tx_ctxt_desc_set_owner(struct sxgbe_tx_ctxt_desc *p)
+{
+ p->own_bit = 1;
+}
+
+/* Get the owner of TX context descriptor */
+static int sxgbe_tx_ctxt_desc_get_owner(struct sxgbe_tx_ctxt_desc *p)
+{
+ return p->own_bit;
+}
+
+/* Set TX mss in TX context Descriptor */
+static void sxgbe_tx_ctxt_desc_set_mss(struct sxgbe_tx_ctxt_desc *p, u16 mss)
+{
+ p->maxseg_size = mss;
+}
+
+/* Get TX mss from TX context Descriptor */
+static int sxgbe_tx_ctxt_desc_get_mss(struct sxgbe_tx_ctxt_desc *p)
+{
+ return p->maxseg_size;
+}
+
+/* Set TX tcmssv in TX context Descriptor */
+static void sxgbe_tx_ctxt_desc_set_tcmssv(struct sxgbe_tx_ctxt_desc *p)
+{
+ p->tcmssv = 1;
+}
+
+/* Reset TX ostc in TX context Descriptor */
+static void sxgbe_tx_ctxt_desc_reset_ostc(struct sxgbe_tx_ctxt_desc *p)
+{
+ p->ostc = 0;
+}
+
+/* Set IVLAN information */
+static void sxgbe_tx_ctxt_desc_set_ivlantag(struct sxgbe_tx_ctxt_desc *p,
+ int is_ivlanvalid, int ivlan_tag,
+ int ivlan_ctl)
+{
+ if (is_ivlanvalid) {
+ p->ivlan_tag_valid = is_ivlanvalid;
+ p->ivlan_tag = ivlan_tag;
+ p->ivlan_tag_ctl = ivlan_ctl;
+ }
+}
+
+/* Return IVLAN Tag */
+static int sxgbe_tx_ctxt_desc_get_ivlantag(struct sxgbe_tx_ctxt_desc *p)
+{
+ return p->ivlan_tag;
+}
+
+/* Set VLAN Tag */
+static void sxgbe_tx_ctxt_desc_set_vlantag(struct sxgbe_tx_ctxt_desc *p,
+ int is_vlanvalid, int vlan_tag)
+{
+ if (is_vlanvalid) {
+ p->vltag_valid = is_vlanvalid;
+ p->vlan_tag = vlan_tag;
+ }
+}
+
+/* Return VLAN Tag */
+static int sxgbe_tx_ctxt_desc_get_vlantag(struct sxgbe_tx_ctxt_desc *p)
+{
+ return p->vlan_tag;
+}
+
+/* Set Time stamp */
+static void sxgbe_tx_ctxt_desc_set_tstamp(struct sxgbe_tx_ctxt_desc *p,
+ u8 ostc_enable, u64 tstamp)
+{
+ if (ostc_enable) {
+ p->ostc = ostc_enable;
+ p->tstamp_lo = (u32) tstamp;
+ p->tstamp_hi = (u32) (tstamp>>32);
+ }
+}
+/* Close TX context descriptor */
+static void sxgbe_tx_ctxt_desc_close(struct sxgbe_tx_ctxt_desc *p)
+{
+ p->own_bit = 1;
+}
+
+/* WB status of context descriptor */
+static int sxgbe_tx_ctxt_desc_get_cde(struct sxgbe_tx_ctxt_desc *p)
+{
+ return p->ctxt_desc_err;
+}
+
+/* DMA RX descriptor ring initialization */
+static void sxgbe_init_rx_desc(struct sxgbe_rx_norm_desc *p, int disable_rx_ic,
+ int mode, int end)
+{
+ p->rdes23.rx_rd_des23.own_bit = 1;
+ if (disable_rx_ic)
+ p->rdes23.rx_rd_des23.int_on_com = disable_rx_ic;
+}
+
+/* Get RX own bit */
+static int sxgbe_get_rx_owner(struct sxgbe_rx_norm_desc *p)
+{
+ return p->rdes23.rx_rd_des23.own_bit;
+}
+
+/* Set RX own bit */
+static void sxgbe_set_rx_owner(struct sxgbe_rx_norm_desc *p)
+{
+ p->rdes23.rx_rd_des23.own_bit = 1;
+}
+
+/* Get the receive frame size */
+static int sxgbe_get_rx_frame_len(struct sxgbe_rx_norm_desc *p)
+{
+ return p->rdes23.rx_wb_des23.pkt_len;
+}
+
+/* Return first Descriptor status */
+static int sxgbe_get_rx_fd_status(struct sxgbe_rx_norm_desc *p)
+{
+ return p->rdes23.rx_wb_des23.first_desc;
+}
+
+/* Return Last Descriptor status */
+static int sxgbe_get_rx_ld_status(struct sxgbe_rx_norm_desc *p)
+{
+ return p->rdes23.rx_wb_des23.last_desc;
+}
+
+
+/* Return the RX status looking at the WB fields */
+static int sxgbe_rx_wbstatus(struct sxgbe_rx_norm_desc *p,
+ struct sxgbe_extra_stats *x, int *checksum)
+{
+ int status = 0;
+
+ *checksum = CHECKSUM_UNNECESSARY;
+ if (p->rdes23.rx_wb_des23.err_summary) {
+ switch (p->rdes23.rx_wb_des23.err_l2_type) {
+ case RX_GMII_ERR:
+ status = -EINVAL;
+ x->rx_code_gmii_err++;
+ break;
+ case RX_WATCHDOG_ERR:
+ status = -EINVAL;
+ x->rx_watchdog_err++;
+ break;
+ case RX_CRC_ERR:
+ status = -EINVAL;
+ x->rx_crc_err++;
+ break;
+ case RX_GAINT_ERR:
+ status = -EINVAL;
+ x->rx_gaint_pkt_err++;
+ break;
+ case RX_IP_HDR_ERR:
+ *checksum = CHECKSUM_NONE;
+ x->ip_hdr_err++;
+ break;
+ case RX_PAYLOAD_ERR:
+ *checksum = CHECKSUM_NONE;
+ x->ip_payload_err++;
+ break;
+ case RX_OVERFLOW_ERR:
+ status = -EINVAL;
+ x->overflow_error++;
+ break;
+ default:
+ pr_err("Invalid Error type\n");
+ break;
+ }
+ } else {
+ switch (p->rdes23.rx_wb_des23.err_l2_type) {
+ case RX_LEN_PKT:
+ x->len_pkt++;
+ break;
+ case RX_MACCTL_PKT:
+ x->mac_ctl_pkt++;
+ break;
+ case RX_DCBCTL_PKT:
+ x->dcb_ctl_pkt++;
+ break;
+ case RX_ARP_PKT:
+ x->arp_pkt++;
+ break;
+ case RX_OAM_PKT:
+ x->oam_pkt++;
+ break;
+ case RX_UNTAG_PKT:
+ x->untag_okt++;
+ break;
+ case RX_OTHER_PKT:
+ x->other_pkt++;
+ break;
+ case RX_SVLAN_PKT:
+ x->svlan_tag_pkt++;
+ break;
+ case RX_CVLAN_PKT:
+ x->cvlan_tag_pkt++;
+ break;
+ case RX_DVLAN_OCVLAN_ICVLAN_PKT:
+ x->dvlan_ocvlan_icvlan_pkt++;
+ break;
+ case RX_DVLAN_OSVLAN_ISVLAN_PKT:
+ x->dvlan_osvlan_isvlan_pkt++;
+ break;
+ case RX_DVLAN_OSVLAN_ICVLAN_PKT:
+ x->dvlan_osvlan_icvlan_pkt++;
+ break;
+ case RX_DVLAN_OCVLAN_ISVLAN_PKT:
+ x->dvlan_ocvlan_icvlan_pkt++;
+ break;
+ default:
+ pr_err("Invalid L2 Packet type\n");
+ break;
+ }
+ }
+
+ /* L3/L4 Pkt type */
+ switch (p->rdes23.rx_wb_des23.layer34_pkt_type) {
+ case RX_NOT_IP_PKT:
+ x->not_ip_pkt++;
+ break;
+ case RX_IPV4_TCP_PKT:
+ x->ip4_tcp_pkt++;
+ break;
+ case RX_IPV4_UDP_PKT:
+ x->ip4_udp_pkt++;
+ break;
+ case RX_IPV4_ICMP_PKT:
+ x->ip4_icmp_pkt++;
+ break;
+ case RX_IPV4_UNKNOWN_PKT:
+ x->ip4_unknown_pkt++;
+ break;
+ case RX_IPV6_TCP_PKT:
+ x->ip6_tcp_pkt++;
+ break;
+ case RX_IPV6_UDP_PKT:
+ x->ip6_udp_pkt++;
+ break;
+ case RX_IPV6_ICMP_PKT:
+ x->ip6_icmp_pkt++;
+ break;
+ case RX_IPV6_UNKNOWN_PKT:
+ x->ip6_unknown_pkt++;
+ break;
+ default:
+ pr_err("Invalid L3/L4 Packet type\n");
+ break;
+ }
+
+ /* Filter */
+ if (p->rdes23.rx_wb_des23.vlan_filter_match)
+ x->vlan_filter_match++;
+
+ if (p->rdes23.rx_wb_des23.sa_filter_fail) {
+ status = -EINVAL;
+ x->sa_filter_fail++;
+ }
+ if (p->rdes23.rx_wb_des23.da_filter_fail) {
+ status = -EINVAL;
+ x->da_filter_fail++;
+ }
+ if (p->rdes23.rx_wb_des23.hash_filter_pass)
+ x->hash_filter_pass++;
+
+ if (p->rdes23.rx_wb_des23.l3_filter_match)
+ x->l3_filter_match++;
+
+ if (p->rdes23.rx_wb_des23.l4_filter_match)
+ x->l4_filter_match++;
+
+ return status;
+}
+
+/* Get own bit of context descriptor */
+static int sxgbe_get_rx_ctxt_owner(struct sxgbe_rx_ctxt_desc *p)
+{
+ return p->own_bit;
+}
+
+/* Set own bit for context descriptor */
+static void sxgbe_set_ctxt_rx_owner(struct sxgbe_rx_ctxt_desc *p)
+{
+ p->own_bit = 1;
+}
+
+
+/* Return the reception status looking at Context control information */
+static void sxgbe_rx_ctxt_wbstatus(struct sxgbe_rx_ctxt_desc *p,
+ struct sxgbe_extra_stats *x)
+{
+ if (p->tstamp_dropped)
+ x->timestamp_dropped++;
+
+ /* ptp */
+ if (p->ptp_msgtype == RX_NO_PTP)
+ x->rx_msg_type_no_ptp++;
+ else if (p->ptp_msgtype == RX_PTP_SYNC)
+ x->rx_ptp_type_sync++;
+ else if (p->ptp_msgtype == RX_PTP_FOLLOW_UP)
+ x->rx_ptp_type_follow_up++;
+ else if (p->ptp_msgtype == RX_PTP_DELAY_REQ)
+ x->rx_ptp_type_delay_req++;
+ else if (p->ptp_msgtype == RX_PTP_DELAY_RESP)
+ x->rx_ptp_type_delay_resp++;
+ else if (p->ptp_msgtype == RX_PTP_PDELAY_REQ)
+ x->rx_ptp_type_pdelay_req++;
+ else if (p->ptp_msgtype == RX_PTP_PDELAY_RESP)
+ x->rx_ptp_type_pdelay_resp++;
+ else if (p->ptp_msgtype == RX_PTP_PDELAY_FOLLOW_UP)
+ x->rx_ptp_type_pdelay_follow_up++;
+ else if (p->ptp_msgtype == RX_PTP_ANNOUNCE)
+ x->rx_ptp_announce++;
+ else if (p->ptp_msgtype == RX_PTP_MGMT)
+ x->rx_ptp_mgmt++;
+ else if (p->ptp_msgtype == RX_PTP_SIGNAL)
+ x->rx_ptp_signal++;
+ else if (p->ptp_msgtype == RX_PTP_RESV_MSG)
+ x->rx_ptp_resv_msg_type++;
+}
+
+/* Get rx timestamp status */
+static int sxgbe_get_rx_ctxt_tstamp_status(struct sxgbe_rx_ctxt_desc *p)
+{
+ if ((p->tstamp_hi == 0xffffffff) && (p->tstamp_lo == 0xffffffff)) {
+ pr_err("Time stamp corrupted\n");
+ return 0;
+ }
+
+ return p->tstamp_available;
+}
+
+
+static u64 sxgbe_get_rx_timestamp(struct sxgbe_rx_ctxt_desc *p)
+{
+ u64 ns;
+
+ ns = p->tstamp_lo;
+ ns |= ((u64)p->tstamp_hi) << 32;
+
+ return ns;
+}
+
+static const struct sxgbe_desc_ops desc_ops = {
+ .init_tx_desc = sxgbe_init_tx_desc,
+ .tx_desc_enable_tse = sxgbe_tx_desc_enable_tse,
+ .prepare_tx_desc = sxgbe_prepare_tx_desc,
+ .tx_vlanctl_desc = sxgbe_tx_vlanctl_desc,
+ .set_tx_owner = sxgbe_set_tx_owner,
+ .get_tx_owner = sxgbe_get_tx_owner,
+ .close_tx_desc = sxgbe_close_tx_desc,
+ .release_tx_desc = sxgbe_release_tx_desc,
+ .clear_tx_ic = sxgbe_clear_tx_ic,
+ .get_tx_ls = sxgbe_get_tx_ls,
+ .get_tx_len = sxgbe_get_tx_len,
+ .tx_enable_tstamp = sxgbe_tx_enable_tstamp,
+ .get_tx_timestamp_status = sxgbe_get_tx_timestamp_status,
+ .tx_ctxt_desc_set_ctxt = sxgbe_tx_ctxt_desc_set_ctxt,
+ .tx_ctxt_desc_set_owner = sxgbe_tx_ctxt_desc_set_owner,
+ .get_tx_ctxt_owner = sxgbe_tx_ctxt_desc_get_owner,
+ .tx_ctxt_desc_set_mss = sxgbe_tx_ctxt_desc_set_mss,
+ .tx_ctxt_desc_get_mss = sxgbe_tx_ctxt_desc_get_mss,
+ .tx_ctxt_desc_set_tcmssv = sxgbe_tx_ctxt_desc_set_tcmssv,
+ .tx_ctxt_desc_reset_ostc = sxgbe_tx_ctxt_desc_reset_ostc,
+ .tx_ctxt_desc_set_ivlantag = sxgbe_tx_ctxt_desc_set_ivlantag,
+ .tx_ctxt_desc_get_ivlantag = sxgbe_tx_ctxt_desc_get_ivlantag,
+ .tx_ctxt_desc_set_vlantag = sxgbe_tx_ctxt_desc_set_vlantag,
+ .tx_ctxt_desc_get_vlantag = sxgbe_tx_ctxt_desc_get_vlantag,
+ .tx_ctxt_set_tstamp = sxgbe_tx_ctxt_desc_set_tstamp,
+ .close_tx_ctxt_desc = sxgbe_tx_ctxt_desc_close,
+ .get_tx_ctxt_cde = sxgbe_tx_ctxt_desc_get_cde,
+ .init_rx_desc = sxgbe_init_rx_desc,
+ .get_rx_owner = sxgbe_get_rx_owner,
+ .set_rx_owner = sxgbe_set_rx_owner,
+ .get_rx_frame_len = sxgbe_get_rx_frame_len,
+ .get_rx_fd_status = sxgbe_get_rx_fd_status,
+ .get_rx_ld_status = sxgbe_get_rx_ld_status,
+ .rx_wbstatus = sxgbe_rx_wbstatus,
+ .get_rx_ctxt_owner = sxgbe_get_rx_ctxt_owner,
+ .set_rx_ctxt_owner = sxgbe_set_ctxt_rx_owner,
+ .rx_ctxt_wbstatus = sxgbe_rx_ctxt_wbstatus,
+ .get_rx_ctxt_tstamp_status = sxgbe_get_rx_ctxt_tstamp_status,
+ .get_timestamp = sxgbe_get_rx_timestamp,
+};
+
+const struct sxgbe_desc_ops *sxgbe_get_desc_ops(void)
+{
+ return &desc_ops;
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.h
new file mode 100644
index 0000000..838cb9f
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.h
@@ -0,0 +1,298 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SXGBE_DESC_H__
+#define __SXGBE_DESC_H__
+
+#define SXGBE_DESC_SIZE_BYTES 16
+
+/* forward declaration */
+struct sxgbe_extra_stats;
+
+/* Transmit checksum insertion control */
+enum tdes_csum_insertion {
+ cic_disabled = 0, /* Checksum Insertion Control */
+ cic_only_ip = 1, /* Only IP header */
+ /* IP header but pseudoheader is not calculated */
+ cic_no_pseudoheader = 2,
+ cic_full = 3, /* IP header and pseudoheader */
+};
+
+struct sxgbe_tx_norm_desc {
+ u64 tdes01; /* buf1 address */
+ union {
+ /* TX Read-Format Desc 2,3 */
+ struct {
+ /* TDES2 */
+ u32 buf1_size:14;
+ u32 vlan_tag_ctl:2;
+ u32 buf2_size:14;
+ u32 timestmp_enable:1;
+ u32 int_on_com:1;
+ /* TDES3 */
+ union {
+ u32 tcp_payload_len:18;
+ struct {
+ u32 total_pkt_len:15;
+ u32 reserved1:1;
+ u32 cksum_ctl:2;
+ } cksum_pktlen;
+ } tx_pkt_len;
+
+ u32 tse_bit:1;
+ u32 tcp_hdr_len:4;
+ u32 sa_insert_ctl:3;
+ u32 crc_pad_ctl:2;
+ u32 last_desc:1;
+ u32 first_desc:1;
+ u32 ctxt_bit:1;
+ u32 own_bit:1;
+ } tx_rd_des23;
+
+ /* tx write back Desc 2,3 */
+ struct {
+ /* WB TES2 */
+ u32 reserved1;
+ /* WB TES3 */
+ u32 reserved2:31;
+ u32 own_bit:1;
+ } tx_wb_des23;
+ } tdes23;
+};
+
+struct sxgbe_rx_norm_desc {
+ union {
+ u32 rdes0; /* buf1 address */
+ struct {
+ u32 out_vlan_tag:16;
+ u32 in_vlan_tag:16;
+ } wb_rx_des0;
+ } rd_wb_des0;
+
+ union {
+ u32 rdes1; /* buf2 address or buf1[63:32] */
+ u32 rss_hash; /* Write-back RX */
+ } rd_wb_des1;
+
+ union {
+ /* RX Read format Desc 2,3 */
+ struct{
+ /* RDES2 */
+ u32 buf2_addr;
+ /* RDES3 */
+ u32 buf2_hi_addr:30;
+ u32 int_on_com:1;
+ u32 own_bit:1;
+ } rx_rd_des23;
+
+ /* RX write back */
+ struct{
+ /* WB RDES2 */
+ u32 hdr_len:10;
+ u32 rdes2_reserved:2;
+ u32 elrd_val:1;
+ u32 iovt_sel:1;
+ u32 res_pkt:1;
+ u32 vlan_filter_match:1;
+ u32 sa_filter_fail:1;
+ u32 da_filter_fail:1;
+ u32 hash_filter_pass:1;
+ u32 macaddr_filter_match:8;
+ u32 l3_filter_match:1;
+ u32 l4_filter_match:1;
+ u32 l34_filter_num:3;
+
+ /* WB RDES3 */
+ u32 pkt_len:14;
+ u32 rdes3_reserved:1;
+ u32 err_summary:1;
+ u32 err_l2_type:4;
+ u32 layer34_pkt_type:4;
+ u32 no_coagulation_pkt:1;
+ u32 in_seq_pkt:1;
+ u32 rss_valid:1;
+ u32 context_des_avail:1;
+ u32 last_desc:1;
+ u32 first_desc:1;
+ u32 recv_context_desc:1;
+ u32 own_bit:1;
+ } rx_wb_des23;
+ } rdes23;
+};
+
+/* Context descriptor structure */
+struct sxgbe_tx_ctxt_desc {
+ u32 tstamp_lo;
+ u32 tstamp_hi;
+ u32 maxseg_size:15;
+ u32 reserved1:1;
+ u32 ivlan_tag:16;
+ u32 vlan_tag:16;
+ u32 vltag_valid:1;
+ u32 ivlan_tag_valid:1;
+ u32 ivlan_tag_ctl:2;
+ u32 reserved2:3;
+ u32 ctxt_desc_err:1;
+ u32 reserved3:2;
+ u32 ostc:1;
+ u32 tcmssv:1;
+ u32 reserved4:2;
+ u32 ctxt_bit:1;
+ u32 own_bit:1;
+};
+
+struct sxgbe_rx_ctxt_desc {
+ u32 tstamp_lo;
+ u32 tstamp_hi;
+ u32 reserved1;
+ u32 ptp_msgtype:4;
+ u32 tstamp_available:1;
+ u32 ptp_rsp_err:1;
+ u32 tstamp_dropped:1;
+ u32 reserved2:23;
+ u32 rx_ctxt_desc:1;
+ u32 own_bit:1;
+};
+
+struct sxgbe_desc_ops {
+ /* DMA TX descriptor ring initialization */
+ void (*init_tx_desc)(struct sxgbe_tx_norm_desc *p);
+
+ /* Invoked by the xmit function to prepare the tx descriptor */
+ void (*tx_desc_enable_tse)(struct sxgbe_tx_norm_desc *p, u8 is_tse,
+ u32 total_hdr_len, u32 tcp_hdr_len,
+ u32 tcp_payload_len);
+
+ /* Assign buffer lengths for descriptor */
+ void (*prepare_tx_desc)(struct sxgbe_tx_norm_desc *p, u8 is_fd,
+ int buf1_len, int pkt_len, int cksum);
+
+ /* Set VLAN control information */
+ void (*tx_vlanctl_desc)(struct sxgbe_tx_norm_desc *p, int vlan_ctl);
+
+ /* Set the owner of the descriptor */
+ void (*set_tx_owner)(struct sxgbe_tx_norm_desc *p);
+
+ /* Get the owner of the descriptor */
+ int (*get_tx_owner)(struct sxgbe_tx_norm_desc *p);
+
+ /* Invoked by the xmit function to close the tx descriptor */
+ void (*close_tx_desc)(struct sxgbe_tx_norm_desc *p);
+
+ /* Clean the tx descriptor as soon as the tx irq is received */
+ void (*release_tx_desc)(struct sxgbe_tx_norm_desc *p);
+
+ /* Clear interrupt on tx frame completion. When this bit is
+ * set an interrupt happens as soon as the frame is transmitted
+ */
+ void (*clear_tx_ic)(struct sxgbe_tx_norm_desc *p);
+
+ /* Last tx segment reports the transmit status */
+ int (*get_tx_ls)(struct sxgbe_tx_norm_desc *p);
+
+ /* Get the buffer size from the descriptor */
+ int (*get_tx_len)(struct sxgbe_tx_norm_desc *p);
+
+ /* Set tx timestamp enable bit */
+ void (*tx_enable_tstamp)(struct sxgbe_tx_norm_desc *p);
+
+ /* get tx timestamp status */
+ int (*get_tx_timestamp_status)(struct sxgbe_tx_norm_desc *p);
+
+ /* TX Context Descripto Specific */
+ void (*tx_ctxt_desc_set_ctxt)(struct sxgbe_tx_ctxt_desc *p);
+
+ /* Set the owner of the TX context descriptor */
+ void (*tx_ctxt_desc_set_owner)(struct sxgbe_tx_ctxt_desc *p);
+
+ /* Get the owner of the TX context descriptor */
+ int (*get_tx_ctxt_owner)(struct sxgbe_tx_ctxt_desc *p);
+
+ /* Set TX mss */
+ void (*tx_ctxt_desc_set_mss)(struct sxgbe_tx_ctxt_desc *p, u16 mss);
+
+ /* Set TX mss */
+ int (*tx_ctxt_desc_get_mss)(struct sxgbe_tx_ctxt_desc *p);
+
+ /* Set TX tcmssv */
+ void (*tx_ctxt_desc_set_tcmssv)(struct sxgbe_tx_ctxt_desc *p);
+
+ /* Reset TX ostc */
+ void (*tx_ctxt_desc_reset_ostc)(struct sxgbe_tx_ctxt_desc *p);
+
+ /* Set IVLAN information */
+ void (*tx_ctxt_desc_set_ivlantag)(struct sxgbe_tx_ctxt_desc *p,
+ int is_ivlanvalid, int ivlan_tag,
+ int ivlan_ctl);
+
+ /* Return IVLAN Tag */
+ int (*tx_ctxt_desc_get_ivlantag)(struct sxgbe_tx_ctxt_desc *p);
+
+ /* Set VLAN Tag */
+ void (*tx_ctxt_desc_set_vlantag)(struct sxgbe_tx_ctxt_desc *p,
+ int is_vlanvalid, int vlan_tag);
+
+ /* Return VLAN Tag */
+ int (*tx_ctxt_desc_get_vlantag)(struct sxgbe_tx_ctxt_desc *p);
+
+ /* Set Time stamp */
+ void (*tx_ctxt_set_tstamp)(struct sxgbe_tx_ctxt_desc *p,
+ u8 ostc_enable, u64 tstamp);
+
+ /* Close TX context descriptor */
+ void (*close_tx_ctxt_desc)(struct sxgbe_tx_ctxt_desc *p);
+
+ /* WB status of context descriptor */
+ int (*get_tx_ctxt_cde)(struct sxgbe_tx_ctxt_desc *p);
+
+ /* DMA RX descriptor ring initialization */
+ void (*init_rx_desc)(struct sxgbe_rx_norm_desc *p, int disable_rx_ic,
+ int mode, int end);
+
+ /* Get own bit */
+ int (*get_rx_owner)(struct sxgbe_rx_norm_desc *p);
+
+ /* Set own bit */
+ void (*set_rx_owner)(struct sxgbe_rx_norm_desc *p);
+
+ /* Get the receive frame size */
+ int (*get_rx_frame_len)(struct sxgbe_rx_norm_desc *p);
+
+ /* Return first Descriptor status */
+ int (*get_rx_fd_status)(struct sxgbe_rx_norm_desc *p);
+
+ /* Return first Descriptor status */
+ int (*get_rx_ld_status)(struct sxgbe_rx_norm_desc *p);
+
+ /* Return the reception status looking at the RDES1 */
+ int (*rx_wbstatus)(struct sxgbe_rx_norm_desc *p,
+ struct sxgbe_extra_stats *x, int *checksum);
+
+ /* Get own bit */
+ int (*get_rx_ctxt_owner)(struct sxgbe_rx_ctxt_desc *p);
+
+ /* Set own bit */
+ void (*set_rx_ctxt_owner)(struct sxgbe_rx_ctxt_desc *p);
+
+ /* Return the reception status looking at Context control information */
+ void (*rx_ctxt_wbstatus)(struct sxgbe_rx_ctxt_desc *p,
+ struct sxgbe_extra_stats *x);
+
+ /* Get rx timestamp status */
+ int (*get_rx_ctxt_tstamp_status)(struct sxgbe_rx_ctxt_desc *p);
+
+ /* Get timestamp value for rx, need to check this */
+ u64 (*get_timestamp)(struct sxgbe_rx_ctxt_desc *p);
+};
+
+const struct sxgbe_desc_ops *sxgbe_get_desc_ops(void);
+
+#endif /* __SXGBE_DESC_H__ */
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c
new file mode 100644
index 0000000..28f89c4
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c
@@ -0,0 +1,382 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/io.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_dma.h"
+#include "sxgbe_reg.h"
+#include "sxgbe_desc.h"
+
+/* DMA core initialization */
+static int sxgbe_dma_init(void __iomem *ioaddr, int fix_burst, int burst_map)
+{
+ int retry_count = 10;
+ u32 reg_val;
+
+ /* reset the DMA */
+ writel(SXGBE_DMA_SOFT_RESET, ioaddr + SXGBE_DMA_MODE_REG);
+ while (retry_count--) {
+ if (!(readl(ioaddr + SXGBE_DMA_MODE_REG) &
+ SXGBE_DMA_SOFT_RESET))
+ break;
+ mdelay(10);
+ }
+
+ if (retry_count < 0)
+ return -EBUSY;
+
+ reg_val = readl(ioaddr + SXGBE_DMA_SYSBUS_MODE_REG);
+
+ /* if fix_burst = 0, Set UNDEF = 1 of DMA_Sys_Mode Register.
+ * if fix_burst = 1, Set UNDEF = 0 of DMA_Sys_Mode Register.
+ * burst_map is bitmap for BLEN[4, 8, 16, 32, 64, 128 and 256].
+ * Set burst_map irrespective of fix_burst value.
+ */
+ if (!fix_burst)
+ reg_val |= SXGBE_DMA_AXI_UNDEF_BURST;
+
+ /* write burst len map */
+ reg_val |= (burst_map << SXGBE_DMA_BLENMAP_LSHIFT);
+
+ writel(reg_val, ioaddr + SXGBE_DMA_SYSBUS_MODE_REG);
+
+ return 0;
+}
+
+static void sxgbe_dma_channel_init(void __iomem *ioaddr, int cha_num,
+ int fix_burst, int pbl, dma_addr_t dma_tx,
+ dma_addr_t dma_rx, int t_rsize, int r_rsize)
+{
+ u32 reg_val;
+ dma_addr_t dma_addr;
+
+ reg_val = readl(ioaddr + SXGBE_DMA_CHA_CTL_REG(cha_num));
+ /* set the pbl */
+ if (fix_burst) {
+ reg_val |= SXGBE_DMA_PBL_X8MODE;
+ writel(reg_val, ioaddr + SXGBE_DMA_CHA_CTL_REG(cha_num));
+ /* program the TX pbl */
+ reg_val = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cha_num));
+ reg_val |= (pbl << SXGBE_DMA_TXPBL_LSHIFT);
+ writel(reg_val, ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cha_num));
+ /* program the RX pbl */
+ reg_val = readl(ioaddr + SXGBE_DMA_CHA_RXCTL_REG(cha_num));
+ reg_val |= (pbl << SXGBE_DMA_RXPBL_LSHIFT);
+ writel(reg_val, ioaddr + SXGBE_DMA_CHA_RXCTL_REG(cha_num));
+ }
+
+ /* program desc registers */
+ writel(upper_32_bits(dma_tx),
+ ioaddr + SXGBE_DMA_CHA_TXDESC_HADD_REG(cha_num));
+ writel(lower_32_bits(dma_tx),
+ ioaddr + SXGBE_DMA_CHA_TXDESC_LADD_REG(cha_num));
+
+ writel(upper_32_bits(dma_rx),
+ ioaddr + SXGBE_DMA_CHA_RXDESC_HADD_REG(cha_num));
+ writel(lower_32_bits(dma_rx),
+ ioaddr + SXGBE_DMA_CHA_RXDESC_LADD_REG(cha_num));
+
+ /* program tail pointers */
+ /* assumption: upper 32 bits are constant and
+ * same as TX/RX desc list
+ */
+ dma_addr = dma_tx + ((t_rsize - 1) * SXGBE_DESC_SIZE_BYTES);
+ writel(lower_32_bits(dma_addr),
+ ioaddr + SXGBE_DMA_CHA_TXDESC_TAILPTR_REG(cha_num));
+
+ dma_addr = dma_rx + ((r_rsize - 1) * SXGBE_DESC_SIZE_BYTES);
+ writel(lower_32_bits(dma_addr),
+ ioaddr + SXGBE_DMA_CHA_RXDESC_LADD_REG(cha_num));
+ /* program the ring sizes */
+ writel(t_rsize - 1, ioaddr + SXGBE_DMA_CHA_TXDESC_RINGLEN_REG(cha_num));
+ writel(r_rsize - 1, ioaddr + SXGBE_DMA_CHA_RXDESC_RINGLEN_REG(cha_num));
+
+ /* Enable TX/RX interrupts */
+ writel(SXGBE_DMA_ENA_INT,
+ ioaddr + SXGBE_DMA_CHA_INT_ENABLE_REG(cha_num));
+}
+
+static void sxgbe_enable_dma_transmission(void __iomem *ioaddr, int cha_num)
+{
+ u32 tx_config;
+
+ tx_config = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cha_num));
+ tx_config |= SXGBE_TX_START_DMA;
+ writel(tx_config, ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cha_num));
+}
+
+static void sxgbe_enable_dma_irq(void __iomem *ioaddr, int dma_cnum)
+{
+ /* Enable TX/RX interrupts */
+ writel(SXGBE_DMA_ENA_INT,
+ ioaddr + SXGBE_DMA_CHA_INT_ENABLE_REG(dma_cnum));
+}
+
+static void sxgbe_disable_dma_irq(void __iomem *ioaddr, int dma_cnum)
+{
+ /* Disable TX/RX interrupts */
+ writel(0, ioaddr + SXGBE_DMA_CHA_INT_ENABLE_REG(dma_cnum));
+}
+
+static void sxgbe_dma_start_tx(void __iomem *ioaddr, int tchannels)
+{
+ int cnum;
+ u32 tx_ctl_reg;
+
+ for (cnum = 0; cnum < tchannels; cnum++) {
+ tx_ctl_reg = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cnum));
+ tx_ctl_reg |= SXGBE_TX_ENABLE;
+ writel(tx_ctl_reg,
+ ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cnum));
+ }
+}
+
+static void sxgbe_dma_start_tx_queue(void __iomem *ioaddr, int dma_cnum)
+{
+ u32 tx_ctl_reg;
+
+ tx_ctl_reg = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(dma_cnum));
+ tx_ctl_reg |= SXGBE_TX_ENABLE;
+ writel(tx_ctl_reg, ioaddr + SXGBE_DMA_CHA_TXCTL_REG(dma_cnum));
+}
+
+static void sxgbe_dma_stop_tx_queue(void __iomem *ioaddr, int dma_cnum)
+{
+ u32 tx_ctl_reg;
+
+ tx_ctl_reg = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(dma_cnum));
+ tx_ctl_reg &= ~(SXGBE_TX_ENABLE);
+ writel(tx_ctl_reg, ioaddr + SXGBE_DMA_CHA_TXCTL_REG(dma_cnum));
+}
+
+static void sxgbe_dma_stop_tx(void __iomem *ioaddr, int tchannels)
+{
+ int cnum;
+ u32 tx_ctl_reg;
+
+ for (cnum = 0; cnum < tchannels; cnum++) {
+ tx_ctl_reg = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cnum));
+ tx_ctl_reg &= ~(SXGBE_TX_ENABLE);
+ writel(tx_ctl_reg, ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cnum));
+ }
+}
+
+static void sxgbe_dma_start_rx(void __iomem *ioaddr, int rchannels)
+{
+ int cnum;
+ u32 rx_ctl_reg;
+
+ for (cnum = 0; cnum < rchannels; cnum++) {
+ rx_ctl_reg = readl(ioaddr + SXGBE_DMA_CHA_RXCTL_REG(cnum));
+ rx_ctl_reg |= SXGBE_RX_ENABLE;
+ writel(rx_ctl_reg,
+ ioaddr + SXGBE_DMA_CHA_RXCTL_REG(cnum));
+ }
+}
+
+static void sxgbe_dma_stop_rx(void __iomem *ioaddr, int rchannels)
+{
+ int cnum;
+ u32 rx_ctl_reg;
+
+ for (cnum = 0; cnum < rchannels; cnum++) {
+ rx_ctl_reg = readl(ioaddr + SXGBE_DMA_CHA_RXCTL_REG(cnum));
+ rx_ctl_reg &= ~(SXGBE_RX_ENABLE);
+ writel(rx_ctl_reg, ioaddr + SXGBE_DMA_CHA_RXCTL_REG(cnum));
+ }
+}
+
+static int sxgbe_tx_dma_int_status(void __iomem *ioaddr, int channel_no,
+ struct sxgbe_extra_stats *x)
+{
+ u32 int_status = readl(ioaddr + SXGBE_DMA_CHA_STATUS_REG(channel_no));
+ u32 clear_val = 0;
+ u32 ret_val = 0;
+
+ /* TX Normal Interrupt Summary */
+ if (likely(int_status & SXGBE_DMA_INT_STATUS_NIS)) {
+ x->normal_irq_n++;
+ if (int_status & SXGBE_DMA_INT_STATUS_TI) {
+ ret_val |= handle_tx;
+ x->tx_normal_irq_n++;
+ clear_val |= SXGBE_DMA_INT_STATUS_TI;
+ }
+
+ if (int_status & SXGBE_DMA_INT_STATUS_TBU) {
+ x->tx_underflow_irq++;
+ ret_val |= tx_bump_tc;
+ clear_val |= SXGBE_DMA_INT_STATUS_TBU;
+ }
+ } else if (unlikely(int_status & SXGBE_DMA_INT_STATUS_AIS)) {
+ /* TX Abnormal Interrupt Summary */
+ if (int_status & SXGBE_DMA_INT_STATUS_TPS) {
+ ret_val |= tx_hard_error;
+ clear_val |= SXGBE_DMA_INT_STATUS_TPS;
+ x->tx_process_stopped_irq++;
+ }
+
+ if (int_status & SXGBE_DMA_INT_STATUS_FBE) {
+ ret_val |= tx_hard_error;
+ x->fatal_bus_error_irq++;
+
+ /* Assumption: FBE bit is the combination of
+ * all the bus access erros and cleared when
+ * the respective error bits cleared
+ */
+
+ /* check for actual cause */
+ if (int_status & SXGBE_DMA_INT_STATUS_TEB0) {
+ x->tx_read_transfer_err++;
+ clear_val |= SXGBE_DMA_INT_STATUS_TEB0;
+ } else {
+ x->tx_write_transfer_err++;
+ }
+
+ if (int_status & SXGBE_DMA_INT_STATUS_TEB1) {
+ x->tx_desc_access_err++;
+ clear_val |= SXGBE_DMA_INT_STATUS_TEB1;
+ } else {
+ x->tx_buffer_access_err++;
+ }
+
+ if (int_status & SXGBE_DMA_INT_STATUS_TEB2) {
+ x->tx_data_transfer_err++;
+ clear_val |= SXGBE_DMA_INT_STATUS_TEB2;
+ }
+ }
+
+ /* context descriptor error */
+ if (int_status & SXGBE_DMA_INT_STATUS_CTXTERR) {
+ x->tx_ctxt_desc_err++;
+ clear_val |= SXGBE_DMA_INT_STATUS_CTXTERR;
+ }
+ }
+
+ /* clear the served bits */
+ writel(clear_val, ioaddr + SXGBE_DMA_CHA_STATUS_REG(channel_no));
+
+ return ret_val;
+}
+
+static int sxgbe_rx_dma_int_status(void __iomem *ioaddr, int channel_no,
+ struct sxgbe_extra_stats *x)
+{
+ u32 int_status = readl(ioaddr + SXGBE_DMA_CHA_STATUS_REG(channel_no));
+ u32 clear_val = 0;
+ u32 ret_val = 0;
+
+ /* RX Normal Interrupt Summary */
+ if (likely(int_status & SXGBE_DMA_INT_STATUS_NIS)) {
+ x->normal_irq_n++;
+ if (int_status & SXGBE_DMA_INT_STATUS_RI) {
+ ret_val |= handle_rx;
+ x->rx_normal_irq_n++;
+ clear_val |= SXGBE_DMA_INT_STATUS_RI;
+ }
+ } else if (unlikely(int_status & SXGBE_DMA_INT_STATUS_AIS)) {
+ /* RX Abnormal Interrupt Summary */
+ if (int_status & SXGBE_DMA_INT_STATUS_RBU) {
+ ret_val |= rx_bump_tc;
+ clear_val |= SXGBE_DMA_INT_STATUS_RBU;
+ x->rx_underflow_irq++;
+ }
+
+ if (int_status & SXGBE_DMA_INT_STATUS_RPS) {
+ ret_val |= rx_hard_error;
+ clear_val |= SXGBE_DMA_INT_STATUS_RPS;
+ x->rx_process_stopped_irq++;
+ }
+
+ if (int_status & SXGBE_DMA_INT_STATUS_FBE) {
+ ret_val |= rx_hard_error;
+ x->fatal_bus_error_irq++;
+
+ /* Assumption: FBE bit is the combination of
+ * all the bus access erros and cleared when
+ * the respective error bits cleared
+ */
+
+ /* check for actual cause */
+ if (int_status & SXGBE_DMA_INT_STATUS_REB0) {
+ x->rx_read_transfer_err++;
+ clear_val |= SXGBE_DMA_INT_STATUS_REB0;
+ } else {
+ x->rx_write_transfer_err++;
+ }
+
+ if (int_status & SXGBE_DMA_INT_STATUS_REB1) {
+ x->rx_desc_access_err++;
+ clear_val |= SXGBE_DMA_INT_STATUS_REB1;
+ } else {
+ x->rx_buffer_access_err++;
+ }
+
+ if (int_status & SXGBE_DMA_INT_STATUS_REB2) {
+ x->rx_data_transfer_err++;
+ clear_val |= SXGBE_DMA_INT_STATUS_REB2;
+ }
+ }
+ }
+
+ /* clear the served bits */
+ writel(clear_val, ioaddr + SXGBE_DMA_CHA_STATUS_REG(channel_no));
+
+ return ret_val;
+}
+
+/* Program the HW RX Watchdog */
+static void sxgbe_dma_rx_watchdog(void __iomem *ioaddr, u32 riwt)
+{
+ u32 que_num;
+
+ SXGBE_FOR_EACH_QUEUE(SXGBE_RX_QUEUES, que_num) {
+ writel(riwt,
+ ioaddr + SXGBE_DMA_CHA_INT_RXWATCHTMR_REG(que_num));
+ }
+}
+
+static void sxgbe_enable_tso(void __iomem *ioaddr, u8 chan_num)
+{
+ u32 ctrl;
+
+ ctrl = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(chan_num));
+ ctrl |= SXGBE_DMA_CHA_TXCTL_TSE_ENABLE;
+ writel(ctrl, ioaddr + SXGBE_DMA_CHA_TXCTL_REG(chan_num));
+}
+
+static const struct sxgbe_dma_ops sxgbe_dma_ops = {
+ .init = sxgbe_dma_init,
+ .cha_init = sxgbe_dma_channel_init,
+ .enable_dma_transmission = sxgbe_enable_dma_transmission,
+ .enable_dma_irq = sxgbe_enable_dma_irq,
+ .disable_dma_irq = sxgbe_disable_dma_irq,
+ .start_tx = sxgbe_dma_start_tx,
+ .start_tx_queue = sxgbe_dma_start_tx_queue,
+ .stop_tx = sxgbe_dma_stop_tx,
+ .stop_tx_queue = sxgbe_dma_stop_tx_queue,
+ .start_rx = sxgbe_dma_start_rx,
+ .stop_rx = sxgbe_dma_stop_rx,
+ .tx_dma_int_status = sxgbe_tx_dma_int_status,
+ .rx_dma_int_status = sxgbe_rx_dma_int_status,
+ .rx_watchdog = sxgbe_dma_rx_watchdog,
+ .enable_tso = sxgbe_enable_tso,
+};
+
+const struct sxgbe_dma_ops *sxgbe_get_dma_ops(void)
+{
+ return &sxgbe_dma_ops;
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.h
new file mode 100644
index 0000000..1607b54
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.h
@@ -0,0 +1,50 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SXGBE_DMA_H__
+#define __SXGBE_DMA_H__
+
+/* forward declaration */
+struct sxgbe_extra_stats;
+
+#define SXGBE_DMA_BLENMAP_LSHIFT 1
+#define SXGBE_DMA_TXPBL_LSHIFT 16
+#define SXGBE_DMA_RXPBL_LSHIFT 16
+#define DEFAULT_DMA_PBL 8
+
+struct sxgbe_dma_ops {
+ /* DMA core initialization */
+ int (*init)(void __iomem *ioaddr, int fix_burst, int burst_map);
+ void (*cha_init)(void __iomem *ioaddr, int cha_num, int fix_burst,
+ int pbl, dma_addr_t dma_tx, dma_addr_t dma_rx,
+ int t_rzie, int r_rsize);
+ void (*enable_dma_transmission)(void __iomem *ioaddr, int dma_cnum);
+ void (*enable_dma_irq)(void __iomem *ioaddr, int dma_cnum);
+ void (*disable_dma_irq)(void __iomem *ioaddr, int dma_cnum);
+ void (*start_tx)(void __iomem *ioaddr, int tchannels);
+ void (*start_tx_queue)(void __iomem *ioaddr, int dma_cnum);
+ void (*stop_tx)(void __iomem *ioaddr, int tchannels);
+ void (*stop_tx_queue)(void __iomem *ioaddr, int dma_cnum);
+ void (*start_rx)(void __iomem *ioaddr, int rchannels);
+ void (*stop_rx)(void __iomem *ioaddr, int rchannels);
+ int (*tx_dma_int_status)(void __iomem *ioaddr, int channel_no,
+ struct sxgbe_extra_stats *x);
+ int (*rx_dma_int_status)(void __iomem *ioaddr, int channel_no,
+ struct sxgbe_extra_stats *x);
+ /* Program the HW RX Watchdog */
+ void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt);
+ /* Enable TSO for each DMA channel */
+ void (*enable_tso)(void __iomem *ioaddr, u8 chan_num);
+};
+
+const struct sxgbe_dma_ops *sxgbe_get_dma_ops(void);
+
+#endif /* __SXGBE_CORE_H__ */
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
new file mode 100644
index 0000000..0415fa5
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
@@ -0,0 +1,524 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/net_tstamp.h>
+#include <linux/phy.h>
+#include <linux/ptp_clock_kernel.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_reg.h"
+#include "sxgbe_dma.h"
+
+struct sxgbe_stats {
+ char stat_string[ETH_GSTRING_LEN];
+ int sizeof_stat;
+ int stat_offset;
+};
+
+#define SXGBE_STAT(m) \
+{ \
+ #m, \
+ FIELD_SIZEOF(struct sxgbe_extra_stats, m), \
+ offsetof(struct sxgbe_priv_data, xstats.m) \
+}
+
+static const struct sxgbe_stats sxgbe_gstrings_stats[] = {
+ /* TX/RX IRQ events */
+ SXGBE_STAT(tx_process_stopped_irq),
+ SXGBE_STAT(tx_ctxt_desc_err),
+ SXGBE_STAT(tx_threshold),
+ SXGBE_STAT(rx_threshold),
+ SXGBE_STAT(tx_pkt_n),
+ SXGBE_STAT(rx_pkt_n),
+ SXGBE_STAT(normal_irq_n),
+ SXGBE_STAT(tx_normal_irq_n),
+ SXGBE_STAT(rx_normal_irq_n),
+ SXGBE_STAT(napi_poll),
+ SXGBE_STAT(tx_clean),
+ SXGBE_STAT(tx_reset_ic_bit),
+ SXGBE_STAT(rx_process_stopped_irq),
+ SXGBE_STAT(rx_underflow_irq),
+
+ /* Bus access errors */
+ SXGBE_STAT(fatal_bus_error_irq),
+ SXGBE_STAT(tx_read_transfer_err),
+ SXGBE_STAT(tx_write_transfer_err),
+ SXGBE_STAT(tx_desc_access_err),
+ SXGBE_STAT(tx_buffer_access_err),
+ SXGBE_STAT(tx_data_transfer_err),
+ SXGBE_STAT(rx_read_transfer_err),
+ SXGBE_STAT(rx_write_transfer_err),
+ SXGBE_STAT(rx_desc_access_err),
+ SXGBE_STAT(rx_buffer_access_err),
+ SXGBE_STAT(rx_data_transfer_err),
+
+ /* EEE-LPI stats */
+ SXGBE_STAT(tx_lpi_entry_n),
+ SXGBE_STAT(tx_lpi_exit_n),
+ SXGBE_STAT(rx_lpi_entry_n),
+ SXGBE_STAT(rx_lpi_exit_n),
+ SXGBE_STAT(eee_wakeup_error_n),
+
+ /* RX specific */
+ /* L2 error */
+ SXGBE_STAT(rx_code_gmii_err),
+ SXGBE_STAT(rx_watchdog_err),
+ SXGBE_STAT(rx_crc_err),
+ SXGBE_STAT(rx_gaint_pkt_err),
+ SXGBE_STAT(ip_hdr_err),
+ SXGBE_STAT(ip_payload_err),
+ SXGBE_STAT(overflow_error),
+
+ /* L2 Pkt type */
+ SXGBE_STAT(len_pkt),
+ SXGBE_STAT(mac_ctl_pkt),
+ SXGBE_STAT(dcb_ctl_pkt),
+ SXGBE_STAT(arp_pkt),
+ SXGBE_STAT(oam_pkt),
+ SXGBE_STAT(untag_okt),
+ SXGBE_STAT(other_pkt),
+ SXGBE_STAT(svlan_tag_pkt),
+ SXGBE_STAT(cvlan_tag_pkt),
+ SXGBE_STAT(dvlan_ocvlan_icvlan_pkt),
+ SXGBE_STAT(dvlan_osvlan_isvlan_pkt),
+ SXGBE_STAT(dvlan_osvlan_icvlan_pkt),
+ SXGBE_STAT(dvan_ocvlan_icvlan_pkt),
+
+ /* L3/L4 Pkt type */
+ SXGBE_STAT(not_ip_pkt),
+ SXGBE_STAT(ip4_tcp_pkt),
+ SXGBE_STAT(ip4_udp_pkt),
+ SXGBE_STAT(ip4_icmp_pkt),
+ SXGBE_STAT(ip4_unknown_pkt),
+ SXGBE_STAT(ip6_tcp_pkt),
+ SXGBE_STAT(ip6_udp_pkt),
+ SXGBE_STAT(ip6_icmp_pkt),
+ SXGBE_STAT(ip6_unknown_pkt),
+
+ /* Filter specific */
+ SXGBE_STAT(vlan_filter_match),
+ SXGBE_STAT(sa_filter_fail),
+ SXGBE_STAT(da_filter_fail),
+ SXGBE_STAT(hash_filter_pass),
+ SXGBE_STAT(l3_filter_match),
+ SXGBE_STAT(l4_filter_match),
+
+ /* RX context specific */
+ SXGBE_STAT(timestamp_dropped),
+ SXGBE_STAT(rx_msg_type_no_ptp),
+ SXGBE_STAT(rx_ptp_type_sync),
+ SXGBE_STAT(rx_ptp_type_follow_up),
+ SXGBE_STAT(rx_ptp_type_delay_req),
+ SXGBE_STAT(rx_ptp_type_delay_resp),
+ SXGBE_STAT(rx_ptp_type_pdelay_req),
+ SXGBE_STAT(rx_ptp_type_pdelay_resp),
+ SXGBE_STAT(rx_ptp_type_pdelay_follow_up),
+ SXGBE_STAT(rx_ptp_announce),
+ SXGBE_STAT(rx_ptp_mgmt),
+ SXGBE_STAT(rx_ptp_signal),
+ SXGBE_STAT(rx_ptp_resv_msg_type),
+};
+#define SXGBE_STATS_LEN ARRAY_SIZE(sxgbe_gstrings_stats)
+
+static int sxgbe_get_eee(struct net_device *dev,
+ struct ethtool_eee *edata)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+ if (!priv->hw_cap.eee)
+ return -EOPNOTSUPP;
+
+ edata->eee_enabled = priv->eee_enabled;
+ edata->eee_active = priv->eee_active;
+ edata->tx_lpi_timer = priv->tx_lpi_timer;
+
+ return phy_ethtool_get_eee(priv->phydev, edata);
+}
+
+static int sxgbe_set_eee(struct net_device *dev,
+ struct ethtool_eee *edata)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+ priv->eee_enabled = edata->eee_enabled;
+
+ if (!priv->eee_enabled) {
+ sxgbe_disable_eee_mode(priv);
+ } else {
+ /* We are asking for enabling the EEE but it is safe
+ * to verify all by invoking the eee_init function.
+ * In case of failure it will return an error.
+ */
+ priv->eee_enabled = sxgbe_eee_init(priv);
+ if (!priv->eee_enabled)
+ return -EOPNOTSUPP;
+
+ /* Do not change tx_lpi_timer in case of failure */
+ priv->tx_lpi_timer = edata->tx_lpi_timer;
+ }
+
+ return phy_ethtool_set_eee(priv->phydev, edata);
+}
+
+static void sxgbe_getdrvinfo(struct net_device *dev,
+ struct ethtool_drvinfo *info)
+{
+ strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+ strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+}
+
+static int sxgbe_getsettings(struct net_device *dev,
+ struct ethtool_cmd *cmd)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+ if (priv->phydev)
+ return phy_ethtool_gset(priv->phydev, cmd);
+
+ return -EOPNOTSUPP;
+}
+
+static int sxgbe_setsettings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+ if (priv->phydev)
+ return phy_ethtool_sset(priv->phydev, cmd);
+
+ return -EOPNOTSUPP;
+}
+
+static u32 sxgbe_getmsglevel(struct net_device *dev)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ return priv->msg_enable;
+}
+
+static void sxgbe_setmsglevel(struct net_device *dev, u32 level)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ priv->msg_enable = level;
+}
+
+static void sxgbe_get_strings(struct net_device *dev, u32 stringset, u8 *data)
+{
+ int i;
+ u8 *p = data;
+
+ switch (stringset) {
+ case ETH_SS_STATS:
+ for (i = 0; i < SXGBE_STATS_LEN; i++) {
+ memcpy(p, sxgbe_gstrings_stats[i].stat_string,
+ ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
+ break;
+ default:
+ WARN_ON(1);
+ break;
+ }
+}
+
+static int sxgbe_get_sset_count(struct net_device *netdev, int sset)
+{
+ int len;
+
+ switch (sset) {
+ case ETH_SS_STATS:
+ len = SXGBE_STATS_LEN;
+ return len;
+ default:
+ return -EINVAL;
+ }
+}
+
+static void sxgbe_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *dummy, u64 *data)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ int i;
+ char *p;
+
+ if (priv->eee_enabled) {
+ int val = phy_get_eee_err(priv->phydev);
+
+ if (val)
+ priv->xstats.eee_wakeup_error_n = val;
+ }
+
+ for (i = 0; i < SXGBE_STATS_LEN; i++) {
+ p = (char *)priv + sxgbe_gstrings_stats[i].stat_offset;
+ data[i] = (sxgbe_gstrings_stats[i].sizeof_stat == sizeof(u64))
+ ? (*(u64 *)p) : (*(u32 *)p);
+ }
+}
+
+static void sxgbe_get_channels(struct net_device *dev,
+ struct ethtool_channels *channel)
+{
+ channel->max_rx = SXGBE_MAX_RX_CHANNELS;
+ channel->max_tx = SXGBE_MAX_TX_CHANNELS;
+ channel->rx_count = SXGBE_RX_QUEUES;
+ channel->tx_count = SXGBE_TX_QUEUES;
+}
+
+static u32 sxgbe_riwt2usec(u32 riwt, struct sxgbe_priv_data *priv)
+{
+ unsigned long clk = clk_get_rate(priv->sxgbe_clk);
+
+ if (!clk)
+ return 0;
+
+ return (riwt * 256) / (clk / 1000000);
+}
+
+static u32 sxgbe_usec2riwt(u32 usec, struct sxgbe_priv_data *priv)
+{
+ unsigned long clk = clk_get_rate(priv->sxgbe_clk);
+
+ if (!clk)
+ return 0;
+
+ return (usec * (clk / 1000000)) / 256;
+}
+
+static int sxgbe_get_coalesce(struct net_device *dev,
+ struct ethtool_coalesce *ec)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+ if (priv->use_riwt)
+ ec->rx_coalesce_usecs = sxgbe_riwt2usec(priv->rx_riwt, priv);
+
+ return 0;
+}
+
+static int sxgbe_set_coalesce(struct net_device *dev,
+ struct ethtool_coalesce *ec)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ unsigned int rx_riwt;
+
+ if (!ec->rx_coalesce_usecs)
+ return -EINVAL;
+
+ rx_riwt = sxgbe_usec2riwt(ec->rx_coalesce_usecs, priv);
+
+ if ((rx_riwt > SXGBE_MAX_DMA_RIWT) || (rx_riwt < SXGBE_MIN_DMA_RIWT))
+ return -EINVAL;
+ else if (!priv->use_riwt)
+ return -EOPNOTSUPP;
+
+ priv->rx_riwt = rx_riwt;
+ priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt);
+
+ return 0;
+}
+
+static int sxgbe_get_rss_hash_opts(struct sxgbe_priv_data *priv,
+ struct ethtool_rxnfc *cmd)
+{
+ cmd->data = 0;
+
+ /* Report default options for RSS on sxgbe */
+ switch (cmd->flow_type) {
+ case TCP_V4_FLOW:
+ case UDP_V4_FLOW:
+ cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ case SCTP_V4_FLOW:
+ case AH_ESP_V4_FLOW:
+ case AH_V4_FLOW:
+ case ESP_V4_FLOW:
+ case IPV4_FLOW:
+ cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+ break;
+ case TCP_V6_FLOW:
+ case UDP_V6_FLOW:
+ cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ case SCTP_V6_FLOW:
+ case AH_ESP_V6_FLOW:
+ case AH_V6_FLOW:
+ case ESP_V6_FLOW:
+ case IPV6_FLOW:
+ cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int sxgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
+ u32 *rule_locs)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ int ret = -EOPNOTSUPP;
+
+ switch (cmd->cmd) {
+ case ETHTOOL_GRXFH:
+ ret = sxgbe_get_rss_hash_opts(priv, cmd);
+ break;
+ default:
+ break;
+ }
+
+ return ret;
+}
+
+static int sxgbe_set_rss_hash_opt(struct sxgbe_priv_data *priv,
+ struct ethtool_rxnfc *cmd)
+{
+ u32 reg_val = 0;
+
+ /* RSS does not support anything other than hashing
+ * to queues on src and dst IPs and ports
+ */
+ if (cmd->data & ~(RXH_IP_SRC | RXH_IP_DST |
+ RXH_L4_B_0_1 | RXH_L4_B_2_3))
+ return -EINVAL;
+
+ switch (cmd->flow_type) {
+ case TCP_V4_FLOW:
+ case TCP_V6_FLOW:
+ if (!(cmd->data & RXH_IP_SRC) ||
+ !(cmd->data & RXH_IP_DST) ||
+ !(cmd->data & RXH_L4_B_0_1) ||
+ !(cmd->data & RXH_L4_B_2_3))
+ return -EINVAL;
+ reg_val = SXGBE_CORE_RSS_CTL_TCP4TE;
+ break;
+ case UDP_V4_FLOW:
+ case UDP_V6_FLOW:
+ if (!(cmd->data & RXH_IP_SRC) ||
+ !(cmd->data & RXH_IP_DST) ||
+ !(cmd->data & RXH_L4_B_0_1) ||
+ !(cmd->data & RXH_L4_B_2_3))
+ return -EINVAL;
+ reg_val = SXGBE_CORE_RSS_CTL_UDP4TE;
+ break;
+ case SCTP_V4_FLOW:
+ case AH_ESP_V4_FLOW:
+ case AH_V4_FLOW:
+ case ESP_V4_FLOW:
+ case AH_ESP_V6_FLOW:
+ case AH_V6_FLOW:
+ case ESP_V6_FLOW:
+ case SCTP_V6_FLOW:
+ case IPV4_FLOW:
+ case IPV6_FLOW:
+ if (!(cmd->data & RXH_IP_SRC) ||
+ !(cmd->data & RXH_IP_DST) ||
+ (cmd->data & RXH_L4_B_0_1) ||
+ (cmd->data & RXH_L4_B_2_3))
+ return -EINVAL;
+ reg_val = SXGBE_CORE_RSS_CTL_IP2TE;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* Read SXGBE RSS control register and update */
+ reg_val |= readl(priv->ioaddr + SXGBE_CORE_RSS_CTL_REG);
+ writel(reg_val, priv->ioaddr + SXGBE_CORE_RSS_CTL_REG);
+ readl(priv->ioaddr + SXGBE_CORE_RSS_CTL_REG);
+
+ return 0;
+}
+
+static int sxgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ int ret = -EOPNOTSUPP;
+
+ switch (cmd->cmd) {
+ case ETHTOOL_SRXFH:
+ ret = sxgbe_set_rss_hash_opt(priv, cmd);
+ break;
+ default:
+ break;
+ }
+
+ return ret;
+}
+
+static void sxgbe_get_regs(struct net_device *dev,
+ struct ethtool_regs *regs, void *space)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ u32 *reg_space = (u32 *)space;
+ int reg_offset;
+ int reg_ix = 0;
+ void __iomem *ioaddr = priv->ioaddr;
+
+ memset(reg_space, 0x0, REG_SPACE_SIZE);
+
+ /* MAC registers */
+ for (reg_offset = START_MAC_REG_OFFSET;
+ reg_offset <= MAX_MAC_REG_OFFSET; reg_offset += 4) {
+ reg_space[reg_ix] = readl(ioaddr + reg_offset);
+ reg_ix++;
+ }
+
+ /* MTL registers */
+ for (reg_offset = START_MTL_REG_OFFSET;
+ reg_offset <= MAX_MTL_REG_OFFSET; reg_offset += 4) {
+ reg_space[reg_ix] = readl(ioaddr + reg_offset);
+ reg_ix++;
+ }
+
+ /* DMA registers */
+ for (reg_offset = START_DMA_REG_OFFSET;
+ reg_offset <= MAX_DMA_REG_OFFSET; reg_offset += 4) {
+ reg_space[reg_ix] = readl(ioaddr + reg_offset);
+ reg_ix++;
+ }
+
+ BUG_ON(reg_ix * 4 > REG_SPACE_SIZE);
+}
+
+static int sxgbe_get_regs_len(struct net_device *dev)
+{
+ return REG_SPACE_SIZE;
+}
+
+static const struct ethtool_ops sxgbe_ethtool_ops = {
+ .get_drvinfo = sxgbe_getdrvinfo,
+ .get_settings = sxgbe_getsettings,
+ .set_settings = sxgbe_setsettings,
+ .get_msglevel = sxgbe_getmsglevel,
+ .set_msglevel = sxgbe_setmsglevel,
+ .get_link = ethtool_op_get_link,
+ .get_strings = sxgbe_get_strings,
+ .get_ethtool_stats = sxgbe_get_ethtool_stats,
+ .get_sset_count = sxgbe_get_sset_count,
+ .get_channels = sxgbe_get_channels,
+ .get_coalesce = sxgbe_get_coalesce,
+ .set_coalesce = sxgbe_set_coalesce,
+ .get_rxnfc = sxgbe_get_rxnfc,
+ .set_rxnfc = sxgbe_set_rxnfc,
+ .get_regs = sxgbe_get_regs,
+ .get_regs_len = sxgbe_get_regs_len,
+ .get_eee = sxgbe_get_eee,
+ .set_eee = sxgbe_set_eee,
+};
+
+void sxgbe_set_ethtool_ops(struct net_device *netdev)
+{
+ SET_ETHTOOL_OPS(netdev, &sxgbe_ethtool_ops);
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
new file mode 100644
index 0000000..a72688e
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -0,0 +1,2317 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/crc32.h>
+#include <linux/dma-mapping.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/if.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/ip.h>
+#include <linux/kernel.h>
+#include <linux/mii.h>
+#include <linux/module.h>
+#include <linux/net_tstamp.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/prefetch.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/tcp.h>
+#include <linux/sxgbe_platform.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_desc.h"
+#include "sxgbe_dma.h"
+#include "sxgbe_mtl.h"
+#include "sxgbe_reg.h"
+
+#define SXGBE_ALIGN(x) L1_CACHE_ALIGN(x)
+#define JUMBO_LEN 9000
+
+/* Module parameters */
+#define TX_TIMEO 5000
+#define DMA_TX_SIZE 512
+#define DMA_RX_SIZE 1024
+#define TC_DEFAULT 64
+#define DMA_BUFFER_SIZE BUF_SIZE_2KiB
+/* The default timer value as per the sxgbe specification 1 sec(1000 ms) */
+#define SXGBE_DEFAULT_LPI_TIMER 1000
+
+static int debug = -1;
+static int eee_timer = SXGBE_DEFAULT_LPI_TIMER;
+
+module_param(eee_timer, int, S_IRUGO | S_IWUSR);
+
+module_param(debug, int, S_IRUGO | S_IWUSR);
+static const u32 default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE |
+ NETIF_MSG_LINK | NETIF_MSG_IFUP |
+ NETIF_MSG_IFDOWN | NETIF_MSG_TIMER);
+
+static irqreturn_t sxgbe_common_interrupt(int irq, void *dev_id);
+static irqreturn_t sxgbe_tx_interrupt(int irq, void *dev_id);
+static irqreturn_t sxgbe_rx_interrupt(int irq, void *dev_id);
+
+#define SXGBE_COAL_TIMER(x) (jiffies + usecs_to_jiffies(x))
+
+#define SXGBE_LPI_TIMER(x) (jiffies + msecs_to_jiffies(x))
+
+/**
+ * sxgbe_verify_args - verify the driver parameters.
+ * Description: it verifies if some wrong parameter is passed to the driver.
+ * Note that wrong parameters are replaced with the default values.
+ */
+static void sxgbe_verify_args(void)
+{
+ if (unlikely(eee_timer < 0))
+ eee_timer = SXGBE_DEFAULT_LPI_TIMER;
+}
+
+static void sxgbe_enable_eee_mode(const struct sxgbe_priv_data *priv)
+{
+ /* Check and enter in LPI mode */
+ if (!priv->tx_path_in_lpi_mode)
+ priv->hw->mac->set_eee_mode(priv->ioaddr);
+}
+
+void sxgbe_disable_eee_mode(struct sxgbe_priv_data * const priv)
+{
+ /* Exit and disable EEE in case of we are are in LPI state. */
+ priv->hw->mac->reset_eee_mode(priv->ioaddr);
+ del_timer_sync(&priv->eee_ctrl_timer);
+ priv->tx_path_in_lpi_mode = false;
+}
+
+/**
+ * sxgbe_eee_ctrl_timer
+ * @arg : data hook
+ * Description:
+ * If there is no data transfer and if we are not in LPI state,
+ * then MAC Transmitter can be moved to LPI state.
+ */
+static void sxgbe_eee_ctrl_timer(unsigned long arg)
+{
+ struct sxgbe_priv_data *priv = (struct sxgbe_priv_data *)arg;
+
+ sxgbe_enable_eee_mode(priv);
+ mod_timer(&priv->eee_ctrl_timer, SXGBE_LPI_TIMER(eee_timer));
+}
+
+/**
+ * sxgbe_eee_init
+ * @priv: private device pointer
+ * Description:
+ * If the EEE support has been enabled while configuring the driver,
+ * if the GMAC actually supports the EEE (from the HW cap reg) and the
+ * phy can also manage EEE, so enable the LPI state and start the timer
+ * to verify if the tx path can enter in LPI state.
+ */
+bool sxgbe_eee_init(struct sxgbe_priv_data * const priv)
+{
+ bool ret = false;
+
+ /* MAC core supports the EEE feature. */
+ if (priv->hw_cap.eee) {
+ /* Check if the PHY supports EEE */
+ if (phy_init_eee(priv->phydev, 1))
+ return false;
+
+ priv->eee_active = 1;
+ init_timer(&priv->eee_ctrl_timer);
+ priv->eee_ctrl_timer.function = sxgbe_eee_ctrl_timer;
+ priv->eee_ctrl_timer.data = (unsigned long)priv;
+ priv->eee_ctrl_timer.expires = SXGBE_LPI_TIMER(eee_timer);
+ add_timer(&priv->eee_ctrl_timer);
+
+ priv->hw->mac->set_eee_timer(priv->ioaddr,
+ SXGBE_DEFAULT_LPI_TIMER,
+ priv->tx_lpi_timer);
+
+ pr_info("Energy-Efficient Ethernet initialized\n");
+
+ ret = true;
+ }
+
+ return ret;
+}
+
+static void sxgbe_eee_adjust(const struct sxgbe_priv_data *priv)
+{
+ /* When the EEE has been already initialised we have to
+ * modify the PLS bit in the LPI ctrl & status reg according
+ * to the PHY link status. For this reason.
+ */
+ if (priv->eee_enabled)
+ priv->hw->mac->set_eee_pls(priv->ioaddr, priv->phydev->link);
+}
+
+/**
+ * sxgbe_clk_csr_set - dynamically set the MDC clock
+ * @priv: driver private structure
+ * Description: this is to dynamically set the MDC clock according to the csr
+ * clock input.
+ */
+static void sxgbe_clk_csr_set(struct sxgbe_priv_data *priv)
+{
+ u32 clk_rate = clk_get_rate(priv->sxgbe_clk);
+
+ /* assign the proper divider, this will be used during
+ * mdio communication
+ */
+ if (clk_rate < SXGBE_CSR_F_150M)
+ priv->clk_csr = SXGBE_CSR_100_150M;
+ else if (clk_rate <= SXGBE_CSR_F_250M)
+ priv->clk_csr = SXGBE_CSR_150_250M;
+ else if (clk_rate <= SXGBE_CSR_F_300M)
+ priv->clk_csr = SXGBE_CSR_250_300M;
+ else if (clk_rate <= SXGBE_CSR_F_350M)
+ priv->clk_csr = SXGBE_CSR_300_350M;
+ else if (clk_rate <= SXGBE_CSR_F_400M)
+ priv->clk_csr = SXGBE_CSR_350_400M;
+ else if (clk_rate <= SXGBE_CSR_F_500M)
+ priv->clk_csr = SXGBE_CSR_400_500M;
+}
+
+/* minimum number of free TX descriptors required to wake up TX process */
+#define SXGBE_TX_THRESH(x) (x->dma_tx_size/4)
+
+static inline u32 sxgbe_tx_avail(struct sxgbe_tx_queue *queue, int tx_qsize)
+{
+ return queue->dirty_tx + tx_qsize - queue->cur_tx - 1;
+}
+
+/**
+ * sxgbe_adjust_link
+ * @dev: net device structure
+ * Description: it adjusts the link parameters.
+ */
+static void sxgbe_adjust_link(struct net_device *dev)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ struct phy_device *phydev = priv->phydev;
+ u8 new_state = 0;
+ u8 speed = 0xff;
+
+ if (!phydev)
+ return;
+
+ /* SXGBE is not supporting auto-negotiation and
+ * half duplex mode. so, not handling duplex change
+ * in this function. only handling speed and link status
+ */
+ if (phydev->link) {
+ if (phydev->speed != priv->speed) {
+ new_state = 1;
+ switch (phydev->speed) {
+ case SPEED_10000:
+ speed = SXGBE_SPEED_10G;
+ break;
+ case SPEED_2500:
+ speed = SXGBE_SPEED_2_5G;
+ break;
+ case SPEED_1000:
+ speed = SXGBE_SPEED_1G;
+ break;
+ default:
+ netif_err(priv, link, dev,
+ "Speed (%d) not supported\n",
+ phydev->speed);
+ }
+
+ priv->speed = phydev->speed;
+ priv->hw->mac->set_speed(priv->ioaddr, speed);
+ }
+
+ if (!priv->oldlink) {
+ new_state = 1;
+ priv->oldlink = 1;
+ }
+ } else if (priv->oldlink) {
+ new_state = 1;
+ priv->oldlink = 0;
+ priv->speed = SPEED_UNKNOWN;
+ }
+
+ if (new_state & netif_msg_link(priv))
+ phy_print_status(phydev);
+
+ /* Alter the MAC settings for EEE */
+ sxgbe_eee_adjust(priv);
+}
+
+/**
+ * sxgbe_init_phy - PHY initialization
+ * @dev: net device structure
+ * Description: it initializes the driver's PHY state, and attaches the PHY
+ * to the mac driver.
+ * Return value:
+ * 0 on success
+ */
+static int sxgbe_init_phy(struct net_device *ndev)
+{
+ char phy_id_fmt[MII_BUS_ID_SIZE + 3];
+ char bus_id[MII_BUS_ID_SIZE];
+ struct phy_device *phydev;
+ struct sxgbe_priv_data *priv = netdev_priv(ndev);
+ int phy_iface = priv->plat->interface;
+
+ /* assign default link status */
+ priv->oldlink = 0;
+ priv->speed = SPEED_UNKNOWN;
+ priv->oldduplex = DUPLEX_UNKNOWN;
+
+ if (priv->plat->phy_bus_name)
+ snprintf(bus_id, MII_BUS_ID_SIZE, "%s-%x",
+ priv->plat->phy_bus_name, priv->plat->bus_id);
+ else
+ snprintf(bus_id, MII_BUS_ID_SIZE, "sxgbe-%x",
+ priv->plat->bus_id);
+
+ snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
+ priv->plat->phy_addr);
+ netdev_dbg(ndev, "%s: trying to attach to %s\n", __func__, phy_id_fmt);
+
+ phydev = phy_connect(ndev, phy_id_fmt, &sxgbe_adjust_link, phy_iface);
+
+ if (IS_ERR(phydev)) {
+ netdev_err(ndev, "Could not attach to PHY\n");
+ return PTR_ERR(phydev);
+ }
+
+ /* Stop Advertising 1000BASE Capability if interface is not GMII */
+ if ((phy_iface == PHY_INTERFACE_MODE_MII) ||
+ (phy_iface == PHY_INTERFACE_MODE_RMII))
+ phydev->advertising &= ~(SUPPORTED_1000baseT_Half |
+ SUPPORTED_1000baseT_Full);
+ if (phydev->phy_id == 0) {
+ phy_disconnect(phydev);
+ return -ENODEV;
+ }
+
+ netdev_dbg(ndev, "%s: attached to PHY (UID 0x%x) Link = %d\n",
+ __func__, phydev->phy_id, phydev->link);
+
+ /* save phy device in private structure */
+ priv->phydev = phydev;
+
+ return 0;
+}
+
+/**
+ * sxgbe_clear_descriptors: clear descriptors
+ * @priv: driver private structure
+ * Description: this function is called to clear the tx and rx descriptors
+ * in case of both basic and extended descriptors are used.
+ */
+static void sxgbe_clear_descriptors(struct sxgbe_priv_data *priv)
+{
+ int i, j;
+ unsigned int txsize = priv->dma_tx_size;
+ unsigned int rxsize = priv->dma_rx_size;
+
+ /* Clear the Rx/Tx descriptors */
+ for (j = 0; j < SXGBE_RX_QUEUES; j++) {
+ for (i = 0; i < rxsize; i++)
+ priv->hw->desc->init_rx_desc(&priv->rxq[j]->dma_rx[i],
+ priv->use_riwt, priv->mode,
+ (i == rxsize - 1));
+ }
+
+ for (j = 0; j < SXGBE_TX_QUEUES; j++) {
+ for (i = 0; i < txsize; i++)
+ priv->hw->desc->init_tx_desc(&priv->txq[j]->dma_tx[i]);
+ }
+}
+
+static int sxgbe_init_rx_buffers(struct net_device *dev,
+ struct sxgbe_rx_norm_desc *p, int i,
+ unsigned int dma_buf_sz,
+ struct sxgbe_rx_queue *rx_ring)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ struct sk_buff *skb;
+
+ skb = __netdev_alloc_skb_ip_align(dev, dma_buf_sz, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ rx_ring->rx_skbuff[i] = skb;
+ rx_ring->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
+ dma_buf_sz, DMA_FROM_DEVICE);
+
+ if (dma_mapping_error(priv->device, rx_ring->rx_skbuff_dma[i])) {
+ netdev_err(dev, "%s: DMA mapping error\n", __func__);
+ dev_kfree_skb_any(skb);
+ return -EINVAL;
+ }
+
+ p->rdes23.rx_rd_des23.buf2_addr = rx_ring->rx_skbuff_dma[i];
+
+ return 0;
+}
+/**
+ * init_tx_ring - init the TX descriptor ring
+ * @dev: net device structure
+ * @tx_ring: ring to be intialised
+ * @tx_rsize: ring size
+ * Description: this function initializes the DMA TX descriptor
+ */
+static int init_tx_ring(struct device *dev, u8 queue_no,
+ struct sxgbe_tx_queue *tx_ring, int tx_rsize)
+{
+ /* TX ring is not allcoated */
+ if (!tx_ring) {
+ dev_err(dev, "No memory for TX queue of SXGBE\n");
+ return -ENOMEM;
+ }
+
+ /* allocate memory for TX descriptors */
+ tx_ring->dma_tx = dma_zalloc_coherent(dev,
+ tx_rsize * sizeof(struct sxgbe_tx_norm_desc),
+ &tx_ring->dma_tx_phy, GFP_KERNEL);
+ if (!tx_ring->dma_tx)
+ return -ENOMEM;
+
+ /* allocate memory for TX skbuff array */
+ tx_ring->tx_skbuff_dma = devm_kcalloc(dev, tx_rsize,
+ sizeof(dma_addr_t), GFP_KERNEL);
+ if (!tx_ring->tx_skbuff_dma)
+ goto dmamem_err;
+
+ tx_ring->tx_skbuff = devm_kcalloc(dev, tx_rsize,
+ sizeof(struct sk_buff *), GFP_KERNEL);
+
+ if (!tx_ring->tx_skbuff)
+ goto dmamem_err;
+
+ /* assign queue number */
+ tx_ring->queue_no = queue_no;
+
+ /* initalise counters */
+ tx_ring->dirty_tx = 0;
+ tx_ring->cur_tx = 0;
+
+ /* initalise TX queue lock */
+ spin_lock_init(&tx_ring->tx_lock);
+
+ return 0;
+
+dmamem_err:
+ dma_free_coherent(dev, tx_rsize * sizeof(struct sxgbe_tx_norm_desc),
+ tx_ring->dma_tx, tx_ring->dma_tx_phy);
+ return -ENOMEM;
+}
+
+/**
+ * free_rx_ring - free the RX descriptor ring
+ * @dev: net device structure
+ * @rx_ring: ring to be intialised
+ * @rx_rsize: ring size
+ * Description: this function initializes the DMA RX descriptor
+ */
+void free_rx_ring(struct device *dev, struct sxgbe_rx_queue *rx_ring,
+ int rx_rsize)
+{
+ dma_free_coherent(dev, rx_rsize * sizeof(struct sxgbe_rx_norm_desc),
+ rx_ring->dma_rx, rx_ring->dma_rx_phy);
+ kfree(rx_ring->rx_skbuff_dma);
+ kfree(rx_ring->rx_skbuff);
+}
+
+/**
+ * init_rx_ring - init the RX descriptor ring
+ * @dev: net device structure
+ * @rx_ring: ring to be intialised
+ * @rx_rsize: ring size
+ * Description: this function initializes the DMA RX descriptor
+ */
+static int init_rx_ring(struct net_device *dev, u8 queue_no,
+ struct sxgbe_rx_queue *rx_ring, int rx_rsize)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ int desc_index;
+ unsigned int bfsize = 0;
+ unsigned int ret = 0;
+
+ /* Set the max buffer size according to the MTU. */
+ bfsize = ALIGN(dev->mtu + ETH_HLEN + ETH_FCS_LEN + NET_IP_ALIGN, 8);
+
+ netif_dbg(priv, probe, dev, "%s: bfsize %d\n", __func__, bfsize);
+
+ /* RX ring is not allcoated */
+ if (rx_ring == NULL) {
+ netdev_err(dev, "No memory for RX queue\n");
+ goto error;
+ }
+
+ /* assign queue number */
+ rx_ring->queue_no = queue_no;
+
+ /* allocate memory for RX descriptors */
+ rx_ring->dma_rx = dma_zalloc_coherent(priv->device,
+ rx_rsize * sizeof(struct sxgbe_rx_norm_desc),
+ &rx_ring->dma_rx_phy, GFP_KERNEL);
+
+ if (rx_ring->dma_rx == NULL)
+ goto error;
+
+ /* allocate memory for RX skbuff array */
+ rx_ring->rx_skbuff_dma = kmalloc_array(rx_rsize,
+ sizeof(dma_addr_t), GFP_KERNEL);
+ if (rx_ring->rx_skbuff_dma == NULL)
+ goto dmamem_err;
+
+ rx_ring->rx_skbuff = kmalloc_array(rx_rsize,
+ sizeof(struct sk_buff *), GFP_KERNEL);
+ if (rx_ring->rx_skbuff == NULL)
+ goto rxbuff_err;
+
+ /* initialise the buffers */
+ for (desc_index = 0; desc_index < rx_rsize; desc_index++) {
+ struct sxgbe_rx_norm_desc *p;
+ p = rx_ring->dma_rx + desc_index;
+ ret = sxgbe_init_rx_buffers(dev, p, desc_index,
+ bfsize, rx_ring);
+ if (ret)
+ goto err_init_rx_buffers;
+ }
+
+ /* initalise counters */
+ rx_ring->cur_rx = 0;
+ rx_ring->dirty_rx = (unsigned int)(desc_index - rx_rsize);
+ priv->dma_buf_sz = bfsize;
+
+ return 0;
+
+err_init_rx_buffers:
+ while (--desc_index >= 0)
+ free_rx_ring(priv->device, rx_ring, desc_index);
+ kfree(rx_ring->rx_skbuff);
+rxbuff_err:
+ kfree(rx_ring->rx_skbuff_dma);
+dmamem_err:
+ dma_free_coherent(priv->device,
+ rx_rsize * sizeof(struct sxgbe_rx_norm_desc),
+ rx_ring->dma_rx, rx_ring->dma_rx_phy);
+error:
+ return -ENOMEM;
+}
+/**
+ * free_tx_ring - free the TX descriptor ring
+ * @dev: net device structure
+ * @tx_ring: ring to be intialised
+ * @tx_rsize: ring size
+ * Description: this function initializes the DMA TX descriptor
+ */
+void free_tx_ring(struct device *dev, struct sxgbe_tx_queue *tx_ring,
+ int tx_rsize)
+{
+ dma_free_coherent(dev, tx_rsize * sizeof(struct sxgbe_tx_norm_desc),
+ tx_ring->dma_tx, tx_ring->dma_tx_phy);
+}
+
+/**
+ * init_dma_desc_rings - init the RX/TX descriptor rings
+ * @dev: net device structure
+ * Description: this function initializes the DMA RX/TX descriptors
+ * and allocates the socket buffers. It suppors the chained and ring
+ * modes.
+ */
+static int init_dma_desc_rings(struct net_device *netd)
+{
+ int queue_num, ret;
+ struct sxgbe_priv_data *priv = netdev_priv(netd);
+ int tx_rsize = priv->dma_tx_size;
+ int rx_rsize = priv->dma_rx_size;
+
+ /* Allocate memory for queue structures and TX descs */
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+ ret = init_tx_ring(priv->device, queue_num,
+ priv->txq[queue_num], tx_rsize);
+ if (ret) {
+ dev_err(&netd->dev, "TX DMA ring allocation failed!\n");
+ goto txalloc_err;
+ }
+
+ /* save private pointer in each ring this
+ * pointer is needed during cleaing TX queue
+ */
+ priv->txq[queue_num]->priv_ptr = priv;
+ }
+
+ /* Allocate memory for queue structures and RX descs */
+ SXGBE_FOR_EACH_QUEUE(SXGBE_RX_QUEUES, queue_num) {
+ ret = init_rx_ring(netd, queue_num,
+ priv->rxq[queue_num], rx_rsize);
+ if (ret) {
+ netdev_err(netd, "RX DMA ring allocation failed!!\n");
+ goto rxalloc_err;
+ }
+
+ /* save private pointer in each ring this
+ * pointer is needed during cleaing TX queue
+ */
+ priv->rxq[queue_num]->priv_ptr = priv;
+ }
+
+ sxgbe_clear_descriptors(priv);
+
+ return 0;
+
+txalloc_err:
+ while (queue_num--)
+ free_tx_ring(priv->device, priv->txq[queue_num], tx_rsize);
+ return ret;
+
+rxalloc_err:
+ while (queue_num--)
+ free_rx_ring(priv->device, priv->rxq[queue_num], rx_rsize);
+ return ret;
+}
+
+static void tx_free_ring_skbufs(struct sxgbe_tx_queue *txqueue)
+{
+ int dma_desc;
+ struct sxgbe_priv_data *priv = txqueue->priv_ptr;
+ int tx_rsize = priv->dma_tx_size;
+
+ for (dma_desc = 0; dma_desc < tx_rsize; dma_desc++) {
+ struct sxgbe_tx_norm_desc *tdesc = txqueue->dma_tx + dma_desc;
+
+ if (txqueue->tx_skbuff_dma[dma_desc])
+ dma_unmap_single(priv->device,
+ txqueue->tx_skbuff_dma[dma_desc],
+ priv->hw->desc->get_tx_len(tdesc),
+ DMA_TO_DEVICE);
+
+ dev_kfree_skb_any(txqueue->tx_skbuff[dma_desc]);
+ txqueue->tx_skbuff[dma_desc] = NULL;
+ txqueue->tx_skbuff_dma[dma_desc] = 0;
+ }
+}
+
+
+static void dma_free_tx_skbufs(struct sxgbe_priv_data *priv)
+{
+ int queue_num;
+
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+ struct sxgbe_tx_queue *tqueue = priv->txq[queue_num];
+ tx_free_ring_skbufs(tqueue);
+ }
+}
+
+static void free_dma_desc_resources(struct sxgbe_priv_data *priv)
+{
+ int queue_num;
+ int tx_rsize = priv->dma_tx_size;
+ int rx_rsize = priv->dma_rx_size;
+
+ /* Release the DMA TX buffers */
+ dma_free_tx_skbufs(priv);
+
+ /* Release the TX ring memory also */
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+ free_tx_ring(priv->device, priv->txq[queue_num], tx_rsize);
+ }
+
+ /* Release the RX ring memory also */
+ SXGBE_FOR_EACH_QUEUE(SXGBE_RX_QUEUES, queue_num) {
+ free_rx_ring(priv->device, priv->rxq[queue_num], rx_rsize);
+ }
+}
+
+static int txring_mem_alloc(struct sxgbe_priv_data *priv)
+{
+ int queue_num;
+
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+ priv->txq[queue_num] = devm_kmalloc(priv->device,
+ sizeof(struct sxgbe_tx_queue), GFP_KERNEL);
+ if (!priv->txq[queue_num])
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int rxring_mem_alloc(struct sxgbe_priv_data *priv)
+{
+ int queue_num;
+
+ SXGBE_FOR_EACH_QUEUE(SXGBE_RX_QUEUES, queue_num) {
+ priv->rxq[queue_num] = devm_kmalloc(priv->device,
+ sizeof(struct sxgbe_rx_queue), GFP_KERNEL);
+ if (!priv->rxq[queue_num])
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+/**
+ * sxgbe_mtl_operation_mode - HW MTL operation mode
+ * @priv: driver private structure
+ * Description: it sets the MTL operation mode: tx/rx MTL thresholds
+ * or Store-And-Forward capability.
+ */
+static void sxgbe_mtl_operation_mode(struct sxgbe_priv_data *priv)
+{
+ int queue_num;
+
+ /* TX/RX threshold control */
+ if (likely(priv->plat->force_sf_dma_mode)) {
+ /* set TC mode for TX QUEUES */
+ SXGBE_FOR_EACH_QUEUE(priv->hw_cap.tx_mtl_queues, queue_num)
+ priv->hw->mtl->set_tx_mtl_mode(priv->ioaddr, queue_num,
+ SXGBE_MTL_SFMODE);
+ priv->tx_tc = SXGBE_MTL_SFMODE;
+
+ /* set TC mode for RX QUEUES */
+ SXGBE_FOR_EACH_QUEUE(priv->hw_cap.rx_mtl_queues, queue_num)
+ priv->hw->mtl->set_rx_mtl_mode(priv->ioaddr, queue_num,
+ SXGBE_MTL_SFMODE);
+ priv->rx_tc = SXGBE_MTL_SFMODE;
+ } else if (unlikely(priv->plat->force_thresh_dma_mode)) {
+ /* set TC mode for TX QUEUES */
+ SXGBE_FOR_EACH_QUEUE(priv->hw_cap.tx_mtl_queues, queue_num)
+ priv->hw->mtl->set_tx_mtl_mode(priv->ioaddr, queue_num,
+ priv->tx_tc);
+ /* set TC mode for RX QUEUES */
+ SXGBE_FOR_EACH_QUEUE(priv->hw_cap.rx_mtl_queues, queue_num)
+ priv->hw->mtl->set_rx_mtl_mode(priv->ioaddr, queue_num,
+ priv->rx_tc);
+ } else {
+ pr_err("ERROR: %s: Invalid TX threshold mode\n", __func__);
+ }
+}
+
+/**
+ * sxgbe_tx_queue_clean:
+ * @priv: driver private structure
+ * Description: it reclaims resources after transmission completes.
+ */
+static void sxgbe_tx_queue_clean(struct sxgbe_tx_queue *tqueue)
+{
+ struct sxgbe_priv_data *priv = tqueue->priv_ptr;
+ unsigned int tx_rsize = priv->dma_tx_size;
+ struct netdev_queue *dev_txq;
+ u8 queue_no = tqueue->queue_no;
+
+ dev_txq = netdev_get_tx_queue(priv->dev, queue_no);
+
+ spin_lock(&tqueue->tx_lock);
+
+ priv->xstats.tx_clean++;
+ while (tqueue->dirty_tx != tqueue->cur_tx) {
+ unsigned int entry = tqueue->dirty_tx % tx_rsize;
+ struct sk_buff *skb = tqueue->tx_skbuff[entry];
+ struct sxgbe_tx_norm_desc *p;
+
+ p = tqueue->dma_tx + entry;
+
+ /* Check if the descriptor is owned by the DMA. */
+ if (priv->hw->desc->get_tx_owner(p))
+ break;
+
+ if (netif_msg_tx_done(priv))
+ pr_debug("%s: curr %d, dirty %d\n",
+ __func__, tqueue->cur_tx, tqueue->dirty_tx);
+
+ if (likely(tqueue->tx_skbuff_dma[entry])) {
+ dma_unmap_single(priv->device,
+ tqueue->tx_skbuff_dma[entry],
+ priv->hw->desc->get_tx_len(p),
+ DMA_TO_DEVICE);
+ tqueue->tx_skbuff_dma[entry] = 0;
+ }
+
+ if (likely(skb)) {
+ dev_kfree_skb(skb);
+ tqueue->tx_skbuff[entry] = NULL;
+ }
+
+ priv->hw->desc->release_tx_desc(p);
+
+ tqueue->dirty_tx++;
+ }
+
+ /* wake up queue */
+ if (unlikely(netif_tx_queue_stopped(dev_txq) &&
+ sxgbe_tx_avail(tqueue, tx_rsize) > SXGBE_TX_THRESH(priv))) {
+ netif_tx_lock(priv->dev);
+ if (netif_tx_queue_stopped(dev_txq) &&
+ sxgbe_tx_avail(tqueue, tx_rsize) > SXGBE_TX_THRESH(priv)) {
+ if (netif_msg_tx_done(priv))
+ pr_debug("%s: restart transmit\n", __func__);
+ netif_tx_wake_queue(dev_txq);
+ }
+ netif_tx_unlock(priv->dev);
+ }
+
+ spin_unlock(&tqueue->tx_lock);
+}
+
+/**
+ * sxgbe_tx_clean:
+ * @priv: driver private structure
+ * Description: it reclaims resources after transmission completes.
+ */
+static void sxgbe_tx_all_clean(struct sxgbe_priv_data * const priv)
+{
+ u8 queue_num;
+
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+ struct sxgbe_tx_queue *tqueue = priv->txq[queue_num];
+
+ sxgbe_tx_queue_clean(tqueue);
+ }
+
+ if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) {
+ sxgbe_enable_eee_mode(priv);
+ mod_timer(&priv->eee_ctrl_timer, SXGBE_LPI_TIMER(eee_timer));
+ }
+}
+
+/**
+ * sxgbe_restart_tx_queue: irq tx error mng function
+ * @priv: driver private structure
+ * Description: it cleans the descriptors and restarts the transmission
+ * in case of errors.
+ */
+static void sxgbe_restart_tx_queue(struct sxgbe_priv_data *priv, int queue_num)
+{
+ struct sxgbe_tx_queue *tx_ring = priv->txq[queue_num];
+ struct netdev_queue *dev_txq = netdev_get_tx_queue(priv->dev,
+ queue_num);
+
+ /* stop the queue */
+ netif_tx_stop_queue(dev_txq);
+
+ /* stop the tx dma */
+ priv->hw->dma->stop_tx_queue(priv->ioaddr, queue_num);
+
+ /* free the skbuffs of the ring */
+ tx_free_ring_skbufs(tx_ring);
+
+ /* initalise counters */
+ tx_ring->cur_tx = 0;
+ tx_ring->dirty_tx = 0;
+
+ /* start the tx dma */
+ priv->hw->dma->start_tx_queue(priv->ioaddr, queue_num);
+
+ priv->dev->stats.tx_errors++;
+
+ /* wakeup the queue */
+ netif_tx_wake_queue(dev_txq);
+}
+
+/**
+ * sxgbe_reset_all_tx_queues: irq tx error mng function
+ * @priv: driver private structure
+ * Description: it cleans all the descriptors and
+ * restarts the transmission on all queues in case of errors.
+ */
+static void sxgbe_reset_all_tx_queues(struct sxgbe_priv_data *priv)
+{
+ int queue_num;
+
+ /* On TX timeout of net device, resetting of all queues
+ * may not be proper way, revisit this later if needed
+ */
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num)
+ sxgbe_restart_tx_queue(priv, queue_num);
+}
+
+/**
+ * sxgbe_get_hw_features: get XMAC capabilities from the HW cap. register.
+ * @priv: driver private structure
+ * Description:
+ * new GMAC chip generations have a new register to indicate the
+ * presence of the optional feature/functions.
+ * This can be also used to override the value passed through the
+ * platform and necessary for old MAC10/100 and GMAC chips.
+ */
+static int sxgbe_get_hw_features(struct sxgbe_priv_data * const priv)
+{
+ int rval = 0;
+ struct sxgbe_hw_features *features = &priv->hw_cap;
+
+ /* Read First Capability Register CAP[0] */
+ rval = priv->hw->mac->get_hw_feature(priv->ioaddr, 0);
+ if (rval) {
+ features->pmt_remote_wake_up =
+ SXGBE_HW_FEAT_PMT_TEMOTE_WOP(rval);
+ features->pmt_magic_frame = SXGBE_HW_FEAT_PMT_MAGIC_PKT(rval);
+ features->atime_stamp = SXGBE_HW_FEAT_IEEE1500_2008(rval);
+ features->tx_csum_offload =
+ SXGBE_HW_FEAT_TX_CSUM_OFFLOAD(rval);
+ features->rx_csum_offload =
+ SXGBE_HW_FEAT_RX_CSUM_OFFLOAD(rval);
+ features->multi_macaddr = SXGBE_HW_FEAT_MACADDR_COUNT(rval);
+ features->tstamp_srcselect = SXGBE_HW_FEAT_TSTMAP_SRC(rval);
+ features->sa_vlan_insert = SXGBE_HW_FEAT_SRCADDR_VLAN(rval);
+ features->eee = SXGBE_HW_FEAT_EEE(rval);
+ }
+
+ /* Read First Capability Register CAP[1] */
+ rval = priv->hw->mac->get_hw_feature(priv->ioaddr, 1);
+ if (rval) {
+ features->rxfifo_size = SXGBE_HW_FEAT_RX_FIFO_SIZE(rval);
+ features->txfifo_size = SXGBE_HW_FEAT_TX_FIFO_SIZE(rval);
+ features->atstmap_hword = SXGBE_HW_FEAT_TX_FIFO_SIZE(rval);
+ features->dcb_enable = SXGBE_HW_FEAT_DCB(rval);
+ features->splithead_enable = SXGBE_HW_FEAT_SPLIT_HDR(rval);
+ features->tcpseg_offload = SXGBE_HW_FEAT_TSO(rval);
+ features->debug_mem = SXGBE_HW_FEAT_DEBUG_MEM_IFACE(rval);
+ features->rss_enable = SXGBE_HW_FEAT_RSS(rval);
+ features->hash_tsize = SXGBE_HW_FEAT_HASH_TABLE_SIZE(rval);
+ features->l3l4_filer_size = SXGBE_HW_FEAT_L3L4_FILTER_NUM(rval);
+ }
+
+ /* Read First Capability Register CAP[2] */
+ rval = priv->hw->mac->get_hw_feature(priv->ioaddr, 2);
+ if (rval) {
+ features->rx_mtl_queues = SXGBE_HW_FEAT_RX_MTL_QUEUES(rval);
+ features->tx_mtl_queues = SXGBE_HW_FEAT_TX_MTL_QUEUES(rval);
+ features->rx_dma_channels = SXGBE_HW_FEAT_RX_DMA_CHANNELS(rval);
+ features->tx_dma_channels = SXGBE_HW_FEAT_TX_DMA_CHANNELS(rval);
+ features->pps_output_count = SXGBE_HW_FEAT_PPS_OUTPUTS(rval);
+ features->aux_input_count = SXGBE_HW_FEAT_AUX_SNAPSHOTS(rval);
+ }
+
+ return rval;
+}
+
+/**
+ * sxgbe_check_ether_addr: check if the MAC addr is valid
+ * @priv: driver private structure
+ * Description:
+ * it is to verify if the MAC address is valid, in case of failures it
+ * generates a random MAC address
+ */
+static void sxgbe_check_ether_addr(struct sxgbe_priv_data *priv)
+{
+ if (!is_valid_ether_addr(priv->dev->dev_addr)) {
+ priv->hw->mac->get_umac_addr((void __iomem *)
+ priv->ioaddr,
+ priv->dev->dev_addr, 0);
+ if (!is_valid_ether_addr(priv->dev->dev_addr))
+ eth_hw_addr_random(priv->dev);
+ }
+ dev_info(priv->device, "device MAC address %pM\n",
+ priv->dev->dev_addr);
+}
+
+/**
+ * sxgbe_init_dma_engine: DMA init.
+ * @priv: driver private structure
+ * Description:
+ * It inits the DMA invoking the specific SXGBE callback.
+ * Some DMA parameters can be passed from the platform;
+ * in case of these are not passed a default is kept for the MAC or GMAC.
+ */
+static int sxgbe_init_dma_engine(struct sxgbe_priv_data *priv)
+{
+ int pbl = DEFAULT_DMA_PBL, fixed_burst = 0, burst_map = 0;
+ int queue_num;
+
+ if (priv->plat->dma_cfg) {
+ pbl = priv->plat->dma_cfg->pbl;
+ fixed_burst = priv->plat->dma_cfg->fixed_burst;
+ burst_map = priv->plat->dma_cfg->burst_map;
+ }
+
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num)
+ priv->hw->dma->cha_init(priv->ioaddr, queue_num,
+ fixed_burst, pbl,
+ (priv->txq[queue_num])->dma_tx_phy,
+ (priv->rxq[queue_num])->dma_rx_phy,
+ priv->dma_tx_size, priv->dma_rx_size);
+
+ return priv->hw->dma->init(priv->ioaddr, fixed_burst, burst_map);
+}
+
+/**
+ * sxgbe_init_mtl_engine: MTL init.
+ * @priv: driver private structure
+ * Description:
+ * It inits the MTL invoking the specific SXGBE callback.
+ */
+static void sxgbe_init_mtl_engine(struct sxgbe_priv_data *priv)
+{
+ int queue_num;
+
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+ priv->hw->mtl->mtl_set_txfifosize(priv->ioaddr, queue_num,
+ priv->hw_cap.tx_mtl_qsize);
+ priv->hw->mtl->mtl_enable_txqueue(priv->ioaddr, queue_num);
+ }
+}
+
+/**
+ * sxgbe_disable_mtl_engine: MTL disable.
+ * @priv: driver private structure
+ * Description:
+ * It disables the MTL queues by invoking the specific SXGBE callback.
+ */
+static void sxgbe_disable_mtl_engine(struct sxgbe_priv_data *priv)
+{
+ int queue_num;
+
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num)
+ priv->hw->mtl->mtl_disable_txqueue(priv->ioaddr, queue_num);
+}
+
+
+/**
+ * sxgbe_tx_timer: mitigation sw timer for tx.
+ * @data: data pointer
+ * Description:
+ * This is the timer handler to directly invoke the sxgbe_tx_clean.
+ */
+static void sxgbe_tx_timer(unsigned long data)
+{
+ struct sxgbe_tx_queue *p = (struct sxgbe_tx_queue *)data;
+ sxgbe_tx_queue_clean(p);
+}
+
+/**
+ * sxgbe_init_tx_coalesce: init tx mitigation options.
+ * @priv: driver private structure
+ * Description:
+ * This inits the transmit coalesce parameters: i.e. timer rate,
+ * timer handler and default threshold used for enabling the
+ * interrupt on completion bit.
+ */
+static void sxgbe_tx_init_coalesce(struct sxgbe_priv_data *priv)
+{
+ u8 queue_num;
+
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+ struct sxgbe_tx_queue *p = priv->txq[queue_num];
+ p->tx_coal_frames = SXGBE_TX_FRAMES;
+ p->tx_coal_timer = SXGBE_COAL_TX_TIMER;
+ init_timer(&p->txtimer);
+ p->txtimer.expires = SXGBE_COAL_TIMER(p->tx_coal_timer);
+ p->txtimer.data = (unsigned long)&priv->txq[queue_num];
+ p->txtimer.function = sxgbe_tx_timer;
+ add_timer(&p->txtimer);
+ }
+}
+
+static void sxgbe_tx_del_timer(struct sxgbe_priv_data *priv)
+{
+ u8 queue_num;
+
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+ struct sxgbe_tx_queue *p = priv->txq[queue_num];
+ del_timer_sync(&p->txtimer);
+ }
+}
+
+/**
+ * sxgbe_open - open entry point of the driver
+ * @dev : pointer to the device structure.
+ * Description:
+ * This function is the open entry point of the driver.
+ * Return value:
+ * 0 on success and an appropriate (-)ve integer as defined in errno.h
+ * file on failure.
+ */
+static int sxgbe_open(struct net_device *dev)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ int ret, queue_num;
+
+ clk_prepare_enable(priv->sxgbe_clk);
+
+ sxgbe_check_ether_addr(priv);
+
+ /* Init the phy */
+ ret = sxgbe_init_phy(dev);
+ if (ret) {
+ netdev_err(dev, "%s: Cannot attach to PHY (error: %d)\n",
+ __func__, ret);
+ goto phy_error;
+ }
+
+ /* Create and initialize the TX/RX descriptors chains. */
+ priv->dma_tx_size = SXGBE_ALIGN(DMA_TX_SIZE);
+ priv->dma_rx_size = SXGBE_ALIGN(DMA_RX_SIZE);
+ priv->dma_buf_sz = SXGBE_ALIGN(DMA_BUFFER_SIZE);
+ priv->tx_tc = TC_DEFAULT;
+ priv->rx_tc = TC_DEFAULT;
+ init_dma_desc_rings(dev);
+
+ /* DMA initialization and SW reset */
+ ret = sxgbe_init_dma_engine(priv);
+ if (ret < 0) {
+ netdev_err(dev, "%s: DMA initialization failed\n", __func__);
+ goto init_error;
+ }
+
+ /* MTL initialization */
+ sxgbe_init_mtl_engine(priv);
+
+ /* Copy the MAC addr into the HW */
+ priv->hw->mac->set_umac_addr(priv->ioaddr, dev->dev_addr, 0);
+
+ /* Initialize the MAC Core */
+ priv->hw->mac->core_init(priv->ioaddr);
+
+ /* Request the IRQ lines */
+ ret = devm_request_irq(priv->device, priv->irq, sxgbe_common_interrupt,
+ IRQF_SHARED, dev->name, dev);
+ if (unlikely(ret < 0)) {
+ netdev_err(dev, "%s: ERROR: allocating the IRQ %d (error: %d)\n",
+ __func__, priv->irq, ret);
+ goto init_error;
+ }
+
+ /* If the LPI irq is different from the mac irq
+ * register a dedicated handler
+ */
+ if (priv->lpi_irq != dev->irq) {
+ ret = devm_request_irq(priv->device, priv->lpi_irq,
+ sxgbe_common_interrupt,
+ IRQF_SHARED, dev->name, dev);
+ if (unlikely(ret < 0)) {
+ netdev_err(dev, "%s: ERROR: allocating the LPI IRQ %d (%d)\n",
+ __func__, priv->lpi_irq, ret);
+ goto init_error;
+ }
+ }
+
+ /* Request TX DMA irq lines */
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+ ret = devm_request_irq(priv->device,
+ (priv->txq[queue_num])->irq_no,
+ sxgbe_tx_interrupt, 0,
+ dev->name, priv->txq[queue_num]);
+ if (unlikely(ret < 0)) {
+ netdev_err(dev, "%s: ERROR: allocating TX IRQ %d (error: %d)\n",
+ __func__, priv->irq, ret);
+ goto init_error;
+ }
+ }
+
+ /* Request RX DMA irq lines */
+ SXGBE_FOR_EACH_QUEUE(SXGBE_RX_QUEUES, queue_num) {
+ ret = devm_request_irq(priv->device,
+ (priv->rxq[queue_num])->irq_no,
+ sxgbe_rx_interrupt, 0,
+ dev->name, priv->rxq[queue_num]);
+ if (unlikely(ret < 0)) {
+ netdev_err(dev, "%s: ERROR: allocating TX IRQ %d (error: %d)\n",
+ __func__, priv->irq, ret);
+ goto init_error;
+ }
+ }
+
+ /* Enable the MAC Rx/Tx */
+ priv->hw->mac->enable_tx(priv->ioaddr, true);
+ priv->hw->mac->enable_rx(priv->ioaddr, true);
+
+ /* Set the HW DMA mode and the COE */
+ sxgbe_mtl_operation_mode(priv);
+
+ /* Extra statistics */
+ memset(&priv->xstats, 0, sizeof(struct sxgbe_extra_stats));
+
+ priv->xstats.tx_threshold = priv->tx_tc;
+ priv->xstats.rx_threshold = priv->rx_tc;
+
+ /* Start the ball rolling... */
+ netdev_dbg(dev, "DMA RX/TX processes started...\n");
+ priv->hw->dma->start_tx(priv->ioaddr, SXGBE_TX_QUEUES);
+ priv->hw->dma->start_rx(priv->ioaddr, SXGBE_RX_QUEUES);
+
+ if (priv->phydev)
+ phy_start(priv->phydev);
+
+ /* initalise TX coalesce parameters */
+ sxgbe_tx_init_coalesce(priv);
+
+ if ((priv->use_riwt) && (priv->hw->dma->rx_watchdog)) {
+ priv->rx_riwt = SXGBE_MAX_DMA_RIWT;
+ priv->hw->dma->rx_watchdog(priv->ioaddr, SXGBE_MAX_DMA_RIWT);
+ }
+
+ priv->tx_lpi_timer = SXGBE_DEFAULT_LPI_TIMER;
+ priv->eee_enabled = sxgbe_eee_init(priv);
+
+ napi_enable(&priv->napi);
+ netif_start_queue(dev);
+
+ return 0;
+
+init_error:
+ free_dma_desc_resources(priv);
+ if (priv->phydev)
+ phy_disconnect(priv->phydev);
+phy_error:
+ clk_disable_unprepare(priv->sxgbe_clk);
+
+ return ret;
+}
+
+/**
+ * sxgbe_release - close entry point of the driver
+ * @dev : device pointer.
+ * Description:
+ * This is the stop entry point of the driver.
+ */
+static int sxgbe_release(struct net_device *dev)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+ if (priv->eee_enabled)
+ del_timer_sync(&priv->eee_ctrl_timer);
+
+ /* Stop and disconnect the PHY */
+ if (priv->phydev) {
+ phy_stop(priv->phydev);
+ phy_disconnect(priv->phydev);
+ priv->phydev = NULL;
+ }
+
+ netif_tx_stop_all_queues(dev);
+
+ napi_disable(&priv->napi);
+
+ /* delete TX timers */
+ sxgbe_tx_del_timer(priv);
+
+ /* Stop TX/RX DMA and clear the descriptors */
+ priv->hw->dma->stop_tx(priv->ioaddr, SXGBE_TX_QUEUES);
+ priv->hw->dma->stop_rx(priv->ioaddr, SXGBE_RX_QUEUES);
+
+ /* disable MTL queue */
+ sxgbe_disable_mtl_engine(priv);
+
+ /* Release and free the Rx/Tx resources */
+ free_dma_desc_resources(priv);
+
+ /* Disable the MAC Rx/Tx */
+ priv->hw->mac->enable_tx(priv->ioaddr, false);
+ priv->hw->mac->enable_rx(priv->ioaddr, false);
+
+ clk_disable_unprepare(priv->sxgbe_clk);
+
+ return 0;
+}
+
+/* Prepare first Tx descriptor for doing TSO operation */
+void sxgbe_tso_prepare(struct sxgbe_priv_data *priv,
+ struct sxgbe_tx_norm_desc *first_desc,
+ struct sk_buff *skb)
+{
+ unsigned int total_hdr_len, tcp_hdr_len;
+
+ /* Write first Tx descriptor with appropriate value */
+ tcp_hdr_len = tcp_hdrlen(skb);
+ total_hdr_len = skb_transport_offset(skb) + tcp_hdr_len;
+
+ first_desc->tdes01 = dma_map_single(priv->device, skb->data,
+ total_hdr_len, DMA_TO_DEVICE);
+ if (dma_mapping_error(priv->device, first_desc->tdes01))
+ pr_err("%s: TX dma mapping failed!!\n", __func__);
+
+ first_desc->tdes23.tx_rd_des23.first_desc = 1;
+ priv->hw->desc->tx_desc_enable_tse(first_desc, 1, total_hdr_len,
+ tcp_hdr_len,
+ skb->len - total_hdr_len);
+}
+
+/**
+ * sxgbe_xmit: Tx entry point of the driver
+ * @skb : the socket buffer
+ * @dev : device pointer
+ * Description : this is the tx entry point of the driver.
+ * It programs the chain or the ring and supports oversized frames
+ * and SG feature.
+ */
+static netdev_tx_t sxgbe_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ unsigned int entry, frag_num;
+ int cksum_flag = 0;
+ struct netdev_queue *dev_txq;
+ unsigned txq_index = skb_get_queue_mapping(skb);
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ unsigned int tx_rsize = priv->dma_tx_size;
+ struct sxgbe_tx_queue *tqueue = priv->txq[txq_index];
+ struct sxgbe_tx_norm_desc *tx_desc, *first_desc;
+ struct sxgbe_tx_ctxt_desc *ctxt_desc = NULL;
+ int nr_frags = skb_shinfo(skb)->nr_frags;
+ int no_pagedlen = skb_headlen(skb);
+ int is_jumbo = 0;
+ u16 cur_mss = skb_shinfo(skb)->gso_size;
+ u32 ctxt_desc_req = 0;
+
+ /* get the TX queue handle */
+ dev_txq = netdev_get_tx_queue(dev, txq_index);
+
+ if (unlikely(skb_is_gso(skb) && tqueue->prev_mss != cur_mss))
+ ctxt_desc_req = 1;
+
+ if (unlikely(vlan_tx_tag_present(skb) ||
+ ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+ tqueue->hwts_tx_en)))
+ ctxt_desc_req = 1;
+
+ /* get the spinlock */
+ spin_lock(&tqueue->tx_lock);
+
+ if (priv->tx_path_in_lpi_mode)
+ sxgbe_disable_eee_mode(priv);
+
+ if (unlikely(sxgbe_tx_avail(tqueue, tx_rsize) < nr_frags + 1)) {
+ if (!netif_tx_queue_stopped(dev_txq)) {
+ netif_tx_stop_queue(dev_txq);
+ netdev_err(dev, "%s: Tx Ring is full when %d queue is awake\n",
+ __func__, txq_index);
+ }
+ /* release the spin lock in case of BUSY */
+ spin_unlock(&tqueue->tx_lock);
+ return NETDEV_TX_BUSY;
+ }
+
+ entry = tqueue->cur_tx % tx_rsize;
+ tx_desc = tqueue->dma_tx + entry;
+
+ first_desc = tx_desc;
+ if (ctxt_desc_req)
+ ctxt_desc = (struct sxgbe_tx_ctxt_desc *)first_desc;
+
+ /* save the skb address */
+ tqueue->tx_skbuff[entry] = skb;
+
+ if (!is_jumbo) {
+ if (likely(skb_is_gso(skb))) {
+ /* TSO support */
+ if (unlikely(tqueue->prev_mss != cur_mss)) {
+ priv->hw->desc->tx_ctxt_desc_set_mss(
+ ctxt_desc, cur_mss);
+ priv->hw->desc->tx_ctxt_desc_set_tcmssv(
+ ctxt_desc);
+ priv->hw->desc->tx_ctxt_desc_reset_ostc(
+ ctxt_desc);
+ priv->hw->desc->tx_ctxt_desc_set_ctxt(
+ ctxt_desc);
+ priv->hw->desc->tx_ctxt_desc_set_owner(
+ ctxt_desc);
+
+ entry = (++tqueue->cur_tx) % tx_rsize;
+ first_desc = tqueue->dma_tx + entry;
+
+ tqueue->prev_mss = cur_mss;
+ }
+ sxgbe_tso_prepare(priv, first_desc, skb);
+ } else {
+ tx_desc->tdes01 = dma_map_single(priv->device,
+ skb->data, no_pagedlen, DMA_TO_DEVICE);
+ if (dma_mapping_error(priv->device, tx_desc->tdes01))
+ netdev_err(dev, "%s: TX dma mapping failed!!\n",
+ __func__);
+
+ priv->hw->desc->prepare_tx_desc(tx_desc, 1, no_pagedlen,
+ no_pagedlen, cksum_flag);
+ }
+ }
+
+ for (frag_num = 0; frag_num < nr_frags; frag_num++) {
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[frag_num];
+ int len = skb_frag_size(frag);
+
+ entry = (++tqueue->cur_tx) % tx_rsize;
+ tx_desc = tqueue->dma_tx + entry;
+ tx_desc->tdes01 = skb_frag_dma_map(priv->device, frag, 0, len,
+ DMA_TO_DEVICE);
+
+ tqueue->tx_skbuff_dma[entry] = tx_desc->tdes01;
+ tqueue->tx_skbuff[entry] = NULL;
+
+ /* prepare the descriptor */
+ priv->hw->desc->prepare_tx_desc(tx_desc, 0, len,
+ len, cksum_flag);
+ /* memory barrier to flush descriptor */
+ wmb();
+
+ /* set the owner */
+ priv->hw->desc->set_tx_owner(tx_desc);
+ }
+
+ /* close the descriptors */
+ priv->hw->desc->close_tx_desc(tx_desc);
+
+ /* memory barrier to flush descriptor */
+ wmb();
+
+ tqueue->tx_count_frames += nr_frags + 1;
+ if (tqueue->tx_count_frames > tqueue->tx_coal_frames) {
+ priv->hw->desc->clear_tx_ic(tx_desc);
+ priv->xstats.tx_reset_ic_bit++;
+ mod_timer(&tqueue->txtimer,
+ SXGBE_COAL_TIMER(tqueue->tx_coal_timer));
+ } else {
+ tqueue->tx_count_frames = 0;
+ }
+
+ /* set owner for first desc */
+ priv->hw->desc->set_tx_owner(first_desc);
+
+ /* memory barrier to flush descriptor */
+ wmb();
+
+ tqueue->cur_tx++;
+
+ /* display current ring */
+ netif_dbg(priv, pktdata, dev, "%s: curr %d dirty=%d entry=%d, first=%p, nfrags=%d\n",
+ __func__, tqueue->cur_tx % tx_rsize,
+ tqueue->dirty_tx % tx_rsize, entry,
+ first_desc, nr_frags);
+
+ if (unlikely(sxgbe_tx_avail(tqueue, tx_rsize) <= (MAX_SKB_FRAGS + 1))) {
+ netif_dbg(priv, hw, dev, "%s: stop transmitted packets\n",
+ __func__);
+ netif_tx_stop_queue(dev_txq);
+ }
+
+ dev->stats.tx_bytes += skb->len;
+
+ if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+ tqueue->hwts_tx_en)) {
+ /* declare that device is doing timestamping */
+ skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+ priv->hw->desc->tx_enable_tstamp(first_desc);
+ }
+
+ if (!tqueue->hwts_tx_en)
+ skb_tx_timestamp(skb);
+
+ priv->hw->dma->enable_dma_transmission(priv->ioaddr, txq_index);
+
+ spin_unlock(&tqueue->tx_lock);
+
+ return NETDEV_TX_OK;
+}
+
+/**
+ * sxgbe_rx_refill: refill used skb preallocated buffers
+ * @priv: driver private structure
+ * Description : this is to reallocate the skb for the reception process
+ * that is based on zero-copy.
+ */
+static void sxgbe_rx_refill(struct sxgbe_priv_data *priv)
+{
+ unsigned int rxsize = priv->dma_rx_size;
+ int bfsize = priv->dma_buf_sz;
+ u8 qnum = priv->cur_rx_qnum;
+
+ for (; priv->rxq[qnum]->cur_rx - priv->rxq[qnum]->dirty_rx > 0;
+ priv->rxq[qnum]->dirty_rx++) {
+ unsigned int entry = priv->rxq[qnum]->dirty_rx % rxsize;
+ struct sxgbe_rx_norm_desc *p;
+
+ p = priv->rxq[qnum]->dma_rx + entry;
+
+ if (likely(priv->rxq[qnum]->rx_skbuff[entry] == NULL)) {
+ struct sk_buff *skb;
+
+ skb = netdev_alloc_skb_ip_align(priv->dev, bfsize);
+
+ if (unlikely(skb == NULL))
+ break;
+
+ priv->rxq[qnum]->rx_skbuff[entry] = skb;
+ priv->rxq[qnum]->rx_skbuff_dma[entry] =
+ dma_map_single(priv->device, skb->data, bfsize,
+ DMA_FROM_DEVICE);
+
+ p->rdes23.rx_rd_des23.buf2_addr =
+ priv->rxq[qnum]->rx_skbuff_dma[entry];
+ }
+
+ /* Added memory barrier for RX descriptor modification */
+ wmb();
+ priv->hw->desc->set_rx_owner(p);
+ /* Added memory barrier for RX descriptor modification */
+ wmb();
+ }
+}
+
+/**
+ * sxgbe_rx: receive the frames from the remote host
+ * @priv: driver private structure
+ * @limit: napi bugget.
+ * Description : this the function called by the napi poll method.
+ * It gets all the frames inside the ring.
+ */
+static int sxgbe_rx(struct sxgbe_priv_data *priv, int limit)
+{
+ u8 qnum = priv->cur_rx_qnum;
+ unsigned int rxsize = priv->dma_rx_size;
+ unsigned int entry = priv->rxq[qnum]->cur_rx;
+ unsigned int next_entry = 0;
+ unsigned int count = 0;
+ int checksum;
+ int status;
+
+ while (count < limit) {
+ struct sxgbe_rx_norm_desc *p;
+ struct sk_buff *skb;
+ int frame_len;
+
+ p = priv->rxq[qnum]->dma_rx + entry;
+
+ if (priv->hw->desc->get_rx_owner(p))
+ break;
+
+ count++;
+
+ next_entry = (++priv->rxq[qnum]->cur_rx) % rxsize;
+ prefetch(priv->rxq[qnum]->dma_rx + next_entry);
+
+ /* Read the status of the incoming frame and also get checksum
+ * value based on whether it is enabled in SXGBE hardware or
+ * not.
+ */
+ status = priv->hw->desc->rx_wbstatus(p, &priv->xstats,
+ &checksum);
+ if (unlikely(status < 0)) {
+ entry = next_entry;
+ continue;
+ }
+ if (unlikely(!priv->rxcsum_insertion))
+ checksum = CHECKSUM_NONE;
+
+ skb = priv->rxq[qnum]->rx_skbuff[entry];
+
+ if (unlikely(!skb))
+ netdev_err(priv->dev, "rx descriptor is not consistent\n");
+
+ prefetch(skb->data - NET_IP_ALIGN);
+ priv->rxq[qnum]->rx_skbuff[entry] = NULL;
+
+ frame_len = priv->hw->desc->get_rx_frame_len(p);
+
+ skb_put(skb, frame_len);
+
+ skb->ip_summed = checksum;
+ if (checksum == CHECKSUM_NONE)
+ netif_receive_skb(skb);
+ else
+ napi_gro_receive(&priv->napi, skb);
+
+ entry = next_entry;
+ }
+
+ sxgbe_rx_refill(priv);
+
+ return count;
+}
+
+/**
+ * sxgbe_poll - sxgbe poll method (NAPI)
+ * @napi : pointer to the napi structure.
+ * @budget : maximum number of packets that the current CPU can receive from
+ * all interfaces.
+ * Description :
+ * To look at the incoming frames and clear the tx resources.
+ */
+static int sxgbe_poll(struct napi_struct *napi, int budget)
+{
+ struct sxgbe_priv_data *priv = container_of(napi,
+ struct sxgbe_priv_data, napi);
+ int work_done = 0;
+ u8 qnum = priv->cur_rx_qnum;
+
+ priv->xstats.napi_poll++;
+ /* first, clean the tx queues */
+ sxgbe_tx_all_clean(priv);
+
+ work_done = sxgbe_rx(priv, budget);
+ if (work_done < budget) {
+ napi_complete(napi);
+ priv->hw->dma->enable_dma_irq(priv->ioaddr, qnum);
+ }
+
+ return work_done;
+}
+
+/**
+ * sxgbe_tx_timeout
+ * @dev : Pointer to net device structure
+ * Description: this function is called when a packet transmission fails to
+ * complete within a reasonable time. The driver will mark the error in the
+ * netdev structure and arrange for the device to be reset to a sane state
+ * in order to transmit a new packet.
+ */
+static void sxgbe_tx_timeout(struct net_device *dev)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+ sxgbe_reset_all_tx_queues(priv);
+}
+
+/**
+ * sxgbe_common_interrupt - main ISR
+ * @irq: interrupt number.
+ * @dev_id: to pass the net device pointer.
+ * Description: this is the main driver interrupt service routine.
+ * It calls the DMA ISR and also the core ISR to manage PMT, MMC, LPI
+ * interrupts.
+ */
+static irqreturn_t sxgbe_common_interrupt(int irq, void *dev_id)
+{
+ struct net_device *netdev = (struct net_device *)dev_id;
+ struct sxgbe_priv_data *priv = netdev_priv(netdev);
+ int status;
+
+ status = priv->hw->mac->host_irq_status(priv->ioaddr, &priv->xstats);
+ /* For LPI we need to save the tx status */
+ if (status & TX_ENTRY_LPI_MODE) {
+ priv->xstats.tx_lpi_entry_n++;
+ priv->tx_path_in_lpi_mode = true;
+ }
+ if (status & TX_EXIT_LPI_MODE) {
+ priv->xstats.tx_lpi_exit_n++;
+ priv->tx_path_in_lpi_mode = false;
+ }
+ if (status & RX_ENTRY_LPI_MODE)
+ priv->xstats.rx_lpi_entry_n++;
+ if (status & RX_EXIT_LPI_MODE)
+ priv->xstats.rx_lpi_exit_n++;
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * sxgbe_tx_interrupt - TX DMA ISR
+ * @irq: interrupt number.
+ * @dev_id: to pass the net device pointer.
+ * Description: this is the tx dma interrupt service routine.
+ */
+static irqreturn_t sxgbe_tx_interrupt(int irq, void *dev_id)
+{
+ int status;
+ struct sxgbe_tx_queue *txq = (struct sxgbe_tx_queue *)dev_id;
+ struct sxgbe_priv_data *priv = txq->priv_ptr;
+
+ /* get the channel status */
+ status = priv->hw->dma->tx_dma_int_status(priv->ioaddr, txq->queue_no,
+ &priv->xstats);
+ /* check for normal path */
+ if (likely((status & handle_tx)))
+ napi_schedule(&priv->napi);
+
+ /* check for unrecoverable error */
+ if (unlikely((status & tx_hard_error)))
+ sxgbe_restart_tx_queue(priv, txq->queue_no);
+
+ /* check for TC configuration change */
+ if (unlikely((status & tx_bump_tc) &&
+ (priv->tx_tc != SXGBE_MTL_SFMODE) &&
+ (priv->tx_tc < 512))) {
+ /* step of TX TC is 32 till 128, otherwise 64 */
+ priv->tx_tc += (priv->tx_tc < 128) ? 32 : 64;
+ priv->hw->mtl->set_tx_mtl_mode(priv->ioaddr,
+ txq->queue_no, priv->tx_tc);
+ priv->xstats.tx_threshold = priv->tx_tc;
+ }
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * sxgbe_rx_interrupt - RX DMA ISR
+ * @irq: interrupt number.
+ * @dev_id: to pass the net device pointer.
+ * Description: this is the rx dma interrupt service routine.
+ */
+static irqreturn_t sxgbe_rx_interrupt(int irq, void *dev_id)
+{
+ int status;
+ struct sxgbe_rx_queue *rxq = (struct sxgbe_rx_queue *)dev_id;
+ struct sxgbe_priv_data *priv = rxq->priv_ptr;
+
+ /* get the channel status */
+ status = priv->hw->dma->rx_dma_int_status(priv->ioaddr, rxq->queue_no,
+ &priv->xstats);
+
+ if (likely((status & handle_rx) && (napi_schedule_prep(&priv->napi)))) {
+ priv->hw->dma->disable_dma_irq(priv->ioaddr, rxq->queue_no);
+ __napi_schedule(&priv->napi);
+ }
+
+ /* check for TC configuration change */
+ if (unlikely((status & rx_bump_tc) &&
+ (priv->rx_tc != SXGBE_MTL_SFMODE) &&
+ (priv->rx_tc < 128))) {
+ /* step of TC is 32 */
+ priv->rx_tc += 32;
+ priv->hw->mtl->set_rx_mtl_mode(priv->ioaddr,
+ rxq->queue_no, priv->rx_tc);
+ priv->xstats.rx_threshold = priv->rx_tc;
+ }
+
+ return IRQ_HANDLED;
+}
+
+static inline u64 sxgbe_get_stat64(void __iomem *ioaddr, int reg_lo, int reg_hi)
+{
+ u64 val = readl(ioaddr + reg_lo);
+
+ val |= ((u64)readl(ioaddr + reg_hi)) << 32;
+
+ return val;
+}
+
+
+/* sxgbe_get_stats64 - entry point to see statistical information of device
+ * @dev : device pointer.
+ * @stats : pointer to hold all the statistical information of device.
+ * Description:
+ * This function is a driver entry point whenever ifconfig command gets
+ * executed to see device statistics. Statistics are number of
+ * bytes sent or received, errors occured etc.
+ * Return value:
+ * This function returns various statistical information of device.
+ */
+static struct rtnl_link_stats64 *sxgbe_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *stats)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ void __iomem *ioaddr = priv->ioaddr;
+ u64 count;
+
+ spin_lock(&priv->stats_lock);
+ /* Freeze the counter registers before reading value otherwise it may
+ * get updated by hardware while we are reading them
+ */
+ writel(SXGBE_MMC_CTRL_CNT_FRZ, ioaddr + SXGBE_MMC_CTL_REG);
+
+ stats->rx_bytes = sxgbe_get_stat64(ioaddr,
+ SXGBE_MMC_RXOCTETLO_GCNT_REG,
+ SXGBE_MMC_RXOCTETHI_GCNT_REG);
+
+ stats->rx_packets = sxgbe_get_stat64(ioaddr,
+ SXGBE_MMC_RXFRAMELO_GBCNT_REG,
+ SXGBE_MMC_RXFRAMEHI_GBCNT_REG);
+
+ stats->multicast = sxgbe_get_stat64(ioaddr,
+ SXGBE_MMC_RXMULTILO_GCNT_REG,
+ SXGBE_MMC_RXMULTIHI_GCNT_REG);
+
+ stats->rx_crc_errors = sxgbe_get_stat64(ioaddr,
+ SXGBE_MMC_RXCRCERRLO_REG,
+ SXGBE_MMC_RXCRCERRHI_REG);
+
+ stats->rx_length_errors = sxgbe_get_stat64(ioaddr,
+ SXGBE_MMC_RXLENERRLO_REG,
+ SXGBE_MMC_RXLENERRHI_REG);
+
+ stats->rx_missed_errors = sxgbe_get_stat64(ioaddr,
+ SXGBE_MMC_RXFIFOOVERFLOWLO_GBCNT_REG,
+ SXGBE_MMC_RXFIFOOVERFLOWHI_GBCNT_REG);
+
+ stats->tx_bytes = sxgbe_get_stat64(ioaddr,
+ SXGBE_MMC_TXOCTETLO_GCNT_REG,
+ SXGBE_MMC_TXOCTETHI_GCNT_REG);
+
+ count = sxgbe_get_stat64(ioaddr, SXGBE_MMC_TXFRAMELO_GBCNT_REG,
+ SXGBE_MMC_TXFRAMEHI_GBCNT_REG);
+
+ stats->tx_errors = sxgbe_get_stat64(ioaddr, SXGBE_MMC_TXFRAMELO_GCNT_REG,
+ SXGBE_MMC_TXFRAMEHI_GCNT_REG);
+ stats->tx_errors = count - stats->tx_errors;
+ stats->tx_packets = count;
+ stats->tx_fifo_errors = sxgbe_get_stat64(ioaddr, SXGBE_MMC_TXUFLWLO_GBCNT_REG,
+ SXGBE_MMC_TXUFLWHI_GBCNT_REG);
+ writel(0, ioaddr + SXGBE_MMC_CTL_REG);
+ spin_unlock(&priv->stats_lock);
+
+ return stats;
+}
+
+/* sxgbe_set_features - entry point to set offload features of the device.
+ * @dev : device pointer.
+ * @features : features which are required to be set.
+ * Description:
+ * This function is a driver entry point and called by Linux kernel whenever
+ * any device features are set or reset by user.
+ * Return value:
+ * This function returns 0 after setting or resetting device features.
+ */
+static int sxgbe_set_features(struct net_device *dev,
+ netdev_features_t features)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ netdev_features_t changed = dev->features ^ features;
+
+ if (changed & NETIF_F_RXCSUM) {
+ if (features & NETIF_F_RXCSUM) {
+ priv->hw->mac->enable_rx_csum(priv->ioaddr);
+ priv->rxcsum_insertion = true;
+ } else {
+ priv->hw->mac->disable_rx_csum(priv->ioaddr);
+ priv->rxcsum_insertion = false;
+ }
+ }
+
+ return 0;
+}
+
+/* sxgbe_change_mtu - entry point to change MTU size for the device.
+ * @dev : device pointer.
+ * @new_mtu : the new MTU size for the device.
+ * Description: the Maximum Transfer Unit (MTU) is used by the network layer
+ * to drive packet transmission. Ethernet has an MTU of 1500 octets
+ * (ETH_DATA_LEN). This value can be changed with ifconfig.
+ * Return value:
+ * 0 on success and an appropriate (-)ve integer as defined in errno.h
+ * file on failure.
+ */
+static int sxgbe_change_mtu(struct net_device *dev, int new_mtu)
+{
+ /* RFC 791, page 25, "Every internet module must be able to forward
+ * a datagram of 68 octets without further fragmentation."
+ */
+ if (new_mtu < MIN_MTU || (new_mtu > MAX_MTU)) {
+ netdev_err(dev, "invalid MTU, MTU should be in between %d and %d\n",
+ MIN_MTU, MAX_MTU);
+ return -EINVAL;
+ }
+
+ /* Return if the buffer sizes will not change */
+ if (dev->mtu == new_mtu)
+ return 0;
+
+ dev->mtu = new_mtu;
+
+ if (!netif_running(dev))
+ return 0;
+
+ /* Recevice ring buffer size is needed to be set based on MTU. If MTU is
+ * changed then reinitilisation of the receive ring buffers need to be
+ * done. Hence bring interface down and bring interface back up
+ */
+ sxgbe_release(dev);
+ return sxgbe_open(dev);
+}
+
+static void sxgbe_set_umac_addr(void __iomem *ioaddr, unsigned char *addr,
+ unsigned int reg_n)
+{
+ unsigned long data;
+
+ data = (addr[5] << 8) | addr[4];
+ /* For MAC Addr registers se have to set the Address Enable (AE)
+ * bit that has no effect on the High Reg 0 where the bit 31 (MO)
+ * is RO.
+ */
+ writel(data | SXGBE_HI_REG_AE, ioaddr + SXGBE_ADDR_HIGH(reg_n));
+ data = (addr[3] << 24) | (addr[2] << 16) | (addr[1] << 8) | addr[0];
+ writel(data, ioaddr + SXGBE_ADDR_LOW(reg_n));
+}
+
+/**
+ * sxgbe_set_rx_mode - entry point for setting different receive mode of
+ * a device. unicast, multicast addressing
+ * @dev : pointer to the device structure
+ * Description:
+ * This function is a driver entry point which gets called by the kernel
+ * whenever different receive mode like unicast, multicast and promiscuous
+ * must be enabled/disabled.
+ * Return value:
+ * void.
+ */
+static void sxgbe_set_rx_mode(struct net_device *dev)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ void __iomem *ioaddr = (void __iomem *)priv->ioaddr;
+ unsigned int value = 0;
+ u32 mc_filter[2];
+ struct netdev_hw_addr *ha;
+ int reg = 1;
+
+ netdev_dbg(dev, "%s: # mcasts %d, # unicast %d\n",
+ __func__, netdev_mc_count(dev), netdev_uc_count(dev));
+
+ if (dev->flags & IFF_PROMISC) {
+ value = SXGBE_FRAME_FILTER_PR;
+
+ } else if ((netdev_mc_count(dev) > SXGBE_HASH_TABLE_SIZE) ||
+ (dev->flags & IFF_ALLMULTI)) {
+ value = SXGBE_FRAME_FILTER_PM; /* pass all multi */
+ writel(0xffffffff, ioaddr + SXGBE_HASH_HIGH);
+ writel(0xffffffff, ioaddr + SXGBE_HASH_LOW);
+
+ } else if (!netdev_mc_empty(dev)) {
+ /* Hash filter for multicast */
+ value = SXGBE_FRAME_FILTER_HMC;
+
+ memset(mc_filter, 0, sizeof(mc_filter));
+ netdev_for_each_mc_addr(ha, dev) {
+ /* The upper 6 bits of the calculated CRC are used to
+ * index the contens of the hash table
+ */
+ int bit_nr = bitrev32(~crc32_le(~0, ha->addr, 6)) >> 26;
+
+ /* The most significant bit determines the register to
+ * use (H/L) while the other 5 bits determine the bit
+ * within the register.
+ */
+ mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31);
+ }
+ writel(mc_filter[0], ioaddr + SXGBE_HASH_LOW);
+ writel(mc_filter[1], ioaddr + SXGBE_HASH_HIGH);
+ }
+
+ /* Handle multiple unicast addresses (perfect filtering) */
+ if (netdev_uc_count(dev) > SXGBE_MAX_PERFECT_ADDRESSES)
+ /* Switch to promiscuous mode if more than 16 addrs
+ * are required
+ */
+ value |= SXGBE_FRAME_FILTER_PR;
+ else {
+ netdev_for_each_uc_addr(ha, dev) {
+ sxgbe_set_umac_addr(ioaddr, ha->addr, reg);
+ reg++;
+ }
+ }
+#ifdef FRAME_FILTER_DEBUG
+ /* Enable Receive all mode (to debug filtering_fail errors) */
+ value |= SXGBE_FRAME_FILTER_RA;
+#endif
+ writel(value, ioaddr + SXGBE_FRAME_FILTER);
+
+ netdev_dbg(dev, "Filter: 0x%08x\n\tHash: HI 0x%08x, LO 0x%08x\n",
+ readl(ioaddr + SXGBE_FRAME_FILTER),
+ readl(ioaddr + SXGBE_HASH_HIGH),
+ readl(ioaddr + SXGBE_HASH_LOW));
+}
+
+/**
+ * sxgbe_config - entry point for changing configuration mode passed on by
+ * ifconfig
+ * @dev : pointer to the device structure
+ * @map : pointer to the device mapping structure
+ * Description:
+ * This function is a driver entry point which gets called by the kernel
+ * whenever some device configuration is changed.
+ * Return value:
+ * This function returns 0 if success and appropriate error otherwise.
+ */
+static int sxgbe_config(struct net_device *dev, struct ifmap *map)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+ /* Can't act on a running interface */
+ if (dev->flags & IFF_UP)
+ return -EBUSY;
+
+ /* Don't allow changing the I/O address */
+ if (map->base_addr != (unsigned long)priv->ioaddr) {
+ netdev_warn(dev, "can't change I/O address\n");
+ return -EOPNOTSUPP;
+ }
+
+ /* Don't allow changing the IRQ */
+ if (map->irq != priv->irq) {
+ netdev_warn(dev, "not change IRQ number %d\n", priv->irq);
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+/**
+ * sxgbe_poll_controller - entry point for polling receive by device
+ * @dev : pointer to the device structure
+ * Description:
+ * This function is used by NETCONSOLE and other diagnostic tools
+ * to allow network I/O with interrupts disabled.
+ * Return value:
+ * Void.
+ */
+static void sxgbe_poll_controller(struct net_device *dev)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+ disable_irq(priv->irq);
+ sxgbe_rx_interrupt(priv->irq, dev);
+ enable_irq(priv->irq);
+}
+#endif
+
+/* sxgbe_ioctl - Entry point for the Ioctl
+ * @dev: Device pointer.
+ * @rq: An IOCTL specefic structure, that can contain a pointer to
+ * a proprietary structure used to pass information to the driver.
+ * @cmd: IOCTL command
+ * Description:
+ * Currently it supports the phy_mii_ioctl(...) and HW time stamping.
+ */
+static int sxgbe_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(dev);
+ int ret = -EOPNOTSUPP;
+
+ if (!netif_running(dev))
+ return -EINVAL;
+
+ switch (cmd) {
+ case SIOCGMIIPHY:
+ case SIOCGMIIREG:
+ case SIOCSMIIREG:
+ if (!priv->phydev)
+ return -EINVAL;
+ ret = phy_mii_ioctl(priv->phydev, rq, cmd);
+ break;
+ default:
+ break;
+ }
+
+ return ret;
+}
+
+static const struct net_device_ops sxgbe_netdev_ops = {
+ .ndo_open = sxgbe_open,
+ .ndo_start_xmit = sxgbe_xmit,
+ .ndo_stop = sxgbe_release,
+ .ndo_get_stats64 = sxgbe_get_stats64,
+ .ndo_change_mtu = sxgbe_change_mtu,
+ .ndo_set_features = sxgbe_set_features,
+ .ndo_set_rx_mode = sxgbe_set_rx_mode,
+ .ndo_tx_timeout = sxgbe_tx_timeout,
+ .ndo_do_ioctl = sxgbe_ioctl,
+ .ndo_set_config = sxgbe_config,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = sxgbe_poll_controller,
+#endif
+ .ndo_set_mac_address = eth_mac_addr,
+};
+
+/* Get the hardware ops */
+static void sxgbe_get_ops(struct sxgbe_ops * const ops_ptr)
+{
+ ops_ptr->mac = sxgbe_get_core_ops();
+ ops_ptr->desc = sxgbe_get_desc_ops();
+ ops_ptr->dma = sxgbe_get_dma_ops();
+ ops_ptr->mtl = sxgbe_get_mtl_ops();
+
+ /* set the MDIO communication Address/Data regisers */
+ ops_ptr->mii.addr = SXGBE_MDIO_SCMD_ADD_REG;
+ ops_ptr->mii.data = SXGBE_MDIO_SCMD_DATA_REG;
+
+ /* Assigning the default link settings
+ * no SXGBE defined default values to be set in registers,
+ * so assigning as 0 for port and duplex
+ */
+ ops_ptr->link.port = 0;
+ ops_ptr->link.duplex = 0;
+ ops_ptr->link.speed = SXGBE_SPEED_10G;
+}
+
+/**
+ * sxgbe_hw_init - Init the GMAC device
+ * @priv: driver private structure
+ * Description: this function checks the HW capability
+ * (if supported) and sets the driver's features.
+ */
+static int sxgbe_hw_init(struct sxgbe_priv_data * const priv)
+{
+ u32 ctrl_ids;
+
+ priv->hw = kmalloc(sizeof(*priv->hw), GFP_KERNEL);
+ if(!priv->hw)
+ return -ENOMEM;
+
+ /* get the hardware ops */
+ sxgbe_get_ops(priv->hw);
+
+ /* get the controller id */
+ ctrl_ids = priv->hw->mac->get_controller_version(priv->ioaddr);
+ priv->hw->ctrl_uid = (ctrl_ids & 0x00ff0000) >> 16;
+ priv->hw->ctrl_id = (ctrl_ids & 0x000000ff);
+ pr_info("user ID: 0x%x, Controller ID: 0x%x\n",
+ priv->hw->ctrl_uid, priv->hw->ctrl_id);
+
+ /* get the H/W features */
+ if (!sxgbe_get_hw_features(priv))
+ pr_info("Hardware features not found\n");
+
+ if (priv->hw_cap.tx_csum_offload)
+ pr_info("TX Checksum offload supported\n");
+
+ if (priv->hw_cap.rx_csum_offload)
+ pr_info("RX Checksum offload supported\n");
+
+ return 0;
+}
+
+/**
+ * sxgbe_drv_probe
+ * @device: device pointer
+ * @plat_dat: platform data pointer
+ * @addr: iobase memory address
+ * Description: this is the main probe function used to
+ * call the alloc_etherdev, allocate the priv structure.
+ */
+struct sxgbe_priv_data *sxgbe_drv_probe(struct device *device,
+ struct sxgbe_plat_data *plat_dat,
+ void __iomem *addr)
+{
+ struct sxgbe_priv_data *priv;
+ struct net_device *ndev;
+ int ret;
+ u8 queue_num;
+
+ ndev = alloc_etherdev_mqs(sizeof(struct sxgbe_priv_data),
+ SXGBE_TX_QUEUES, SXGBE_RX_QUEUES);
+ if (!ndev)
+ return NULL;
+
+ SET_NETDEV_DEV(ndev, device);
+
+ priv = netdev_priv(ndev);
+ priv->device = device;
+ priv->dev = ndev;
+
+ sxgbe_set_ethtool_ops(ndev);
+ priv->plat = plat_dat;
+ priv->ioaddr = addr;
+
+ /* Verify driver arguments */
+ sxgbe_verify_args();
+
+ /* Init MAC and get the capabilities */
+ ret = sxgbe_hw_init(priv);
+ if (ret)
+ goto error_free_netdev;
+
+ /* allocate memory resources for Descriptor rings */
+ ret = txring_mem_alloc(priv);
+ if (ret)
+ goto error_free_netdev;
+
+ ret = rxring_mem_alloc(priv);
+ if (ret)
+ goto error_free_netdev;
+
+ ndev->netdev_ops = &sxgbe_netdev_ops;
+
+ ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+ NETIF_F_RXCSUM | NETIF_F_TSO | NETIF_F_TSO6 |
+ NETIF_F_GRO;
+ ndev->features |= ndev->hw_features | NETIF_F_HIGHDMA;
+ ndev->watchdog_timeo = msecs_to_jiffies(TX_TIMEO);
+
+ /* assign filtering support */
+ ndev->priv_flags |= IFF_UNICAST_FLT;
+
+ priv->msg_enable = netif_msg_init(debug, default_msg_level);
+
+ /* Enable TCP segmentation offload for all DMA channels */
+ if (priv->hw_cap.tcpseg_offload) {
+ SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+ priv->hw->dma->enable_tso(priv->ioaddr, queue_num);
+ }
+ }
+
+ /* Enable Rx checksum offload */
+ if (priv->hw_cap.rx_csum_offload) {
+ priv->hw->mac->enable_rx_csum(priv->ioaddr);
+ priv->rxcsum_insertion = true;
+ }
+
+ /* Initialise pause frame settings */
+ priv->rx_pause = 1;
+ priv->tx_pause = 1;
+
+ /* Rx Watchdog is available, enable depend on platform data */
+ if (!priv->plat->riwt_off) {
+ priv->use_riwt = 1;
+ pr_info("Enable RX Mitigation via HW Watchdog Timer\n");
+ }
+
+ netif_napi_add(ndev, &priv->napi, sxgbe_poll, 64);
+
+ spin_lock_init(&priv->stats_lock);
+
+ priv->sxgbe_clk = clk_get(priv->device, SXGBE_RESOURCE_NAME);
+ if (IS_ERR(priv->sxgbe_clk)) {
+ netdev_warn(ndev, "%s: warning: cannot get CSR clock\n",
+ __func__);
+ goto error_clk_get;
+ }
+
+ /* If a specific clk_csr value is passed from the platform
+ * this means that the CSR Clock Range selection cannot be
+ * changed at run-time and it is fixed. Viceversa the driver'll try to
+ * set the MDC clock dynamically according to the csr actual
+ * clock input.
+ */
+ if (!priv->plat->clk_csr)
+ sxgbe_clk_csr_set(priv);
+ else
+ priv->clk_csr = priv->plat->clk_csr;
+
+ /* MDIO bus Registration */
+ ret = sxgbe_mdio_register(ndev);
+ if (ret < 0) {
+ netdev_dbg(ndev, "%s: MDIO bus (id: %d) registration failed\n",
+ __func__, priv->plat->bus_id);
+ goto error_mdio_register;
+ }
+
+ ret = register_netdev(ndev);
+ if (ret) {
+ pr_err("%s: ERROR %i registering the device\n", __func__, ret);
+ goto error_netdev_register;
+ }
+
+ sxgbe_check_ether_addr(priv);
+
+ return priv;
+
+error_mdio_register:
+ clk_put(priv->sxgbe_clk);
+error_clk_get:
+error_netdev_register:
+ netif_napi_del(&priv->napi);
+error_free_netdev:
+ free_netdev(ndev);
+
+ return NULL;
+}
+
+/**
+ * sxgbe_drv_remove
+ * @ndev: net device pointer
+ * Description: this function resets the TX/RX processes, disables the MAC RX/TX
+ * changes the link status, releases the DMA descriptor rings.
+ */
+int sxgbe_drv_remove(struct net_device *ndev)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(ndev);
+
+ netdev_info(ndev, "%s: removing driver\n", __func__);
+
+ priv->hw->dma->stop_rx(priv->ioaddr, SXGBE_RX_QUEUES);
+ priv->hw->dma->stop_tx(priv->ioaddr, SXGBE_TX_QUEUES);
+
+ priv->hw->mac->enable_tx(priv->ioaddr, false);
+ priv->hw->mac->enable_rx(priv->ioaddr, false);
+
+ netif_napi_del(&priv->napi);
+
+ sxgbe_mdio_unregister(ndev);
+
+ unregister_netdev(ndev);
+
+ free_netdev(ndev);
+
+ return 0;
+}
+
+#ifdef CONFIG_PM
+int sxgbe_suspend(struct net_device *ndev)
+{
+ return 0;
+}
+
+int sxgbe_resume(struct net_device *ndev)
+{
+ return 0;
+}
+
+int sxgbe_freeze(struct net_device *ndev)
+{
+ return -ENOSYS;
+}
+
+int sxgbe_restore(struct net_device *ndev)
+{
+ return -ENOSYS;
+}
+#endif /* CONFIG_PM */
+
+/* Driver is configured as Platform driver */
+static int __init sxgbe_init(void)
+{
+ int ret;
+
+ ret = sxgbe_register_platform();
+ if (ret)
+ goto err;
+ return 0;
+err:
+ pr_err("driver registration failed\n");
+ return ret;
+}
+
+static void __exit sxgbe_exit(void)
+{
+ sxgbe_unregister_platform();
+}
+
+module_init(sxgbe_init);
+module_exit(sxgbe_exit);
+
+#ifndef MODULE
+static int __init sxgbe_cmdline_opt(char *str)
+{
+ char *opt;
+
+ if (!str || !*str)
+ return -EINVAL;
+ while ((opt = strsep(&str, ",")) != NULL) {
+ if (!strncmp(opt, "eee_timer:", 6)) {
+ if (kstrtoint(opt + 10, 0, &eee_timer))
+ goto err;
+ }
+ }
+ return 0;
+
+err:
+ pr_err("%s: ERROR broken module parameter conversion\n", __func__);
+ return -EINVAL;
+}
+
+__setup("sxgbeeth=", sxgbe_cmdline_opt);
+#endif /* MODULE */
+
+
+
+MODULE_DESCRIPTION("SAMSUNG 10G/2.5G/1G Ethernet PLATFORM driver");
+
+MODULE_PARM_DESC(debug, "Message Level (-1: default, 0: no output, 16: all)");
+MODULE_PARM_DESC(eee_timer, "EEE-LPI Default LS timer value");
+
+MODULE_AUTHOR("Siva Reddy Kallam <siva.kallam@samsung.com>");
+MODULE_AUTHOR("ByungHo An <bh74.an@samsung.com>");
+MODULE_AUTHOR("Girish K S <ks.giri@samsung.com>");
+MODULE_AUTHOR("Vipul Pandya <vipul.pandya@samsung.com>");
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c
new file mode 100644
index 0000000..b0eb0a2
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c
@@ -0,0 +1,251 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/io.h>
+#include <linux/mii.h>
+#include <linux/netdevice.h>
+#include <linux/platform_device.h>
+#include <linux/phy.h>
+#include <linux/slab.h>
+#include <linux/sxgbe_platform.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_reg.h"
+
+#define SXGBE_SMA_WRITE_CMD 0x01 /* write command */
+#define SXGBE_SMA_PREAD_CMD 0x02 /* post read increament address */
+#define SXGBE_SMA_READ_CMD 0x03 /* read command */
+#define SXGBE_SMA_SKIP_ADDRFRM 0x00040000 /* skip the address frame */
+#define SXGBE_MII_BUSY 0x00800000 /* mii busy */
+
+static int sxgbe_mdio_busy_wait(void __iomem *ioaddr, unsigned int mii_data)
+{
+ unsigned long fin_time = jiffies + 3 * HZ; /* 3 seconds */
+
+ while (!time_after(jiffies, fin_time)) {
+ if (!(readl(ioaddr + mii_data) & SXGBE_MII_BUSY))
+ return 0;
+ cpu_relax();
+ }
+
+ return -EBUSY;
+}
+
+static void sxgbe_mdio_ctrl_data(struct sxgbe_priv_data *sp, u32 cmd,
+ u16 phydata)
+{
+ u32 reg = phydata;
+
+ reg |= (cmd << 16) | SXGBE_SMA_SKIP_ADDRFRM |
+ ((sp->clk_csr & 0x7) << 19) | SXGBE_MII_BUSY;
+ writel(reg, sp->ioaddr + sp->hw->mii.data);
+}
+
+static void sxgbe_mdio_c45(struct sxgbe_priv_data *sp, u32 cmd, int phyaddr,
+ int phyreg, u16 phydata)
+{
+ u32 reg;
+
+ /* set mdio address register */
+ reg = ((phyreg >> 16) & 0x1f) << 21;
+ reg |= (phyaddr << 16) | (phyreg & 0xffff);
+ writel(reg, sp->ioaddr + sp->hw->mii.addr);
+
+ sxgbe_mdio_ctrl_data(sp, cmd, phydata);
+}
+
+static void sxgbe_mdio_c22(struct sxgbe_priv_data *sp, u32 cmd, int phyaddr,
+ int phyreg, u16 phydata)
+{
+ u32 reg;
+
+ writel(1 << phyaddr, sp->ioaddr + SXGBE_MDIO_CLAUSE22_PORT_REG);
+
+ /* set mdio address register */
+ reg = (phyaddr << 16) | (phyreg & 0x1f);
+ writel(reg, sp->ioaddr + sp->hw->mii.addr);
+
+ sxgbe_mdio_ctrl_data(sp, cmd, phydata);
+}
+
+static int sxgbe_mdio_access(struct sxgbe_priv_data *sp, u32 cmd, int phyaddr,
+ int phyreg, u16 phydata)
+{
+ const struct mii_regs *mii = &sp->hw->mii;
+ int rc;
+
+ rc = sxgbe_mdio_busy_wait(sp->ioaddr, mii->data);
+ if (rc < 0)
+ return rc;
+
+ if (phyreg & MII_ADDR_C45) {
+ sxgbe_mdio_c45(sp, cmd, phyaddr, phyreg, phydata);
+ } else {
+ /* Ports 0-3 only support C22. */
+ if (phyaddr >= 4)
+ return -ENODEV;
+
+ sxgbe_mdio_c22(sp, cmd, phyaddr, phyreg, phydata);
+ }
+
+ return sxgbe_mdio_busy_wait(sp->ioaddr, mii->data);
+}
+
+/**
+ * sxgbe_mdio_read
+ * @bus: points to the mii_bus structure
+ * @phyaddr: address of phy port
+ * @phyreg: address of register with in phy register
+ * Description: this function used for C45 and C22 MDIO Read
+ */
+static int sxgbe_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg)
+{
+ struct net_device *ndev = bus->priv;
+ struct sxgbe_priv_data *priv = netdev_priv(ndev);
+ int rc;
+
+ rc = sxgbe_mdio_access(priv, SXGBE_SMA_READ_CMD, phyaddr, phyreg, 0);
+ if (rc < 0)
+ return rc;
+
+ return readl(priv->ioaddr + priv->hw->mii.data) & 0xffff;
+}
+
+/**
+ * sxgbe_mdio_write
+ * @bus: points to the mii_bus structure
+ * @phyaddr: address of phy port
+ * @phyreg: address of phy registers
+ * @phydata: data to be written into phy register
+ * Description: this function is used for C45 and C22 MDIO write
+ */
+static int sxgbe_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg,
+ u16 phydata)
+{
+ struct net_device *ndev = bus->priv;
+ struct sxgbe_priv_data *priv = netdev_priv(ndev);
+
+ return sxgbe_mdio_access(priv, SXGBE_SMA_WRITE_CMD, phyaddr, phyreg,
+ phydata);
+}
+
+int sxgbe_mdio_register(struct net_device *ndev)
+{
+ struct mii_bus *mdio_bus;
+ struct sxgbe_priv_data *priv = netdev_priv(ndev);
+ struct sxgbe_mdio_bus_data *mdio_data = priv->plat->mdio_bus_data;
+ int err, phy_addr;
+ int *irqlist;
+ bool act;
+
+ /* allocate the new mdio bus */
+ mdio_bus = mdiobus_alloc();
+ if (!mdio_bus) {
+ netdev_err(ndev, "%s: mii bus allocation failed\n", __func__);
+ return -ENOMEM;
+ }
+
+ if (mdio_data->irqs)
+ irqlist = mdio_data->irqs;
+ else
+ irqlist = priv->mii_irq;
+
+ /* assign mii bus fields */
+ mdio_bus->name = "samsxgbe";
+ mdio_bus->read = &sxgbe_mdio_read;
+ mdio_bus->write = &sxgbe_mdio_write;
+ snprintf(mdio_bus->id, MII_BUS_ID_SIZE, "%s-%x",
+ mdio_bus->name, priv->plat->bus_id);
+ mdio_bus->priv = ndev;
+ mdio_bus->phy_mask = mdio_data->phy_mask;
+ mdio_bus->parent = priv->device;
+
+ /* register with kernel subsystem */
+ err = mdiobus_register(mdio_bus);
+ if (err != 0) {
+ netdev_err(ndev, "mdiobus register failed\n");
+ goto mdiobus_err;
+ }
+
+ for (phy_addr = 0; phy_addr < PHY_MAX_ADDR; phy_addr++) {
+ struct phy_device *phy = mdio_bus->phy_map[phy_addr];
+
+ if (phy) {
+ char irq_num[4];
+ char *irq_str;
+ /* If an IRQ was provided to be assigned after
+ * the bus probe, do it here.
+ */
+ if ((mdio_data->irqs == NULL) &&
+ (mdio_data->probed_phy_irq > 0)) {
+ irqlist[phy_addr] = mdio_data->probed_phy_irq;
+ phy->irq = mdio_data->probed_phy_irq;
+ }
+
+ /* If we're going to bind the MAC to this PHY bus,
+ * and no PHY number was provided to the MAC,
+ * use the one probed here.
+ */
+ if (priv->plat->phy_addr == -1)
+ priv->plat->phy_addr = phy_addr;
+
+ act = (priv->plat->phy_addr == phy_addr);
+ switch (phy->irq) {
+ case PHY_POLL:
+ irq_str = "POLL";
+ break;
+ case PHY_IGNORE_INTERRUPT:
+ irq_str = "IGNORE";
+ break;
+ default:
+ sprintf(irq_num, "%d", phy->irq);
+ irq_str = irq_num;
+ break;
+ }
+ netdev_info(ndev, "PHY ID %08x at %d IRQ %s (%s)%s\n",
+ phy->phy_id, phy_addr, irq_str,
+ dev_name(&phy->dev), act ? " active" : "");
+ }
+ }
+
+ if (!err) {
+ netdev_err(ndev, "PHY not found\n");
+ mdiobus_unregister(mdio_bus);
+ mdiobus_free(mdio_bus);
+ goto mdiobus_err;
+ }
+
+ priv->mii = mdio_bus;
+
+ return 0;
+
+mdiobus_err:
+ mdiobus_free(mdio_bus);
+ return err;
+}
+
+int sxgbe_mdio_unregister(struct net_device *ndev)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(ndev);
+
+ if (!priv->mii)
+ return 0;
+
+ mdiobus_unregister(priv->mii);
+ priv->mii->priv = NULL;
+ mdiobus_free(priv->mii);
+ priv->mii = NULL;
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.c
new file mode 100644
index 0000000..324681c
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.c
@@ -0,0 +1,254 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/io.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/jiffies.h>
+
+#include "sxgbe_mtl.h"
+#include "sxgbe_reg.h"
+
+static void sxgbe_mtl_init(void __iomem *ioaddr, unsigned int etsalg,
+ unsigned int raa)
+{
+ u32 reg_val;
+
+ reg_val = readl(ioaddr + SXGBE_MTL_OP_MODE_REG);
+ reg_val &= ETS_RST;
+
+ /* ETS Algorith */
+ switch (etsalg & SXGBE_MTL_OPMODE_ESTMASK) {
+ case ETS_WRR:
+ reg_val &= ETS_WRR;
+ break;
+ case ETS_WFQ:
+ reg_val |= ETS_WFQ;
+ break;
+ case ETS_DWRR:
+ reg_val |= ETS_DWRR;
+ break;
+ }
+ writel(reg_val, ioaddr + SXGBE_MTL_OP_MODE_REG);
+
+ switch (raa & SXGBE_MTL_OPMODE_RAAMASK) {
+ case RAA_SP:
+ reg_val &= RAA_SP;
+ break;
+ case RAA_WSP:
+ reg_val |= RAA_WSP;
+ break;
+ }
+ writel(reg_val, ioaddr + SXGBE_MTL_OP_MODE_REG);
+}
+
+/* For Dynamic DMA channel mapping for Rx queue */
+static void sxgbe_mtl_dma_dm_rxqueue(void __iomem *ioaddr)
+{
+ writel(RX_QUEUE_DYNAMIC, ioaddr + SXGBE_MTL_RXQ_DMAMAP0_REG);
+ writel(RX_QUEUE_DYNAMIC, ioaddr + SXGBE_MTL_RXQ_DMAMAP1_REG);
+ writel(RX_QUEUE_DYNAMIC, ioaddr + SXGBE_MTL_RXQ_DMAMAP2_REG);
+}
+
+static void sxgbe_mtl_set_txfifosize(void __iomem *ioaddr, int queue_num,
+ int queue_fifo)
+{
+ u32 fifo_bits, reg_val;
+
+ /* 0 means 256 bytes */
+ fifo_bits = (queue_fifo / SXGBE_MTL_TX_FIFO_DIV) - 1;
+ reg_val = readl(ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+ reg_val |= (fifo_bits << SXGBE_MTL_FIFO_LSHIFT);
+ writel(reg_val, ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_set_rxfifosize(void __iomem *ioaddr, int queue_num,
+ int queue_fifo)
+{
+ u32 fifo_bits, reg_val;
+
+ /* 0 means 256 bytes */
+ fifo_bits = (queue_fifo / SXGBE_MTL_RX_FIFO_DIV)-1;
+ reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+ reg_val |= (fifo_bits << SXGBE_MTL_FIFO_LSHIFT);
+ writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_enable_txqueue(void __iomem *ioaddr, int queue_num)
+{
+ u32 reg_val;
+
+ reg_val = readl(ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+ reg_val |= SXGBE_MTL_ENABLE_QUEUE;
+ writel(reg_val, ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_disable_txqueue(void __iomem *ioaddr, int queue_num)
+{
+ u32 reg_val;
+
+ reg_val = readl(ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+ reg_val &= ~SXGBE_MTL_ENABLE_QUEUE;
+ writel(reg_val, ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fc_active(void __iomem *ioaddr, int queue_num,
+ int threshold)
+{
+ u32 reg_val;
+
+ reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+ reg_val &= ~(SXGBE_MTL_FCMASK << RX_FC_ACTIVE);
+ reg_val |= (threshold << RX_FC_ACTIVE);
+
+ writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fc_enable(void __iomem *ioaddr, int queue_num)
+{
+ u32 reg_val;
+
+ reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+ reg_val |= SXGBE_MTL_ENABLE_FC;
+ writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fc_deactive(void __iomem *ioaddr, int queue_num,
+ int threshold)
+{
+ u32 reg_val;
+
+ reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+ reg_val &= ~(SXGBE_MTL_FCMASK << RX_FC_DEACTIVE);
+ reg_val |= (threshold << RX_FC_DEACTIVE);
+
+ writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fep_enable(void __iomem *ioaddr, int queue_num)
+{
+ u32 reg_val;
+
+ reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+ reg_val |= SXGBE_MTL_RXQ_OP_FEP;
+
+ writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fep_disable(void __iomem *ioaddr, int queue_num)
+{
+ u32 reg_val;
+
+ reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+ reg_val &= ~(SXGBE_MTL_RXQ_OP_FEP);
+
+ writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fup_enable(void __iomem *ioaddr, int queue_num)
+{
+ u32 reg_val;
+
+ reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+ reg_val |= SXGBE_MTL_RXQ_OP_FUP;
+
+ writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fup_disable(void __iomem *ioaddr, int queue_num)
+{
+ u32 reg_val;
+
+ reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+ reg_val &= ~(SXGBE_MTL_RXQ_OP_FUP);
+
+ writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+
+static void sxgbe_set_tx_mtl_mode(void __iomem *ioaddr, int queue_num,
+ int tx_mode)
+{
+ u32 reg_val;
+
+ reg_val = readl(ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+ /* TX specific MTL mode settings */
+ if (tx_mode == SXGBE_MTL_SFMODE) {
+ reg_val |= SXGBE_MTL_SFMODE;
+ } else {
+ /* set the TTC values */
+ if (tx_mode <= 64)
+ reg_val |= MTL_CONTROL_TTC_64;
+ else if (tx_mode <= 96)
+ reg_val |= MTL_CONTROL_TTC_96;
+ else if (tx_mode <= 128)
+ reg_val |= MTL_CONTROL_TTC_128;
+ else if (tx_mode <= 192)
+ reg_val |= MTL_CONTROL_TTC_192;
+ else if (tx_mode <= 256)
+ reg_val |= MTL_CONTROL_TTC_256;
+ else if (tx_mode <= 384)
+ reg_val |= MTL_CONTROL_TTC_384;
+ else
+ reg_val |= MTL_CONTROL_TTC_512;
+ }
+
+ /* write into TXQ operation register */
+ writel(reg_val, ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_set_rx_mtl_mode(void __iomem *ioaddr, int queue_num,
+ int rx_mode)
+{
+ u32 reg_val;
+
+ reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+ /* RX specific MTL mode settings */
+ if (rx_mode == SXGBE_RX_MTL_SFMODE) {
+ reg_val |= SXGBE_RX_MTL_SFMODE;
+ } else {
+ if (rx_mode <= 64)
+ reg_val |= MTL_CONTROL_RTC_64;
+ else if (rx_mode <= 96)
+ reg_val |= MTL_CONTROL_RTC_96;
+ else if (rx_mode <= 128)
+ reg_val |= MTL_CONTROL_RTC_128;
+ }
+
+ /* write into RXQ operation register */
+ writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static const struct sxgbe_mtl_ops mtl_ops = {
+ .mtl_set_txfifosize = sxgbe_mtl_set_txfifosize,
+ .mtl_set_rxfifosize = sxgbe_mtl_set_rxfifosize,
+ .mtl_enable_txqueue = sxgbe_mtl_enable_txqueue,
+ .mtl_disable_txqueue = sxgbe_mtl_disable_txqueue,
+ .mtl_dynamic_dma_rxqueue = sxgbe_mtl_dma_dm_rxqueue,
+ .set_tx_mtl_mode = sxgbe_set_tx_mtl_mode,
+ .set_rx_mtl_mode = sxgbe_set_rx_mtl_mode,
+ .mtl_init = sxgbe_mtl_init,
+ .mtl_fc_active = sxgbe_mtl_fc_active,
+ .mtl_fc_deactive = sxgbe_mtl_fc_deactive,
+ .mtl_fc_enable = sxgbe_mtl_fc_enable,
+ .mtl_fep_enable = sxgbe_mtl_fep_enable,
+ .mtl_fep_disable = sxgbe_mtl_fep_disable,
+ .mtl_fup_enable = sxgbe_mtl_fup_enable,
+ .mtl_fup_disable = sxgbe_mtl_fup_disable
+};
+
+const struct sxgbe_mtl_ops *sxgbe_get_mtl_ops(void)
+{
+ return &mtl_ops;
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.h
new file mode 100644
index 0000000..7e4810c
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.h
@@ -0,0 +1,104 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SXGBE_MTL_H__
+#define __SXGBE_MTL_H__
+
+#define SXGBE_MTL_OPMODE_ESTMASK 0x3
+#define SXGBE_MTL_OPMODE_RAAMASK 0x1
+#define SXGBE_MTL_FCMASK 0x7
+#define SXGBE_MTL_TX_FIFO_DIV 256
+#define SXGBE_MTL_RX_FIFO_DIV 256
+
+#define SXGBE_MTL_RXQ_OP_FEP BIT(4)
+#define SXGBE_MTL_RXQ_OP_FUP BIT(3)
+#define SXGBE_MTL_ENABLE_FC 0x80
+
+#define ETS_WRR 0xFFFFFF9F
+#define ETS_RST 0xFFFFFF9F
+#define ETS_WFQ 0x00000020
+#define ETS_DWRR 0x00000040
+#define RAA_SP 0xFFFFFFFB
+#define RAA_WSP 0x00000004
+
+#define RX_QUEUE_DYNAMIC 0x80808080
+#define RX_FC_ACTIVE 8
+#define RX_FC_DEACTIVE 13
+
+enum ttc_control {
+ MTL_CONTROL_TTC_64 = 0x00000000,
+ MTL_CONTROL_TTC_96 = 0x00000020,
+ MTL_CONTROL_TTC_128 = 0x00000030,
+ MTL_CONTROL_TTC_192 = 0x00000040,
+ MTL_CONTROL_TTC_256 = 0x00000050,
+ MTL_CONTROL_TTC_384 = 0x00000060,
+ MTL_CONTROL_TTC_512 = 0x00000070,
+};
+
+enum rtc_control {
+ MTL_CONTROL_RTC_64 = 0x00000000,
+ MTL_CONTROL_RTC_96 = 0x00000002,
+ MTL_CONTROL_RTC_128 = 0x00000003,
+};
+
+enum flow_control_th {
+ MTL_FC_FULL_1K = 0x00000000,
+ MTL_FC_FULL_2K = 0x00000001,
+ MTL_FC_FULL_4K = 0x00000002,
+ MTL_FC_FULL_5K = 0x00000003,
+ MTL_FC_FULL_6K = 0x00000004,
+ MTL_FC_FULL_8K = 0x00000005,
+ MTL_FC_FULL_16K = 0x00000006,
+ MTL_FC_FULL_24K = 0x00000007,
+};
+
+struct sxgbe_mtl_ops {
+ void (*mtl_init)(void __iomem *ioaddr, unsigned int etsalg,
+ unsigned int raa);
+
+ void (*mtl_set_txfifosize)(void __iomem *ioaddr, int queue_num,
+ int mtl_fifo);
+
+ void (*mtl_set_rxfifosize)(void __iomem *ioaddr, int queue_num,
+ int queue_fifo);
+
+ void (*mtl_enable_txqueue)(void __iomem *ioaddr, int queue_num);
+
+ void (*mtl_disable_txqueue)(void __iomem *ioaddr, int queue_num);
+
+ void (*set_tx_mtl_mode)(void __iomem *ioaddr, int queue_num,
+ int tx_mode);
+
+ void (*set_rx_mtl_mode)(void __iomem *ioaddr, int queue_num,
+ int rx_mode);
+
+ void (*mtl_dynamic_dma_rxqueue)(void __iomem *ioaddr);
+
+ void (*mtl_fc_active)(void __iomem *ioaddr, int queue_num,
+ int threshold);
+
+ void (*mtl_fc_deactive)(void __iomem *ioaddr, int queue_num,
+ int threshold);
+
+ void (*mtl_fc_enable)(void __iomem *ioaddr, int queue_num);
+
+ void (*mtl_fep_enable)(void __iomem *ioaddr, int queue_num);
+
+ void (*mtl_fep_disable)(void __iomem *ioaddr, int queue_num);
+
+ void (*mtl_fup_enable)(void __iomem *ioaddr, int queue_num);
+
+ void (*mtl_fup_disable)(void __iomem *ioaddr, int queue_num);
+};
+
+const struct sxgbe_mtl_ops *sxgbe_get_mtl_ops(void);
+
+#endif /* __SXGBE_MTL_H__ */
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c
new file mode 100644
index 0000000..b147d46
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c
@@ -0,0 +1,259 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/etherdevice.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_net.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/sxgbe_platform.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_reg.h"
+
+#ifdef CONFIG_OF
+static int sxgbe_probe_config_dt(struct platform_device *pdev,
+ struct sxgbe_plat_data *plat,
+ const char **mac)
+{
+ struct device_node *np = pdev->dev.of_node;
+ struct sxgbe_dma_cfg *dma_cfg;
+
+ if (!np)
+ return -ENODEV;
+
+ *mac = of_get_mac_address(np);
+ plat->interface = of_get_phy_mode(np);
+
+ plat->bus_id = of_alias_get_id(np, "ethernet");
+ if (plat->bus_id < 0)
+ plat->bus_id = 0;
+
+ plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
+ sizeof(*plat->mdio_bus_data),
+ GFP_KERNEL);
+
+ dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), GFP_KERNEL);
+ if (!dma_cfg)
+ return -ENOMEM;
+
+ plat->dma_cfg = dma_cfg;
+ of_property_read_u32(np, "samsung,pbl", &dma_cfg->pbl);
+ if (of_property_read_u32(np, "samsung,burst-map", &dma_cfg->burst_map) == 0)
+ dma_cfg->fixed_burst = true;
+
+ return 0;
+}
+#else
+static int sxgbe_probe_config_dt(struct platform_device *pdev,
+ struct sxgbe_plat_data *plat,
+ const char **mac)
+{
+ return -ENOSYS;
+}
+#endif /* CONFIG_OF */
+
+/**
+ * sxgbe_platform_probe
+ * @pdev: platform device pointer
+ * Description: platform_device probe function. It allocates
+ * the necessary resources and invokes the main to init
+ * the net device, register the mdio bus etc.
+ */
+static int sxgbe_platform_probe(struct platform_device *pdev)
+{
+ int ret;
+ int i, chan;
+ struct resource *res;
+ struct device *dev = &pdev->dev;
+ void __iomem *addr;
+ struct sxgbe_priv_data *priv = NULL;
+ struct sxgbe_plat_data *plat_dat = NULL;
+ const char *mac = NULL;
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct device_node *node = dev->of_node;
+
+ /* Get memory resource */
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ goto err_out;
+
+ addr = devm_ioremap_resource(dev, res);
+ if (IS_ERR(addr))
+ return PTR_ERR(addr);
+
+ if (pdev->dev.of_node) {
+ plat_dat = devm_kzalloc(&pdev->dev,
+ sizeof(struct sxgbe_plat_data),
+ GFP_KERNEL);
+ if (!plat_dat)
+ return -ENOMEM;
+
+ ret = sxgbe_probe_config_dt(pdev, plat_dat, &mac);
+ if (ret) {
+ pr_err("%s: main dt probe failed\n", __func__);
+ return ret;
+ }
+ }
+
+ /* Get MAC address if available (DT) */
+ if (mac)
+ ether_addr_copy(priv->dev->dev_addr, mac);
+
+ priv = sxgbe_drv_probe(&(pdev->dev), plat_dat, addr);
+ if (!priv) {
+ pr_err("%s: main driver probe failed\n", __func__);
+ goto err_out;
+ }
+
+ /* Get the SXGBE common INT information */
+ priv->irq = irq_of_parse_and_map(node, 0);
+ if (priv->irq <= 0) {
+ dev_err(dev, "sxgbe common irq parsing failed\n");
+ goto err_drv_remove;
+ }
+
+ /* Get the TX/RX IRQ numbers */
+ for (i = 0, chan = 1; i < SXGBE_TX_QUEUES; i++) {
+ priv->txq[i]->irq_no = irq_of_parse_and_map(node, chan++);
+ if (priv->txq[i]->irq_no <= 0) {
+ dev_err(dev, "sxgbe tx irq parsing failed\n");
+ goto err_tx_irq_unmap;
+ }
+ }
+
+ for (i = 0; i < SXGBE_RX_QUEUES; i++) {
+ priv->rxq[i]->irq_no = irq_of_parse_and_map(node, chan++);
+ if (priv->rxq[i]->irq_no <= 0) {
+ dev_err(dev, "sxgbe rx irq parsing failed\n");
+ goto err_rx_irq_unmap;
+ }
+ }
+
+ priv->lpi_irq = irq_of_parse_and_map(node, chan);
+ if (priv->lpi_irq <= 0) {
+ dev_err(dev, "sxgbe lpi irq parsing failed\n");
+ goto err_rx_irq_unmap;
+ }
+
+ platform_set_drvdata(pdev, priv->dev);
+
+ pr_debug("platform driver registration completed\n");
+
+ return 0;
+
+err_rx_irq_unmap:
+ while (--i)
+ irq_dispose_mapping(priv->rxq[i]->irq_no);
+ i = SXGBE_TX_QUEUES;
+err_tx_irq_unmap:
+ while (--i)
+ irq_dispose_mapping(priv->txq[i]->irq_no);
+ irq_dispose_mapping(priv->irq);
+err_drv_remove:
+ sxgbe_drv_remove(ndev);
+err_out:
+ return -ENODEV;
+}
+
+/**
+ * sxgbe_platform_remove
+ * @pdev: platform device pointer
+ * Description: this function calls the main to free the net resources
+ * and calls the platforms hook and release the resources (e.g. mem).
+ */
+static int sxgbe_platform_remove(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ int ret = sxgbe_drv_remove(ndev);
+
+ return ret;
+}
+
+#ifdef CONFIG_PM
+static int sxgbe_platform_suspend(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+
+ return sxgbe_suspend(ndev);
+}
+
+static int sxgbe_platform_resume(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+
+ return sxgbe_resume(ndev);
+}
+
+static int sxgbe_platform_freeze(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+
+ return sxgbe_freeze(ndev);
+}
+
+static int sxgbe_platform_restore(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+
+ return sxgbe_restore(ndev);
+}
+
+static const struct dev_pm_ops sxgbe_platform_pm_ops = {
+ .suspend = sxgbe_platform_suspend,
+ .resume = sxgbe_platform_resume,
+ .freeze = sxgbe_platform_freeze,
+ .thaw = sxgbe_platform_restore,
+ .restore = sxgbe_platform_restore,
+};
+#else
+static const struct dev_pm_ops sxgbe_platform_pm_ops;
+#endif /* CONFIG_PM */
+
+static const struct of_device_id sxgbe_dt_ids[] = {
+ { .compatible = "samsung,sxgbe-v2.0a"},
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, sxgbe_dt_ids);
+
+static struct platform_driver sxgbe_platform_driver = {
+ .probe = sxgbe_platform_probe,
+ .remove = sxgbe_platform_remove,
+ .driver = {
+ .name = SXGBE_RESOURCE_NAME,
+ .owner = THIS_MODULE,
+ .pm = &sxgbe_platform_pm_ops,
+ .of_match_table = of_match_ptr(sxgbe_dt_ids),
+ },
+};
+
+int sxgbe_register_platform(void)
+{
+ int err;
+
+ err = platform_driver_register(&sxgbe_platform_driver);
+ if (err)
+ pr_err("failed to register the platform driver\n");
+
+ return err;
+}
+
+void sxgbe_unregister_platform(void)
+{
+ platform_driver_unregister(&sxgbe_platform_driver);
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h
new file mode 100644
index 0000000..5a89acb
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h
@@ -0,0 +1,488 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SXGBE_REGMAP_H__
+#define __SXGBE_REGMAP_H__
+
+/* SXGBE MAC Registers */
+#define SXGBE_CORE_TX_CONFIG_REG 0x0000
+#define SXGBE_CORE_RX_CONFIG_REG 0x0004
+#define SXGBE_CORE_PKT_FILTER_REG 0x0008
+#define SXGBE_CORE_WATCHDOG_TIMEOUT_REG 0x000C
+#define SXGBE_CORE_HASH_TABLE_REG0 0x0010
+#define SXGBE_CORE_HASH_TABLE_REG1 0x0014
+#define SXGBE_CORE_HASH_TABLE_REG2 0x0018
+#define SXGBE_CORE_HASH_TABLE_REG3 0x001C
+#define SXGBE_CORE_HASH_TABLE_REG4 0x0020
+#define SXGBE_CORE_HASH_TABLE_REG5 0x0024
+#define SXGBE_CORE_HASH_TABLE_REG6 0x0028
+#define SXGBE_CORE_HASH_TABLE_REG7 0x002C
+
+/* EEE-LPI Registers */
+#define SXGBE_CORE_LPI_CTRL_STATUS 0x00D0
+#define SXGBE_CORE_LPI_TIMER_CTRL 0x00D4
+
+/* VLAN Specific Registers */
+#define SXGBE_CORE_VLAN_TAG_REG 0x0050
+#define SXGBE_CORE_VLAN_HASHTAB_REG 0x0058
+#define SXGBE_CORE_VLAN_INSCTL_REG 0x0060
+#define SXGBE_CORE_VLAN_INNERCTL_REG 0x0064
+#define SXGBE_CORE_RX_ETHTYPE_MATCH_REG 0x006C
+
+/* Flow Contol Registers */
+#define SXGBE_CORE_TX_Q0_FLOWCTL_REG 0x0070
+#define SXGBE_CORE_TX_Q1_FLOWCTL_REG 0x0074
+#define SXGBE_CORE_TX_Q2_FLOWCTL_REG 0x0078
+#define SXGBE_CORE_TX_Q3_FLOWCTL_REG 0x007C
+#define SXGBE_CORE_TX_Q4_FLOWCTL_REG 0x0080
+#define SXGBE_CORE_TX_Q5_FLOWCTL_REG 0x0084
+#define SXGBE_CORE_TX_Q6_FLOWCTL_REG 0x0088
+#define SXGBE_CORE_TX_Q7_FLOWCTL_REG 0x008C
+#define SXGBE_CORE_RX_FLOWCTL_REG 0x0090
+#define SXGBE_CORE_RX_CTL0_REG 0x00A0
+#define SXGBE_CORE_RX_CTL1_REG 0x00A4
+#define SXGBE_CORE_RX_CTL2_REG 0x00A8
+#define SXGBE_CORE_RX_CTL3_REG 0x00AC
+
+/* Interrupt Registers */
+#define SXGBE_CORE_INT_STATUS_REG 0x00B0
+#define SXGBE_CORE_INT_ENABLE_REG 0x00B4
+#define SXGBE_CORE_RXTX_ERR_STATUS_REG 0x00B8
+#define SXGBE_CORE_PMT_CTL_STATUS_REG 0x00C0
+#define SXGBE_CORE_RWK_PKT_FILTER_REG 0x00C4
+#define SXGBE_CORE_VERSION_REG 0x0110
+#define SXGBE_CORE_DEBUG_REG 0x0114
+#define SXGBE_CORE_HW_FEA_REG(index) (0x011C + index * 4)
+
+/* SMA(MDIO) module registers */
+#define SXGBE_MDIO_SCMD_ADD_REG 0x0200
+#define SXGBE_MDIO_SCMD_DATA_REG 0x0204
+#define SXGBE_MDIO_CCMD_WADD_REG 0x0208
+#define SXGBE_MDIO_CCMD_WDATA_REG 0x020C
+#define SXGBE_MDIO_CSCAN_PORT_REG 0x0210
+#define SXGBE_MDIO_INT_STATUS_REG 0x0214
+#define SXGBE_MDIO_INT_ENABLE_REG 0x0218
+#define SXGBE_MDIO_PORT_CONDCON_REG 0x021C
+#define SXGBE_MDIO_CLAUSE22_PORT_REG 0x0220
+
+/* port specific, addr = 0-3 */
+#define SXGBE_MDIO_DEV_BASE_REG 0x0230
+#define SXGBE_MDIO_PORT_DEV_REG(addr) \
+ (SXGBE_MDIO_DEV_BASE_REG + (0x10 * addr) + 0x0)
+#define SXGBE_MDIO_PORT_LSTATUS_REG(addr) \
+ (SXGBE_MDIO_DEV_BASE_REG + (0x10 * addr) + 0x4)
+#define SXGBE_MDIO_PORT_ALIVE_REG(addr) \
+ (SXGBE_MDIO_DEV_BASE_REG + (0x10 * addr) + 0x8)
+
+#define SXGBE_CORE_GPIO_CTL_REG 0x0278
+#define SXGBE_CORE_GPIO_STATUS_REG 0x027C
+
+/* Address registers for filtering */
+#define SXGBE_CORE_ADD_BASE_REG 0x0300
+
+/* addr = 0-31 */
+#define SXGBE_CORE_ADD_HIGHOFFSET(addr) \
+ (SXGBE_CORE_ADD_BASE_REG + (0x8 * addr) + 0x0)
+#define SXGBE_CORE_ADD_LOWOFFSET(addr) \
+ (SXGBE_CORE_ADD_BASE_REG + (0x8 * addr) + 0x4)
+
+/* SXGBE MMC registers */
+#define SXGBE_MMC_CTL_REG 0x0800
+#define SXGBE_MMC_RXINT_STATUS_REG 0x0804
+#define SXGBE_MMC_TXINT_STATUS_REG 0x0808
+#define SXGBE_MMC_RXINT_ENABLE_REG 0x080C
+#define SXGBE_MMC_TXINT_ENABLE_REG 0x0810
+
+/* TX specific counters */
+#define SXGBE_MMC_TXOCTETHI_GBCNT_REG 0x0814
+#define SXGBE_MMC_TXOCTETLO_GBCNT_REG 0x0818
+#define SXGBE_MMC_TXFRAMELO_GBCNT_REG 0x081C
+#define SXGBE_MMC_TXFRAMEHI_GBCNT_REG 0x0820
+#define SXGBE_MMC_TXBROADLO_GCNT_REG 0x0824
+#define SXGBE_MMC_TXBROADHI_GCNT_REG 0x0828
+#define SXGBE_MMC_TXMULTILO_GCNT_REG 0x082C
+#define SXGBE_MMC_TXMULTIHI_GCNT_REG 0x0830
+#define SXGBE_MMC_TX64LO_GBCNT_REG 0x0834
+#define SXGBE_MMC_TX64HI_GBCNT_REG 0x0838
+#define SXGBE_MMC_TX65TO127LO_GBCNT_REG 0x083C
+#define SXGBE_MMC_TX65TO127HI_GBCNT_REG 0x0840
+#define SXGBE_MMC_TX128TO255LO_GBCNT_REG 0x0844
+#define SXGBE_MMC_TX128TO255HI_GBCNT_REG 0x0848
+#define SXGBE_MMC_TX256TO511LO_GBCNT_REG 0x084C
+#define SXGBE_MMC_TX256TO511HI_GBCNT_REG 0x0850
+#define SXGBE_MMC_TX512TO1023LO_GBCNT_REG 0x0854
+#define SXGBE_MMC_TX512TO1023HI_GBCNT_REG 0x0858
+#define SXGBE_MMC_TX1023TOMAXLO_GBCNT_REG 0x085C
+#define SXGBE_MMC_TX1023TOMAXHI_GBCNT_REG 0x0860
+#define SXGBE_MMC_TXUNICASTLO_GBCNT_REG 0x0864
+#define SXGBE_MMC_TXUNICASTHI_GBCNT_REG 0x0868
+#define SXGBE_MMC_TXMULTILO_GBCNT_REG 0x086C
+#define SXGBE_MMC_TXMULTIHI_GBCNT_REG 0x0870
+#define SXGBE_MMC_TXBROADLO_GBCNT_REG 0x0874
+#define SXGBE_MMC_TXBROADHI_GBCNT_REG 0x0878
+#define SXGBE_MMC_TXUFLWLO_GBCNT_REG 0x087C
+#define SXGBE_MMC_TXUFLWHI_GBCNT_REG 0x0880
+#define SXGBE_MMC_TXOCTETLO_GCNT_REG 0x0884
+#define SXGBE_MMC_TXOCTETHI_GCNT_REG 0x0888
+#define SXGBE_MMC_TXFRAMELO_GCNT_REG 0x088C
+#define SXGBE_MMC_TXFRAMEHI_GCNT_REG 0x0890
+#define SXGBE_MMC_TXPAUSELO_CNT_REG 0x0894
+#define SXGBE_MMC_TXPAUSEHI_CNT_REG 0x0898
+#define SXGBE_MMC_TXVLANLO_GCNT_REG 0x089C
+#define SXGBE_MMC_TXVLANHI_GCNT_REG 0x08A0
+
+/* RX specific counters */
+#define SXGBE_MMC_RXFRAMELO_GBCNT_REG 0x0900
+#define SXGBE_MMC_RXFRAMEHI_GBCNT_REG 0x0904
+#define SXGBE_MMC_RXOCTETLO_GBCNT_REG 0x0908
+#define SXGBE_MMC_RXOCTETHI_GBCNT_REG 0x090C
+#define SXGBE_MMC_RXOCTETLO_GCNT_REG 0x0910
+#define SXGBE_MMC_RXOCTETHI_GCNT_REG 0x0914
+#define SXGBE_MMC_RXBROADLO_GCNT_REG 0x0918
+#define SXGBE_MMC_RXBROADHI_GCNT_REG 0x091C
+#define SXGBE_MMC_RXMULTILO_GCNT_REG 0x0920
+#define SXGBE_MMC_RXMULTIHI_GCNT_REG 0x0924
+#define SXGBE_MMC_RXCRCERRLO_REG 0x0928
+#define SXGBE_MMC_RXCRCERRHI_REG 0x092C
+#define SXGBE_MMC_RXSHORT64BFRAME_ERR_REG 0x0930
+#define SXGBE_MMC_RXJABBERERR_REG 0x0934
+#define SXGBE_MMC_RXSHORT64BFRAME_COR_REG 0x0938
+#define SXGBE_MMC_RXOVERMAXFRAME_COR_REG 0x093C
+#define SXGBE_MMC_RX64LO_GBCNT_REG 0x0940
+#define SXGBE_MMC_RX64HI_GBCNT_REG 0x0944
+#define SXGBE_MMC_RX65TO127LO_GBCNT_REG 0x0948
+#define SXGBE_MMC_RX65TO127HI_GBCNT_REG 0x094C
+#define SXGBE_MMC_RX128TO255LO_GBCNT_REG 0x0950
+#define SXGBE_MMC_RX128TO255HI_GBCNT_REG 0x0954
+#define SXGBE_MMC_RX256TO511LO_GBCNT_REG 0x0958
+#define SXGBE_MMC_RX256TO511HI_GBCNT_REG 0x095C
+#define SXGBE_MMC_RX512TO1023LO_GBCNT_REG 0x0960
+#define SXGBE_MMC_RX512TO1023HI_GBCNT_REG 0x0964
+#define SXGBE_MMC_RX1023TOMAXLO_GBCNT_REG 0x0968
+#define SXGBE_MMC_RX1023TOMAXHI_GBCNT_REG 0x096C
+#define SXGBE_MMC_RXUNICASTLO_GCNT_REG 0x0970
+#define SXGBE_MMC_RXUNICASTHI_GCNT_REG 0x0974
+#define SXGBE_MMC_RXLENERRLO_REG 0x0978
+#define SXGBE_MMC_RXLENERRHI_REG 0x097C
+#define SXGBE_MMC_RXOUTOFRANGETYPELO_REG 0x0980
+#define SXGBE_MMC_RXOUTOFRANGETYPEHI_REG 0x0984
+#define SXGBE_MMC_RXPAUSELO_CNT_REG 0x0988
+#define SXGBE_MMC_RXPAUSEHI_CNT_REG 0x098C
+#define SXGBE_MMC_RXFIFOOVERFLOWLO_GBCNT_REG 0x0990
+#define SXGBE_MMC_RXFIFOOVERFLOWHI_GBCNT_REG 0x0994
+#define SXGBE_MMC_RXVLANLO_GBCNT_REG 0x0998
+#define SXGBE_MMC_RXVLANHI_GBCNT_REG 0x099C
+#define SXGBE_MMC_RXWATCHDOG_ERR_REG 0x09A0
+
+/* L3/L4 function registers */
+#define SXGBE_CORE_L34_ADDCTL_REG 0x0C00
+#define SXGBE_CORE_L34_ADDCTL_REG 0x0C00
+#define SXGBE_CORE_L34_DATA_REG 0x0C04
+
+/* ARP registers */
+#define SXGBE_CORE_ARP_ADD_REG 0x0C10
+
+/* RSS registers */
+#define SXGBE_CORE_RSS_CTL_REG 0x0C80
+#define SXGBE_CORE_RSS_ADD_REG 0x0C88
+#define SXGBE_CORE_RSS_DATA_REG 0x0C8C
+
+/* RSS control register bits */
+#define SXGBE_CORE_RSS_CTL_UDP4TE BIT(3)
+#define SXGBE_CORE_RSS_CTL_TCP4TE BIT(2)
+#define SXGBE_CORE_RSS_CTL_IP2TE BIT(1)
+#define SXGBE_CORE_RSS_CTL_RSSE BIT(0)
+
+/* IEEE 1588 registers */
+#define SXGBE_CORE_TSTAMP_CTL_REG 0x0D00
+#define SXGBE_CORE_SUBSEC_INC_REG 0x0D04
+#define SXGBE_CORE_SYSTIME_SEC_REG 0x0D0C
+#define SXGBE_CORE_SYSTIME_NSEC_REG 0x0D10
+#define SXGBE_CORE_SYSTIME_SECUP_REG 0x0D14
+#define SXGBE_CORE_TSTAMP_ADD_REG 0x0D18
+#define SXGBE_CORE_SYSTIME_HWORD_REG 0x0D1C
+#define SXGBE_CORE_TSTAMP_STATUS_REG 0x0D20
+#define SXGBE_CORE_TXTIME_STATUSNSEC_REG 0x0D30
+#define SXGBE_CORE_TXTIME_STATUSSEC_REG 0x0D34
+
+/* Auxiliary registers */
+#define SXGBE_CORE_AUX_CTL_REG 0x0D40
+#define SXGBE_CORE_AUX_TSTAMP_NSEC_REG 0x0D48
+#define SXGBE_CORE_AUX_TSTAMP_SEC_REG 0x0D4C
+#define SXGBE_CORE_AUX_TSTAMP_INGCOR_REG 0x0D50
+#define SXGBE_CORE_AUX_TSTAMP_ENGCOR_REG 0x0D54
+#define SXGBE_CORE_AUX_TSTAMP_INGCOR_NSEC_REG 0x0D58
+#define SXGBE_CORE_AUX_TSTAMP_INGCOR_SUBNSEC_REG 0x0D5C
+#define SXGBE_CORE_AUX_TSTAMP_ENGCOR_NSEC_REG 0x0D60
+#define SXGBE_CORE_AUX_TSTAMP_ENGCOR_SUBNSEC_REG 0x0D64
+
+/* PPS registers */
+#define SXGBE_CORE_PPS_CTL_REG 0x0D70
+#define SXGBE_CORE_PPS_BASE 0x0D80
+
+/* addr = 0 - 3 */
+#define SXGBE_CORE_PPS_TTIME_SEC_REG(addr) \
+ (SXGBE_CORE_PPS_BASE + (0x10 * addr) + 0x0)
+#define SXGBE_CORE_PPS_TTIME_NSEC_REG(addr) \
+ (SXGBE_CORE_PPS_BASE + (0x10 * addr) + 0x4)
+#define SXGBE_CORE_PPS_INTERVAL_REG(addr) \
+ (SXGBE_CORE_PPS_BASE + (0x10 * addr) + 0x8)
+#define SXGBE_CORE_PPS_WIDTH_REG(addr) \
+ (SXGBE_CORE_PPS_BASE + (0x10 * addr) + 0xC)
+#define SXGBE_CORE_PTO_CTL_REG 0x0DC0
+#define SXGBE_CORE_SRCPORT_ITY0_REG 0x0DC4
+#define SXGBE_CORE_SRCPORT_ITY1_REG 0x0DC8
+#define SXGBE_CORE_SRCPORT_ITY2_REG 0x0DCC
+#define SXGBE_CORE_LOGMSG_LEVEL_REG 0x0DD0
+
+/* SXGBE MTL Registers */
+#define SXGBE_MTL_BASE_REG 0x1000
+#define SXGBE_MTL_OP_MODE_REG (SXGBE_MTL_BASE_REG + 0x0000)
+#define SXGBE_MTL_DEBUG_CTL_REG (SXGBE_MTL_BASE_REG + 0x0008)
+#define SXGBE_MTL_DEBUG_STATUS_REG (SXGBE_MTL_BASE_REG + 0x000C)
+#define SXGBE_MTL_FIFO_DEBUGDATA_REG (SXGBE_MTL_BASE_REG + 0x0010)
+#define SXGBE_MTL_INT_STATUS_REG (SXGBE_MTL_BASE_REG + 0x0020)
+#define SXGBE_MTL_RXQ_DMAMAP0_REG (SXGBE_MTL_BASE_REG + 0x0030)
+#define SXGBE_MTL_RXQ_DMAMAP1_REG (SXGBE_MTL_BASE_REG + 0x0034)
+#define SXGBE_MTL_RXQ_DMAMAP2_REG (SXGBE_MTL_BASE_REG + 0x0038)
+#define SXGBE_MTL_TX_PRTYMAP0_REG (SXGBE_MTL_BASE_REG + 0x0040)
+#define SXGBE_MTL_TX_PRTYMAP1_REG (SXGBE_MTL_BASE_REG + 0x0044)
+
+/* TC/Queue registers, qnum=0-15 */
+#define SXGBE_MTL_TC_TXBASE_REG (SXGBE_MTL_BASE_REG + 0x0100)
+#define SXGBE_MTL_TXQ_OPMODE_REG(qnum) \
+ (SXGBE_MTL_TC_TXBASE_REG + (qnum * 0x80) + 0x00)
+#define SXGBE_MTL_SFMODE BIT(1)
+#define SXGBE_MTL_FIFO_LSHIFT 16
+#define SXGBE_MTL_ENABLE_QUEUE 0x00000008
+#define SXGBE_MTL_TXQ_UNDERFLOW_REG(qnum) \
+ (SXGBE_MTL_TC_TXBASE_REG + (qnum * 0x80) + 0x04)
+#define SXGBE_MTL_TXQ_DEBUG_REG(qnum) \
+ (SXGBE_MTL_TC_TXBASE_REG + (qnum * 0x80) + 0x08)
+#define SXGBE_MTL_TXQ_ETSCTL_REG(qnum) \
+ (SXGBE_MTL_TC_TXBASE_REG + (qnum * 0x80) + 0x10)
+#define SXGBE_MTL_TXQ_ETSSTATUS_REG(qnum) \
+ (SXGBE_MTL_TC_TXBASE_REG + (qnum * 0x80) + 0x14)
+#define SXGBE_MTL_TXQ_QUANTWEIGHT_REG(qnum) \
+ (SXGBE_MTL_TC_TXBASE_REG + (qnum * 0x80) + 0x18)
+
+#define SXGBE_MTL_TC_RXBASE_REG 0x1140
+#define SXGBE_RX_MTL_SFMODE BIT(5)
+#define SXGBE_MTL_RXQ_OPMODE_REG(qnum) \
+ (SXGBE_MTL_TC_RXBASE_REG + (qnum * 0x80) + 0x00)
+#define SXGBE_MTL_RXQ_MISPKTOVERFLOW_REG(qnum) \
+ (SXGBE_MTL_TC_RXBASE_REG + (qnum * 0x80) + 0x04)
+#define SXGBE_MTL_RXQ_DEBUG_REG(qnum) \
+ (SXGBE_MTL_TC_RXBASE_REG + (qnum * 0x80) + 0x08)
+#define SXGBE_MTL_RXQ_CTL_REG(qnum) \
+ (SXGBE_MTL_TC_RXBASE_REG + (qnum * 0x80) + 0x0C)
+#define SXGBE_MTL_RXQ_INTENABLE_REG(qnum) \
+ (SXGBE_MTL_TC_RXBASE_REG + (qnum * 0x80) + 0x30)
+#define SXGBE_MTL_RXQ_INTSTATUS_REG(qnum) \
+ (SXGBE_MTL_TC_RXBASE_REG + (qnum * 0x80) + 0x34)
+
+/* SXGBE DMA Registers */
+#define SXGBE_DMA_BASE_REG 0x3000
+#define SXGBE_DMA_MODE_REG (SXGBE_DMA_BASE_REG + 0x0000)
+#define SXGBE_DMA_SOFT_RESET BIT(0)
+#define SXGBE_DMA_SYSBUS_MODE_REG (SXGBE_DMA_BASE_REG + 0x0004)
+#define SXGBE_DMA_AXI_UNDEF_BURST BIT(0)
+#define SXGBE_DMA_ENHACE_ADDR_MODE BIT(11)
+#define SXGBE_DMA_INT_STATUS_REG (SXGBE_DMA_BASE_REG + 0x0008)
+#define SXGBE_DMA_AXI_ARCACHECTL_REG (SXGBE_DMA_BASE_REG + 0x0010)
+#define SXGBE_DMA_AXI_AWCACHECTL_REG (SXGBE_DMA_BASE_REG + 0x0018)
+#define SXGBE_DMA_DEBUG_STATUS0_REG (SXGBE_DMA_BASE_REG + 0x0020)
+#define SXGBE_DMA_DEBUG_STATUS1_REG (SXGBE_DMA_BASE_REG + 0x0024)
+#define SXGBE_DMA_DEBUG_STATUS2_REG (SXGBE_DMA_BASE_REG + 0x0028)
+#define SXGBE_DMA_DEBUG_STATUS3_REG (SXGBE_DMA_BASE_REG + 0x002C)
+#define SXGBE_DMA_DEBUG_STATUS4_REG (SXGBE_DMA_BASE_REG + 0x0030)
+#define SXGBE_DMA_DEBUG_STATUS5_REG (SXGBE_DMA_BASE_REG + 0x0034)
+
+/* Channel Registers, cha_num = 0-15 */
+#define SXGBE_DMA_CHA_BASE_REG \
+ (SXGBE_DMA_BASE_REG + 0x0100)
+#define SXGBE_DMA_CHA_CTL_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x00)
+#define SXGBE_DMA_PBL_X8MODE BIT(16)
+#define SXGBE_DMA_CHA_TXCTL_TSE_ENABLE BIT(12)
+#define SXGBE_DMA_CHA_TXCTL_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x04)
+#define SXGBE_DMA_CHA_RXCTL_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x08)
+#define SXGBE_DMA_CHA_TXDESC_HADD_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x10)
+#define SXGBE_DMA_CHA_TXDESC_LADD_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x14)
+#define SXGBE_DMA_CHA_RXDESC_HADD_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x18)
+#define SXGBE_DMA_CHA_RXDESC_LADD_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x1C)
+#define SXGBE_DMA_CHA_TXDESC_TAILPTR_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x24)
+#define SXGBE_DMA_CHA_RXDESC_TAILPTR_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x2C)
+#define SXGBE_DMA_CHA_TXDESC_RINGLEN_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x30)
+#define SXGBE_DMA_CHA_RXDESC_RINGLEN_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x34)
+#define SXGBE_DMA_CHA_INT_ENABLE_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x38)
+#define SXGBE_DMA_CHA_INT_RXWATCHTMR_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x3C)
+#define SXGBE_DMA_CHA_TXDESC_CURADDLO_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x44)
+#define SXGBE_DMA_CHA_RXDESC_CURADDLO_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x4C)
+#define SXGBE_DMA_CHA_CURTXBUF_ADDHI_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x50)
+#define SXGBE_DMA_CHA_CURTXBUF_ADDLO_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x54)
+#define SXGBE_DMA_CHA_CURRXBUF_ADDHI_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x58)
+#define SXGBE_DMA_CHA_CURRXBUF_ADDLO_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x5C)
+#define SXGBE_DMA_CHA_STATUS_REG(cha_num) \
+ (SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x60)
+
+/* TX DMA control register specific */
+#define SXGBE_TX_START_DMA BIT(0)
+
+/* sxgbe tx configuration register bitfields */
+#define SXGBE_SPEED_10G 0x0
+#define SXGBE_SPEED_2_5G 0x1
+#define SXGBE_SPEED_1G 0x2
+#define SXGBE_SPEED_LSHIFT 29
+
+#define SXGBE_TX_ENABLE BIT(0)
+#define SXGBE_TX_DISDIC_ALGO BIT(1)
+#define SXGBE_TX_JABBER_DISABLE BIT(16)
+
+/* sxgbe rx configuration register bitfields */
+#define SXGBE_RX_ENABLE BIT(0)
+#define SXGBE_RX_ACS_ENABLE BIT(1)
+#define SXGBE_RX_WATCHDOG_DISABLE BIT(7)
+#define SXGBE_RX_JUMBPKT_ENABLE BIT(8)
+#define SXGBE_RX_CSUMOFFLOAD_ENABLE BIT(9)
+#define SXGBE_RX_LOOPBACK_ENABLE BIT(10)
+#define SXGBE_RX_ARPOFFLOAD_ENABLE BIT(31)
+
+/* sxgbe vlan Tag Register bitfields */
+#define SXGBE_VLAN_SVLAN_ENABLE BIT(18)
+#define SXGBE_VLAN_DOUBLEVLAN_ENABLE BIT(26)
+#define SXGBE_VLAN_INNERVLAN_ENABLE BIT(27)
+
+/* XMAC VLAN Tag Inclusion Register(0x0060) bitfields
+ * Below fields same for Inner VLAN Tag Inclusion
+ * Register(0x0064) register
+ */
+enum vlan_tag_ctl_tx {
+ VLAN_TAG_TX_NOP,
+ VLAN_TAG_TX_DEL,
+ VLAN_TAG_TX_INSERT,
+ VLAN_TAG_TX_REPLACE
+};
+#define SXGBE_VLAN_PRTY_CTL BIT(18)
+#define SXGBE_VLAN_CSVL_CTL BIT(19)
+
+/* SXGBE TX Q Flow Control Register bitfields */
+#define SXGBE_TX_FLOW_CTL_FCB BIT(0)
+#define SXGBE_TX_FLOW_CTL_TFB BIT(1)
+
+/* SXGBE RX Q Flow Control Register bitfields */
+#define SXGBE_RX_FLOW_CTL_ENABLE BIT(0)
+#define SXGBE_RX_UNICAST_DETECT BIT(1)
+#define SXGBE_RX_PRTYFLOW_CTL_ENABLE BIT(8)
+
+/* sxgbe rx Q control0 register bitfields */
+#define SXGBE_RX_Q_ENABLE 0x2
+
+/* SXGBE hardware features bitfield specific */
+/* Capability Register 0 */
+#define SXGBE_HW_FEAT_GMII(cap) ((cap & 0x00000002) >> 1)
+#define SXGBE_HW_FEAT_VLAN_HASH_FILTER(cap) ((cap & 0x00000010) >> 4)
+#define SXGBE_HW_FEAT_SMA(cap) ((cap & 0x00000020) >> 5)
+#define SXGBE_HW_FEAT_PMT_TEMOTE_WOP(cap) ((cap & 0x00000040) >> 6)
+#define SXGBE_HW_FEAT_PMT_MAGIC_PKT(cap) ((cap & 0x00000080) >> 7)
+#define SXGBE_HW_FEAT_RMON(cap) ((cap & 0x00000100) >> 8)
+#define SXGBE_HW_FEAT_ARP_OFFLOAD(cap) ((cap & 0x00000200) >> 9)
+#define SXGBE_HW_FEAT_IEEE1500_2008(cap) ((cap & 0x00001000) >> 12)
+#define SXGBE_HW_FEAT_EEE(cap) ((cap & 0x00002000) >> 13)
+#define SXGBE_HW_FEAT_TX_CSUM_OFFLOAD(cap) ((cap & 0x00004000) >> 14)
+#define SXGBE_HW_FEAT_RX_CSUM_OFFLOAD(cap) ((cap & 0x00010000) >> 16)
+#define SXGBE_HW_FEAT_MACADDR_COUNT(cap) ((cap & 0x007C0000) >> 18)
+#define SXGBE_HW_FEAT_TSTMAP_SRC(cap) ((cap & 0x06000000) >> 25)
+#define SXGBE_HW_FEAT_SRCADDR_VLAN(cap) ((cap & 0x08000000) >> 27)
+
+/* Capability Register 1 */
+#define SXGBE_HW_FEAT_RX_FIFO_SIZE(cap) ((cap & 0x0000001F))
+#define SXGBE_HW_FEAT_TX_FIFO_SIZE(cap) ((cap & 0x000007C0) >> 6)
+#define SXGBE_HW_FEAT_IEEE1588_HWORD(cap) ((cap & 0x00002000) >> 13)
+#define SXGBE_HW_FEAT_DCB(cap) ((cap & 0x00010000) >> 16)
+#define SXGBE_HW_FEAT_SPLIT_HDR(cap) ((cap & 0x00020000) >> 17)
+#define SXGBE_HW_FEAT_TSO(cap) ((cap & 0x00040000) >> 18)
+#define SXGBE_HW_FEAT_DEBUG_MEM_IFACE(cap) ((cap & 0x00080000) >> 19)
+#define SXGBE_HW_FEAT_RSS(cap) ((cap & 0x00100000) >> 20)
+#define SXGBE_HW_FEAT_HASH_TABLE_SIZE(cap) ((cap & 0x03000000) >> 24)
+#define SXGBE_HW_FEAT_L3L4_FILTER_NUM(cap) ((cap & 0x78000000) >> 27)
+
+/* Capability Register 2 */
+#define SXGBE_HW_FEAT_RX_MTL_QUEUES(cap) ((cap & 0x0000000F))
+#define SXGBE_HW_FEAT_TX_MTL_QUEUES(cap) ((cap & 0x000003C0) >> 6)
+#define SXGBE_HW_FEAT_RX_DMA_CHANNELS(cap) ((cap & 0x0000F000) >> 12)
+#define SXGBE_HW_FEAT_TX_DMA_CHANNELS(cap) ((cap & 0x003C0000) >> 18)
+#define SXGBE_HW_FEAT_PPS_OUTPUTS(cap) ((cap & 0x07000000) >> 24)
+#define SXGBE_HW_FEAT_AUX_SNAPSHOTS(cap) ((cap & 0x70000000) >> 28)
+
+/* DMAchannel interrupt enable specific */
+/* DMA Normal interrupt */
+#define SXGBE_DMA_INT_ENA_NIE BIT(16) /* Normal Summary */
+#define SXGBE_DMA_INT_ENA_TIE BIT(0) /* Transmit Interrupt */
+#define SXGBE_DMA_INT_ENA_TUE BIT(2) /* Transmit Buffer Unavailable */
+#define SXGBE_DMA_INT_ENA_RIE BIT(6) /* Receive Interrupt */
+
+#define SXGBE_DMA_INT_NORMAL \
+ (SXGBE_DMA_INT_ENA_NIE | SXGBE_DMA_INT_ENA_RIE | \
+ SXGBE_DMA_INT_ENA_TIE | SXGBE_DMA_INT_ENA_TUE)
+
+/* DMA Abnormal interrupt */
+#define SXGBE_DMA_INT_ENA_AIE BIT(15) /* Abnormal Summary */
+#define SXGBE_DMA_INT_ENA_TSE BIT(1) /* Transmit Stopped */
+#define SXGBE_DMA_INT_ENA_RUE BIT(7) /* Receive Buffer Unavailable */
+#define SXGBE_DMA_INT_ENA_RSE BIT(8) /* Receive Stopped */
+#define SXGBE_DMA_INT_ENA_FBE BIT(12) /* Fatal Bus Error */
+#define SXGBE_DMA_INT_ENA_CDEE BIT(13) /* Context Descriptor Error */
+
+#define SXGBE_DMA_INT_ABNORMAL \
+ (SXGBE_DMA_INT_ENA_AIE | SXGBE_DMA_INT_ENA_TSE | \
+ SXGBE_DMA_INT_ENA_RUE | SXGBE_DMA_INT_ENA_RSE | \
+ SXGBE_DMA_INT_ENA_FBE | SXGBE_DMA_INT_ENA_CDEE)
+
+#define SXGBE_DMA_ENA_INT (SXGBE_DMA_INT_NORMAL | SXGBE_DMA_INT_ABNORMAL)
+
+/* DMA channel interrupt status specific */
+#define SXGBE_DMA_INT_STATUS_REB2 BIT(21)
+#define SXGBE_DMA_INT_STATUS_REB1 BIT(20)
+#define SXGBE_DMA_INT_STATUS_REB0 BIT(19)
+#define SXGBE_DMA_INT_STATUS_TEB2 BIT(18)
+#define SXGBE_DMA_INT_STATUS_TEB1 BIT(17)
+#define SXGBE_DMA_INT_STATUS_TEB0 BIT(16)
+#define SXGBE_DMA_INT_STATUS_NIS BIT(15)
+#define SXGBE_DMA_INT_STATUS_AIS BIT(14)
+#define SXGBE_DMA_INT_STATUS_CTXTERR BIT(13)
+#define SXGBE_DMA_INT_STATUS_FBE BIT(12)
+#define SXGBE_DMA_INT_STATUS_RPS BIT(8)
+#define SXGBE_DMA_INT_STATUS_RBU BIT(7)
+#define SXGBE_DMA_INT_STATUS_RI BIT(6)
+#define SXGBE_DMA_INT_STATUS_TBU BIT(2)
+#define SXGBE_DMA_INT_STATUS_TPS BIT(1)
+#define SXGBE_DMA_INT_STATUS_TI BIT(0)
+
+#endif /* __SXGBE_REGMAP_H__ */
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.c
new file mode 100644
index 0000000..51c3219
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.c
@@ -0,0 +1,91 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include "sxgbe_common.h"
+#include "sxgbe_xpcs.h"
+
+static int sxgbe_xpcs_read(struct net_device *ndev, unsigned int reg)
+{
+ u32 value;
+ struct sxgbe_priv_data *priv = netdev_priv(ndev);
+
+ value = readl(priv->ioaddr + XPCS_OFFSET + reg);
+
+ return value;
+}
+
+static int sxgbe_xpcs_write(struct net_device *ndev, int reg, int data)
+{
+ struct sxgbe_priv_data *priv = netdev_priv(ndev);
+
+ writel(data, priv->ioaddr + XPCS_OFFSET + reg);
+
+ return 0;
+}
+
+int sxgbe_xpcs_init(struct net_device *ndev)
+{
+ u32 value;
+
+ value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
+ /* 10G XAUI mode */
+ sxgbe_xpcs_write(ndev, SR_PCS_CONTROL2, XPCS_TYPE_SEL_X);
+ sxgbe_xpcs_write(ndev, VR_PCS_MMD_XAUI_MODE_CONTROL, XPCS_XAUI_MODE);
+ sxgbe_xpcs_write(ndev, VR_PCS_MMD_XAUI_MODE_CONTROL, value | BIT(13));
+ sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value | BIT(11));
+
+ do {
+ value = sxgbe_xpcs_read(ndev, VR_PCS_MMD_DIGITAL_STATUS);
+ } while ((value & XPCS_QSEQ_STATE_MPLLOFF) == XPCS_QSEQ_STATE_STABLE);
+
+ value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
+ sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value & ~BIT(11));
+
+ do {
+ value = sxgbe_xpcs_read(ndev, VR_PCS_MMD_DIGITAL_STATUS);
+ } while ((value & XPCS_QSEQ_STATE_MPLLOFF) != XPCS_QSEQ_STATE_STABLE);
+
+ return 0;
+}
+
+int sxgbe_xpcs_init_1G(struct net_device *ndev)
+{
+ int value;
+
+ /* 10GBASE-X PCS (1G) mode */
+ sxgbe_xpcs_write(ndev, SR_PCS_CONTROL2, XPCS_TYPE_SEL_X);
+ sxgbe_xpcs_write(ndev, VR_PCS_MMD_XAUI_MODE_CONTROL, XPCS_XAUI_MODE);
+ value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
+ sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value & ~BIT(13));
+
+ value = sxgbe_xpcs_read(ndev, SR_MII_MMD_CONTROL);
+ sxgbe_xpcs_write(ndev, SR_MII_MMD_CONTROL, value | BIT(6));
+ sxgbe_xpcs_write(ndev, SR_MII_MMD_CONTROL, value & ~BIT(13));
+ value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
+ sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value | BIT(11));
+
+ do {
+ value = sxgbe_xpcs_read(ndev, VR_PCS_MMD_DIGITAL_STATUS);
+ } while ((value & XPCS_QSEQ_STATE_MPLLOFF) != XPCS_QSEQ_STATE_STABLE);
+
+ value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
+ sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value & ~BIT(11));
+
+ /* Auto Negotiation cluase 37 enable */
+ value = sxgbe_xpcs_read(ndev, SR_MII_MMD_CONTROL);
+ sxgbe_xpcs_write(ndev, SR_MII_MMD_CONTROL, value | BIT(12));
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.h
new file mode 100644
index 0000000..6b26a50
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.h
@@ -0,0 +1,38 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Byungho An <bh74.an@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SXGBE_XPCS_H__
+#define __SXGBE_XPCS_H__
+
+/* XPCS Registers */
+#define XPCS_OFFSET 0x1A060000
+#define SR_PCS_MMD_CONTROL1 0x030000
+#define SR_PCS_CONTROL2 0x030007
+#define VR_PCS_MMD_XAUI_MODE_CONTROL 0x038004
+#define VR_PCS_MMD_DIGITAL_STATUS 0x038010
+#define SR_MII_MMD_CONTROL 0x1F0000
+#define SR_MII_MMD_AN_ADV 0x1F0004
+#define SR_MII_MMD_AN_LINK_PARTNER_BA 0x1F0005
+#define VR_MII_MMD_AN_CONTROL 0x1F8001
+#define VR_MII_MMD_AN_INT_STATUS 0x1F8002
+
+#define XPCS_QSEQ_STATE_STABLE 0x10
+#define XPCS_QSEQ_STATE_MPLLOFF 0x1c
+#define XPCS_TYPE_SEL_R 0x00
+#define XPCS_TYPE_SEL_X 0x01
+#define XPCS_TYPE_SEL_W 0x02
+#define XPCS_XAUI_MODE 0x00
+#define XPCS_RXAUI_MODE 0x01
+
+int sxgbe_xpcs_init(struct net_device *ndev);
+int sxgbe_xpcs_init_1G(struct net_device *ndev);
+
+#endif /* __SXGBE_XPCS_H__ */
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 174a92f..651626e 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -162,8 +162,8 @@
if (outlen < MC_CMD_GET_MAC_ADDRESSES_OUT_LEN)
return -EIO;
- memcpy(mac_address,
- MCDI_PTR(outbuf, GET_MAC_ADDRESSES_OUT_MAC_ADDR_BASE), ETH_ALEN);
+ ether_addr_copy(mac_address,
+ MCDI_PTR(outbuf, GET_MAC_ADDRESSES_OUT_MAC_ADDR_BASE));
return 0;
}
@@ -172,8 +172,8 @@
struct efx_ef10_nic_data *nic_data;
int i, rc;
- /* We can have one VI for each 8K region. However we need
- * multiple TX queues per channel.
+ /* We can have one VI for each 8K region. However, until we
+ * use TX option descriptors we need two TX queues per channel.
*/
efx->max_channels =
min_t(unsigned int,
@@ -1955,6 +1955,9 @@
int tx_descs = 0;
int spent = 0;
+ if (quota <= 0)
+ return spent;
+
read_ptr = channel->eventq_read_ptr;
for (;;) {
@@ -3145,12 +3148,10 @@
table->dev_uc_count = -1;
} else {
table->dev_uc_count = 1 + netdev_uc_count(net_dev);
- memcpy(table->dev_uc_list[0].addr, net_dev->dev_addr,
- ETH_ALEN);
+ ether_addr_copy(table->dev_uc_list[0].addr, net_dev->dev_addr);
i = 1;
netdev_for_each_uc_addr(uc, net_dev) {
- memcpy(table->dev_uc_list[i].addr,
- uc->addr, ETH_ALEN);
+ ether_addr_copy(table->dev_uc_list[i].addr, uc->addr);
i++;
}
}
@@ -3162,8 +3163,7 @@
eth_broadcast_addr(table->dev_mc_list[0].addr);
i = 1;
netdev_for_each_mc_addr(mc, net_dev) {
- memcpy(table->dev_mc_list[i].addr,
- mc->addr, ETH_ALEN);
+ ether_addr_copy(table->dev_mc_list[i].addr, mc->addr);
i++;
}
}
diff --git a/drivers/net/ethernet/sfc/ef10_regs.h b/drivers/net/ethernet/sfc/ef10_regs.h
index 207ac9a..62a55dd 100644
--- a/drivers/net/ethernet/sfc/ef10_regs.h
+++ b/drivers/net/ethernet/sfc/ef10_regs.h
@@ -227,36 +227,6 @@
#define ESF_DZ_RX_KER_BUF_ADDR_LBN 0
#define ESF_DZ_RX_KER_BUF_ADDR_WIDTH 48
-/* RX_USER_DESC */
-#define ESF_DZ_RX_USR_RESERVED_LBN 62
-#define ESF_DZ_RX_USR_RESERVED_WIDTH 2
-#define ESF_DZ_RX_USR_BYTE_CNT_LBN 48
-#define ESF_DZ_RX_USR_BYTE_CNT_WIDTH 14
-#define ESF_DZ_RX_USR_BUF_PAGE_SIZE_LBN 44
-#define ESF_DZ_RX_USR_BUF_PAGE_SIZE_WIDTH 4
-#define ESE_DZ_USR_BUF_PAGE_SZ_4MB 10
-#define ESE_DZ_USR_BUF_PAGE_SZ_1MB 8
-#define ESE_DZ_USR_BUF_PAGE_SZ_64KB 4
-#define ESE_DZ_USR_BUF_PAGE_SZ_4KB 0
-#define ESF_DZ_RX_USR_BUF_ID_OFFSET_LBN 0
-#define ESF_DZ_RX_USR_BUF_ID_OFFSET_WIDTH 44
-#define ESF_DZ_RX_USR_4KBPS_BUF_ID_LBN 12
-#define ESF_DZ_RX_USR_4KBPS_BUF_ID_WIDTH 32
-#define ESF_DZ_RX_USR_64KBPS_BUF_ID_LBN 16
-#define ESF_DZ_RX_USR_64KBPS_BUF_ID_WIDTH 28
-#define ESF_DZ_RX_USR_1MBPS_BUF_ID_LBN 20
-#define ESF_DZ_RX_USR_1MBPS_BUF_ID_WIDTH 24
-#define ESF_DZ_RX_USR_4MBPS_BUF_ID_LBN 22
-#define ESF_DZ_RX_USR_4MBPS_BUF_ID_WIDTH 22
-#define ESF_DZ_RX_USR_4MBPS_BYTE_OFFSET_LBN 0
-#define ESF_DZ_RX_USR_4MBPS_BYTE_OFFSET_WIDTH 22
-#define ESF_DZ_RX_USR_1MBPS_BYTE_OFFSET_LBN 0
-#define ESF_DZ_RX_USR_1MBPS_BYTE_OFFSET_WIDTH 20
-#define ESF_DZ_RX_USR_64KBPS_BYTE_OFFSET_LBN 0
-#define ESF_DZ_RX_USR_64KBPS_BYTE_OFFSET_WIDTH 16
-#define ESF_DZ_RX_USR_4KBPS_BYTE_OFFSET_LBN 0
-#define ESF_DZ_RX_USR_4KBPS_BYTE_OFFSET_WIDTH 12
-
/* TX_CSUM_TSTAMP_DESC */
#define ESF_DZ_TX_DESC_IS_OPT_LBN 63
#define ESF_DZ_TX_DESC_IS_OPT_WIDTH 1
@@ -338,37 +308,6 @@
#define ESF_DZ_TX_TSO_TCP_SEQNO_LBN 0
#define ESF_DZ_TX_TSO_TCP_SEQNO_WIDTH 32
-/* TX_USER_DESC */
-#define ESF_DZ_TX_USR_TYPE_LBN 63
-#define ESF_DZ_TX_USR_TYPE_WIDTH 1
-#define ESF_DZ_TX_USR_CONT_LBN 62
-#define ESF_DZ_TX_USR_CONT_WIDTH 1
-#define ESF_DZ_TX_USR_BYTE_CNT_LBN 48
-#define ESF_DZ_TX_USR_BYTE_CNT_WIDTH 14
-#define ESF_DZ_TX_USR_BUF_PAGE_SIZE_LBN 44
-#define ESF_DZ_TX_USR_BUF_PAGE_SIZE_WIDTH 4
-#define ESE_DZ_USR_BUF_PAGE_SZ_4MB 10
-#define ESE_DZ_USR_BUF_PAGE_SZ_1MB 8
-#define ESE_DZ_USR_BUF_PAGE_SZ_64KB 4
-#define ESE_DZ_USR_BUF_PAGE_SZ_4KB 0
-#define ESF_DZ_TX_USR_BUF_ID_OFFSET_LBN 0
-#define ESF_DZ_TX_USR_BUF_ID_OFFSET_WIDTH 44
-#define ESF_DZ_TX_USR_4KBPS_BUF_ID_LBN 12
-#define ESF_DZ_TX_USR_4KBPS_BUF_ID_WIDTH 32
-#define ESF_DZ_TX_USR_64KBPS_BUF_ID_LBN 16
-#define ESF_DZ_TX_USR_64KBPS_BUF_ID_WIDTH 28
-#define ESF_DZ_TX_USR_1MBPS_BUF_ID_LBN 20
-#define ESF_DZ_TX_USR_1MBPS_BUF_ID_WIDTH 24
-#define ESF_DZ_TX_USR_4MBPS_BUF_ID_LBN 22
-#define ESF_DZ_TX_USR_4MBPS_BUF_ID_WIDTH 22
-#define ESF_DZ_TX_USR_4MBPS_BYTE_OFFSET_LBN 0
-#define ESF_DZ_TX_USR_4MBPS_BYTE_OFFSET_WIDTH 22
-#define ESF_DZ_TX_USR_1MBPS_BYTE_OFFSET_LBN 0
-#define ESF_DZ_TX_USR_1MBPS_BYTE_OFFSET_WIDTH 20
-#define ESF_DZ_TX_USR_64KBPS_BYTE_OFFSET_LBN 0
-#define ESF_DZ_TX_USR_64KBPS_BYTE_OFFSET_WIDTH 16
-#define ESF_DZ_TX_USR_4KBPS_BYTE_OFFSET_LBN 0
-#define ESF_DZ_TX_USR_4KBPS_BYTE_OFFSET_WIDTH 12
/*************************************************************************/
/* TX_DESC_UPD_REG: Transmit descriptor update register.
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 83d4643..52589f6 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -503,8 +503,6 @@
goto fail;
}
- channel->n_rx_frm_trunc = 0;
-
return 0;
fail:
@@ -1014,7 +1012,7 @@
return rc;
/* Initialise MAC address to permanent address */
- memcpy(efx->net_dev->dev_addr, efx->net_dev->perm_addr, ETH_ALEN);
+ ether_addr_copy(efx->net_dev->dev_addr, efx->net_dev->perm_addr);
return 0;
}
@@ -1346,20 +1344,23 @@
for (i = 0; i < n_channels; i++)
xentries[i].entry = i;
- rc = pci_enable_msix(efx->pci_dev, xentries, n_channels);
- if (rc > 0) {
+ rc = pci_enable_msix_range(efx->pci_dev,
+ xentries, 1, n_channels);
+ if (rc < 0) {
+ /* Fall back to single channel MSI */
+ efx->interrupt_mode = EFX_INT_MODE_MSI;
+ netif_err(efx, drv, efx->net_dev,
+ "could not enable MSI-X\n");
+ } else if (rc < n_channels) {
netif_err(efx, drv, efx->net_dev,
"WARNING: Insufficient MSI-X vectors"
" available (%d < %u).\n", rc, n_channels);
netif_err(efx, drv, efx->net_dev,
"WARNING: Performance may be reduced.\n");
- EFX_BUG_ON_PARANOID(rc >= n_channels);
n_channels = rc;
- rc = pci_enable_msix(efx->pci_dev, xentries,
- n_channels);
}
- if (rc == 0) {
+ if (rc > 0) {
efx->n_channels = n_channels;
if (n_channels > extra_channels)
n_channels -= extra_channels;
@@ -1375,11 +1376,6 @@
for (i = 0; i < efx->n_channels; i++)
efx_get_channel(efx, i)->irq =
xentries[i].vector;
- } else {
- /* Fall back to single channel MSI */
- efx->interrupt_mode = EFX_INT_MODE_MSI;
- netif_err(efx, drv, efx->net_dev,
- "could not enable MSI-X\n");
}
}
@@ -2115,7 +2111,7 @@
{
struct efx_nic *efx = netdev_priv(net_dev);
struct sockaddr *addr = data;
- char *new_addr = addr->sa_data;
+ u8 *new_addr = addr->sa_data;
if (!is_valid_ether_addr(new_addr)) {
netif_err(efx, drv, efx->net_dev,
@@ -2124,7 +2120,7 @@
return -EADDRNOTAVAIL;
}
- memcpy(net_dev->dev_addr, new_addr, net_dev->addr_len);
+ ether_addr_copy(net_dev->dev_addr, new_addr);
efx_sriov_mac_address_changed(efx);
/* Reconfigure the MAC */
@@ -3273,6 +3269,6 @@
MODULE_AUTHOR("Solarflare Communications and "
"Michael Brown <mbrown@fensystems.co.uk>");
-MODULE_DESCRIPTION("Solarflare Communications network driver");
+MODULE_DESCRIPTION("Solarflare network driver");
MODULE_LICENSE("GPL");
MODULE_DEVICE_TABLE(pci, efx_pci_table);
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index dbd7b78..9903258 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -14,7 +14,7 @@
#include "net_driver.h"
#include "filter.h"
-/* Solarstorm controllers use BAR 0 for I/O space and BAR 2(&3) for memory */
+/* All controllers use BAR 0 for I/O space and BAR 2(&3) for memory */
#define EFX_MEM_BAR 2
/* TX */
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 2294289..0de8b07 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -251,6 +251,9 @@
* @test_index: Starting index of the test
* @strings: Ethtool strings, or %NULL
* @data: Ethtool test results, or %NULL
+ *
+ * Fill in a block of loopback self-test entries. Return new test
+ * index.
*/
static int efx_fill_loopback_test(struct efx_nic *efx,
struct efx_loopback_self_tests *lb_tests,
@@ -290,6 +293,12 @@
* @tests: Efx self-test results structure, or %NULL
* @strings: Ethtool strings, or %NULL
* @data: Ethtool test results, or %NULL
+ *
+ * Get self-test number of strings, strings, and/or test results.
+ * Return number of strings (== number of test results).
+ *
+ * The reason for merging these three functions is to make sure that
+ * they can never be inconsistent.
*/
static int efx_ethtool_fill_self_tests(struct efx_nic *efx,
struct efx_self_tests *tests,
@@ -444,7 +453,7 @@
{
struct efx_nic *efx = netdev_priv(net_dev);
struct efx_self_tests *efx_tests;
- int already_up;
+ bool already_up;
int rc = -ENOMEM;
efx_tests = kzalloc(sizeof(*efx_tests), GFP_KERNEL);
@@ -452,8 +461,8 @@
goto fail;
if (efx->state != STATE_READY) {
- rc = -EIO;
- goto fail1;
+ rc = -EBUSY;
+ goto out;
}
netif_info(efx, drv, efx->net_dev, "starting %sline testing\n",
@@ -466,7 +475,7 @@
if (rc) {
netif_err(efx, drv, efx->net_dev,
"failed opening device.\n");
- goto fail1;
+ goto out;
}
}
@@ -479,8 +488,7 @@
rc == 0 ? "passed" : "failed",
(test->flags & ETH_TEST_FL_OFFLINE) ? "off" : "on");
-fail1:
- /* Fill ethtool results structures */
+out:
efx_ethtool_fill_self_tests(efx, efx_tests, NULL, data);
kfree(efx_tests);
fail:
@@ -691,7 +699,6 @@
pause->autoneg = !!(efx->wanted_fc & EFX_FC_AUTO);
}
-
static void efx_ethtool_get_wol(struct net_device *net_dev,
struct ethtool_wolinfo *wol)
{
@@ -720,7 +727,7 @@
}
/* MAC address mask including only I/G bit */
-static const u8 mac_addr_ig_mask[ETH_ALEN] = { 0x01, 0, 0, 0, 0, 0 };
+static const u8 mac_addr_ig_mask[ETH_ALEN] __aligned(2) = {0x01, 0, 0, 0, 0, 0};
#define IP4_ADDR_FULL_MASK ((__force __be32)~0)
#define PORT_FULL_MASK ((__force __be16)~0)
@@ -780,16 +787,16 @@
rule->flow_type = ETHER_FLOW;
if (spec.match_flags &
(EFX_FILTER_MATCH_LOC_MAC | EFX_FILTER_MATCH_LOC_MAC_IG)) {
- memcpy(mac_entry->h_dest, spec.loc_mac, ETH_ALEN);
+ ether_addr_copy(mac_entry->h_dest, spec.loc_mac);
if (spec.match_flags & EFX_FILTER_MATCH_LOC_MAC)
- memset(mac_mask->h_dest, ~0, ETH_ALEN);
+ eth_broadcast_addr(mac_mask->h_dest);
else
- memcpy(mac_mask->h_dest, mac_addr_ig_mask,
- ETH_ALEN);
+ ether_addr_copy(mac_mask->h_dest,
+ mac_addr_ig_mask);
}
if (spec.match_flags & EFX_FILTER_MATCH_REM_MAC) {
- memcpy(mac_entry->h_source, spec.rem_mac, ETH_ALEN);
- memset(mac_mask->h_source, ~0, ETH_ALEN);
+ ether_addr_copy(mac_entry->h_source, spec.rem_mac);
+ eth_broadcast_addr(mac_mask->h_source);
}
if (spec.match_flags & EFX_FILTER_MATCH_ETHER_TYPE) {
mac_entry->h_proto = spec.ether_type;
@@ -961,13 +968,13 @@
spec.match_flags |= EFX_FILTER_MATCH_LOC_MAC;
else
return -EINVAL;
- memcpy(spec.loc_mac, mac_entry->h_dest, ETH_ALEN);
+ ether_addr_copy(spec.loc_mac, mac_entry->h_dest);
}
if (!is_zero_ether_addr(mac_mask->h_source)) {
if (!is_broadcast_ether_addr(mac_mask->h_source))
return -EINVAL;
spec.match_flags |= EFX_FILTER_MATCH_REM_MAC;
- memcpy(spec.rem_mac, mac_entry->h_source, ETH_ALEN);
+ ether_addr_copy(spec.rem_mac, mac_entry->h_source);
}
if (mac_mask->h_proto) {
if (mac_mask->h_proto != ETHER_TYPE_FULL_MASK)
diff --git a/drivers/net/ethernet/sfc/falcon.c b/drivers/net/ethernet/sfc/falcon.c
index 18d6f76..8ec20b7 100644
--- a/drivers/net/ethernet/sfc/falcon.c
+++ b/drivers/net/ethernet/sfc/falcon.c
@@ -422,7 +422,6 @@
efx_readd(efx, ®, FR_AA_WORK_AROUND_BROKEN_PCI_READS);
}
-
static irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id)
{
struct efx_nic *efx = dev_id;
@@ -467,6 +466,7 @@
efx_schedule_channel_irq(efx_get_channel(efx, 1));
return IRQ_HANDLED;
}
+
/**************************************************************************
*
* RSS
@@ -1358,6 +1358,7 @@
case 100: link_speed = 1; break;
default: link_speed = 0; break;
}
+
/* MAC_LINK_STATUS controls MAC backpressure but doesn't work
* as advertised. Disable to ensure packets are not
* indefinitely held and TX queue can be flushed at any point
@@ -2182,7 +2183,7 @@
}
/* Read the MAC addresses */
- memcpy(efx->net_dev->perm_addr, nvconfig->mac_address[0], ETH_ALEN);
+ ether_addr_copy(efx->net_dev->perm_addr, nvconfig->mac_address[0]);
netif_dbg(efx, probe, efx->net_dev, "PHY is %d phy_id %d\n",
efx->phy_type, efx->mdio.prtad);
@@ -2868,4 +2869,3 @@
.mcdi_max_ver = -1,
.max_rx_ip_filters = FR_BZ_RX_FILTER_TBL0_ROWS,
};
-
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index f72489a..a087613 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -311,7 +311,6 @@
*/
void efx_farch_tx_write(struct efx_tx_queue *tx_queue)
{
-
struct efx_tx_buffer *buffer;
efx_qword_t *txd;
unsigned write_ptr;
@@ -1249,6 +1248,9 @@
int tx_packets = 0;
int spent = 0;
+ if (budget <= 0)
+ return spent;
+
read_ptr = channel->eventq_read_ptr;
for (;;) {
@@ -1609,7 +1611,6 @@
return IRQ_HANDLED;
}
-
/* Setup RSS indirection table.
* This maps from the hash value of the packet to RXQ
*/
diff --git a/drivers/net/ethernet/sfc/filter.h b/drivers/net/ethernet/sfc/filter.h
index 3ef298d..d0ed7f7 100644
--- a/drivers/net/ethernet/sfc/filter.h
+++ b/drivers/net/ethernet/sfc/filter.h
@@ -243,7 +243,7 @@
}
if (addr != NULL) {
spec->match_flags |= EFX_FILTER_MATCH_LOC_MAC;
- memcpy(spec->loc_mac, addr, ETH_ALEN);
+ ether_addr_copy(spec->loc_mac, addr);
}
return 0;
}
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index eb59abb..7bd4b14 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -1187,6 +1187,9 @@
int rc;
BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_IN_LEN != 0);
+ /* we need __aligned(2) for ether_addr_copy */
+ BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_OFST & 1);
+ BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1_OFST & 1);
rc = efx_mcdi_rpc(efx, MC_CMD_GET_BOARD_CFG, NULL, 0,
outbuf, sizeof(outbuf), &outlen);
@@ -1199,11 +1202,10 @@
}
if (mac_address)
- memcpy(mac_address,
- port_num ?
- MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1) :
- MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0),
- ETH_ALEN);
+ ether_addr_copy(mac_address,
+ port_num ?
+ MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1) :
+ MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0));
if (fw_subtype_list) {
for (i = 0;
i < MCDI_VAR_ARRAY_LEN(outlen,
@@ -1532,7 +1534,7 @@
MCDI_SET_DWORD(inbuf, WOL_FILTER_SET_IN_WOL_TYPE, type);
MCDI_SET_DWORD(inbuf, WOL_FILTER_SET_IN_FILTER_MODE,
MC_CMD_FILTER_MODE_SIMPLE);
- memcpy(MCDI_PTR(inbuf, WOL_FILTER_SET_IN_MAGIC_MAC), mac, ETH_ALEN);
+ ether_addr_copy(MCDI_PTR(inbuf, WOL_FILTER_SET_IN_MAGIC_MAC), mac);
rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_SET, inbuf, sizeof(inbuf),
outbuf, sizeof(outbuf), &outlen);
diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c
index 91d2325..e5fc4e1 100644
--- a/drivers/net/ethernet/sfc/mcdi_port.c
+++ b/drivers/net/ethernet/sfc/mcdi_port.c
@@ -854,8 +854,8 @@
BUILD_BUG_ON(MC_CMD_SET_MAC_OUT_LEN != 0);
- memcpy(MCDI_PTR(cmdbytes, SET_MAC_IN_ADDR),
- efx->net_dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(MCDI_PTR(cmdbytes, SET_MAC_IN_ADDR),
+ efx->net_dev->dev_addr);
MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_MTU,
EFX_MAX_FRAME_LEN(efx->net_dev->mtu));
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index af2b8c5..8a400a0 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -1323,7 +1323,6 @@
return &rx_queue->buffer[index];
}
-
/**
* EFX_MAX_FRAME_LEN - calculate maximum frame length
*
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index 79226b1..32d969e 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -530,4 +530,3 @@
efx->rx_nodesc_drops_prev_state = !!(efx->net_dev->flags & IFF_UP);
*rx_nodesc_drops -= efx->rx_nodesc_drops_while_down;
}
-
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index eb75fbd..6b861e3 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -223,7 +223,6 @@
* @evt_list: List of MC receive events awaiting packets
* @evt_free_list: List of free events
* @evt_lock: Lock for manipulating evt_list and evt_free_list
- * @evt_overflow: Boolean indicating that event list has overflowed
* @rx_evts: Instantiated events (on evt_list and evt_free_list)
* @workwq: Work queue for processing pending PTP operations
* @work: Work task
@@ -275,7 +274,6 @@
struct list_head evt_list;
struct list_head evt_free_list;
spinlock_t evt_lock;
- bool evt_overflow;
struct efx_ptp_event_rx rx_evts[MAX_RECEIVE_EVENTS];
struct workqueue_struct *workwq;
struct work_struct work;
@@ -768,37 +766,36 @@
return -EAGAIN;
}
- /* Convert the NIC time into kernel time. No correction is required-
- * this time is the output of a firmware process.
+ /* Calculate delay from last good sync (host time) to last_time.
+ * It is possible that the seconds rolled over between taking
+ * the start reading and the last value written by the host. The
+ * timescales are such that a gap of more than one second is never
+ * expected. delta is *not* normalised.
+ */
+ start_sec = ptp->timeset[last_good].host_start >> MC_NANOSECOND_BITS;
+ last_sec = last_time->ts_real.tv_sec & MC_SECOND_MASK;
+ if (start_sec != last_sec &&
+ ((start_sec + 1) & MC_SECOND_MASK) != last_sec) {
+ netif_warn(efx, hw, efx->net_dev,
+ "PTP bad synchronisation seconds\n");
+ return -EAGAIN;
+ }
+ delta.tv_sec = (last_sec - start_sec) & 1;
+ delta.tv_nsec =
+ last_time->ts_real.tv_nsec -
+ (ptp->timeset[last_good].host_start & MC_NANOSECOND_MASK);
+
+ /* Convert the NIC time at last good sync into kernel time.
+ * No correction is required - this time is the output of a
+ * firmware process.
*/
mc_time = ptp->nic_to_kernel_time(ptp->timeset[last_good].major,
ptp->timeset[last_good].minor, 0);
- /* Calculate delay from actual PPS to last_time */
- delta = ktime_to_timespec(mc_time);
- delta.tv_nsec +=
- last_time->ts_real.tv_nsec -
- (ptp->timeset[last_good].host_start & MC_NANOSECOND_MASK);
+ /* Calculate delay from NIC top of second to last_time */
+ delta.tv_nsec += ktime_to_timespec(mc_time).tv_nsec;
- /* It is possible that the seconds rolled over between taking
- * the start reading and the last value written by the host. The
- * timescales are such that a gap of more than one second is never
- * expected.
- */
- start_sec = ptp->timeset[last_good].host_start >> MC_NANOSECOND_BITS;
- last_sec = last_time->ts_real.tv_sec & MC_SECOND_MASK;
- if (start_sec != last_sec) {
- if (((start_sec + 1) & MC_SECOND_MASK) != last_sec) {
- netif_warn(efx, hw, efx->net_dev,
- "PTP bad synchronisation seconds\n");
- return -EAGAIN;
- } else {
- delta.tv_sec = 1;
- }
- } else {
- delta.tv_sec = 0;
- }
-
+ /* Set PPS timestamp to match NIC top of second */
ptp->host_time_pps = *last_time;
pps_sub_ts(&ptp->host_time_pps, delta);
@@ -941,11 +938,6 @@
}
}
}
- /* If the event overflow flag is set and the event list is now empty
- * clear the flag to re-enable the overflow warning message.
- */
- if (ptp->evt_overflow && list_empty(&ptp->evt_list))
- ptp->evt_overflow = false;
spin_unlock_bh(&ptp->evt_lock);
}
@@ -989,11 +981,6 @@
break;
}
}
- /* If the event overflow flag is set and the event list is now empty
- * clear the flag to re-enable the overflow warning message.
- */
- if (ptp->evt_overflow && list_empty(&ptp->evt_list))
- ptp->evt_overflow = false;
spin_unlock_bh(&ptp->evt_lock);
return rc;
@@ -1147,7 +1134,6 @@
list_for_each_safe(cursor, next, &efx->ptp_data->evt_list) {
list_move(cursor, &efx->ptp_data->evt_free_list);
}
- ptp->evt_overflow = false;
spin_unlock_bh(&efx->ptp_data->evt_lock);
return rc;
@@ -1208,6 +1194,7 @@
.n_alarm = 0,
.n_ext_ts = 0,
.n_per_out = 0,
+ .n_pins = 0,
.pps = 1,
.adjfreq = efx_phc_adjfreq,
.adjtime = efx_phc_adjtime,
@@ -1253,7 +1240,6 @@
spin_lock_init(&ptp->evt_lock);
for (pos = 0; pos < MAX_RECEIVE_EVENTS; pos++)
list_add(&ptp->rx_evts[pos].link, &ptp->evt_free_list);
- ptp->evt_overflow = false;
/* Get the NIC PTP attributes and set up time conversions */
rc = efx_ptp_get_attributes(efx);
@@ -1380,6 +1366,7 @@
struct efx_ptp_match *match = (struct efx_ptp_match *)skb->cb;
u8 *match_data_012, *match_data_345;
unsigned int version;
+ u8 *data;
match->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS);
@@ -1388,7 +1375,8 @@
if (!pskb_may_pull(skb, PTP_V1_MIN_LENGTH)) {
return false;
}
- version = ntohs(*(__be16 *)&skb->data[PTP_V1_VERSION_OFFSET]);
+ data = skb->data;
+ version = ntohs(*(__be16 *)&data[PTP_V1_VERSION_OFFSET]);
if (version != PTP_VERSION_V1) {
return false;
}
@@ -1396,13 +1384,14 @@
/* PTP V1 uses all six bytes of the UUID to match the packet
* to the timestamp
*/
- match_data_012 = skb->data + PTP_V1_UUID_OFFSET;
- match_data_345 = skb->data + PTP_V1_UUID_OFFSET + 3;
+ match_data_012 = data + PTP_V1_UUID_OFFSET;
+ match_data_345 = data + PTP_V1_UUID_OFFSET + 3;
} else {
if (!pskb_may_pull(skb, PTP_V2_MIN_LENGTH)) {
return false;
}
- version = skb->data[PTP_V2_VERSION_OFFSET];
+ data = skb->data;
+ version = data[PTP_V2_VERSION_OFFSET];
if ((version & PTP_VERSION_V2_MASK) != PTP_VERSION_V2) {
return false;
}
@@ -1414,17 +1403,17 @@
* enhanced mode fixes this issue and uses bytes 0-2
* and byte 5-7 of the UUID.
*/
- match_data_345 = skb->data + PTP_V2_UUID_OFFSET + 5;
+ match_data_345 = data + PTP_V2_UUID_OFFSET + 5;
if (ptp->mode == MC_CMD_PTP_MODE_V2) {
- match_data_012 = skb->data + PTP_V2_UUID_OFFSET + 2;
+ match_data_012 = data + PTP_V2_UUID_OFFSET + 2;
} else {
- match_data_012 = skb->data + PTP_V2_UUID_OFFSET + 0;
+ match_data_012 = data + PTP_V2_UUID_OFFSET + 0;
BUG_ON(ptp->mode != MC_CMD_PTP_MODE_V2_ENHANCED);
}
}
/* Does this packet require timestamping? */
- if (ntohs(*(__be16 *)&skb->data[PTP_DPORT_OFFSET]) == PTP_EVENT_PORT) {
+ if (ntohs(*(__be16 *)&data[PTP_DPORT_OFFSET]) == PTP_EVENT_PORT) {
match->state = PTP_PACKET_STATE_UNMATCHED;
/* We expect the sequence number to be in the same position in
@@ -1440,8 +1429,8 @@
(match_data_345[0] << 24));
match->words[1] = (match_data_345[1] |
(match_data_345[2] << 8) |
- (skb->data[PTP_V1_SEQUENCE_OFFSET +
- PTP_V1_SEQUENCE_LENGTH - 1] <<
+ (data[PTP_V1_SEQUENCE_OFFSET +
+ PTP_V1_SEQUENCE_LENGTH - 1] <<
16));
} else {
match->state = PTP_PACKET_STATE_MATCH_UNWANTED;
@@ -1635,13 +1624,9 @@
list_add_tail(&evt->link, &ptp->evt_list);
queue_work(ptp->workwq, &ptp->work);
- } else if (!ptp->evt_overflow) {
- /* Log a warning message and set the event overflow flag.
- * The message won't be logged again until the event queue
- * becomes empty.
- */
+ } else if (net_ratelimit()) {
+ /* Log a rate-limited warning message. */
netif_err(efx, rx_err, efx->net_dev, "PTP event queue overflow\n");
- ptp->evt_overflow = true;
}
spin_unlock_bh(&ptp->evt_lock);
}
@@ -1668,6 +1653,13 @@
struct efx_ptp_data *ptp = efx->ptp_data;
int code = EFX_QWORD_FIELD(*ev, MCDI_EVENT_CODE);
+ if (!ptp) {
+ if (net_ratelimit())
+ netif_warn(efx, drv, efx->net_dev,
+ "Received PTP event but PTP not set up\n");
+ return;
+ }
+
if (!ptp->enabled)
return;
diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c
index 2664181..0fc5bae 100644
--- a/drivers/net/ethernet/sfc/selftest.c
+++ b/drivers/net/ethernet/sfc/selftest.c
@@ -50,7 +50,7 @@
} __packed;
/* Loopback test source MAC address */
-static const unsigned char payload_source[ETH_ALEN] = {
+static const u8 payload_source[ETH_ALEN] __aligned(2) = {
0x00, 0x0f, 0x53, 0x1b, 0x1b, 0x1b,
};
@@ -366,8 +366,8 @@
struct efx_loopback_payload *payload = &state->payload;
/* Initialise the layerII header */
- memcpy(&payload->header.h_dest, net_dev->dev_addr, ETH_ALEN);
- memcpy(&payload->header.h_source, &payload_source, ETH_ALEN);
+ ether_addr_copy((u8 *)&payload->header.h_dest, net_dev->dev_addr);
+ ether_addr_copy((u8 *)&payload->header.h_source, payload_source);
payload->header.h_proto = htons(ETH_P_IP);
/* saddr set later and used as incrementing count */
diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c
index 0c38f92..9a9205e 100644
--- a/drivers/net/ethernet/sfc/siena_sriov.c
+++ b/drivers/net/ethernet/sfc/siena_sriov.c
@@ -1095,7 +1095,7 @@
/* Fill the remaining addresses */
list_for_each_entry(local_addr, &efx->local_addr_list, link) {
- memcpy(peer->mac_addr, local_addr->addr, ETH_ALEN);
+ ether_addr_copy(peer->mac_addr, local_addr->addr);
peer->tci = 0;
++peer;
++peer_count;
@@ -1303,8 +1303,7 @@
goto fail_vfs;
rtnl_lock();
- memcpy(vfdi_status->peers[0].mac_addr,
- net_dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(vfdi_status->peers[0].mac_addr, net_dev->dev_addr);
efx->vf_init_count = efx->vf_count;
rtnl_unlock();
@@ -1452,8 +1451,8 @@
if (!efx->vf_init_count)
return;
- memcpy(vfdi_status->peers[0].mac_addr,
- efx->net_dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(vfdi_status->peers[0].mac_addr,
+ efx->net_dev->dev_addr);
queue_work(vfdi_workqueue, &efx->peer_work);
}
@@ -1570,7 +1569,7 @@
vf = efx->vf + vf_i;
mutex_lock(&vf->status_lock);
- memcpy(vf->addr.mac_addr, mac, ETH_ALEN);
+ ether_addr_copy(vf->addr.mac_addr, mac);
__efx_sriov_update_vf_addr(vf);
mutex_unlock(&vf->status_lock);
@@ -1633,7 +1632,7 @@
vf = efx->vf + vf_i;
ivi->vf = vf_i;
- memcpy(ivi->mac, vf->addr.mac_addr, ETH_ALEN);
+ ether_addr_copy(ivi->mac, vf->addr.mac_addr);
ivi->tx_rate = 0;
tci = ntohs(vf->addr.tci);
ivi->vlan = tci & VLAN_VID_MASK;
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index c49d1fb..fa94753 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -429,7 +429,9 @@
}
/* Transfer ownership of the skb to the final buffer */
+#ifdef EFX_USE_PIO
finish_packet:
+#endif
buffer->skb = skb;
buffer->flags = EFX_TX_BUF_SKB | dma_flags;
@@ -785,15 +787,6 @@
* Requires TX checksum offload support.
*/
-/* Number of bytes inserted at the start of a TSO header buffer,
- * similar to NET_IP_ALIGN.
- */
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-#define TSOH_OFFSET 0
-#else
-#define TSOH_OFFSET NET_IP_ALIGN
-#endif
-
#define PTR_DIFF(p1, p2) ((u8 *)(p1) - (u8 *)(p2))
/**
@@ -880,13 +873,13 @@
EFX_BUG_ON_PARANOID(buffer->flags);
EFX_BUG_ON_PARANOID(buffer->unmap_len);
- if (likely(len <= TSOH_STD_SIZE - TSOH_OFFSET)) {
+ if (likely(len <= TSOH_STD_SIZE - NET_IP_ALIGN)) {
unsigned index =
(tx_queue->insert_count & tx_queue->ptr_mask) / 2;
struct efx_buffer *page_buf =
&tx_queue->tsoh_page[index / TSOH_PER_PAGE];
unsigned offset =
- TSOH_STD_SIZE * (index % TSOH_PER_PAGE) + TSOH_OFFSET;
+ TSOH_STD_SIZE * (index % TSOH_PER_PAGE) + NET_IP_ALIGN;
if (unlikely(!page_buf->addr) &&
efx_nic_alloc_buffer(tx_queue->efx, page_buf, PAGE_SIZE,
@@ -899,10 +892,10 @@
} else {
tx_queue->tso_long_headers++;
- buffer->heap_buf = kmalloc(TSOH_OFFSET + len, GFP_ATOMIC);
+ buffer->heap_buf = kmalloc(NET_IP_ALIGN + len, GFP_ATOMIC);
if (unlikely(!buffer->heap_buf))
return NULL;
- result = (u8 *)buffer->heap_buf + TSOH_OFFSET;
+ result = (u8 *)buffer->heap_buf + NET_IP_ALIGN;
buffer->flags = EFX_TX_BUF_CONT | EFX_TX_BUF_HEAP;
}
@@ -1009,7 +1002,7 @@
static int tso_start(struct tso_state *st, struct efx_nic *efx,
const struct sk_buff *skb)
{
- bool use_options = efx_nic_rev(efx) >= EFX_REV_HUNT_A0;
+ bool use_opt_desc = efx_nic_rev(efx) >= EFX_REV_HUNT_A0;
struct device *dma_dev = &efx->pci_dev->dev;
unsigned int header_len, in_len;
dma_addr_t dma_addr;
@@ -1035,7 +1028,7 @@
st->out_len = skb->len - header_len;
- if (!use_options) {
+ if (!use_opt_desc) {
st->header_unmap_len = 0;
if (likely(in_len == 0)) {
diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c
index 5eb933c..7daa7d4 100644
--- a/drivers/net/ethernet/silan/sc92031.c
+++ b/drivers/net/ethernet/silan/sc92031.c
@@ -987,7 +987,7 @@
spin_unlock(&priv->lock);
out:
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index ff57a46..6072f09 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -1614,7 +1614,7 @@
skb->data, skb->len, PCI_DMA_TODEVICE);
if (unlikely(pci_dma_mapping_error(sis_priv->pci_dev,
sis_priv->tx_ring[entry].bufptr))) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
sis_priv->tx_skbuff[entry] = NULL;
net_dev->stats.tx_dropped++;
spin_unlock_irqrestore(&sis_priv->lock, flags);
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index c50fb08..66b05e6 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -551,7 +551,7 @@
dev->stats.tx_errors++;
dev->stats.tx_dropped++;
spin_unlock_irqrestore(&lp->lock, flags);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 839c0e6..d1b4dca 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -621,7 +621,7 @@
done: if (!THROTTLE_TX_PKTS)
netif_wake_queue(dev);
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
}
/*
@@ -657,7 +657,7 @@
netdev_warn(dev, "Far too big packet error.\n");
dev->stats.tx_errors++;
dev->stats.tx_dropped++;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 6382b7c..a0fc151 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -439,7 +439,8 @@
/* Request clock */
pdata->clk = clk_get(&pdev->dev, NULL);
if (IS_ERR(pdata->clk))
- netdev_warn(ndev, "couldn't get clock %li\n", PTR_ERR(pdata->clk));
+ dev_dbg(&pdev->dev, "couldn't get clock %li\n",
+ PTR_ERR(pdata->clk));
return ret;
}
@@ -1672,7 +1673,7 @@
pdata->ops->tx_writefifo(pdata, (unsigned int *)bufp, wrsz);
freespace -= (skb->len + 32);
skb_tx_timestamp(skb);
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
if (unlikely(smsc911x_tx_get_txstatcount(pdata) >= 30))
smsc911x_tx_update_txcounters(dev);
@@ -2379,8 +2380,6 @@
int res_size, irq_flags;
int retval;
- pr_info("Driver version %s\n", SMSC_DRV_VERSION);
-
res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
"smsc911x-memory");
if (!res)
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index e2f202e..2d09c11 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -26,6 +26,16 @@
If unsure, say N.
+config DWMAC_SOCFPGA
+ bool "SOCFPGA dwmac support"
+ depends on STMMAC_PLATFORM && MFD_SYSCON && (ARCH_SOCFPGA || COMPILE_TEST)
+ help
+ Support for ethernet controller on Altera SOCFPGA
+
+ This selects the Altera SOCFPGA SoC glue layer support
+ for the stmmac device driver. This driver is used for
+ arria5 and cyclone5 FPGA SoCs.
+
config DWMAC_SUNXI
bool "Allwinner GMAC support"
depends on STMMAC_PLATFORM && ARCH_SUNXI
@@ -37,6 +47,17 @@
stmmac device driver. This driver is used for A20/A31
GMAC ethernet controller.
+config DWMAC_STI
+ bool "STi GMAC support"
+ depends on STMMAC_PLATFORM && ARCH_STI
+ default y
+ ---help---
+ Support for ethernet controller on STi SOCs.
+
+ This selects STi SoC glue layer support for the stmmac
+ device driver. This driver is used on for the STi series
+ SOCs GMAC ethernet controller.
+
config STMMAC_PCI
bool "STMMAC PCI bus support"
depends on STMMAC_ETH && PCI
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index ecadece..18695eb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -2,6 +2,8 @@
stmmac-$(CONFIG_STMMAC_PLATFORM) += stmmac_platform.o
stmmac-$(CONFIG_STMMAC_PCI) += stmmac_pci.o
stmmac-$(CONFIG_DWMAC_SUNXI) += dwmac-sunxi.o
+stmmac-$(CONFIG_DWMAC_STI) += dwmac-sti.o
+stmmac-$(CONFIG_DWMAC_SOCFPGA) += dwmac-socfpga.o
stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o \
chain_mode.o dwmac_lib.o dwmac1000_core.o dwmac1000_dma.o \
dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o \
diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
index 72d282b..c553f6b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
@@ -151,7 +151,7 @@
sizeof(struct dma_desc)));
}
-const struct stmmac_chain_mode_ops chain_mode_ops = {
+const struct stmmac_mode_ops chain_mode_ops = {
.init = stmmac_init_dma_chain,
.is_jumbo_frm = stmmac_is_jumbo_frm,
.jumbo_frm = stmmac_jumbo_frm,
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 7834a39..74610f3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -419,20 +419,13 @@
unsigned int data; /* MII Data */
};
-struct stmmac_ring_mode_ops {
- unsigned int (*is_jumbo_frm) (int len, int ehn_desc);
- unsigned int (*jumbo_frm) (void *priv, struct sk_buff *skb, int csum);
- void (*refill_desc3) (void *priv, struct dma_desc *p);
- void (*init_desc3) (struct dma_desc *p);
- void (*clean_desc3) (void *priv, struct dma_desc *p);
- int (*set_16kib_bfsize) (int mtu);
-};
-
-struct stmmac_chain_mode_ops {
+struct stmmac_mode_ops {
void (*init) (void *des, dma_addr_t phy_addr, unsigned int size,
unsigned int extend_desc);
unsigned int (*is_jumbo_frm) (int len, int ehn_desc);
unsigned int (*jumbo_frm) (void *priv, struct sk_buff *skb, int csum);
+ int (*set_16kib_bfsize)(int mtu);
+ void (*init_desc3)(struct dma_desc *p);
void (*refill_desc3) (void *priv, struct dma_desc *p);
void (*clean_desc3) (void *priv, struct dma_desc *p);
};
@@ -441,8 +434,7 @@
const struct stmmac_ops *mac;
const struct stmmac_desc_ops *desc;
const struct stmmac_dma_ops *dma;
- const struct stmmac_ring_mode_ops *ring;
- const struct stmmac_chain_mode_ops *chain;
+ const struct stmmac_mode_ops *mode;
const struct stmmac_hwtimestamp *ptp;
struct mii_regs mii; /* MII register Addresses */
struct mac_link link;
@@ -460,7 +452,7 @@
void stmmac_set_mac(void __iomem *ioaddr, bool enable);
void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr);
-extern const struct stmmac_ring_mode_ops ring_mode_ops;
-extern const struct stmmac_chain_mode_ops chain_mode_ops;
+extern const struct stmmac_mode_ops ring_mode_ops;
+extern const struct stmmac_mode_ops chain_mode_ops;
#endif /* __COMMON_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
new file mode 100644
index 0000000..fd8a217
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -0,0 +1,130 @@
+/* Copyright Altera Corporation (C) 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Adopted from dwmac-sti.c
+ */
+
+#include <linux/mfd/syscon.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+#include <linux/phy.h>
+#include <linux/regmap.h>
+#include <linux/stmmac.h>
+
+#define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII 0x0
+#define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII 0x1
+#define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RMII 0x2
+#define SYSMGR_EMACGRP_CTRL_PHYSEL_WIDTH 2
+#define SYSMGR_EMACGRP_CTRL_PHYSEL_MASK 0x00000003
+
+struct socfpga_dwmac {
+ int interface;
+ u32 reg_offset;
+ u32 reg_shift;
+ struct device *dev;
+ struct regmap *sys_mgr_base_addr;
+};
+
+static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device *dev)
+{
+ struct device_node *np = dev->of_node;
+ struct regmap *sys_mgr_base_addr;
+ u32 reg_offset, reg_shift;
+ int ret;
+
+ dwmac->interface = of_get_phy_mode(np);
+
+ sys_mgr_base_addr = syscon_regmap_lookup_by_phandle(np, "altr,sysmgr-syscon");
+ if (IS_ERR(sys_mgr_base_addr)) {
+ dev_info(dev, "No sysmgr-syscon node found\n");
+ return PTR_ERR(sys_mgr_base_addr);
+ }
+
+ ret = of_property_read_u32_index(np, "altr,sysmgr-syscon", 1, ®_offset);
+ if (ret) {
+ dev_info(dev, "Could not read reg_offset from sysmgr-syscon!\n");
+ return -EINVAL;
+ }
+
+ ret = of_property_read_u32_index(np, "altr,sysmgr-syscon", 2, ®_shift);
+ if (ret) {
+ dev_info(dev, "Could not read reg_shift from sysmgr-syscon!\n");
+ return -EINVAL;
+ }
+
+ dwmac->reg_offset = reg_offset;
+ dwmac->reg_shift = reg_shift;
+ dwmac->sys_mgr_base_addr = sys_mgr_base_addr;
+ dwmac->dev = dev;
+
+ return 0;
+}
+
+static int socfpga_dwmac_setup(struct socfpga_dwmac *dwmac)
+{
+ struct regmap *sys_mgr_base_addr = dwmac->sys_mgr_base_addr;
+ int phymode = dwmac->interface;
+ u32 reg_offset = dwmac->reg_offset;
+ u32 reg_shift = dwmac->reg_shift;
+ u32 ctrl, val;
+
+ switch (phymode) {
+ case PHY_INTERFACE_MODE_RGMII:
+ val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII;
+ break;
+ case PHY_INTERFACE_MODE_MII:
+ case PHY_INTERFACE_MODE_GMII:
+ val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII;
+ break;
+ default:
+ dev_err(dwmac->dev, "bad phy mode %d\n", phymode);
+ return -EINVAL;
+ }
+
+ regmap_read(sys_mgr_base_addr, reg_offset, &ctrl);
+ ctrl &= ~(SYSMGR_EMACGRP_CTRL_PHYSEL_MASK << reg_shift);
+ ctrl |= val << reg_shift;
+
+ regmap_write(sys_mgr_base_addr, reg_offset, ctrl);
+ return 0;
+}
+
+static void *socfpga_dwmac_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ int ret;
+ struct socfpga_dwmac *dwmac;
+
+ dwmac = devm_kzalloc(dev, sizeof(*dwmac), GFP_KERNEL);
+ if (!dwmac)
+ return ERR_PTR(-ENOMEM);
+
+ ret = socfpga_dwmac_parse_data(dwmac, dev);
+ if (ret) {
+ dev_err(dev, "Unable to parse OF data\n");
+ return ERR_PTR(ret);
+ }
+
+ ret = socfpga_dwmac_setup(dwmac);
+ if (ret) {
+ dev_err(dev, "couldn't setup SoC glue (%d)\n", ret);
+ return ERR_PTR(ret);
+ }
+
+ return dwmac;
+}
+
+const struct stmmac_of_data socfpga_gmac_data = {
+ .setup = socfpga_dwmac_probe,
+};
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
new file mode 100644
index 0000000..552bbc1
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -0,0 +1,330 @@
+/**
+ * dwmac-sti.c - STMicroelectronics DWMAC Specific Glue layer
+ *
+ * Copyright (C) 2003-2014 STMicroelectronics (R&D) Limited
+ * Author: Srinivas Kandagatla <srinivas.kandagatla@st.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/stmmac.h>
+#include <linux/phy.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+
+/**
+ * STi GMAC glue logic.
+ * --------------------
+ *
+ * _
+ * | \
+ * --------|0 \ ETH_SEL_INTERNAL_NOTEXT_PHYCLK
+ * phyclk | |___________________________________________
+ * | | | (phyclk-in)
+ * --------|1 / |
+ * int-clk |_ / |
+ * | _
+ * | | \
+ * |_______|1 \ ETH_SEL_TX_RETIME_CLK
+ * | |___________________________
+ * | | (tx-retime-clk)
+ * _______|0 /
+ * | |_ /
+ * _ |
+ * | \ |
+ * --------|0 \ |
+ * clk_125 | |__|
+ * | | ETH_SEL_TXCLK_NOT_CLK125
+ * --------|1 /
+ * txclk |_ /
+ *
+ *
+ * ETH_SEL_INTERNAL_NOTEXT_PHYCLK is valid only for RMII where PHY can
+ * generate 50MHz clock or MAC can generate it.
+ * This bit is configured by "st,ext-phyclk" property.
+ *
+ * ETH_SEL_TXCLK_NOT_CLK125 is only valid for gigabit modes, where the 125Mhz
+ * clock either comes from clk-125 pin or txclk pin. This configuration is
+ * totally driven by the board wiring. This bit is configured by
+ * "st,tx-retime-src" property.
+ *
+ * TXCLK configuration is different for different phy interface modes
+ * and changes according to link speed in modes like RGMII.
+ *
+ * Below table summarizes the clock requirement and clock sources for
+ * supported phy interface modes with link speeds.
+ * ________________________________________________
+ *| PHY_MODE | 1000 Mbit Link | 100 Mbit Link |
+ * ------------------------------------------------
+ *| MII | n/a | 25Mhz |
+ *| | | txclk |
+ * ------------------------------------------------
+ *| GMII | 125Mhz | 25Mhz |
+ *| | clk-125/txclk | txclk |
+ * ------------------------------------------------
+ *| RGMII | 125Mhz | 25Mhz |
+ *| | clk-125/txclk | clkgen |
+ * ------------------------------------------------
+ *| RMII | n/a | 25Mhz |
+ *| | |clkgen/phyclk-in |
+ * ------------------------------------------------
+ *
+ * TX lines are always retimed with a clk, which can vary depending
+ * on the board configuration. Below is the table of these bits
+ * in eth configuration register depending on source of retime clk.
+ *
+ *---------------------------------------------------------------
+ * src | tx_rt_clk | int_not_ext_phyclk | txclk_n_clk125|
+ *---------------------------------------------------------------
+ * txclk | 0 | n/a | 1 |
+ *---------------------------------------------------------------
+ * ck_125| 0 | n/a | 0 |
+ *---------------------------------------------------------------
+ * phyclk| 1 | 0 | n/a |
+ *---------------------------------------------------------------
+ * clkgen| 1 | 1 | n/a |
+ *---------------------------------------------------------------
+ */
+
+ /* Register definition */
+
+ /* 3 bits [8:6]
+ * [6:6] ETH_SEL_TXCLK_NOT_CLK125
+ * [7:7] ETH_SEL_INTERNAL_NOTEXT_PHYCLK
+ * [8:8] ETH_SEL_TX_RETIME_CLK
+ *
+ */
+
+#define TX_RETIME_SRC_MASK GENMASK(8, 6)
+#define ETH_SEL_TX_RETIME_CLK BIT(8)
+#define ETH_SEL_INTERNAL_NOTEXT_PHYCLK BIT(7)
+#define ETH_SEL_TXCLK_NOT_CLK125 BIT(6)
+
+#define ENMII_MASK GENMASK(5, 5)
+#define ENMII BIT(5)
+
+/**
+ * 3 bits [4:2]
+ * 000-GMII/MII
+ * 001-RGMII
+ * 010-SGMII
+ * 100-RMII
+*/
+#define MII_PHY_SEL_MASK GENMASK(4, 2)
+#define ETH_PHY_SEL_RMII BIT(4)
+#define ETH_PHY_SEL_SGMII BIT(3)
+#define ETH_PHY_SEL_RGMII BIT(2)
+#define ETH_PHY_SEL_GMII 0x0
+#define ETH_PHY_SEL_MII 0x0
+
+#define IS_PHY_IF_MODE_RGMII(iface) (iface == PHY_INTERFACE_MODE_RGMII || \
+ iface == PHY_INTERFACE_MODE_RGMII_ID || \
+ iface == PHY_INTERFACE_MODE_RGMII_RXID || \
+ iface == PHY_INTERFACE_MODE_RGMII_TXID)
+
+#define IS_PHY_IF_MODE_GBIT(iface) (IS_PHY_IF_MODE_RGMII(iface) || \
+ iface == PHY_INTERFACE_MODE_GMII)
+
+struct sti_dwmac {
+ int interface;
+ bool ext_phyclk;
+ bool is_tx_retime_src_clk_125;
+ struct clk *clk;
+ int reg;
+ struct device *dev;
+ struct regmap *regmap;
+};
+
+static u32 phy_intf_sels[] = {
+ [PHY_INTERFACE_MODE_MII] = ETH_PHY_SEL_MII,
+ [PHY_INTERFACE_MODE_GMII] = ETH_PHY_SEL_GMII,
+ [PHY_INTERFACE_MODE_RGMII] = ETH_PHY_SEL_RGMII,
+ [PHY_INTERFACE_MODE_RGMII_ID] = ETH_PHY_SEL_RGMII,
+ [PHY_INTERFACE_MODE_SGMII] = ETH_PHY_SEL_SGMII,
+ [PHY_INTERFACE_MODE_RMII] = ETH_PHY_SEL_RMII,
+};
+
+enum {
+ TX_RETIME_SRC_NA = 0,
+ TX_RETIME_SRC_TXCLK = 1,
+ TX_RETIME_SRC_CLK_125,
+ TX_RETIME_SRC_PHYCLK,
+ TX_RETIME_SRC_CLKGEN,
+};
+
+static const char *const tx_retime_srcs[] = {
+ [TX_RETIME_SRC_NA] = "",
+ [TX_RETIME_SRC_TXCLK] = "txclk",
+ [TX_RETIME_SRC_CLK_125] = "clk_125",
+ [TX_RETIME_SRC_PHYCLK] = "phyclk",
+ [TX_RETIME_SRC_CLKGEN] = "clkgen",
+};
+
+static u32 tx_retime_val[] = {
+ [TX_RETIME_SRC_TXCLK] = ETH_SEL_TXCLK_NOT_CLK125,
+ [TX_RETIME_SRC_CLK_125] = 0x0,
+ [TX_RETIME_SRC_PHYCLK] = ETH_SEL_TX_RETIME_CLK,
+ [TX_RETIME_SRC_CLKGEN] = ETH_SEL_TX_RETIME_CLK |
+ ETH_SEL_INTERNAL_NOTEXT_PHYCLK,
+};
+
+static void setup_retime_src(struct sti_dwmac *dwmac, u32 spd)
+{
+ u32 src = 0, freq = 0;
+
+ if (spd == SPEED_100) {
+ if (dwmac->interface == PHY_INTERFACE_MODE_MII ||
+ dwmac->interface == PHY_INTERFACE_MODE_GMII) {
+ src = TX_RETIME_SRC_TXCLK;
+ } else if (dwmac->interface == PHY_INTERFACE_MODE_RMII) {
+ if (dwmac->ext_phyclk) {
+ src = TX_RETIME_SRC_PHYCLK;
+ } else {
+ src = TX_RETIME_SRC_CLKGEN;
+ freq = 50000000;
+ }
+
+ } else if (IS_PHY_IF_MODE_RGMII(dwmac->interface)) {
+ src = TX_RETIME_SRC_CLKGEN;
+ freq = 25000000;
+ }
+
+ if (src == TX_RETIME_SRC_CLKGEN && dwmac->clk)
+ clk_set_rate(dwmac->clk, freq);
+
+ } else if (spd == SPEED_1000) {
+ if (dwmac->is_tx_retime_src_clk_125)
+ src = TX_RETIME_SRC_CLK_125;
+ else
+ src = TX_RETIME_SRC_TXCLK;
+ }
+
+ regmap_update_bits(dwmac->regmap, dwmac->reg,
+ TX_RETIME_SRC_MASK, tx_retime_val[src]);
+}
+
+static void sti_dwmac_exit(struct platform_device *pdev, void *priv)
+{
+ struct sti_dwmac *dwmac = priv;
+
+ if (dwmac->clk)
+ clk_disable_unprepare(dwmac->clk);
+}
+
+static void sti_fix_mac_speed(void *priv, unsigned int spd)
+{
+ struct sti_dwmac *dwmac = priv;
+
+ setup_retime_src(dwmac, spd);
+
+ return;
+}
+
+static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
+ struct platform_device *pdev)
+{
+ struct resource *res;
+ struct device *dev = &pdev->dev;
+ struct device_node *np = dev->of_node;
+ struct regmap *regmap;
+ int err;
+
+ if (!np)
+ return -EINVAL;
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sti-ethconf");
+ if (!res)
+ return -ENODATA;
+
+ regmap = syscon_regmap_lookup_by_phandle(np, "st,syscon");
+ if (IS_ERR(regmap))
+ return PTR_ERR(regmap);
+
+ dwmac->dev = dev;
+ dwmac->interface = of_get_phy_mode(np);
+ dwmac->regmap = regmap;
+ dwmac->reg = res->start;
+ dwmac->ext_phyclk = of_property_read_bool(np, "st,ext-phyclk");
+ dwmac->is_tx_retime_src_clk_125 = false;
+
+ if (IS_PHY_IF_MODE_GBIT(dwmac->interface)) {
+ const char *rs;
+
+ err = of_property_read_string(np, "st,tx-retime-src", &rs);
+ if (err < 0) {
+ dev_err(dev, "st,tx-retime-src not specified\n");
+ return err;
+ }
+
+ if (!strcasecmp(rs, "clk_125"))
+ dwmac->is_tx_retime_src_clk_125 = true;
+ }
+
+ dwmac->clk = devm_clk_get(dev, "sti-ethclk");
+
+ if (IS_ERR(dwmac->clk))
+ dwmac->clk = NULL;
+
+ return 0;
+}
+
+static int sti_dwmac_init(struct platform_device *pdev, void *priv)
+{
+ struct sti_dwmac *dwmac = priv;
+ struct regmap *regmap = dwmac->regmap;
+ int iface = dwmac->interface;
+ u32 reg = dwmac->reg;
+ u32 val, spd;
+
+ if (dwmac->clk)
+ clk_prepare_enable(dwmac->clk);
+
+ regmap_update_bits(regmap, reg, MII_PHY_SEL_MASK, phy_intf_sels[iface]);
+
+ val = (iface == PHY_INTERFACE_MODE_REVMII) ? 0 : ENMII;
+ regmap_update_bits(regmap, reg, ENMII_MASK, val);
+
+ if (IS_PHY_IF_MODE_GBIT(iface))
+ spd = SPEED_1000;
+ else
+ spd = SPEED_100;
+
+ setup_retime_src(dwmac, spd);
+
+ return 0;
+}
+
+static void *sti_dwmac_setup(struct platform_device *pdev)
+{
+ struct sti_dwmac *dwmac;
+ int ret;
+
+ dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL);
+ if (!dwmac)
+ return ERR_PTR(-ENOMEM);
+
+ ret = sti_dwmac_parse_data(dwmac, pdev);
+ if (ret) {
+ dev_err(&pdev->dev, "Unable to parse OF data\n");
+ return ERR_PTR(ret);
+ }
+
+ return dwmac;
+}
+
+const struct stmmac_of_data sti_gmac_data = {
+ .fix_mac_speed = sti_fix_mac_speed,
+ .setup = sti_dwmac_setup,
+ .init = sti_dwmac_init,
+ .exit = sti_dwmac_exit,
+};
diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index a96c7c2..650a4be 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -100,10 +100,9 @@
{
struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
- if (unlikely(priv->plat->has_gmac))
- /* Fill DES3 in case of RING mode */
- if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
- p->des3 = p->des2 + BUF_SIZE_8KiB;
+ /* Fill DES3 in case of RING mode */
+ if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
+ p->des3 = p->des2 + BUF_SIZE_8KiB;
}
/* In ring mode we need to fill the desc3 because it is used as buffer */
@@ -126,7 +125,7 @@
return ret;
}
-const struct stmmac_ring_mode_ops ring_mode_ops = {
+const struct stmmac_mode_ops ring_mode_ops = {
.is_jumbo_frm = stmmac_is_jumbo_frm,
.jumbo_frm = stmmac_jumbo_frm,
.refill_desc3 = stmmac_refill_desc3,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index d9af26e..ca01035 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -133,6 +133,12 @@
#ifdef CONFIG_DWMAC_SUNXI
extern const struct stmmac_of_data sun7i_gmac_data;
#endif
+#ifdef CONFIG_DWMAC_STI
+extern const struct stmmac_of_data sti_gmac_data;
+#endif
+#ifdef CONFIG_DWMAC_SOCFPGA
+extern const struct stmmac_of_data socfpga_gmac_data;
+#endif
extern struct platform_driver stmmac_pltfr_driver;
static inline int stmmac_register_platform(void)
{
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a2e7d2c..d940034 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -92,8 +92,8 @@
module_param(tc, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(tc, "DMA threshold control value");
-#define DMA_BUFFER_SIZE BUF_SIZE_4KiB
-static int buf_sz = DMA_BUFFER_SIZE;
+#define DEFAULT_BUFSIZE 1536
+static int buf_sz = DEFAULT_BUFSIZE;
module_param(buf_sz, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(buf_sz, "DMA buffer size");
@@ -136,8 +136,8 @@
dma_rxsize = DMA_RX_SIZE;
if (unlikely(dma_txsize < 0))
dma_txsize = DMA_TX_SIZE;
- if (unlikely((buf_sz < DMA_BUFFER_SIZE) || (buf_sz > BUF_SIZE_16KiB)))
- buf_sz = DMA_BUFFER_SIZE;
+ if (unlikely((buf_sz < DEFAULT_BUFSIZE) || (buf_sz > BUF_SIZE_16KiB)))
+ buf_sz = DEFAULT_BUFSIZE;
if (unlikely(flow_ctrl > 1))
flow_ctrl = FLOW_AUTO;
else if (likely(flow_ctrl < 0))
@@ -286,10 +286,25 @@
/* MAC core supports the EEE feature. */
if (priv->dma_cap.eee) {
- /* Check if the PHY supports EEE */
- if (phy_init_eee(priv->phydev, 1))
- goto out;
+ int tx_lpi_timer = priv->tx_lpi_timer;
+ /* Check if the PHY supports EEE */
+ if (phy_init_eee(priv->phydev, 1)) {
+ /* To manage at run-time if the EEE cannot be supported
+ * anymore (for example because the lp caps have been
+ * changed).
+ * In that case the driver disable own timers.
+ */
+ if (priv->eee_active) {
+ pr_debug("stmmac: disable EEE\n");
+ del_timer_sync(&priv->eee_ctrl_timer);
+ priv->hw->mac->set_eee_timer(priv->ioaddr, 0,
+ tx_lpi_timer);
+ }
+ priv->eee_active = 0;
+ goto out;
+ }
+ /* Activate the EEE and start timers */
if (!priv->eee_active) {
priv->eee_active = 1;
init_timer(&priv->eee_ctrl_timer);
@@ -300,13 +315,13 @@
priv->hw->mac->set_eee_timer(priv->ioaddr,
STMMAC_DEFAULT_LIT_LS,
- priv->tx_lpi_timer);
+ tx_lpi_timer);
} else
/* Set HW EEE according to the speed */
priv->hw->mac->set_eee_pls(priv->ioaddr,
priv->phydev->link);
- pr_info("stmmac: Energy-Efficient Ethernet initialized\n");
+ pr_debug("stmmac: Energy-Efficient Ethernet initialized\n");
ret = true;
}
@@ -886,10 +901,10 @@
ret = BUF_SIZE_8KiB;
else if (mtu >= BUF_SIZE_2KiB)
ret = BUF_SIZE_4KiB;
- else if (mtu >= DMA_BUFFER_SIZE)
+ else if (mtu > DEFAULT_BUFSIZE)
ret = BUF_SIZE_2KiB;
else
- ret = DMA_BUFFER_SIZE;
+ ret = DEFAULT_BUFSIZE;
return ret;
}
@@ -951,9 +966,9 @@
p->des2 = priv->rx_skbuff_dma[i];
- if ((priv->mode == STMMAC_RING_MODE) &&
+ if ((priv->hw->mode->init_desc3) &&
(priv->dma_buf_sz == BUF_SIZE_16KiB))
- priv->hw->ring->init_desc3(p);
+ priv->hw->mode->init_desc3(p);
return 0;
}
@@ -984,11 +999,8 @@
unsigned int bfsize = 0;
int ret = -ENOMEM;
- /* Set the max buffer size according to the DESC mode
- * and the MTU. Note that RING mode allows 16KiB bsize.
- */
- if (priv->mode == STMMAC_RING_MODE)
- bfsize = priv->hw->ring->set_16kib_bfsize(dev->mtu);
+ if (priv->hw->mode->set_16kib_bfsize)
+ bfsize = priv->hw->mode->set_16kib_bfsize(dev->mtu);
if (bfsize < BUF_SIZE_16KiB)
bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz);
@@ -1029,15 +1041,15 @@
/* Setup the chained descriptor addresses */
if (priv->mode == STMMAC_CHAIN_MODE) {
if (priv->extend_desc) {
- priv->hw->chain->init(priv->dma_erx, priv->dma_rx_phy,
- rxsize, 1);
- priv->hw->chain->init(priv->dma_etx, priv->dma_tx_phy,
- txsize, 1);
+ priv->hw->mode->init(priv->dma_erx, priv->dma_rx_phy,
+ rxsize, 1);
+ priv->hw->mode->init(priv->dma_etx, priv->dma_tx_phy,
+ txsize, 1);
} else {
- priv->hw->chain->init(priv->dma_rx, priv->dma_rx_phy,
- rxsize, 0);
- priv->hw->chain->init(priv->dma_tx, priv->dma_tx_phy,
- txsize, 0);
+ priv->hw->mode->init(priv->dma_rx, priv->dma_rx_phy,
+ rxsize, 0);
+ priv->hw->mode->init(priv->dma_tx, priv->dma_tx_phy,
+ txsize, 0);
}
}
@@ -1288,10 +1300,10 @@
DMA_TO_DEVICE);
priv->tx_skbuff_dma[entry] = 0;
}
- priv->hw->ring->clean_desc3(priv, p);
+ priv->hw->mode->clean_desc3(priv, p);
if (likely(skb != NULL)) {
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
priv->tx_skbuff[entry] = NULL;
}
@@ -1705,7 +1717,7 @@
priv->dma_rx_size = STMMAC_ALIGN(dma_rxsize);
priv->dma_buf_sz = STMMAC_ALIGN(buf_sz);
- alloc_dma_desc_resources(priv);
+ ret = alloc_dma_desc_resources(priv);
if (ret < 0) {
pr_err("%s: DMA descriptors allocation failed\n", __func__);
goto dma_desc_error;
@@ -1844,6 +1856,7 @@
int nfrags = skb_shinfo(skb)->nr_frags;
struct dma_desc *desc, *first;
unsigned int nopaged_len = skb_headlen(skb);
+ unsigned int enh_desc = priv->plat->enh_desc;
if (unlikely(stmmac_tx_avail(priv) < nfrags + 1)) {
if (!netif_queue_stopped(dev)) {
@@ -1871,27 +1884,19 @@
first = desc;
/* To program the descriptors according to the size of the frame */
- if (priv->mode == STMMAC_RING_MODE) {
- is_jumbo = priv->hw->ring->is_jumbo_frm(skb->len,
- priv->plat->enh_desc);
- if (unlikely(is_jumbo))
- entry = priv->hw->ring->jumbo_frm(priv, skb,
- csum_insertion);
- } else {
- is_jumbo = priv->hw->chain->is_jumbo_frm(skb->len,
- priv->plat->enh_desc);
- if (unlikely(is_jumbo))
- entry = priv->hw->chain->jumbo_frm(priv, skb,
- csum_insertion);
- }
+ if (enh_desc)
+ is_jumbo = priv->hw->mode->is_jumbo_frm(skb->len, enh_desc);
+
if (likely(!is_jumbo)) {
desc->des2 = dma_map_single(priv->device, skb->data,
nopaged_len, DMA_TO_DEVICE);
priv->tx_skbuff_dma[entry] = desc->des2;
priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len,
csum_insertion, priv->mode);
- } else
+ } else {
desc = first;
+ entry = priv->hw->mode->jumbo_frm(priv, skb, csum_insertion);
+ }
for (i = 0; i < nfrags; i++) {
const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
@@ -2029,7 +2034,7 @@
p->des2 = priv->rx_skbuff_dma[entry];
- priv->hw->ring->refill_desc3(priv, p);
+ priv->hw->mode->refill_desc3(priv, p);
if (netif_msg_rx_status(priv))
pr_debug("\trefill entry #%d\n", entry);
@@ -2633,11 +2638,11 @@
/* To use the chained or ring mode */
if (chain_mode) {
- priv->hw->chain = &chain_mode_ops;
+ priv->hw->mode = &chain_mode_ops;
pr_info(" Chain mode enabled\n");
priv->mode = STMMAC_CHAIN_MODE;
} else {
- priv->hw->ring = &ring_mode_ops;
+ priv->hw->mode = &ring_mode_ops;
pr_info(" Ring mode enabled\n");
priv->mode = STMMAC_RING_MODE;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 5884a7d..46aef510 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -33,6 +33,14 @@
#ifdef CONFIG_DWMAC_SUNXI
{ .compatible = "allwinner,sun7i-a20-gmac", .data = &sun7i_gmac_data},
#endif
+#ifdef CONFIG_DWMAC_STI
+ { .compatible = "st,stih415-dwmac", .data = &sti_gmac_data},
+ { .compatible = "st,stih416-dwmac", .data = &sti_gmac_data},
+ { .compatible = "st,stid127-dwmac", .data = &sti_gmac_data},
+#endif
+#ifdef CONFIG_DWMAC_SOCFPGA
+ { .compatible = "altr,socfpga-stmmac", .data = &socfpga_gmac_data },
+#endif
/* SoC specific glue layers should come before generic bindings */
{ .compatible = "st,spear600-gmac"},
{ .compatible = "snps,dwmac-3.610"},
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 7680581..b7ad356 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -164,6 +164,7 @@
.n_alarm = 0,
.n_ext_ts = 0,
.n_per_out = 0,
+ .n_pins = 0,
.pps = 0,
.adjfreq = stmmac_adjust_freq,
.adjtime = stmmac_adjust_time,
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 8e2266e..79606f47a 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -9041,7 +9041,7 @@
struct msix_entry msi_vec[NIU_NUM_LDG];
struct niu_parent *parent = np->parent;
struct pci_dev *pdev = np->pdev;
- int i, num_irqs, err;
+ int i, num_irqs;
u8 first_ldg;
first_ldg = (NIU_NUM_LDG / parent->num_ports) * np->port;
@@ -9053,21 +9053,16 @@
(np->port == 0 ? 3 : 1));
BUG_ON(num_irqs > (NIU_NUM_LDG / parent->num_ports));
-retry:
for (i = 0; i < num_irqs; i++) {
msi_vec[i].vector = 0;
msi_vec[i].entry = i;
}
- err = pci_enable_msix(pdev, msi_vec, num_irqs);
- if (err < 0) {
+ num_irqs = pci_enable_msix_range(pdev, msi_vec, 1, num_irqs);
+ if (num_irqs < 0) {
np->flags &= ~NIU_FLAGS_MSIX;
return;
}
- if (err > 0) {
- num_irqs = err;
- goto retry;
- }
np->flags |= NIU_FLAGS_MSIX;
for (i = 0; i < num_irqs; i++)
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index c2799dc..102a66f 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -688,7 +688,7 @@
}
dev->stats.tx_packets++;
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
}
gp->tx_old = entry;
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index bde63e3..5d5fec6 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -378,7 +378,6 @@
u32 version;
u32 coal_intvl;
u32 bus_freq_mhz;
- struct net_device_stats stats;
int rx_packet_max;
int host_port;
struct clk *clk;
@@ -554,7 +553,7 @@
* common for both the interface as the interface shares
* the same hardware resource.
*/
- for (i = 0; i <= priv->data.slaves; i++)
+ for (i = 0; i < priv->data.slaves; i++)
if (priv->slaves[i].ndev->flags & IFF_PROMISC)
flag = true;
@@ -578,7 +577,7 @@
unsigned long timeout = jiffies + HZ;
/* Disable Learn for all ports */
- for (i = 0; i <= priv->data.slaves; i++) {
+ for (i = 0; i < priv->data.slaves; i++) {
cpsw_ale_control_set(ale, i,
ALE_PORT_NOLEARN, 1);
cpsw_ale_control_set(ale, i,
@@ -606,7 +605,7 @@
cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 0);
/* Enable Learn for all ports */
- for (i = 0; i <= priv->data.slaves; i++) {
+ for (i = 0; i < priv->data.slaves; i++) {
cpsw_ale_control_set(ale, i,
ALE_PORT_NOLEARN, 0);
cpsw_ale_control_set(ale, i,
@@ -673,8 +672,8 @@
if (unlikely(netif_queue_stopped(ndev)))
netif_wake_queue(ndev);
cpts_tx_timestamp(priv->cpts, skb);
- priv->stats.tx_packets++;
- priv->stats.tx_bytes += len;
+ ndev->stats.tx_packets++;
+ ndev->stats.tx_bytes += len;
dev_kfree_skb_any(skb);
}
@@ -700,10 +699,10 @@
cpts_rx_timestamp(priv->cpts, skb);
skb->protocol = eth_type_trans(skb, ndev);
netif_receive_skb(skb);
- priv->stats.rx_bytes += len;
- priv->stats.rx_packets++;
+ ndev->stats.rx_bytes += len;
+ ndev->stats.rx_packets++;
} else {
- priv->stats.rx_dropped++;
+ ndev->stats.rx_dropped++;
new_skb = skb;
}
@@ -1164,11 +1163,17 @@
static void cpsw_slave_stop(struct cpsw_slave *slave, struct cpsw_priv *priv)
{
+ u32 slave_port;
+
+ slave_port = cpsw_get_slave_port(priv, slave->slave_num);
+
if (!slave->phy)
return;
phy_stop(slave->phy);
phy_disconnect(slave->phy);
slave->phy = NULL;
+ cpsw_ale_control_set(priv->ale, slave_port,
+ ALE_PORT_STATE, ALE_PORT_STATE_DISABLE);
}
static int cpsw_ndo_open(struct net_device *ndev)
@@ -1307,7 +1312,7 @@
if (skb_padto(skb, CPSW_MIN_PACKET_SIZE)) {
cpsw_err(priv, tx_err, "packet pad failed\n");
- priv->stats.tx_dropped++;
+ ndev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
@@ -1331,7 +1336,7 @@
return NETDEV_TX_OK;
fail:
- priv->stats.tx_dropped++;
+ ndev->stats.tx_dropped++;
netif_stop_queue(ndev);
return NETDEV_TX_BUSY;
}
@@ -1471,7 +1476,6 @@
static int cpsw_ndo_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
{
struct cpsw_priv *priv = netdev_priv(dev);
- struct mii_ioctl_data *data = if_mii(req);
int slave_no = cpsw_slave_index(priv);
if (!netif_running(dev))
@@ -1484,14 +1488,11 @@
case SIOCGHWTSTAMP:
return cpsw_hwtstamp_get(dev, req);
#endif
- case SIOCGMIIPHY:
- data->phy_id = priv->slaves[slave_no].phy->addr;
- break;
- default:
- return -ENOTSUPP;
}
- return 0;
+ if (!priv->slaves[slave_no].phy)
+ return -EOPNOTSUPP;
+ return phy_mii_ioctl(priv->slaves[slave_no].phy, req, cmd);
}
static void cpsw_ndo_tx_timeout(struct net_device *ndev)
@@ -1499,7 +1500,7 @@
struct cpsw_priv *priv = netdev_priv(ndev);
cpsw_err(priv, tx_err, "transmit timeout, restarting dma\n");
- priv->stats.tx_errors++;
+ ndev->stats.tx_errors++;
cpsw_intr_disable(priv);
cpdma_ctlr_int_ctrl(priv->dma, false);
cpdma_chan_stop(priv->txch);
@@ -1538,12 +1539,6 @@
return 0;
}
-static struct net_device_stats *cpsw_ndo_get_stats(struct net_device *ndev)
-{
- struct cpsw_priv *priv = netdev_priv(ndev);
- return &priv->stats;
-}
-
#ifdef CONFIG_NET_POLL_CONTROLLER
static void cpsw_ndo_poll_controller(struct net_device *ndev)
{
@@ -1636,7 +1631,6 @@
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = eth_change_mtu,
.ndo_tx_timeout = cpsw_ndo_tx_timeout,
- .ndo_get_stats = cpsw_ndo_get_stats,
.ndo_set_rx_mode = cpsw_ndo_set_rx_mode,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = cpsw_ndo_poll_controller,
@@ -1878,14 +1872,29 @@
mdio_node = of_find_node_by_phandle(be32_to_cpup(parp));
phyid = be32_to_cpup(parp+1);
mdio = of_find_device_by_node(mdio_node);
- snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
- PHY_ID_FMT, mdio->name, phyid);
+
+ if (strncmp(mdio->name, "gpio", 4) == 0) {
+ /* GPIO bitbang MDIO driver attached */
+ struct mii_bus *bus = dev_get_drvdata(&mdio->dev);
+
+ snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
+ PHY_ID_FMT, bus->id, phyid);
+ } else {
+ /* davinci MDIO driver attached */
+ snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
+ PHY_ID_FMT, mdio->name, phyid);
+ }
mac_addr = of_get_mac_address(slave_node);
if (mac_addr)
memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN);
slave_data->phy_if = of_get_phy_mode(slave_node);
+ if (slave_data->phy_if < 0) {
+ pr_err("Missing or malformed slave[%d] phy-mode property\n",
+ i);
+ return slave_data->phy_if;
+ }
if (data->dual_emac) {
if (of_property_read_u32(slave_node, "dual_emac_res_vlan",
@@ -2208,10 +2217,6 @@
goto clean_ale_ret;
}
- if (cpts_register(&pdev->dev, priv->cpts,
- data->cpts_clock_mult, data->cpts_clock_shift))
- dev_err(priv->dev, "error registering cpts device\n");
-
cpsw_notice(priv, probe, "initialized device (regs %pa, irq %d)\n",
&ss_res->start, ndev->irq);
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 8c351f1..a3bbf59 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -31,10 +31,6 @@
#ifdef CONFIG_TI_CPTS
-static struct sock_filter ptp_filter[] = {
- PTP_FILTER
-};
-
#define cpts_read32(c, r) __raw_readl(&c->reg->r)
#define cpts_write32(c, v, r) __raw_writel(v, &c->reg->r)
@@ -217,6 +213,7 @@
.name = "CTPS timer",
.max_adj = 1000000,
.n_ext_ts = 0,
+ .n_pins = 0,
.pps = 0,
.adjfreq = cpts_ptp_adjfreq,
.adjtime = cpts_ptp_adjtime,
@@ -300,7 +297,7 @@
u64 ns = 0;
struct cpts_event *event;
struct list_head *this, *next;
- unsigned int class = sk_run_filter(skb, ptp_filter);
+ unsigned int class = ptp_classify_raw(skb);
unsigned long flags;
u16 seqid;
u8 mtype;
@@ -371,10 +368,6 @@
int err, i;
unsigned long flags;
- if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter))) {
- pr_err("cpts: bad ptp filter\n");
- return -EINVAL;
- }
cpts->info = cpts_info;
cpts->clock = ptp_clock_register(&cpts->info, dev);
if (IS_ERR(cpts->clock)) {
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 364d0c7..88ef270 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -355,7 +355,7 @@
int i;
spin_lock_irqsave(&ctlr->lock, flags);
- if (ctlr->state != CPDMA_STATE_ACTIVE) {
+ if (ctlr->state == CPDMA_STATE_TEARDOWN) {
spin_unlock_irqrestore(&ctlr->lock, flags);
return -EINVAL;
}
@@ -891,7 +891,7 @@
unsigned timeout;
spin_lock_irqsave(&chan->lock, flags);
- if (chan->state != CPDMA_STATE_ACTIVE) {
+ if (chan->state == CPDMA_STATE_TEARDOWN) {
spin_unlock_irqrestore(&chan->lock, flags);
return -EINVAL;
}
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index cd9b164..8f0e69c 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1532,9 +1532,9 @@
struct device *emac_dev = &ndev->dev;
u32 cnt;
struct resource *res;
- int ret;
+ int q, m, ret;
+ int res_num = 0, irq_num = 0;
int i = 0;
- int k = 0;
struct emac_priv *priv = netdev_priv(ndev);
pm_runtime_get(&priv->pdev->dev);
@@ -1564,15 +1564,24 @@
}
/* Request IRQ */
+ while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ,
+ res_num))) {
+ for (irq_num = res->start; irq_num <= res->end; irq_num++) {
+ dev_err(emac_dev, "Request IRQ %d\n", irq_num);
+ if (request_irq(irq_num, emac_irq, 0, ndev->name,
+ ndev)) {
+ dev_err(emac_dev,
+ "DaVinci EMAC: request_irq() failed\n");
+ ret = -EBUSY;
- while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, k))) {
- for (i = res->start; i <= res->end; i++) {
- if (devm_request_irq(&priv->pdev->dev, i, emac_irq,
- 0, ndev->name, ndev))
goto rollback;
+ }
}
- k++;
+ res_num++;
}
+ /* prepare counters for rollback in case of an error */
+ res_num--;
+ irq_num--;
/* Start/Enable EMAC hardware */
emac_hw_enable(priv);
@@ -1639,11 +1648,23 @@
return 0;
-rollback:
-
- dev_err(emac_dev, "DaVinci EMAC: devm_request_irq() failed");
- ret = -EBUSY;
err:
+ emac_int_disable(priv);
+ napi_disable(&priv->napi);
+
+rollback:
+ for (q = res_num; q >= 0; q--) {
+ res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, q);
+ /* at the first iteration, irq_num is already set to the
+ * right value
+ */
+ if (q != res_num)
+ irq_num = res->end;
+
+ for (m = irq_num; m >= res->start; m--)
+ free_irq(m, ndev);
+ }
+ cpdma_ctlr_stop(priv->dma);
pm_runtime_put(&priv->pdev->dev);
return ret;
}
@@ -1659,6 +1680,9 @@
*/
static int emac_dev_stop(struct net_device *ndev)
{
+ struct resource *res;
+ int i = 0;
+ int irq_num;
struct emac_priv *priv = netdev_priv(ndev);
struct device *emac_dev = &ndev->dev;
@@ -1674,6 +1698,13 @@
if (priv->phydev)
phy_disconnect(priv->phydev);
+ /* Free IRQ */
+ while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, i))) {
+ for (irq_num = res->start; irq_num <= res->end; irq_num++)
+ free_irq(irq_num, priv->ndev);
+ i++;
+ }
+
if (netif_msg_drv(priv))
dev_notice(emac_dev, "DaVinci EMAC: %s stopped\n", ndev->name);
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 023237a..7e1c91d 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -659,6 +659,9 @@
struct info_mpipe *info_mpipe =
container_of(napi, struct info_mpipe, napi);
+ if (budget <= 0)
+ goto done;
+
instance = info_mpipe->instance;
while ((n = gxio_mpipe_iqueue_try_peek(
&info_mpipe->iqueue,
@@ -870,6 +873,7 @@
.name = "mPIPE clock",
.max_adj = 999999999,
.n_ext_ts = 0,
+ .n_pins = 0,
.pps = 0,
.adjfreq = ptp_mpipe_adjfreq,
.adjtime = ptp_mpipe_adjtime,
@@ -2071,7 +2075,7 @@
/* Return subqueue id on this core (one per core). */
static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv, select_queue_fallback_t fallback)
{
return smp_processor_id();
}
diff --git a/drivers/net/ethernet/tile/tilepro.c b/drivers/net/ethernet/tile/tilepro.c
index edb2e12..e5a5c5d 100644
--- a/drivers/net/ethernet/tile/tilepro.c
+++ b/drivers/net/ethernet/tile/tilepro.c
@@ -831,6 +831,9 @@
unsigned int work = 0;
+ if (budget <= 0)
+ goto done;
+
while (priv->active) {
int index = qup->__packet_receive_read;
if (index == qsp->__packet_receive_queue.__packet_write)
@@ -1821,7 +1824,7 @@
/* Handle completions. */
for (i = 0; i < nolds; i++)
- kfree_skb(olds[i]);
+ dev_consume_skb_any(olds[i]);
/* Update stats. */
u64_stats_update_begin(&stats->syncp);
@@ -2005,7 +2008,7 @@
/* Handle completions. */
for (i = 0; i < nolds; i++)
- kfree_skb(olds[i]);
+ dev_consume_skb_any(olds[i]);
/* HACK: Track "expanded" size for short packets (e.g. 42 < 60). */
u64_stats_update_begin(&stats->syncp);
@@ -2068,14 +2071,14 @@
cpu_stats = &priv->cpu[i]->stats;
do {
- start = u64_stats_fetch_begin_bh(&cpu_stats->syncp);
+ start = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
trx_packets = cpu_stats->rx_packets;
ttx_packets = cpu_stats->tx_packets;
trx_bytes = cpu_stats->rx_bytes;
ttx_bytes = cpu_stats->tx_bytes;
trx_errors = cpu_stats->rx_errors;
trx_dropped = cpu_stats->rx_dropped;
- } while (u64_stats_fetch_retry_bh(&cpu_stats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start));
rx_packets += trx_packets;
tx_packets += ttx_packets;
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
index 3f4a32e..0282d01 100644
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ b/drivers/net/ethernet/toshiba/spider_net.c
@@ -860,7 +860,7 @@
if (skb) {
pci_unmap_single(card->pdev, buf_addr, skb->len,
PCI_DMA_TODEVICE);
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
}
}
return 0;
diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index 88e9c73..fef5573 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -1645,6 +1645,9 @@
int received = 0, handled;
u32 status;
+ if (budget <= 0)
+ return received;
+
spin_lock(&lp->rx_lock);
status = tc_readl(&tr->Int_Src);
do {
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index ef312bc..f61dc2b 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -923,7 +923,7 @@
if (rc) {
dev_err(&pdev->dev,
"32-bit PCI DMA addresses not supported by the card!?\n");
- goto err_out;
+ goto err_out_pci_disable;
}
/* sanity check */
@@ -931,7 +931,7 @@
(pci_resource_len(pdev, 1) < io_size)) {
rc = -EIO;
dev_err(&pdev->dev, "Insufficient PCI resources, aborting\n");
- goto err_out;
+ goto err_out_pci_disable;
}
pioaddr = pci_resource_start(pdev, 0);
@@ -942,7 +942,7 @@
dev = alloc_etherdev(sizeof(struct rhine_private));
if (!dev) {
rc = -ENOMEM;
- goto err_out;
+ goto err_out_pci_disable;
}
SET_NETDEV_DEV(dev, &pdev->dev);
@@ -1022,7 +1022,7 @@
/* The chip-specific entries in the device structure. */
dev->netdev_ops = &rhine_netdev_ops;
- dev->ethtool_ops = &netdev_ethtool_ops,
+ dev->ethtool_ops = &netdev_ethtool_ops;
dev->watchdog_timeo = TX_TIMEOUT;
netif_napi_add(dev, &rp->napi, rhine_napipoll, 64);
@@ -1084,6 +1084,8 @@
pci_release_regions(pdev);
err_out_free_netdev:
free_netdev(dev);
+err_out_pci_disable:
+ pci_disable_device(pdev);
err_out:
return rc;
}
@@ -1676,7 +1678,7 @@
/* Must use alignment buffer. */
if (skb->len > PKT_BUF_SZ) {
/* packet too long, drop it */
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
rp->tx_skbuff[entry] = NULL;
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
@@ -1696,7 +1698,7 @@
pci_map_single(rp->pdev, skb->data, skb->len,
PCI_DMA_TODEVICE);
if (dma_mapping_error(&rp->pdev->dev, rp->tx_skbuff_dma[entry])) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
rp->tx_skbuff_dma[entry] = 0;
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
@@ -1834,7 +1836,7 @@
rp->tx_skbuff[entry]->len,
PCI_DMA_TODEVICE);
}
- dev_kfree_skb(rp->tx_skbuff[entry]);
+ dev_consume_skb_any(rp->tx_skbuff[entry]);
rp->tx_skbuff[entry] = NULL;
entry = (++rp->dirty_tx) % TX_RING_SIZE;
}
@@ -2070,16 +2072,16 @@
netdev_stats_to_stats64(stats, &dev->stats);
do {
- start = u64_stats_fetch_begin_bh(&rp->rx_stats.syncp);
+ start = u64_stats_fetch_begin_irq(&rp->rx_stats.syncp);
stats->rx_packets = rp->rx_stats.packets;
stats->rx_bytes = rp->rx_stats.bytes;
- } while (u64_stats_fetch_retry_bh(&rp->rx_stats.syncp, start));
+ } while (u64_stats_fetch_retry_irq(&rp->rx_stats.syncp, start));
do {
- start = u64_stats_fetch_begin_bh(&rp->tx_stats.syncp);
+ start = u64_stats_fetch_begin_irq(&rp->tx_stats.syncp);
stats->tx_packets = rp->tx_stats.packets;
stats->tx_bytes = rp->tx_stats.bytes;
- } while (u64_stats_fetch_retry_bh(&rp->tx_stats.syncp, start));
+ } while (u64_stats_fetch_retry_irq(&rp->tx_stats.syncp, start));
return stats;
}
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index ad61d26..de08e86 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -2565,7 +2565,7 @@
/* The hardware can handle at most 7 memory segments, so merge
* the skb if there are more */
if (skb_shinfo(skb)->nr_frags > 6 && __skb_linearize(skb)) {
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index 0df36c6..104d46f 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -641,11 +641,10 @@
if (!mem)
return -ENXIO;
mem_size = resource_size(mem);
- if (!devm_request_mem_region(&pdev->dev, mem->start, mem_size, name))
- return -EBUSY;
- priv->base = devm_ioremap(&pdev->dev, mem->start, mem_size);
- if (!priv->base)
- return -EBUSY;
+
+ priv->base = devm_ioremap_resource(&pdev->dev, mem);
+ if (IS_ERR(priv->base))
+ return PTR_ERR(priv->base);
spin_lock_init(&priv->reg_lock);
priv->indirect = mem_size < W5100_BUS_DIRECT_SIZE;
diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c
index 71c27b3..1f33c4c 100644
--- a/drivers/net/ethernet/wiznet/w5300.c
+++ b/drivers/net/ethernet/wiznet/w5300.c
@@ -561,11 +561,10 @@
if (!mem)
return -ENXIO;
mem_size = resource_size(mem);
- if (!devm_request_mem_region(&pdev->dev, mem->start, mem_size, name))
- return -EBUSY;
- priv->base = devm_ioremap(&pdev->dev, mem->start, mem_size);
- if (!priv->base)
- return -EBUSY;
+
+ priv->base = devm_ioremap_resource(&pdev->dev, mem);
+ if (IS_ERR(priv->base))
+ return PTR_ERR(priv->base);
spin_lock_init(&priv->reg_lock);
priv->indirect = mem_size < W5300_BUS_DIRECT_SIZE;
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index a434750..fa193c4 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -771,8 +771,8 @@
/* if we're doing rx csum offload, set it up */
if (((lp->temac_features & TEMAC_FEATURE_RX_CSUM) != 0) &&
- (skb->protocol == __constant_htons(ETH_P_IP)) &&
- (skb->len > 64)) {
+ (skb->protocol == htons(ETH_P_IP)) &&
+ (skb->len > 64)) {
skb->csum = cur_p->app3 & 0xFFFF;
skb->ip_summed = CHECKSUM_COMPLETE;
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 1ec65fe..7b0a735 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -26,6 +26,7 @@
#include <linux/netdevice.h>
#include <linux/of_mdio.h>
#include <linux/of_platform.h>
+#include <linux/of_irq.h>
#include <linux/of_address.h>
#include <linux/skbuff.h>
#include <linux/spinlock.h>
@@ -600,7 +601,8 @@
size += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
packets++;
- lp->tx_bd_ci = ++lp->tx_bd_ci % TX_BD_NUM;
+ ++lp->tx_bd_ci;
+ lp->tx_bd_ci %= TX_BD_NUM;
cur_p = &lp->tx_bd_v[lp->tx_bd_ci];
status = cur_p->status;
}
@@ -686,7 +688,8 @@
skb_headlen(skb), DMA_TO_DEVICE);
for (ii = 0; ii < num_frag; ii++) {
- lp->tx_bd_tail = ++lp->tx_bd_tail % TX_BD_NUM;
+ ++lp->tx_bd_tail;
+ lp->tx_bd_tail %= TX_BD_NUM;
cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
frag = &skb_shinfo(skb)->frags[ii];
cur_p->phys = dma_map_single(ndev->dev.parent,
@@ -702,7 +705,8 @@
tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail;
/* Start the transfer */
axienet_dma_out32(lp, XAXIDMA_TX_TDESC_OFFSET, tail_p);
- lp->tx_bd_tail = ++lp->tx_bd_tail % TX_BD_NUM;
+ ++lp->tx_bd_tail;
+ lp->tx_bd_tail %= TX_BD_NUM;
return NETDEV_TX_OK;
}
@@ -752,7 +756,7 @@
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
} else if ((lp->features & XAE_FEATURE_PARTIAL_RX_CSUM) != 0 &&
- skb->protocol == __constant_htons(ETH_P_IP) &&
+ skb->protocol == htons(ETH_P_IP) &&
skb->len > 64) {
skb->csum = be32_to_cpu(cur_p->app3 & 0xFFFF);
skb->ip_summed = CHECKSUM_COMPLETE;
@@ -774,7 +778,8 @@
cur_p->status = 0;
cur_p->sw_id_offset = (u32) new_skb;
- lp->rx_bd_ci = ++lp->rx_bd_ci % RX_BD_NUM;
+ ++lp->rx_bd_ci;
+ lp->rx_bd_ci %= RX_BD_NUM;
cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
}
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 36052b9..0d87c67 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -795,18 +795,6 @@
}
/**
- * xemaclite_mdio_reset - Reset the mdio bus.
- * @bus: Pointer to the MII bus
- *
- * This function is required(?) as per Documentation/networking/phy.txt.
- * There is no reset in this device; this function always returns 0.
- */
-static int xemaclite_mdio_reset(struct mii_bus *bus)
-{
- return 0;
-}
-
-/**
* xemaclite_mdio_setup - Register mii_bus for the Emaclite device
* @lp: Pointer to the Emaclite device private data
* @ofdev: Pointer to OF device structure
@@ -861,7 +849,6 @@
bus->name = "Xilinx Emaclite MDIO";
bus->read = xemaclite_mdio_read;
bus->write = xemaclite_mdio_write;
- bus->reset = xemaclite_mdio_reset;
bus->parent = dev;
bus->irq = lp->mdio_irqs; /* preallocated IRQ table */
@@ -1037,7 +1024,7 @@
skb_tx_timestamp(new_skb);
dev->stats.tx_bytes += len;
- dev_kfree_skb(new_skb);
+ dev_consume_skb_any(new_skb);
return 0;
}
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index 25283f1..f7e0f0f 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -256,10 +256,6 @@
static struct port *npe_port_tab[MAX_NPES];
static struct dma_pool *dma_pool;
-static struct sock_filter ptp_filter[] = {
- PTP_FILTER
-};
-
static int ixp_ptp_match(struct sk_buff *skb, u16 uid_hi, u32 uid_lo, u16 seqid)
{
u8 *data = skb->data;
@@ -267,7 +263,7 @@
u16 *hi, *id;
u32 lo;
- if (sk_run_filter(skb, ptp_filter) != PTP_CLASS_V1_IPV4)
+ if (ptp_classify_raw(skb) != PTP_CLASS_V1_IPV4)
return 0;
offset = ETH_HLEN + IPV4_HLEN(data) + UDP_HLEN;
@@ -1413,11 +1409,6 @@
char phy_id[MII_BUS_ID_SIZE + 3];
int err;
- if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter))) {
- pr_err("ixp4xx_eth: bad ptp filter\n");
- return -EINVAL;
- }
-
if (!(dev = alloc_etherdev(sizeof(struct port))))
return -ENOMEM;
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 61dd244..8190165 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -1184,7 +1184,7 @@
struct yam_mcs *p;
int i;
- del_timer(&yam_timer);
+ del_timer_sync(&yam_timer);
for (i = 0; i < NR_PORTS; i++) {
struct net_device *dev = yam_devs[i];
if (dev) {
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 7b594ce..13010b4 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -30,6 +30,7 @@
/* Fwd declaration */
struct hv_netvsc_packet;
+struct ndis_tcp_ip_checksum_info;
/* Represent the xfer page packet which contains 1 or more netvsc packet */
struct xferpage_packet {
@@ -73,7 +74,7 @@
} completion;
/* This points to the memory after page_buf */
- void *extension;
+ struct rndis_message *rndis_msg;
u32 total_data_buflen;
/* Points to the send/receive buffer where the ethernet frame is */
@@ -117,7 +118,8 @@
void netvsc_linkstatus_callback(struct hv_device *device_obj,
unsigned int status);
int netvsc_recv_callback(struct hv_device *device_obj,
- struct hv_netvsc_packet *packet);
+ struct hv_netvsc_packet *packet,
+ struct ndis_tcp_ip_checksum_info *csum_info);
int rndis_filter_open(struct hv_device *dev);
int rndis_filter_close(struct hv_device *dev);
int rndis_filter_device_add(struct hv_device *dev,
@@ -126,11 +128,6 @@
int rndis_filter_receive(struct hv_device *dev,
struct hv_netvsc_packet *pkt);
-
-
-int rndis_filter_send(struct hv_device *dev,
- struct hv_netvsc_packet *pkt);
-
int rndis_filter_set_packet_filter(struct rndis_device *dev, u32 new_filter);
int rndis_filter_set_device_mac(struct hv_device *hdev, char *mac);
@@ -139,6 +136,8 @@
#define NVSP_PROTOCOL_VERSION_1 2
#define NVSP_PROTOCOL_VERSION_2 0x30002
+#define NVSP_PROTOCOL_VERSION_4 0x40000
+#define NVSP_PROTOCOL_VERSION_5 0x50000
enum {
NVSP_MSG_TYPE_NONE = 0,
@@ -193,6 +192,23 @@
NVSP_MSG2_TYPE_ALLOC_CHIMNEY_HANDLE,
NVSP_MSG2_TYPE_ALLOC_CHIMNEY_HANDLE_COMP,
+
+ NVSP_MSG2_MAX = NVSP_MSG2_TYPE_ALLOC_CHIMNEY_HANDLE_COMP,
+
+ /* Version 4 messages */
+ NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION,
+ NVSP_MSG4_TYPE_SWITCH_DATA_PATH,
+ NVSP_MSG4_TYPE_UPLINK_CONNECT_STATE_DEPRECATED,
+
+ NVSP_MSG4_MAX = NVSP_MSG4_TYPE_UPLINK_CONNECT_STATE_DEPRECATED,
+
+ /* Version 5 messages */
+ NVSP_MSG5_TYPE_OID_QUERY_EX,
+ NVSP_MSG5_TYPE_OID_QUERY_EX_COMP,
+ NVSP_MSG5_TYPE_SUBCHANNEL,
+ NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE,
+
+ NVSP_MSG5_MAX = NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE,
};
enum {
@@ -447,10 +463,44 @@
struct nvsp_2_free_rxbuf free_rxbuf;
} __packed;
+enum nvsp_subchannel_operation {
+ NVSP_SUBCHANNEL_NONE = 0,
+ NVSP_SUBCHANNEL_ALLOCATE,
+ NVSP_SUBCHANNEL_MAX
+};
+
+struct nvsp_5_subchannel_request {
+ u32 op;
+ u32 num_subchannels;
+} __packed;
+
+struct nvsp_5_subchannel_complete {
+ u32 status;
+ u32 num_subchannels; /* Actual number of subchannels allocated */
+} __packed;
+
+struct nvsp_5_send_indirect_table {
+ /* The number of entries in the send indirection table */
+ u32 count;
+
+ /* The offset of the send indireciton table from top of this struct.
+ * The send indirection table tells which channel to put the send
+ * traffic on. Each entry is a channel number.
+ */
+ u32 offset;
+} __packed;
+
+union nvsp_5_message_uber {
+ struct nvsp_5_subchannel_request subchn_req;
+ struct nvsp_5_subchannel_complete subchn_comp;
+ struct nvsp_5_send_indirect_table send_table;
+} __packed;
+
union nvsp_all_messages {
union nvsp_message_init_uber init_msg;
union nvsp_1_message_uber v1_msg;
union nvsp_2_message_uber v2_msg;
+ union nvsp_5_message_uber v5_msg;
} __packed;
/* ALL Messages */
@@ -463,6 +513,7 @@
#define NETVSC_MTU 65536
#define NETVSC_RECEIVE_BUFFER_SIZE (1024*1024*16) /* 16MB */
+#define NETVSC_RECEIVE_BUFFER_SIZE_LEGACY (1024*1024*15) /* 15MB */
#define NETVSC_RECEIVE_BUFFER_ID 0xcafe
@@ -506,6 +557,8 @@
/* Holds rndis device info */
void *extension;
+ /* The recive buffer for this device */
+ unsigned char cb_buffer[NETVSC_PACKET_SIZE];
};
/* NdisInitialize message */
@@ -671,9 +724,133 @@
};
};
+struct ndis_oject_header {
+ u8 type;
+ u8 revision;
+ u16 size;
+};
+
+#define NDIS_OBJECT_TYPE_DEFAULT 0x80
+#define NDIS_OFFLOAD_PARAMETERS_REVISION_3 3
+#define NDIS_OFFLOAD_PARAMETERS_NO_CHANGE 0
+#define NDIS_OFFLOAD_PARAMETERS_LSOV2_DISABLED 1
+#define NDIS_OFFLOAD_PARAMETERS_LSOV2_ENABLED 2
+#define NDIS_OFFLOAD_PARAMETERS_LSOV1_ENABLED 2
+#define NDIS_OFFLOAD_PARAMETERS_RSC_DISABLED 1
+#define NDIS_OFFLOAD_PARAMETERS_RSC_ENABLED 2
+#define NDIS_OFFLOAD_PARAMETERS_TX_RX_DISABLED 1
+#define NDIS_OFFLOAD_PARAMETERS_TX_ENABLED_RX_DISABLED 2
+#define NDIS_OFFLOAD_PARAMETERS_RX_ENABLED_TX_DISABLED 3
+#define NDIS_OFFLOAD_PARAMETERS_TX_RX_ENABLED 4
+
+#define NDIS_TCP_LARGE_SEND_OFFLOAD_V2_TYPE 1
+#define NDIS_TCP_LARGE_SEND_OFFLOAD_IPV4 0
+#define NDIS_TCP_LARGE_SEND_OFFLOAD_IPV6 1
+
+/*
+ * New offload OIDs for NDIS 6
+ */
+#define OID_TCP_OFFLOAD_CURRENT_CONFIG 0xFC01020B /* query only */
+#define OID_TCP_OFFLOAD_PARAMETERS 0xFC01020C /* set only */
+#define OID_TCP_OFFLOAD_HARDWARE_CAPABILITIES 0xFC01020D/* query only */
+#define OID_TCP_CONNECTION_OFFLOAD_CURRENT_CONFIG 0xFC01020E /* query only */
+#define OID_TCP_CONNECTION_OFFLOAD_HARDWARE_CAPABILITIES 0xFC01020F /* query */
+#define OID_OFFLOAD_ENCAPSULATION 0x0101010A /* set/query */
+
+struct ndis_offload_params {
+ struct ndis_oject_header header;
+ u8 ip_v4_csum;
+ u8 tcp_ip_v4_csum;
+ u8 udp_ip_v4_csum;
+ u8 tcp_ip_v6_csum;
+ u8 udp_ip_v6_csum;
+ u8 lso_v1;
+ u8 ip_sec_v1;
+ u8 lso_v2_ipv4;
+ u8 lso_v2_ipv6;
+ u8 tcp_connection_ip_v4;
+ u8 tcp_connection_ip_v6;
+ u32 flags;
+ u8 ip_sec_v2;
+ u8 ip_sec_v2_ip_v4;
+ struct {
+ u8 rsc_ip_v4;
+ u8 rsc_ip_v6;
+ };
+ struct {
+ u8 encapsulated_packet_task_offload;
+ u8 encapsulation_types;
+ };
+};
+
+struct ndis_tcp_ip_checksum_info {
+ union {
+ struct {
+ u32 is_ipv4:1;
+ u32 is_ipv6:1;
+ u32 tcp_checksum:1;
+ u32 udp_checksum:1;
+ u32 ip_header_checksum:1;
+ u32 reserved:11;
+ u32 tcp_header_offset:10;
+ } transmit;
+ struct {
+ u32 tcp_checksum_failed:1;
+ u32 udp_checksum_failed:1;
+ u32 ip_checksum_failed:1;
+ u32 tcp_checksum_succeeded:1;
+ u32 udp_checksum_succeeded:1;
+ u32 ip_checksum_succeeded:1;
+ u32 loopback:1;
+ u32 tcp_checksum_value_invalid:1;
+ u32 ip_checksum_value_invalid:1;
+ } receive;
+ u32 value;
+ };
+};
+
+struct ndis_tcp_lso_info {
+ union {
+ struct {
+ u32 unused:30;
+ u32 type:1;
+ u32 reserved2:1;
+ } transmit;
+ struct {
+ u32 mss:20;
+ u32 tcp_header_offset:10;
+ u32 type:1;
+ u32 reserved2:1;
+ } lso_v1_transmit;
+ struct {
+ u32 tcp_payload:30;
+ u32 type:1;
+ u32 reserved2:1;
+ } lso_v1_transmit_complete;
+ struct {
+ u32 mss:20;
+ u32 tcp_header_offset:10;
+ u32 type:1;
+ u32 ip_version:1;
+ } lso_v2_transmit;
+ struct {
+ u32 reserved:30;
+ u32 type:1;
+ u32 reserved2:1;
+ } lso_v2_transmit_complete;
+ u32 value;
+ };
+};
+
#define NDIS_VLAN_PPI_SIZE (sizeof(struct rndis_per_packet_info) + \
sizeof(struct ndis_pkt_8021q_info))
+#define NDIS_CSUM_PPI_SIZE (sizeof(struct rndis_per_packet_info) + \
+ sizeof(struct ndis_tcp_ip_checksum_info))
+
+#define NDIS_LSO_PPI_SIZE (sizeof(struct rndis_per_packet_info) + \
+ sizeof(struct ndis_tcp_lso_info))
+
/* Format of Information buffer passed in a SetRequest for the OID */
/* OID_GEN_RNDIS_CONFIG_PARAMETER. */
struct rndis_config_parameter_info {
@@ -846,12 +1023,6 @@
};
-struct rndis_filter_packet {
- void *completion_ctx;
- void (*completion)(void *context);
- struct rndis_message msg;
-};
-
/* Handy macros */
/* get the size of an RNDIS message. Pass in the message type, */
@@ -905,6 +1076,16 @@
#define NDIS_PACKET_TYPE_FUNCTIONAL 0x00000400
#define NDIS_PACKET_TYPE_MAC_FRAME 0x00000800
+#define INFO_IPV4 2
+#define INFO_IPV6 4
+#define INFO_TCP 2
+#define INFO_UDP 4
+
+#define TRANSPORT_INFO_NOT_IP 0
+#define TRANSPORT_INFO_IPV4_TCP ((INFO_IPV4 << 16) | INFO_TCP)
+#define TRANSPORT_INFO_IPV4_UDP ((INFO_IPV4 << 16) | INFO_UDP)
+#define TRANSPORT_INFO_IPV6_TCP ((INFO_IPV6 << 16) | INFO_TCP)
+#define TRANSPORT_INFO_IPV6_UDP ((INFO_IPV6 << 16) | INFO_UDP)
#endif /* _HYPERV_NET_H */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 03a2c6e..daddea2 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -290,7 +290,7 @@
NVSP_STAT_SUCCESS)
return -EINVAL;
- if (nvsp_ver != NVSP_PROTOCOL_VERSION_2)
+ if (nvsp_ver == NVSP_PROTOCOL_VERSION_1)
return 0;
/* NVSPv2 only: Send NDIS config */
@@ -314,6 +314,9 @@
struct nvsp_message *init_packet;
int ndis_version;
struct net_device *ndev;
+ u32 ver_list[] = { NVSP_PROTOCOL_VERSION_1, NVSP_PROTOCOL_VERSION_2,
+ NVSP_PROTOCOL_VERSION_4, NVSP_PROTOCOL_VERSION_5 };
+ int i, num_ver = 4; /* number of different NVSP versions */
net_device = get_outbound_net_device(device);
if (!net_device)
@@ -323,13 +326,14 @@
init_packet = &net_device->channel_init_pkt;
/* Negotiate the latest NVSP protocol supported */
- if (negotiate_nvsp_ver(device, net_device, init_packet,
- NVSP_PROTOCOL_VERSION_2) == 0) {
- net_device->nvsp_version = NVSP_PROTOCOL_VERSION_2;
- } else if (negotiate_nvsp_ver(device, net_device, init_packet,
- NVSP_PROTOCOL_VERSION_1) == 0) {
- net_device->nvsp_version = NVSP_PROTOCOL_VERSION_1;
- } else {
+ for (i = num_ver - 1; i >= 0; i--)
+ if (negotiate_nvsp_ver(device, net_device, init_packet,
+ ver_list[i]) == 0) {
+ net_device->nvsp_version = ver_list[i];
+ break;
+ }
+
+ if (i < 0) {
ret = -EPROTO;
goto cleanup;
}
@@ -339,7 +343,10 @@
/* Send the ndis version */
memset(init_packet, 0, sizeof(struct nvsp_message));
- ndis_version = 0x00050001;
+ if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_4)
+ ndis_version = 0x00050001;
+ else
+ ndis_version = 0x0006001e;
init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_NDIS_VER;
init_packet->msg.v1_msg.
@@ -358,6 +365,11 @@
goto cleanup;
/* Post the big receive buffer to NetVSP */
+ if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_2)
+ net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE_LEGACY;
+ else
+ net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE;
+
ret = netvsc_init_recv_buf(device);
cleanup:
@@ -432,17 +444,14 @@
return avail_write * 100 / ring_info->ring_datasize;
}
-static void netvsc_send_completion(struct hv_device *device,
+static void netvsc_send_completion(struct netvsc_device *net_device,
+ struct hv_device *device,
struct vmpacket_descriptor *packet)
{
- struct netvsc_device *net_device;
struct nvsp_message *nvsp_packet;
struct hv_netvsc_packet *nvsc_packet;
struct net_device *ndev;
- net_device = get_inbound_net_device(device);
- if (!net_device)
- return;
ndev = net_device->ndev;
nvsp_packet = (struct nvsp_message *)((unsigned long)packet +
@@ -561,13 +570,13 @@
}
static void netvsc_send_recv_completion(struct hv_device *device,
+ struct netvsc_device *net_device,
u64 transaction_id, u32 status)
{
struct nvsp_message recvcompMessage;
int retries = 0;
int ret;
struct net_device *ndev;
- struct netvsc_device *net_device = hv_get_drvdata(device);
ndev = net_device->ndev;
@@ -653,14 +662,15 @@
/* Send a receive completion for the xfer page packet */
if (fsend_receive_comp)
- netvsc_send_recv_completion(device, transaction_id, status);
+ netvsc_send_recv_completion(device, net_device, transaction_id,
+ status);
}
-static void netvsc_receive(struct hv_device *device,
- struct vmpacket_descriptor *packet)
+static void netvsc_receive(struct netvsc_device *net_device,
+ struct hv_device *device,
+ struct vmpacket_descriptor *packet)
{
- struct netvsc_device *net_device;
struct vmtransfer_page_packet_header *vmxferpage_packet;
struct nvsp_message *nvsp_packet;
struct hv_netvsc_packet *netvsc_packet = NULL;
@@ -673,9 +683,6 @@
LIST_HEAD(listHead);
- net_device = get_inbound_net_device(device);
- if (!net_device)
- return;
ndev = net_device->ndev;
/*
@@ -741,7 +748,7 @@
spin_unlock_irqrestore(&net_device->recv_pkt_list_lock,
flags);
- netvsc_send_recv_completion(device,
+ netvsc_send_recv_completion(device, net_device,
vmxferpage_packet->d.trans_id,
NVSP_STAT_FAIL);
@@ -800,22 +807,16 @@
struct netvsc_device *net_device;
u32 bytes_recvd;
u64 request_id;
- unsigned char *packet;
struct vmpacket_descriptor *desc;
unsigned char *buffer;
int bufferlen = NETVSC_PACKET_SIZE;
struct net_device *ndev;
- packet = kzalloc(NETVSC_PACKET_SIZE * sizeof(unsigned char),
- GFP_ATOMIC);
- if (!packet)
- return;
- buffer = packet;
-
net_device = get_inbound_net_device(device);
if (!net_device)
- goto out;
+ return;
ndev = net_device->ndev;
+ buffer = net_device->cb_buffer;
do {
ret = vmbus_recvpacket_raw(device->channel, buffer, bufferlen,
@@ -825,11 +826,13 @@
desc = (struct vmpacket_descriptor *)buffer;
switch (desc->type) {
case VM_PKT_COMP:
- netvsc_send_completion(device, desc);
+ netvsc_send_completion(net_device,
+ device, desc);
break;
case VM_PKT_DATA_USING_XFER_PAGES:
- netvsc_receive(device, desc);
+ netvsc_receive(net_device,
+ device, desc);
break;
default:
@@ -841,23 +844,16 @@
break;
}
- /* reset */
- if (bufferlen > NETVSC_PACKET_SIZE) {
- kfree(buffer);
- buffer = packet;
- bufferlen = NETVSC_PACKET_SIZE;
- }
} else {
- /* reset */
- if (bufferlen > NETVSC_PACKET_SIZE) {
- kfree(buffer);
- buffer = packet;
- bufferlen = NETVSC_PACKET_SIZE;
- }
-
+ /*
+ * We are done for this pass.
+ */
break;
}
+
} else if (ret == -ENOBUFS) {
+ if (bufferlen > NETVSC_PACKET_SIZE)
+ kfree(buffer);
/* Handle large packet */
buffer = kmalloc(bytes_recvd, GFP_ATOMIC);
if (buffer == NULL) {
@@ -872,8 +868,8 @@
}
} while (1);
-out:
- kfree(buffer);
+ if (bufferlen > NETVSC_PACKET_SIZE)
+ kfree(buffer);
return;
}
@@ -907,7 +903,6 @@
ndev = net_device->ndev;
/* Initialize the NetVSC channel extension */
- net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE;
spin_lock_init(&net_device->recv_pkt_list_lock);
INIT_LIST_HEAD(&net_device->recv_pkt_list);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 7756118..4e4cf9e 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -88,8 +88,12 @@
{
struct net_device_context *net_device_ctx = netdev_priv(net);
struct hv_device *device_obj = net_device_ctx->device_ctx;
+ struct netvsc_device *nvdev;
+ struct rndis_device *rdev;
int ret = 0;
+ netif_carrier_off(net);
+
/* Open up the device */
ret = rndis_filter_open(device_obj);
if (ret != 0) {
@@ -99,6 +103,11 @@
netif_start_queue(net);
+ nvdev = hv_get_drvdata(device_obj);
+ rdev = nvdev->extension;
+ if (!rdev->link_state)
+ netif_carrier_on(net);
+
return ret;
}
@@ -119,6 +128,27 @@
return ret;
}
+static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size,
+ int pkt_type)
+{
+ struct rndis_packet *rndis_pkt;
+ struct rndis_per_packet_info *ppi;
+
+ rndis_pkt = &msg->msg.pkt;
+ rndis_pkt->data_offset += ppi_size;
+
+ ppi = (struct rndis_per_packet_info *)((void *)rndis_pkt +
+ rndis_pkt->per_pkt_info_offset + rndis_pkt->per_pkt_info_len);
+
+ ppi->size = ppi_size;
+ ppi->type = pkt_type;
+ ppi->ppi_offset = sizeof(struct rndis_per_packet_info);
+
+ rndis_pkt->per_pkt_info_len += ppi_size;
+
+ return ppi;
+}
+
static void netvsc_xmit_completion(void *context)
{
struct hv_netvsc_packet *packet = (struct hv_netvsc_packet *)context;
@@ -131,22 +161,164 @@
dev_kfree_skb_any(skb);
}
+static u32 fill_pg_buf(struct page *page, u32 offset, u32 len,
+ struct hv_page_buffer *pb)
+{
+ int j = 0;
+
+ /* Deal with compund pages by ignoring unused part
+ * of the page.
+ */
+ page += (offset >> PAGE_SHIFT);
+ offset &= ~PAGE_MASK;
+
+ while (len > 0) {
+ unsigned long bytes;
+
+ bytes = PAGE_SIZE - offset;
+ if (bytes > len)
+ bytes = len;
+ pb[j].pfn = page_to_pfn(page);
+ pb[j].offset = offset;
+ pb[j].len = bytes;
+
+ offset += bytes;
+ len -= bytes;
+
+ if (offset == PAGE_SIZE && len) {
+ page++;
+ offset = 0;
+ j++;
+ }
+ }
+
+ return j + 1;
+}
+
+static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
+ struct hv_page_buffer *pb)
+{
+ u32 slots_used = 0;
+ char *data = skb->data;
+ int frags = skb_shinfo(skb)->nr_frags;
+ int i;
+
+ /* The packet is laid out thus:
+ * 1. hdr
+ * 2. skb linear data
+ * 3. skb fragment data
+ */
+ if (hdr != NULL)
+ slots_used += fill_pg_buf(virt_to_page(hdr),
+ offset_in_page(hdr),
+ len, &pb[slots_used]);
+
+ slots_used += fill_pg_buf(virt_to_page(data),
+ offset_in_page(data),
+ skb_headlen(skb), &pb[slots_used]);
+
+ for (i = 0; i < frags; i++) {
+ skb_frag_t *frag = skb_shinfo(skb)->frags + i;
+
+ slots_used += fill_pg_buf(skb_frag_page(frag),
+ frag->page_offset,
+ skb_frag_size(frag), &pb[slots_used]);
+ }
+ return slots_used;
+}
+
+static int count_skb_frag_slots(struct sk_buff *skb)
+{
+ int i, frags = skb_shinfo(skb)->nr_frags;
+ int pages = 0;
+
+ for (i = 0; i < frags; i++) {
+ skb_frag_t *frag = skb_shinfo(skb)->frags + i;
+ unsigned long size = skb_frag_size(frag);
+ unsigned long offset = frag->page_offset;
+
+ /* Skip unused frames from start of page */
+ offset &= ~PAGE_MASK;
+ pages += PFN_UP(offset + size);
+ }
+ return pages;
+}
+
+static int netvsc_get_slots(struct sk_buff *skb)
+{
+ char *data = skb->data;
+ unsigned int offset = offset_in_page(data);
+ unsigned int len = skb_headlen(skb);
+ int slots;
+ int frag_slots;
+
+ slots = DIV_ROUND_UP(offset + len, PAGE_SIZE);
+ frag_slots = count_skb_frag_slots(skb);
+ return slots + frag_slots;
+}
+
+static u32 get_net_transport_info(struct sk_buff *skb, u32 *trans_off)
+{
+ u32 ret_val = TRANSPORT_INFO_NOT_IP;
+
+ if ((eth_hdr(skb)->h_proto != htons(ETH_P_IP)) &&
+ (eth_hdr(skb)->h_proto != htons(ETH_P_IPV6))) {
+ goto not_ip;
+ }
+
+ *trans_off = skb_transport_offset(skb);
+
+ if ((eth_hdr(skb)->h_proto == htons(ETH_P_IP))) {
+ struct iphdr *iphdr = ip_hdr(skb);
+
+ if (iphdr->protocol == IPPROTO_TCP)
+ ret_val = TRANSPORT_INFO_IPV4_TCP;
+ else if (iphdr->protocol == IPPROTO_UDP)
+ ret_val = TRANSPORT_INFO_IPV4_UDP;
+ } else {
+ if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
+ ret_val = TRANSPORT_INFO_IPV6_TCP;
+ else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)
+ ret_val = TRANSPORT_INFO_IPV6_UDP;
+ }
+
+not_ip:
+ return ret_val;
+}
+
static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
struct hv_netvsc_packet *packet;
int ret;
- unsigned int i, num_pages, npg_data;
+ unsigned int num_data_pgs;
+ struct rndis_message *rndis_msg;
+ struct rndis_packet *rndis_pkt;
+ u32 rndis_msg_size;
+ bool isvlan;
+ struct rndis_per_packet_info *ppi;
+ struct ndis_tcp_ip_checksum_info *csum_info;
+ struct ndis_tcp_lso_info *lso_info;
+ int hdr_offset;
+ u32 net_trans_info;
- /* Add multipages for skb->data and additional 2 for RNDIS */
- npg_data = (((unsigned long)skb->data + skb_headlen(skb) - 1)
- >> PAGE_SHIFT) - ((unsigned long)skb->data >> PAGE_SHIFT) + 1;
- num_pages = skb_shinfo(skb)->nr_frags + npg_data + 2;
+
+ /* We will atmost need two pages to describe the rndis
+ * header. We can only transmit MAX_PAGE_BUFFER_COUNT number
+ * of pages in a single packet.
+ */
+ num_data_pgs = netvsc_get_slots(skb) + 2;
+ if (num_data_pgs > MAX_PAGE_BUFFER_COUNT) {
+ netdev_err(net, "Packet too big: %u\n", skb->len);
+ dev_kfree_skb(skb);
+ net->stats.tx_dropped++;
+ return NETDEV_TX_OK;
+ }
/* Allocate a netvsc packet based on # of frags. */
packet = kzalloc(sizeof(struct hv_netvsc_packet) +
- (num_pages * sizeof(struct hv_page_buffer)) +
- sizeof(struct rndis_filter_packet) +
+ (num_data_pgs * sizeof(struct hv_page_buffer)) +
+ sizeof(struct rndis_message) +
NDIS_VLAN_PPI_SIZE, GFP_ATOMIC);
if (!packet) {
/* out of memory, drop packet */
@@ -159,53 +331,111 @@
packet->vlan_tci = skb->vlan_tci;
- packet->extension = (void *)(unsigned long)packet +
- sizeof(struct hv_netvsc_packet) +
- (num_pages * sizeof(struct hv_page_buffer));
-
- /* If the rndis msg goes beyond 1 page, we will add 1 later */
- packet->page_buf_cnt = num_pages - 1;
-
- /* Initialize it from the skb */
+ packet->is_data_pkt = true;
packet->total_data_buflen = skb->len;
- /* Start filling in the page buffers starting after RNDIS buffer. */
- packet->page_buf[1].pfn = virt_to_phys(skb->data) >> PAGE_SHIFT;
- packet->page_buf[1].offset
- = (unsigned long)skb->data & (PAGE_SIZE - 1);
- if (npg_data == 1)
- packet->page_buf[1].len = skb_headlen(skb);
- else
- packet->page_buf[1].len = PAGE_SIZE
- - packet->page_buf[1].offset;
-
- for (i = 2; i <= npg_data; i++) {
- packet->page_buf[i].pfn = virt_to_phys(skb->data
- + PAGE_SIZE * (i-1)) >> PAGE_SHIFT;
- packet->page_buf[i].offset = 0;
- packet->page_buf[i].len = PAGE_SIZE;
- }
- if (npg_data > 1)
- packet->page_buf[npg_data].len = (((unsigned long)skb->data
- + skb_headlen(skb) - 1) & (PAGE_SIZE - 1)) + 1;
-
- /* Additional fragments are after SKB data */
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- const skb_frag_t *f = &skb_shinfo(skb)->frags[i];
-
- packet->page_buf[i+npg_data+1].pfn =
- page_to_pfn(skb_frag_page(f));
- packet->page_buf[i+npg_data+1].offset = f->page_offset;
- packet->page_buf[i+npg_data+1].len = skb_frag_size(f);
- }
+ packet->rndis_msg = (struct rndis_message *)((unsigned long)packet +
+ sizeof(struct hv_netvsc_packet) +
+ (num_data_pgs * sizeof(struct hv_page_buffer)));
/* Set the completion routine */
packet->completion.send.send_completion = netvsc_xmit_completion;
packet->completion.send.send_completion_ctx = packet;
packet->completion.send.send_completion_tid = (unsigned long)skb;
- ret = rndis_filter_send(net_device_ctx->device_ctx,
- packet);
+ isvlan = packet->vlan_tci & VLAN_TAG_PRESENT;
+
+ /* Add the rndis header */
+ rndis_msg = packet->rndis_msg;
+ rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET;
+ rndis_msg->msg_len = packet->total_data_buflen;
+ rndis_pkt = &rndis_msg->msg.pkt;
+ rndis_pkt->data_offset = sizeof(struct rndis_packet);
+ rndis_pkt->data_len = packet->total_data_buflen;
+ rndis_pkt->per_pkt_info_offset = sizeof(struct rndis_packet);
+
+ rndis_msg_size = RNDIS_MESSAGE_SIZE(struct rndis_packet);
+
+ if (isvlan) {
+ struct ndis_pkt_8021q_info *vlan;
+
+ rndis_msg_size += NDIS_VLAN_PPI_SIZE;
+ ppi = init_ppi_data(rndis_msg, NDIS_VLAN_PPI_SIZE,
+ IEEE_8021Q_INFO);
+ vlan = (struct ndis_pkt_8021q_info *)((void *)ppi +
+ ppi->ppi_offset);
+ vlan->vlanid = packet->vlan_tci & VLAN_VID_MASK;
+ vlan->pri = (packet->vlan_tci & VLAN_PRIO_MASK) >>
+ VLAN_PRIO_SHIFT;
+ }
+
+ net_trans_info = get_net_transport_info(skb, &hdr_offset);
+ if (net_trans_info == TRANSPORT_INFO_NOT_IP)
+ goto do_send;
+
+ /*
+ * Setup the sendside checksum offload only if this is not a
+ * GSO packet.
+ */
+ if (skb_is_gso(skb))
+ goto do_lso;
+
+ rndis_msg_size += NDIS_CSUM_PPI_SIZE;
+ ppi = init_ppi_data(rndis_msg, NDIS_CSUM_PPI_SIZE,
+ TCPIP_CHKSUM_PKTINFO);
+
+ csum_info = (struct ndis_tcp_ip_checksum_info *)((void *)ppi +
+ ppi->ppi_offset);
+
+ if (net_trans_info & (INFO_IPV4 << 16))
+ csum_info->transmit.is_ipv4 = 1;
+ else
+ csum_info->transmit.is_ipv6 = 1;
+
+ if (net_trans_info & INFO_TCP) {
+ csum_info->transmit.tcp_checksum = 1;
+ csum_info->transmit.tcp_header_offset = hdr_offset;
+ } else if (net_trans_info & INFO_UDP) {
+ csum_info->transmit.udp_checksum = 1;
+ }
+ goto do_send;
+
+do_lso:
+ rndis_msg_size += NDIS_LSO_PPI_SIZE;
+ ppi = init_ppi_data(rndis_msg, NDIS_LSO_PPI_SIZE,
+ TCP_LARGESEND_PKTINFO);
+
+ lso_info = (struct ndis_tcp_lso_info *)((void *)ppi +
+ ppi->ppi_offset);
+
+ lso_info->lso_v2_transmit.type = NDIS_TCP_LARGE_SEND_OFFLOAD_V2_TYPE;
+ if (net_trans_info & (INFO_IPV4 << 16)) {
+ lso_info->lso_v2_transmit.ip_version =
+ NDIS_TCP_LARGE_SEND_OFFLOAD_IPV4;
+ ip_hdr(skb)->tot_len = 0;
+ ip_hdr(skb)->check = 0;
+ tcp_hdr(skb)->check =
+ ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr, 0, IPPROTO_TCP, 0);
+ } else {
+ lso_info->lso_v2_transmit.ip_version =
+ NDIS_TCP_LARGE_SEND_OFFLOAD_IPV6;
+ ipv6_hdr(skb)->payload_len = 0;
+ tcp_hdr(skb)->check =
+ ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0);
+ }
+ lso_info->lso_v2_transmit.tcp_header_offset = hdr_offset;
+ lso_info->lso_v2_transmit.mss = skb_shinfo(skb)->gso_size;
+
+do_send:
+ /* Start filling in the page buffers with the rndis hdr */
+ rndis_msg->msg_len += rndis_msg_size;
+ packet->page_buf_cnt = init_page_array(rndis_msg, rndis_msg_size,
+ skb, &packet->page_buf[0]);
+
+ ret = netvsc_send(net_device_ctx->device_ctx, packet);
+
if (ret == 0) {
net->stats.tx_bytes += skb->len;
net->stats.tx_packets++;
@@ -229,23 +459,24 @@
struct net_device *net;
struct net_device_context *ndev_ctx;
struct netvsc_device *net_device;
+ struct rndis_device *rdev;
net_device = hv_get_drvdata(device_obj);
+ rdev = net_device->extension;
+
+ rdev->link_state = status != 1;
+
net = net_device->ndev;
- if (!net) {
- netdev_err(net, "got link status but net device "
- "not initialized yet\n");
+ if (!net || net->reg_state != NETREG_REGISTERED)
return;
- }
+ ndev_ctx = netdev_priv(net);
if (status == 1) {
- netif_carrier_on(net);
- ndev_ctx = netdev_priv(net);
schedule_delayed_work(&ndev_ctx->dwork, 0);
schedule_delayed_work(&ndev_ctx->dwork, msecs_to_jiffies(20));
} else {
- netif_carrier_off(net);
+ schedule_delayed_work(&ndev_ctx->dwork, 0);
}
}
@@ -254,7 +485,8 @@
* "wire" on the specified device.
*/
int netvsc_recv_callback(struct hv_device *device_obj,
- struct hv_netvsc_packet *packet)
+ struct hv_netvsc_packet *packet,
+ struct ndis_tcp_ip_checksum_info *csum_info)
{
struct net_device *net;
struct sk_buff *skb;
@@ -281,7 +513,17 @@
packet->total_data_buflen);
skb->protocol = eth_type_trans(skb, net);
- skb->ip_summed = CHECKSUM_NONE;
+ if (csum_info) {
+ /* We only look at the IP checksum here.
+ * Should we be dropping the packet if checksum
+ * failed? How do we deal with other checksums - TCP/UDP?
+ */
+ if (csum_info->receive.ip_checksum_succeeded)
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ else
+ skb->ip_summed = CHECKSUM_NONE;
+ }
+
if (packet->vlan_tci & VLAN_TAG_PRESENT)
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
packet->vlan_tci);
@@ -317,7 +559,7 @@
if (nvdev == NULL || nvdev->destroy)
return -ENODEV;
- if (nvdev->nvsp_version == NVSP_PROTOCOL_VERSION_2)
+ if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
limit = NETVSC_MTU;
if (mtu < 68 || mtu > limit)
@@ -388,17 +630,35 @@
* current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, add
* another netif_notify_peers() into a delayed work, otherwise GARP packet
* will not be sent after quick migration, and cause network disconnection.
+ * Also, we update the carrier status here.
*/
-static void netvsc_send_garp(struct work_struct *w)
+static void netvsc_link_change(struct work_struct *w)
{
struct net_device_context *ndev_ctx;
struct net_device *net;
struct netvsc_device *net_device;
+ struct rndis_device *rdev;
+ bool notify;
+
+ rtnl_lock();
ndev_ctx = container_of(w, struct net_device_context, dwork.work);
net_device = hv_get_drvdata(ndev_ctx->device_ctx);
+ rdev = net_device->extension;
net = net_device->ndev;
- netdev_notify_peers(net);
+
+ if (rdev->link_state) {
+ netif_carrier_off(net);
+ notify = false;
+ } else {
+ netif_carrier_on(net);
+ notify = true;
+ }
+
+ rtnl_unlock();
+
+ if (notify)
+ netdev_notify_peers(net);
}
@@ -414,20 +674,20 @@
if (!net)
return -ENOMEM;
- /* Set initial state */
netif_carrier_off(net);
net_device_ctx = netdev_priv(net);
net_device_ctx->device_ctx = dev;
hv_set_drvdata(dev, net);
- INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_send_garp);
+ INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
INIT_WORK(&net_device_ctx->work, do_set_multicast);
net->netdev_ops = &device_ops;
- /* TODO: Add GSO and Checksum offload */
- net->hw_features = 0;
- net->features = NETIF_F_HW_VLAN_CTAG_TX;
+ net->hw_features = NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_IP_CSUM |
+ NETIF_F_TSO;
+ net->features = NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_SG | NETIF_F_RXCSUM |
+ NETIF_F_IP_CSUM | NETIF_F_TSO;
SET_ETHTOOL_OPS(net, ðtool_ops);
SET_NETDEV_DEV(net, &dev->device);
@@ -443,13 +703,13 @@
}
memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
- netif_carrier_on(net);
-
ret = register_netdev(net);
if (ret != 0) {
pr_err("Unable to register netdev.\n");
rndis_filter_device_remove(dev);
free_netdev(net);
+ } else {
+ schedule_delayed_work(&net_device_ctx->dwork, 0);
}
return ret;
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 1084e5d..4a37e3d 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -58,9 +58,6 @@
u8 request_ext[RNDIS_EXT_LEN];
};
-static void rndis_filter_send_completion(void *ctx);
-
-
static struct rndis_device *get_rndis_device(void)
{
struct rndis_device *device;
@@ -243,6 +240,22 @@
return ret;
}
+static void rndis_set_link_state(struct rndis_device *rdev,
+ struct rndis_request *request)
+{
+ u32 link_status;
+ struct rndis_query_complete *query_complete;
+
+ query_complete = &request->response_msg.msg.query_complete;
+
+ if (query_complete->status == RNDIS_STATUS_SUCCESS &&
+ query_complete->info_buflen == sizeof(u32)) {
+ memcpy(&link_status, (void *)((unsigned long)query_complete +
+ query_complete->info_buf_offset), sizeof(u32));
+ rdev->link_state = link_status != 0;
+ }
+}
+
static void rndis_filter_receive_response(struct rndis_device *dev,
struct rndis_message *resp)
{
@@ -272,12 +285,16 @@
sizeof(struct rndis_message) + RNDIS_EXT_LEN) {
memcpy(&request->response_msg, resp,
resp->msg_len);
+ if (request->request_msg.ndis_msg_type ==
+ RNDIS_MSG_QUERY && request->request_msg.msg.
+ query_req.oid == RNDIS_OID_GEN_MEDIA_CONNECT_STATUS)
+ rndis_set_link_state(dev, request);
} else {
netdev_err(ndev,
"rndis response buffer overflow "
"detected (size %u max %zu)\n",
resp->msg_len,
- sizeof(struct rndis_filter_packet));
+ sizeof(struct rndis_message));
if (resp->ndis_msg_type ==
RNDIS_MSG_RESET_C) {
@@ -353,6 +370,7 @@
struct rndis_packet *rndis_pkt;
u32 data_offset;
struct ndis_pkt_8021q_info *vlan;
+ struct ndis_tcp_ip_checksum_info *csum_info;
rndis_pkt = &msg->msg.pkt;
@@ -391,7 +409,8 @@
pkt->vlan_tci = 0;
}
- netvsc_recv_callback(dev->net_dev->dev, pkt);
+ csum_info = rndis_get_ppi(rndis_pkt, TCPIP_CHKSUM_PKTINFO);
+ netvsc_recv_callback(dev->net_dev->dev, pkt, csum_info);
}
int rndis_filter_receive(struct hv_device *dev,
@@ -610,6 +629,61 @@
return ret;
}
+int rndis_filter_set_offload_params(struct hv_device *hdev,
+ struct ndis_offload_params *req_offloads)
+{
+ struct netvsc_device *nvdev = hv_get_drvdata(hdev);
+ struct rndis_device *rdev = nvdev->extension;
+ struct net_device *ndev = nvdev->ndev;
+ struct rndis_request *request;
+ struct rndis_set_request *set;
+ struct ndis_offload_params *offload_params;
+ struct rndis_set_complete *set_complete;
+ u32 extlen = sizeof(struct ndis_offload_params);
+ int ret, t;
+
+ request = get_rndis_request(rdev, RNDIS_MSG_SET,
+ RNDIS_MESSAGE_SIZE(struct rndis_set_request) + extlen);
+ if (!request)
+ return -ENOMEM;
+
+ set = &request->request_msg.msg.set_req;
+ set->oid = OID_TCP_OFFLOAD_PARAMETERS;
+ set->info_buflen = extlen;
+ set->info_buf_offset = sizeof(struct rndis_set_request);
+ set->dev_vc_handle = 0;
+
+ offload_params = (struct ndis_offload_params *)((ulong)set +
+ set->info_buf_offset);
+ *offload_params = *req_offloads;
+ offload_params->header.type = NDIS_OBJECT_TYPE_DEFAULT;
+ offload_params->header.revision = NDIS_OFFLOAD_PARAMETERS_REVISION_3;
+ offload_params->header.size = extlen;
+
+ ret = rndis_filter_send_request(rdev, request);
+ if (ret != 0)
+ goto cleanup;
+
+ t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+ if (t == 0) {
+ netdev_err(ndev, "timeout before we got aOFFLOAD set response...\n");
+ /* can't put_rndis_request, since we may still receive a
+ * send-completion.
+ */
+ return -EBUSY;
+ } else {
+ set_complete = &request->response_msg.msg.set_complete;
+ if (set_complete->status != RNDIS_STATUS_SUCCESS) {
+ netdev_err(ndev, "Fail to set MAC on host side:0x%x\n",
+ set_complete->status);
+ ret = -EINVAL;
+ }
+ }
+
+cleanup:
+ put_rndis_request(rdev, request);
+ return ret;
+}
static int rndis_filter_query_device_link_status(struct rndis_device *dev)
{
@@ -620,7 +694,6 @@
ret = rndis_filter_query_device(dev,
RNDIS_OID_GEN_MEDIA_CONNECT_STATUS,
&link_status, &size);
- dev->link_state = (link_status != 0) ? true : false;
return ret;
}
@@ -810,6 +883,7 @@
struct netvsc_device *net_device;
struct rndis_device *rndis_device;
struct netvsc_device_info *device_info = additional_info;
+ struct ndis_offload_params offloads;
rndis_device = get_rndis_device();
if (!rndis_device)
@@ -849,6 +923,26 @@
memcpy(device_info->mac_adr, rndis_device->hw_mac_adr, ETH_ALEN);
+ /* Turn on the offloads; the host supports all of the relevant
+ * offloads.
+ */
+ memset(&offloads, 0, sizeof(struct ndis_offload_params));
+ /* A value of zero means "no change"; now turn on what we
+ * want.
+ */
+ offloads.ip_v4_csum = NDIS_OFFLOAD_PARAMETERS_TX_RX_ENABLED;
+ offloads.tcp_ip_v4_csum = NDIS_OFFLOAD_PARAMETERS_TX_RX_ENABLED;
+ offloads.udp_ip_v4_csum = NDIS_OFFLOAD_PARAMETERS_TX_RX_ENABLED;
+ offloads.tcp_ip_v6_csum = NDIS_OFFLOAD_PARAMETERS_TX_RX_ENABLED;
+ offloads.udp_ip_v6_csum = NDIS_OFFLOAD_PARAMETERS_TX_RX_ENABLED;
+ offloads.lso_v2_ipv4 = NDIS_OFFLOAD_PARAMETERS_LSOV2_ENABLED;
+
+
+ ret = rndis_filter_set_offload_params(dev, &offloads);
+ if (ret)
+ goto err_dev_remv;
+
+
rndis_filter_query_device_link_status(rndis_device);
device_info->link_state = rndis_device->link_state;
@@ -858,6 +952,10 @@
device_info->link_state ? "down" : "up");
return ret;
+
+err_dev_remv:
+ rndis_filter_device_remove(dev);
+ return ret;
}
void rndis_filter_device_remove(struct hv_device *dev)
@@ -894,101 +992,3 @@
return rndis_filter_close_device(nvdev->extension);
}
-
-int rndis_filter_send(struct hv_device *dev,
- struct hv_netvsc_packet *pkt)
-{
- int ret;
- struct rndis_filter_packet *filter_pkt;
- struct rndis_message *rndis_msg;
- struct rndis_packet *rndis_pkt;
- u32 rndis_msg_size;
- bool isvlan = pkt->vlan_tci & VLAN_TAG_PRESENT;
-
- /* Add the rndis header */
- filter_pkt = (struct rndis_filter_packet *)pkt->extension;
-
- rndis_msg = &filter_pkt->msg;
- rndis_msg_size = RNDIS_MESSAGE_SIZE(struct rndis_packet);
- if (isvlan)
- rndis_msg_size += NDIS_VLAN_PPI_SIZE;
-
- rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET;
- rndis_msg->msg_len = pkt->total_data_buflen +
- rndis_msg_size;
-
- rndis_pkt = &rndis_msg->msg.pkt;
- rndis_pkt->data_offset = sizeof(struct rndis_packet);
- if (isvlan)
- rndis_pkt->data_offset += NDIS_VLAN_PPI_SIZE;
- rndis_pkt->data_len = pkt->total_data_buflen;
-
- if (isvlan) {
- struct rndis_per_packet_info *ppi;
- struct ndis_pkt_8021q_info *vlan;
-
- rndis_pkt->per_pkt_info_offset = sizeof(struct rndis_packet);
- rndis_pkt->per_pkt_info_len = NDIS_VLAN_PPI_SIZE;
-
- ppi = (struct rndis_per_packet_info *)((ulong)rndis_pkt +
- rndis_pkt->per_pkt_info_offset);
- ppi->size = NDIS_VLAN_PPI_SIZE;
- ppi->type = IEEE_8021Q_INFO;
- ppi->ppi_offset = sizeof(struct rndis_per_packet_info);
-
- vlan = (struct ndis_pkt_8021q_info *)((ulong)ppi +
- ppi->ppi_offset);
- vlan->vlanid = pkt->vlan_tci & VLAN_VID_MASK;
- vlan->pri = (pkt->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
- }
-
- pkt->is_data_pkt = true;
- pkt->page_buf[0].pfn = virt_to_phys(rndis_msg) >> PAGE_SHIFT;
- pkt->page_buf[0].offset =
- (unsigned long)rndis_msg & (PAGE_SIZE-1);
- pkt->page_buf[0].len = rndis_msg_size;
-
- /* Add one page_buf if the rndis msg goes beyond page boundary */
- if (pkt->page_buf[0].offset + rndis_msg_size > PAGE_SIZE) {
- int i;
- for (i = pkt->page_buf_cnt; i > 1; i--)
- pkt->page_buf[i] = pkt->page_buf[i-1];
- pkt->page_buf_cnt++;
- pkt->page_buf[0].len = PAGE_SIZE - pkt->page_buf[0].offset;
- pkt->page_buf[1].pfn = virt_to_phys((void *)((ulong)
- rndis_msg + pkt->page_buf[0].len)) >> PAGE_SHIFT;
- pkt->page_buf[1].offset = 0;
- pkt->page_buf[1].len = rndis_msg_size - pkt->page_buf[0].len;
- }
-
- /* Save the packet send completion and context */
- filter_pkt->completion = pkt->completion.send.send_completion;
- filter_pkt->completion_ctx =
- pkt->completion.send.send_completion_ctx;
-
- /* Use ours */
- pkt->completion.send.send_completion = rndis_filter_send_completion;
- pkt->completion.send.send_completion_ctx = filter_pkt;
-
- ret = netvsc_send(dev, pkt);
- if (ret != 0) {
- /*
- * Reset the completion to originals to allow retries from
- * above
- */
- pkt->completion.send.send_completion =
- filter_pkt->completion;
- pkt->completion.send.send_completion_ctx =
- filter_pkt->completion_ctx;
- }
-
- return ret;
-}
-
-static void rndis_filter_send_completion(void *ctx)
-{
- struct rndis_filter_packet *filter_pkt = ctx;
-
- /* Pass it back to the original handler */
- filter_pkt->completion(filter_pkt->completion_ctx);
-}
diff --git a/drivers/net/ieee802154/Kconfig b/drivers/net/ieee802154/Kconfig
index 08ae465..3e89bea 100644
--- a/drivers/net/ieee802154/Kconfig
+++ b/drivers/net/ieee802154/Kconfig
@@ -15,9 +15,9 @@
depends on IEEE802154_DRIVERS
---help---
Say Y here to enable the fake driver that serves as an example
- of HardMAC device driver.
+ of HardMAC device driver.
- This driver can also be built as a module. To do so say M here.
+ This driver can also be built as a module. To do so say M here.
The module will be called 'fakehard'.
config IEEE802154_FAKELB
@@ -31,17 +31,23 @@
The module will be called 'fakelb'.
config IEEE802154_AT86RF230
- depends on IEEE802154_DRIVERS && MAC802154
- tristate "AT86RF230/231 transceiver driver"
- depends on SPI
+ depends on IEEE802154_DRIVERS && MAC802154
+ tristate "AT86RF230/231/233/212 transceiver driver"
+ depends on SPI
+ ---help---
+ Say Y here to enable the at86rf230/231/233/212 SPI 802.15.4 wireless
+ controller.
+
+ This driver can also be built as a module. To do so, say M here.
+ the module will be called 'at86rf230'.
config IEEE802154_MRF24J40
- tristate "Microchip MRF24J40 transceiver driver"
- depends on IEEE802154_DRIVERS && MAC802154
- depends on SPI
- ---help---
- Say Y here to enable the MRF24J20 SPI 802.15.4 wireless
- controller.
+ tristate "Microchip MRF24J40 transceiver driver"
+ depends on IEEE802154_DRIVERS && MAC802154
+ depends on SPI
+ ---help---
+ Say Y here to enable the MRF24J20 SPI 802.15.4 wireless
+ controller.
- This driver can also be built as a module. To do so, say M here.
- the module will be called 'mrf24j40'.
+ This driver can also be built as a module. To do so, say M here.
+ the module will be called 'mrf24j40'.
diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index ab31544..e8004ef 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -31,13 +31,13 @@
#include <linux/spi/spi.h>
#include <linux/spi/at86rf230.h>
#include <linux/skbuff.h>
+#include <linux/of_gpio.h>
#include <net/mac802154.h>
#include <net/wpan-phy.h>
struct at86rf230_local {
struct spi_device *spi;
- int rstn, slp_tr, dig2;
u8 part;
u8 vers;
@@ -53,8 +53,16 @@
spinlock_t lock;
bool irq_busy;
bool is_tx;
+ bool tx_aret;
+
+ int rssi_base_val;
};
+static bool is_rf212(struct at86rf230_local *local)
+{
+ return local->part == 7;
+}
+
#define RG_TRX_STATUS (0x01)
#define SR_TRX_STATUS 0x01, 0x1f, 0
#define SR_RESERVED_01_3 0x01, 0x20, 5
@@ -100,7 +108,10 @@
#define SR_SFD_VALUE 0x0b, 0xff, 0
#define RG_TRX_CTRL_2 (0x0c)
#define SR_OQPSK_DATA_RATE 0x0c, 0x03, 0
-#define SR_RESERVED_0c_2 0x0c, 0x7c, 2
+#define SR_SUB_MODE 0x0c, 0x04, 2
+#define SR_BPSK_QPSK 0x0c, 0x08, 3
+#define SR_OQPSK_SUB1_RC_EN 0x0c, 0x10, 4
+#define SR_RESERVED_0c_5 0x0c, 0x60, 5
#define SR_RX_SAFE_MODE 0x0c, 0x80, 7
#define RG_ANT_DIV (0x0d)
#define SR_ANT_CTRL 0x0d, 0x03, 0
@@ -145,7 +156,7 @@
#define SR_RESERVED_17_5 0x17, 0x08, 3
#define SR_AACK_UPLD_RES_FT 0x17, 0x10, 4
#define SR_AACK_FLTR_RES_FT 0x17, 0x20, 5
-#define SR_RESERVED_17_2 0x17, 0x40, 6
+#define SR_CSMA_LBT_MODE 0x17, 0x40, 6
#define SR_RESERVED_17_1 0x17, 0x80, 7
#define RG_FTN_CTRL (0x18)
#define SR_RESERVED_18_2 0x18, 0x7f, 0
@@ -234,6 +245,7 @@
#define STATE_TX_ON 0x09
/* 0x0a - 0x0e */ /* 0x0a - UNSUPPORTED_ATTRIBUTE */
#define STATE_SLEEP 0x0F
+#define STATE_PREP_DEEP_SLEEP 0x10
#define STATE_BUSY_RX_AACK 0x11
#define STATE_BUSY_TX_ARET 0x12
#define STATE_RX_AACK_ON 0x16
@@ -244,6 +256,57 @@
#define STATE_TRANSITION_IN_PROGRESS 0x1F
static int
+__at86rf230_detect_device(struct spi_device *spi, u16 *man_id, u8 *part,
+ u8 *version)
+{
+ u8 data[4];
+ u8 *buf = kmalloc(2, GFP_KERNEL);
+ int status;
+ struct spi_message msg;
+ struct spi_transfer xfer = {
+ .len = 2,
+ .tx_buf = buf,
+ .rx_buf = buf,
+ };
+ u8 reg;
+
+ if (!buf)
+ return -ENOMEM;
+
+ for (reg = RG_PART_NUM; reg <= RG_MAN_ID_1; reg++) {
+ buf[0] = (reg & CMD_REG_MASK) | CMD_REG;
+ buf[1] = 0xff;
+ dev_vdbg(&spi->dev, "buf[0] = %02x\n", buf[0]);
+ spi_message_init(&msg);
+ spi_message_add_tail(&xfer, &msg);
+
+ status = spi_sync(spi, &msg);
+ dev_vdbg(&spi->dev, "status = %d\n", status);
+ if (msg.status)
+ status = msg.status;
+
+ dev_vdbg(&spi->dev, "status = %d\n", status);
+ dev_vdbg(&spi->dev, "buf[0] = %02x\n", buf[0]);
+ dev_vdbg(&spi->dev, "buf[1] = %02x\n", buf[1]);
+
+ if (status == 0)
+ data[reg - RG_PART_NUM] = buf[1];
+ else
+ break;
+ }
+
+ if (status == 0) {
+ *part = data[0];
+ *version = data[1];
+ *man_id = (data[3] << 8) | data[2];
+ }
+
+ kfree(buf);
+
+ return status;
+}
+
+static int
__at86rf230_write(struct at86rf230_local *lp, u8 addr, u8 data)
{
u8 *buf = lp->buf;
@@ -489,7 +552,9 @@
} while (val == STATE_TRANSITION_IN_PROGRESS);
- if (val == desired_status)
+ if (val == desired_status ||
+ (desired_status == STATE_RX_ON && val == STATE_BUSY_RX) ||
+ (desired_status == STATE_RX_AACK_ON && val == STATE_BUSY_RX_AACK))
return 0;
pr_err("unexpected state change: %d, asked for %d\n", val, state);
@@ -510,7 +575,11 @@
if (rc)
return rc;
- return at86rf230_state(dev, STATE_RX_ON);
+ rc = at86rf230_state(dev, STATE_TX_ON);
+ if (rc)
+ return rc;
+
+ return at86rf230_state(dev, STATE_RX_AACK_ON);
}
static void
@@ -520,6 +589,39 @@
}
static int
+at86rf230_set_channel(struct at86rf230_local *lp, int page, int channel)
+{
+ lp->rssi_base_val = -91;
+
+ return at86rf230_write_subreg(lp, SR_CHANNEL, channel);
+}
+
+static int
+at86rf212_set_channel(struct at86rf230_local *lp, int page, int channel)
+{
+ int rc;
+
+ if (channel == 0)
+ rc = at86rf230_write_subreg(lp, SR_SUB_MODE, 0);
+ else
+ rc = at86rf230_write_subreg(lp, SR_SUB_MODE, 1);
+ if (rc < 0)
+ return rc;
+
+ if (page == 0) {
+ rc = at86rf230_write_subreg(lp, SR_BPSK_QPSK, 0);
+ lp->rssi_base_val = -100;
+ } else {
+ rc = at86rf230_write_subreg(lp, SR_BPSK_QPSK, 1);
+ lp->rssi_base_val = -98;
+ }
+ if (rc < 0)
+ return rc;
+
+ return at86rf230_write_subreg(lp, SR_CHANNEL, channel);
+}
+
+static int
at86rf230_channel(struct ieee802154_dev *dev, int page, int channel)
{
struct at86rf230_local *lp = dev->priv;
@@ -527,14 +629,22 @@
might_sleep();
- if (page != 0 || channel < 11 || channel > 26) {
+ if (page < 0 || page > 31 ||
+ !(lp->dev->phy->channels_supported[page] & BIT(channel))) {
WARN_ON(1);
return -EINVAL;
}
- rc = at86rf230_write_subreg(lp, SR_CHANNEL, channel);
+ if (is_rf212(lp))
+ rc = at86rf212_set_channel(lp, page, channel);
+ else
+ rc = at86rf230_set_channel(lp, page, channel);
+ if (rc < 0)
+ return rc;
+
msleep(1); /* Wait for PLL */
dev->phy->current_channel = channel;
+ dev->phy->current_page = page;
return 0;
}
@@ -546,12 +656,12 @@
int rc;
unsigned long flags;
- spin_lock(&lp->lock);
+ spin_lock_irqsave(&lp->lock, flags);
if (lp->irq_busy) {
- spin_unlock(&lp->lock);
+ spin_unlock_irqrestore(&lp->lock, flags);
return -EBUSY;
}
- spin_unlock(&lp->lock);
+ spin_unlock_irqrestore(&lp->lock, flags);
might_sleep();
@@ -568,6 +678,12 @@
if (rc)
goto err_rx;
+ if (lp->tx_aret) {
+ rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_TX_ARET_ON);
+ if (rc)
+ goto err_rx;
+ }
+
rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_BUSY_TX);
if (rc)
goto err_rx;
@@ -630,30 +746,31 @@
struct at86rf230_local *lp = dev->priv;
if (changed & IEEE802515_AFILT_SADDR_CHANGED) {
+ u16 addr = le16_to_cpu(filt->short_addr);
+
dev_vdbg(&lp->spi->dev,
"at86rf230_set_hw_addr_filt called for saddr\n");
- __at86rf230_write(lp, RG_SHORT_ADDR_0, filt->short_addr);
- __at86rf230_write(lp, RG_SHORT_ADDR_1, filt->short_addr >> 8);
+ __at86rf230_write(lp, RG_SHORT_ADDR_0, addr);
+ __at86rf230_write(lp, RG_SHORT_ADDR_1, addr >> 8);
}
if (changed & IEEE802515_AFILT_PANID_CHANGED) {
+ u16 pan = le16_to_cpu(filt->pan_id);
+
dev_vdbg(&lp->spi->dev,
"at86rf230_set_hw_addr_filt called for pan id\n");
- __at86rf230_write(lp, RG_PAN_ID_0, filt->pan_id);
- __at86rf230_write(lp, RG_PAN_ID_1, filt->pan_id >> 8);
+ __at86rf230_write(lp, RG_PAN_ID_0, pan);
+ __at86rf230_write(lp, RG_PAN_ID_1, pan >> 8);
}
if (changed & IEEE802515_AFILT_IEEEADDR_CHANGED) {
+ u8 i, addr[8];
+
+ memcpy(addr, &filt->ieee_addr, 8);
dev_vdbg(&lp->spi->dev,
"at86rf230_set_hw_addr_filt called for IEEE addr\n");
- at86rf230_write_subreg(lp, SR_IEEE_ADDR_0, filt->ieee_addr[7]);
- at86rf230_write_subreg(lp, SR_IEEE_ADDR_1, filt->ieee_addr[6]);
- at86rf230_write_subreg(lp, SR_IEEE_ADDR_2, filt->ieee_addr[5]);
- at86rf230_write_subreg(lp, SR_IEEE_ADDR_3, filt->ieee_addr[4]);
- at86rf230_write_subreg(lp, SR_IEEE_ADDR_4, filt->ieee_addr[3]);
- at86rf230_write_subreg(lp, SR_IEEE_ADDR_5, filt->ieee_addr[2]);
- at86rf230_write_subreg(lp, SR_IEEE_ADDR_6, filt->ieee_addr[1]);
- at86rf230_write_subreg(lp, SR_IEEE_ADDR_7, filt->ieee_addr[0]);
+ for (i = 0; i < 8; i++)
+ __at86rf230_write(lp, RG_IEEE_ADDR_0 + i, addr[i]);
}
if (changed & IEEE802515_AFILT_PANC_CHANGED) {
@@ -668,6 +785,93 @@
return 0;
}
+static int
+at86rf212_set_txpower(struct ieee802154_dev *dev, int db)
+{
+ struct at86rf230_local *lp = dev->priv;
+
+ /* typical maximum output is 5dBm with RG_PHY_TX_PWR 0x60, lower five
+ * bits decrease power in 1dB steps. 0x60 represents extra PA gain of
+ * 0dB.
+ * thus, supported values for db range from -26 to 5, for 31dB of
+ * reduction to 0dB of reduction.
+ */
+ if (db > 5 || db < -26)
+ return -EINVAL;
+
+ db = -(db - 5);
+
+ return __at86rf230_write(lp, RG_PHY_TX_PWR, 0x60 | db);
+}
+
+static int
+at86rf212_set_lbt(struct ieee802154_dev *dev, bool on)
+{
+ struct at86rf230_local *lp = dev->priv;
+
+ return at86rf230_write_subreg(lp, SR_CSMA_LBT_MODE, on);
+}
+
+static int
+at86rf212_set_cca_mode(struct ieee802154_dev *dev, u8 mode)
+{
+ struct at86rf230_local *lp = dev->priv;
+
+ return at86rf230_write_subreg(lp, SR_CCA_MODE, mode);
+}
+
+static int
+at86rf212_set_cca_ed_level(struct ieee802154_dev *dev, s32 level)
+{
+ struct at86rf230_local *lp = dev->priv;
+ int desens_steps;
+
+ if (level < lp->rssi_base_val || level > 30)
+ return -EINVAL;
+
+ desens_steps = (level - lp->rssi_base_val) * 100 / 207;
+
+ return at86rf230_write_subreg(lp, SR_CCA_ED_THRES, desens_steps);
+}
+
+static int
+at86rf212_set_csma_params(struct ieee802154_dev *dev, u8 min_be, u8 max_be,
+ u8 retries)
+{
+ struct at86rf230_local *lp = dev->priv;
+ int rc;
+
+ if (min_be > max_be || max_be > 8 || retries > 5)
+ return -EINVAL;
+
+ rc = at86rf230_write_subreg(lp, SR_MIN_BE, min_be);
+ if (rc)
+ return rc;
+
+ rc = at86rf230_write_subreg(lp, SR_MAX_BE, max_be);
+ if (rc)
+ return rc;
+
+ return at86rf230_write_subreg(lp, SR_MAX_CSMA_RETRIES, max_be);
+}
+
+static int
+at86rf212_set_frame_retries(struct ieee802154_dev *dev, s8 retries)
+{
+ struct at86rf230_local *lp = dev->priv;
+ int rc = 0;
+
+ if (retries < -1 || retries > 15)
+ return -EINVAL;
+
+ lp->tx_aret = retries >= 0;
+
+ if (retries >= 0)
+ rc = at86rf230_write_subreg(lp, SR_MAX_FRAME_RETRIES, retries);
+
+ return rc;
+}
+
static struct ieee802154_ops at86rf230_ops = {
.owner = THIS_MODULE,
.xmit = at86rf230_xmit,
@@ -678,6 +882,22 @@
.set_hw_addr_filt = at86rf230_set_hw_addr_filt,
};
+static struct ieee802154_ops at86rf212_ops = {
+ .owner = THIS_MODULE,
+ .xmit = at86rf230_xmit,
+ .ed = at86rf230_ed,
+ .set_channel = at86rf230_channel,
+ .start = at86rf230_start,
+ .stop = at86rf230_stop,
+ .set_hw_addr_filt = at86rf230_set_hw_addr_filt,
+ .set_txpower = at86rf212_set_txpower,
+ .set_lbt = at86rf212_set_lbt,
+ .set_cca_mode = at86rf212_set_cca_mode,
+ .set_cca_ed_level = at86rf212_set_cca_ed_level,
+ .set_csma_params = at86rf212_set_csma_params,
+ .set_frame_retries = at86rf212_set_frame_retries,
+};
+
static void at86rf230_irqwork(struct work_struct *work)
{
struct at86rf230_local *lp =
@@ -695,8 +915,8 @@
status &= ~IRQ_TRX_UR; /* FIXME: possibly handle ???*/
if (status & IRQ_TRX_END) {
- spin_lock_irqsave(&lp->lock, flags);
status &= ~IRQ_TRX_END;
+ spin_lock_irqsave(&lp->lock, flags);
if (lp->is_tx) {
lp->is_tx = 0;
spin_unlock_irqrestore(&lp->lock, flags);
@@ -725,10 +945,11 @@
static irqreturn_t at86rf230_isr(int irq, void *data)
{
struct at86rf230_local *lp = data;
+ unsigned long flags;
- spin_lock(&lp->lock);
+ spin_lock_irqsave(&lp->lock, flags);
lp->irq_busy = 1;
- spin_unlock(&lp->lock);
+ spin_unlock_irqrestore(&lp->lock, flags);
schedule_work(&lp->irqwork);
@@ -752,22 +973,15 @@
struct at86rf230_platform_data *pdata = lp->spi->dev.platform_data;
int rc, irq_pol;
u8 status;
+ u8 csma_seed[2];
rc = at86rf230_read_subreg(lp, SR_TRX_STATUS, &status);
if (rc)
return rc;
- dev_info(&lp->spi->dev, "Status: %02x\n", status);
- if (status == STATE_P_ON) {
- rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_TRX_OFF);
- if (rc)
- return rc;
- msleep(1);
- rc = at86rf230_read_subreg(lp, SR_TRX_STATUS, &status);
- if (rc)
- return rc;
- dev_info(&lp->spi->dev, "Status: %02x\n", status);
- }
+ rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_FORCE_TRX_OFF);
+ if (rc)
+ return rc;
/* configure irq polarity, defaults to high active */
if (pdata->irq_type & (IRQF_TRIGGER_FALLING | IRQF_TRIGGER_LOW))
@@ -783,6 +997,14 @@
if (rc)
return rc;
+ get_random_bytes(csma_seed, ARRAY_SIZE(csma_seed));
+ rc = at86rf230_write_subreg(lp, SR_CSMA_SEED_0, csma_seed[0]);
+ if (rc)
+ return rc;
+ rc = at86rf230_write_subreg(lp, SR_CSMA_SEED_1, csma_seed[1]);
+ if (rc)
+ return rc;
+
/* CLKM changes are applied immediately */
rc = at86rf230_write_subreg(lp, SR_CLKM_SHA_SEL, 0x00);
if (rc)
@@ -795,16 +1017,6 @@
/* Wait the next SLEEP cycle */
msleep(100);
- rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_TX_ON);
- if (rc)
- return rc;
- msleep(1);
-
- rc = at86rf230_read_subreg(lp, SR_TRX_STATUS, &status);
- if (rc)
- return rc;
- dev_info(&lp->spi->dev, "Status: %02x\n", status);
-
rc = at86rf230_read_subreg(lp, SR_DVDD_OK, &status);
if (rc)
return rc;
@@ -824,14 +1036,38 @@
return 0;
}
-static void at86rf230_fill_data(struct spi_device *spi)
+static struct at86rf230_platform_data *
+at86rf230_get_pdata(struct spi_device *spi)
{
- struct at86rf230_local *lp = spi_get_drvdata(spi);
- struct at86rf230_platform_data *pdata = spi->dev.platform_data;
+ struct at86rf230_platform_data *pdata;
+ const char *irq_type;
- lp->rstn = pdata->rstn;
- lp->slp_tr = pdata->slp_tr;
- lp->dig2 = pdata->dig2;
+ if (!IS_ENABLED(CONFIG_OF) || !spi->dev.of_node)
+ return spi->dev.platform_data;
+
+ pdata = devm_kzalloc(&spi->dev, sizeof(*pdata), GFP_KERNEL);
+ if (!pdata)
+ goto done;
+
+ pdata->rstn = of_get_named_gpio(spi->dev.of_node, "reset-gpio", 0);
+ pdata->slp_tr = of_get_named_gpio(spi->dev.of_node, "sleep-gpio", 0);
+
+ pdata->irq_type = IRQF_TRIGGER_RISING;
+ of_property_read_string(spi->dev.of_node, "irq-type", &irq_type);
+ if (!strcmp(irq_type, "level-high"))
+ pdata->irq_type = IRQF_TRIGGER_HIGH;
+ else if (!strcmp(irq_type, "level-low"))
+ pdata->irq_type = IRQF_TRIGGER_LOW;
+ else if (!strcmp(irq_type, "edge-rising"))
+ pdata->irq_type = IRQF_TRIGGER_RISING;
+ else if (!strcmp(irq_type, "edge-falling"))
+ pdata->irq_type = IRQF_TRIGGER_FALLING;
+ else
+ dev_warn(&spi->dev, "wrong irq-type specified using edge-rising\n");
+
+ spi->dev.platform_data = pdata;
+done:
+ return pdata;
}
static int at86rf230_probe(struct spi_device *spi)
@@ -839,37 +1075,114 @@
struct at86rf230_platform_data *pdata;
struct ieee802154_dev *dev;
struct at86rf230_local *lp;
- u8 man_id_0, man_id_1, status;
+ u16 man_id = 0;
+ u8 part = 0, version = 0, status;
irq_handler_t irq_handler;
work_func_t irq_worker;
- int rc, supported = 0;
+ int rc;
const char *chip;
+ struct ieee802154_ops *ops = NULL;
if (!spi->irq) {
dev_err(&spi->dev, "no IRQ specified\n");
return -EINVAL;
}
- pdata = spi->dev.platform_data;
+ pdata = at86rf230_get_pdata(spi);
if (!pdata) {
dev_err(&spi->dev, "no platform_data\n");
return -EINVAL;
}
- dev = ieee802154_alloc_device(sizeof(*lp), &at86rf230_ops);
- if (!dev)
- return -ENOMEM;
+ if (gpio_is_valid(pdata->rstn)) {
+ rc = gpio_request(pdata->rstn, "rstn");
+ if (rc)
+ return rc;
+ }
+
+ if (gpio_is_valid(pdata->slp_tr)) {
+ rc = gpio_request(pdata->slp_tr, "slp_tr");
+ if (rc)
+ goto err_slp_tr;
+ }
+
+ if (gpio_is_valid(pdata->rstn)) {
+ rc = gpio_direction_output(pdata->rstn, 1);
+ if (rc)
+ goto err_gpio_dir;
+ }
+
+ if (gpio_is_valid(pdata->slp_tr)) {
+ rc = gpio_direction_output(pdata->slp_tr, 0);
+ if (rc)
+ goto err_gpio_dir;
+ }
+
+ /* Reset */
+ if (gpio_is_valid(pdata->rstn)) {
+ udelay(1);
+ gpio_set_value(pdata->rstn, 0);
+ udelay(1);
+ gpio_set_value(pdata->rstn, 1);
+ usleep_range(120, 240);
+ }
+
+ rc = __at86rf230_detect_device(spi, &man_id, &part, &version);
+ if (rc < 0)
+ goto err_gpio_dir;
+
+ if (man_id != 0x001f) {
+ dev_err(&spi->dev, "Non-Atmel dev found (MAN_ID %02x %02x)\n",
+ man_id >> 8, man_id & 0xFF);
+ rc = -EINVAL;
+ goto err_gpio_dir;
+ }
+
+ switch (part) {
+ case 2:
+ chip = "at86rf230";
+ /* FIXME: should be easy to support; */
+ break;
+ case 3:
+ chip = "at86rf231";
+ ops = &at86rf230_ops;
+ break;
+ case 7:
+ chip = "at86rf212";
+ if (version == 1)
+ ops = &at86rf212_ops;
+ break;
+ case 11:
+ chip = "at86rf233";
+ ops = &at86rf230_ops;
+ break;
+ default:
+ chip = "UNKNOWN";
+ break;
+ }
+
+ dev_info(&spi->dev, "Detected %s chip version %d\n", chip, version);
+ if (!ops) {
+ rc = -ENOTSUPP;
+ goto err_gpio_dir;
+ }
+
+ dev = ieee802154_alloc_device(sizeof(*lp), ops);
+ if (!dev) {
+ rc = -ENOMEM;
+ goto err_gpio_dir;
+ }
lp = dev->priv;
lp->dev = dev;
+ lp->part = part;
+ lp->vers = version;
lp->spi = spi;
dev->parent = &spi->dev;
dev->extra_tx_headroom = 0;
- /* We do support only 2.4 Ghz */
- dev->phy->channels_supported[0] = 0x7FFF800;
- dev->flags = IEEE802154_HW_OMIT_CKSUM;
+ dev->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK;
if (pdata->irq_type & (IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING)) {
irq_worker = at86rf230_irqwork;
@@ -886,86 +1199,22 @@
spi_set_drvdata(spi, lp);
- at86rf230_fill_data(spi);
-
- rc = gpio_request(lp->rstn, "rstn");
- if (rc)
- goto err_rstn;
-
- if (gpio_is_valid(lp->slp_tr)) {
- rc = gpio_request(lp->slp_tr, "slp_tr");
- if (rc)
- goto err_slp_tr;
- }
-
- rc = gpio_direction_output(lp->rstn, 1);
- if (rc)
- goto err_gpio_dir;
-
- if (gpio_is_valid(lp->slp_tr)) {
- rc = gpio_direction_output(lp->slp_tr, 0);
- if (rc)
- goto err_gpio_dir;
- }
-
- /* Reset */
- msleep(1);
- gpio_set_value(lp->rstn, 0);
- msleep(1);
- gpio_set_value(lp->rstn, 1);
- msleep(1);
-
- rc = at86rf230_read_subreg(lp, SR_MAN_ID_0, &man_id_0);
- if (rc)
- goto err_gpio_dir;
- rc = at86rf230_read_subreg(lp, SR_MAN_ID_1, &man_id_1);
- if (rc)
- goto err_gpio_dir;
-
- if (man_id_1 != 0x00 || man_id_0 != 0x1f) {
- dev_err(&spi->dev, "Non-Atmel dev found (MAN_ID %02x %02x)\n",
- man_id_1, man_id_0);
- rc = -EINVAL;
- goto err_gpio_dir;
- }
-
- rc = at86rf230_read_subreg(lp, SR_PART_NUM, &lp->part);
- if (rc)
- goto err_gpio_dir;
-
- rc = at86rf230_read_subreg(lp, SR_VERSION_NUM, &lp->vers);
- if (rc)
- goto err_gpio_dir;
-
- switch (lp->part) {
- case 2:
- chip = "at86rf230";
- /* supported = 1; FIXME: should be easy to support; */
- break;
- case 3:
- chip = "at86rf231";
- supported = 1;
- break;
- default:
- chip = "UNKNOWN";
- break;
- }
-
- dev_info(&spi->dev, "Detected %s chip version %d\n", chip, lp->vers);
- if (!supported) {
- rc = -ENOTSUPP;
- goto err_gpio_dir;
+ if (is_rf212(lp)) {
+ dev->phy->channels_supported[0] = 0x00007FF;
+ dev->phy->channels_supported[2] = 0x00007FF;
+ } else {
+ dev->phy->channels_supported[0] = 0x7FFF800;
}
rc = at86rf230_hw_init(lp);
if (rc)
- goto err_gpio_dir;
+ goto err_hw_init;
rc = request_irq(spi->irq, irq_handler,
IRQF_SHARED | pdata->irq_type,
dev_name(&spi->dev), lp);
if (rc)
- goto err_gpio_dir;
+ goto err_hw_init;
/* Read irq status register to reset irq line */
rc = at86rf230_read_subreg(lp, RG_IRQ_STATUS, 0xff, 0, &status);
@@ -980,30 +1229,35 @@
err_irq:
free_irq(spi->irq, lp);
+err_hw_init:
flush_work(&lp->irqwork);
-err_gpio_dir:
- if (gpio_is_valid(lp->slp_tr))
- gpio_free(lp->slp_tr);
-err_slp_tr:
- gpio_free(lp->rstn);
-err_rstn:
+ spi_set_drvdata(spi, NULL);
mutex_destroy(&lp->bmux);
ieee802154_free_device(lp->dev);
+
+err_gpio_dir:
+ if (gpio_is_valid(pdata->slp_tr))
+ gpio_free(pdata->slp_tr);
+err_slp_tr:
+ if (gpio_is_valid(pdata->rstn))
+ gpio_free(pdata->rstn);
return rc;
}
static int at86rf230_remove(struct spi_device *spi)
{
struct at86rf230_local *lp = spi_get_drvdata(spi);
+ struct at86rf230_platform_data *pdata = spi->dev.platform_data;
ieee802154_unregister_device(lp->dev);
free_irq(spi->irq, lp);
flush_work(&lp->irqwork);
- if (gpio_is_valid(lp->slp_tr))
- gpio_free(lp->slp_tr);
- gpio_free(lp->rstn);
+ if (gpio_is_valid(pdata->slp_tr))
+ gpio_free(pdata->slp_tr);
+ if (gpio_is_valid(pdata->rstn))
+ gpio_free(pdata->rstn);
mutex_destroy(&lp->bmux);
ieee802154_free_device(lp->dev);
@@ -1012,8 +1266,19 @@
return 0;
}
+#if IS_ENABLED(CONFIG_OF)
+static struct of_device_id at86rf230_of_match[] = {
+ { .compatible = "atmel,at86rf230", },
+ { .compatible = "atmel,at86rf231", },
+ { .compatible = "atmel,at86rf233", },
+ { .compatible = "atmel,at86rf212", },
+ { },
+};
+#endif
+
static struct spi_driver at86rf230_driver = {
.driver = {
+ .of_match_table = of_match_ptr(at86rf230_of_match),
.name = "at86rf230",
.owner = THIS_MODULE,
},
diff --git a/drivers/net/ieee802154/fakehard.c b/drivers/net/ieee802154/fakehard.c
index bf0d55e..78f18be 100644
--- a/drivers/net/ieee802154/fakehard.c
+++ b/drivers/net/ieee802154/fakehard.c
@@ -63,11 +63,11 @@
*
* Return the ID of the PAN from the PIB.
*/
-static u16 fake_get_pan_id(const struct net_device *dev)
+static __le16 fake_get_pan_id(const struct net_device *dev)
{
BUG_ON(dev->type != ARPHRD_IEEE802154);
- return 0xeba1;
+ return cpu_to_le16(0xeba1);
}
/**
@@ -78,11 +78,11 @@
* device. If the device has not yet had a short address assigned
* then this should return 0xFFFF to indicate a lack of association.
*/
-static u16 fake_get_short_addr(const struct net_device *dev)
+static __le16 fake_get_short_addr(const struct net_device *dev)
{
BUG_ON(dev->type != ARPHRD_IEEE802154);
- return 0x1;
+ return cpu_to_le16(0x1);
}
/**
@@ -149,7 +149,7 @@
* 802.15.4-2006 document.
*/
static int fake_assoc_resp(struct net_device *dev,
- struct ieee802154_addr *addr, u16 short_addr, u8 status)
+ struct ieee802154_addr *addr, __le16 short_addr, u8 status)
{
return 0;
}
@@ -191,10 +191,10 @@
* Note: This is in section 7.5.2.3 of the IEEE 802.15.4-2006
* document, with 7.3.8 describing coordinator realignment.
*/
-static int fake_start_req(struct net_device *dev, struct ieee802154_addr *addr,
- u8 channel, u8 page,
- u8 bcn_ord, u8 sf_ord, u8 pan_coord, u8 blx,
- u8 coord_realign)
+static int fake_start_req(struct net_device *dev,
+ struct ieee802154_addr *addr, u8 channel, u8 page,
+ u8 bcn_ord, u8 sf_ord, u8 pan_coord, u8 blx,
+ u8 coord_realign)
{
struct wpan_phy *phy = fake_to_phy(dev);
@@ -281,8 +281,8 @@
switch (cmd) {
case SIOCGIFADDR:
/* FIXME: fixed here, get from device IRL */
- pan_id = fake_get_pan_id(dev);
- short_addr = fake_get_short_addr(dev);
+ pan_id = le16_to_cpu(fake_get_pan_id(dev));
+ short_addr = le16_to_cpu(fake_get_short_addr(dev));
if (pan_id == IEEE802154_PANID_BROADCAST ||
short_addr == IEEE802154_ADDR_BROADCAST)
return -EADDRNOTAVAIL;
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index 246befa..78a6552 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -465,8 +465,8 @@
if (changed & IEEE802515_AFILT_SADDR_CHANGED) {
/* Short Addr */
u8 addrh, addrl;
- addrh = filt->short_addr >> 8 & 0xff;
- addrl = filt->short_addr & 0xff;
+ addrh = le16_to_cpu(filt->short_addr) >> 8 & 0xff;
+ addrl = le16_to_cpu(filt->short_addr) & 0xff;
write_short_reg(devrec, REG_SADRH, addrh);
write_short_reg(devrec, REG_SADRL, addrl);
@@ -476,15 +476,16 @@
if (changed & IEEE802515_AFILT_IEEEADDR_CHANGED) {
/* Device Address */
- int i;
+ u8 i, addr[8];
+
+ memcpy(addr, &filt->ieee_addr, 8);
for (i = 0; i < 8; i++)
- write_short_reg(devrec, REG_EADR0+i,
- filt->ieee_addr[7-i]);
+ write_short_reg(devrec, REG_EADR0 + i, addr[i]);
#ifdef DEBUG
printk(KERN_DEBUG "Set long addr to: ");
for (i = 0; i < 8; i++)
- printk("%02hhx ", filt->ieee_addr[i]);
+ printk("%02hhx ", addr[7 - i]);
printk(KERN_DEBUG "\n");
#endif
}
@@ -492,8 +493,8 @@
if (changed & IEEE802515_AFILT_PANID_CHANGED) {
/* PAN ID */
u8 panidl, panidh;
- panidh = filt->pan_id >> 8 & 0xff;
- panidl = filt->pan_id & 0xff;
+ panidh = le16_to_cpu(filt->pan_id) >> 8 & 0xff;
+ panidl = le16_to_cpu(filt->pan_id) & 0xff;
write_short_reg(devrec, REG_PANIDH, panidh);
write_short_reg(devrec, REG_PANIDL, panidl);
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index c14d39b..46a7790 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -136,18 +136,18 @@
unsigned int start;
do {
- start = u64_stats_fetch_begin_bh(&dp->rsync);
+ start = u64_stats_fetch_begin_irq(&dp->rsync);
stats->rx_packets = dp->rx_packets;
stats->rx_bytes = dp->rx_bytes;
- } while (u64_stats_fetch_retry_bh(&dp->rsync, start));
+ } while (u64_stats_fetch_retry_irq(&dp->rsync, start));
do {
- start = u64_stats_fetch_begin_bh(&dp->tsync);
+ start = u64_stats_fetch_begin_irq(&dp->tsync);
stats->tx_packets = dp->tx_packets;
stats->tx_bytes = dp->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&dp->tsync, start));
+ } while (u64_stats_fetch_retry_irq(&dp->tsync, start));
stats->rx_dropped = dev->stats.rx_dropped;
stats->tx_dropped = dev->stats.tx_dropped;
@@ -180,7 +180,8 @@
dev->tx_queue_len = TX_Q_LIMIT;
dev->features |= IFB_FEATURES;
- dev->vlan_features |= IFB_FEATURES;
+ dev->vlan_features |= IFB_FEATURES & ~(NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX);
dev->flags |= IFF_NOARP;
dev->flags &= ~IFF_MULTICAST;
diff --git a/drivers/net/irda/Kconfig b/drivers/net/irda/Kconfig
index 2dc82f1..3da44d5 100644
--- a/drivers/net/irda/Kconfig
+++ b/drivers/net/irda/Kconfig
@@ -210,13 +210,6 @@
To compile it as a module, choose M here: the module will be called
kingsun-sir.
-config EP7211_DONGLE
- tristate "Cirrus Logic clps711x I/R support"
- depends on IRTTY_SIR && ARCH_CLPS711X && IRDA
- help
- Say Y here if you want to build support for the Cirrus logic
- EP7211 chipset's infrared module.
-
config KSDAZZLE_DONGLE
tristate "KingSun Dazzle IrDA-USB dongle"
depends on IRDA && USB
diff --git a/drivers/net/irda/Makefile b/drivers/net/irda/Makefile
index dfc6453..be8ab5b 100644
--- a/drivers/net/irda/Makefile
+++ b/drivers/net/irda/Makefile
@@ -35,7 +35,6 @@
obj-$(CONFIG_ACT200L_DONGLE) += act200l-sir.o
obj-$(CONFIG_MA600_DONGLE) += ma600-sir.o
obj-$(CONFIG_TOIM3232_DONGLE) += toim3232-sir.o
-obj-$(CONFIG_EP7211_DONGLE) += ep7211-sir.o
obj-$(CONFIG_KINGSUN_DONGLE) += kingsun-sir.o
obj-$(CONFIG_KSDAZZLE_DONGLE) += ksdazzle-sir.o
obj-$(CONFIG_KS959_DONGLE) += ks959-sir.o
diff --git a/drivers/net/irda/ep7211-sir.c b/drivers/net/irda/ep7211-sir.c
deleted file mode 100644
index 5fe1f4d..0000000
--- a/drivers/net/irda/ep7211-sir.c
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * IR port driver for the Cirrus Logic CLPS711X processors
- *
- * Copyright 2001, Blue Mug Inc. All rights reserved.
- * Copyright 2007, Samuel Ortiz <samuel@sortiz.org>
- */
-
-#include <linux/module.h>
-#include <linux/platform_device.h>
-
-#include <mach/hardware.h>
-
-#include "sir-dev.h"
-
-static int clps711x_dongle_open(struct sir_dev *dev)
-{
- unsigned int syscon;
-
- /* Turn on the SIR encoder. */
- syscon = clps_readl(SYSCON1);
- syscon |= SYSCON1_SIREN;
- clps_writel(syscon, SYSCON1);
-
- return 0;
-}
-
-static int clps711x_dongle_close(struct sir_dev *dev)
-{
- unsigned int syscon;
-
- /* Turn off the SIR encoder. */
- syscon = clps_readl(SYSCON1);
- syscon &= ~SYSCON1_SIREN;
- clps_writel(syscon, SYSCON1);
-
- return 0;
-}
-
-static struct dongle_driver clps711x_dongle = {
- .owner = THIS_MODULE,
- .driver_name = "EP7211 IR driver",
- .type = IRDA_EP7211_DONGLE,
- .open = clps711x_dongle_open,
- .close = clps711x_dongle_close,
-};
-
-static int clps711x_sir_probe(struct platform_device *pdev)
-{
- return irda_register_dongle(&clps711x_dongle);
-}
-
-static int clps711x_sir_remove(struct platform_device *pdev)
-{
- return irda_unregister_dongle(&clps711x_dongle);
-}
-
-static struct platform_driver clps711x_sir_driver = {
- .driver = {
- .name = "sir-clps711x",
- .owner = THIS_MODULE,
- },
- .probe = clps711x_sir_probe,
- .remove = clps711x_sir_remove,
-};
-module_platform_driver(clps711x_sir_driver);
-
-MODULE_AUTHOR("Samuel Ortiz <samuel@sortiz.org>");
-MODULE_DESCRIPTION("EP7211 IR dongle driver");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("irda-dongle-13"); /* IRDA_EP7211_DONGLE */
diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c
index 177441a..24b6ddd 100644
--- a/drivers/net/irda/irtty-sir.c
+++ b/drivers/net/irda/irtty-sir.c
@@ -522,7 +522,6 @@
sirdev_put_instance(priv->dev);
/* Stop tty */
- irtty_stop_receiver(tty, TRUE);
clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
if (tty->ops->stop)
tty->ops->stop(tty);
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index c5011e0..bb96409 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -111,10 +111,10 @@
lb_stats = per_cpu_ptr(dev->lstats, i);
do {
- start = u64_stats_fetch_begin_bh(&lb_stats->syncp);
+ start = u64_stats_fetch_begin_irq(&lb_stats->syncp);
tbytes = lb_stats->bytes;
tpackets = lb_stats->packets;
- } while (u64_stats_fetch_retry_bh(&lb_stats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&lb_stats->syncp, start));
bytes += tbytes;
packets += tpackets;
}
@@ -136,16 +136,9 @@
static int loopback_dev_init(struct net_device *dev)
{
- int i;
- dev->lstats = alloc_percpu(struct pcpu_lstats);
+ dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
if (!dev->lstats)
return -ENOMEM;
-
- for_each_possible_cpu(i) {
- struct pcpu_lstats *lb_stats;
- lb_stats = per_cpu_ptr(dev->lstats, i);
- u64_stats_init(&lb_stats->syncp);
- }
return 0;
}
@@ -160,6 +153,7 @@
.ndo_init = loopback_dev_init,
.ndo_start_xmit= loopback_xmit,
.ndo_get_stats64 = loopback_get_stats64,
+ .ndo_set_mac_address = eth_mac_addr,
};
/*
@@ -174,6 +168,7 @@
dev->tx_queue_len = 0;
dev->type = ARPHRD_LOOPBACK; /* 0x0001*/
dev->flags = IFF_LOOPBACK;
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
dev->hw_features = NETIF_F_ALL_TSO | NETIF_F_UFO;
dev->features = NETIF_F_SG | NETIF_F_FRAGLIST
@@ -181,6 +176,7 @@
| NETIF_F_UFO
| NETIF_F_HW_CSUM
| NETIF_F_RXCSUM
+ | NETIF_F_SCTP_CSUM
| NETIF_F_HIGHDMA
| NETIF_F_LLTX
| NETIF_F_NETNS_LOCAL
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 8433de4..753a8c2 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -506,6 +506,9 @@
static struct lock_class_key macvlan_netdev_xmit_lock_key;
static struct lock_class_key macvlan_netdev_addr_lock_key;
+#define ALWAYS_ON_FEATURES \
+ (NETIF_F_SG | NETIF_F_GEN_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX)
+
#define MACVLAN_FEATURES \
(NETIF_F_SG | NETIF_F_ALL_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_GSO_ROBUST | \
@@ -534,28 +537,21 @@
{
struct macvlan_dev *vlan = netdev_priv(dev);
const struct net_device *lowerdev = vlan->lowerdev;
- int i;
dev->state = (dev->state & ~MACVLAN_STATE_MASK) |
(lowerdev->state & MACVLAN_STATE_MASK);
dev->features = lowerdev->features & MACVLAN_FEATURES;
- dev->features |= NETIF_F_LLTX;
+ dev->features |= ALWAYS_ON_FEATURES;
dev->gso_max_size = lowerdev->gso_max_size;
dev->iflink = lowerdev->ifindex;
dev->hard_header_len = lowerdev->hard_header_len;
macvlan_set_lockdep_class(dev);
- vlan->pcpu_stats = alloc_percpu(struct vlan_pcpu_stats);
+ vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
if (!vlan->pcpu_stats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct vlan_pcpu_stats *mvlstats;
- mvlstats = per_cpu_ptr(vlan->pcpu_stats, i);
- u64_stats_init(&mvlstats->syncp);
- }
-
return 0;
}
@@ -586,13 +582,13 @@
for_each_possible_cpu(i) {
p = per_cpu_ptr(vlan->pcpu_stats, i);
do {
- start = u64_stats_fetch_begin_bh(&p->syncp);
+ start = u64_stats_fetch_begin_irq(&p->syncp);
rx_packets = p->rx_packets;
rx_bytes = p->rx_bytes;
rx_multicast = p->rx_multicast;
tx_packets = p->tx_packets;
tx_bytes = p->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&p->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&p->syncp, start));
stats->rx_packets += rx_packets;
stats->rx_bytes += rx_bytes;
@@ -699,7 +695,7 @@
features = netdev_increment_features(vlan->lowerdev->features,
features,
mask);
- features |= NETIF_F_LLTX;
+ features |= ALWAYS_ON_FEATURES;
return features;
}
@@ -879,14 +875,15 @@
dev->priv_flags |= IFF_MACVLAN;
err = netdev_upper_dev_link(lowerdev, dev);
if (err)
- goto destroy_port;
-
+ goto unregister_netdev;
list_add_tail_rcu(&vlan->list, &port->vlans);
netif_stacked_transfer_operstate(lowerdev, dev);
return 0;
+unregister_netdev:
+ unregister_netdevice(dev);
destroy_port:
port->count -= 1;
if (!port->count)
diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c
index d2bb12b..34924df 100644
--- a/drivers/net/nlmon.c
+++ b/drivers/net/nlmon.c
@@ -47,16 +47,7 @@
static int nlmon_dev_init(struct net_device *dev)
{
- int i;
-
- dev->lstats = alloc_percpu(struct pcpu_lstats);
-
- for_each_possible_cpu(i) {
- struct pcpu_lstats *nlmstats;
- nlmstats = per_cpu_ptr(dev->lstats, i);
- u64_stats_init(&nlmstats->syncp);
- }
-
+ dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
return dev->lstats == NULL ? -ENOMEM : 0;
}
@@ -99,10 +90,10 @@
nl_stats = per_cpu_ptr(dev->lstats, i);
do {
- start = u64_stats_fetch_begin_bh(&nl_stats->syncp);
+ start = u64_stats_fetch_begin_irq(&nl_stats->syncp);
tbytes = nl_stats->bytes;
tpackets = nl_stats->packets;
- } while (u64_stats_fetch_retry_bh(&nl_stats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&nl_stats->syncp, start));
packets += tpackets;
bytes += tbytes;
@@ -145,7 +136,8 @@
dev->ethtool_ops = &nlmon_ethtool_ops;
dev->destructor = free_netdev;
- dev->features = NETIF_F_FRAGLIST | NETIF_F_HIGHDMA;
+ dev->features = NETIF_F_SG | NETIF_F_FRAGLIST |
+ NETIF_F_HIGHDMA | NETIF_F_LLTX;
dev->flags = IFF_NOARP;
/* That's rather a softlimit here, which, of course,
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 9b5d46c..6a17f92 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -71,6 +71,12 @@
---help---
Currently supports the 6348 and 6358 PHYs.
+config BCM7XXX_PHY
+ tristate "Drivers for Broadcom 7xxx SOCs internal PHYs"
+ ---help---
+ Currently supports the BCM7366, BCM7439, BCM7445, and
+ 40nm and 65nm generation of BCM7xxx Set Top Box SoCs.
+
config BCM87XX_PHY
tristate "Driver for Broadcom BCM8706 and BCM8727 PHYs"
help
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 9013dfa..07d2402 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -12,6 +12,7 @@
obj-$(CONFIG_VITESSE_PHY) += vitesse.o
obj-$(CONFIG_BROADCOM_PHY) += broadcom.o
obj-$(CONFIG_BCM63XX_PHY) += bcm63xx.o
+obj-$(CONFIG_BCM7XXX_PHY) += bcm7xxx.o
obj-$(CONFIG_BCM87XX_PHY) += bcm87xx.o
obj-$(CONFIG_ICPLUS_PHY) += icplus.o
obj-$(CONFIG_REALTEK_PHY) += realtek.o
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index bc71947..643464d 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -27,6 +27,9 @@
#define AT803X_MMD_ACCESS_CONTROL 0x0D
#define AT803X_MMD_ACCESS_CONTROL_DATA 0x0E
#define AT803X_FUNC_DATA 0x4003
+#define AT803X_INER 0x0012
+#define AT803X_INER_INIT 0xec00
+#define AT803X_INSR 0x0013
#define AT803X_DEBUG_ADDR 0x1D
#define AT803X_DEBUG_DATA 0x1E
#define AT803X_DEBUG_SYSTEM_MODE_CTRL 0x05
@@ -191,6 +194,31 @@
return 0;
}
+static int at803x_ack_interrupt(struct phy_device *phydev)
+{
+ int err;
+
+ err = phy_read(phydev, AT803X_INSR);
+
+ return (err < 0) ? err : 0;
+}
+
+static int at803x_config_intr(struct phy_device *phydev)
+{
+ int err;
+ int value;
+
+ value = phy_read(phydev, AT803X_INER);
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ err = phy_write(phydev, AT803X_INER,
+ value | AT803X_INER_INIT);
+ else
+ err = phy_write(phydev, AT803X_INER, 0);
+
+ return err;
+}
+
static struct phy_driver at803x_driver[] = {
{
/* ATHEROS 8035 */
@@ -240,6 +268,8 @@
.flags = PHY_HAS_INTERRUPT,
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
+ .ack_interrupt = &at803x_ack_interrupt,
+ .config_intr = &at803x_config_intr,
.driver = {
.owner = THIS_MODULE,
},
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
new file mode 100644
index 0000000..526b94c
--- /dev/null
+++ b/drivers/net/phy/bcm7xxx.c
@@ -0,0 +1,359 @@
+/*
+ * Broadcom BCM7xxx internal transceivers support.
+ *
+ * Copyright (C) 2014, Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/phy.h>
+#include <linux/delay.h>
+#include <linux/bitops.h>
+#include <linux/brcmphy.h>
+
+/* Broadcom BCM7xxx internal PHY registers */
+#define MII_BCM7XXX_CHANNEL_WIDTH 0x2000
+
+/* 40nm only register definitions */
+#define MII_BCM7XXX_100TX_AUX_CTL 0x10
+#define MII_BCM7XXX_100TX_FALSE_CAR 0x13
+#define MII_BCM7XXX_100TX_DISC 0x14
+#define MII_BCM7XXX_AUX_MODE 0x1d
+#define MII_BCM7XX_64CLK_MDIO BIT(12)
+#define MII_BCM7XXX_CORE_BASE1E 0x1e
+#define MII_BCM7XXX_TEST 0x1f
+#define MII_BCM7XXX_SHD_MODE_2 BIT(2)
+
+/* 28nm only register definitions */
+#define MISC_ADDR(base, channel) base, channel
+
+#define DSP_TAP10 MISC_ADDR(0x0a, 0)
+#define PLL_PLLCTRL_1 MISC_ADDR(0x32, 1)
+#define PLL_PLLCTRL_2 MISC_ADDR(0x32, 2)
+#define PLL_PLLCTRL_4 MISC_ADDR(0x33, 0)
+
+#define AFE_RXCONFIG_0 MISC_ADDR(0x38, 0)
+#define AFE_RXCONFIG_1 MISC_ADDR(0x38, 1)
+#define AFE_RX_LP_COUNTER MISC_ADDR(0x38, 3)
+#define AFE_TX_CONFIG MISC_ADDR(0x39, 0)
+#define AFE_HPF_TRIM_OTHERS MISC_ADDR(0x3a, 0)
+
+#define CORE_EXPB0 0xb0
+
+static int bcm7445_config_init(struct phy_device *phydev)
+{
+ int ret;
+ const struct bcm7445_regs {
+ int reg;
+ u16 value;
+ } bcm7445_regs_cfg[] = {
+ /* increases ADC latency by 24ns */
+ { MII_BCM54XX_EXP_SEL, 0x0038 },
+ { MII_BCM54XX_EXP_DATA, 0xAB95 },
+ /* increases internal 1V LDO voltage by 5% */
+ { MII_BCM54XX_EXP_SEL, 0x2038 },
+ { MII_BCM54XX_EXP_DATA, 0xBB22 },
+ /* reduce RX low pass filter corner frequency */
+ { MII_BCM54XX_EXP_SEL, 0x6038 },
+ { MII_BCM54XX_EXP_DATA, 0xFFC5 },
+ /* reduce RX high pass filter corner frequency */
+ { MII_BCM54XX_EXP_SEL, 0x003a },
+ { MII_BCM54XX_EXP_DATA, 0x2002 },
+ };
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(bcm7445_regs_cfg); i++) {
+ ret = phy_write(phydev,
+ bcm7445_regs_cfg[i].reg,
+ bcm7445_regs_cfg[i].value);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static void phy_write_exp(struct phy_device *phydev,
+ u16 reg, u16 value)
+{
+ phy_write(phydev, MII_BCM54XX_EXP_SEL, MII_BCM54XX_EXP_SEL_ER | reg);
+ phy_write(phydev, MII_BCM54XX_EXP_DATA, value);
+}
+
+static void phy_write_misc(struct phy_device *phydev,
+ u16 reg, u16 chl, u16 value)
+{
+ int tmp;
+
+ phy_write(phydev, MII_BCM54XX_AUX_CTL, MII_BCM54XX_AUXCTL_SHDWSEL_MISC);
+
+ tmp = phy_read(phydev, MII_BCM54XX_AUX_CTL);
+ tmp |= MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA;
+ phy_write(phydev, MII_BCM54XX_AUX_CTL, tmp);
+
+ tmp = (chl * MII_BCM7XXX_CHANNEL_WIDTH) | reg;
+ phy_write(phydev, MII_BCM54XX_EXP_SEL, tmp);
+
+ phy_write(phydev, MII_BCM54XX_EXP_DATA, value);
+}
+
+static int bcm7xxx_28nm_afe_config_init(struct phy_device *phydev)
+{
+ /* Increase VCO range to prevent unlocking problem of PLL at low
+ * temp
+ */
+ phy_write_misc(phydev, PLL_PLLCTRL_1, 0x0048);
+
+ /* Change Ki to 011 */
+ phy_write_misc(phydev, PLL_PLLCTRL_2, 0x021b);
+
+ /* Disable loading of TVCO buffer to bandgap, set bandgap trim
+ * to 111
+ */
+ phy_write_misc(phydev, PLL_PLLCTRL_4, 0x0e20);
+
+ /* Adjust bias current trim by -3 */
+ phy_write_misc(phydev, DSP_TAP10, 0x690b);
+
+ /* Switch to CORE_BASE1E */
+ phy_write(phydev, MII_BCM7XXX_CORE_BASE1E, 0xd);
+
+ /* Reset R_CAL/RC_CAL Engine */
+ phy_write_exp(phydev, CORE_EXPB0, 0x0010);
+
+ /* Disable Reset R_CAL/RC_CAL Engine */
+ phy_write_exp(phydev, CORE_EXPB0, 0x0000);
+
+ /* write AFE_RXCONFIG_0 */
+ phy_write_misc(phydev, AFE_RXCONFIG_0, 0xeb19);
+
+ /* write AFE_RXCONFIG_1 */
+ phy_write_misc(phydev, AFE_RXCONFIG_1, 0x9a3f);
+
+ /* write AFE_RX_LP_COUNTER */
+ phy_write_misc(phydev, AFE_RX_LP_COUNTER, 0x7fc0);
+
+ /* write AFE_HPF_TRIM_OTHERS */
+ phy_write_misc(phydev, AFE_HPF_TRIM_OTHERS, 0x000b);
+
+ /* write AFTE_TX_CONFIG */
+ phy_write_misc(phydev, AFE_TX_CONFIG, 0x0800);
+
+ return 0;
+}
+
+static int bcm7xxx_28nm_config_init(struct phy_device *phydev)
+{
+ int ret;
+
+ ret = bcm7445_config_init(phydev);
+ if (ret)
+ return ret;
+
+ return bcm7xxx_28nm_afe_config_init(phydev);
+}
+
+static int phy_set_clr_bits(struct phy_device *dev, int location,
+ int set_mask, int clr_mask)
+{
+ int v, ret;
+
+ v = phy_read(dev, location);
+ if (v < 0)
+ return v;
+
+ v &= ~clr_mask;
+ v |= set_mask;
+
+ ret = phy_write(dev, location, v);
+ if (ret < 0)
+ return ret;
+
+ return v;
+}
+
+static int bcm7xxx_config_init(struct phy_device *phydev)
+{
+ int ret;
+
+ /* Enable 64 clock MDIO */
+ phy_write(phydev, MII_BCM7XXX_AUX_MODE, MII_BCM7XX_64CLK_MDIO);
+ phy_read(phydev, MII_BCM7XXX_AUX_MODE);
+
+ /* Workaround only required for 100Mbits/sec */
+ if (!(phydev->dev_flags & PHY_BRCM_100MBPS_WAR))
+ return 0;
+
+ /* set shadow mode 2 */
+ ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST,
+ MII_BCM7XXX_SHD_MODE_2, MII_BCM7XXX_SHD_MODE_2);
+ if (ret < 0)
+ return ret;
+
+ /* set iddq_clkbias */
+ phy_write(phydev, MII_BCM7XXX_100TX_DISC, 0x0F00);
+ udelay(10);
+
+ /* reset iddq_clkbias */
+ phy_write(phydev, MII_BCM7XXX_100TX_DISC, 0x0C00);
+
+ phy_write(phydev, MII_BCM7XXX_100TX_FALSE_CAR, 0x7555);
+
+ /* reset shadow mode 2 */
+ ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, MII_BCM7XXX_SHD_MODE_2, 0);
+ if (ret < 0)
+ return ret;
+
+ return 0;
+}
+
+/* Workaround for putting the PHY in IDDQ mode, required
+ * for all BCM7XXX PHYs
+ */
+static int bcm7xxx_suspend(struct phy_device *phydev)
+{
+ int ret;
+ const struct bcm7xxx_regs {
+ int reg;
+ u16 value;
+ } bcm7xxx_suspend_cfg[] = {
+ { MII_BCM7XXX_TEST, 0x008b },
+ { MII_BCM7XXX_100TX_AUX_CTL, 0x01c0 },
+ { MII_BCM7XXX_100TX_DISC, 0x7000 },
+ { MII_BCM7XXX_TEST, 0x000f },
+ { MII_BCM7XXX_100TX_AUX_CTL, 0x20d0 },
+ { MII_BCM7XXX_TEST, 0x000b },
+ };
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(bcm7xxx_suspend_cfg); i++) {
+ ret = phy_write(phydev,
+ bcm7xxx_suspend_cfg[i].reg,
+ bcm7xxx_suspend_cfg[i].value);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int bcm7xxx_dummy_config_init(struct phy_device *phydev)
+{
+ return 0;
+}
+
+static struct phy_driver bcm7xxx_driver[] = {
+{
+ .phy_id = PHY_ID_BCM7366,
+ .phy_id_mask = 0xfffffff0,
+ .name = "Broadcom BCM7366",
+ .features = PHY_GBIT_FEATURES |
+ SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+ .flags = PHY_IS_INTERNAL,
+ .config_init = bcm7xxx_28nm_afe_config_init,
+ .config_aneg = genphy_config_aneg,
+ .read_status = genphy_read_status,
+ .suspend = bcm7xxx_suspend,
+ .resume = bcm7xxx_28nm_afe_config_init,
+ .driver = { .owner = THIS_MODULE },
+}, {
+ .phy_id = PHY_ID_BCM7439,
+ .phy_id_mask = 0xfffffff0,
+ .name = "Broadcom BCM7439",
+ .features = PHY_GBIT_FEATURES |
+ SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+ .flags = PHY_IS_INTERNAL,
+ .config_init = bcm7xxx_28nm_afe_config_init,
+ .config_aneg = genphy_config_aneg,
+ .read_status = genphy_read_status,
+ .suspend = bcm7xxx_suspend,
+ .resume = bcm7xxx_28nm_afe_config_init,
+ .driver = { .owner = THIS_MODULE },
+}, {
+ .phy_id = PHY_ID_BCM7445,
+ .phy_id_mask = 0xfffffff0,
+ .name = "Broadcom BCM7445",
+ .features = PHY_GBIT_FEATURES |
+ SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+ .flags = PHY_IS_INTERNAL,
+ .config_init = bcm7xxx_28nm_config_init,
+ .config_aneg = genphy_config_aneg,
+ .read_status = genphy_read_status,
+ .suspend = bcm7xxx_suspend,
+ .resume = bcm7xxx_28nm_config_init,
+ .driver = { .owner = THIS_MODULE },
+}, {
+ .name = "Broadcom BCM7XXX 28nm",
+ .phy_id = PHY_ID_BCM7XXX_28,
+ .phy_id_mask = PHY_BCM_OUI_MASK,
+ .features = PHY_GBIT_FEATURES |
+ SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+ .flags = PHY_IS_INTERNAL,
+ .config_init = bcm7xxx_28nm_config_init,
+ .config_aneg = genphy_config_aneg,
+ .read_status = genphy_read_status,
+ .suspend = bcm7xxx_suspend,
+ .resume = bcm7xxx_28nm_config_init,
+ .driver = { .owner = THIS_MODULE },
+}, {
+ .phy_id = PHY_BCM_OUI_4,
+ .phy_id_mask = 0xffff0000,
+ .name = "Broadcom BCM7XXX 40nm",
+ .features = PHY_GBIT_FEATURES |
+ SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+ .flags = PHY_IS_INTERNAL,
+ .config_init = bcm7xxx_config_init,
+ .config_aneg = genphy_config_aneg,
+ .read_status = genphy_read_status,
+ .suspend = bcm7xxx_suspend,
+ .resume = bcm7xxx_config_init,
+ .driver = { .owner = THIS_MODULE },
+}, {
+ .phy_id = PHY_BCM_OUI_5,
+ .phy_id_mask = 0xffffff00,
+ .name = "Broadcom BCM7XXX 65nm",
+ .features = PHY_BASIC_FEATURES |
+ SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+ .flags = PHY_IS_INTERNAL,
+ .config_init = bcm7xxx_dummy_config_init,
+ .config_aneg = genphy_config_aneg,
+ .read_status = genphy_read_status,
+ .suspend = bcm7xxx_suspend,
+ .resume = bcm7xxx_config_init,
+ .driver = { .owner = THIS_MODULE },
+} };
+
+static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
+ { PHY_ID_BCM7366, 0xfffffff0, },
+ { PHY_ID_BCM7439, 0xfffffff0, },
+ { PHY_ID_BCM7445, 0xfffffff0, },
+ { PHY_ID_BCM7XXX_28, 0xfffffc00 },
+ { PHY_BCM_OUI_4, 0xffff0000 },
+ { PHY_BCM_OUI_5, 0xffffff00 },
+ { }
+};
+
+static int __init bcm7xxx_phy_init(void)
+{
+ return phy_drivers_register(bcm7xxx_driver,
+ ARRAY_SIZE(bcm7xxx_driver));
+}
+
+static void __exit bcm7xxx_phy_exit(void)
+{
+ phy_drivers_unregister(bcm7xxx_driver,
+ ARRAY_SIZE(bcm7xxx_driver));
+}
+
+module_init(bcm7xxx_phy_init);
+module_exit(bcm7xxx_phy_exit);
+
+MODULE_DEVICE_TABLE(mdio, bcm7xxx_tbl);
+
+MODULE_DESCRIPTION("Broadcom BCM7xxx internal PHY driver");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Broadcom Corporation");
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index f8c90ea..34088d6 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -25,58 +25,6 @@
#define BRCM_PHY_REV(phydev) \
((phydev)->drv->phy_id & ~((phydev)->drv->phy_id_mask))
-
-#define MII_BCM54XX_ECR 0x10 /* BCM54xx extended control register */
-#define MII_BCM54XX_ECR_IM 0x1000 /* Interrupt mask */
-#define MII_BCM54XX_ECR_IF 0x0800 /* Interrupt force */
-
-#define MII_BCM54XX_ESR 0x11 /* BCM54xx extended status register */
-#define MII_BCM54XX_ESR_IS 0x1000 /* Interrupt status */
-
-#define MII_BCM54XX_EXP_DATA 0x15 /* Expansion register data */
-#define MII_BCM54XX_EXP_SEL 0x17 /* Expansion register select */
-#define MII_BCM54XX_EXP_SEL_SSD 0x0e00 /* Secondary SerDes select */
-#define MII_BCM54XX_EXP_SEL_ER 0x0f00 /* Expansion register select */
-
-#define MII_BCM54XX_AUX_CTL 0x18 /* Auxiliary control register */
-#define MII_BCM54XX_ISR 0x1a /* BCM54xx interrupt status register */
-#define MII_BCM54XX_IMR 0x1b /* BCM54xx interrupt mask register */
-#define MII_BCM54XX_INT_CRCERR 0x0001 /* CRC error */
-#define MII_BCM54XX_INT_LINK 0x0002 /* Link status changed */
-#define MII_BCM54XX_INT_SPEED 0x0004 /* Link speed change */
-#define MII_BCM54XX_INT_DUPLEX 0x0008 /* Duplex mode changed */
-#define MII_BCM54XX_INT_LRS 0x0010 /* Local receiver status changed */
-#define MII_BCM54XX_INT_RRS 0x0020 /* Remote receiver status changed */
-#define MII_BCM54XX_INT_SSERR 0x0040 /* Scrambler synchronization error */
-#define MII_BCM54XX_INT_UHCD 0x0080 /* Unsupported HCD negotiated */
-#define MII_BCM54XX_INT_NHCD 0x0100 /* No HCD */
-#define MII_BCM54XX_INT_NHCDL 0x0200 /* No HCD link */
-#define MII_BCM54XX_INT_ANPR 0x0400 /* Auto-negotiation page received */
-#define MII_BCM54XX_INT_LC 0x0800 /* All counters below 128 */
-#define MII_BCM54XX_INT_HC 0x1000 /* Counter above 32768 */
-#define MII_BCM54XX_INT_MDIX 0x2000 /* MDIX status change */
-#define MII_BCM54XX_INT_PSERR 0x4000 /* Pair swap error */
-
-#define MII_BCM54XX_SHD 0x1c /* 0x1c shadow registers */
-#define MII_BCM54XX_SHD_WRITE 0x8000
-#define MII_BCM54XX_SHD_VAL(x) ((x & 0x1f) << 10)
-#define MII_BCM54XX_SHD_DATA(x) ((x & 0x3ff) << 0)
-
-/*
- * AUXILIARY CONTROL SHADOW ACCESS REGISTERS. (PHY REG 0x18)
- */
-#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000
-#define MII_BCM54XX_AUXCTL_ACTL_TX_6DB 0x0400
-#define MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA 0x0800
-
-#define MII_BCM54XX_AUXCTL_MISC_WREN 0x8000
-#define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200
-#define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC 0x7000
-#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x0007
-
-#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000
-
-
/*
* Broadcom LED source encodings. These are used in BCM5461, BCM5481,
* BCM5482, and possibly some others.
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 547725f..352c5e4 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -47,6 +47,7 @@
#define CAL_EVENT 7
#define CAL_TRIGGER 7
#define PER_TRIGGER 6
+#define DP83640_N_PINS 12
#define MII_DP83640_MICR 0x11
#define MII_DP83640_MISR 0x12
@@ -173,6 +174,37 @@
MODULE_PARM_DESC(gpio_tab, \
"Which GPIO line to use for which purpose: cal,perout,extts1,...,extts6");
+static void dp83640_gpio_defaults(struct ptp_pin_desc *pd)
+{
+ int i, index;
+
+ for (i = 0; i < DP83640_N_PINS; i++) {
+ snprintf(pd[i].name, sizeof(pd[i].name), "GPIO%d", 1 + i);
+ pd[i].index = i;
+ }
+
+ for (i = 0; i < GPIO_TABLE_SIZE; i++) {
+ if (gpio_tab[i] < 1 || gpio_tab[i] > DP83640_N_PINS) {
+ pr_err("gpio_tab[%d]=%hu out of range", i, gpio_tab[i]);
+ return;
+ }
+ }
+
+ index = gpio_tab[CALIBRATE_GPIO] - 1;
+ pd[index].func = PTP_PF_PHYSYNC;
+ pd[index].chan = 0;
+
+ index = gpio_tab[PEROUT_GPIO] - 1;
+ pd[index].func = PTP_PF_PEROUT;
+ pd[index].chan = 0;
+
+ for (i = EXTTS0_GPIO; i < GPIO_TABLE_SIZE; i++) {
+ index = gpio_tab[i] - 1;
+ pd[index].func = PTP_PF_EXTTS;
+ pd[index].chan = i - EXTTS0_GPIO;
+ }
+}
+
/* a list of clocks and a mutex to protect it */
static LIST_HEAD(phyter_clocks);
static DEFINE_MUTEX(phyter_clocks_lock);
@@ -266,15 +298,22 @@
return ns;
}
-static void periodic_output(struct dp83640_clock *clock,
- struct ptp_clock_request *clkreq, bool on)
+static int periodic_output(struct dp83640_clock *clock,
+ struct ptp_clock_request *clkreq, bool on)
{
struct dp83640_private *dp83640 = clock->chosen;
struct phy_device *phydev = dp83640->phydev;
- u32 sec, nsec, period;
+ u32 sec, nsec, pwidth;
u16 gpio, ptp_trig, trigger, val;
- gpio = on ? gpio_tab[PEROUT_GPIO] : 0;
+ if (on) {
+ gpio = 1 + ptp_find_pin(clock->ptp_clock, PTP_PF_PEROUT, 0);
+ if (gpio < 1)
+ return -EINVAL;
+ } else {
+ gpio = 0;
+ }
+
trigger = PER_TRIGGER;
ptp_trig = TRIG_WR |
@@ -291,13 +330,14 @@
ext_write(0, phydev, PAGE5, PTP_TRIG, ptp_trig);
ext_write(0, phydev, PAGE4, PTP_CTL, val);
mutex_unlock(&clock->extreg_lock);
- return;
+ return 0;
}
sec = clkreq->perout.start.sec;
nsec = clkreq->perout.start.nsec;
- period = clkreq->perout.period.sec * 1000000000UL;
- period += clkreq->perout.period.nsec;
+ pwidth = clkreq->perout.period.sec * 1000000000UL;
+ pwidth += clkreq->perout.period.nsec;
+ pwidth /= 2;
mutex_lock(&clock->extreg_lock);
@@ -310,8 +350,8 @@
ext_write(0, phydev, PAGE4, PTP_TDR, nsec >> 16); /* ns[31:16] */
ext_write(0, phydev, PAGE4, PTP_TDR, sec & 0xffff); /* sec[15:0] */
ext_write(0, phydev, PAGE4, PTP_TDR, sec >> 16); /* sec[31:16] */
- ext_write(0, phydev, PAGE4, PTP_TDR, period & 0xffff); /* ns[15:0] */
- ext_write(0, phydev, PAGE4, PTP_TDR, period >> 16); /* ns[31:16] */
+ ext_write(0, phydev, PAGE4, PTP_TDR, pwidth & 0xffff); /* ns[15:0] */
+ ext_write(0, phydev, PAGE4, PTP_TDR, pwidth >> 16); /* ns[31:16] */
/*enable trigger*/
val &= ~TRIG_LOAD;
@@ -319,6 +359,7 @@
ext_write(0, phydev, PAGE4, PTP_CTL, val);
mutex_unlock(&clock->extreg_lock);
+ return 0;
}
/* ptp clock methods */
@@ -424,20 +465,26 @@
struct dp83640_clock *clock =
container_of(ptp, struct dp83640_clock, caps);
struct phy_device *phydev = clock->chosen->phydev;
- int index;
+ unsigned int index;
u16 evnt, event_num, gpio_num;
switch (rq->type) {
case PTP_CLK_REQ_EXTTS:
index = rq->extts.index;
- if (index < 0 || index >= N_EXT_TS)
+ if (index >= N_EXT_TS)
return -EINVAL;
event_num = EXT_EVENT + index;
evnt = EVNT_WR | (event_num & EVNT_SEL_MASK) << EVNT_SEL_SHIFT;
if (on) {
- gpio_num = gpio_tab[EXTTS0_GPIO + index];
+ gpio_num = 1 + ptp_find_pin(clock->ptp_clock,
+ PTP_PF_EXTTS, index);
+ if (gpio_num < 1)
+ return -EINVAL;
evnt |= (gpio_num & EVNT_GPIO_MASK) << EVNT_GPIO_SHIFT;
- evnt |= EVNT_RISE;
+ if (rq->extts.flags & PTP_FALLING_EDGE)
+ evnt |= EVNT_FALL;
+ else
+ evnt |= EVNT_RISE;
}
ext_write(0, phydev, PAGE5, PTP_EVNT, evnt);
return 0;
@@ -445,8 +492,7 @@
case PTP_CLK_REQ_PEROUT:
if (rq->perout.index != 0)
return -EINVAL;
- periodic_output(clock, rq, on);
- return 0;
+ return periodic_output(clock, rq, on);
default:
break;
@@ -455,6 +501,12 @@
return -EOPNOTSUPP;
}
+static int ptp_dp83640_verify(struct ptp_clock_info *ptp, unsigned int pin,
+ enum ptp_pin_function func, unsigned int chan)
+{
+ return 0;
+}
+
static u8 status_frame_dst[6] = { 0x01, 0x1B, 0x19, 0x00, 0x00, 0x00 };
static u8 status_frame_src[6] = { 0x08, 0x00, 0x17, 0x0B, 0x6B, 0x0F };
@@ -872,6 +924,7 @@
mutex_destroy(&clock->extreg_lock);
mutex_destroy(&clock->clock_lock);
put_device(&clock->bus->dev);
+ kfree(clock->caps.pin_config);
kfree(clock);
}
@@ -891,12 +944,18 @@
clock->caps.n_alarm = 0;
clock->caps.n_ext_ts = N_EXT_TS;
clock->caps.n_per_out = 1;
+ clock->caps.n_pins = DP83640_N_PINS;
clock->caps.pps = 0;
clock->caps.adjfreq = ptp_dp83640_adjfreq;
clock->caps.adjtime = ptp_dp83640_adjtime;
clock->caps.gettime = ptp_dp83640_gettime;
clock->caps.settime = ptp_dp83640_settime;
clock->caps.enable = ptp_dp83640_enable;
+ clock->caps.verify = ptp_dp83640_verify;
+ /*
+ * Convert the module param defaults into a dynamic pin configuration.
+ */
+ dp83640_gpio_defaults(clock->caps.pin_config);
/*
* Get a reference to this bus instance.
*/
@@ -947,6 +1006,13 @@
if (!clock)
goto out;
+ clock->caps.pin_config = kzalloc(sizeof(struct ptp_pin_desc) *
+ DP83640_N_PINS, GFP_KERNEL);
+ if (!clock->caps.pin_config) {
+ kfree(clock);
+ clock = NULL;
+ goto out;
+ }
dp83640_clock_init(clock, bus);
list_add_tail(&phyter_clocks, &clock->list);
out:
@@ -1003,11 +1069,6 @@
} else
list_add_tail(&dp83640->list, &clock->phylist);
- if (clock->chosen && !list_empty(&clock->phylist))
- recalibrate(clock);
- else
- enable_broadcast(dp83640->phydev, clock->page, 1);
-
dp83640_clock_put(clock);
return 0;
@@ -1058,6 +1119,21 @@
kfree(dp83640);
}
+static int dp83640_config_init(struct phy_device *phydev)
+{
+ struct dp83640_private *dp83640 = phydev->priv;
+ struct dp83640_clock *clock = dp83640->clock;
+
+ if (clock->chosen && !list_empty(&clock->phylist))
+ recalibrate(clock);
+ else
+ enable_broadcast(phydev, clock->page, 1);
+
+ enable_status_frames(phydev, true);
+ ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE);
+ return 0;
+}
+
static int dp83640_ack_interrupt(struct phy_device *phydev)
{
int err = phy_read(phydev, MII_DP83640_MISR);
@@ -1195,11 +1271,6 @@
mutex_lock(&dp83640->clock->extreg_lock);
- if (dp83640->hwts_tx_en || dp83640->hwts_rx_en) {
- enable_status_frames(phydev, true);
- ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE);
- }
-
ext_write(0, phydev, PAGE5, PTP_TXCFG0, txcfg0);
ext_write(0, phydev, PAGE5, PTP_RXCFG0, rxcfg0);
@@ -1281,6 +1352,7 @@
}
/* fall through */
case HWTSTAMP_TX_ON:
+ skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
skb_queue_tail(&dp83640->tx_queue, skb);
schedule_work(&dp83640->ts_work);
break;
@@ -1330,6 +1402,7 @@
.flags = PHY_HAS_INTERRUPT,
.probe = dp83640_probe,
.remove = dp83640_remove,
+ .config_init = dp83640_config_init,
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
.ack_interrupt = dp83640_ack_interrupt,
@@ -1353,7 +1426,7 @@
}
MODULE_DESCRIPTION("National Semiconductor DP83640 PHY driver");
-MODULE_AUTHOR("Richard Cochran <richardcochran@gmail.at>");
+MODULE_AUTHOR("Richard Cochran <richardcochran@gmail.com>");
MODULE_LICENSE("GPL");
module_init(dp83640_init);
diff --git a/drivers/net/phy/mdio-sun4i.c b/drivers/net/phy/mdio-sun4i.c
index bb88bc7..15bc7f9 100644
--- a/drivers/net/phy/mdio-sun4i.c
+++ b/drivers/net/phy/mdio-sun4i.c
@@ -90,11 +90,6 @@
return 0;
}
-static int sun4i_mdio_reset(struct mii_bus *bus)
-{
- return 0;
-}
-
static int sun4i_mdio_probe(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
@@ -110,7 +105,6 @@
bus->name = "sun4i_mii_bus";
bus->read = &sun4i_mdio_read;
bus->write = &sun4i_mdio_write;
- bus->reset = &sun4i_mdio_reset;
snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(&pdev->dev));
bus->parent = &pdev->dev;
@@ -170,6 +164,9 @@
}
static const struct of_device_id sun4i_mdio_dt_ids[] = {
+ { .compatible = "allwinner,sun4i-a10-mdio" },
+
+ /* Deprecated */
{ .compatible = "allwinner,sun4i-mdio" },
{ }
};
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 71e4900..76f54b3 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -432,8 +432,28 @@
}
static DEVICE_ATTR_RO(phy_id);
+static ssize_t
+phy_interface_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct phy_device *phydev = to_phy_device(dev);
+
+ return sprintf(buf, "%s\n", phy_modes(phydev->interface));
+}
+static DEVICE_ATTR_RO(phy_interface);
+
+static ssize_t
+phy_has_fixups_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct phy_device *phydev = to_phy_device(dev);
+
+ return sprintf(buf, "%d\n", phydev->has_fixups);
+}
+static DEVICE_ATTR_RO(phy_has_fixups);
+
static struct attribute *mdio_dev_attrs[] = {
&dev_attr_phy_id.attr,
+ &dev_attr_phy_interface.attr,
+ &dev_attr_phy_has_fixups.attr,
NULL,
};
ATTRIBUTE_GROUPS(mdio_dev);
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 5a8993b..5ad971a 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -148,15 +148,52 @@
return rc < 0 ? rc : 0;
}
+static int kszphy_setup_led(struct phy_device *phydev,
+ unsigned int reg, unsigned int shift)
+{
+
+ struct device *dev = &phydev->dev;
+ struct device_node *of_node = dev->of_node;
+ int rc, temp;
+ u32 val;
+
+ if (!of_node && dev->parent->of_node)
+ of_node = dev->parent->of_node;
+
+ if (of_property_read_u32(of_node, "micrel,led-mode", &val))
+ return 0;
+
+ temp = phy_read(phydev, reg);
+ if (temp < 0)
+ return temp;
+
+ temp &= ~(3 << shift);
+ temp |= val << shift;
+ rc = phy_write(phydev, reg, temp);
+
+ return rc < 0 ? rc : 0;
+}
+
static int kszphy_config_init(struct phy_device *phydev)
{
return 0;
}
+static int kszphy_config_init_led8041(struct phy_device *phydev)
+{
+ /* single led control, register 0x1e bits 15..14 */
+ return kszphy_setup_led(phydev, 0x1e, 14);
+}
+
static int ksz8021_config_init(struct phy_device *phydev)
{
- int rc;
const u16 val = KSZPHY_OMSO_B_CAST_OFF | KSZPHY_OMSO_RMII_OVERRIDE;
+ int rc;
+
+ rc = kszphy_setup_led(phydev, 0x1f, 4);
+ if (rc)
+ dev_err(&phydev->dev, "failed to set led mode\n");
+
phy_write(phydev, MII_KSZPHY_OMSO, val);
rc = ksz_config_flags(phydev);
return rc < 0 ? rc : 0;
@@ -166,6 +203,10 @@
{
int rc;
+ rc = kszphy_setup_led(phydev, 0x1f, 4);
+ if (rc)
+ dev_err(&phydev->dev, "failed to set led mode\n");
+
rc = ksz_config_flags(phydev);
return rc < 0 ? rc : 0;
}
@@ -327,7 +368,7 @@
.features = (PHY_BASIC_FEATURES | SUPPORTED_Pause
| SUPPORTED_Asym_Pause),
.flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
- .config_init = kszphy_config_init,
+ .config_init = kszphy_config_init_led8041,
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
.ack_interrupt = kszphy_ack_interrupt,
@@ -342,7 +383,7 @@
.features = PHY_BASIC_FEATURES |
SUPPORTED_Pause | SUPPORTED_Asym_Pause,
.flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
- .config_init = kszphy_config_init,
+ .config_init = kszphy_config_init_led8041,
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
.ack_interrupt = kszphy_ack_interrupt,
@@ -371,7 +412,7 @@
.phy_id_mask = 0x00ffffff,
.features = (PHY_BASIC_FEATURES | SUPPORTED_Pause),
.flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
- .config_init = kszphy_config_init,
+ .config_init = kszphy_config_init_led8041,
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
.ack_interrupt = kszphy_ack_interrupt,
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 19c9eca..1d788f1 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -38,6 +38,26 @@
#include <asm/irq.h>
+static const char *phy_speed_to_str(int speed)
+{
+ switch (speed) {
+ case SPEED_10:
+ return "10Mbps";
+ case SPEED_100:
+ return "100Mbps";
+ case SPEED_1000:
+ return "1Gbps";
+ case SPEED_2500:
+ return "2.5Gbps";
+ case SPEED_10000:
+ return "10Gbps";
+ case SPEED_UNKNOWN:
+ return "Unknown";
+ default:
+ return "Unsupported (update phy.c)";
+ }
+}
+
/**
* phy_print_status - Convenience function to print out the current phy status
* @phydev: the phy_device struct
@@ -45,12 +65,13 @@
void phy_print_status(struct phy_device *phydev)
{
if (phydev->link) {
- pr_info("%s - Link is Up - %d/%s\n",
- dev_name(&phydev->dev),
- phydev->speed,
- DUPLEX_FULL == phydev->duplex ? "Full" : "Half");
+ netdev_info(phydev->attached_dev,
+ "Link is Up - %s/%s - flow control %s\n",
+ phy_speed_to_str(phydev->speed),
+ DUPLEX_FULL == phydev->duplex ? "Full" : "Half",
+ phydev->pause ? "rx/tx" : "off");
} else {
- pr_info("%s - Link is Down\n", dev_name(&phydev->dev));
+ netdev_info(phydev->attached_dev, "Link is Down\n");
}
}
EXPORT_SYMBOL(phy_print_status);
@@ -62,7 +83,7 @@
* If the @phydev driver has an ack_interrupt function, call it to
* ack and clear the phy device's interrupt.
*
- * Returns 0 on success on < 0 on error.
+ * Returns 0 on success or < 0 on error.
*/
static int phy_clear_interrupt(struct phy_device *phydev)
{
@@ -77,7 +98,7 @@
* @phydev: the phy_device struct
* @interrupts: interrupt flags to configure for this @phydev
*
- * Returns 0 on success on < 0 on error.
+ * Returns 0 on success or < 0 on error.
*/
static int phy_config_interrupt(struct phy_device *phydev, u32 interrupts)
{
@@ -93,15 +114,16 @@
* phy_aneg_done - return auto-negotiation status
* @phydev: target phy_device struct
*
- * Description: Reads the status register and returns 0 either if
- * auto-negotiation is incomplete, or if there was an error.
- * Returns BMSR_ANEGCOMPLETE if auto-negotiation is done.
+ * Description: Return the auto-negotiation status from this @phydev
+ * Returns > 0 on success or < 0 on error. 0 means that auto-negotiation
+ * is still pending.
*/
static inline int phy_aneg_done(struct phy_device *phydev)
{
- int retval = phy_read(phydev, MII_BMSR);
+ if (phydev->drv->aneg_done)
+ return phydev->drv->aneg_done(phydev);
- return (retval < 0) ? retval : (retval & BMSR_ANEGCOMPLETE);
+ return genphy_aneg_done(phydev);
}
/* A structure for mapping a particular speed and duplex
@@ -164,9 +186,9 @@
* of that setting. Returns the index of the last setting if
* none of the others match.
*/
-static inline int phy_find_setting(int speed, int duplex)
+static inline unsigned int phy_find_setting(int speed, int duplex)
{
- int idx = 0;
+ unsigned int idx = 0;
while (idx < ARRAY_SIZE(settings) &&
(settings[idx].speed != speed || settings[idx].duplex != duplex))
@@ -185,7 +207,7 @@
* the mask in features. Returns the index of the last setting
* if nothing else matches.
*/
-static inline int phy_find_valid(int idx, u32 features)
+static inline unsigned int phy_find_valid(unsigned int idx, u32 features)
{
while (idx < MAX_NUM_SETTINGS && !(settings[idx].setting & features))
idx++;
@@ -204,7 +226,7 @@
static void phy_sanitize_settings(struct phy_device *phydev)
{
u32 features = phydev->supported;
- int idx;
+ unsigned int idx;
/* Sanitize settings based on PHY capabilities */
if ((features & SUPPORTED_Autoneg) == 0)
@@ -283,7 +305,10 @@
ethtool_cmd_speed_set(cmd, phydev->speed);
cmd->duplex = phydev->duplex;
- cmd->port = PORT_MII;
+ if (phydev->interface == PHY_INTERFACE_MODE_MOCA)
+ cmd->port = PORT_BNC;
+ else
+ cmd->port = PORT_MII;
cmd->phy_address = phydev->addr;
cmd->transceiver = phy_is_internal(phydev) ?
XCVR_INTERNAL : XCVR_EXTERNAL;
@@ -954,7 +979,8 @@
(phydev->interface == PHY_INTERFACE_MODE_RGMII))) {
int eee_lp, eee_cap, eee_adv;
u32 lp, cap, adv;
- int idx, status;
+ int status;
+ unsigned int idx;
/* Read phy status to properly get the right settings */
status = phy_read_status(phydev);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 4b03e63..0ce6066 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -139,6 +139,7 @@
mutex_unlock(&phy_fixup_lock);
return err;
}
+ phydev->has_fixups = true;
}
}
mutex_unlock(&phy_fixup_lock);
@@ -534,16 +535,16 @@
int phy_init_hw(struct phy_device *phydev)
{
- int ret;
+ int ret = 0;
if (!phydev->drv || !phydev->drv->config_init)
return 0;
- ret = phy_write(phydev, MII_BMCR, BMCR_RESET);
- if (ret < 0)
- return ret;
+ if (phydev->drv->soft_reset)
+ ret = phydev->drv->soft_reset(phydev);
+ else
+ ret = genphy_soft_reset(phydev);
- ret = phy_poll_reset(phydev);
if (ret < 0)
return ret;
@@ -683,10 +684,9 @@
int phy_suspend(struct phy_device *phydev)
{
struct phy_driver *phydrv = to_phy_driver(phydev->dev.driver);
- struct ethtool_wolinfo wol;
+ struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
/* If the device has WOL enabled, we cannot suspend the PHY */
- wol.cmd = ETHTOOL_GWOL;
phy_ethtool_get_wol(phydev, &wol);
if (wol.wolopts)
return -EBUSY;
@@ -719,7 +719,7 @@
static int genphy_config_advert(struct phy_device *phydev)
{
u32 advertise;
- int oldadv, adv;
+ int oldadv, adv, bmsr;
int err, changed = 0;
/* Only allow advertising what this PHY supports */
@@ -744,26 +744,36 @@
changed = 1;
}
+ bmsr = phy_read(phydev, MII_BMSR);
+ if (bmsr < 0)
+ return bmsr;
+
+ /* Per 802.3-2008, Section 22.2.4.2.16 Extended status all
+ * 1000Mbits/sec capable PHYs shall have the BMSR_ESTATEN bit set to a
+ * logical 1.
+ */
+ if (!(bmsr & BMSR_ESTATEN))
+ return changed;
+
/* Configure gigabit if it's supported */
+ adv = phy_read(phydev, MII_CTRL1000);
+ if (adv < 0)
+ return adv;
+
+ oldadv = adv;
+ adv &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF);
+
if (phydev->supported & (SUPPORTED_1000baseT_Half |
SUPPORTED_1000baseT_Full)) {
- adv = phy_read(phydev, MII_CTRL1000);
- if (adv < 0)
- return adv;
-
- oldadv = adv;
- adv &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF);
adv |= ethtool_adv_to_mii_ctrl1000_t(advertise);
-
- if (adv != oldadv) {
- err = phy_write(phydev, MII_CTRL1000, adv);
-
- if (err < 0)
- return err;
+ if (adv != oldadv)
changed = 1;
- }
}
+ err = phy_write(phydev, MII_CTRL1000, adv);
+ if (err < 0)
+ return err;
+
return changed;
}
@@ -855,6 +865,22 @@
}
EXPORT_SYMBOL(genphy_config_aneg);
+/**
+ * genphy_aneg_done - return auto-negotiation status
+ * @phydev: target phy_device struct
+ *
+ * Description: Reads the status register and returns 0 either if
+ * auto-negotiation is incomplete, or if there was an error.
+ * Returns BMSR_ANEGCOMPLETE if auto-negotiation is done.
+ */
+int genphy_aneg_done(struct phy_device *phydev)
+{
+ int retval = phy_read(phydev, MII_BMSR);
+
+ return (retval < 0) ? retval : (retval & BMSR_ANEGCOMPLETE);
+}
+EXPORT_SYMBOL(genphy_aneg_done);
+
static int gen10g_config_aneg(struct phy_device *phydev)
{
return 0;
@@ -906,6 +932,8 @@
int err;
int lpa;
int lpagb = 0;
+ int common_adv;
+ int common_adv_gb = 0;
/* Update the link, but return if there was an error */
err = genphy_update_link(phydev);
@@ -927,7 +955,7 @@
phydev->lp_advertising =
mii_stat1000_to_ethtool_lpa_t(lpagb);
- lpagb &= adv << 2;
+ common_adv_gb = lpagb & adv << 2;
}
lpa = phy_read(phydev, MII_LPA);
@@ -940,25 +968,25 @@
if (adv < 0)
return adv;
- lpa &= adv;
+ common_adv = lpa & adv;
phydev->speed = SPEED_10;
phydev->duplex = DUPLEX_HALF;
phydev->pause = 0;
phydev->asym_pause = 0;
- if (lpagb & (LPA_1000FULL | LPA_1000HALF)) {
+ if (common_adv_gb & (LPA_1000FULL | LPA_1000HALF)) {
phydev->speed = SPEED_1000;
- if (lpagb & LPA_1000FULL)
+ if (common_adv_gb & LPA_1000FULL)
phydev->duplex = DUPLEX_FULL;
- } else if (lpa & (LPA_100FULL | LPA_100HALF)) {
+ } else if (common_adv & (LPA_100FULL | LPA_100HALF)) {
phydev->speed = SPEED_100;
- if (lpa & LPA_100FULL)
+ if (common_adv & LPA_100FULL)
phydev->duplex = DUPLEX_FULL;
} else
- if (lpa & LPA_10FULL)
+ if (common_adv & LPA_10FULL)
phydev->duplex = DUPLEX_FULL;
if (phydev->duplex == DUPLEX_FULL) {
@@ -1018,6 +1046,27 @@
return 0;
}
+/**
+ * genphy_soft_reset - software reset the PHY via BMCR_RESET bit
+ * @phydev: target phy_device struct
+ *
+ * Description: Perform a software PHY reset using the standard
+ * BMCR_RESET bit and poll for the reset bit to be cleared.
+ *
+ * Returns: 0 on success, < 0 on failure
+ */
+int genphy_soft_reset(struct phy_device *phydev)
+{
+ int ret;
+
+ ret = phy_write(phydev, MII_BMCR, BMCR_RESET);
+ if (ret < 0)
+ return ret;
+
+ return phy_poll_reset(phydev);
+}
+EXPORT_SYMBOL(genphy_soft_reset);
+
static int genphy_config_init(struct phy_device *phydev)
{
int val;
@@ -1064,6 +1113,12 @@
return 0;
}
+static int gen10g_soft_reset(struct phy_device *phydev)
+{
+ /* Do nothing for now */
+ return 0;
+}
+
static int gen10g_config_init(struct phy_device *phydev)
{
/* Temporarily just say we support everything */
@@ -1238,9 +1293,11 @@
.phy_id = 0xffffffff,
.phy_id_mask = 0xffffffff,
.name = "Generic PHY",
+ .soft_reset = genphy_soft_reset,
.config_init = genphy_config_init,
.features = 0,
.config_aneg = genphy_config_aneg,
+ .aneg_done = genphy_aneg_done,
.read_status = genphy_read_status,
.suspend = genphy_suspend,
.resume = genphy_resume,
@@ -1249,6 +1306,7 @@
.phy_id = 0xffffffff,
.phy_id_mask = 0xffffffff,
.name = "Generic 10G PHY",
+ .soft_reset = gen10g_soft_reset,
.config_init = gen10g_config_init,
.features = 0,
.config_aneg = gen10g_config_aneg,
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 72ff14b..e3923eb 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -143,9 +143,8 @@
struct sk_buff_head mrq; /* MP: receive reconstruction queue */
#endif /* CONFIG_PPP_MULTILINK */
#ifdef CONFIG_PPP_FILTER
- struct sock_filter *pass_filter; /* filter for packets to pass */
- struct sock_filter *active_filter;/* filter for pkts to reset idle */
- unsigned pass_len, active_len;
+ struct sk_filter *pass_filter; /* filter for packets to pass */
+ struct sk_filter *active_filter;/* filter for pkts to reset idle */
#endif /* CONFIG_PPP_FILTER */
struct net *ppp_net; /* the net we belong to */
struct ppp_link_stats stats64; /* 64 bit network stats */
@@ -755,28 +754,42 @@
case PPPIOCSPASS:
{
struct sock_filter *code;
+
err = get_filter(argp, &code);
if (err >= 0) {
+ struct sock_fprog fprog = {
+ .len = err,
+ .filter = code,
+ };
+
ppp_lock(ppp);
- kfree(ppp->pass_filter);
- ppp->pass_filter = code;
- ppp->pass_len = err;
+ if (ppp->pass_filter)
+ sk_unattached_filter_destroy(ppp->pass_filter);
+ err = sk_unattached_filter_create(&ppp->pass_filter,
+ &fprog);
+ kfree(code);
ppp_unlock(ppp);
- err = 0;
}
break;
}
case PPPIOCSACTIVE:
{
struct sock_filter *code;
+
err = get_filter(argp, &code);
if (err >= 0) {
+ struct sock_fprog fprog = {
+ .len = err,
+ .filter = code,
+ };
+
ppp_lock(ppp);
- kfree(ppp->active_filter);
- ppp->active_filter = code;
- ppp->active_len = err;
+ if (ppp->active_filter)
+ sk_unattached_filter_destroy(ppp->active_filter);
+ err = sk_unattached_filter_create(&ppp->active_filter,
+ &fprog);
+ kfree(code);
ppp_unlock(ppp);
- err = 0;
}
break;
}
@@ -1184,7 +1197,7 @@
a four-byte PPP header on each packet */
*skb_push(skb, 2) = 1;
if (ppp->pass_filter &&
- sk_run_filter(skb, ppp->pass_filter) == 0) {
+ SK_RUN_FILTER(ppp->pass_filter, skb) == 0) {
if (ppp->debug & 1)
netdev_printk(KERN_DEBUG, ppp->dev,
"PPP: outbound frame "
@@ -1194,7 +1207,7 @@
}
/* if this packet passes the active filter, record the time */
if (!(ppp->active_filter &&
- sk_run_filter(skb, ppp->active_filter) == 0))
+ SK_RUN_FILTER(ppp->active_filter, skb) == 0))
ppp->last_xmit = jiffies;
skb_pull(skb, 2);
#else
@@ -1818,7 +1831,7 @@
*skb_push(skb, 2) = 0;
if (ppp->pass_filter &&
- sk_run_filter(skb, ppp->pass_filter) == 0) {
+ SK_RUN_FILTER(ppp->pass_filter, skb) == 0) {
if (ppp->debug & 1)
netdev_printk(KERN_DEBUG, ppp->dev,
"PPP: inbound frame "
@@ -1827,7 +1840,7 @@
return;
}
if (!(ppp->active_filter &&
- sk_run_filter(skb, ppp->active_filter) == 0))
+ SK_RUN_FILTER(ppp->active_filter, skb) == 0))
ppp->last_recv = jiffies;
__skb_pull(skb, 2);
} else
@@ -2672,6 +2685,10 @@
ppp->minseq = -1;
skb_queue_head_init(&ppp->mrq);
#endif /* CONFIG_PPP_MULTILINK */
+#ifdef CONFIG_PPP_FILTER
+ ppp->pass_filter = NULL;
+ ppp->active_filter = NULL;
+#endif /* CONFIG_PPP_FILTER */
/*
* drum roll: don't forget to set
@@ -2802,10 +2819,15 @@
skb_queue_purge(&ppp->mrq);
#endif /* CONFIG_PPP_MULTILINK */
#ifdef CONFIG_PPP_FILTER
- kfree(ppp->pass_filter);
- ppp->pass_filter = NULL;
- kfree(ppp->active_filter);
- ppp->active_filter = NULL;
+ if (ppp->pass_filter) {
+ sk_unattached_filter_destroy(ppp->pass_filter);
+ ppp->pass_filter = NULL;
+ }
+
+ if (ppp->active_filter) {
+ sk_unattached_filter_destroy(ppp->active_filter);
+ ppp->active_filter = NULL;
+ }
#endif /* CONFIG_PPP_FILTER */
kfree_skb(ppp->xmit_pending);
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 2840742..33008c1 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1031,8 +1031,7 @@
}
#ifdef CONFIG_NET_POLL_CONTROLLER
-static int team_port_enable_netpoll(struct team *team, struct team_port *port,
- gfp_t gfp)
+static int team_port_enable_netpoll(struct team *team, struct team_port *port)
{
struct netpoll *np;
int err;
@@ -1040,11 +1039,11 @@
if (!team->dev->npinfo)
return 0;
- np = kzalloc(sizeof(*np), gfp);
+ np = kzalloc(sizeof(*np), GFP_KERNEL);
if (!np)
return -ENOMEM;
- err = __netpoll_setup(np, port->dev, gfp);
+ err = __netpoll_setup(np, port->dev);
if (err) {
kfree(np);
return err;
@@ -1067,8 +1066,7 @@
kfree(np);
}
#else
-static int team_port_enable_netpoll(struct team *team, struct team_port *port,
- gfp_t gfp)
+static int team_port_enable_netpoll(struct team *team, struct team_port *port)
{
return 0;
}
@@ -1156,7 +1154,7 @@
goto err_vids_add;
}
- err = team_port_enable_netpoll(team, port, GFP_KERNEL);
+ err = team_port_enable_netpoll(team, port);
if (err) {
netdev_err(dev, "Failed to enable netpoll on device %s\n",
portname);
@@ -1540,16 +1538,10 @@
mutex_init(&team->lock);
team_set_no_mode(team);
- team->pcpu_stats = alloc_percpu(struct team_pcpu_stats);
+ team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats);
if (!team->pcpu_stats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct team_pcpu_stats *team_stats;
- team_stats = per_cpu_ptr(team->pcpu_stats, i);
- u64_stats_init(&team_stats->syncp);
- }
-
for (i = 0; i < TEAM_PORT_HASHENTRIES; i++)
INIT_HLIST_HEAD(&team->en_port_hlist[i]);
INIT_LIST_HEAD(&team->port_list);
@@ -1648,7 +1640,7 @@
}
static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv, select_queue_fallback_t fallback)
{
/*
* This helper function exists to help dev_pick_tx get the correct
@@ -1767,13 +1759,13 @@
for_each_possible_cpu(i) {
p = per_cpu_ptr(team->pcpu_stats, i);
do {
- start = u64_stats_fetch_begin_bh(&p->syncp);
+ start = u64_stats_fetch_begin_irq(&p->syncp);
rx_packets = p->rx_packets;
rx_bytes = p->rx_bytes;
rx_multicast = p->rx_multicast;
tx_packets = p->tx_packets;
tx_bytes = p->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&p->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&p->syncp, start));
stats->rx_packets += rx_packets;
stats->rx_bytes += rx_bytes;
@@ -1856,7 +1848,7 @@
}
static int team_netpoll_setup(struct net_device *dev,
- struct netpoll_info *npifo, gfp_t gfp)
+ struct netpoll_info *npifo)
{
struct team *team = netdev_priv(dev);
struct team_port *port;
@@ -1864,7 +1856,7 @@
mutex_lock(&team->lock);
list_for_each_entry(port, &team->port_list, list) {
- err = team_port_enable_netpoll(team, port, gfp);
+ err = team_port_enable_netpoll(team, port);
if (err) {
__team_netpoll_cleanup(team);
break;
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index d671fc3..dbde341 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -432,9 +432,9 @@
struct lb_stats tmp;
do {
- start = u64_stats_fetch_begin_bh(syncp);
+ start = u64_stats_fetch_begin_irq(syncp);
tmp.tx_bytes = cpu_stats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(syncp, start));
+ } while (u64_stats_fetch_retry_irq(syncp, start));
acc_stats->tx_bytes += tmp.tx_bytes;
}
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 44c4db8..ee328ba 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -366,7 +366,7 @@
* hope the rxq no. may help here.
*/
static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv, select_queue_fallback_t fallback)
{
struct tun_struct *tun = netdev_priv(dev);
struct tun_flow_entry *e;
@@ -452,7 +452,7 @@
--tun->numqueues;
if (clean) {
- rcu_assign_pointer(tfile->tun, NULL);
+ RCU_INIT_POINTER(tfile->tun, NULL);
sock_put(&tfile->sk);
} else
tun_disable_queue(tun, tfile);
@@ -499,12 +499,12 @@
tfile = rtnl_dereference(tun->tfiles[i]);
BUG_ON(!tfile);
wake_up_all(&tfile->wq.wait);
- rcu_assign_pointer(tfile->tun, NULL);
+ RCU_INIT_POINTER(tfile->tun, NULL);
--tun->numqueues;
}
list_for_each_entry(tfile, &tun->disabled, next) {
wake_up_all(&tfile->wq.wait);
- rcu_assign_pointer(tfile->tun, NULL);
+ RCU_INIT_POINTER(tfile->tun, NULL);
}
BUG_ON(tun->numqueues != 0);
@@ -1686,7 +1686,9 @@
TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
dev->features = dev->hw_features;
- dev->vlan_features = dev->features;
+ dev->vlan_features = dev->features &
+ ~(NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX);
INIT_LIST_HEAD(&tun->disabled);
err = tun_attach(tun, file, false);
@@ -2192,7 +2194,7 @@
&tun_proto);
if (!tfile)
return -ENOMEM;
- rcu_assign_pointer(tfile->tun, NULL);
+ RCU_INIT_POINTER(tfile->tun, NULL);
tfile->net = get_net(current->nsproxy->net_ns);
tfile->flags = 0;
tfile->ifindex = 0;
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 6b638a0..7e7269f 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -292,6 +292,21 @@
This option adds support for CoreChip-sz SR9700 based USB 1.1
10/100 Ethernet adapters.
+config USB_NET_SR9800
+ tristate "CoreChip-sz SR9800 based USB 2.0 10/100 ethernet devices"
+ depends on USB_USBNET
+ select CRC32
+ ---help---
+ Say Y if you want to use one of the following 100Mbps USB Ethernet
+ device based on the CoreChip-sz SR9800 chip.
+
+ This driver makes the adapter appear as a normal Ethernet interface,
+ typically on eth0, if it is the only ethernet device, or perhaps on
+ eth1, if you have a PCI or ISA ethernet card installed.
+
+ To compile this driver as a module, choose M here: the
+ module will be called sr9800.
+
config USB_NET_SMSC75XX
tristate "SMSC LAN75XX based USB 2.0 gigabit ethernet devices"
depends on USB_USBNET
diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile
index b17b5e8..e2797f1 100644
--- a/drivers/net/usb/Makefile
+++ b/drivers/net/usb/Makefile
@@ -11,10 +11,11 @@
obj-$(CONFIG_USB_NET_AX8817X) += asix.o
asix-y := asix_devices.o asix_common.o ax88172a.o
obj-$(CONFIG_USB_NET_AX88179_178A) += ax88179_178a.o
-obj-$(CONFIG_USB_NET_CDCETHER) += cdc_ether.o r815x.o
+obj-$(CONFIG_USB_NET_CDCETHER) += cdc_ether.o
obj-$(CONFIG_USB_NET_CDC_EEM) += cdc_eem.o
obj-$(CONFIG_USB_NET_DM9601) += dm9601.o
obj-$(CONFIG_USB_NET_SR9700) += sr9700.o
+obj-$(CONFIG_USB_NET_SR9800) += sr9800.o
obj-$(CONFIG_USB_NET_SMSC75XX) += smsc75xx.o
obj-$(CONFIG_USB_NET_SMSC95XX) += smsc95xx.o
obj-$(CONFIG_USB_NET_GL620A) += gl620a.o
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 9765a7d..5d19409 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -917,7 +917,8 @@
.status = asix_status,
.link_reset = ax88178_link_reset,
.reset = ax88178_reset,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
+ FLAG_MULTI_PACKET,
.rx_fixup = asix_rx_fixup_common,
.tx_fixup = asix_tx_fixup,
};
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index d6f64da..054e59c 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1029,20 +1029,12 @@
dev->mii.phy_id = 0x03;
dev->mii.supports_gmii = 1;
- if (usb_device_no_sg_constraint(dev->udev))
- dev->can_dma_sg = 1;
-
dev->net->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_RXCSUM;
dev->net->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_RXCSUM;
- if (dev->can_dma_sg) {
- dev->net->features |= NETIF_F_SG | NETIF_F_TSO;
- dev->net->hw_features |= NETIF_F_SG | NETIF_F_TSO;
- }
-
/* Enable checksum offload */
*tmp = AX_RXCOE_IP | AX_RXCOE_TCP | AX_RXCOE_UDP |
AX_RXCOE_TCPV6 | AX_RXCOE_UDPV6;
@@ -1118,6 +1110,10 @@
u16 hdr_off;
u32 *pkt_hdr;
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
skb_trim(skb, skb->len - 4);
memcpy(&rx_hdr, skb_tail_pointer(skb), 4);
le32_to_cpus(&rx_hdr);
@@ -1391,6 +1387,19 @@
.tx_fixup = ax88179_tx_fixup,
};
+static const struct driver_info dlink_dub1312_info = {
+ .description = "D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter",
+ .bind = ax88179_bind,
+ .unbind = ax88179_unbind,
+ .status = ax88179_status,
+ .link_reset = ax88179_link_reset,
+ .reset = ax88179_reset,
+ .stop = ax88179_stop,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
+ .rx_fixup = ax88179_rx_fixup,
+ .tx_fixup = ax88179_tx_fixup,
+};
+
static const struct driver_info sitecom_info = {
.description = "Sitecom USB 3.0 to Gigabit Adapter",
.bind = ax88179_bind,
@@ -1417,6 +1426,19 @@
.tx_fixup = ax88179_tx_fixup,
};
+static const struct driver_info lenovo_info = {
+ .description = "Lenovo OneLinkDock Gigabit LAN",
+ .bind = ax88179_bind,
+ .unbind = ax88179_unbind,
+ .status = ax88179_status,
+ .link_reset = ax88179_link_reset,
+ .reset = ax88179_reset,
+ .stop = ax88179_stop,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
+ .rx_fixup = ax88179_rx_fixup,
+ .tx_fixup = ax88179_tx_fixup,
+};
+
static const struct usb_device_id products[] = {
{
/* ASIX AX88179 10/100/1000 */
@@ -1427,6 +1449,10 @@
USB_DEVICE(0x0b95, 0x178a),
.driver_info = (unsigned long)&ax88178a_info,
}, {
+ /* D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter */
+ USB_DEVICE(0x2001, 0x4a00),
+ .driver_info = (unsigned long)&dlink_dub1312_info,
+}, {
/* Sitecom USB 3.0 to Gigabit Adapter */
USB_DEVICE(0x0df6, 0x0072),
.driver_info = (unsigned long)&sitecom_info,
@@ -1434,6 +1460,10 @@
/* Samsung USB Ethernet Adapter */
USB_DEVICE(0x04e8, 0xa100),
.driver_info = (unsigned long)&samsung_info,
+}, {
+ /* Lenovo OneLinkDock Gigabit LAN */
+ USB_DEVICE(0x17ef, 0x304b),
+ .driver_info = (unsigned long)&lenovo_info,
},
{ },
};
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 42e1769..bd363b2 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -652,6 +652,13 @@
.driver_info = 0,
},
+/* Samsung USB Ethernet Adapters */
+{
+ USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, 0xa101, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+ .driver_info = 0,
+},
+
/* WHITELIST!!!
*
* CDC Ether uses two interfaces, not necessarily consecutive.
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index dbff290..549dbac 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -68,12 +68,12 @@
static int cdc_ncm_setup(struct usbnet *dev)
{
struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
- struct usb_cdc_ncm_ntb_parameters ncm_parm;
u32 val;
u8 flags;
u8 iface_no;
int err;
int eth_hlen;
+ u16 mbim_mtu;
u16 ntb_fmt_supported;
__le16 max_datagram_size;
@@ -82,22 +82,22 @@
err = usbnet_read_cmd(dev, USB_CDC_GET_NTB_PARAMETERS,
USB_TYPE_CLASS | USB_DIR_IN
|USB_RECIP_INTERFACE,
- 0, iface_no, &ncm_parm,
- sizeof(ncm_parm));
+ 0, iface_no, &ctx->ncm_parm,
+ sizeof(ctx->ncm_parm));
if (err < 0) {
dev_err(&dev->intf->dev, "failed GET_NTB_PARAMETERS\n");
return err; /* GET_NTB_PARAMETERS is required */
}
/* read correct set of parameters according to device mode */
- ctx->rx_max = le32_to_cpu(ncm_parm.dwNtbInMaxSize);
- ctx->tx_max = le32_to_cpu(ncm_parm.dwNtbOutMaxSize);
- ctx->tx_remainder = le16_to_cpu(ncm_parm.wNdpOutPayloadRemainder);
- ctx->tx_modulus = le16_to_cpu(ncm_parm.wNdpOutDivisor);
- ctx->tx_ndp_modulus = le16_to_cpu(ncm_parm.wNdpOutAlignment);
+ ctx->rx_max = le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize);
+ ctx->tx_max = le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize);
+ ctx->tx_remainder = le16_to_cpu(ctx->ncm_parm.wNdpOutPayloadRemainder);
+ ctx->tx_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutDivisor);
+ ctx->tx_ndp_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutAlignment);
/* devices prior to NCM Errata shall set this field to zero */
- ctx->tx_max_datagrams = le16_to_cpu(ncm_parm.wNtbOutMaxDatagrams);
- ntb_fmt_supported = le16_to_cpu(ncm_parm.bmNtbFormatsSupported);
+ ctx->tx_max_datagrams = le16_to_cpu(ctx->ncm_parm.wNtbOutMaxDatagrams);
+ ntb_fmt_supported = le16_to_cpu(ctx->ncm_parm.bmNtbFormatsSupported);
/* there are some minor differences in NCM and MBIM defaults */
if (cdc_ncm_comm_intf_is_mbim(ctx->control->cur_altsetting)) {
@@ -146,7 +146,7 @@
}
/* inform device about NTB input size changes */
- if (ctx->rx_max != le32_to_cpu(ncm_parm.dwNtbInMaxSize)) {
+ if (ctx->rx_max != le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize)) {
__le32 dwNtbInMaxSize = cpu_to_le32(ctx->rx_max);
err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_INPUT_SIZE,
@@ -162,14 +162,6 @@
dev_dbg(&dev->intf->dev, "Using default maximum transmit length=%d\n",
CDC_NCM_NTB_MAX_SIZE_TX);
ctx->tx_max = CDC_NCM_NTB_MAX_SIZE_TX;
-
- /* Adding a pad byte here simplifies the handling in
- * cdc_ncm_fill_tx_frame, by making tx_max always
- * represent the real skb max size.
- */
- if (ctx->tx_max % usb_maxpacket(dev->udev, dev->out, 1) == 0)
- ctx->tx_max++;
-
}
/*
@@ -261,6 +253,14 @@
/* set MTU to max supported by the device if necessary */
if (dev->net->mtu > ctx->max_datagram_size - eth_hlen)
dev->net->mtu = ctx->max_datagram_size - eth_hlen;
+
+ /* do not exceed operater preferred MTU */
+ if (ctx->mbim_extended_desc) {
+ mbim_mtu = le16_to_cpu(ctx->mbim_extended_desc->wMTU);
+ if (mbim_mtu != 0 && mbim_mtu < dev->net->mtu)
+ dev->net->mtu = mbim_mtu;
+ }
+
return 0;
}
@@ -399,6 +399,14 @@
ctx->mbim_desc = (const struct usb_cdc_mbim_desc *)buf;
break;
+ case USB_CDC_MBIM_EXTENDED_TYPE:
+ if (buf[0] < sizeof(*(ctx->mbim_extended_desc)))
+ break;
+
+ ctx->mbim_extended_desc =
+ (const struct usb_cdc_mbim_extended_desc *)buf;
+ break;
+
default:
break;
}
@@ -439,6 +447,10 @@
goto error2;
}
+ /* initialize data interface */
+ if (cdc_ncm_setup(dev))
+ goto error2;
+
/* configure data interface */
temp = usb_set_interface(dev->udev, iface_no, data_altsetting);
if (temp) {
@@ -453,12 +465,6 @@
goto error2;
}
- /* initialize data interface */
- if (cdc_ncm_setup(dev)) {
- dev_dbg(&intf->dev, "cdc_ncm_setup() failed\n");
- goto error2;
- }
-
usb_set_intfdata(ctx->data, dev);
usb_set_intfdata(ctx->control, dev);
@@ -475,6 +481,15 @@
dev->hard_mtu = ctx->tx_max;
dev->rx_urb_size = ctx->rx_max;
+ /* cdc_ncm_setup will override dwNtbOutMaxSize if it is
+ * outside the sane range. Adding a pad byte here if necessary
+ * simplifies the handling in cdc_ncm_fill_tx_frame, making
+ * tx_max always represent the real skb max size.
+ */
+ if (ctx->tx_max != le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) &&
+ ctx->tx_max % usb_maxpacket(dev->udev, dev->out, 1) == 0)
+ ctx->tx_max++;
+
return 0;
error2:
diff --git a/drivers/net/usb/gl620a.c b/drivers/net/usb/gl620a.c
index e4a8a93..1cc24e6 100644
--- a/drivers/net/usb/gl620a.c
+++ b/drivers/net/usb/gl620a.c
@@ -84,6 +84,10 @@
u32 size;
u32 count;
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
header = (struct gl_header *) skb->data;
// get the packet count of the received skb
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 1a48234..660bd5e 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -1201,16 +1201,18 @@
struct hso_serial *serial = urb->context;
int status = urb->status;
+ D4("\n--- Got serial_read_bulk callback %02x ---", status);
+
/* sanity check */
if (!serial) {
D1("serial == NULL");
return;
- } else if (status) {
+ }
+ if (status) {
handle_usb_error(status, __func__, serial->parent);
return;
}
- D4("\n--- Got serial_read_bulk callback %02x ---", status);
D1("Actual length = %d\n", urb->actual_length);
DUMP1(urb->transfer_buffer, urb->actual_length);
@@ -1218,25 +1220,13 @@
if (serial->port.count == 0)
return;
- if (status == 0) {
- if (serial->parent->port_spec & HSO_INFO_CRC_BUG)
- fix_crc_bug(urb, serial->in_endp->wMaxPacketSize);
- /* Valid data, handle RX data */
- spin_lock(&serial->serial_lock);
- serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 1;
- put_rxbuf_data_and_resubmit_bulk_urb(serial);
- spin_unlock(&serial->serial_lock);
- } else if (status == -ENOENT || status == -ECONNRESET) {
- /* Unlinked - check for throttled port. */
- D2("Port %d, successfully unlinked urb", serial->minor);
- spin_lock(&serial->serial_lock);
- serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 0;
- hso_resubmit_rx_bulk_urb(serial, urb);
- spin_unlock(&serial->serial_lock);
- } else {
- D2("Port %d, status = %d for read urb", serial->minor, status);
- return;
- }
+ if (serial->parent->port_spec & HSO_INFO_CRC_BUG)
+ fix_crc_bug(urb, serial->in_endp->wMaxPacketSize);
+ /* Valid data, handle RX data */
+ spin_lock(&serial->serial_lock);
+ serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 1;
+ put_rxbuf_data_and_resubmit_bulk_urb(serial);
+ spin_unlock(&serial->serial_lock);
}
/*
diff --git a/drivers/net/usb/lg-vl600.c b/drivers/net/usb/lg-vl600.c
index acfcc32..8f37efd 100644
--- a/drivers/net/usb/lg-vl600.c
+++ b/drivers/net/usb/lg-vl600.c
@@ -210,7 +210,7 @@
* (0x86dd) so Linux can understand it.
*/
if ((buf->data[sizeof(*ethhdr)] & 0xf0) == 0x60)
- ethhdr->h_proto = __constant_htons(ETH_P_IPV6);
+ ethhdr->h_proto = htons(ETH_P_IPV6);
}
if (count) {
diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c
index a305a7b..82d844a 100644
--- a/drivers/net/usb/mcs7830.c
+++ b/drivers/net/usb/mcs7830.c
@@ -526,8 +526,9 @@
{
u8 status;
- if (skb->len == 0) {
- dev_err(&dev->udev->dev, "unexpected empty rx frame\n");
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len) {
+ dev_err(&dev->udev->dev, "unexpected tiny rx frame\n");
return 0;
}
diff --git a/drivers/net/usb/net1080.c b/drivers/net/usb/net1080.c
index 0a85d92..4cbdb13 100644
--- a/drivers/net/usb/net1080.c
+++ b/drivers/net/usb/net1080.c
@@ -364,6 +364,10 @@
struct nc_trailer *trailer;
u16 hdr_len, packet_len;
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
if (!(skb->len & 0x01)) {
netdev_dbg(dev->net, "rx framesize %d range %d..%d mtu %d\n",
skb->len, dev->net->hard_header_len, dev->hard_mtu,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 23bdd5b..313cb6c 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -80,10 +80,10 @@
{
__be16 proto;
- /* usbnet rx_complete guarantees that skb->len is at least
- * hard_header_len, so we can inspect the dest address without
- * checking skb->len
- */
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
switch (skb->data[0] & 0xf0) {
case 0x40:
proto = htons(ETH_P_IP);
@@ -712,6 +712,7 @@
{QMI_FIXED_INTF(0x19d2, 0x1255, 3)},
{QMI_FIXED_INTF(0x19d2, 0x1255, 4)},
{QMI_FIXED_INTF(0x19d2, 0x1256, 4)},
+ {QMI_FIXED_INTF(0x19d2, 0x1270, 5)}, /* ZTE MF667 */
{QMI_FIXED_INTF(0x19d2, 0x1401, 2)},
{QMI_FIXED_INTF(0x19d2, 0x1402, 2)}, /* ZTE MF60 */
{QMI_FIXED_INTF(0x19d2, 0x1424, 2)},
@@ -723,6 +724,7 @@
{QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */
{QMI_FIXED_INTF(0x1199, 0x68a2, 19)}, /* Sierra Wireless MC7710 in QMI mode */
{QMI_FIXED_INTF(0x1199, 0x901c, 8)}, /* Sierra Wireless EM7700 */
+ {QMI_FIXED_INTF(0x1199, 0x9051, 8)}, /* Netgear AirCard 340U */
{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
{QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */
{QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */
@@ -730,6 +732,7 @@
{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */
{QMI_FIXED_INTF(0x0b3c, 0xc005, 6)}, /* Olivetti Olicard 200 */
{QMI_FIXED_INTF(0x1e2d, 0x0060, 4)}, /* Cinterion PLxx */
+ {QMI_FIXED_INTF(0x1e2d, 0x0053, 4)}, /* Cinterion PHxx,PXxx */
/* 4. Gobi 1000 devices */
{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index e8fac73..18e12a3 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -21,9 +21,10 @@
#include <linux/list.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
+#include <net/ip6_checksum.h>
/* Version Information */
-#define DRIVER_VERSION "v1.04.0 (2014/01/15)"
+#define DRIVER_VERSION "v1.06.0 (2014/03/03)"
#define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
#define DRIVER_DESC "Realtek RTL8152/RTL8153 Based USB Ethernet Adapters"
#define MODULENAME "r8152"
@@ -59,9 +60,11 @@
#define PLA_TCR0 0xe610
#define PLA_TCR1 0xe612
#define PLA_TXFIFO_CTRL 0xe618
-#define PLA_RSTTELLY 0xe800
+#define PLA_RSTTALLY 0xe800
#define PLA_CR 0xe813
#define PLA_CRWECR 0xe81c
+#define PLA_CONFIG12 0xe81e /* CONFIG1, CONFIG2 */
+#define PLA_CONFIG34 0xe820 /* CONFIG3, CONFIG4 */
#define PLA_CONFIG5 0xe822
#define PLA_PHY_PWR 0xe84c
#define PLA_OOB_CTRL 0xe84f
@@ -69,7 +72,7 @@
#define PLA_MISC_0 0xe858
#define PLA_MISC_1 0xe85a
#define PLA_OCP_GPHY_BASE 0xe86c
-#define PLA_TELLYCNT 0xe890
+#define PLA_TALLYCNT 0xe890
#define PLA_SFF_STS_7 0xe8de
#define PLA_PHYSTATUS 0xe908
#define PLA_BP_BA 0xfc26
@@ -177,6 +180,9 @@
/* PLA_TCR1 */
#define VERSION_MASK 0x7cf0
+/* PLA_RSTTALLY */
+#define TALLY_RESET 0x0001
+
/* PLA_CR */
#define CR_RST 0x10
#define CR_RE 0x08
@@ -216,7 +222,14 @@
/* PAL_BDC_CR */
#define ALDPS_PROXY_MODE 0x0001
+/* PLA_CONFIG34 */
+#define LINK_ON_WAKE_EN 0x0010
+#define LINK_OFF_WAKE_EN 0x0008
+
/* PLA_CONFIG5 */
+#define BWF_EN 0x0040
+#define MWF_EN 0x0020
+#define UWF_EN 0x0010
#define LAN_WAKE_EN 0x0002
/* PLA_LED_FEATURE */
@@ -436,6 +449,9 @@
RTL8152_SET_RX_MODE,
WORK_ENABLE,
RTL8152_LINK_CHG,
+ SELECTIVE_SUSPEND,
+ PHY_RESET,
+ SCHEDULE_TASKLET,
};
/* Define these values to match your device */
@@ -452,11 +468,37 @@
#define REALTEK_USB_DEVICE(vend, prod) \
USB_DEVICE_INTERFACE_CLASS(vend, prod, USB_CLASS_VENDOR_SPEC)
+struct tally_counter {
+ __le64 tx_packets;
+ __le64 rx_packets;
+ __le64 tx_errors;
+ __le32 rx_errors;
+ __le16 rx_missed;
+ __le16 align_errors;
+ __le32 tx_one_collision;
+ __le32 tx_multi_collision;
+ __le64 rx_unicast;
+ __le64 rx_broadcast;
+ __le32 rx_multicast;
+ __le16 tx_aborted;
+ __le16 tx_underun;
+};
+
struct rx_desc {
__le32 opts1;
#define RX_LEN_MASK 0x7fff
+
__le32 opts2;
+#define RD_UDP_CS (1 << 23)
+#define RD_TCP_CS (1 << 22)
+#define RD_IPV6_CS (1 << 20)
+#define RD_IPV4_CS (1 << 19)
+
__le32 opts3;
+#define IPF (1 << 23) /* IP checksum fail */
+#define UDPF (1 << 22) /* UDP checksum fail */
+#define TCPF (1 << 21) /* TCP checksum fail */
+
__le32 opts4;
__le32 opts5;
__le32 opts6;
@@ -466,13 +508,21 @@
__le32 opts1;
#define TX_FS (1 << 31) /* First segment of a packet */
#define TX_LS (1 << 30) /* Final segment of a packet */
-#define TX_LEN_MASK 0x3ffff
+#define GTSENDV4 (1 << 28)
+#define GTSENDV6 (1 << 27)
+#define GTTCPHO_SHIFT 18
+#define GTTCPHO_MAX 0x7fU
+#define TX_LEN_MAX 0x3ffffU
__le32 opts2;
#define UDP_CS (1 << 31) /* Calculate UDP/IP checksum */
#define TCP_CS (1 << 30) /* Calculate TCP/IP checksum */
#define IPV4_CS (1 << 29) /* Calculate IPv4 checksum */
#define IPV6_CS (1 << 28) /* Calculate IPv6 checksum */
+#define MSS_SHIFT 17
+#define MSS_MAX 0x7ffU
+#define TCPHO_SHIFT 17
+#define TCPHO_MAX 0x7ffU
};
struct r8152;
@@ -514,11 +564,13 @@
void (*init)(struct r8152 *);
int (*enable)(struct r8152 *);
void (*disable)(struct r8152 *);
+ void (*up)(struct r8152 *);
void (*down)(struct r8152 *);
void (*unload)(struct r8152 *);
} rtl_ops;
int intr_interval;
+ u32 saved_wolopts;
u32 msg_enable;
u32 tx_qlen;
u16 ocp_base;
@@ -537,12 +589,21 @@
RTL_VER_MAX
};
+enum tx_csum_stat {
+ TX_CSUM_SUCCESS = 0,
+ TX_CSUM_TSO,
+ TX_CSUM_NONE
+};
+
/* Maximum number of multicast addresses to filter (vs. Rx-all-multicast).
* The RTL chips use a 64 element hash table based on the Ethernet CRC.
*/
static const int multicast_filter_limit = 32;
static unsigned int rx_buf_sz = 16384;
+#define RTL_LIMITED_TSO_SIZE (rx_buf_sz - sizeof(struct tx_desc) - \
+ VLAN_ETH_HLEN - VLAN_HLEN)
+
static
int get_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data)
{
@@ -580,6 +641,7 @@
value, index, tmp, size, 500);
kfree(tmp);
+
return ret;
}
@@ -865,11 +927,21 @@
static int read_mii_word(struct net_device *netdev, int phy_id, int reg)
{
struct r8152 *tp = netdev_priv(netdev);
+ int ret;
if (phy_id != R8152_PHY_ID)
return -EINVAL;
- return r8152_mdio_read(tp, reg);
+ ret = usb_autopm_get_interface(tp->intf);
+ if (ret < 0)
+ goto out;
+
+ ret = r8152_mdio_read(tp, reg);
+
+ usb_autopm_put_interface(tp->intf);
+
+out:
+ return ret;
}
static
@@ -880,7 +952,12 @@
if (phy_id != R8152_PHY_ID)
return;
+ if (usb_autopm_get_interface(tp->intf) < 0)
+ return;
+
r8152_mdio_write(tp, reg, val);
+
+ usb_autopm_put_interface(tp->intf);
}
static
@@ -889,11 +966,26 @@
static inline void set_ethernet_addr(struct r8152 *tp)
{
struct net_device *dev = tp->netdev;
+ int ret;
u8 node_id[8] = {0};
- if (pla_ocp_read(tp, PLA_IDR, sizeof(node_id), node_id) < 0)
+ if (tp->version == RTL_VER_01)
+ ret = pla_ocp_read(tp, PLA_IDR, sizeof(node_id), node_id);
+ else
+ ret = pla_ocp_read(tp, PLA_BACKUP, sizeof(node_id), node_id);
+
+ if (ret < 0) {
netif_notice(tp, probe, dev, "inet addr fail\n");
- else {
+ } else {
+ if (tp->version != RTL_VER_01) {
+ ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR,
+ CRWECR_CONFIG);
+ pla_ocp_write(tp, PLA_IDR, BYTE_EN_SIX_BYTES,
+ sizeof(node_id), node_id);
+ ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR,
+ CRWECR_NORAML);
+ }
+
memcpy(dev->dev_addr, node_id, dev->addr_len);
memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);
}
@@ -916,15 +1008,9 @@
return 0;
}
-static struct net_device_stats *rtl8152_get_stats(struct net_device *dev)
-{
- return &dev->stats;
-}
-
static void read_bulk_callback(struct urb *urb)
{
struct net_device *netdev;
- unsigned long flags;
int status = urb->status;
struct rx_agg *agg;
struct r8152 *tp;
@@ -951,14 +1037,16 @@
if (!netif_carrier_ok(netdev))
return;
+ usb_mark_last_busy(tp->udev);
+
switch (status) {
case 0:
if (urb->actual_length < ETH_ZLEN)
break;
- spin_lock_irqsave(&tp->rx_lock, flags);
+ spin_lock(&tp->rx_lock);
list_add_tail(&agg->list, &tp->rx_done);
- spin_unlock_irqrestore(&tp->rx_lock, flags);
+ spin_unlock(&tp->rx_lock);
tasklet_schedule(&tp->tl);
return;
case -ESHUTDOWN:
@@ -981,9 +1069,9 @@
if (result == -ENODEV) {
netif_device_detach(tp->netdev);
} else if (result) {
- spin_lock_irqsave(&tp->rx_lock, flags);
+ spin_lock(&tp->rx_lock);
list_add_tail(&agg->list, &tp->rx_done);
- spin_unlock_irqrestore(&tp->rx_lock, flags);
+ spin_unlock(&tp->rx_lock);
tasklet_schedule(&tp->tl);
}
}
@@ -991,7 +1079,7 @@
static void write_bulk_callback(struct urb *urb)
{
struct net_device_stats *stats;
- unsigned long flags;
+ struct net_device *netdev;
struct tx_agg *agg;
struct r8152 *tp;
int status = urb->status;
@@ -1004,21 +1092,24 @@
if (!tp)
return;
- stats = rtl8152_get_stats(tp->netdev);
+ netdev = tp->netdev;
+ stats = &netdev->stats;
if (status) {
if (net_ratelimit())
- netdev_warn(tp->netdev, "Tx status %d\n", status);
+ netdev_warn(netdev, "Tx status %d\n", status);
stats->tx_errors += agg->skb_num;
} else {
stats->tx_packets += agg->skb_num;
stats->tx_bytes += agg->skb_len;
}
- spin_lock_irqsave(&tp->tx_lock, flags);
+ spin_lock(&tp->tx_lock);
list_add_tail(&agg->list, &tp->tx_free);
- spin_unlock_irqrestore(&tp->tx_lock, flags);
+ spin_unlock(&tp->tx_lock);
- if (!netif_carrier_ok(tp->netdev))
+ usb_autopm_put_interface_async(tp->intf);
+
+ if (!netif_carrier_ok(netdev))
return;
if (!test_bit(WORK_ENABLE, &tp->flags))
@@ -1223,6 +1314,9 @@
struct tx_agg *agg = NULL;
unsigned long flags;
+ if (list_empty(&tp->tx_free))
+ return NULL;
+
spin_lock_irqsave(&tp->tx_lock, flags);
if (!list_empty(&tp->tx_free)) {
struct list_head *cursor;
@@ -1236,24 +1330,138 @@
return agg;
}
-static void
-r8152_tx_csum(struct r8152 *tp, struct tx_desc *desc, struct sk_buff *skb)
+static inline __be16 get_protocol(struct sk_buff *skb)
{
- memset(desc, 0, sizeof(*desc));
+ __be16 protocol;
- desc->opts1 = cpu_to_le32((skb->len & TX_LEN_MASK) | TX_FS | TX_LS);
+ if (skb->protocol == htons(ETH_P_8021Q))
+ protocol = vlan_eth_hdr(skb)->h_vlan_encapsulated_proto;
+ else
+ protocol = skb->protocol;
- if (skb->ip_summed == CHECKSUM_PARTIAL) {
- __be16 protocol;
+ return protocol;
+}
+
+/*
+ * r8152_csum_workaround()
+ * The hw limites the value the transport offset. When the offset is out of the
+ * range, calculate the checksum by sw.
+ */
+static void r8152_csum_workaround(struct r8152 *tp, struct sk_buff *skb,
+ struct sk_buff_head *list)
+{
+ if (skb_shinfo(skb)->gso_size) {
+ netdev_features_t features = tp->netdev->features;
+ struct sk_buff_head seg_list;
+ struct sk_buff *segs, *nskb;
+
+ features &= ~(NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_TSO);
+ segs = skb_gso_segment(skb, features);
+ if (IS_ERR(segs) || !segs)
+ goto drop;
+
+ __skb_queue_head_init(&seg_list);
+
+ do {
+ nskb = segs;
+ segs = segs->next;
+ nskb->next = NULL;
+ __skb_queue_tail(&seg_list, nskb);
+ } while (segs);
+
+ skb_queue_splice(&seg_list, list);
+ dev_kfree_skb(skb);
+ } else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ if (skb_checksum_help(skb) < 0)
+ goto drop;
+
+ __skb_queue_head(list, skb);
+ } else {
+ struct net_device_stats *stats;
+
+drop:
+ stats = &tp->netdev->stats;
+ stats->tx_dropped++;
+ dev_kfree_skb(skb);
+ }
+}
+
+/*
+ * msdn_giant_send_check()
+ * According to the document of microsoft, the TCP Pseudo Header excludes the
+ * packet length for IPv6 TCP large packets.
+ */
+static int msdn_giant_send_check(struct sk_buff *skb)
+{
+ const struct ipv6hdr *ipv6h;
+ struct tcphdr *th;
+ int ret;
+
+ ret = skb_cow_head(skb, 0);
+ if (ret)
+ return ret;
+
+ ipv6h = ipv6_hdr(skb);
+ th = tcp_hdr(skb);
+
+ th->check = 0;
+ th->check = ~tcp_v6_check(0, &ipv6h->saddr, &ipv6h->daddr, 0);
+
+ return ret;
+}
+
+static int r8152_tx_csum(struct r8152 *tp, struct tx_desc *desc,
+ struct sk_buff *skb, u32 len, u32 transport_offset)
+{
+ u32 mss = skb_shinfo(skb)->gso_size;
+ u32 opts1, opts2 = 0;
+ int ret = TX_CSUM_SUCCESS;
+
+ WARN_ON_ONCE(len > TX_LEN_MAX);
+
+ opts1 = len | TX_FS | TX_LS;
+
+ if (mss) {
+ if (transport_offset > GTTCPHO_MAX) {
+ netif_warn(tp, tx_err, tp->netdev,
+ "Invalid transport offset 0x%x for TSO\n",
+ transport_offset);
+ ret = TX_CSUM_TSO;
+ goto unavailable;
+ }
+
+ switch (get_protocol(skb)) {
+ case htons(ETH_P_IP):
+ opts1 |= GTSENDV4;
+ break;
+
+ case htons(ETH_P_IPV6):
+ if (msdn_giant_send_check(skb)) {
+ ret = TX_CSUM_TSO;
+ goto unavailable;
+ }
+ opts1 |= GTSENDV6;
+ break;
+
+ default:
+ WARN_ON_ONCE(1);
+ break;
+ }
+
+ opts1 |= transport_offset << GTTCPHO_SHIFT;
+ opts2 |= min(mss, MSS_MAX) << MSS_SHIFT;
+ } else if (skb->ip_summed == CHECKSUM_PARTIAL) {
u8 ip_protocol;
- u32 opts2 = 0;
- if (skb->protocol == htons(ETH_P_8021Q))
- protocol = vlan_eth_hdr(skb)->h_vlan_encapsulated_proto;
- else
- protocol = skb->protocol;
+ if (transport_offset > TCPHO_MAX) {
+ netif_warn(tp, tx_err, tp->netdev,
+ "Invalid transport offset 0x%x\n",
+ transport_offset);
+ ret = TX_CSUM_NONE;
+ goto unavailable;
+ }
- switch (protocol) {
+ switch (get_protocol(skb)) {
case htons(ETH_P_IP):
opts2 |= IPV4_CS;
ip_protocol = ip_hdr(skb)->protocol;
@@ -1269,24 +1477,34 @@
break;
}
- if (ip_protocol == IPPROTO_TCP) {
+ if (ip_protocol == IPPROTO_TCP)
opts2 |= TCP_CS;
- opts2 |= (skb_transport_offset(skb) & 0x7fff) << 17;
- } else if (ip_protocol == IPPROTO_UDP) {
+ else if (ip_protocol == IPPROTO_UDP)
opts2 |= UDP_CS;
- } else {
+ else
WARN_ON_ONCE(1);
- }
- desc->opts2 = cpu_to_le32(opts2);
+ opts2 |= transport_offset << TCPHO_SHIFT;
}
+
+ desc->opts2 = cpu_to_le32(opts2);
+ desc->opts1 = cpu_to_le32(opts1);
+
+unavailable:
+ return ret;
}
static int r8152_tx_agg_fill(struct r8152 *tp, struct tx_agg *agg)
{
- int remain;
+ struct sk_buff_head skb_head, *tx_queue = &tp->tx_queue;
+ int remain, ret;
u8 *tx_data;
+ __skb_queue_head_init(&skb_head);
+ spin_lock(&tx_queue->lock);
+ skb_queue_splice_init(tx_queue, &skb_head);
+ spin_unlock(&tx_queue->lock);
+
tx_data = agg->head;
agg->skb_num = agg->skb_len = 0;
remain = rx_buf_sz;
@@ -1295,32 +1513,56 @@
struct tx_desc *tx_desc;
struct sk_buff *skb;
unsigned int len;
+ u32 offset;
- skb = skb_dequeue(&tp->tx_queue);
+ skb = __skb_dequeue(&skb_head);
if (!skb)
break;
- remain -= sizeof(*tx_desc);
- len = skb->len;
- if (remain < len) {
- skb_queue_head(&tp->tx_queue, skb);
+ len = skb->len + sizeof(*tx_desc);
+
+ if (len > remain) {
+ __skb_queue_head(&skb_head, skb);
break;
}
tx_data = tx_agg_align(tx_data);
tx_desc = (struct tx_desc *)tx_data;
+
+ offset = (u32)skb_transport_offset(skb);
+
+ if (r8152_tx_csum(tp, tx_desc, skb, skb->len, offset)) {
+ r8152_csum_workaround(tp, skb, &skb_head);
+ continue;
+ }
+
tx_data += sizeof(*tx_desc);
- r8152_tx_csum(tp, tx_desc, skb);
- memcpy(tx_data, skb->data, len);
- agg->skb_num++;
- agg->skb_len += len;
- dev_kfree_skb_any(skb);
+ len = skb->len;
+ if (skb_copy_bits(skb, 0, tx_data, len) < 0) {
+ struct net_device_stats *stats = &tp->netdev->stats;
+
+ stats->tx_dropped++;
+ dev_kfree_skb_any(skb);
+ tx_data -= sizeof(*tx_desc);
+ continue;
+ }
tx_data += len;
+ agg->skb_len += len;
+ agg->skb_num++;
+
+ dev_kfree_skb_any(skb);
+
remain = rx_buf_sz - (int)(tx_agg_align(tx_data) - agg->head);
}
+ if (!skb_queue_empty(&skb_head)) {
+ spin_lock(&tx_queue->lock);
+ skb_queue_splice(&skb_head, tx_queue);
+ spin_unlock(&tx_queue->lock);
+ }
+
netif_tx_lock(tp->netdev);
if (netif_queue_stopped(tp->netdev) &&
@@ -1329,20 +1571,67 @@
netif_tx_unlock(tp->netdev);
+ ret = usb_autopm_get_interface_async(tp->intf);
+ if (ret < 0)
+ goto out_tx_fill;
+
usb_fill_bulk_urb(agg->urb, tp->udev, usb_sndbulkpipe(tp->udev, 2),
agg->head, (int)(tx_data - (u8 *)agg->head),
(usb_complete_t)write_bulk_callback, agg);
- return usb_submit_urb(agg->urb, GFP_ATOMIC);
+ ret = usb_submit_urb(agg->urb, GFP_ATOMIC);
+ if (ret < 0)
+ usb_autopm_put_interface_async(tp->intf);
+
+out_tx_fill:
+ return ret;
+}
+
+static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc)
+{
+ u8 checksum = CHECKSUM_NONE;
+ u32 opts2, opts3;
+
+ if (tp->version == RTL_VER_01)
+ goto return_result;
+
+ opts2 = le32_to_cpu(rx_desc->opts2);
+ opts3 = le32_to_cpu(rx_desc->opts3);
+
+ if (opts2 & RD_IPV4_CS) {
+ if (opts3 & IPF)
+ checksum = CHECKSUM_NONE;
+ else if ((opts2 & RD_UDP_CS) && (opts3 & UDPF))
+ checksum = CHECKSUM_NONE;
+ else if ((opts2 & RD_TCP_CS) && (opts3 & TCPF))
+ checksum = CHECKSUM_NONE;
+ else
+ checksum = CHECKSUM_UNNECESSARY;
+ } else if (RD_IPV6_CS) {
+ if ((opts2 & RD_UDP_CS) && !(opts3 & UDPF))
+ checksum = CHECKSUM_UNNECESSARY;
+ else if ((opts2 & RD_TCP_CS) && !(opts3 & TCPF))
+ checksum = CHECKSUM_UNNECESSARY;
+ }
+
+return_result:
+ return checksum;
}
static void rx_bottom(struct r8152 *tp)
{
unsigned long flags;
- struct list_head *cursor, *next;
+ struct list_head *cursor, *next, rx_queue;
+ if (list_empty(&tp->rx_done))
+ return;
+
+ INIT_LIST_HEAD(&rx_queue);
spin_lock_irqsave(&tp->rx_lock, flags);
- list_for_each_safe(cursor, next, &tp->rx_done) {
+ list_splice_init(&tp->rx_done, &rx_queue);
+ spin_unlock_irqrestore(&tp->rx_lock, flags);
+
+ list_for_each_safe(cursor, next, &rx_queue) {
struct rx_desc *rx_desc;
struct rx_agg *agg;
int len_used = 0;
@@ -1351,7 +1640,6 @@
int ret;
list_del_init(cursor);
- spin_unlock_irqrestore(&tp->rx_lock, flags);
agg = list_entry(cursor, struct rx_agg, list);
urb = agg->urb;
@@ -1364,7 +1652,7 @@
while (urb->actual_length > len_used) {
struct net_device *netdev = tp->netdev;
- struct net_device_stats *stats;
+ struct net_device_stats *stats = &netdev->stats;
unsigned int pkt_len;
struct sk_buff *skb;
@@ -1376,23 +1664,24 @@
if (urb->actual_length < len_used)
break;
- stats = rtl8152_get_stats(netdev);
-
pkt_len -= CRC_SIZE;
rx_data += sizeof(struct rx_desc);
skb = netdev_alloc_skb_ip_align(netdev, pkt_len);
if (!skb) {
stats->rx_dropped++;
- break;
+ goto find_next_rx;
}
+
+ skb->ip_summed = r8152_rx_csum(tp, rx_desc);
memcpy(skb->data, rx_data, pkt_len);
skb_put(skb, pkt_len);
skb->protocol = eth_type_trans(skb, netdev);
- netif_rx(skb);
+ netif_receive_skb(skb);
stats->rx_packets++;
stats->rx_bytes += pkt_len;
+find_next_rx:
rx_data = rx_agg_align(rx_data + pkt_len + CRC_SIZE);
rx_desc = (struct rx_desc *)rx_data;
len_used = (int)(rx_data - (u8 *)agg->head);
@@ -1401,13 +1690,13 @@
submit:
ret = r8152_submit_rx(tp, agg, GFP_ATOMIC);
- spin_lock_irqsave(&tp->rx_lock, flags);
if (ret && ret != -ENODEV) {
- list_add_tail(&agg->list, next);
+ spin_lock_irqsave(&tp->rx_lock, flags);
+ list_add_tail(&agg->list, &tp->rx_done);
+ spin_unlock_irqrestore(&tp->rx_lock, flags);
tasklet_schedule(&tp->tl);
}
}
- spin_unlock_irqrestore(&tp->rx_lock, flags);
}
static void tx_bottom(struct r8152 *tp)
@@ -1426,19 +1715,18 @@
res = r8152_tx_agg_fill(tp, agg);
if (res) {
- struct net_device_stats *stats;
- struct net_device *netdev;
- unsigned long flags;
-
- netdev = tp->netdev;
- stats = rtl8152_get_stats(netdev);
+ struct net_device *netdev = tp->netdev;
if (res == -ENODEV) {
netif_device_detach(netdev);
} else {
+ struct net_device_stats *stats = &netdev->stats;
+ unsigned long flags;
+
netif_warn(tp, tx_err, netdev,
"failed tx_urb %d\n", res);
stats->tx_dropped += agg->skb_num;
+
spin_lock_irqsave(&tp->tx_lock, flags);
list_add_tail(&agg->list, &tp->tx_free);
spin_unlock_irqrestore(&tp->tx_lock, flags);
@@ -1478,6 +1766,26 @@
return usb_submit_urb(agg->urb, mem_flags);
}
+static void rtl_drop_queued_tx(struct r8152 *tp)
+{
+ struct net_device_stats *stats = &tp->netdev->stats;
+ struct sk_buff_head skb_head, *tx_queue = &tp->tx_queue;
+ struct sk_buff *skb;
+
+ if (skb_queue_empty(tx_queue))
+ return;
+
+ __skb_queue_head_init(&skb_head);
+ spin_lock_bh(&tx_queue->lock);
+ skb_queue_splice_init(tx_queue, &skb_head);
+ spin_unlock_bh(&tx_queue->lock);
+
+ while ((skb = __skb_dequeue(&skb_head))) {
+ dev_kfree_skb(skb);
+ stats->tx_dropped++;
+ }
+}
+
static void rtl8152_tx_timeout(struct net_device *netdev)
{
struct r8152 *tp = netdev_priv(netdev);
@@ -1541,7 +1849,7 @@
}
static netdev_tx_t rtl8152_start_xmit(struct sk_buff *skb,
- struct net_device *netdev)
+ struct net_device *netdev)
{
struct r8152 *tp = netdev_priv(netdev);
@@ -1549,13 +1857,17 @@
skb_queue_tail(&tp->tx_queue, skb);
- if (list_empty(&tp->tx_free) &&
- skb_queue_len(&tp->tx_queue) > tp->tx_qlen)
+ if (!list_empty(&tp->tx_free)) {
+ if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
+ set_bit(SCHEDULE_TASKLET, &tp->flags);
+ schedule_delayed_work(&tp->schedule, 0);
+ } else {
+ usb_mark_last_busy(tp->udev);
+ tasklet_schedule(&tp->tl);
+ }
+ } else if (skb_queue_len(&tp->tx_queue) > tp->tx_qlen)
netif_stop_queue(netdev);
- if (!list_empty(&tp->tx_free))
- tasklet_schedule(&tp->tl);
-
return NETDEV_TX_OK;
}
@@ -1613,6 +1925,18 @@
}
}
+static void rxdy_gated_en(struct r8152 *tp, bool enable)
+{
+ u32 ocp_data;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1);
+ if (enable)
+ ocp_data |= RXDY_GATED_EN;
+ else
+ ocp_data &= ~RXDY_GATED_EN;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data);
+}
+
static int rtl_enable(struct r8152 *tp)
{
u32 ocp_data;
@@ -1624,9 +1948,7 @@
ocp_data |= CR_RE | CR_TE;
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CR, ocp_data);
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1);
- ocp_data &= ~RXDY_GATED_EN;
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data);
+ rxdy_gated_en(tp, false);
INIT_LIST_HEAD(&tp->rx_done);
ret = 0;
@@ -1681,8 +2003,6 @@
static void rtl8152_disable(struct r8152 *tp)
{
- struct net_device_stats *stats = rtl8152_get_stats(tp->netdev);
- struct sk_buff *skb;
u32 ocp_data;
int i;
@@ -1690,17 +2010,12 @@
ocp_data &= ~RCR_ACPT_ALL;
ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data);
- while ((skb = skb_dequeue(&tp->tx_queue))) {
- dev_kfree_skb(skb);
- stats->tx_dropped++;
- }
+ rtl_drop_queued_tx(tp);
for (i = 0; i < RTL8152_MAX_TX; i++)
usb_kill_urb(tp->tx_info[i].urb);
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1);
- ocp_data |= RXDY_GATED_EN;
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data);
+ rxdy_gated_en(tp, true);
for (i = 0; i < 1000; i++) {
ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
@@ -1721,18 +2036,209 @@
rtl8152_nic_reset(tp);
}
+static void r8152_power_cut_en(struct r8152 *tp, bool enable)
+{
+ u32 ocp_data;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_UPS_CTRL);
+ if (enable)
+ ocp_data |= POWER_CUT;
+ else
+ ocp_data &= ~POWER_CUT;
+ ocp_write_word(tp, MCU_TYPE_USB, USB_UPS_CTRL, ocp_data);
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_PM_CTRL_STATUS);
+ ocp_data &= ~RESUME_INDICATE;
+ ocp_write_word(tp, MCU_TYPE_USB, USB_PM_CTRL_STATUS, ocp_data);
+}
+
+#define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST)
+
+static u32 __rtl_get_wol(struct r8152 *tp)
+{
+ u32 ocp_data;
+ u32 wolopts = 0;
+
+ ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG5);
+ if (!(ocp_data & LAN_WAKE_EN))
+ return 0;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG34);
+ if (ocp_data & LINK_ON_WAKE_EN)
+ wolopts |= WAKE_PHY;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG5);
+ if (ocp_data & UWF_EN)
+ wolopts |= WAKE_UCAST;
+ if (ocp_data & BWF_EN)
+ wolopts |= WAKE_BCAST;
+ if (ocp_data & MWF_EN)
+ wolopts |= WAKE_MCAST;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL);
+ if (ocp_data & MAGIC_EN)
+ wolopts |= WAKE_MAGIC;
+
+ return wolopts;
+}
+
+static void __rtl_set_wol(struct r8152 *tp, u32 wolopts)
+{
+ u32 ocp_data;
+
+ ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG34);
+ ocp_data &= ~LINK_ON_WAKE_EN;
+ if (wolopts & WAKE_PHY)
+ ocp_data |= LINK_ON_WAKE_EN;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG34, ocp_data);
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG5);
+ ocp_data &= ~(UWF_EN | BWF_EN | MWF_EN | LAN_WAKE_EN);
+ if (wolopts & WAKE_UCAST)
+ ocp_data |= UWF_EN;
+ if (wolopts & WAKE_BCAST)
+ ocp_data |= BWF_EN;
+ if (wolopts & WAKE_MCAST)
+ ocp_data |= MWF_EN;
+ if (wolopts & WAKE_ANY)
+ ocp_data |= LAN_WAKE_EN;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG5, ocp_data);
+
+ ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL);
+ ocp_data &= ~MAGIC_EN;
+ if (wolopts & WAKE_MAGIC)
+ ocp_data |= MAGIC_EN;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL, ocp_data);
+
+ if (wolopts & WAKE_ANY)
+ device_set_wakeup_enable(&tp->udev->dev, true);
+ else
+ device_set_wakeup_enable(&tp->udev->dev, false);
+}
+
+static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
+{
+ if (enable) {
+ u32 ocp_data;
+
+ __rtl_set_wol(tp, WAKE_ANY);
+
+ ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG34);
+ ocp_data |= LINK_OFF_WAKE_EN;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG34, ocp_data);
+
+ ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
+ } else {
+ __rtl_set_wol(tp, tp->saved_wolopts);
+ }
+}
+
+static void rtl_phy_reset(struct r8152 *tp)
+{
+ u16 data;
+ int i;
+
+ clear_bit(PHY_RESET, &tp->flags);
+
+ data = r8152_mdio_read(tp, MII_BMCR);
+
+ /* don't reset again before the previous one complete */
+ if (data & BMCR_RESET)
+ return;
+
+ data |= BMCR_RESET;
+ r8152_mdio_write(tp, MII_BMCR, data);
+
+ for (i = 0; i < 50; i++) {
+ msleep(20);
+ if ((r8152_mdio_read(tp, MII_BMCR) & BMCR_RESET) == 0)
+ break;
+ }
+}
+
+static void rtl_clear_bp(struct r8152 *tp)
+{
+ ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_0, 0);
+ ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_2, 0);
+ ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_4, 0);
+ ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_6, 0);
+ ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_0, 0);
+ ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_2, 0);
+ ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_4, 0);
+ ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_6, 0);
+ mdelay(3);
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_BP_BA, 0);
+ ocp_write_word(tp, MCU_TYPE_USB, USB_BP_BA, 0);
+}
+
+static void r8153_clear_bp(struct r8152 *tp)
+{
+ ocp_write_byte(tp, MCU_TYPE_PLA, PLA_BP_EN, 0);
+ ocp_write_byte(tp, MCU_TYPE_USB, USB_BP_EN, 0);
+ rtl_clear_bp(tp);
+}
+
+static void r8153_teredo_off(struct r8152 *tp)
+{
+ u32 ocp_data;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG);
+ ocp_data &= ~(TEREDO_SEL | TEREDO_RS_EVENT_MASK | OOB_TEREDO_EN);
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG, ocp_data);
+
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_WDT6_CTRL, WDT6_SET_MODE);
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_REALWOW_TIMER, 0);
+ ocp_write_dword(tp, MCU_TYPE_PLA, PLA_TEREDO_TIMER, 0);
+}
+
+static void r8152b_disable_aldps(struct r8152 *tp)
+{
+ ocp_reg_write(tp, OCP_ALDPS_CONFIG, ENPDNPS | LINKENA | DIS_SDSAVE);
+ msleep(20);
+}
+
+static inline void r8152b_enable_aldps(struct r8152 *tp)
+{
+ ocp_reg_write(tp, OCP_ALDPS_CONFIG, ENPWRSAVE | ENPDNPS |
+ LINKENA | DIS_SDSAVE);
+}
+
+static void r8152b_hw_phy_cfg(struct r8152 *tp)
+{
+ u16 data;
+
+ data = r8152_mdio_read(tp, MII_BMCR);
+ if (data & BMCR_PDOWN) {
+ data &= ~BMCR_PDOWN;
+ r8152_mdio_write(tp, MII_BMCR, data);
+ }
+
+ r8152b_disable_aldps(tp);
+
+ rtl_clear_bp(tp);
+
+ r8152b_enable_aldps(tp);
+ set_bit(PHY_RESET, &tp->flags);
+}
+
static void r8152b_exit_oob(struct r8152 *tp)
{
- u32 ocp_data;
- int i;
+ u32 ocp_data;
+ int i;
ocp_data = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR);
ocp_data &= ~RCR_ACPT_ALL;
ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data);
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1);
- ocp_data |= RXDY_GATED_EN;
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data);
+ rxdy_gated_en(tp, true);
+ r8153_teredo_off(tp);
+ r8152b_hw_phy_cfg(tp);
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CR, 0x00);
@@ -1838,10 +2344,6 @@
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, RTL8152_RMS);
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL);
- ocp_data |= MAGIC_EN;
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL, ocp_data);
-
ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CPCR);
ocp_data |= CPCR_RX_VLAN;
ocp_write_word(tp, MCU_TYPE_PLA, PLA_CPCR, ocp_data);
@@ -1854,36 +2356,26 @@
ocp_data |= NOW_IS_OOB | DIS_MCU_CLROOB;
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
- ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG5, LAN_WAKE_EN);
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1);
- ocp_data &= ~RXDY_GATED_EN;
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data);
+ rxdy_gated_en(tp, false);
ocp_data = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR);
ocp_data |= RCR_APM | RCR_AM | RCR_AB;
ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data);
}
-static void r8152b_disable_aldps(struct r8152 *tp)
-{
- ocp_reg_write(tp, OCP_ALDPS_CONFIG, ENPDNPS | LINKENA | DIS_SDSAVE);
- msleep(20);
-}
-
-static inline void r8152b_enable_aldps(struct r8152 *tp)
-{
- ocp_reg_write(tp, OCP_ALDPS_CONFIG, ENPWRSAVE | ENPDNPS |
- LINKENA | DIS_SDSAVE);
-}
-
static void r8153_hw_phy_cfg(struct r8152 *tp)
{
u32 ocp_data;
u16 data;
ocp_reg_write(tp, OCP_ADC_CFG, CKADSEL_L | ADC_EN | EN_EMI_L);
- r8152_mdio_write(tp, MII_BMCR, BMCR_ANENABLE);
+ data = r8152_mdio_read(tp, MII_BMCR);
+ if (data & BMCR_PDOWN) {
+ data &= ~BMCR_PDOWN;
+ r8152_mdio_write(tp, MII_BMCR, data);
+ }
+
+ r8153_clear_bp(tp);
if (tp->version == RTL_VER_03) {
data = ocp_reg_read(tp, OCP_EEE_CFG);
@@ -1919,9 +2411,11 @@
data = sram_read(tp, SRAM_10M_AMP2);
data |= AMP_DN;
sram_write(tp, SRAM_10M_AMP2, data);
+
+ set_bit(PHY_RESET, &tp->flags);
}
-static void r8153_u1u2en(struct r8152 *tp, int enable)
+static void r8153_u1u2en(struct r8152 *tp, bool enable)
{
u8 u1u2[8];
@@ -1933,7 +2427,7 @@
usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2);
}
-static void r8153_u2p3en(struct r8152 *tp, int enable)
+static void r8153_u2p3en(struct r8152 *tp, bool enable)
{
u32 ocp_data;
@@ -1945,7 +2439,7 @@
ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data);
}
-static void r8153_power_cut_en(struct r8152 *tp, int enable)
+static void r8153_power_cut_en(struct r8152 *tp, bool enable)
{
u32 ocp_data;
@@ -1961,28 +2455,12 @@
ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data);
}
-static void r8153_teredo_off(struct r8152 *tp)
-{
- u32 ocp_data;
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG);
- ocp_data &= ~(TEREDO_SEL | TEREDO_RS_EVENT_MASK | OOB_TEREDO_EN);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG, ocp_data);
-
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_WDT6_CTRL, WDT6_SET_MODE);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_REALWOW_TIMER, 0);
- ocp_write_dword(tp, MCU_TYPE_PLA, PLA_TEREDO_TIMER, 0);
-}
-
static void r8153_first_init(struct r8152 *tp)
{
u32 ocp_data;
int i;
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1);
- ocp_data |= RXDY_GATED_EN;
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data);
-
+ rxdy_gated_en(tp, true);
r8153_teredo_off(tp);
ocp_data = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR);
@@ -2075,10 +2553,6 @@
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, RTL8152_RMS);
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL);
- ocp_data |= MAGIC_EN;
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL, ocp_data);
-
ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG);
ocp_data &= ~TEREDO_WAKE_MASK;
ocp_write_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG, ocp_data);
@@ -2095,11 +2569,7 @@
ocp_data |= NOW_IS_OOB | DIS_MCU_CLROOB;
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
- ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG5, LAN_WAKE_EN);
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1);
- ocp_data &= ~RXDY_GATED_EN;
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data);
+ rxdy_gated_en(tp, false);
ocp_data = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR);
ocp_data |= RCR_APM | RCR_AM | RCR_AB;
@@ -2190,12 +2660,26 @@
bmcr = BMCR_ANENABLE | BMCR_ANRESTART;
}
+ if (test_bit(PHY_RESET, &tp->flags))
+ bmcr |= BMCR_RESET;
+
if (tp->mii.supports_gmii)
r8152_mdio_write(tp, MII_CTRL1000, gbcr);
r8152_mdio_write(tp, MII_ADVERTISE, anar);
r8152_mdio_write(tp, MII_BMCR, bmcr);
+ if (test_bit(PHY_RESET, &tp->flags)) {
+ int i;
+
+ clear_bit(PHY_RESET, &tp->flags);
+ for (i = 0; i < 50; i++) {
+ msleep(20);
+ if ((r8152_mdio_read(tp, MII_BMCR) & BMCR_RESET) == 0)
+ break;
+ }
+ }
+
out:
return ret;
@@ -2203,12 +2687,7 @@
static void rtl8152_down(struct r8152 *tp)
{
- u32 ocp_data;
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_UPS_CTRL);
- ocp_data &= ~POWER_CUT;
- ocp_write_word(tp, MCU_TYPE_USB, USB_UPS_CTRL, ocp_data);
-
+ r8152_power_cut_en(tp, false);
r8152b_disable_aldps(tp);
r8152b_enter_oob(tp);
r8152b_enable_aldps(tp);
@@ -2216,8 +2695,8 @@
static void rtl8153_down(struct r8152 *tp)
{
- r8153_u1u2en(tp, 0);
- r8153_power_cut_en(tp, 0);
+ r8153_u1u2en(tp, false);
+ r8153_power_cut_en(tp, false);
r8153_disable_aldps(tp);
r8153_enter_oob(tp);
r8153_enable_aldps(tp);
@@ -2252,6 +2731,9 @@
{
struct r8152 *tp = container_of(work, struct r8152, schedule.work);
+ if (usb_autopm_get_interface(tp->intf) < 0)
+ return;
+
if (!test_bit(WORK_ENABLE, &tp->flags))
goto out1;
@@ -2264,8 +2746,17 @@
if (test_bit(RTL8152_SET_RX_MODE, &tp->flags))
_rtl8152_set_rx_mode(tp->netdev);
+ if (test_bit(SCHEDULE_TASKLET, &tp->flags) &&
+ (tp->speed & LINK_STATUS)) {
+ clear_bit(SCHEDULE_TASKLET, &tp->flags);
+ tasklet_schedule(&tp->tl);
+ }
+
+ if (test_bit(PHY_RESET, &tp->flags))
+ rtl_phy_reset(tp);
+
out1:
- return;
+ usb_autopm_put_interface(tp->intf);
}
static int rtl8152_open(struct net_device *netdev)
@@ -2273,15 +2764,27 @@
struct r8152 *tp = netdev_priv(netdev);
int res = 0;
- res = usb_submit_urb(tp->intr_urb, GFP_KERNEL);
- if (res) {
- if (res == -ENODEV)
- netif_device_detach(tp->netdev);
- netif_warn(tp, ifup, netdev, "intr_urb submit failed: %d\n",
- res);
- return res;
+ res = alloc_all_mem(tp);
+ if (res)
+ goto out;
+
+ res = usb_autopm_get_interface(tp->intf);
+ if (res < 0) {
+ free_all_mem(tp);
+ goto out;
}
+ /* The WORK_ENABLE may be set when autoresume occurs */
+ if (test_bit(WORK_ENABLE, &tp->flags)) {
+ clear_bit(WORK_ENABLE, &tp->flags);
+ usb_kill_urb(tp->intr_urb);
+ cancel_delayed_work_sync(&tp->schedule);
+ if (tp->speed & LINK_STATUS)
+ tp->rtl_ops.disable(tp);
+ }
+
+ tp->rtl_ops.up(tp);
+
rtl8152_set_speed(tp, AUTONEG_ENABLE,
tp->mii.supports_gmii ? SPEED_1000 : SPEED_100,
DUPLEX_FULL);
@@ -2290,6 +2793,18 @@
netif_start_queue(netdev);
set_bit(WORK_ENABLE, &tp->flags);
+ res = usb_submit_urb(tp->intr_urb, GFP_KERNEL);
+ if (res) {
+ if (res == -ENODEV)
+ netif_device_detach(tp->netdev);
+ netif_warn(tp, ifup, netdev, "intr_urb submit failed: %d\n",
+ res);
+ free_all_mem(tp);
+ }
+
+ usb_autopm_put_interface(tp->intf);
+
+out:
return res;
}
@@ -2298,39 +2813,36 @@
struct r8152 *tp = netdev_priv(netdev);
int res = 0;
- usb_kill_urb(tp->intr_urb);
clear_bit(WORK_ENABLE, &tp->flags);
+ usb_kill_urb(tp->intr_urb);
cancel_delayed_work_sync(&tp->schedule);
netif_stop_queue(netdev);
- tasklet_disable(&tp->tl);
- tp->rtl_ops.disable(tp);
- tasklet_enable(&tp->tl);
+
+ res = usb_autopm_get_interface(tp->intf);
+ if (res < 0) {
+ rtl_drop_queued_tx(tp);
+ } else {
+ /*
+ * The autosuspend may have been enabled and wouldn't
+ * be disable when autoresume occurs, because the
+ * netif_running() would be false.
+ */
+ if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
+ rtl_runtime_suspend_enable(tp, false);
+ clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+ }
+
+ tasklet_disable(&tp->tl);
+ tp->rtl_ops.down(tp);
+ tasklet_enable(&tp->tl);
+ usb_autopm_put_interface(tp->intf);
+ }
+
+ free_all_mem(tp);
return res;
}
-static void rtl_clear_bp(struct r8152 *tp)
-{
- ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_0, 0);
- ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_2, 0);
- ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_4, 0);
- ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_6, 0);
- ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_0, 0);
- ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_2, 0);
- ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_4, 0);
- ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_6, 0);
- mdelay(3);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_BP_BA, 0);
- ocp_write_word(tp, MCU_TYPE_USB, USB_BP_BA, 0);
-}
-
-static void r8153_clear_bp(struct r8152 *tp)
-{
- ocp_write_byte(tp, MCU_TYPE_PLA, PLA_BP_EN, 0);
- ocp_write_byte(tp, MCU_TYPE_USB, USB_BP_EN, 0);
- rtl_clear_bp(tp);
-}
-
static void r8152b_enable_eee(struct r8152 *tp)
{
u32 ocp_data;
@@ -2379,18 +2891,18 @@
r8152_mdio_write(tp, MII_ADVERTISE, anar);
}
-static void r8152b_hw_phy_cfg(struct r8152 *tp)
+static void rtl_tally_reset(struct r8152 *tp)
{
- r8152_mdio_write(tp, MII_BMCR, BMCR_ANENABLE);
- r8152b_disable_aldps(tp);
+ u32 ocp_data;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_RSTTALLY);
+ ocp_data |= TALLY_RESET;
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_RSTTALLY, ocp_data);
}
static void r8152b_init(struct r8152 *tp)
{
u32 ocp_data;
- int i;
-
- rtl_clear_bp(tp);
if (tp->version == RTL_VER_01) {
ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_LED_FEATURE);
@@ -2398,17 +2910,7 @@
ocp_write_word(tp, MCU_TYPE_PLA, PLA_LED_FEATURE, ocp_data);
}
- r8152b_hw_phy_cfg(tp);
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_UPS_CTRL);
- ocp_data &= ~POWER_CUT;
- ocp_write_word(tp, MCU_TYPE_USB, USB_UPS_CTRL, ocp_data);
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_PM_CTRL_STATUS);
- ocp_data &= ~RESUME_INDICATE;
- ocp_write_word(tp, MCU_TYPE_USB, USB_PM_CTRL_STATUS, ocp_data);
-
- r8152b_exit_oob(tp);
+ r8152_power_cut_en(tp, false);
ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_PHY_PWR);
ocp_data |= TX_10M_IDLE_EN | PFM_PWM_SWITCH;
@@ -2424,14 +2926,7 @@
r8152b_enable_eee(tp);
r8152b_enable_aldps(tp);
r8152b_enable_fc(tp);
-
- r8152_mdio_write(tp, MII_BMCR, BMCR_RESET | BMCR_ANENABLE |
- BMCR_ANRESTART);
- for (i = 0; i < 100; i++) {
- udelay(100);
- if (!(r8152_mdio_read(tp, MII_BMCR) & BMCR_RESET))
- break;
- }
+ rtl_tally_reset(tp);
/* enable rx aggregation */
ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_USB_CTRL);
@@ -2444,7 +2939,7 @@
u32 ocp_data;
int i;
- r8153_u1u2en(tp, 0);
+ r8153_u1u2en(tp, false);
for (i = 0; i < 500; i++) {
if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) &
@@ -2460,14 +2955,12 @@
msleep(20);
}
- r8153_u2p3en(tp, 0);
+ r8153_u2p3en(tp, false);
ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_WDT11_CTRL);
ocp_data &= ~TIMER11_EN;
ocp_write_word(tp, MCU_TYPE_USB, USB_WDT11_CTRL, ocp_data);
- r8153_clear_bp(tp);
-
ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_LED_FEATURE);
ocp_data &= ~LED_MODE_MASK;
ocp_write_word(tp, MCU_TYPE_PLA, PLA_LED_FEATURE, ocp_data);
@@ -2485,10 +2978,8 @@
ocp_data |= SEN_VAL_NORMAL | SEL_RXIDLE;
ocp_write_word(tp, MCU_TYPE_USB, USB_AFE_CTRL2, ocp_data);
- r8153_power_cut_en(tp, 0);
- r8153_u1u2en(tp, 1);
-
- r8153_first_init(tp);
+ r8153_power_cut_en(tp, false);
+ r8153_u1u2en(tp, true);
ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, ALDPS_SPDWN_RATIO);
ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, EEE_SPDWN_RATIO);
@@ -2503,26 +2994,31 @@
r8153_enable_eee(tp);
r8153_enable_aldps(tp);
r8152b_enable_fc(tp);
-
- r8152_mdio_write(tp, MII_BMCR, BMCR_RESET | BMCR_ANENABLE |
- BMCR_ANRESTART);
+ rtl_tally_reset(tp);
}
static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
{
struct r8152 *tp = usb_get_intfdata(intf);
- netif_device_detach(tp->netdev);
+ if (PMSG_IS_AUTO(message))
+ set_bit(SELECTIVE_SUSPEND, &tp->flags);
+ else
+ netif_device_detach(tp->netdev);
if (netif_running(tp->netdev)) {
clear_bit(WORK_ENABLE, &tp->flags);
usb_kill_urb(tp->intr_urb);
cancel_delayed_work_sync(&tp->schedule);
- tasklet_disable(&tp->tl);
+ if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
+ rtl_runtime_suspend_enable(tp, true);
+ } else {
+ tasklet_disable(&tp->tl);
+ tp->rtl_ops.down(tp);
+ tasklet_enable(&tp->tl);
+ }
}
- tp->rtl_ops.down(tp);
-
return 0;
}
@@ -2530,22 +3026,77 @@
{
struct r8152 *tp = usb_get_intfdata(intf);
- tp->rtl_ops.init(tp);
- netif_device_attach(tp->netdev);
+ if (!test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
+ tp->rtl_ops.init(tp);
+ netif_device_attach(tp->netdev);
+ }
+
if (netif_running(tp->netdev)) {
- rtl8152_set_speed(tp, AUTONEG_ENABLE,
+ if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
+ rtl_runtime_suspend_enable(tp, false);
+ clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+ if (tp->speed & LINK_STATUS)
+ tp->rtl_ops.disable(tp);
+ } else {
+ tp->rtl_ops.up(tp);
+ rtl8152_set_speed(tp, AUTONEG_ENABLE,
tp->mii.supports_gmii ? SPEED_1000 : SPEED_100,
DUPLEX_FULL);
+ }
tp->speed = 0;
netif_carrier_off(tp->netdev);
set_bit(WORK_ENABLE, &tp->flags);
usb_submit_urb(tp->intr_urb, GFP_KERNEL);
- tasklet_enable(&tp->tl);
}
return 0;
}
+static void rtl8152_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+ struct r8152 *tp = netdev_priv(dev);
+
+ if (usb_autopm_get_interface(tp->intf) < 0)
+ return;
+
+ wol->supported = WAKE_ANY;
+ wol->wolopts = __rtl_get_wol(tp);
+
+ usb_autopm_put_interface(tp->intf);
+}
+
+static int rtl8152_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+{
+ struct r8152 *tp = netdev_priv(dev);
+ int ret;
+
+ ret = usb_autopm_get_interface(tp->intf);
+ if (ret < 0)
+ goto out_set_wol;
+
+ __rtl_set_wol(tp, wol->wolopts);
+ tp->saved_wolopts = wol->wolopts & WAKE_ANY;
+
+ usb_autopm_put_interface(tp->intf);
+
+out_set_wol:
+ return ret;
+}
+
+static u32 rtl8152_get_msglevel(struct net_device *dev)
+{
+ struct r8152 *tp = netdev_priv(dev);
+
+ return tp->msg_enable;
+}
+
+static void rtl8152_set_msglevel(struct net_device *dev, u32 value)
+{
+ struct r8152 *tp = netdev_priv(dev);
+
+ tp->msg_enable = value;
+}
+
static void rtl8152_get_drvinfo(struct net_device *netdev,
struct ethtool_drvinfo *info)
{
@@ -2570,8 +3121,76 @@
static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
{
struct r8152 *tp = netdev_priv(dev);
+ int ret;
- return rtl8152_set_speed(tp, cmd->autoneg, cmd->speed, cmd->duplex);
+ ret = usb_autopm_get_interface(tp->intf);
+ if (ret < 0)
+ goto out;
+
+ ret = rtl8152_set_speed(tp, cmd->autoneg, cmd->speed, cmd->duplex);
+
+ usb_autopm_put_interface(tp->intf);
+
+out:
+ return ret;
+}
+
+static const char rtl8152_gstrings[][ETH_GSTRING_LEN] = {
+ "tx_packets",
+ "rx_packets",
+ "tx_errors",
+ "rx_errors",
+ "rx_missed",
+ "align_errors",
+ "tx_single_collisions",
+ "tx_multi_collisions",
+ "rx_unicast",
+ "rx_broadcast",
+ "rx_multicast",
+ "tx_aborted",
+ "tx_underrun",
+};
+
+static int rtl8152_get_sset_count(struct net_device *dev, int sset)
+{
+ switch (sset) {
+ case ETH_SS_STATS:
+ return ARRAY_SIZE(rtl8152_gstrings);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static void rtl8152_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *stats, u64 *data)
+{
+ struct r8152 *tp = netdev_priv(dev);
+ struct tally_counter tally;
+
+ generic_ocp_read(tp, PLA_TALLYCNT, sizeof(tally), &tally, MCU_TYPE_PLA);
+
+ data[0] = le64_to_cpu(tally.tx_packets);
+ data[1] = le64_to_cpu(tally.rx_packets);
+ data[2] = le64_to_cpu(tally.tx_errors);
+ data[3] = le32_to_cpu(tally.rx_errors);
+ data[4] = le16_to_cpu(tally.rx_missed);
+ data[5] = le16_to_cpu(tally.align_errors);
+ data[6] = le32_to_cpu(tally.tx_one_collision);
+ data[7] = le32_to_cpu(tally.tx_multi_collision);
+ data[8] = le64_to_cpu(tally.rx_unicast);
+ data[9] = le64_to_cpu(tally.rx_broadcast);
+ data[10] = le32_to_cpu(tally.rx_multicast);
+ data[11] = le16_to_cpu(tally.tx_aborted);
+ data[12] = le16_to_cpu(tally.tx_underun);
+}
+
+static void rtl8152_get_strings(struct net_device *dev, u32 stringset, u8 *data)
+{
+ switch (stringset) {
+ case ETH_SS_STATS:
+ memcpy(data, *rtl8152_gstrings, sizeof(rtl8152_gstrings));
+ break;
+ }
}
static struct ethtool_ops ops = {
@@ -2579,13 +3198,24 @@
.get_settings = rtl8152_get_settings,
.set_settings = rtl8152_set_settings,
.get_link = ethtool_op_get_link,
+ .get_msglevel = rtl8152_get_msglevel,
+ .set_msglevel = rtl8152_set_msglevel,
+ .get_wol = rtl8152_get_wol,
+ .set_wol = rtl8152_set_wol,
+ .get_strings = rtl8152_get_strings,
+ .get_sset_count = rtl8152_get_sset_count,
+ .get_ethtool_stats = rtl8152_get_ethtool_stats,
};
static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
{
struct r8152 *tp = netdev_priv(netdev);
struct mii_ioctl_data *data = if_mii(rq);
- int res = 0;
+ int res;
+
+ res = usb_autopm_get_interface(tp->intf);
+ if (res < 0)
+ goto out;
switch (cmd) {
case SIOCGMIIPHY:
@@ -2608,6 +3238,9 @@
res = -EOPNOTSUPP;
}
+ usb_autopm_put_interface(tp->intf);
+
+out:
return res;
}
@@ -2660,22 +3293,13 @@
static void rtl8152_unload(struct r8152 *tp)
{
- u32 ocp_data;
-
- if (tp->version != RTL_VER_01) {
- ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_UPS_CTRL);
- ocp_data |= POWER_CUT;
- ocp_write_word(tp, MCU_TYPE_USB, USB_UPS_CTRL, ocp_data);
- }
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_PM_CTRL_STATUS);
- ocp_data &= ~RESUME_INDICATE;
- ocp_write_word(tp, MCU_TYPE_USB, USB_PM_CTRL_STATUS, ocp_data);
+ if (tp->version != RTL_VER_01)
+ r8152_power_cut_en(tp, true);
}
static void rtl8153_unload(struct r8152 *tp)
{
- r8153_power_cut_en(tp, 1);
+ r8153_power_cut_en(tp, true);
}
static int rtl_ops_init(struct r8152 *tp, const struct usb_device_id *id)
@@ -2690,6 +3314,7 @@
ops->init = r8152b_init;
ops->enable = rtl8152_enable;
ops->disable = rtl8152_disable;
+ ops->up = r8152b_exit_oob;
ops->down = rtl8152_down;
ops->unload = rtl8152_unload;
ret = 0;
@@ -2698,6 +3323,7 @@
ops->init = r8153_init;
ops->enable = rtl8153_enable;
ops->disable = rtl8152_disable;
+ ops->up = r8153_first_init;
ops->down = rtl8153_down;
ops->unload = rtl8153_unload;
ret = 0;
@@ -2713,6 +3339,7 @@
ops->init = r8153_init;
ops->enable = rtl8153_enable;
ops->disable = rtl8152_disable;
+ ops->up = r8153_first_init;
ops->down = rtl8153_down;
ops->unload = rtl8153_unload;
ret = 0;
@@ -2740,6 +3367,12 @@
struct net_device *netdev;
int ret;
+ if (udev->actconfig->desc.bConfigurationValue != 1) {
+ usb_driver_set_configuration(udev, 1);
+ return -ENODEV;
+ }
+
+ usb_reset_device(udev);
netdev = alloc_etherdev(sizeof(struct r8152));
if (!netdev) {
dev_err(&intf->dev, "Out of memory\n");
@@ -2764,9 +3397,15 @@
netdev->netdev_ops = &rtl8152_netdev_ops;
netdev->watchdog_timeo = RTL8152_TX_TIMEOUT;
- netdev->features |= NETIF_F_IP_CSUM;
- netdev->hw_features = NETIF_F_IP_CSUM;
+ netdev->features |= NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_SG |
+ NETIF_F_TSO | NETIF_F_FRAGLIST | NETIF_F_IPV6_CSUM |
+ NETIF_F_TSO6;
+ netdev->hw_features = NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_SG |
+ NETIF_F_TSO | NETIF_F_FRAGLIST |
+ NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
+
SET_ETHTOOL_OPS(netdev, &ops);
+ netif_set_gso_max_size(netdev, RTL_LIMITED_TSO_SIZE);
tp->mii.dev = netdev;
tp->mii.mdio_read = read_mii_word;
@@ -2776,14 +3415,12 @@
tp->mii.phy_id = R8152_PHY_ID;
tp->mii.supports_gmii = 0;
+ intf->needs_remote_wakeup = 1;
+
r8152b_get_version(tp);
tp->rtl_ops.init(tp);
set_ethernet_addr(tp);
- ret = alloc_all_mem(tp);
- if (ret)
- goto out;
-
usb_set_intfdata(intf, tp);
ret = register_netdev(netdev);
@@ -2792,6 +3429,12 @@
goto out1;
}
+ tp->saved_wolopts = __rtl_get_wol(tp);
+ if (tp->saved_wolopts)
+ device_set_wakeup_enable(&udev->dev, true);
+ else
+ device_set_wakeup_enable(&udev->dev, false);
+
netif_info(tp, probe, netdev, "%s\n", DRIVER_VERSION);
return 0;
@@ -2813,16 +3456,15 @@
tasklet_kill(&tp->tl);
unregister_netdev(tp->netdev);
tp->rtl_ops.unload(tp);
- free_all_mem(tp);
free_netdev(tp->netdev);
}
}
/* table of devices that work with this driver */
static struct usb_device_id rtl8152_table[] = {
- {REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8152)},
- {REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8153)},
- {REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, PRODUCT_ID_SAMSUNG)},
+ {USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8152)},
+ {USB_DEVICE(VENDOR_ID_REALTEK, PRODUCT_ID_RTL8153)},
+ {USB_DEVICE(VENDOR_ID_SAMSUNG, PRODUCT_ID_SAMSUNG)},
{}
};
@@ -2836,6 +3478,8 @@
.suspend = rtl8152_suspend,
.resume = rtl8152_resume,
.reset_resume = rtl8152_resume,
+ .supports_autosuspend = 1,
+ .disable_hub_initiated_lpm = 1,
};
module_usb_driver(rtl8152_driver);
diff --git a/drivers/net/usb/r815x.c b/drivers/net/usb/r815x.c
deleted file mode 100644
index f0a8791..0000000
--- a/drivers/net/usb/r815x.c
+++ /dev/null
@@ -1,248 +0,0 @@
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/mii.h>
-#include <linux/usb.h>
-#include <linux/usb/cdc.h>
-#include <linux/usb/usbnet.h>
-
-#define RTL815x_REQT_READ 0xc0
-#define RTL815x_REQT_WRITE 0x40
-#define RTL815x_REQ_GET_REGS 0x05
-#define RTL815x_REQ_SET_REGS 0x05
-
-#define MCU_TYPE_PLA 0x0100
-#define OCP_BASE 0xe86c
-#define BASE_MII 0xa400
-
-#define BYTE_EN_DWORD 0xff
-#define BYTE_EN_WORD 0x33
-#define BYTE_EN_BYTE 0x11
-
-#define R815x_PHY_ID 32
-#define REALTEK_VENDOR_ID 0x0bda
-
-
-static int pla_read_word(struct usb_device *udev, u16 index)
-{
- int ret;
- u8 shift = index & 2;
- __le32 *tmp;
-
- tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
- if (!tmp)
- return -ENOMEM;
-
- index &= ~3;
-
- ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
- RTL815x_REQ_GET_REGS, RTL815x_REQT_READ,
- index, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500);
- if (ret < 0)
- goto out2;
-
- ret = __le32_to_cpu(*tmp);
- ret >>= (shift * 8);
- ret &= 0xffff;
-
-out2:
- kfree(tmp);
- return ret;
-}
-
-static int pla_write_word(struct usb_device *udev, u16 index, u32 data)
-{
- __le32 *tmp;
- u32 mask = 0xffff;
- u16 byen = BYTE_EN_WORD;
- u8 shift = index & 2;
- int ret;
-
- tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
- if (!tmp)
- return -ENOMEM;
-
- data &= mask;
-
- if (shift) {
- byen <<= shift;
- mask <<= (shift * 8);
- data <<= (shift * 8);
- index &= ~3;
- }
-
- ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
- RTL815x_REQ_GET_REGS, RTL815x_REQT_READ,
- index, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500);
- if (ret < 0)
- goto out3;
-
- data |= __le32_to_cpu(*tmp) & ~mask;
- *tmp = __cpu_to_le32(data);
-
- ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
- RTL815x_REQ_SET_REGS, RTL815x_REQT_WRITE,
- index, MCU_TYPE_PLA | byen, tmp, sizeof(*tmp),
- 500);
-
-out3:
- kfree(tmp);
- return ret;
-}
-
-static int ocp_reg_read(struct usbnet *dev, u16 addr)
-{
- u16 ocp_base, ocp_index;
- int ret;
-
- ocp_base = addr & 0xf000;
- ret = pla_write_word(dev->udev, OCP_BASE, ocp_base);
- if (ret < 0)
- goto out;
-
- ocp_index = (addr & 0x0fff) | 0xb000;
- ret = pla_read_word(dev->udev, ocp_index);
-
-out:
- return ret;
-}
-
-static int ocp_reg_write(struct usbnet *dev, u16 addr, u16 data)
-{
- u16 ocp_base, ocp_index;
- int ret;
-
- ocp_base = addr & 0xf000;
- ret = pla_write_word(dev->udev, OCP_BASE, ocp_base);
- if (ret < 0)
- goto out1;
-
- ocp_index = (addr & 0x0fff) | 0xb000;
- ret = pla_write_word(dev->udev, ocp_index, data);
-
-out1:
- return ret;
-}
-
-static int r815x_mdio_read(struct net_device *netdev, int phy_id, int reg)
-{
- struct usbnet *dev = netdev_priv(netdev);
- int ret;
-
- if (phy_id != R815x_PHY_ID)
- return -EINVAL;
-
- if (usb_autopm_get_interface(dev->intf) < 0)
- return -ENODEV;
-
- ret = ocp_reg_read(dev, BASE_MII + reg * 2);
-
- usb_autopm_put_interface(dev->intf);
- return ret;
-}
-
-static
-void r815x_mdio_write(struct net_device *netdev, int phy_id, int reg, int val)
-{
- struct usbnet *dev = netdev_priv(netdev);
-
- if (phy_id != R815x_PHY_ID)
- return;
-
- if (usb_autopm_get_interface(dev->intf) < 0)
- return;
-
- ocp_reg_write(dev, BASE_MII + reg * 2, val);
-
- usb_autopm_put_interface(dev->intf);
-}
-
-static int r8153_bind(struct usbnet *dev, struct usb_interface *intf)
-{
- int status;
-
- status = usbnet_cdc_bind(dev, intf);
- if (status < 0)
- return status;
-
- dev->mii.dev = dev->net;
- dev->mii.mdio_read = r815x_mdio_read;
- dev->mii.mdio_write = r815x_mdio_write;
- dev->mii.phy_id_mask = 0x3f;
- dev->mii.reg_num_mask = 0x1f;
- dev->mii.phy_id = R815x_PHY_ID;
- dev->mii.supports_gmii = 1;
-
- return status;
-}
-
-static int r8152_bind(struct usbnet *dev, struct usb_interface *intf)
-{
- int status;
-
- status = usbnet_cdc_bind(dev, intf);
- if (status < 0)
- return status;
-
- dev->mii.dev = dev->net;
- dev->mii.mdio_read = r815x_mdio_read;
- dev->mii.mdio_write = r815x_mdio_write;
- dev->mii.phy_id_mask = 0x3f;
- dev->mii.reg_num_mask = 0x1f;
- dev->mii.phy_id = R815x_PHY_ID;
- dev->mii.supports_gmii = 0;
-
- return status;
-}
-
-static const struct driver_info r8152_info = {
- .description = "RTL8152 ECM Device",
- .flags = FLAG_ETHER | FLAG_POINTTOPOINT,
- .bind = r8152_bind,
- .unbind = usbnet_cdc_unbind,
- .status = usbnet_cdc_status,
- .manage_power = usbnet_manage_power,
-};
-
-static const struct driver_info r8153_info = {
- .description = "RTL8153 ECM Device",
- .flags = FLAG_ETHER | FLAG_POINTTOPOINT,
- .bind = r8153_bind,
- .unbind = usbnet_cdc_unbind,
- .status = usbnet_cdc_status,
- .manage_power = usbnet_manage_power,
-};
-
-static const struct usb_device_id products[] = {
-{
- USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8152, USB_CLASS_COMM,
- USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
- .driver_info = (unsigned long) &r8152_info,
-},
-
-{
- USB_DEVICE_AND_INTERFACE_INFO(REALTEK_VENDOR_ID, 0x8153, USB_CLASS_COMM,
- USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
- .driver_info = (unsigned long) &r8153_info,
-},
-
- { }, /* END */
-};
-MODULE_DEVICE_TABLE(usb, products);
-
-static struct usb_driver r815x_driver = {
- .name = "r815x",
- .id_table = products,
- .probe = usbnet_probe,
- .disconnect = usbnet_disconnect,
- .suspend = usbnet_suspend,
- .resume = usbnet_resume,
- .reset_resume = usbnet_resume,
- .supports_autosuspend = 1,
- .disable_hub_initiated_lpm = 1,
-};
-
-module_usb_driver(r815x_driver);
-
-MODULE_AUTHOR("Hayes Wang");
-MODULE_DESCRIPTION("Realtek USB ECM device");
-MODULE_LICENSE("GPL");
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index a48bc0f..524a47a281 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -492,6 +492,10 @@
*/
int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
{
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
/* peripheral may have batched packets to us... */
while (likely(skb->len)) {
struct rndis_data_hdr *hdr = (void *)skb->data;
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index f17b9e0..d9e7892 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -2106,6 +2106,10 @@
static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
{
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
while (skb->len > 0) {
u32 rx_cmd_a, rx_cmd_b, align_count, size;
struct sk_buff *ax_skb;
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 8dd54a0..424db65e 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1723,6 +1723,10 @@
static int smsc95xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
{
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
while (skb->len > 0) {
u32 header, align_count;
struct sk_buff *ax_skb;
diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c
new file mode 100644
index 0000000..b94a0fb
--- /dev/null
+++ b/drivers/net/usb/sr9800.c
@@ -0,0 +1,874 @@
+/* CoreChip-sz SR9800 one chip USB 2.0 Ethernet Devices
+ *
+ * Author : Liu Junliang <liujunliang_ljl@163.com>
+ *
+ * Based on asix_common.c, asix_devices.c
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.*
+ */
+
+#include <linux/module.h>
+#include <linux/kmod.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/workqueue.h>
+#include <linux/mii.h>
+#include <linux/usb.h>
+#include <linux/crc32.h>
+#include <linux/usb/usbnet.h>
+#include <linux/slab.h>
+#include <linux/if_vlan.h>
+
+#include "sr9800.h"
+
+static int sr_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
+ u16 size, void *data)
+{
+ int err;
+
+ err = usbnet_read_cmd(dev, cmd, SR_REQ_RD_REG, value, index,
+ data, size);
+ if ((err != size) && (err >= 0))
+ err = -EINVAL;
+
+ return err;
+}
+
+static int sr_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
+ u16 size, void *data)
+{
+ int err;
+
+ err = usbnet_write_cmd(dev, cmd, SR_REQ_WR_REG, value, index,
+ data, size);
+ if ((err != size) && (err >= 0))
+ err = -EINVAL;
+
+ return err;
+}
+
+static void
+sr_write_cmd_async(struct usbnet *dev, u8 cmd, u16 value, u16 index,
+ u16 size, void *data)
+{
+ usbnet_write_cmd_async(dev, cmd, SR_REQ_WR_REG, value, index, data,
+ size);
+}
+
+static int sr_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
+{
+ int offset = 0;
+
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
+ while (offset + sizeof(u32) < skb->len) {
+ struct sk_buff *sr_skb;
+ u16 size;
+ u32 header = get_unaligned_le32(skb->data + offset);
+
+ offset += sizeof(u32);
+ /* get the packet length */
+ size = (u16) (header & 0x7ff);
+ if (size != ((~header >> 16) & 0x07ff)) {
+ netdev_err(dev->net, "%s : Bad Header Length\n",
+ __func__);
+ return 0;
+ }
+
+ if ((size > dev->net->mtu + ETH_HLEN + VLAN_HLEN) ||
+ (size + offset > skb->len)) {
+ netdev_err(dev->net, "%s : Bad RX Length %d\n",
+ __func__, size);
+ return 0;
+ }
+ sr_skb = netdev_alloc_skb_ip_align(dev->net, size);
+ if (!sr_skb)
+ return 0;
+
+ skb_put(sr_skb, size);
+ memcpy(sr_skb->data, skb->data + offset, size);
+ usbnet_skb_return(dev, sr_skb);
+
+ offset += (size + 1) & 0xfffe;
+ }
+
+ if (skb->len != offset) {
+ netdev_err(dev->net, "%s : Bad SKB Length %d\n", __func__,
+ skb->len);
+ return 0;
+ }
+
+ return 1;
+}
+
+static struct sk_buff *sr_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
+ gfp_t flags)
+{
+ int headroom = skb_headroom(skb);
+ int tailroom = skb_tailroom(skb);
+ u32 padbytes = 0xffff0000;
+ u32 packet_len;
+ int padlen;
+
+ padlen = ((skb->len + 4) % (dev->maxpacket - 1)) ? 0 : 4;
+
+ if ((!skb_cloned(skb)) && ((headroom + tailroom) >= (4 + padlen))) {
+ if ((headroom < 4) || (tailroom < padlen)) {
+ skb->data = memmove(skb->head + 4, skb->data,
+ skb->len);
+ skb_set_tail_pointer(skb, skb->len);
+ }
+ } else {
+ struct sk_buff *skb2;
+ skb2 = skb_copy_expand(skb, 4, padlen, flags);
+ dev_kfree_skb_any(skb);
+ skb = skb2;
+ if (!skb)
+ return NULL;
+ }
+
+ skb_push(skb, 4);
+ packet_len = (((skb->len - 4) ^ 0x0000ffff) << 16) + (skb->len - 4);
+ cpu_to_le32s(&packet_len);
+ skb_copy_to_linear_data(skb, &packet_len, sizeof(packet_len));
+
+ if (padlen) {
+ cpu_to_le32s(&padbytes);
+ memcpy(skb_tail_pointer(skb), &padbytes, sizeof(padbytes));
+ skb_put(skb, sizeof(padbytes));
+ }
+
+ return skb;
+}
+
+static void sr_status(struct usbnet *dev, struct urb *urb)
+{
+ struct sr9800_int_data *event;
+ int link;
+
+ if (urb->actual_length < 8)
+ return;
+
+ event = urb->transfer_buffer;
+ link = event->link & 0x01;
+ if (netif_carrier_ok(dev->net) != link) {
+ usbnet_link_change(dev, link, 1);
+ netdev_dbg(dev->net, "Link Status is: %d\n", link);
+ }
+
+ return;
+}
+
+static inline int sr_set_sw_mii(struct usbnet *dev)
+{
+ int ret;
+
+ ret = sr_write_cmd(dev, SR_CMD_SET_SW_MII, 0x0000, 0, 0, NULL);
+ if (ret < 0)
+ netdev_err(dev->net, "Failed to enable software MII access\n");
+ return ret;
+}
+
+static inline int sr_set_hw_mii(struct usbnet *dev)
+{
+ int ret;
+
+ ret = sr_write_cmd(dev, SR_CMD_SET_HW_MII, 0x0000, 0, 0, NULL);
+ if (ret < 0)
+ netdev_err(dev->net, "Failed to enable hardware MII access\n");
+ return ret;
+}
+
+static inline int sr_get_phy_addr(struct usbnet *dev)
+{
+ u8 buf[2];
+ int ret;
+
+ ret = sr_read_cmd(dev, SR_CMD_READ_PHY_ID, 0, 0, 2, buf);
+ if (ret < 0) {
+ netdev_err(dev->net, "%s : Error reading PHYID register:%02x\n",
+ __func__, ret);
+ goto out;
+ }
+ netdev_dbg(dev->net, "%s : returning 0x%04x\n", __func__,
+ *((__le16 *)buf));
+
+ ret = buf[1];
+
+out:
+ return ret;
+}
+
+static int sr_sw_reset(struct usbnet *dev, u8 flags)
+{
+ int ret;
+
+ ret = sr_write_cmd(dev, SR_CMD_SW_RESET, flags, 0, 0, NULL);
+ if (ret < 0)
+ netdev_err(dev->net, "Failed to send software reset:%02x\n",
+ ret);
+
+ return ret;
+}
+
+static u16 sr_read_rx_ctl(struct usbnet *dev)
+{
+ __le16 v;
+ int ret;
+
+ ret = sr_read_cmd(dev, SR_CMD_READ_RX_CTL, 0, 0, 2, &v);
+ if (ret < 0) {
+ netdev_err(dev->net, "Error reading RX_CTL register:%02x\n",
+ ret);
+ goto out;
+ }
+
+ ret = le16_to_cpu(v);
+out:
+ return ret;
+}
+
+static int sr_write_rx_ctl(struct usbnet *dev, u16 mode)
+{
+ int ret;
+
+ netdev_dbg(dev->net, "%s : mode = 0x%04x\n", __func__, mode);
+ ret = sr_write_cmd(dev, SR_CMD_WRITE_RX_CTL, mode, 0, 0, NULL);
+ if (ret < 0)
+ netdev_err(dev->net,
+ "Failed to write RX_CTL mode to 0x%04x:%02x\n",
+ mode, ret);
+
+ return ret;
+}
+
+static u16 sr_read_medium_status(struct usbnet *dev)
+{
+ __le16 v;
+ int ret;
+
+ ret = sr_read_cmd(dev, SR_CMD_READ_MEDIUM_STATUS, 0, 0, 2, &v);
+ if (ret < 0) {
+ netdev_err(dev->net,
+ "Error reading Medium Status register:%02x\n", ret);
+ return ret; /* TODO: callers not checking for error ret */
+ }
+
+ return le16_to_cpu(v);
+}
+
+static int sr_write_medium_mode(struct usbnet *dev, u16 mode)
+{
+ int ret;
+
+ netdev_dbg(dev->net, "%s : mode = 0x%04x\n", __func__, mode);
+ ret = sr_write_cmd(dev, SR_CMD_WRITE_MEDIUM_MODE, mode, 0, 0, NULL);
+ if (ret < 0)
+ netdev_err(dev->net,
+ "Failed to write Medium Mode mode to 0x%04x:%02x\n",
+ mode, ret);
+ return ret;
+}
+
+static int sr_write_gpio(struct usbnet *dev, u16 value, int sleep)
+{
+ int ret;
+
+ netdev_dbg(dev->net, "%s : value = 0x%04x\n", __func__, value);
+ ret = sr_write_cmd(dev, SR_CMD_WRITE_GPIOS, value, 0, 0, NULL);
+ if (ret < 0)
+ netdev_err(dev->net, "Failed to write GPIO value 0x%04x:%02x\n",
+ value, ret);
+ if (sleep)
+ msleep(sleep);
+
+ return ret;
+}
+
+/* SR9800 have a 16-bit RX_CTL value */
+static void sr_set_multicast(struct net_device *net)
+{
+ struct usbnet *dev = netdev_priv(net);
+ struct sr_data *data = (struct sr_data *)&dev->data;
+ u16 rx_ctl = SR_DEFAULT_RX_CTL;
+
+ if (net->flags & IFF_PROMISC) {
+ rx_ctl |= SR_RX_CTL_PRO;
+ } else if (net->flags & IFF_ALLMULTI ||
+ netdev_mc_count(net) > SR_MAX_MCAST) {
+ rx_ctl |= SR_RX_CTL_AMALL;
+ } else if (netdev_mc_empty(net)) {
+ /* just broadcast and directed */
+ } else {
+ /* We use the 20 byte dev->data
+ * for our 8 byte filter buffer
+ * to avoid allocating memory that
+ * is tricky to free later
+ */
+ struct netdev_hw_addr *ha;
+ u32 crc_bits;
+
+ memset(data->multi_filter, 0, SR_MCAST_FILTER_SIZE);
+
+ /* Build the multicast hash filter. */
+ netdev_for_each_mc_addr(ha, net) {
+ crc_bits = ether_crc(ETH_ALEN, ha->addr) >> 26;
+ data->multi_filter[crc_bits >> 3] |=
+ 1 << (crc_bits & 7);
+ }
+
+ sr_write_cmd_async(dev, SR_CMD_WRITE_MULTI_FILTER, 0, 0,
+ SR_MCAST_FILTER_SIZE, data->multi_filter);
+
+ rx_ctl |= SR_RX_CTL_AM;
+ }
+
+ sr_write_cmd_async(dev, SR_CMD_WRITE_RX_CTL, rx_ctl, 0, 0, NULL);
+}
+
+static int sr_mdio_read(struct net_device *net, int phy_id, int loc)
+{
+ struct usbnet *dev = netdev_priv(net);
+ __le16 res;
+
+ mutex_lock(&dev->phy_mutex);
+ sr_set_sw_mii(dev);
+ sr_read_cmd(dev, SR_CMD_READ_MII_REG, phy_id, (__u16)loc, 2, &res);
+ sr_set_hw_mii(dev);
+ mutex_unlock(&dev->phy_mutex);
+
+ netdev_dbg(dev->net,
+ "%s : phy_id=0x%02x, loc=0x%02x, returns=0x%04x\n", __func__,
+ phy_id, loc, le16_to_cpu(res));
+
+ return le16_to_cpu(res);
+}
+
+static void
+sr_mdio_write(struct net_device *net, int phy_id, int loc, int val)
+{
+ struct usbnet *dev = netdev_priv(net);
+ __le16 res = cpu_to_le16(val);
+
+ netdev_dbg(dev->net,
+ "%s : phy_id=0x%02x, loc=0x%02x, val=0x%04x\n", __func__,
+ phy_id, loc, val);
+ mutex_lock(&dev->phy_mutex);
+ sr_set_sw_mii(dev);
+ sr_write_cmd(dev, SR_CMD_WRITE_MII_REG, phy_id, (__u16)loc, 2, &res);
+ sr_set_hw_mii(dev);
+ mutex_unlock(&dev->phy_mutex);
+}
+
+/* Get the PHY Identifier from the PHYSID1 & PHYSID2 MII registers */
+static u32 sr_get_phyid(struct usbnet *dev)
+{
+ int phy_reg;
+ u32 phy_id;
+ int i;
+
+ /* Poll for the rare case the FW or phy isn't ready yet. */
+ for (i = 0; i < 100; i++) {
+ phy_reg = sr_mdio_read(dev->net, dev->mii.phy_id, MII_PHYSID1);
+ if (phy_reg != 0 && phy_reg != 0xFFFF)
+ break;
+ mdelay(1);
+ }
+
+ if (phy_reg <= 0 || phy_reg == 0xFFFF)
+ return 0;
+
+ phy_id = (phy_reg & 0xffff) << 16;
+
+ phy_reg = sr_mdio_read(dev->net, dev->mii.phy_id, MII_PHYSID2);
+ if (phy_reg < 0)
+ return 0;
+
+ phy_id |= (phy_reg & 0xffff);
+
+ return phy_id;
+}
+
+static void
+sr_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo)
+{
+ struct usbnet *dev = netdev_priv(net);
+ u8 opt;
+
+ if (sr_read_cmd(dev, SR_CMD_READ_MONITOR_MODE, 0, 0, 1, &opt) < 0) {
+ wolinfo->supported = 0;
+ wolinfo->wolopts = 0;
+ return;
+ }
+ wolinfo->supported = WAKE_PHY | WAKE_MAGIC;
+ wolinfo->wolopts = 0;
+ if (opt & SR_MONITOR_LINK)
+ wolinfo->wolopts |= WAKE_PHY;
+ if (opt & SR_MONITOR_MAGIC)
+ wolinfo->wolopts |= WAKE_MAGIC;
+}
+
+static int
+sr_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo)
+{
+ struct usbnet *dev = netdev_priv(net);
+ u8 opt = 0;
+
+ if (wolinfo->wolopts & WAKE_PHY)
+ opt |= SR_MONITOR_LINK;
+ if (wolinfo->wolopts & WAKE_MAGIC)
+ opt |= SR_MONITOR_MAGIC;
+
+ if (sr_write_cmd(dev, SR_CMD_WRITE_MONITOR_MODE,
+ opt, 0, 0, NULL) < 0)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int sr_get_eeprom_len(struct net_device *net)
+{
+ struct usbnet *dev = netdev_priv(net);
+ struct sr_data *data = (struct sr_data *)&dev->data;
+
+ return data->eeprom_len;
+}
+
+static int sr_get_eeprom(struct net_device *net,
+ struct ethtool_eeprom *eeprom, u8 *data)
+{
+ struct usbnet *dev = netdev_priv(net);
+ __le16 *ebuf = (__le16 *)data;
+ int ret;
+ int i;
+
+ /* Crude hack to ensure that we don't overwrite memory
+ * if an odd length is supplied
+ */
+ if (eeprom->len % 2)
+ return -EINVAL;
+
+ eeprom->magic = SR_EEPROM_MAGIC;
+
+ /* sr9800 returns 2 bytes from eeprom on read */
+ for (i = 0; i < eeprom->len / 2; i++) {
+ ret = sr_read_cmd(dev, SR_CMD_READ_EEPROM, eeprom->offset + i,
+ 0, 2, &ebuf[i]);
+ if (ret < 0)
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static void sr_get_drvinfo(struct net_device *net,
+ struct ethtool_drvinfo *info)
+{
+ struct usbnet *dev = netdev_priv(net);
+ struct sr_data *data = (struct sr_data *)&dev->data;
+
+ /* Inherit standard device info */
+ usbnet_get_drvinfo(net, info);
+ strncpy(info->driver, DRIVER_NAME, sizeof(info->driver));
+ strncpy(info->version, DRIVER_VERSION, sizeof(info->version));
+ info->eedump_len = data->eeprom_len;
+}
+
+static u32 sr_get_link(struct net_device *net)
+{
+ struct usbnet *dev = netdev_priv(net);
+
+ return mii_link_ok(&dev->mii);
+}
+
+static int sr_ioctl(struct net_device *net, struct ifreq *rq, int cmd)
+{
+ struct usbnet *dev = netdev_priv(net);
+
+ return generic_mii_ioctl(&dev->mii, if_mii(rq), cmd, NULL);
+}
+
+static int sr_set_mac_address(struct net_device *net, void *p)
+{
+ struct usbnet *dev = netdev_priv(net);
+ struct sr_data *data = (struct sr_data *)&dev->data;
+ struct sockaddr *addr = p;
+
+ if (netif_running(net))
+ return -EBUSY;
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+
+ memcpy(net->dev_addr, addr->sa_data, ETH_ALEN);
+
+ /* We use the 20 byte dev->data
+ * for our 6 byte mac buffer
+ * to avoid allocating memory that
+ * is tricky to free later
+ */
+ memcpy(data->mac_addr, addr->sa_data, ETH_ALEN);
+ sr_write_cmd_async(dev, SR_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN,
+ data->mac_addr);
+
+ return 0;
+}
+
+static const struct ethtool_ops sr9800_ethtool_ops = {
+ .get_drvinfo = sr_get_drvinfo,
+ .get_link = sr_get_link,
+ .get_msglevel = usbnet_get_msglevel,
+ .set_msglevel = usbnet_set_msglevel,
+ .get_wol = sr_get_wol,
+ .set_wol = sr_set_wol,
+ .get_eeprom_len = sr_get_eeprom_len,
+ .get_eeprom = sr_get_eeprom,
+ .get_settings = usbnet_get_settings,
+ .set_settings = usbnet_set_settings,
+ .nway_reset = usbnet_nway_reset,
+};
+
+static int sr9800_link_reset(struct usbnet *dev)
+{
+ struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET };
+ u16 mode;
+
+ mii_check_media(&dev->mii, 1, 1);
+ mii_ethtool_gset(&dev->mii, &ecmd);
+ mode = SR9800_MEDIUM_DEFAULT;
+
+ if (ethtool_cmd_speed(&ecmd) != SPEED_100)
+ mode &= ~SR_MEDIUM_PS;
+
+ if (ecmd.duplex != DUPLEX_FULL)
+ mode &= ~SR_MEDIUM_FD;
+
+ netdev_dbg(dev->net, "%s : speed: %u duplex: %d mode: 0x%04x\n",
+ __func__, ethtool_cmd_speed(&ecmd), ecmd.duplex, mode);
+
+ sr_write_medium_mode(dev, mode);
+
+ return 0;
+}
+
+
+static int sr9800_set_default_mode(struct usbnet *dev)
+{
+ u16 rx_ctl;
+ int ret;
+
+ sr_mdio_write(dev->net, dev->mii.phy_id, MII_BMCR, BMCR_RESET);
+ sr_mdio_write(dev->net, dev->mii.phy_id, MII_ADVERTISE,
+ ADVERTISE_ALL | ADVERTISE_CSMA);
+ mii_nway_restart(&dev->mii);
+
+ ret = sr_write_medium_mode(dev, SR9800_MEDIUM_DEFAULT);
+ if (ret < 0)
+ goto out;
+
+ ret = sr_write_cmd(dev, SR_CMD_WRITE_IPG012,
+ SR9800_IPG0_DEFAULT | SR9800_IPG1_DEFAULT,
+ SR9800_IPG2_DEFAULT, 0, NULL);
+ if (ret < 0) {
+ netdev_dbg(dev->net, "Write IPG,IPG1,IPG2 failed: %d\n", ret);
+ goto out;
+ }
+
+ /* Set RX_CTL to default values with 2k buffer, and enable cactus */
+ ret = sr_write_rx_ctl(dev, SR_DEFAULT_RX_CTL);
+ if (ret < 0)
+ goto out;
+
+ rx_ctl = sr_read_rx_ctl(dev);
+ netdev_dbg(dev->net, "RX_CTL is 0x%04x after all initializations\n",
+ rx_ctl);
+
+ rx_ctl = sr_read_medium_status(dev);
+ netdev_dbg(dev->net, "Medium Status:0x%04x after all initializations\n",
+ rx_ctl);
+
+ return 0;
+out:
+ return ret;
+}
+
+static int sr9800_reset(struct usbnet *dev)
+{
+ struct sr_data *data = (struct sr_data *)&dev->data;
+ int ret, embd_phy;
+ u16 rx_ctl;
+
+ ret = sr_write_gpio(dev,
+ SR_GPIO_RSE | SR_GPIO_GPO_2 | SR_GPIO_GPO2EN, 5);
+ if (ret < 0)
+ goto out;
+
+ embd_phy = ((sr_get_phy_addr(dev) & 0x1f) == 0x10 ? 1 : 0);
+
+ ret = sr_write_cmd(dev, SR_CMD_SW_PHY_SELECT, embd_phy, 0, 0, NULL);
+ if (ret < 0) {
+ netdev_dbg(dev->net, "Select PHY #1 failed: %d\n", ret);
+ goto out;
+ }
+
+ ret = sr_sw_reset(dev, SR_SWRESET_IPPD | SR_SWRESET_PRL);
+ if (ret < 0)
+ goto out;
+
+ msleep(150);
+
+ ret = sr_sw_reset(dev, SR_SWRESET_CLEAR);
+ if (ret < 0)
+ goto out;
+
+ msleep(150);
+
+ if (embd_phy) {
+ ret = sr_sw_reset(dev, SR_SWRESET_IPRL);
+ if (ret < 0)
+ goto out;
+ } else {
+ ret = sr_sw_reset(dev, SR_SWRESET_PRTE);
+ if (ret < 0)
+ goto out;
+ }
+
+ msleep(150);
+ rx_ctl = sr_read_rx_ctl(dev);
+ netdev_dbg(dev->net, "RX_CTL is 0x%04x after software reset\n", rx_ctl);
+ ret = sr_write_rx_ctl(dev, 0x0000);
+ if (ret < 0)
+ goto out;
+
+ rx_ctl = sr_read_rx_ctl(dev);
+ netdev_dbg(dev->net, "RX_CTL is 0x%04x setting to 0x0000\n", rx_ctl);
+
+ ret = sr_sw_reset(dev, SR_SWRESET_PRL);
+ if (ret < 0)
+ goto out;
+
+ msleep(150);
+
+ ret = sr_sw_reset(dev, SR_SWRESET_IPRL | SR_SWRESET_PRL);
+ if (ret < 0)
+ goto out;
+
+ msleep(150);
+
+ ret = sr9800_set_default_mode(dev);
+ if (ret < 0)
+ goto out;
+
+ /* Rewrite MAC address */
+ memcpy(data->mac_addr, dev->net->dev_addr, ETH_ALEN);
+ ret = sr_write_cmd(dev, SR_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN,
+ data->mac_addr);
+ if (ret < 0)
+ goto out;
+
+ return 0;
+
+out:
+ return ret;
+}
+
+static const struct net_device_ops sr9800_netdev_ops = {
+ .ndo_open = usbnet_open,
+ .ndo_stop = usbnet_stop,
+ .ndo_start_xmit = usbnet_start_xmit,
+ .ndo_tx_timeout = usbnet_tx_timeout,
+ .ndo_change_mtu = usbnet_change_mtu,
+ .ndo_set_mac_address = sr_set_mac_address,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_do_ioctl = sr_ioctl,
+ .ndo_set_rx_mode = sr_set_multicast,
+};
+
+static int sr9800_phy_powerup(struct usbnet *dev)
+{
+ int ret;
+
+ /* set the embedded Ethernet PHY in power-down state */
+ ret = sr_sw_reset(dev, SR_SWRESET_IPPD | SR_SWRESET_IPRL);
+ if (ret < 0) {
+ netdev_err(dev->net, "Failed to power down PHY : %d\n", ret);
+ return ret;
+ }
+ msleep(20);
+
+ /* set the embedded Ethernet PHY in power-up state */
+ ret = sr_sw_reset(dev, SR_SWRESET_IPRL);
+ if (ret < 0) {
+ netdev_err(dev->net, "Failed to reset PHY: %d\n", ret);
+ return ret;
+ }
+ msleep(600);
+
+ /* set the embedded Ethernet PHY in reset state */
+ ret = sr_sw_reset(dev, SR_SWRESET_CLEAR);
+ if (ret < 0) {
+ netdev_err(dev->net, "Failed to power up PHY: %d\n", ret);
+ return ret;
+ }
+ msleep(20);
+
+ /* set the embedded Ethernet PHY in power-up state */
+ ret = sr_sw_reset(dev, SR_SWRESET_IPRL);
+ if (ret < 0) {
+ netdev_err(dev->net, "Failed to reset PHY: %d\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int sr9800_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+ struct sr_data *data = (struct sr_data *)&dev->data;
+ u16 led01_mux, led23_mux;
+ int ret, embd_phy;
+ u32 phyid;
+ u16 rx_ctl;
+
+ data->eeprom_len = SR9800_EEPROM_LEN;
+
+ usbnet_get_endpoints(dev, intf);
+
+ /* LED Setting Rule :
+ * AABB:CCDD
+ * AA : MFA0(LED0)
+ * BB : MFA1(LED1)
+ * CC : MFA2(LED2), Reserved for SR9800
+ * DD : MFA3(LED3), Reserved for SR9800
+ */
+ led01_mux = (SR_LED_MUX_LINK_ACTIVE << 8) | SR_LED_MUX_LINK;
+ led23_mux = (SR_LED_MUX_LINK_ACTIVE << 8) | SR_LED_MUX_TX_ACTIVE;
+ ret = sr_write_cmd(dev, SR_CMD_LED_MUX, led01_mux, led23_mux, 0, NULL);
+ if (ret < 0) {
+ netdev_err(dev->net, "set LINK LED failed : %d\n", ret);
+ goto out;
+ }
+
+ /* Get the MAC address */
+ ret = sr_read_cmd(dev, SR_CMD_READ_NODE_ID, 0, 0, ETH_ALEN,
+ dev->net->dev_addr);
+ if (ret < 0) {
+ netdev_dbg(dev->net, "Failed to read MAC address: %d\n", ret);
+ return ret;
+ }
+ netdev_dbg(dev->net, "mac addr : %pM\n", dev->net->dev_addr);
+
+ /* Initialize MII structure */
+ dev->mii.dev = dev->net;
+ dev->mii.mdio_read = sr_mdio_read;
+ dev->mii.mdio_write = sr_mdio_write;
+ dev->mii.phy_id_mask = 0x1f;
+ dev->mii.reg_num_mask = 0x1f;
+ dev->mii.phy_id = sr_get_phy_addr(dev);
+
+ dev->net->netdev_ops = &sr9800_netdev_ops;
+ dev->net->ethtool_ops = &sr9800_ethtool_ops;
+
+ embd_phy = ((dev->mii.phy_id & 0x1f) == 0x10 ? 1 : 0);
+ /* Reset the PHY to normal operation mode */
+ ret = sr_write_cmd(dev, SR_CMD_SW_PHY_SELECT, embd_phy, 0, 0, NULL);
+ if (ret < 0) {
+ netdev_dbg(dev->net, "Select PHY #1 failed: %d\n", ret);
+ return ret;
+ }
+
+ /* Init PHY routine */
+ ret = sr9800_phy_powerup(dev);
+ if (ret < 0)
+ goto out;
+
+ rx_ctl = sr_read_rx_ctl(dev);
+ netdev_dbg(dev->net, "RX_CTL is 0x%04x after software reset\n", rx_ctl);
+ ret = sr_write_rx_ctl(dev, 0x0000);
+ if (ret < 0)
+ goto out;
+
+ rx_ctl = sr_read_rx_ctl(dev);
+ netdev_dbg(dev->net, "RX_CTL is 0x%04x setting to 0x0000\n", rx_ctl);
+
+ /* Read PHYID register *AFTER* the PHY was reset properly */
+ phyid = sr_get_phyid(dev);
+ netdev_dbg(dev->net, "PHYID=0x%08x\n", phyid);
+
+ /* medium mode setting */
+ ret = sr9800_set_default_mode(dev);
+ if (ret < 0)
+ goto out;
+
+ if (dev->udev->speed == USB_SPEED_HIGH) {
+ ret = sr_write_cmd(dev, SR_CMD_BULKIN_SIZE,
+ SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_4K].byte_cnt,
+ SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_4K].threshold,
+ 0, NULL);
+ if (ret < 0) {
+ netdev_err(dev->net, "Reset RX_CTL failed: %d\n", ret);
+ goto out;
+ }
+ dev->rx_urb_size =
+ SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_4K].size;
+ } else {
+ ret = sr_write_cmd(dev, SR_CMD_BULKIN_SIZE,
+ SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_2K].byte_cnt,
+ SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_2K].threshold,
+ 0, NULL);
+ if (ret < 0) {
+ netdev_err(dev->net, "Reset RX_CTL failed: %d\n", ret);
+ goto out;
+ }
+ dev->rx_urb_size =
+ SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_2K].size;
+ }
+ netdev_dbg(dev->net, "%s : setting rx_urb_size with : %zu\n", __func__,
+ dev->rx_urb_size);
+ return 0;
+
+out:
+ return ret;
+}
+
+static const struct driver_info sr9800_driver_info = {
+ .description = "CoreChip SR9800 USB 2.0 Ethernet",
+ .bind = sr9800_bind,
+ .status = sr_status,
+ .link_reset = sr9800_link_reset,
+ .reset = sr9800_reset,
+ .flags = DRIVER_FLAG,
+ .rx_fixup = sr_rx_fixup,
+ .tx_fixup = sr_tx_fixup,
+};
+
+static const struct usb_device_id products[] = {
+ {
+ USB_DEVICE(0x0fe6, 0x9800), /* SR9800 Device */
+ .driver_info = (unsigned long) &sr9800_driver_info,
+ },
+ {}, /* END */
+};
+
+MODULE_DEVICE_TABLE(usb, products);
+
+static struct usb_driver sr_driver = {
+ .name = DRIVER_NAME,
+ .id_table = products,
+ .probe = usbnet_probe,
+ .suspend = usbnet_suspend,
+ .resume = usbnet_resume,
+ .disconnect = usbnet_disconnect,
+ .supports_autosuspend = 1,
+};
+
+module_usb_driver(sr_driver);
+
+MODULE_AUTHOR("Liu Junliang <liujunliang_ljl@163.com");
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_DESCRIPTION("SR9800 USB 2.0 USB2NET Dev : http://www.corechip-sz.com");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/usb/sr9800.h b/drivers/net/usb/sr9800.h
new file mode 100644
index 0000000..18f6702
--- /dev/null
+++ b/drivers/net/usb/sr9800.h
@@ -0,0 +1,202 @@
+/* CoreChip-sz SR9800 one chip USB 2.0 Ethernet Devices
+ *
+ * Author : Liu Junliang <liujunliang_ljl@163.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef _SR9800_H
+#define _SR9800_H
+
+/* SR9800 spec. command table on Linux Platform */
+
+/* command : Software Station Management Control Reg */
+#define SR_CMD_SET_SW_MII 0x06
+/* command : PHY Read Reg */
+#define SR_CMD_READ_MII_REG 0x07
+/* command : PHY Write Reg */
+#define SR_CMD_WRITE_MII_REG 0x08
+/* command : Hardware Station Management Control Reg */
+#define SR_CMD_SET_HW_MII 0x0a
+/* command : SROM Read Reg */
+#define SR_CMD_READ_EEPROM 0x0b
+/* command : SROM Write Reg */
+#define SR_CMD_WRITE_EEPROM 0x0c
+/* command : SROM Write Enable Reg */
+#define SR_CMD_WRITE_ENABLE 0x0d
+/* command : SROM Write Disable Reg */
+#define SR_CMD_WRITE_DISABLE 0x0e
+/* command : RX Control Read Reg */
+#define SR_CMD_READ_RX_CTL 0x0f
+#define SR_RX_CTL_PRO (1 << 0)
+#define SR_RX_CTL_AMALL (1 << 1)
+#define SR_RX_CTL_SEP (1 << 2)
+#define SR_RX_CTL_AB (1 << 3)
+#define SR_RX_CTL_AM (1 << 4)
+#define SR_RX_CTL_AP (1 << 5)
+#define SR_RX_CTL_ARP (1 << 6)
+#define SR_RX_CTL_SO (1 << 7)
+#define SR_RX_CTL_RH1M (1 << 8)
+#define SR_RX_CTL_RH2M (1 << 9)
+#define SR_RX_CTL_RH3M (1 << 10)
+/* command : RX Control Write Reg */
+#define SR_CMD_WRITE_RX_CTL 0x10
+/* command : IPG0/IPG1/IPG2 Control Read Reg */
+#define SR_CMD_READ_IPG012 0x11
+/* command : IPG0/IPG1/IPG2 Control Write Reg */
+#define SR_CMD_WRITE_IPG012 0x12
+/* command : Node ID Read Reg */
+#define SR_CMD_READ_NODE_ID 0x13
+/* command : Node ID Write Reg */
+#define SR_CMD_WRITE_NODE_ID 0x14
+/* command : Multicast Filter Array Read Reg */
+#define SR_CMD_READ_MULTI_FILTER 0x15
+/* command : Multicast Filter Array Write Reg */
+#define SR_CMD_WRITE_MULTI_FILTER 0x16
+/* command : Eth/HomePNA PHY Address Reg */
+#define SR_CMD_READ_PHY_ID 0x19
+/* command : Medium Status Read Reg */
+#define SR_CMD_READ_MEDIUM_STATUS 0x1a
+#define SR_MONITOR_LINK (1 << 1)
+#define SR_MONITOR_MAGIC (1 << 2)
+#define SR_MONITOR_HSFS (1 << 4)
+/* command : Medium Status Write Reg */
+#define SR_CMD_WRITE_MEDIUM_MODE 0x1b
+#define SR_MEDIUM_GM (1 << 0)
+#define SR_MEDIUM_FD (1 << 1)
+#define SR_MEDIUM_AC (1 << 2)
+#define SR_MEDIUM_ENCK (1 << 3)
+#define SR_MEDIUM_RFC (1 << 4)
+#define SR_MEDIUM_TFC (1 << 5)
+#define SR_MEDIUM_JFE (1 << 6)
+#define SR_MEDIUM_PF (1 << 7)
+#define SR_MEDIUM_RE (1 << 8)
+#define SR_MEDIUM_PS (1 << 9)
+#define SR_MEDIUM_RSV (1 << 10)
+#define SR_MEDIUM_SBP (1 << 11)
+#define SR_MEDIUM_SM (1 << 12)
+/* command : Monitor Mode Status Read Reg */
+#define SR_CMD_READ_MONITOR_MODE 0x1c
+/* command : Monitor Mode Status Write Reg */
+#define SR_CMD_WRITE_MONITOR_MODE 0x1d
+/* command : GPIO Status Read Reg */
+#define SR_CMD_READ_GPIOS 0x1e
+#define SR_GPIO_GPO0EN (1 << 0) /* GPIO0 Output enable */
+#define SR_GPIO_GPO_0 (1 << 1) /* GPIO0 Output value */
+#define SR_GPIO_GPO1EN (1 << 2) /* GPIO1 Output enable */
+#define SR_GPIO_GPO_1 (1 << 3) /* GPIO1 Output value */
+#define SR_GPIO_GPO2EN (1 << 4) /* GPIO2 Output enable */
+#define SR_GPIO_GPO_2 (1 << 5) /* GPIO2 Output value */
+#define SR_GPIO_RESERVED (1 << 6) /* Reserved */
+#define SR_GPIO_RSE (1 << 7) /* Reload serial EEPROM */
+/* command : GPIO Status Write Reg */
+#define SR_CMD_WRITE_GPIOS 0x1f
+/* command : Eth PHY Power and Reset Control Reg */
+#define SR_CMD_SW_RESET 0x20
+#define SR_SWRESET_CLEAR 0x00
+#define SR_SWRESET_RR (1 << 0)
+#define SR_SWRESET_RT (1 << 1)
+#define SR_SWRESET_PRTE (1 << 2)
+#define SR_SWRESET_PRL (1 << 3)
+#define SR_SWRESET_BZ (1 << 4)
+#define SR_SWRESET_IPRL (1 << 5)
+#define SR_SWRESET_IPPD (1 << 6)
+/* command : Software Interface Selection Status Read Reg */
+#define SR_CMD_SW_PHY_STATUS 0x21
+/* command : Software Interface Selection Status Write Reg */
+#define SR_CMD_SW_PHY_SELECT 0x22
+/* command : BULK in Buffer Size Reg */
+#define SR_CMD_BULKIN_SIZE 0x2A
+/* command : LED_MUX Control Reg */
+#define SR_CMD_LED_MUX 0x70
+#define SR_LED_MUX_TX_ACTIVE (1 << 0)
+#define SR_LED_MUX_RX_ACTIVE (1 << 1)
+#define SR_LED_MUX_COLLISION (1 << 2)
+#define SR_LED_MUX_DUP_COL (1 << 3)
+#define SR_LED_MUX_DUP (1 << 4)
+#define SR_LED_MUX_SPEED (1 << 5)
+#define SR_LED_MUX_LINK_ACTIVE (1 << 6)
+#define SR_LED_MUX_LINK (1 << 7)
+
+/* Register Access Flags */
+#define SR_REQ_RD_REG (USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE)
+#define SR_REQ_WR_REG (USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE)
+
+/* Multicast Filter Array size & Max Number */
+#define SR_MCAST_FILTER_SIZE 8
+#define SR_MAX_MCAST 64
+
+/* IPG0/1/2 Default Value */
+#define SR9800_IPG0_DEFAULT 0x15
+#define SR9800_IPG1_DEFAULT 0x0c
+#define SR9800_IPG2_DEFAULT 0x12
+
+/* Medium Status Default Mode */
+#define SR9800_MEDIUM_DEFAULT \
+ (SR_MEDIUM_FD | SR_MEDIUM_RFC | \
+ SR_MEDIUM_TFC | SR_MEDIUM_PS | \
+ SR_MEDIUM_AC | SR_MEDIUM_RE)
+
+/* RX Control Default Setting */
+#define SR_DEFAULT_RX_CTL \
+ (SR_RX_CTL_SO | SR_RX_CTL_AB | SR_RX_CTL_RH1M)
+
+/* EEPROM Magic Number & EEPROM Size */
+#define SR_EEPROM_MAGIC 0xdeadbeef
+#define SR9800_EEPROM_LEN 0xff
+
+/* SR9800 Driver Version and Driver Name */
+#define DRIVER_VERSION "11-Nov-2013"
+#define DRIVER_NAME "CoreChips"
+#define DRIVER_FLAG \
+ (FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET)
+
+/* SR9800 BULKIN Buffer Size */
+#define SR9800_MAX_BULKIN_2K 0
+#define SR9800_MAX_BULKIN_4K 1
+#define SR9800_MAX_BULKIN_6K 2
+#define SR9800_MAX_BULKIN_8K 3
+#define SR9800_MAX_BULKIN_16K 4
+#define SR9800_MAX_BULKIN_20K 5
+#define SR9800_MAX_BULKIN_24K 6
+#define SR9800_MAX_BULKIN_32K 7
+
+struct {unsigned short size, byte_cnt, threshold; } SR9800_BULKIN_SIZE[] = {
+ /* 2k */
+ {2048, 0x8000, 0x8001},
+ /* 4k */
+ {4096, 0x8100, 0x8147},
+ /* 6k */
+ {6144, 0x8200, 0x81EB},
+ /* 8k */
+ {8192, 0x8300, 0x83D7},
+ /* 16 */
+ {16384, 0x8400, 0x851E},
+ /* 20k */
+ {20480, 0x8500, 0x8666},
+ /* 24k */
+ {24576, 0x8600, 0x87AE},
+ /* 32k */
+ {32768, 0x8700, 0x8A3D},
+};
+
+/* This structure cannot exceed sizeof(unsigned long [5]) AKA 20 bytes */
+struct sr_data {
+ u8 multi_filter[SR_MCAST_FILTER_SIZE];
+ u8 mac_addr[ETH_ALEN];
+ u8 phymode;
+ u8 ledmode;
+ u8 eeprom_len;
+};
+
+struct sr9800_int_data {
+ __le16 res1;
+ u8 link;
+ __le16 res2;
+ u8 status;
+ __le16 res3;
+} __packed;
+
+#endif /* _SR9800_H */
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 4671da7..f9e96c4 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -542,17 +542,19 @@
}
// else network stack removes extra byte if we forced a short packet
- if (skb->len) {
- /* all data was already cloned from skb inside the driver */
- if (dev->driver_info->flags & FLAG_MULTI_PACKET)
- dev_kfree_skb_any(skb);
- else
- usbnet_skb_return(dev, skb);
+ /* all data was already cloned from skb inside the driver */
+ if (dev->driver_info->flags & FLAG_MULTI_PACKET)
+ goto done;
+
+ if (skb->len < ETH_HLEN) {
+ dev->net->stats.rx_errors++;
+ dev->net->stats.rx_length_errors++;
+ netif_dbg(dev, rx_err, dev->net, "rx length %d\n", skb->len);
+ } else {
+ usbnet_skb_return(dev, skb);
return;
}
- netif_dbg(dev, rx_err, dev->net, "drop\n");
- dev->net->stats.rx_errors++;
done:
skb_queue_tail(&dev->done, skb);
}
@@ -574,13 +576,6 @@
switch (urb_status) {
/* success */
case 0:
- if (skb->len < dev->net->hard_header_len) {
- state = rx_cleanup;
- dev->net->stats.rx_errors++;
- dev->net->stats.rx_length_errors++;
- netif_dbg(dev, rx_err, dev->net,
- "rx length %d\n", skb->len);
- }
break;
/* stalls need manual reset. this is rare ... except that
@@ -757,14 +752,12 @@
// precondition: never called in_interrupt
static void usbnet_terminate_urbs(struct usbnet *dev)
{
- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(unlink_wakeup);
DECLARE_WAITQUEUE(wait, current);
int temp;
/* ensure there are no more active urbs */
- add_wait_queue(&unlink_wakeup, &wait);
+ add_wait_queue(&dev->wait, &wait);
set_current_state(TASK_UNINTERRUPTIBLE);
- dev->wait = &unlink_wakeup;
temp = unlink_urbs(dev, &dev->txq) +
unlink_urbs(dev, &dev->rxq);
@@ -778,15 +771,14 @@
"waited for %d urb completions\n", temp);
}
set_current_state(TASK_RUNNING);
- dev->wait = NULL;
- remove_wait_queue(&unlink_wakeup, &wait);
+ remove_wait_queue(&dev->wait, &wait);
}
int usbnet_stop (struct net_device *net)
{
struct usbnet *dev = netdev_priv(net);
struct driver_info *info = dev->driver_info;
- int retval;
+ int retval, pm;
clear_bit(EVENT_DEV_OPEN, &dev->flags);
netif_stop_queue (net);
@@ -796,6 +788,8 @@
net->stats.rx_packets, net->stats.tx_packets,
net->stats.rx_errors, net->stats.tx_errors);
+ /* to not race resume */
+ pm = usb_autopm_get_interface(dev->intf);
/* allow minidriver to stop correctly (wireless devices to turn off
* radio etc) */
if (info->stop) {
@@ -822,6 +816,9 @@
dev->flags = 0;
del_timer_sync (&dev->delay);
tasklet_kill (&dev->bh);
+ if (!pm)
+ usb_autopm_put_interface(dev->intf);
+
if (info->manage_power &&
!test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags))
info->manage_power(dev, 0);
@@ -1442,11 +1439,12 @@
/* restart RX again after disabling due to high error rate */
clear_bit(EVENT_RX_KILL, &dev->flags);
- // waiting for all pending urbs to complete?
- if (dev->wait) {
- if ((dev->txq.qlen + dev->rxq.qlen + dev->done.qlen) == 0) {
- wake_up (dev->wait);
- }
+ /* waiting for all pending urbs to complete?
+ * only then can we forgo submitting anew
+ */
+ if (waitqueue_active(&dev->wait)) {
+ if (dev->txq.qlen + dev->rxq.qlen + dev->done.qlen == 0)
+ wake_up_all(&dev->wait);
// or are we maybe short a few urbs?
} else if (netif_running (dev->net) &&
@@ -1585,6 +1583,7 @@
dev->driver_name = name;
dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV
| NETIF_MSG_PROBE | NETIF_MSG_LINK);
+ init_waitqueue_head(&dev->wait);
skb_queue_head_init (&dev->rxq);
skb_queue_head_init (&dev->txq);
skb_queue_head_init (&dev->done);
@@ -1796,9 +1795,10 @@
spin_unlock_irq(&dev->txq.lock);
if (test_bit(EVENT_DEV_OPEN, &dev->flags)) {
- /* handle remote wakeup ASAP */
- if (!dev->wait &&
- netif_device_present(dev->net) &&
+ /* handle remote wakeup ASAP
+ * we cannot race against stop
+ */
+ if (netif_device_present(dev->net) &&
!timer_pending(&dev->delay) &&
!test_bit(EVENT_RX_HALT, &dev->flags))
rx_alloc_submit(dev, GFP_NOIO);
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 2ec2041..b4a10bc 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -14,6 +14,7 @@
#include <linux/etherdevice.h>
#include <linux/u64_stats_sync.h>
+#include <net/rtnetlink.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <linux/veth.h>
@@ -155,10 +156,10 @@
unsigned int start;
do {
- start = u64_stats_fetch_begin_bh(&stats->syncp);
+ start = u64_stats_fetch_begin_irq(&stats->syncp);
packets = stats->packets;
bytes = stats->bytes;
- } while (u64_stats_fetch_retry_bh(&stats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&stats->syncp, start));
result->packets += packets;
result->bytes += bytes;
}
@@ -235,18 +236,9 @@
static int veth_dev_init(struct net_device *dev)
{
- int i;
-
- dev->vstats = alloc_percpu(struct pcpu_vstats);
+ dev->vstats = netdev_alloc_pcpu_stats(struct pcpu_vstats);
if (!dev->vstats)
return -ENOMEM;
-
- for_each_possible_cpu(i) {
- struct pcpu_vstats *veth_stats;
- veth_stats = per_cpu_ptr(dev->vstats, i);
- u64_stats_init(&veth_stats->syncp);
- }
-
return 0;
}
@@ -285,7 +277,11 @@
dev->ethtool_ops = &veth_ethtool_ops;
dev->features |= NETIF_F_LLTX;
dev->features |= VETH_FEATURES;
- dev->vlan_features = dev->features;
+ dev->vlan_features = dev->features &
+ ~(NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_HW_VLAN_STAG_RX);
dev->destructor = veth_dev_free;
dev->hw_features = VETH_FEATURES;
@@ -332,10 +328,9 @@
nla_peer = data[VETH_INFO_PEER];
ifmp = nla_data(nla_peer);
- err = nla_parse(peer_tb, IFLA_MAX,
- nla_data(nla_peer) + sizeof(struct ifinfomsg),
- nla_len(nla_peer) - sizeof(struct ifinfomsg),
- ifla_policy);
+ err = rtnl_nla_parse_ifla(peer_tb,
+ nla_data(nla_peer) + sizeof(struct ifinfomsg),
+ nla_len(nla_peer) - sizeof(struct ifinfomsg));
if (err < 0)
return err;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d75f8ed..6f15d9b 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -671,8 +671,7 @@
if (err)
break;
} while (rq->vq->num_free);
- if (unlikely(!virtqueue_kick(rq->vq)))
- return false;
+ virtqueue_kick(rq->vq);
return !oom;
}
@@ -877,15 +876,16 @@
err = xmit_skb(sq, skb);
/* This should not happen! */
- if (unlikely(err) || unlikely(!virtqueue_kick(sq->vq))) {
+ if (unlikely(err)) {
dev->stats.tx_fifo_errors++;
if (net_ratelimit())
dev_warn(&dev->dev,
"Unexpected TXQ (%d) queue failure: %d\n", qnum, err);
dev->stats.tx_dropped++;
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
+ virtqueue_kick(sq->vq);
/* Don't wait up for transmitted skbs to be freed. */
skb_orphan(skb);
@@ -1000,16 +1000,16 @@
u64 tpackets, tbytes, rpackets, rbytes;
do {
- start = u64_stats_fetch_begin_bh(&stats->tx_syncp);
+ start = u64_stats_fetch_begin_irq(&stats->tx_syncp);
tpackets = stats->tx_packets;
tbytes = stats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&stats->tx_syncp, start));
+ } while (u64_stats_fetch_retry_irq(&stats->tx_syncp, start));
do {
- start = u64_stats_fetch_begin_bh(&stats->rx_syncp);
+ start = u64_stats_fetch_begin_irq(&stats->rx_syncp);
rpackets = stats->rx_packets;
rbytes = stats->rx_bytes;
- } while (u64_stats_fetch_retry_bh(&stats->rx_syncp, start));
+ } while (u64_stats_fetch_retry_irq(&stats->rx_syncp, start));
tot->rx_packets += rpackets;
tot->tx_packets += tpackets;
@@ -1711,7 +1711,8 @@
/* If we can receive ANY GSO packets, we must allocate large ones. */
if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) ||
- virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
+ virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) ||
+ virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO))
vi->big_packets = true;
if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 3be786f..9739434 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1078,7 +1078,7 @@
spin_unlock_irqrestore(&tq->tx_lock, flags);
drop_pkt:
tq->stats.drop_total++;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -1762,11 +1762,20 @@
{
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
- if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE)
- vmxnet3_disable_all_intrs(adapter);
-
- vmxnet3_do_poll(adapter, adapter->rx_queue[0].rx_ring[0].size);
- vmxnet3_enable_all_intrs(adapter);
+ switch (adapter->intr.type) {
+#ifdef CONFIG_PCI_MSI
+ case VMXNET3_IT_MSIX: {
+ int i;
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ vmxnet3_msix_rx(0, &adapter->rx_queue[i]);
+ break;
+ }
+#endif
+ case VMXNET3_IT_MSI:
+ default:
+ vmxnet3_intr(0, adapter->netdev);
+ break;
+ }
}
#endif /* CONFIG_NET_POLL_CONTROLLER */
@@ -2729,47 +2738,35 @@
/*
* Enable MSIx vectors.
* Returns :
- * 0 on successful enabling of required vectors,
* VMXNET3_LINUX_MIN_MSIX_VECT when only minimum number of vectors required
- * could be enabled.
- * number of vectors which can be enabled otherwise (this number is smaller
+ * were enabled.
+ * number of vectors which were enabled otherwise (this number is greater
* than VMXNET3_LINUX_MIN_MSIX_VECT)
*/
static int
-vmxnet3_acquire_msix_vectors(struct vmxnet3_adapter *adapter,
- int vectors)
+vmxnet3_acquire_msix_vectors(struct vmxnet3_adapter *adapter, int nvec)
{
- int err = 0, vector_threshold;
- vector_threshold = VMXNET3_LINUX_MIN_MSIX_VECT;
+ int ret = pci_enable_msix_range(adapter->pdev,
+ adapter->intr.msix_entries, nvec, nvec);
- while (vectors >= vector_threshold) {
- err = pci_enable_msix(adapter->pdev, adapter->intr.msix_entries,
- vectors);
- if (!err) {
- adapter->intr.num_intrs = vectors;
- return 0;
- } else if (err < 0) {
- dev_err(&adapter->netdev->dev,
- "Failed to enable MSI-X, error: %d\n", err);
- vectors = 0;
- } else if (err < vector_threshold) {
- break;
- } else {
- /* If fails to enable required number of MSI-x vectors
- * try enabling minimum number of vectors required.
- */
- dev_err(&adapter->netdev->dev,
- "Failed to enable %d MSI-X, trying %d instead\n",
- vectors, vector_threshold);
- vectors = vector_threshold;
- }
+ if (ret == -ENOSPC && nvec > VMXNET3_LINUX_MIN_MSIX_VECT) {
+ dev_err(&adapter->netdev->dev,
+ "Failed to enable %d MSI-X, trying %d\n",
+ nvec, VMXNET3_LINUX_MIN_MSIX_VECT);
+
+ ret = pci_enable_msix_range(adapter->pdev,
+ adapter->intr.msix_entries,
+ VMXNET3_LINUX_MIN_MSIX_VECT,
+ VMXNET3_LINUX_MIN_MSIX_VECT);
}
- dev_info(&adapter->pdev->dev,
- "Number of MSI-X interrupts which can be allocated "
- "is lower than min threshold required.\n");
- return err;
+ if (ret < 0) {
+ dev_err(&adapter->netdev->dev,
+ "Failed to enable MSI-X, error: %d\n", ret);
+ }
+
+ return ret;
}
@@ -2796,56 +2793,50 @@
#ifdef CONFIG_PCI_MSI
if (adapter->intr.type == VMXNET3_IT_MSIX) {
- int vector, err = 0;
+ int i, nvec;
- adapter->intr.num_intrs = (adapter->share_intr ==
- VMXNET3_INTR_TXSHARE) ? 1 :
- adapter->num_tx_queues;
- adapter->intr.num_intrs += (adapter->share_intr ==
- VMXNET3_INTR_BUDDYSHARE) ? 0 :
- adapter->num_rx_queues;
- adapter->intr.num_intrs += 1; /* for link event */
+ nvec = adapter->share_intr == VMXNET3_INTR_TXSHARE ?
+ 1 : adapter->num_tx_queues;
+ nvec += adapter->share_intr == VMXNET3_INTR_BUDDYSHARE ?
+ 0 : adapter->num_rx_queues;
+ nvec += 1; /* for link event */
+ nvec = nvec > VMXNET3_LINUX_MIN_MSIX_VECT ?
+ nvec : VMXNET3_LINUX_MIN_MSIX_VECT;
- adapter->intr.num_intrs = (adapter->intr.num_intrs >
- VMXNET3_LINUX_MIN_MSIX_VECT
- ? adapter->intr.num_intrs :
- VMXNET3_LINUX_MIN_MSIX_VECT);
+ for (i = 0; i < nvec; i++)
+ adapter->intr.msix_entries[i].entry = i;
- for (vector = 0; vector < adapter->intr.num_intrs; vector++)
- adapter->intr.msix_entries[vector].entry = vector;
+ nvec = vmxnet3_acquire_msix_vectors(adapter, nvec);
+ if (nvec < 0)
+ goto msix_err;
- err = vmxnet3_acquire_msix_vectors(adapter,
- adapter->intr.num_intrs);
/* If we cannot allocate one MSIx vector per queue
* then limit the number of rx queues to 1
*/
- if (err == VMXNET3_LINUX_MIN_MSIX_VECT) {
+ if (nvec == VMXNET3_LINUX_MIN_MSIX_VECT) {
if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE
|| adapter->num_rx_queues != 1) {
adapter->share_intr = VMXNET3_INTR_TXSHARE;
netdev_err(adapter->netdev,
"Number of rx queues : 1\n");
adapter->num_rx_queues = 1;
- adapter->intr.num_intrs =
- VMXNET3_LINUX_MIN_MSIX_VECT;
}
- return;
}
- if (!err)
- return;
+ adapter->intr.num_intrs = nvec;
+ return;
+
+msix_err:
/* If we cannot allocate MSIx vectors use only one rx queue */
dev_info(&adapter->pdev->dev,
"Failed to enable MSI-X, error %d. "
- "Limiting #rx queues to 1, try MSI.\n", err);
+ "Limiting #rx queues to 1, try MSI.\n", nvec);
adapter->intr.type = VMXNET3_IT_MSI;
}
if (adapter->intr.type == VMXNET3_IT_MSI) {
- int err;
- err = pci_enable_msi(adapter->pdev);
- if (!err) {
+ if (!pci_enable_msi(adapter->pdev)) {
adapter->num_rx_queues = 1;
adapter->intr.num_intrs = 1;
return;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 026a313..0d862a5 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -469,7 +469,6 @@
/* Look up Ethernet address in forwarding table */
static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan,
const u8 *mac)
-
{
struct hlist_head *head = vxlan_fdb_head(vxlan, mac);
struct vxlan_fdb *f;
@@ -596,10 +595,8 @@
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
- goto found;
}
-found:
type = eh->h_proto;
rcu_read_lock();
@@ -1135,7 +1132,6 @@
{
struct vxlan_sock *vs;
struct vxlanhdr *vxh;
- __be16 port;
/* Need Vxlan and inner Ethernet header to be present */
if (!pskb_may_pull(skb, VXLAN_HLEN))
@@ -1153,8 +1149,6 @@
if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB)))
goto drop;
- port = inet_sk(sk)->inet_sport;
-
vs = rcu_dereference_sk_user_data(sk);
if (!vs)
goto drop;
@@ -1321,6 +1315,9 @@
neigh_release(n);
+ if (reply == NULL)
+ goto out;
+
skb_reset_mac_header(reply);
__skb_pull(reply, skb_network_offset(reply));
reply->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1342,15 +1339,103 @@
}
#if IS_ENABLED(CONFIG_IPV6)
+
+static struct sk_buff *vxlan_na_create(struct sk_buff *request,
+ struct neighbour *n, bool isrouter)
+{
+ struct net_device *dev = request->dev;
+ struct sk_buff *reply;
+ struct nd_msg *ns, *na;
+ struct ipv6hdr *pip6;
+ u8 *daddr;
+ int na_olen = 8; /* opt hdr + ETH_ALEN for target */
+ int ns_olen;
+ int i, len;
+
+ if (dev == NULL)
+ return NULL;
+
+ len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
+ sizeof(*na) + na_olen + dev->needed_tailroom;
+ reply = alloc_skb(len, GFP_ATOMIC);
+ if (reply == NULL)
+ return NULL;
+
+ reply->protocol = htons(ETH_P_IPV6);
+ reply->dev = dev;
+ skb_reserve(reply, LL_RESERVED_SPACE(request->dev));
+ skb_push(reply, sizeof(struct ethhdr));
+ skb_set_mac_header(reply, 0);
+
+ ns = (struct nd_msg *)skb_transport_header(request);
+
+ daddr = eth_hdr(request)->h_source;
+ ns_olen = request->len - skb_transport_offset(request) - sizeof(*ns);
+ for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
+ if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
+ daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
+ break;
+ }
+ }
+
+ /* Ethernet header */
+ ether_addr_copy(eth_hdr(reply)->h_dest, daddr);
+ ether_addr_copy(eth_hdr(reply)->h_source, n->ha);
+ eth_hdr(reply)->h_proto = htons(ETH_P_IPV6);
+ reply->protocol = htons(ETH_P_IPV6);
+
+ skb_pull(reply, sizeof(struct ethhdr));
+ skb_set_network_header(reply, 0);
+ skb_put(reply, sizeof(struct ipv6hdr));
+
+ /* IPv6 header */
+
+ pip6 = ipv6_hdr(reply);
+ memset(pip6, 0, sizeof(struct ipv6hdr));
+ pip6->version = 6;
+ pip6->priority = ipv6_hdr(request)->priority;
+ pip6->nexthdr = IPPROTO_ICMPV6;
+ pip6->hop_limit = 255;
+ pip6->daddr = ipv6_hdr(request)->saddr;
+ pip6->saddr = *(struct in6_addr *)n->primary_key;
+
+ skb_pull(reply, sizeof(struct ipv6hdr));
+ skb_set_transport_header(reply, 0);
+
+ na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen);
+
+ /* Neighbor Advertisement */
+ memset(na, 0, sizeof(*na)+na_olen);
+ na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
+ na->icmph.icmp6_router = isrouter;
+ na->icmph.icmp6_override = 1;
+ na->icmph.icmp6_solicited = 1;
+ na->target = ns->target;
+ ether_addr_copy(&na->opt[2], n->ha);
+ na->opt[0] = ND_OPT_TARGET_LL_ADDR;
+ na->opt[1] = na_olen >> 3;
+
+ na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr,
+ &pip6->daddr, sizeof(*na)+na_olen, IPPROTO_ICMPV6,
+ csum_partial(na, sizeof(*na)+na_olen, 0));
+
+ pip6->payload_len = htons(sizeof(*na)+na_olen);
+
+ skb_push(reply, sizeof(struct ipv6hdr));
+
+ reply->ip_summed = CHECKSUM_UNNECESSARY;
+
+ return reply;
+}
+
static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct neighbour *n;
- union vxlan_addr ipa;
+ struct nd_msg *msg;
const struct ipv6hdr *iphdr;
const struct in6_addr *saddr, *daddr;
- struct nd_msg *msg;
- struct inet6_dev *in6_dev = NULL;
+ struct neighbour *n;
+ struct inet6_dev *in6_dev;
in6_dev = __in6_dev_get(dev);
if (!in6_dev)
@@ -1363,19 +1448,20 @@
saddr = &iphdr->saddr;
daddr = &iphdr->daddr;
- if (ipv6_addr_loopback(daddr) ||
- ipv6_addr_is_multicast(daddr))
- goto out;
-
msg = (struct nd_msg *)skb_transport_header(skb);
if (msg->icmph.icmp6_code != 0 ||
msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
goto out;
- n = neigh_lookup(ipv6_stub->nd_tbl, daddr, dev);
+ if (ipv6_addr_loopback(daddr) ||
+ ipv6_addr_is_multicast(&msg->target))
+ goto out;
+
+ n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev);
if (n) {
struct vxlan_fdb *f;
+ struct sk_buff *reply;
if (!(n->nud_state & NUD_CONNECTED)) {
neigh_release(n);
@@ -1389,13 +1475,23 @@
goto out;
}
- ipv6_stub->ndisc_send_na(dev, n, saddr, &msg->target,
- !!in6_dev->cnf.forwarding,
- true, false, false);
+ reply = vxlan_na_create(skb, n,
+ !!(f ? f->flags & NTF_ROUTER : 0));
+
neigh_release(n);
+
+ if (reply == NULL)
+ goto out;
+
+ if (netif_rx_ni(reply) == NET_RX_DROP)
+ dev->stats.rx_dropped++;
+
} else if (vxlan->flags & VXLAN_F_L3MISS) {
- ipa.sin6.sin6_addr = *daddr;
- ipa.sa.sa_family = AF_INET6;
+ union vxlan_addr ipa = {
+ .sin6.sin6_addr = msg->target,
+ .sa.sa_family = AF_INET6,
+ };
+
vxlan_ip_miss(dev, &ipa);
}
@@ -1981,19 +2077,11 @@
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
struct vxlan_sock *vs;
- int i;
- dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct pcpu_sw_netstats *vxlan_stats;
- vxlan_stats = per_cpu_ptr(dev->tstats, i);
- u64_stats_init(&vxlan_stats->syncp);
- }
-
-
spin_lock(&vn->sock_lock);
vs = vxlan_find_sock(dev_net(dev), vxlan->dst_port);
if (vs) {
diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
index 0d1c759..19f7cb2 100644
--- a/drivers/net/wan/dlci.c
+++ b/drivers/net/wan/dlci.c
@@ -71,12 +71,9 @@
const void *saddr, unsigned len)
{
struct frhdr hdr;
- struct dlci_local *dlp;
unsigned int hlen;
char *dest;
- dlp = netdev_priv(dev);
-
hdr.control = FRAD_I_UI;
switch (type)
{
@@ -107,11 +104,9 @@
static void dlci_receive(struct sk_buff *skb, struct net_device *dev)
{
- struct dlci_local *dlp;
struct frhdr *hdr;
int process, header;
- dlp = netdev_priv(dev);
if (!pskb_may_pull(skb, sizeof(*hdr))) {
netdev_notice(dev, "invalid data no header\n");
dev->stats.rx_errors++;
diff --git a/drivers/net/wimax/i2400m/netdev.c b/drivers/net/wimax/i2400m/netdev.c
index 4889613..a9970f1 100644
--- a/drivers/net/wimax/i2400m/netdev.c
+++ b/drivers/net/wimax/i2400m/netdev.c
@@ -374,8 +374,7 @@
d_fnstart(3, dev, "(skb %p net_dev %p)\n", skb, net_dev);
- if (skb_header_cloned(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_cow_head(skb, 0))
goto drop;
if (i2400m->state == I2400M_SS_IDLE)
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 0992f7c..c8a9dfa 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -1547,6 +1547,7 @@
if (reg != last_val)
return true;
+ udelay(1);
last_val = reg;
if ((reg & 0x7E7FFFEF) == 0x00702400)
continue;
@@ -1559,8 +1560,6 @@
default:
return true;
}
-
- udelay(1);
} while (count-- > 0);
return false;
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index f76e6b9..87cbec4 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -2065,7 +2065,7 @@
ATH_TXBUF_RESET(bf);
- if (tid) {
+ if (tid && ieee80211_is_data_present(hdr->frame_control)) {
fragno = le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_FRAG;
seqno = tid->seq_next;
hdr->seq_ctrl = cpu_to_le16(tid->seq_next << IEEE80211_SEQ_SEQ_SHIFT);
@@ -2188,7 +2188,7 @@
txq->stopped = true;
}
- if (txctl->an)
+ if (txctl->an && ieee80211_is_data_present(hdr->frame_control))
tid = ath_get_skb_tid(sc, txctl->an, skb);
if (info->flags & IEEE80211_TX_CTL_PS_RESPONSE) {
diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c
index 58fc096..f1e1bb3 100644
--- a/drivers/net/wireless/ath/wil6210/pcie_bus.c
+++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c
@@ -41,30 +41,28 @@
switch (use_msi) {
case 3:
case 1:
+ wil_dbg_misc(wil, "Setup %d MSI interrupts\n", use_msi);
+ break;
case 0:
+ wil_dbg_misc(wil, "MSI interrupts disabled, use INTx\n");
break;
default:
- wil_err(wil, "Invalid use_msi=%d, default to 1\n",
- use_msi);
+ wil_err(wil, "Invalid use_msi=%d, default to 1\n", use_msi);
use_msi = 1;
}
- wil->n_msi = use_msi;
- if (wil->n_msi) {
- wil_dbg_misc(wil, "Setup %d MSI interrupts\n", use_msi);
- rc = pci_enable_msi_block(pdev, wil->n_msi);
- if (rc && (wil->n_msi == 3)) {
- wil_err(wil, "3 MSI mode failed, try 1 MSI\n");
- wil->n_msi = 1;
- rc = pci_enable_msi_block(pdev, wil->n_msi);
- }
- if (rc) {
- wil_err(wil, "pci_enable_msi failed, use INTx\n");
- wil->n_msi = 0;
- }
- } else {
- wil_dbg_misc(wil, "MSI interrupts disabled, use INTx\n");
+
+ if (use_msi == 3 && pci_enable_msi_range(pdev, 3, 3) < 0) {
+ wil_err(wil, "3 MSI mode failed, try 1 MSI\n");
+ use_msi = 1;
}
+ if (use_msi == 1 && pci_enable_msi(pdev)) {
+ wil_err(wil, "pci_enable_msi failed, use INTx\n");
+ use_msi = 0;
+ }
+
+ wil->n_msi = use_msi;
+
rc = wil6210_init_irq(wil, pdev->irq);
if (rc)
goto stop_master;
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c b/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
index 47a6f39..13c89a0 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
@@ -2140,8 +2140,10 @@
if (pkt_pad == NULL)
return -ENOMEM;
ret = brcmf_sdio_txpkt_hdalign(bus, pkt_pad);
- if (unlikely(ret < 0))
+ if (unlikely(ret < 0)) {
+ kfree_skb(pkt_pad);
return ret;
+ }
memcpy(pkt_pad->data,
pkt->data + pkt->len - tail_chop,
tail_chop);
diff --git a/drivers/net/wireless/mwifiex/11ac.c b/drivers/net/wireless/mwifiex/11ac.c
index bb43251..c92f27a 100644
--- a/drivers/net/wireless/mwifiex/11ac.c
+++ b/drivers/net/wireless/mwifiex/11ac.c
@@ -192,8 +192,7 @@
vht_cap->header.len =
cpu_to_le16(sizeof(struct ieee80211_vht_cap));
memcpy((u8 *)vht_cap + sizeof(struct mwifiex_ie_types_header),
- (u8 *)bss_desc->bcn_vht_cap +
- sizeof(struct ieee_types_header),
+ (u8 *)bss_desc->bcn_vht_cap,
le16_to_cpu(vht_cap->header.len));
mwifiex_fill_vht_cap_tlv(priv, &vht_cap->vht_cap,
diff --git a/drivers/net/wireless/mwifiex/11n.c b/drivers/net/wireless/mwifiex/11n.c
index 70159dd..d14ead8 100644
--- a/drivers/net/wireless/mwifiex/11n.c
+++ b/drivers/net/wireless/mwifiex/11n.c
@@ -323,8 +323,7 @@
ht_cap->header.len =
cpu_to_le16(sizeof(struct ieee80211_ht_cap));
memcpy((u8 *) ht_cap + sizeof(struct mwifiex_ie_types_header),
- (u8 *) bss_desc->bcn_ht_cap +
- sizeof(struct ieee_types_header),
+ (u8 *)bss_desc->bcn_ht_cap,
le16_to_cpu(ht_cap->header.len));
mwifiex_fill_cap_info(priv, radio_type, &ht_cap->ht_cap);
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 668a91c..77db088 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -749,7 +749,7 @@
static u16
mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv, select_queue_fallback_t fallback)
{
skb->priority = cfg80211_classify8021d(skb, NULL);
return mwifiex_1d_to_wmm_queue[skb->priority];
diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c
index e496497..7b3af3d 100644
--- a/drivers/net/wireless/mwifiex/scan.c
+++ b/drivers/net/wireless/mwifiex/scan.c
@@ -2324,12 +2324,12 @@
curr_bss->ht_info_offset);
if (curr_bss->bcn_vht_cap)
- curr_bss->bcn_ht_cap = (void *)(curr_bss->beacon_buf +
- curr_bss->vht_cap_offset);
+ curr_bss->bcn_vht_cap = (void *)(curr_bss->beacon_buf +
+ curr_bss->vht_cap_offset);
if (curr_bss->bcn_vht_oper)
- curr_bss->bcn_ht_oper = (void *)(curr_bss->beacon_buf +
- curr_bss->vht_info_offset);
+ curr_bss->bcn_vht_oper = (void *)(curr_bss->beacon_buf +
+ curr_bss->vht_info_offset);
if (curr_bss->bcn_bss_co_2040)
curr_bss->bcn_bss_co_2040 =
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c
index 7f8b5d1..41d4a81 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/rt2x00/rt2800lib.c
@@ -5460,14 +5460,15 @@
rt2800_bbp_write(rt2x00dev, 68, 0x0b);
- rt2800_bbp_write(rt2x00dev, 69, 0x0d);
- rt2800_bbp_write(rt2x00dev, 70, 0x06);
+ rt2800_bbp_write(rt2x00dev, 69, 0x12);
rt2800_bbp_write(rt2x00dev, 73, 0x13);
rt2800_bbp_write(rt2x00dev, 75, 0x46);
rt2800_bbp_write(rt2x00dev, 76, 0x28);
rt2800_bbp_write(rt2x00dev, 77, 0x59);
+ rt2800_bbp_write(rt2x00dev, 70, 0x0a);
+
rt2800_bbp_write(rt2x00dev, 79, 0x13);
rt2800_bbp_write(rt2x00dev, 80, 0x05);
rt2800_bbp_write(rt2x00dev, 81, 0x33);
@@ -5510,7 +5511,6 @@
if (rt2x00_rt(rt2x00dev, RT5392)) {
rt2800_bbp_write(rt2x00dev, 134, 0xd0);
rt2800_bbp_write(rt2x00dev, 135, 0xf6);
- rt2800_bbp_write(rt2x00dev, 148, 0x84);
}
rt2800_disable_unused_dac_adc(rt2x00dev);
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 4c76bcb..89b2d42 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -48,37 +48,19 @@
typedef unsigned int pending_ring_idx_t;
#define INVALID_PENDING_RING_IDX (~0U)
-/* For the head field in pending_tx_info: it is used to indicate
- * whether this tx info is the head of one or more coalesced requests.
- *
- * When head != INVALID_PENDING_RING_IDX, it means the start of a new
- * tx requests queue and the end of previous queue.
- *
- * An example sequence of head fields (I = INVALID_PENDING_RING_IDX):
- *
- * ...|0 I I I|5 I|9 I I I|...
- * -->|<-INUSE----------------
- *
- * After consuming the first slot(s) we have:
- *
- * ...|V V V V|5 I|9 I I I|...
- * -----FREE->|<-INUSE--------
- *
- * where V stands for "valid pending ring index". Any number other
- * than INVALID_PENDING_RING_IDX is OK. These entries are considered
- * free and can contain any number other than
- * INVALID_PENDING_RING_IDX. In practice we use 0.
- *
- * The in use non-INVALID_PENDING_RING_IDX (say 0, 5 and 9 in the
- * above example) number is the index into pending_tx_info and
- * mmap_pages arrays.
- */
struct pending_tx_info {
- struct xen_netif_tx_request req; /* coalesced tx request */
- pending_ring_idx_t head; /* head != INVALID_PENDING_RING_IDX
- * if it is head of one or more tx
- * reqs
- */
+ struct xen_netif_tx_request req; /* tx request */
+ /* Callback data for released SKBs. The callback is always
+ * xenvif_zerocopy_callback, desc contains the pending_idx, which is
+ * also an index in pending_tx_info array. It is initialized in
+ * xenvif_alloc and it never changes.
+ * skb_shinfo(skb)->destructor_arg points to the first mapped slot's
+ * callback_struct in this array of struct pending_tx_info's, then ctx
+ * to the next, or NULL if there is no more slot for this skb.
+ * ubuf_to_vif is a helper which finds the struct xenvif from a pointer
+ * to this field.
+ */
+ struct ubuf_info callback_struct;
};
#define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE)
@@ -99,7 +81,7 @@
#define MAX_BUFFER_OFFSET PAGE_SIZE
-#define MAX_PENDING_REQS 256
+#define MAX_PENDING_REQS XEN_NETIF_TX_RING_SIZE
/* It's possible for an skb to have a maximal number of frags
* but still be less than MAX_BUFFER_OFFSET in size. Thus the
@@ -108,6 +90,15 @@
*/
#define MAX_GRANT_COPY_OPS (MAX_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE)
+#define NETBACK_INVALID_HANDLE -1
+
+/* To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating
+ * the maximum slots a valid packet can use. Now this value is defined
+ * to be XEN_NETIF_NR_SLOTS_MIN, which is supposed to be supported by
+ * all backend.
+ */
+#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN
+
struct xenvif {
/* Unique identifier for this interface. */
domid_t domid;
@@ -126,13 +117,26 @@
pending_ring_idx_t pending_cons;
u16 pending_ring[MAX_PENDING_REQS];
struct pending_tx_info pending_tx_info[MAX_PENDING_REQS];
+ grant_handle_t grant_tx_handle[MAX_PENDING_REQS];
- /* Coalescing tx requests before copying makes number of grant
- * copy ops greater or equal to number of slots required. In
- * worst case a tx request consumes 2 gnttab_copy.
+ struct gnttab_map_grant_ref tx_map_ops[MAX_PENDING_REQS];
+ struct gnttab_unmap_grant_ref tx_unmap_ops[MAX_PENDING_REQS];
+ /* passed to gnttab_[un]map_refs with pages under (un)mapping */
+ struct page *pages_to_map[MAX_PENDING_REQS];
+ struct page *pages_to_unmap[MAX_PENDING_REQS];
+
+ /* This prevents zerocopy callbacks to race over dealloc_ring */
+ spinlock_t callback_lock;
+ /* This prevents dealloc thread and NAPI instance to race over response
+ * creation and pending_ring in xenvif_idx_release. In xenvif_tx_err
+ * it only protect response creation
*/
- struct gnttab_copy tx_copy_ops[2*MAX_PENDING_REQS];
-
+ spinlock_t response_lock;
+ pending_ring_idx_t dealloc_prod;
+ pending_ring_idx_t dealloc_cons;
+ u16 dealloc_ring[MAX_PENDING_REQS];
+ struct task_struct *dealloc_task;
+ wait_queue_head_t dealloc_wq;
/* Use kthread for guest RX */
struct task_struct *task;
@@ -143,11 +147,10 @@
char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */
struct xen_netif_rx_back_ring rx;
struct sk_buff_head rx_queue;
- bool rx_queue_stopped;
- /* Set when the RX interrupt is triggered by the frontend.
- * The worker thread may need to wake the queue.
- */
- bool rx_event;
+ RING_IDX rx_last_skb_slots;
+ bool rx_queue_purge;
+
+ struct timer_list wake_queue;
/* This array is allocated seperately as it is large */
struct gnttab_copy *grant_copy_op;
@@ -179,6 +182,10 @@
/* Statistics */
unsigned long rx_gso_checksum_fixup;
+ unsigned long tx_zerocopy_sent;
+ unsigned long tx_zerocopy_success;
+ unsigned long tx_zerocopy_fail;
+ unsigned long tx_frag_overflow;
/* Miscellaneous private stuff. */
struct net_device *dev;
@@ -220,9 +227,11 @@
int xenvif_tx_action(struct xenvif *vif, int budget);
-int xenvif_kthread(void *data);
+int xenvif_kthread_guest_rx(void *data);
void xenvif_kick_thread(struct xenvif *vif);
+int xenvif_dealloc_kthread(void *data);
+
/* Determine whether the needed number of slots (req) are available,
* and set req_event if not.
*/
@@ -230,6 +239,24 @@
void xenvif_stop_queue(struct xenvif *vif);
+/* Callback from stack when TX packet can be released */
+void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success);
+
+/* Unmap a pending page and release it back to the guest */
+void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx);
+
+static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif)
+{
+ return MAX_PENDING_REQS -
+ vif->pending_prod + vif->pending_cons;
+}
+
+/* Callback from stack when TX packet can be released */
+void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success);
+
extern bool separate_tx_rx_irq;
+extern unsigned int rx_drain_timeout_msecs;
+extern unsigned int rx_drain_timeout_jiffies;
+
#endif /* __XEN_NETBACK__COMMON_H__ */
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index b9de31e..cdc298e 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -38,6 +38,7 @@
#include <xen/events.h>
#include <asm/xen/hypercall.h>
+#include <xen/balloon.h>
#define XENVIF_QUEUE_LENGTH 32
#define XENVIF_NAPI_WEIGHT 64
@@ -100,7 +101,6 @@
{
struct xenvif *vif = dev_id;
- vif->rx_event = true;
xenvif_kick_thread(vif);
return IRQ_HANDLED;
@@ -114,6 +114,18 @@
return IRQ_HANDLED;
}
+static void xenvif_wake_queue(unsigned long data)
+{
+ struct xenvif *vif = (struct xenvif *)data;
+
+ if (netif_queue_stopped(vif->dev)) {
+ netdev_err(vif->dev, "draining TX queue\n");
+ vif->rx_queue_purge = true;
+ xenvif_kick_thread(vif);
+ netif_wake_queue(vif->dev);
+ }
+}
+
static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct xenvif *vif = netdev_priv(dev);
@@ -122,7 +134,9 @@
BUG_ON(skb->dev != dev);
/* Drop the packet if vif is not ready */
- if (vif->task == NULL || !xenvif_schedulable(vif))
+ if (vif->task == NULL ||
+ vif->dealloc_task == NULL ||
+ !xenvif_schedulable(vif))
goto drop;
/* At best we'll need one slot for the header and one for each
@@ -133,16 +147,20 @@
/* If the skb is GSO then we'll also need an extra slot for the
* metadata.
*/
- if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
- skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+ if (skb_is_gso(skb))
min_slots_needed++;
/* If the skb can't possibly fit in the remaining slots
* then turn off the queue to give the ring a chance to
* drain.
*/
- if (!xenvif_rx_ring_slots_available(vif, min_slots_needed))
+ if (!xenvif_rx_ring_slots_available(vif, min_slots_needed)) {
+ vif->wake_queue.function = xenvif_wake_queue;
+ vif->wake_queue.data = (unsigned long)vif;
xenvif_stop_queue(vif);
+ mod_timer(&vif->wake_queue,
+ jiffies + rx_drain_timeout_jiffies);
+ }
skb_queue_tail(&vif->rx_queue, skb);
xenvif_kick_thread(vif);
@@ -235,6 +253,28 @@
"rx_gso_checksum_fixup",
offsetof(struct xenvif, rx_gso_checksum_fixup)
},
+ /* If (sent != success + fail), there are probably packets never
+ * freed up properly!
+ */
+ {
+ "tx_zerocopy_sent",
+ offsetof(struct xenvif, tx_zerocopy_sent),
+ },
+ {
+ "tx_zerocopy_success",
+ offsetof(struct xenvif, tx_zerocopy_success),
+ },
+ {
+ "tx_zerocopy_fail",
+ offsetof(struct xenvif, tx_zerocopy_fail)
+ },
+ /* Number of packets exceeding MAX_SKB_FRAG slots. You should use
+ * a guest with the same MAX_SKB_FRAG
+ */
+ {
+ "tx_frag_overflow",
+ offsetof(struct xenvif, tx_frag_overflow)
+ },
};
static int xenvif_get_sset_count(struct net_device *dev, int string_set)
@@ -328,6 +368,8 @@
init_timer(&vif->credit_timeout);
vif->credit_window_start = get_jiffies_64();
+ init_timer(&vif->wake_queue);
+
dev->netdev_ops = &xenvif_netdev_ops;
dev->hw_features = NETIF_F_SG |
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
@@ -344,8 +386,26 @@
vif->pending_prod = MAX_PENDING_REQS;
for (i = 0; i < MAX_PENDING_REQS; i++)
vif->pending_ring[i] = i;
- for (i = 0; i < MAX_PENDING_REQS; i++)
- vif->mmap_pages[i] = NULL;
+ spin_lock_init(&vif->callback_lock);
+ spin_lock_init(&vif->response_lock);
+ /* If ballooning is disabled, this will consume real memory, so you
+ * better enable it. The long term solution would be to use just a
+ * bunch of valid page descriptors, without dependency on ballooning
+ */
+ err = alloc_xenballooned_pages(MAX_PENDING_REQS,
+ vif->mmap_pages,
+ false);
+ if (err) {
+ netdev_err(dev, "Could not reserve mmap_pages\n");
+ return ERR_PTR(-ENOMEM);
+ }
+ for (i = 0; i < MAX_PENDING_REQS; i++) {
+ vif->pending_tx_info[i].callback_struct = (struct ubuf_info)
+ { .callback = xenvif_zerocopy_callback,
+ .ctx = NULL,
+ .desc = i };
+ vif->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;
+ }
/*
* Initialise a dummy MAC address. We choose the numerically
@@ -383,12 +443,14 @@
BUG_ON(vif->tx_irq);
BUG_ON(vif->task);
+ BUG_ON(vif->dealloc_task);
err = xenvif_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref);
if (err < 0)
goto err;
init_waitqueue_head(&vif->wq);
+ init_waitqueue_head(&vif->dealloc_wq);
if (tx_evtchn == rx_evtchn) {
/* feature-split-event-channels == 0 */
@@ -422,8 +484,8 @@
disable_irq(vif->rx_irq);
}
- task = kthread_create(xenvif_kthread,
- (void *)vif, "%s", vif->dev->name);
+ task = kthread_create(xenvif_kthread_guest_rx,
+ (void *)vif, "%s-guest-rx", vif->dev->name);
if (IS_ERR(task)) {
pr_warn("Could not allocate kthread for %s\n", vif->dev->name);
err = PTR_ERR(task);
@@ -432,6 +494,16 @@
vif->task = task;
+ task = kthread_create(xenvif_dealloc_kthread,
+ (void *)vif, "%s-dealloc", vif->dev->name);
+ if (IS_ERR(task)) {
+ pr_warn("Could not allocate kthread for %s\n", vif->dev->name);
+ err = PTR_ERR(task);
+ goto err_rx_unbind;
+ }
+
+ vif->dealloc_task = task;
+
rtnl_lock();
if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
dev_set_mtu(vif->dev, ETH_DATA_LEN);
@@ -442,6 +514,7 @@
rtnl_unlock();
wake_up_process(vif->task);
+ wake_up_process(vif->dealloc_task);
return 0;
@@ -475,10 +548,16 @@
xenvif_carrier_off(vif);
if (vif->task) {
+ del_timer_sync(&vif->wake_queue);
kthread_stop(vif->task);
vif->task = NULL;
}
+ if (vif->dealloc_task) {
+ kthread_stop(vif->dealloc_task);
+ vif->dealloc_task = NULL;
+ }
+
if (vif->tx_irq) {
if (vif->tx_irq == vif->rx_irq)
unbind_from_irqhandler(vif->tx_irq, vif);
@@ -494,6 +573,43 @@
void xenvif_free(struct xenvif *vif)
{
+ int i, unmap_timeout = 0;
+ /* Here we want to avoid timeout messages if an skb can be legitimately
+ * stuck somewhere else. Realistically this could be an another vif's
+ * internal or QDisc queue. That another vif also has this
+ * rx_drain_timeout_msecs timeout, but the timer only ditches the
+ * internal queue. After that, the QDisc queue can put in worst case
+ * XEN_NETIF_RX_RING_SIZE / MAX_SKB_FRAGS skbs into that another vif's
+ * internal queue, so we need several rounds of such timeouts until we
+ * can be sure that no another vif should have skb's from us. We are
+ * not sending more skb's, so newly stuck packets are not interesting
+ * for us here.
+ */
+ unsigned int worst_case_skb_lifetime = (rx_drain_timeout_msecs/1000) *
+ DIV_ROUND_UP(XENVIF_QUEUE_LENGTH, (XEN_NETIF_RX_RING_SIZE / MAX_SKB_FRAGS));
+
+ for (i = 0; i < MAX_PENDING_REQS; ++i) {
+ if (vif->grant_tx_handle[i] != NETBACK_INVALID_HANDLE) {
+ unmap_timeout++;
+ schedule_timeout(msecs_to_jiffies(1000));
+ if (unmap_timeout > worst_case_skb_lifetime &&
+ net_ratelimit())
+ netdev_err(vif->dev,
+ "Page still granted! Index: %x\n",
+ i);
+ /* If there are still unmapped pages, reset the loop to
+ * start checking again. We shouldn't exit here until
+ * dealloc thread and NAPI instance release all the
+ * pages. If a kernel bug causes the skbs to stall
+ * somewhere, the interface cannot be brought down
+ * properly.
+ */
+ i = -1;
+ }
+ }
+
+ free_xenballooned_pages(MAX_PENDING_REQS, vif->mmap_pages);
+
netif_napi_del(&vif->napi);
unregister_netdev(vif->dev);
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 6b62c3e..cb784fe 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -37,6 +37,7 @@
#include <linux/kthread.h>
#include <linux/if_vlan.h>
#include <linux/udp.h>
+#include <linux/highmem.h>
#include <net/tcp.h>
@@ -54,6 +55,13 @@
bool separate_tx_rx_irq = 1;
module_param(separate_tx_rx_irq, bool, 0644);
+/* When guest ring is filled up, qdisc queues the packets for us, but we have
+ * to timeout them, otherwise other guests' packets can get stuck there
+ */
+unsigned int rx_drain_timeout_msecs = 10000;
+module_param(rx_drain_timeout_msecs, uint, 0444);
+unsigned int rx_drain_timeout_jiffies;
+
/*
* This is the maximum slots a skb can have. If a guest sends a skb
* which exceeds this limit it is considered malicious.
@@ -62,24 +70,6 @@
static unsigned int fatal_skb_slots = FATAL_SKB_SLOTS_DEFAULT;
module_param(fatal_skb_slots, uint, 0444);
-/*
- * To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating
- * the maximum slots a valid packet can use. Now this value is defined
- * to be XEN_NETIF_NR_SLOTS_MIN, which is supposed to be supported by
- * all backend.
- */
-#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN
-
-/*
- * If head != INVALID_PENDING_RING_IDX, it means this tx request is head of
- * one or more merged tx requests, otherwise it is the continuation of
- * previous tx request.
- */
-static inline int pending_tx_is_head(struct xenvif *vif, RING_IDX idx)
-{
- return vif->pending_tx_info[idx].head != INVALID_PENDING_RING_IDX;
-}
-
static void xenvif_idx_release(struct xenvif *vif, u16 pending_idx,
u8 status);
@@ -109,6 +99,21 @@
return (unsigned long)pfn_to_kaddr(idx_to_pfn(vif, idx));
}
+#define callback_param(vif, pending_idx) \
+ (vif->pending_tx_info[pending_idx].callback_struct)
+
+/* Find the containing VIF's structure from a pointer in pending_tx_info array
+ */
+static inline struct xenvif* ubuf_to_vif(struct ubuf_info *ubuf)
+{
+ u16 pending_idx = ubuf->desc;
+ struct pending_tx_info *temp =
+ container_of(ubuf, struct pending_tx_info, callback_struct);
+ return container_of(temp - pending_idx,
+ struct xenvif,
+ pending_tx_info[0]);
+}
+
/* This is a miniumum size for the linear area to avoid lots of
* calls to __pskb_pull_tail() as we set up checksum offsets. The
* value 128 was chosen as it covers all IPv4 and most likely
@@ -131,12 +136,6 @@
return i & (MAX_PENDING_REQS-1);
}
-static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif)
-{
- return MAX_PENDING_REQS -
- vif->pending_prod + vif->pending_cons;
-}
-
bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed)
{
RING_IDX prod, cons;
@@ -235,12 +234,14 @@
static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
struct netrx_pending_operations *npo,
struct page *page, unsigned long size,
- unsigned long offset, int *head)
+ unsigned long offset, int *head,
+ struct xenvif *foreign_vif,
+ grant_ref_t foreign_gref)
{
struct gnttab_copy *copy_gop;
struct xenvif_rx_meta *meta;
unsigned long bytes;
- int gso_type;
+ int gso_type = XEN_NETIF_GSO_TYPE_NONE;
/* Data must not cross a page boundary. */
BUG_ON(size + offset > PAGE_SIZE<<compound_order(page));
@@ -277,8 +278,15 @@
copy_gop->flags = GNTCOPY_dest_gref;
copy_gop->len = bytes;
- copy_gop->source.domid = DOMID_SELF;
- copy_gop->source.u.gmfn = virt_to_mfn(page_address(page));
+ if (foreign_vif) {
+ copy_gop->source.domid = foreign_vif->domid;
+ copy_gop->source.u.ref = foreign_gref;
+ copy_gop->flags |= GNTCOPY_source_gref;
+ } else {
+ copy_gop->source.domid = DOMID_SELF;
+ copy_gop->source.u.gmfn =
+ virt_to_mfn(page_address(page));
+ }
copy_gop->source.offset = offset;
copy_gop->dest.domid = vif->domid;
@@ -299,12 +307,12 @@
}
/* Leave a gap for the GSO descriptor. */
- if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
- gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
- else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
- gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
- else
- gso_type = XEN_NETIF_GSO_TYPE_NONE;
+ if (skb_is_gso(skb)) {
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+ gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
+ else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+ gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
+ }
if (*head && ((1 << gso_type) & vif->gso_mask))
vif->rx.req_cons++;
@@ -338,19 +346,18 @@
int head = 1;
int old_meta_prod;
int gso_type;
- int gso_size;
+ struct ubuf_info *ubuf = skb_shinfo(skb)->destructor_arg;
+ grant_ref_t foreign_grefs[MAX_SKB_FRAGS];
+ struct xenvif *foreign_vif = NULL;
old_meta_prod = npo->meta_prod;
- if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
- gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
- gso_size = skb_shinfo(skb)->gso_size;
- } else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) {
- gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
- gso_size = skb_shinfo(skb)->gso_size;
- } else {
- gso_type = XEN_NETIF_GSO_TYPE_NONE;
- gso_size = 0;
+ gso_type = XEN_NETIF_GSO_TYPE_NONE;
+ if (skb_is_gso(skb)) {
+ if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+ gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
+ else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+ gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
}
/* Set up a GSO prefix descriptor, if necessary */
@@ -358,7 +365,7 @@
req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
meta = npo->meta + npo->meta_prod++;
meta->gso_type = gso_type;
- meta->gso_size = gso_size;
+ meta->gso_size = skb_shinfo(skb)->gso_size;
meta->size = 0;
meta->id = req->id;
}
@@ -368,7 +375,7 @@
if ((1 << gso_type) & vif->gso_mask) {
meta->gso_type = gso_type;
- meta->gso_size = gso_size;
+ meta->gso_size = skb_shinfo(skb)->gso_size;
} else {
meta->gso_type = XEN_NETIF_GSO_TYPE_NONE;
meta->gso_size = 0;
@@ -379,6 +386,19 @@
npo->copy_off = 0;
npo->copy_gref = req->gref;
+ if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) &&
+ (ubuf->callback == &xenvif_zerocopy_callback)) {
+ int i = 0;
+ foreign_vif = ubuf_to_vif(ubuf);
+
+ do {
+ u16 pending_idx = ubuf->desc;
+ foreign_grefs[i++] =
+ foreign_vif->pending_tx_info[pending_idx].req.gref;
+ ubuf = (struct ubuf_info *) ubuf->ctx;
+ } while (ubuf);
+ }
+
data = skb->data;
while (data < skb_tail_pointer(skb)) {
unsigned int offset = offset_in_page(data);
@@ -388,7 +408,9 @@
len = skb_tail_pointer(skb) - data;
xenvif_gop_frag_copy(vif, skb, npo,
- virt_to_page(data), len, offset, &head);
+ virt_to_page(data), len, offset, &head,
+ NULL,
+ 0);
data += len;
}
@@ -397,7 +419,9 @@
skb_frag_page(&skb_shinfo(skb)->frags[i]),
skb_frag_size(&skb_shinfo(skb)->frags[i]),
skb_shinfo(skb)->frags[i].page_offset,
- &head);
+ &head,
+ foreign_vif,
+ foreign_grefs[i]);
}
return npo->meta_prod - old_meta_prod;
@@ -455,10 +479,12 @@
}
}
-struct skb_cb_overlay {
+struct xenvif_rx_cb {
int meta_slots_used;
};
+#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb)
+
void xenvif_kick_thread(struct xenvif *vif)
{
wake_up(&vif->wq);
@@ -474,9 +500,7 @@
LIST_HEAD(notify);
int ret;
unsigned long offset;
- struct skb_cb_overlay *sco;
bool need_to_notify = false;
- bool ring_full = false;
struct netrx_pending_operations npo = {
.copy = vif->grant_copy_op,
@@ -486,7 +510,7 @@
skb_queue_head_init(&rxq);
while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) {
- int max_slots_needed;
+ RING_IDX max_slots_needed;
int i;
/* We need a cheap worse case estimate for the number of
@@ -501,29 +525,28 @@
size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
max_slots_needed += DIV_ROUND_UP(size, PAGE_SIZE);
}
- if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
- skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+ if (skb_is_gso(skb) &&
+ (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
+ skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6))
max_slots_needed++;
/* If the skb may not fit then bail out now */
if (!xenvif_rx_ring_slots_available(vif, max_slots_needed)) {
skb_queue_head(&vif->rx_queue, skb);
need_to_notify = true;
- ring_full = true;
+ vif->rx_last_skb_slots = max_slots_needed;
break;
- }
+ } else
+ vif->rx_last_skb_slots = 0;
- sco = (struct skb_cb_overlay *)skb->cb;
- sco->meta_slots_used = xenvif_gop_skb(skb, &npo);
- BUG_ON(sco->meta_slots_used > max_slots_needed);
+ XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo);
+ BUG_ON(XENVIF_RX_CB(skb)->meta_slots_used > max_slots_needed);
__skb_queue_tail(&rxq, skb);
}
BUG_ON(npo.meta_prod > ARRAY_SIZE(vif->meta));
- vif->rx_queue_stopped = !npo.copy_prod && ring_full;
-
if (!npo.copy_prod)
goto done;
@@ -531,7 +554,6 @@
gnttab_batch_copy(vif->grant_copy_op, npo.copy_prod);
while ((skb = __skb_dequeue(&rxq)) != NULL) {
- sco = (struct skb_cb_overlay *)skb->cb;
if ((1 << vif->meta[npo.meta_cons].gso_type) &
vif->gso_prefix_mask) {
@@ -542,19 +564,21 @@
resp->offset = vif->meta[npo.meta_cons].gso_size;
resp->id = vif->meta[npo.meta_cons].id;
- resp->status = sco->meta_slots_used;
+ resp->status = XENVIF_RX_CB(skb)->meta_slots_used;
npo.meta_cons++;
- sco->meta_slots_used--;
+ XENVIF_RX_CB(skb)->meta_slots_used--;
}
vif->dev->stats.tx_bytes += skb->len;
vif->dev->stats.tx_packets++;
- status = xenvif_check_gop(vif, sco->meta_slots_used, &npo);
+ status = xenvif_check_gop(vif,
+ XENVIF_RX_CB(skb)->meta_slots_used,
+ &npo);
- if (sco->meta_slots_used == 1)
+ if (XENVIF_RX_CB(skb)->meta_slots_used == 1)
flags = 0;
else
flags = XEN_NETRXF_more_data;
@@ -591,13 +615,13 @@
xenvif_add_frag_responses(vif, status,
vif->meta + npo.meta_cons + 1,
- sco->meta_slots_used);
+ XENVIF_RX_CB(skb)->meta_slots_used);
RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret);
need_to_notify |= !!ret;
- npo.meta_cons += sco->meta_slots_used;
+ npo.meta_cons += XENVIF_RX_CB(skb)->meta_slots_used;
dev_kfree_skb(skb);
}
@@ -647,9 +671,12 @@
struct xen_netif_tx_request *txp, RING_IDX end)
{
RING_IDX cons = vif->tx.req_cons;
+ unsigned long flags;
do {
+ spin_lock_irqsave(&vif->response_lock, flags);
make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
+ spin_unlock_irqrestore(&vif->response_lock, flags);
if (cons == end)
break;
txp = RING_GET_REQUEST(&vif->tx, cons++);
@@ -761,180 +788,168 @@
return slots;
}
-static struct page *xenvif_alloc_page(struct xenvif *vif,
- u16 pending_idx)
+
+struct xenvif_tx_cb {
+ u16 pending_idx;
+};
+
+#define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb)
+
+static inline void xenvif_tx_create_gop(struct xenvif *vif,
+ u16 pending_idx,
+ struct xen_netif_tx_request *txp,
+ struct gnttab_map_grant_ref *gop)
{
- struct page *page;
+ vif->pages_to_map[gop-vif->tx_map_ops] = vif->mmap_pages[pending_idx];
+ gnttab_set_map_op(gop, idx_to_kaddr(vif, pending_idx),
+ GNTMAP_host_map | GNTMAP_readonly,
+ txp->gref, vif->domid);
- page = alloc_page(GFP_ATOMIC|__GFP_COLD);
- if (!page)
- return NULL;
- vif->mmap_pages[pending_idx] = page;
-
- return page;
+ memcpy(&vif->pending_tx_info[pending_idx].req, txp,
+ sizeof(*txp));
}
-static struct gnttab_copy *xenvif_get_requests(struct xenvif *vif,
- struct sk_buff *skb,
- struct xen_netif_tx_request *txp,
- struct gnttab_copy *gop)
+static inline struct sk_buff *xenvif_alloc_skb(unsigned int size)
+{
+ struct sk_buff *skb =
+ alloc_skb(size + NET_SKB_PAD + NET_IP_ALIGN,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (unlikely(skb == NULL))
+ return NULL;
+
+ /* Packets passed to netif_rx() must have some headroom. */
+ skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+
+ /* Initialize it here to avoid later surprises */
+ skb_shinfo(skb)->destructor_arg = NULL;
+
+ return skb;
+}
+
+static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
+ struct sk_buff *skb,
+ struct xen_netif_tx_request *txp,
+ struct gnttab_map_grant_ref *gop)
{
struct skb_shared_info *shinfo = skb_shinfo(skb);
skb_frag_t *frags = shinfo->frags;
- u16 pending_idx = *((u16 *)skb->data);
- u16 head_idx = 0;
- int slot, start;
- struct page *page;
- pending_ring_idx_t index, start_idx = 0;
- uint16_t dst_offset;
- unsigned int nr_slots;
- struct pending_tx_info *first = NULL;
+ u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx;
+ int start;
+ pending_ring_idx_t index;
+ unsigned int nr_slots, frag_overflow = 0;
/* At this point shinfo->nr_frags is in fact the number of
* slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.
*/
+ if (shinfo->nr_frags > MAX_SKB_FRAGS) {
+ frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS;
+ BUG_ON(frag_overflow > MAX_SKB_FRAGS);
+ shinfo->nr_frags = MAX_SKB_FRAGS;
+ }
nr_slots = shinfo->nr_frags;
/* Skip first skb fragment if it is on same page as header fragment. */
start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);
- /* Coalesce tx requests, at this point the packet passed in
- * should be <= 64K. Any packets larger than 64K have been
- * handled in xenvif_count_requests().
- */
- for (shinfo->nr_frags = slot = start; slot < nr_slots;
- shinfo->nr_frags++) {
- struct pending_tx_info *pending_tx_info =
- vif->pending_tx_info;
+ for (shinfo->nr_frags = start; shinfo->nr_frags < nr_slots;
+ shinfo->nr_frags++, txp++, gop++) {
+ index = pending_index(vif->pending_cons++);
+ pending_idx = vif->pending_ring[index];
+ xenvif_tx_create_gop(vif, pending_idx, txp, gop);
+ frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx);
+ }
- page = alloc_page(GFP_ATOMIC|__GFP_COLD);
- if (!page)
- goto err;
-
- dst_offset = 0;
- first = NULL;
- while (dst_offset < PAGE_SIZE && slot < nr_slots) {
- gop->flags = GNTCOPY_source_gref;
-
- gop->source.u.ref = txp->gref;
- gop->source.domid = vif->domid;
- gop->source.offset = txp->offset;
-
- gop->dest.domid = DOMID_SELF;
-
- gop->dest.offset = dst_offset;
- gop->dest.u.gmfn = virt_to_mfn(page_address(page));
-
- if (dst_offset + txp->size > PAGE_SIZE) {
- /* This page can only merge a portion
- * of tx request. Do not increment any
- * pointer / counter here. The txp
- * will be dealt with in future
- * rounds, eventually hitting the
- * `else` branch.
- */
- gop->len = PAGE_SIZE - dst_offset;
- txp->offset += gop->len;
- txp->size -= gop->len;
- dst_offset += gop->len; /* quit loop */
- } else {
- /* This tx request can be merged in the page */
- gop->len = txp->size;
- dst_offset += gop->len;
-
- index = pending_index(vif->pending_cons++);
-
- pending_idx = vif->pending_ring[index];
-
- memcpy(&pending_tx_info[pending_idx].req, txp,
- sizeof(*txp));
-
- /* Poison these fields, corresponding
- * fields for head tx req will be set
- * to correct values after the loop.
- */
- vif->mmap_pages[pending_idx] = (void *)(~0UL);
- pending_tx_info[pending_idx].head =
- INVALID_PENDING_RING_IDX;
-
- if (!first) {
- first = &pending_tx_info[pending_idx];
- start_idx = index;
- head_idx = pending_idx;
- }
-
- txp++;
- slot++;
- }
-
- gop++;
+ if (frag_overflow) {
+ struct sk_buff *nskb = xenvif_alloc_skb(0);
+ if (unlikely(nskb == NULL)) {
+ if (net_ratelimit())
+ netdev_err(vif->dev,
+ "Can't allocate the frag_list skb.\n");
+ return NULL;
}
- first->req.offset = 0;
- first->req.size = dst_offset;
- first->head = start_idx;
- vif->mmap_pages[head_idx] = page;
- frag_set_pending_idx(&frags[shinfo->nr_frags], head_idx);
- }
+ shinfo = skb_shinfo(nskb);
+ frags = shinfo->frags;
- BUG_ON(shinfo->nr_frags > MAX_SKB_FRAGS);
+ for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow;
+ shinfo->nr_frags++, txp++, gop++) {
+ index = pending_index(vif->pending_cons++);
+ pending_idx = vif->pending_ring[index];
+ xenvif_tx_create_gop(vif, pending_idx, txp, gop);
+ frag_set_pending_idx(&frags[shinfo->nr_frags],
+ pending_idx);
+ }
+
+ skb_shinfo(skb)->frag_list = nskb;
+ }
return gop;
-err:
- /* Unwind, freeing all pages and sending error responses. */
- while (shinfo->nr_frags-- > start) {
- xenvif_idx_release(vif,
- frag_get_pending_idx(&frags[shinfo->nr_frags]),
- XEN_NETIF_RSP_ERROR);
- }
- /* The head too, if necessary. */
- if (start)
- xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);
+}
- return NULL;
+static inline void xenvif_grant_handle_set(struct xenvif *vif,
+ u16 pending_idx,
+ grant_handle_t handle)
+{
+ if (unlikely(vif->grant_tx_handle[pending_idx] !=
+ NETBACK_INVALID_HANDLE)) {
+ netdev_err(vif->dev,
+ "Trying to overwrite active handle! pending_idx: %x\n",
+ pending_idx);
+ BUG();
+ }
+ vif->grant_tx_handle[pending_idx] = handle;
+}
+
+static inline void xenvif_grant_handle_reset(struct xenvif *vif,
+ u16 pending_idx)
+{
+ if (unlikely(vif->grant_tx_handle[pending_idx] ==
+ NETBACK_INVALID_HANDLE)) {
+ netdev_err(vif->dev,
+ "Trying to unmap invalid handle! pending_idx: %x\n",
+ pending_idx);
+ BUG();
+ }
+ vif->grant_tx_handle[pending_idx] = NETBACK_INVALID_HANDLE;
}
static int xenvif_tx_check_gop(struct xenvif *vif,
struct sk_buff *skb,
- struct gnttab_copy **gopp)
+ struct gnttab_map_grant_ref **gopp)
{
- struct gnttab_copy *gop = *gopp;
- u16 pending_idx = *((u16 *)skb->data);
+ struct gnttab_map_grant_ref *gop = *gopp;
+ u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx;
struct skb_shared_info *shinfo = skb_shinfo(skb);
struct pending_tx_info *tx_info;
int nr_frags = shinfo->nr_frags;
int i, err, start;
- u16 peek; /* peek into next tx request */
+ struct sk_buff *first_skb = NULL;
/* Check status of header. */
err = gop->status;
if (unlikely(err))
xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);
+ else
+ xenvif_grant_handle_set(vif, pending_idx , gop->handle);
/* Skip first skb fragment if it is on same page as header fragment. */
start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);
+check_frags:
for (i = start; i < nr_frags; i++) {
int j, newerr;
- pending_ring_idx_t head;
pending_idx = frag_get_pending_idx(&shinfo->frags[i]);
tx_info = &vif->pending_tx_info[pending_idx];
- head = tx_info->head;
/* Check error status: if okay then remember grant handle. */
- do {
- newerr = (++gop)->status;
- if (newerr)
- break;
- peek = vif->pending_ring[pending_index(++head)];
- } while (!pending_tx_is_head(vif, peek));
+ newerr = (++gop)->status;
if (likely(!newerr)) {
+ xenvif_grant_handle_set(vif, pending_idx , gop->handle);
/* Had a previous error? Invalidate this fragment. */
if (unlikely(err))
- xenvif_idx_release(vif, pending_idx,
- XEN_NETIF_RSP_OKAY);
+ xenvif_idx_unmap(vif, pending_idx);
continue;
}
@@ -944,20 +959,45 @@
/* Not the first error? Preceding frags already invalidated. */
if (err)
continue;
-
/* First error: invalidate header and preceding fragments. */
- pending_idx = *((u16 *)skb->data);
- xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY);
+ if (!first_skb)
+ pending_idx = XENVIF_TX_CB(skb)->pending_idx;
+ else
+ pending_idx = XENVIF_TX_CB(skb)->pending_idx;
+ xenvif_idx_unmap(vif, pending_idx);
for (j = start; j < i; j++) {
pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
- xenvif_idx_release(vif, pending_idx,
- XEN_NETIF_RSP_OKAY);
+ xenvif_idx_unmap(vif, pending_idx);
}
/* Remember the error: invalidate all subsequent fragments. */
err = newerr;
}
+ if (skb_has_frag_list(skb)) {
+ first_skb = skb;
+ skb = shinfo->frag_list;
+ shinfo = skb_shinfo(skb);
+ nr_frags = shinfo->nr_frags;
+ start = 0;
+
+ goto check_frags;
+ }
+
+ /* There was a mapping error in the frag_list skb. We have to unmap
+ * the first skb's frags
+ */
+ if (first_skb && err) {
+ int j;
+ shinfo = skb_shinfo(first_skb);
+ pending_idx = XENVIF_TX_CB(skb)->pending_idx;
+ start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);
+ for (j = start; j < shinfo->nr_frags; j++) {
+ pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
+ xenvif_idx_unmap(vif, pending_idx);
+ }
+ }
+
*gopp = gop + 1;
return err;
}
@@ -967,6 +1007,10 @@
struct skb_shared_info *shinfo = skb_shinfo(skb);
int nr_frags = shinfo->nr_frags;
int i;
+ u16 prev_pending_idx = INVALID_PENDING_IDX;
+
+ if (skb_shinfo(skb)->destructor_arg)
+ prev_pending_idx = XENVIF_TX_CB(skb)->pending_idx;
for (i = 0; i < nr_frags; i++) {
skb_frag_t *frag = shinfo->frags + i;
@@ -976,6 +1020,17 @@
pending_idx = frag_get_pending_idx(frag);
+ /* If this is not the first frag, chain it to the previous*/
+ if (unlikely(prev_pending_idx == INVALID_PENDING_IDX))
+ skb_shinfo(skb)->destructor_arg =
+ &callback_param(vif, pending_idx);
+ else if (likely(pending_idx != prev_pending_idx))
+ callback_param(vif, prev_pending_idx).ctx =
+ &callback_param(vif, pending_idx);
+
+ callback_param(vif, pending_idx).ctx = NULL;
+ prev_pending_idx = pending_idx;
+
txp = &vif->pending_tx_info[pending_idx].req;
page = virt_to_page(idx_to_kaddr(vif, pending_idx));
__skb_fill_page_desc(skb, i, page, txp->offset, txp->size);
@@ -983,10 +1038,15 @@
skb->data_len += txp->size;
skb->truesize += txp->size;
- /* Take an extra reference to offset xenvif_idx_release */
+ /* Take an extra reference to offset network stack's put_page */
get_page(vif->mmap_pages[pending_idx]);
- xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY);
}
+ /* FIXME: __skb_fill_page_desc set this to true because page->pfmemalloc
+ * overlaps with "index", and "mapping" is not set. I think mapping
+ * should be set. If delivered to local stack, it would drop this
+ * skb in sk_filter unless the socket has the right to use it.
+ */
+ skb->pfmemalloc = false;
}
static int xenvif_get_extras(struct xenvif *vif,
@@ -1106,16 +1166,13 @@
static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget)
{
- struct gnttab_copy *gop = vif->tx_copy_ops, *request_gop;
+ struct gnttab_map_grant_ref *gop = vif->tx_map_ops, *request_gop;
struct sk_buff *skb;
int ret;
- while ((nr_pending_reqs(vif) + XEN_NETBK_LEGACY_SLOTS_MAX
- < MAX_PENDING_REQS) &&
- (skb_queue_len(&vif->tx_queue) < budget)) {
+ while (skb_queue_len(&vif->tx_queue) < budget) {
struct xen_netif_tx_request txreq;
struct xen_netif_tx_request txfrags[XEN_NETBK_LEGACY_SLOTS_MAX];
- struct page *page;
struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1];
u16 pending_idx;
RING_IDX idx;
@@ -1191,8 +1248,7 @@
ret < XEN_NETBK_LEGACY_SLOTS_MAX) ?
PKT_PROT_LEN : txreq.size;
- skb = alloc_skb(data_len + NET_SKB_PAD + NET_IP_ALIGN,
- GFP_ATOMIC | __GFP_NOWARN);
+ skb = xenvif_alloc_skb(data_len);
if (unlikely(skb == NULL)) {
netdev_dbg(vif->dev,
"Can't allocate a skb in start_xmit.\n");
@@ -1200,9 +1256,6 @@
break;
}
- /* Packets passed to netif_rx() must have some headroom. */
- skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
-
if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) {
struct xen_netif_extra_info *gso;
gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
@@ -1214,31 +1267,11 @@
}
}
- /* XXX could copy straight to head */
- page = xenvif_alloc_page(vif, pending_idx);
- if (!page) {
- kfree_skb(skb);
- xenvif_tx_err(vif, &txreq, idx);
- break;
- }
-
- gop->source.u.ref = txreq.gref;
- gop->source.domid = vif->domid;
- gop->source.offset = txreq.offset;
-
- gop->dest.u.gmfn = virt_to_mfn(page_address(page));
- gop->dest.domid = DOMID_SELF;
- gop->dest.offset = txreq.offset;
-
- gop->len = txreq.size;
- gop->flags = GNTCOPY_source_gref;
+ xenvif_tx_create_gop(vif, pending_idx, &txreq, gop);
gop++;
- memcpy(&vif->pending_tx_info[pending_idx].req,
- &txreq, sizeof(txreq));
- vif->pending_tx_info[pending_idx].head = index;
- *((u16 *)skb->data) = pending_idx;
+ XENVIF_TX_CB(skb)->pending_idx = pending_idx;
__skb_put(skb, data_len);
@@ -1266,17 +1299,82 @@
vif->tx.req_cons = idx;
- if ((gop-vif->tx_copy_ops) >= ARRAY_SIZE(vif->tx_copy_ops))
+ if ((gop-vif->tx_map_ops) >= ARRAY_SIZE(vif->tx_map_ops))
break;
}
- return gop - vif->tx_copy_ops;
+ return gop - vif->tx_map_ops;
}
+/* Consolidate skb with a frag_list into a brand new one with local pages on
+ * frags. Returns 0 or -ENOMEM if can't allocate new pages.
+ */
+static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb)
+{
+ unsigned int offset = skb_headlen(skb);
+ skb_frag_t frags[MAX_SKB_FRAGS];
+ int i;
+ struct ubuf_info *uarg;
+ struct sk_buff *nskb = skb_shinfo(skb)->frag_list;
+
+ vif->tx_zerocopy_sent += 2;
+ vif->tx_frag_overflow++;
+
+ xenvif_fill_frags(vif, nskb);
+ /* Subtract frags size, we will correct it later */
+ skb->truesize -= skb->data_len;
+ skb->len += nskb->len;
+ skb->data_len += nskb->len;
+
+ /* create a brand new frags array and coalesce there */
+ for (i = 0; offset < skb->len; i++) {
+ struct page *page;
+ unsigned int len;
+
+ BUG_ON(i >= MAX_SKB_FRAGS);
+ page = alloc_page(GFP_ATOMIC|__GFP_COLD);
+ if (!page) {
+ int j;
+ skb->truesize += skb->data_len;
+ for (j = 0; j < i; j++)
+ put_page(frags[j].page.p);
+ return -ENOMEM;
+ }
+
+ if (offset + PAGE_SIZE < skb->len)
+ len = PAGE_SIZE;
+ else
+ len = skb->len - offset;
+ if (skb_copy_bits(skb, offset, page_address(page), len))
+ BUG();
+
+ offset += len;
+ frags[i].page.p = page;
+ frags[i].page_offset = 0;
+ skb_frag_size_set(&frags[i], len);
+ }
+ /* swap out with old one */
+ memcpy(skb_shinfo(skb)->frags,
+ frags,
+ i * sizeof(skb_frag_t));
+ skb_shinfo(skb)->nr_frags = i;
+ skb->truesize += i * PAGE_SIZE;
+
+ /* remove traces of mapped pages and frag_list */
+ skb_frag_list_init(skb);
+ uarg = skb_shinfo(skb)->destructor_arg;
+ uarg->callback(uarg, true);
+ skb_shinfo(skb)->destructor_arg = NULL;
+
+ skb_shinfo(nskb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+ kfree_skb(nskb);
+
+ return 0;
+}
static int xenvif_tx_submit(struct xenvif *vif)
{
- struct gnttab_copy *gop = vif->tx_copy_ops;
+ struct gnttab_map_grant_ref *gop = vif->tx_map_ops;
struct sk_buff *skb;
int work_done = 0;
@@ -1285,7 +1383,7 @@
u16 pending_idx;
unsigned data_len;
- pending_idx = *((u16 *)skb->data);
+ pending_idx = XENVIF_TX_CB(skb)->pending_idx;
txp = &vif->pending_tx_info[pending_idx].req;
/* Check the remap error code. */
@@ -1300,14 +1398,16 @@
memcpy(skb->data,
(void *)(idx_to_kaddr(vif, pending_idx)|txp->offset),
data_len);
+ callback_param(vif, pending_idx).ctx = NULL;
if (data_len < txp->size) {
/* Append the packet payload as a fragment. */
txp->offset += data_len;
txp->size -= data_len;
+ skb_shinfo(skb)->destructor_arg =
+ &callback_param(vif, pending_idx);
} else {
/* Schedule a response immediately. */
- xenvif_idx_release(vif, pending_idx,
- XEN_NETIF_RSP_OKAY);
+ xenvif_idx_unmap(vif, pending_idx);
}
if (txp->flags & XEN_NETTXF_csum_blank)
@@ -1317,6 +1417,17 @@
xenvif_fill_frags(vif, skb);
+ if (unlikely(skb_has_frag_list(skb))) {
+ if (xenvif_handle_frag_list(vif, skb)) {
+ if (net_ratelimit())
+ netdev_err(vif->dev,
+ "Not enough memory to consolidate frag_list!\n");
+ skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+ kfree_skb(skb);
+ continue;
+ }
+ }
+
if (skb_is_nonlinear(skb) && skb_headlen(skb) < PKT_PROT_LEN) {
int target = min_t(int, skb->len, PKT_PROT_LEN);
__pskb_pull_tail(skb, target - skb_headlen(skb));
@@ -1329,6 +1440,9 @@
if (checksum_setup(vif, skb)) {
netdev_dbg(vif->dev,
"Can't setup checksum in net_tx_action\n");
+ /* We have to set this flag to trigger the callback */
+ if (skb_shinfo(skb)->destructor_arg)
+ skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
kfree_skb(skb);
continue;
}
@@ -1354,17 +1468,126 @@
work_done++;
+ /* Set this flag right before netif_receive_skb, otherwise
+ * someone might think this packet already left netback, and
+ * do a skb_copy_ubufs while we are still in control of the
+ * skb. E.g. the __pskb_pull_tail earlier can do such thing.
+ */
+ if (skb_shinfo(skb)->destructor_arg) {
+ skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
+ vif->tx_zerocopy_sent++;
+ }
+
netif_receive_skb(skb);
}
return work_done;
}
+void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success)
+{
+ unsigned long flags;
+ pending_ring_idx_t index;
+ struct xenvif *vif = ubuf_to_vif(ubuf);
+
+ /* This is the only place where we grab this lock, to protect callbacks
+ * from each other.
+ */
+ spin_lock_irqsave(&vif->callback_lock, flags);
+ do {
+ u16 pending_idx = ubuf->desc;
+ ubuf = (struct ubuf_info *) ubuf->ctx;
+ BUG_ON(vif->dealloc_prod - vif->dealloc_cons >=
+ MAX_PENDING_REQS);
+ index = pending_index(vif->dealloc_prod);
+ vif->dealloc_ring[index] = pending_idx;
+ /* Sync with xenvif_tx_dealloc_action:
+ * insert idx then incr producer.
+ */
+ smp_wmb();
+ vif->dealloc_prod++;
+ } while (ubuf);
+ wake_up(&vif->dealloc_wq);
+ spin_unlock_irqrestore(&vif->callback_lock, flags);
+
+ if (likely(zerocopy_success))
+ vif->tx_zerocopy_success++;
+ else
+ vif->tx_zerocopy_fail++;
+}
+
+static inline void xenvif_tx_dealloc_action(struct xenvif *vif)
+{
+ struct gnttab_unmap_grant_ref *gop;
+ pending_ring_idx_t dc, dp;
+ u16 pending_idx, pending_idx_release[MAX_PENDING_REQS];
+ unsigned int i = 0;
+
+ dc = vif->dealloc_cons;
+ gop = vif->tx_unmap_ops;
+
+ /* Free up any grants we have finished using */
+ do {
+ dp = vif->dealloc_prod;
+
+ /* Ensure we see all indices enqueued by all
+ * xenvif_zerocopy_callback().
+ */
+ smp_rmb();
+
+ while (dc != dp) {
+ BUG_ON(gop - vif->tx_unmap_ops > MAX_PENDING_REQS);
+ pending_idx =
+ vif->dealloc_ring[pending_index(dc++)];
+
+ pending_idx_release[gop-vif->tx_unmap_ops] =
+ pending_idx;
+ vif->pages_to_unmap[gop-vif->tx_unmap_ops] =
+ vif->mmap_pages[pending_idx];
+ gnttab_set_unmap_op(gop,
+ idx_to_kaddr(vif, pending_idx),
+ GNTMAP_host_map,
+ vif->grant_tx_handle[pending_idx]);
+ xenvif_grant_handle_reset(vif, pending_idx);
+ ++gop;
+ }
+
+ } while (dp != vif->dealloc_prod);
+
+ vif->dealloc_cons = dc;
+
+ if (gop - vif->tx_unmap_ops > 0) {
+ int ret;
+ ret = gnttab_unmap_refs(vif->tx_unmap_ops,
+ NULL,
+ vif->pages_to_unmap,
+ gop - vif->tx_unmap_ops);
+ if (ret) {
+ netdev_err(vif->dev, "Unmap fail: nr_ops %tx ret %d\n",
+ gop - vif->tx_unmap_ops, ret);
+ for (i = 0; i < gop - vif->tx_unmap_ops; ++i) {
+ if (gop[i].status != GNTST_okay)
+ netdev_err(vif->dev,
+ " host_addr: %llx handle: %x status: %d\n",
+ gop[i].host_addr,
+ gop[i].handle,
+ gop[i].status);
+ }
+ BUG();
+ }
+ }
+
+ for (i = 0; i < gop - vif->tx_unmap_ops; ++i)
+ xenvif_idx_release(vif, pending_idx_release[i],
+ XEN_NETIF_RSP_OKAY);
+}
+
+
/* Called after netfront has transmitted */
int xenvif_tx_action(struct xenvif *vif, int budget)
{
unsigned nr_gops;
- int work_done;
+ int work_done, ret;
if (unlikely(!tx_work_todo(vif)))
return 0;
@@ -1374,7 +1597,11 @@
if (nr_gops == 0)
return 0;
- gnttab_batch_copy(vif->tx_copy_ops, nr_gops);
+ ret = gnttab_map_refs(vif->tx_map_ops,
+ NULL,
+ vif->pages_to_map,
+ nr_gops);
+ BUG_ON(ret);
work_done = xenvif_tx_submit(vif);
@@ -1385,45 +1612,18 @@
u8 status)
{
struct pending_tx_info *pending_tx_info;
- pending_ring_idx_t head;
- u16 peek; /* peek into next tx request */
-
- BUG_ON(vif->mmap_pages[pending_idx] == (void *)(~0UL));
-
- /* Already complete? */
- if (vif->mmap_pages[pending_idx] == NULL)
- return;
+ pending_ring_idx_t index;
+ unsigned long flags;
pending_tx_info = &vif->pending_tx_info[pending_idx];
-
- head = pending_tx_info->head;
-
- BUG_ON(!pending_tx_is_head(vif, head));
- BUG_ON(vif->pending_ring[pending_index(head)] != pending_idx);
-
- do {
- pending_ring_idx_t index;
- pending_ring_idx_t idx = pending_index(head);
- u16 info_idx = vif->pending_ring[idx];
-
- pending_tx_info = &vif->pending_tx_info[info_idx];
- make_tx_response(vif, &pending_tx_info->req, status);
-
- /* Setting any number other than
- * INVALID_PENDING_RING_IDX indicates this slot is
- * starting a new packet / ending a previous packet.
- */
- pending_tx_info->head = 0;
-
- index = pending_index(vif->pending_prod++);
- vif->pending_ring[index] = vif->pending_ring[info_idx];
-
- peek = vif->pending_ring[pending_index(++head)];
-
- } while (!pending_tx_is_head(vif, peek));
-
- put_page(vif->mmap_pages[pending_idx]);
- vif->mmap_pages[pending_idx] = NULL;
+ spin_lock_irqsave(&vif->response_lock, flags);
+ make_tx_response(vif, &pending_tx_info->req, status);
+ index = pending_index(vif->pending_prod);
+ vif->pending_ring[index] = pending_idx;
+ /* TX shouldn't use the index before we give it back here */
+ mb();
+ vif->pending_prod++;
+ spin_unlock_irqrestore(&vif->response_lock, flags);
}
@@ -1471,23 +1671,54 @@
return resp;
}
+void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx)
+{
+ int ret;
+ struct gnttab_unmap_grant_ref tx_unmap_op;
+
+ gnttab_set_unmap_op(&tx_unmap_op,
+ idx_to_kaddr(vif, pending_idx),
+ GNTMAP_host_map,
+ vif->grant_tx_handle[pending_idx]);
+ xenvif_grant_handle_reset(vif, pending_idx);
+
+ ret = gnttab_unmap_refs(&tx_unmap_op, NULL,
+ &vif->mmap_pages[pending_idx], 1);
+ if (ret) {
+ netdev_err(vif->dev,
+ "Unmap fail: ret: %d pending_idx: %d host_addr: %llx handle: %x status: %d\n",
+ ret,
+ pending_idx,
+ tx_unmap_op.host_addr,
+ tx_unmap_op.handle,
+ tx_unmap_op.status);
+ BUG();
+ }
+
+ xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY);
+}
+
static inline int rx_work_todo(struct xenvif *vif)
{
- return (!skb_queue_empty(&vif->rx_queue) && !vif->rx_queue_stopped) ||
- vif->rx_event;
+ return (!skb_queue_empty(&vif->rx_queue) &&
+ xenvif_rx_ring_slots_available(vif, vif->rx_last_skb_slots)) ||
+ vif->rx_queue_purge;
}
static inline int tx_work_todo(struct xenvif *vif)
{
- if (likely(RING_HAS_UNCONSUMED_REQUESTS(&vif->tx)) &&
- (nr_pending_reqs(vif) + XEN_NETBK_LEGACY_SLOTS_MAX
- < MAX_PENDING_REQS))
+ if (likely(RING_HAS_UNCONSUMED_REQUESTS(&vif->tx)))
return 1;
return 0;
}
+static inline bool tx_dealloc_work_todo(struct xenvif *vif)
+{
+ return vif->dealloc_cons != vif->dealloc_prod;
+}
+
void xenvif_unmap_frontend_rings(struct xenvif *vif)
{
if (vif->tx.sring)
@@ -1545,7 +1776,7 @@
netif_wake_queue(vif->dev);
}
-int xenvif_kthread(void *data)
+int xenvif_kthread_guest_rx(void *data)
{
struct xenvif *vif = data;
struct sk_buff *skb;
@@ -1557,14 +1788,19 @@
if (kthread_should_stop())
break;
+ if (vif->rx_queue_purge) {
+ skb_queue_purge(&vif->rx_queue);
+ vif->rx_queue_purge = false;
+ }
+
if (!skb_queue_empty(&vif->rx_queue))
xenvif_rx_action(vif);
- vif->rx_event = false;
-
if (skb_queue_empty(&vif->rx_queue) &&
- netif_queue_stopped(vif->dev))
+ netif_queue_stopped(vif->dev)) {
+ del_timer_sync(&vif->wake_queue);
xenvif_start_queue(vif);
+ }
cond_resched();
}
@@ -1576,6 +1812,28 @@
return 0;
}
+int xenvif_dealloc_kthread(void *data)
+{
+ struct xenvif *vif = data;
+
+ while (!kthread_should_stop()) {
+ wait_event_interruptible(vif->dealloc_wq,
+ tx_dealloc_work_todo(vif) ||
+ kthread_should_stop());
+ if (kthread_should_stop())
+ break;
+
+ xenvif_tx_dealloc_action(vif);
+ cond_resched();
+ }
+
+ /* Unmap anything remaining*/
+ if (tx_dealloc_work_todo(vif))
+ xenvif_tx_dealloc_action(vif);
+
+ return 0;
+}
+
static int __init netback_init(void)
{
int rc = 0;
@@ -1593,6 +1851,8 @@
if (rc)
goto failed_init;
+ rx_drain_timeout_jiffies = msecs_to_jiffies(rx_drain_timeout_msecs);
+
return 0;
failed_init:
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index ff04d4f..057b0570 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -658,7 +658,7 @@
drop:
dev->stats.tx_dropped++;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -907,6 +907,7 @@
/* Ethernet work: Delayed to here as it peeks the header. */
skb->protocol = eth_type_trans(skb, dev);
+ skb_reset_network_header(skb);
if (checksum_setup(dev, skb)) {
kfree_skb(skb);
@@ -1059,13 +1060,13 @@
unsigned int start;
do {
- start = u64_stats_fetch_begin_bh(&stats->syncp);
+ start = u64_stats_fetch_begin_irq(&stats->syncp);
rx_packets = stats->rx_packets;
tx_packets = stats->tx_packets;
rx_bytes = stats->rx_bytes;
tx_bytes = stats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&stats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&stats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
@@ -1281,16 +1282,10 @@
np->rx_refill_timer.function = rx_refill_timeout;
err = -ENOMEM;
- np->stats = alloc_percpu(struct netfront_stats);
+ np->stats = netdev_alloc_pcpu_stats(struct netfront_stats);
if (np->stats == NULL)
goto exit;
- for_each_possible_cpu(i) {
- struct netfront_stats *xen_nf_stats;
- xen_nf_stats = per_cpu_ptr(np->stats, i);
- u64_stats_init(&xen_nf_stats->syncp);
- }
-
/* Initialise tx_skbs as a free chain containing every entry. */
np->tx_skb_freelist = 0;
for (i = 0; i < NET_TX_RING_SIZE; i++) {
@@ -1832,7 +1827,6 @@
case XenbusStateReconfiguring:
case XenbusStateReconfigured:
case XenbusStateUnknown:
- case XenbusStateClosed:
break;
case XenbusStateInitWait:
@@ -1847,6 +1841,10 @@
netdev_notify_peers(netdev);
break;
+ case XenbusStateClosed:
+ if (dev->state == XenbusStateClosed)
+ break;
+ /* Missed the backend's CLOSING state -- fallthrough */
case XenbusStateClosing:
xenbus_frontend_closed(dev);
break;
diff --git a/drivers/of/address.c b/drivers/of/address.c
index d3dd41c..1a54f1f 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -99,11 +99,12 @@
static int of_bus_pci_match(struct device_node *np)
{
/*
+ * "pciex" is PCI Express
* "vci" is for the /chaos bridge on 1st-gen PCI powermacs
* "ht" is hypertransport
*/
- return !strcmp(np->type, "pci") || !strcmp(np->type, "vci") ||
- !strcmp(np->type, "ht");
+ return !strcmp(np->type, "pci") || !strcmp(np->type, "pciex") ||
+ !strcmp(np->type, "vci") || !strcmp(np->type, "ht");
}
static void of_bus_pci_count_cells(struct device_node *np,
diff --git a/drivers/of/base.c b/drivers/of/base.c
index ff85450..89e888a 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -342,27 +342,72 @@
}
EXPORT_SYMBOL(of_get_cpu_node);
-/** Checks if the given "compat" string matches one of the strings in
- * the device's "compatible" property
+/**
+ * __of_device_is_compatible() - Check if the node matches given constraints
+ * @device: pointer to node
+ * @compat: required compatible string, NULL or "" for any match
+ * @type: required device_type value, NULL or "" for any match
+ * @name: required node name, NULL or "" for any match
+ *
+ * Checks if the given @compat, @type and @name strings match the
+ * properties of the given @device. A constraints can be skipped by
+ * passing NULL or an empty string as the constraint.
+ *
+ * Returns 0 for no match, and a positive integer on match. The return
+ * value is a relative score with larger values indicating better
+ * matches. The score is weighted for the most specific compatible value
+ * to get the highest score. Matching type is next, followed by matching
+ * name. Practically speaking, this results in the following priority
+ * order for matches:
+ *
+ * 1. specific compatible && type && name
+ * 2. specific compatible && type
+ * 3. specific compatible && name
+ * 4. specific compatible
+ * 5. general compatible && type && name
+ * 6. general compatible && type
+ * 7. general compatible && name
+ * 8. general compatible
+ * 9. type && name
+ * 10. type
+ * 11. name
*/
static int __of_device_is_compatible(const struct device_node *device,
- const char *compat)
+ const char *compat, const char *type, const char *name)
{
- const char* cp;
- int cplen, l;
+ struct property *prop;
+ const char *cp;
+ int index = 0, score = 0;
- cp = __of_get_property(device, "compatible", &cplen);
- if (cp == NULL)
- return 0;
- while (cplen > 0) {
- if (of_compat_cmp(cp, compat, strlen(compat)) == 0)
- return 1;
- l = strlen(cp) + 1;
- cp += l;
- cplen -= l;
+ /* Compatible match has highest priority */
+ if (compat && compat[0]) {
+ prop = __of_find_property(device, "compatible", NULL);
+ for (cp = of_prop_next_string(prop, NULL); cp;
+ cp = of_prop_next_string(prop, cp), index++) {
+ if (of_compat_cmp(cp, compat, strlen(compat)) == 0) {
+ score = INT_MAX/2 - (index << 2);
+ break;
+ }
+ }
+ if (!score)
+ return 0;
}
- return 0;
+ /* Matching type is better than matching name */
+ if (type && type[0]) {
+ if (!device->type || of_node_cmp(type, device->type))
+ return 0;
+ score += 2;
+ }
+
+ /* Matching name is a bit better than not */
+ if (name && name[0]) {
+ if (!device->name || of_node_cmp(name, device->name))
+ return 0;
+ score++;
+ }
+
+ return score;
}
/** Checks if the given "compat" string matches one of the strings in
@@ -375,7 +420,7 @@
int res;
raw_spin_lock_irqsave(&devtree_lock, flags);
- res = __of_device_is_compatible(device, compat);
+ res = __of_device_is_compatible(device, compat, NULL, NULL);
raw_spin_unlock_irqrestore(&devtree_lock, flags);
return res;
}
@@ -681,10 +726,7 @@
raw_spin_lock_irqsave(&devtree_lock, flags);
np = from ? from->allnext : of_allnodes;
for (; np; np = np->allnext) {
- if (type
- && !(np->type && (of_node_cmp(np->type, type) == 0)))
- continue;
- if (__of_device_is_compatible(np, compatible) &&
+ if (__of_device_is_compatible(np, compatible, type, NULL) &&
of_node_get(np))
break;
}
@@ -734,43 +776,22 @@
const struct of_device_id *__of_match_node(const struct of_device_id *matches,
const struct device_node *node)
{
- const char *cp;
- int cplen, l;
+ const struct of_device_id *best_match = NULL;
+ int score, best_score = 0;
if (!matches)
return NULL;
- cp = __of_get_property(node, "compatible", &cplen);
- do {
- const struct of_device_id *m = matches;
-
- /* Check against matches with current compatible string */
- while (m->name[0] || m->type[0] || m->compatible[0]) {
- int match = 1;
- if (m->name[0])
- match &= node->name
- && !strcmp(m->name, node->name);
- if (m->type[0])
- match &= node->type
- && !strcmp(m->type, node->type);
- if (m->compatible[0])
- match &= cp
- && !of_compat_cmp(m->compatible, cp,
- strlen(m->compatible));
- if (match)
- return m;
- m++;
+ for (; matches->name[0] || matches->type[0] || matches->compatible[0]; matches++) {
+ score = __of_device_is_compatible(node, matches->compatible,
+ matches->type, matches->name);
+ if (score > best_score) {
+ best_match = matches;
+ best_score = score;
}
+ }
- /* Get node's next compatible string */
- if (cp) {
- l = strlen(cp) + 1;
- cp += l;
- cplen -= l;
- }
- } while (cp && (cplen > 0));
-
- return NULL;
+ return best_match;
}
/**
@@ -778,10 +799,7 @@
* @matches: array of of device match structures to search in
* @node: the of device structure to match against
*
- * Low level utility function used by device matching. Matching order
- * is to compare each of the node's compatibles with all given matches
- * first. This implies node's compatible is sorted from specific to
- * generic while matches can be in any order.
+ * Low level utility function used by device matching.
*/
const struct of_device_id *of_match_node(const struct of_device_id *matches,
const struct device_node *node)
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 875b7b6..9a95831 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -24,7 +24,11 @@
static void of_set_phy_supported(struct phy_device *phydev, u32 max_speed)
{
- phydev->supported |= PHY_DEFAULT_FEATURES;
+ /* The default values for phydev->supported are provided by the PHY
+ * driver "features" member, we want to reset to sane defaults fist
+ * before supporting higher speeds.
+ */
+ phydev->supported &= PHY_DEFAULT_FEATURES;
switch (max_speed) {
default:
@@ -39,27 +43,50 @@
}
}
+/* Extract the clause 22 phy ID from the compatible string of the form
+ * ethernet-phy-idAAAA.BBBB */
+static int of_get_phy_id(struct device_node *device, u32 *phy_id)
+{
+ struct property *prop;
+ const char *cp;
+ unsigned int upper, lower;
+
+ of_property_for_each_string(device, "compatible", prop, cp) {
+ if (sscanf(cp, "ethernet-phy-id%4x.%4x", &upper, &lower) == 2) {
+ *phy_id = ((upper & 0xFFFF) << 16) | (lower & 0xFFFF);
+ return 0;
+ }
+ }
+ return -EINVAL;
+}
+
static int of_mdiobus_register_phy(struct mii_bus *mdio, struct device_node *child,
u32 addr)
{
struct phy_device *phy;
bool is_c45;
- int rc, prev_irq;
+ int rc;
u32 max_speed = 0;
+ u32 phy_id;
is_c45 = of_device_is_compatible(child,
"ethernet-phy-ieee802.3-c45");
- phy = get_phy_device(mdio, addr, is_c45);
+ if (!is_c45 && !of_get_phy_id(child, &phy_id))
+ phy = phy_device_create(mdio, addr, phy_id, 0, NULL);
+ else
+ phy = get_phy_device(mdio, addr, is_c45);
if (!phy || IS_ERR(phy))
return 1;
- if (mdio->irq) {
- prev_irq = mdio->irq[addr];
- mdio->irq[addr] =
- irq_of_parse_and_map(child, 0);
- if (!mdio->irq[addr])
- mdio->irq[addr] = prev_irq;
+ rc = irq_of_parse_and_map(child, 0);
+ if (rc > 0) {
+ phy->irq = rc;
+ if (mdio->irq)
+ mdio->irq[addr] = rc;
+ } else {
+ if (mdio->irq)
+ phy->irq = mdio->irq[addr];
}
/* Associate the OF node with the device structure so it
diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c
index a208a45..84215c1 100644
--- a/drivers/of/of_net.c
+++ b/drivers/of/of_net.c
@@ -12,28 +12,6 @@
#include <linux/export.h>
/**
- * It maps 'enum phy_interface_t' found in include/linux/phy.h
- * into the device tree binding of 'phy-mode', so that Ethernet
- * device driver can get phy interface from device tree.
- */
-static const char *phy_modes[] = {
- [PHY_INTERFACE_MODE_NA] = "",
- [PHY_INTERFACE_MODE_MII] = "mii",
- [PHY_INTERFACE_MODE_GMII] = "gmii",
- [PHY_INTERFACE_MODE_SGMII] = "sgmii",
- [PHY_INTERFACE_MODE_TBI] = "tbi",
- [PHY_INTERFACE_MODE_REVMII] = "rev-mii",
- [PHY_INTERFACE_MODE_RMII] = "rmii",
- [PHY_INTERFACE_MODE_RGMII] = "rgmii",
- [PHY_INTERFACE_MODE_RGMII_ID] = "rgmii-id",
- [PHY_INTERFACE_MODE_RGMII_RXID] = "rgmii-rxid",
- [PHY_INTERFACE_MODE_RGMII_TXID] = "rgmii-txid",
- [PHY_INTERFACE_MODE_RTBI] = "rtbi",
- [PHY_INTERFACE_MODE_SMII] = "smii",
- [PHY_INTERFACE_MODE_XGMII] = "xgmii",
-};
-
-/**
* of_get_phy_mode - Get phy mode for given device_node
* @np: Pointer to the given device_node
*
@@ -49,8 +27,8 @@
if (err < 0)
return err;
- for (i = 0; i < ARRAY_SIZE(phy_modes); i++)
- if (!strcasecmp(pm, phy_modes[i]))
+ for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++)
+ if (!strcasecmp(pm, phy_modes(i)))
return i;
return -ENODEV;
diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c
index e21012b..6643d19 100644
--- a/drivers/of/selftest.c
+++ b/drivers/of/selftest.c
@@ -300,6 +300,72 @@
of_node_put(np);
}
+static struct of_device_id match_node_table[] = {
+ { .data = "A", .name = "name0", }, /* Name alone is lowest priority */
+ { .data = "B", .type = "type1", }, /* followed by type alone */
+
+ { .data = "Ca", .name = "name2", .type = "type1", }, /* followed by both together */
+ { .data = "Cb", .name = "name2", }, /* Only match when type doesn't match */
+ { .data = "Cc", .name = "name2", .type = "type2", },
+
+ { .data = "E", .compatible = "compat3" },
+ { .data = "G", .compatible = "compat2", },
+ { .data = "H", .compatible = "compat2", .name = "name5", },
+ { .data = "I", .compatible = "compat2", .type = "type1", },
+ { .data = "J", .compatible = "compat2", .type = "type1", .name = "name8", },
+ { .data = "K", .compatible = "compat2", .name = "name9", },
+ {}
+};
+
+static struct {
+ const char *path;
+ const char *data;
+} match_node_tests[] = {
+ { .path = "/testcase-data/match-node/name0", .data = "A", },
+ { .path = "/testcase-data/match-node/name1", .data = "B", },
+ { .path = "/testcase-data/match-node/a/name2", .data = "Ca", },
+ { .path = "/testcase-data/match-node/b/name2", .data = "Cb", },
+ { .path = "/testcase-data/match-node/c/name2", .data = "Cc", },
+ { .path = "/testcase-data/match-node/name3", .data = "E", },
+ { .path = "/testcase-data/match-node/name4", .data = "G", },
+ { .path = "/testcase-data/match-node/name5", .data = "H", },
+ { .path = "/testcase-data/match-node/name6", .data = "G", },
+ { .path = "/testcase-data/match-node/name7", .data = "I", },
+ { .path = "/testcase-data/match-node/name8", .data = "J", },
+ { .path = "/testcase-data/match-node/name9", .data = "K", },
+};
+
+static void __init of_selftest_match_node(void)
+{
+ struct device_node *np;
+ const struct of_device_id *match;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(match_node_tests); i++) {
+ np = of_find_node_by_path(match_node_tests[i].path);
+ if (!np) {
+ selftest(0, "missing testcase node %s\n",
+ match_node_tests[i].path);
+ continue;
+ }
+
+ match = of_match_node(match_node_table, np);
+ if (!match) {
+ selftest(0, "%s didn't match anything\n",
+ match_node_tests[i].path);
+ continue;
+ }
+
+ if (strcmp(match->data, match_node_tests[i].data) != 0) {
+ selftest(0, "%s got wrong match. expected %s, got %s\n",
+ match_node_tests[i].path, match_node_tests[i].data,
+ (const char *)match->data);
+ continue;
+ }
+ selftest(1, "passed");
+ }
+}
+
static int __init of_selftest(void)
{
struct device_node *np;
@@ -316,6 +382,7 @@
of_selftest_property_match_string();
of_selftest_parse_interrupts();
of_selftest_parse_interrupts_extended();
+ of_selftest_match_node();
pr_info("end of selftest - %i passed, %i failed\n",
selftest_results.passed, selftest_results.failed);
return 0;
diff --git a/drivers/of/testcase-data/testcases.dtsi b/drivers/of/testcase-data/testcases.dtsi
new file mode 100644
index 0000000..3a5b75a
--- /dev/null
+++ b/drivers/of/testcase-data/testcases.dtsi
@@ -0,0 +1,3 @@
+#include "tests-phandle.dtsi"
+#include "tests-interrupts.dtsi"
+#include "tests-match.dtsi"
diff --git a/arch/arm/boot/dts/testcases/tests-interrupts.dtsi b/drivers/of/testcase-data/tests-interrupts.dtsi
similarity index 100%
rename from arch/arm/boot/dts/testcases/tests-interrupts.dtsi
rename to drivers/of/testcase-data/tests-interrupts.dtsi
diff --git a/drivers/of/testcase-data/tests-match.dtsi b/drivers/of/testcase-data/tests-match.dtsi
new file mode 100644
index 0000000..c9e5411
--- /dev/null
+++ b/drivers/of/testcase-data/tests-match.dtsi
@@ -0,0 +1,19 @@
+
+/ {
+ testcase-data {
+ match-node {
+ name0 { };
+ name1 { device_type = "type1"; };
+ a { name2 { device_type = "type1"; }; };
+ b { name2 { }; };
+ c { name2 { device_type = "type2"; }; };
+ name3 { compatible = "compat3"; };
+ name4 { compatible = "compat2", "compat3"; };
+ name5 { compatible = "compat2", "compat3"; };
+ name6 { compatible = "compat1", "compat2", "compat3"; };
+ name7 { compatible = "compat2"; device_type = "type1"; };
+ name8 { compatible = "compat2"; device_type = "type1"; };
+ name9 { compatible = "compat2"; };
+ };
+ };
+};
diff --git a/arch/arm/boot/dts/testcases/tests-phandle.dtsi b/drivers/of/testcase-data/tests-phandle.dtsi
similarity index 100%
rename from arch/arm/boot/dts/testcases/tests-phandle.dtsi
rename to drivers/of/testcase-data/tests-phandle.dtsi
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 00660cc..3890166 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -162,8 +162,6 @@
avail = *r;
pci_clip_resource_to_region(bus, &avail, region);
- if (!resource_size(&avail))
- continue;
/*
* "min" is typically PCIBIOS_MIN_IO or PCIBIOS_MIN_MEM to
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index 13478ec..0e79665 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -60,14 +60,6 @@
#define PCIE_DEBUG_CTRL 0x1a60
#define PCIE_DEBUG_SOFT_RESET BIT(20)
-/*
- * This product ID is registered by Marvell, and used when the Marvell
- * SoC is not the root complex, but an endpoint on the PCIe bus. It is
- * therefore safe to re-use this PCI ID for our emulated PCI-to-PCI
- * bridge.
- */
-#define MARVELL_EMULATED_PCI_PCI_BRIDGE_ID 0x7846
-
/* PCI configuration space of a PCI-to-PCI bridge */
struct mvebu_sw_pci_bridge {
u16 vendor;
@@ -388,7 +380,8 @@
bridge->class = PCI_CLASS_BRIDGE_PCI;
bridge->vendor = PCI_VENDOR_ID_MARVELL;
- bridge->device = MARVELL_EMULATED_PCI_PCI_BRIDGE_ID;
+ bridge->device = mvebu_readl(port, PCIE_DEV_ID_OFF) >> 16;
+ bridge->revision = mvebu_readl(port, PCIE_DEV_REV_OFF) & 0xff;
bridge->header_type = PCI_HEADER_TYPE_BRIDGE;
bridge->cache_line_size = 0x10;
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index e2a783f..7c7a388 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -730,6 +730,17 @@
return (unsigned int)sta;
}
+static inline bool device_status_valid(unsigned int sta)
+{
+ /*
+ * ACPI spec says that _STA may return bit 0 clear with bit 3 set
+ * if the device is valid but does not require a device driver to be
+ * loaded (Section 6.3.7 of ACPI 5.0A).
+ */
+ unsigned int mask = ACPI_STA_DEVICE_ENABLED | ACPI_STA_DEVICE_FUNCTIONING;
+ return (sta & mask) == mask;
+}
+
/**
* trim_stale_devices - remove PCI devices that are not responding.
* @dev: PCI device to start walking the hierarchy from.
@@ -745,7 +756,7 @@
unsigned long long sta;
status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
- alive = (ACPI_SUCCESS(status) && sta == ACPI_STA_ALL)
+ alive = (ACPI_SUCCESS(status) && device_status_valid(sta))
|| acpiphp_no_hotplug(handle);
}
if (!alive) {
@@ -792,7 +803,7 @@
mutex_lock(&slot->crit_sect);
if (slot_no_hotplug(slot)) {
; /* do nothing */
- } else if (get_slot_status(slot) == ACPI_STA_ALL) {
+ } else if (device_status_valid(get_slot_status(slot))) {
/* remove stale devices if any */
list_for_each_entry_safe_reverse(dev, tmp,
&bus->devices, bus_list)
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 7a0fec6..955ab79 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -545,9 +545,15 @@
return -ENOMEM;
list_for_each_entry(entry, &pdev->msi_list, list) {
char *name = kmalloc(20, GFP_KERNEL);
- msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL);
- if (!msi_dev_attr)
+ if (!name)
goto error_attrs;
+
+ msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL);
+ if (!msi_dev_attr) {
+ kfree(name);
+ goto error_attrs;
+ }
+
sprintf(name, "%d", entry->irq);
sysfs_attr_init(&msi_dev_attr->attr);
msi_dev_attr->attr.name = name;
@@ -589,6 +595,7 @@
++count;
msi_attr = msi_attrs[count];
}
+ kfree(msi_attrs);
return ret;
}
@@ -959,7 +966,6 @@
/**
* pci_msix_vec_count - return the number of device's MSI-X table entries
* @dev: pointer to the pci_dev data structure of MSI-X device function
-
* This function returns the number of device's MSI-X table entries and
* therefore the number of MSI-X vectors device is capable of sending.
* It returns a negative errno if the device is not capable of sending MSI-X
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 1febe90..fdbc294 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1181,6 +1181,8 @@
static int do_pci_enable_device(struct pci_dev *dev, int bars)
{
int err;
+ u16 cmd;
+ u8 pin;
err = pci_set_power_state(dev, PCI_D0);
if (err < 0 && err != -EIO)
@@ -1190,6 +1192,17 @@
return err;
pci_fixup_device(pci_fixup_enable, dev);
+ if (dev->msi_enabled || dev->msix_enabled)
+ return 0;
+
+ pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+ if (pin) {
+ pci_read_config_word(dev, PCI_COMMAND, &cmd);
+ if (cmd & PCI_COMMAND_INTX_DISABLE)
+ pci_write_config_word(dev, PCI_COMMAND,
+ cmd & ~PCI_COMMAND_INTX_DISABLE);
+ }
+
return 0;
}
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index afa2354..c7a551c 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -5,7 +5,7 @@
menu "PHY Subsystem"
config GENERIC_PHY
- tristate "PHY Core"
+ bool "PHY Core"
help
Generic PHY support.
@@ -61,6 +61,7 @@
config BCM_KONA_USB2_PHY
tristate "Broadcom Kona USB2 PHY Driver"
depends on GENERIC_PHY
+ depends on HAS_IOMEM
help
Enable this to support the Broadcom Kona USB 2.0 PHY.
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 645c867..6c73837 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -162,6 +162,9 @@
{
int ret;
+ if (!phy)
+ return 0;
+
ret = phy_pm_runtime_get_sync(phy);
if (ret < 0 && ret != -ENOTSUPP)
return ret;
@@ -173,6 +176,8 @@
dev_err(&phy->dev, "phy init failed --> %d\n", ret);
goto out;
}
+ } else {
+ ret = 0; /* Override possible ret == -ENOTSUPP */
}
++phy->init_count;
@@ -187,6 +192,9 @@
{
int ret;
+ if (!phy)
+ return 0;
+
ret = phy_pm_runtime_get_sync(phy);
if (ret < 0 && ret != -ENOTSUPP)
return ret;
@@ -212,6 +220,9 @@
{
int ret;
+ if (!phy)
+ return 0;
+
ret = phy_pm_runtime_get_sync(phy);
if (ret < 0 && ret != -ENOTSUPP)
return ret;
@@ -223,6 +234,8 @@
dev_err(&phy->dev, "phy poweron failed --> %d\n", ret);
goto out;
}
+ } else {
+ ret = 0; /* Override possible ret == -ENOTSUPP */
}
++phy->power_count;
mutex_unlock(&phy->mutex);
@@ -240,6 +253,9 @@
{
int ret;
+ if (!phy)
+ return 0;
+
mutex_lock(&phy->mutex);
if (phy->power_count == 1 && phy->ops->power_off) {
ret = phy->ops->power_off(phy);
@@ -308,7 +324,7 @@
*/
void phy_put(struct phy *phy)
{
- if (IS_ERR(phy))
+ if (!phy || IS_ERR(phy))
return;
module_put(phy->ops->owner);
@@ -328,6 +344,9 @@
{
int r;
+ if (!phy)
+ return;
+
r = devres_destroy(dev, devm_phy_release, devm_phy_match, phy);
dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n");
}
@@ -389,17 +408,11 @@
index = of_property_match_string(dev->of_node, "phy-names",
string);
phy = of_phy_get(dev, index);
- if (IS_ERR(phy)) {
- dev_err(dev, "unable to find phy\n");
- return phy;
- }
} else {
phy = phy_lookup(dev, string);
- if (IS_ERR(phy)) {
- dev_err(dev, "unable to find phy\n");
- return phy;
- }
}
+ if (IS_ERR(phy))
+ return phy;
if (!try_module_get(phy->ops->owner))
return ERR_PTR(-EPROBE_DEFER);
@@ -411,6 +424,27 @@
EXPORT_SYMBOL_GPL(phy_get);
/**
+ * phy_optional_get() - lookup and obtain a reference to an optional phy.
+ * @dev: device that requests this phy
+ * @string: the phy name as given in the dt data or the name of the controller
+ * port for non-dt case
+ *
+ * Returns the phy driver, after getting a refcount to it; or
+ * NULL if there is no such phy. The caller is responsible for
+ * calling phy_put() to release that count.
+ */
+struct phy *phy_optional_get(struct device *dev, const char *string)
+{
+ struct phy *phy = phy_get(dev, string);
+
+ if (PTR_ERR(phy) == -ENODEV)
+ phy = NULL;
+
+ return phy;
+}
+EXPORT_SYMBOL_GPL(phy_optional_get);
+
+/**
* devm_phy_get() - lookup and obtain a reference to a phy.
* @dev: device that requests this phy
* @string: the phy name as given in the dt data or phy device name
@@ -441,6 +475,30 @@
EXPORT_SYMBOL_GPL(devm_phy_get);
/**
+ * devm_phy_optional_get() - lookup and obtain a reference to an optional phy.
+ * @dev: device that requests this phy
+ * @string: the phy name as given in the dt data or phy device name
+ * for non-dt case
+ *
+ * Gets the phy using phy_get(), and associates a device with it using
+ * devres. On driver detach, release function is invoked on the devres
+ * data, then, devres data is freed. This differs to devm_phy_get() in
+ * that if the phy does not exist, it is not considered an error and
+ * -ENODEV will not be returned. Instead the NULL phy is returned,
+ * which can be passed to all other phy consumer calls.
+ */
+struct phy *devm_phy_optional_get(struct device *dev, const char *string)
+{
+ struct phy *phy = devm_phy_get(dev, string);
+
+ if (PTR_ERR(phy) == -ENODEV)
+ phy = NULL;
+
+ return phy;
+}
+EXPORT_SYMBOL_GPL(devm_phy_optional_get);
+
+/**
* phy_create() - create a new phy
* @dev: device that is creating the new phy
* @ops: function pointers for performing phy operations
diff --git a/drivers/phy/phy-exynos-dp-video.c b/drivers/phy/phy-exynos-dp-video.c
index 1dbe6ce..0786fef 100644
--- a/drivers/phy/phy-exynos-dp-video.c
+++ b/drivers/phy/phy-exynos-dp-video.c
@@ -76,10 +76,6 @@
if (IS_ERR(state->regs))
return PTR_ERR(state->regs);
- phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
- if (IS_ERR(phy_provider))
- return PTR_ERR(phy_provider);
-
phy = devm_phy_create(dev, &exynos_dp_video_phy_ops, NULL);
if (IS_ERR(phy)) {
dev_err(dev, "failed to create Display Port PHY\n");
@@ -87,6 +83,10 @@
}
phy_set_drvdata(phy, state);
+ phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
+ if (IS_ERR(phy_provider))
+ return PTR_ERR(phy_provider);
+
return 0;
}
diff --git a/drivers/phy/phy-exynos-mipi-video.c b/drivers/phy/phy-exynos-mipi-video.c
index 0c5efab..7f13932 100644
--- a/drivers/phy/phy-exynos-mipi-video.c
+++ b/drivers/phy/phy-exynos-mipi-video.c
@@ -134,11 +134,6 @@
dev_set_drvdata(dev, state);
spin_lock_init(&state->slock);
- phy_provider = devm_of_phy_provider_register(dev,
- exynos_mipi_video_phy_xlate);
- if (IS_ERR(phy_provider))
- return PTR_ERR(phy_provider);
-
for (i = 0; i < EXYNOS_MIPI_PHYS_NUM; i++) {
struct phy *phy = devm_phy_create(dev,
&exynos_mipi_video_phy_ops, NULL);
@@ -152,6 +147,11 @@
phy_set_drvdata(phy, &state->phys[i]);
}
+ phy_provider = devm_of_phy_provider_register(dev,
+ exynos_mipi_video_phy_xlate);
+ if (IS_ERR(phy_provider))
+ return PTR_ERR(phy_provider);
+
return 0;
}
diff --git a/drivers/phy/phy-mvebu-sata.c b/drivers/phy/phy-mvebu-sata.c
index d43786f..d70ecd6 100644
--- a/drivers/phy/phy-mvebu-sata.c
+++ b/drivers/phy/phy-mvebu-sata.c
@@ -99,17 +99,17 @@
if (IS_ERR(priv->clk))
return PTR_ERR(priv->clk);
- phy_provider = devm_of_phy_provider_register(&pdev->dev,
- of_phy_simple_xlate);
- if (IS_ERR(phy_provider))
- return PTR_ERR(phy_provider);
-
phy = devm_phy_create(&pdev->dev, &phy_mvebu_sata_ops, NULL);
if (IS_ERR(phy))
return PTR_ERR(phy);
phy_set_drvdata(phy, priv);
+ phy_provider = devm_of_phy_provider_register(&pdev->dev,
+ of_phy_simple_xlate);
+ if (IS_ERR(phy_provider))
+ return PTR_ERR(phy_provider);
+
/* The boot loader may of left it on. Turn it off. */
phy_mvebu_sata_power_off(phy);
diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c
index bfc5c33..7699752 100644
--- a/drivers/phy/phy-omap-usb2.c
+++ b/drivers/phy/phy-omap-usb2.c
@@ -177,11 +177,6 @@
phy->phy.otg = otg;
phy->phy.type = USB_PHY_TYPE_USB2;
- phy_provider = devm_of_phy_provider_register(phy->dev,
- of_phy_simple_xlate);
- if (IS_ERR(phy_provider))
- return PTR_ERR(phy_provider);
-
control_node = of_parse_phandle(node, "ctrl-module", 0);
if (!control_node) {
dev_err(&pdev->dev, "Failed to get control device phandle\n");
@@ -214,6 +209,11 @@
phy_set_drvdata(generic_phy, phy);
+ phy_provider = devm_of_phy_provider_register(phy->dev,
+ of_phy_simple_xlate);
+ if (IS_ERR(phy_provider))
+ return PTR_ERR(phy_provider);
+
phy->wkupclk = devm_clk_get(phy->dev, "usb_phy_cm_clk32k");
if (IS_ERR(phy->wkupclk)) {
dev_err(&pdev->dev, "unable to get usb_phy_cm_clk32k\n");
diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c
index daf65e6..c3ace1d 100644
--- a/drivers/phy/phy-twl4030-usb.c
+++ b/drivers/phy/phy-twl4030-usb.c
@@ -695,11 +695,6 @@
otg->set_host = twl4030_set_host;
otg->set_peripheral = twl4030_set_peripheral;
- phy_provider = devm_of_phy_provider_register(twl->dev,
- of_phy_simple_xlate);
- if (IS_ERR(phy_provider))
- return PTR_ERR(phy_provider);
-
phy = devm_phy_create(twl->dev, &ops, init_data);
if (IS_ERR(phy)) {
dev_dbg(&pdev->dev, "Failed to create PHY\n");
@@ -708,6 +703,11 @@
phy_set_drvdata(phy, twl);
+ phy_provider = devm_of_phy_provider_register(twl->dev,
+ of_phy_simple_xlate);
+ if (IS_ERR(phy_provider))
+ return PTR_ERR(phy_provider);
+
/* init spinlock for workqueue */
spin_lock_init(&twl->lock);
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index be361b7..1e4e693 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -217,7 +217,7 @@
select PINCTRL_MXS
config PINCTRL_MSM
- tristate
+ bool
select PINMUX
select PINCONF
select GENERIC_PINCONF
diff --git a/drivers/pinctrl/pinctrl-capri.c b/drivers/pinctrl/pinctrl-capri.c
index 4669c53..eb25002 100644
--- a/drivers/pinctrl/pinctrl-capri.c
+++ b/drivers/pinctrl/pinctrl-capri.c
@@ -1435,7 +1435,7 @@
}
static struct of_device_id capri_pinctrl_of_match[] = {
- { .compatible = "brcm,capri-pinctrl", },
+ { .compatible = "brcm,bcm11351-pinctrl", },
{ },
};
diff --git a/drivers/pinctrl/pinctrl-sunxi.c b/drivers/pinctrl/pinctrl-sunxi.c
index 9ccf681..f9fabe9 100644
--- a/drivers/pinctrl/pinctrl-sunxi.c
+++ b/drivers/pinctrl/pinctrl-sunxi.c
@@ -14,6 +14,7 @@
#include <linux/clk.h>
#include <linux/gpio.h>
#include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_address.h>
@@ -584,7 +585,7 @@
spin_lock_irqsave(&pctl->lock, flags);
regval = readl(pctl->membase + reg);
- regval &= ~IRQ_CFG_IRQ_MASK;
+ regval &= ~(IRQ_CFG_IRQ_MASK << index);
writel(regval | (mode << index), pctl->membase + reg);
spin_unlock_irqrestore(&pctl->lock, flags);
@@ -665,6 +666,7 @@
static void sunxi_pinctrl_irq_handler(unsigned irq, struct irq_desc *desc)
{
+ struct irq_chip *chip = irq_get_chip(irq);
struct sunxi_pinctrl *pctl = irq_get_handler_data(irq);
const unsigned long reg = readl(pctl->membase + IRQ_STATUS_REG);
@@ -674,10 +676,12 @@
if (reg) {
int irqoffset;
+ chained_irq_enter(chip, desc);
for_each_set_bit(irqoffset, ®, SUNXI_IRQ_NUMBER) {
int pin_irq = irq_find_mapping(pctl->domain, irqoffset);
generic_handle_irq(pin_irq);
}
+ chained_irq_exit(chip, desc);
}
}
diff --git a/drivers/pinctrl/pinctrl-sunxi.h b/drivers/pinctrl/pinctrl-sunxi.h
index 01c494f..552b0e9 100644
--- a/drivers/pinctrl/pinctrl-sunxi.h
+++ b/drivers/pinctrl/pinctrl-sunxi.h
@@ -511,7 +511,7 @@
static inline u32 sunxi_irq_cfg_reg(u16 irq)
{
- u8 reg = irq / IRQ_CFG_IRQ_PER_REG;
+ u8 reg = irq / IRQ_CFG_IRQ_PER_REG * 0x04;
return reg + IRQ_CFG_REG;
}
@@ -523,7 +523,7 @@
static inline u32 sunxi_irq_ctrl_reg(u16 irq)
{
- u8 reg = irq / IRQ_CTRL_IRQ_PER_REG;
+ u8 reg = irq / IRQ_CTRL_IRQ_PER_REG * 0x04;
return reg + IRQ_CTRL_REG;
}
@@ -535,7 +535,7 @@
static inline u32 sunxi_irq_status_reg(u16 irq)
{
- u8 reg = irq / IRQ_STATUS_IRQ_PER_REG;
+ u8 reg = irq / IRQ_STATUS_IRQ_PER_REG * 0x04;
return reg + IRQ_STATUS_REG;
}
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
index 77d103f..567d691 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
@@ -89,7 +89,8 @@
/* GPSR6 */
FN_IP13_10, FN_IP13_11, FN_IP13_12, FN_IP13_13, FN_IP13_14,
- FN_IP13_15, FN_IP13_18_16, FN_IP13_21_19, FN_IP13_22, FN_IP13_24_23,
+ FN_IP13_15, FN_IP13_18_16, FN_IP13_21_19,
+ FN_IP13_22, FN_IP13_24_23, FN_SD1_CLK,
FN_IP13_25, FN_IP13_26, FN_IP13_27, FN_IP13_30_28, FN_IP14_1_0,
FN_IP14_2, FN_IP14_3, FN_IP14_4, FN_IP14_5, FN_IP14_6, FN_IP14_7,
FN_IP14_10_8, FN_IP14_13_11, FN_IP14_16_14, FN_IP14_19_17,
@@ -788,6 +789,7 @@
PINMUX_DATA(USB1_PWEN_MARK, FN_USB1_PWEN),
PINMUX_DATA(USB1_OVC_MARK, FN_USB1_OVC),
PINMUX_DATA(DU0_DOTCLKIN_MARK, FN_DU0_DOTCLKIN),
+ PINMUX_DATA(SD1_CLK_MARK, FN_SD1_CLK),
/* IPSR0 */
PINMUX_IPSR_DATA(IP0_0, D0),
@@ -3825,7 +3827,7 @@
GP_6_11_FN, FN_IP13_25,
GP_6_10_FN, FN_IP13_24_23,
GP_6_9_FN, FN_IP13_22,
- 0, 0,
+ GP_6_8_FN, FN_SD1_CLK,
GP_6_7_FN, FN_IP13_21_19,
GP_6_6_FN, FN_IP13_18_16,
GP_6_5_FN, FN_IP13_15,
diff --git a/drivers/pinctrl/sirf/pinctrl-sirf.c b/drivers/pinctrl/sirf/pinctrl-sirf.c
index a0d6152..617a491 100644
--- a/drivers/pinctrl/sirf/pinctrl-sirf.c
+++ b/drivers/pinctrl/sirf/pinctrl-sirf.c
@@ -598,7 +598,7 @@
{
struct sirfsoc_gpio_bank *bank = irq_data_get_irq_chip_data(d);
- if (gpio_lock_as_irq(&bank->chip.gc, d->hwirq))
+ if (gpio_lock_as_irq(&bank->chip.gc, d->hwirq % SIRFSOC_GPIO_BANK_SIZE))
dev_err(bank->chip.gc.dev,
"unable to lock HW IRQ %lu for IRQ\n",
d->hwirq);
@@ -611,7 +611,7 @@
struct sirfsoc_gpio_bank *bank = irq_data_get_irq_chip_data(d);
sirfsoc_gpio_irq_mask(d);
- gpio_unlock_as_irq(&bank->chip.gc, d->hwirq);
+ gpio_unlock_as_irq(&bank->chip.gc, d->hwirq % SIRFSOC_GPIO_BANK_SIZE);
}
static struct irq_chip sirfsoc_irq_chip = {
diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index 167f3d0..66977eb 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -183,9 +183,7 @@
struct resource r = {0};
int i, flags;
- if (acpi_dev_resource_memory(res, &r)
- || acpi_dev_resource_io(res, &r)
- || acpi_dev_resource_address_space(res, &r)
+ if (acpi_dev_resource_address_space(res, &r)
|| acpi_dev_resource_ext_address_space(res, &r)) {
pnp_add_resource(dev, &r);
return AE_OK;
@@ -217,6 +215,17 @@
}
switch (res->type) {
+ case ACPI_RESOURCE_TYPE_MEMORY24:
+ case ACPI_RESOURCE_TYPE_MEMORY32:
+ case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
+ if (acpi_dev_resource_memory(res, &r))
+ pnp_add_resource(dev, &r);
+ break;
+ case ACPI_RESOURCE_TYPE_IO:
+ case ACPI_RESOURCE_TYPE_FIXED_IO:
+ if (acpi_dev_resource_io(res, &r))
+ pnp_add_resource(dev, &r);
+ break;
case ACPI_RESOURCE_TYPE_DMA:
dma = &res->data.dma;
if (dma->channel_count > 0 && dma->channels[0] != (u8) -1)
diff --git a/drivers/power/ds2782_battery.c b/drivers/power/ds2782_battery.c
index 5631748..041f9b6 100644
--- a/drivers/power/ds2782_battery.c
+++ b/drivers/power/ds2782_battery.c
@@ -192,7 +192,7 @@
/*
* Voltage is measured in units of 1.22mV. The voltage is stored as
- * a 10-bit number plus sign, in the upper bits of a 16-bit register
+ * a 12-bit number plus sign, in the upper bits of a 16-bit register
*/
err = ds278x_read_reg16(info, DS278x_REG_VOLT_MSB, &raw);
if (err)
diff --git a/drivers/power/isp1704_charger.c b/drivers/power/isp1704_charger.c
index 80edb7d..0b4cf9d 100644
--- a/drivers/power/isp1704_charger.c
+++ b/drivers/power/isp1704_charger.c
@@ -444,8 +444,6 @@
ret = PTR_ERR(isp->phy);
goto fail0;
}
- if (!isp->phy)
- goto fail0;
isp->dev = &pdev->dev;
platform_set_drvdata(pdev, isp);
diff --git a/drivers/power/max17040_battery.c b/drivers/power/max17040_battery.c
index c7ff6d6..0fbac86 100644
--- a/drivers/power/max17040_battery.c
+++ b/drivers/power/max17040_battery.c
@@ -148,7 +148,7 @@
{
struct max17040_chip *chip = i2c_get_clientdata(client);
- if (chip->pdata->battery_online)
+ if (chip->pdata && chip->pdata->battery_online)
chip->online = chip->pdata->battery_online();
else
chip->online = 1;
@@ -158,7 +158,8 @@
{
struct max17040_chip *chip = i2c_get_clientdata(client);
- if (!chip->pdata->charger_online || !chip->pdata->charger_enable) {
+ if (!chip->pdata || !chip->pdata->charger_online
+ || !chip->pdata->charger_enable) {
chip->status = POWER_SUPPLY_STATUS_UNKNOWN;
return;
}
diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 34a0c60..419056d 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -25,6 +25,96 @@
#include "ptp_private.h"
+static int ptp_disable_pinfunc(struct ptp_clock_info *ops,
+ enum ptp_pin_function func, unsigned int chan)
+{
+ struct ptp_clock_request rq;
+ int err = 0;
+
+ memset(&rq, 0, sizeof(rq));
+
+ switch (func) {
+ case PTP_PF_NONE:
+ break;
+ case PTP_PF_EXTTS:
+ rq.type = PTP_CLK_REQ_EXTTS;
+ rq.extts.index = chan;
+ err = ops->enable(ops, &rq, 0);
+ break;
+ case PTP_PF_PEROUT:
+ rq.type = PTP_CLK_REQ_PEROUT;
+ rq.perout.index = chan;
+ err = ops->enable(ops, &rq, 0);
+ break;
+ case PTP_PF_PHYSYNC:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return err;
+}
+
+int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin,
+ enum ptp_pin_function func, unsigned int chan)
+{
+ struct ptp_clock_info *info = ptp->info;
+ struct ptp_pin_desc *pin1 = NULL, *pin2 = &info->pin_config[pin];
+ unsigned int i;
+
+ /* Check to see if any other pin previously had this function. */
+ for (i = 0; i < info->n_pins; i++) {
+ if (info->pin_config[i].func == func &&
+ info->pin_config[i].chan == chan) {
+ pin1 = &info->pin_config[i];
+ break;
+ }
+ }
+ if (pin1 && i == pin)
+ return 0;
+
+ /* Check the desired function and channel. */
+ switch (func) {
+ case PTP_PF_NONE:
+ break;
+ case PTP_PF_EXTTS:
+ if (chan >= info->n_ext_ts)
+ return -EINVAL;
+ break;
+ case PTP_PF_PEROUT:
+ if (chan >= info->n_per_out)
+ return -EINVAL;
+ break;
+ case PTP_PF_PHYSYNC:
+ pr_err("sorry, cannot reassign the calibration pin\n");
+ return -EINVAL;
+ default:
+ return -EINVAL;
+ }
+
+ if (pin2->func == PTP_PF_PHYSYNC) {
+ pr_err("sorry, cannot reprogram the calibration pin\n");
+ return -EINVAL;
+ }
+
+ if (info->verify(info, pin, func, chan)) {
+ pr_err("driver cannot use function %u on pin %u\n", func, chan);
+ return -EOPNOTSUPP;
+ }
+
+ /* Disable whatever function was previously assigned. */
+ if (pin1) {
+ ptp_disable_pinfunc(info, func, chan);
+ pin1->func = PTP_PF_NONE;
+ pin1->chan = 0;
+ }
+ ptp_disable_pinfunc(info, pin2->func, pin2->chan);
+ pin2->func = func;
+ pin2->chan = chan;
+
+ return 0;
+}
+
int ptp_open(struct posix_clock *pc, fmode_t fmode)
{
return 0;
@@ -35,12 +125,13 @@
struct ptp_clock_caps caps;
struct ptp_clock_request req;
struct ptp_sys_offset *sysoff = NULL;
+ struct ptp_pin_desc pd;
struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
struct ptp_clock_info *ops = ptp->info;
struct ptp_clock_time *pct;
struct timespec ts;
int enable, err = 0;
- unsigned int i;
+ unsigned int i, pin_index;
switch (cmd) {
@@ -51,6 +142,7 @@
caps.n_ext_ts = ptp->info->n_ext_ts;
caps.n_per_out = ptp->info->n_per_out;
caps.pps = ptp->info->pps;
+ caps.n_pins = ptp->info->n_pins;
if (copy_to_user((void __user *)arg, &caps, sizeof(caps)))
err = -EFAULT;
break;
@@ -126,6 +218,40 @@
err = -EFAULT;
break;
+ case PTP_PIN_GETFUNC:
+ if (copy_from_user(&pd, (void __user *)arg, sizeof(pd))) {
+ err = -EFAULT;
+ break;
+ }
+ pin_index = pd.index;
+ if (pin_index >= ops->n_pins) {
+ err = -EINVAL;
+ break;
+ }
+ if (mutex_lock_interruptible(&ptp->pincfg_mux))
+ return -ERESTARTSYS;
+ pd = ops->pin_config[pin_index];
+ mutex_unlock(&ptp->pincfg_mux);
+ if (!err && copy_to_user((void __user *)arg, &pd, sizeof(pd)))
+ err = -EFAULT;
+ break;
+
+ case PTP_PIN_SETFUNC:
+ if (copy_from_user(&pd, (void __user *)arg, sizeof(pd))) {
+ err = -EFAULT;
+ break;
+ }
+ pin_index = pd.index;
+ if (pin_index >= ops->n_pins) {
+ err = -EINVAL;
+ break;
+ }
+ if (mutex_lock_interruptible(&ptp->pincfg_mux))
+ return -ERESTARTSYS;
+ err = ptp_set_pinfunc(ptp, pin_index, pd.func, pd.chan);
+ mutex_unlock(&ptp->pincfg_mux);
+ break;
+
default:
err = -ENOTTY;
break;
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index a8319b2..e25d2bc 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -169,6 +169,7 @@
struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
mutex_destroy(&ptp->tsevq_mux);
+ mutex_destroy(&ptp->pincfg_mux);
ida_simple_remove(&ptp_clocks_map, ptp->index);
kfree(ptp);
}
@@ -203,6 +204,7 @@
ptp->index = index;
spin_lock_init(&ptp->tsevq.lock);
mutex_init(&ptp->tsevq_mux);
+ mutex_init(&ptp->pincfg_mux);
init_waitqueue_head(&ptp->tsev_wq);
/* Create a new device in our class. */
@@ -249,6 +251,7 @@
device_destroy(ptp_class, ptp->devid);
no_device:
mutex_destroy(&ptp->tsevq_mux);
+ mutex_destroy(&ptp->pincfg_mux);
no_slot:
kfree(ptp);
no_memory:
@@ -305,6 +308,26 @@
}
EXPORT_SYMBOL(ptp_clock_index);
+int ptp_find_pin(struct ptp_clock *ptp,
+ enum ptp_pin_function func, unsigned int chan)
+{
+ struct ptp_pin_desc *pin = NULL;
+ int i;
+
+ mutex_lock(&ptp->pincfg_mux);
+ for (i = 0; i < ptp->info->n_pins; i++) {
+ if (ptp->info->pin_config[i].func == func &&
+ ptp->info->pin_config[i].chan == chan) {
+ pin = &ptp->info->pin_config[i];
+ break;
+ }
+ }
+ mutex_unlock(&ptp->pincfg_mux);
+
+ return pin ? i : -1;
+}
+EXPORT_SYMBOL(ptp_find_pin);
+
/* module operations */
static void __exit ptp_exit(void)
diff --git a/drivers/ptp/ptp_ixp46x.c b/drivers/ptp/ptp_ixp46x.c
index 4a08727..604d340 100644
--- a/drivers/ptp/ptp_ixp46x.c
+++ b/drivers/ptp/ptp_ixp46x.c
@@ -244,6 +244,7 @@
.name = "IXP46X timer",
.max_adj = 66666655,
.n_ext_ts = N_EXT_TS,
+ .n_pins = 0,
.pps = 0,
.adjfreq = ptp_ixp_adjfreq,
.adjtime = ptp_ixp_adjtime,
diff --git a/drivers/ptp/ptp_pch.c b/drivers/ptp/ptp_pch.c
index 71a2559..90a1063 100644
--- a/drivers/ptp/ptp_pch.c
+++ b/drivers/ptp/ptp_pch.c
@@ -514,6 +514,7 @@
.name = "PCH timer",
.max_adj = 50000000,
.n_ext_ts = N_EXT_TS,
+ .n_pins = 0,
.pps = 0,
.adjfreq = ptp_pch_adjfreq,
.adjtime = ptp_pch_adjtime,
diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
index df03f2e..9c5d414 100644
--- a/drivers/ptp/ptp_private.h
+++ b/drivers/ptp/ptp_private.h
@@ -48,8 +48,12 @@
long dialed_frequency; /* remembers the frequency adjustment */
struct timestamp_event_queue tsevq; /* simple fifo for time stamps */
struct mutex tsevq_mux; /* one process at a time reading the fifo */
+ struct mutex pincfg_mux; /* protect concurrent info->pin_config access */
wait_queue_head_t tsev_wq;
int defunct; /* tells readers to go away when clock is being removed */
+ struct device_attribute *pin_dev_attr;
+ struct attribute **pin_attr;
+ struct attribute_group pin_attr_group;
};
/*
@@ -69,6 +73,10 @@
* see ptp_chardev.c
*/
+/* caller must hold pincfg_mux */
+int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin,
+ enum ptp_pin_function func, unsigned int chan);
+
long ptp_ioctl(struct posix_clock *pc,
unsigned int cmd, unsigned long arg);
diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c
index 13ec531..302e626 100644
--- a/drivers/ptp/ptp_sysfs.c
+++ b/drivers/ptp/ptp_sysfs.c
@@ -18,6 +18,7 @@
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/capability.h>
+#include <linux/slab.h>
#include "ptp_private.h"
@@ -42,6 +43,7 @@
PTP_SHOW_INT(n_alarms, n_alarm);
PTP_SHOW_INT(n_external_timestamps, n_ext_ts);
PTP_SHOW_INT(n_periodic_outputs, n_per_out);
+PTP_SHOW_INT(n_programmable_pins, n_pins);
PTP_SHOW_INT(pps_available, pps);
static struct attribute *ptp_attrs[] = {
@@ -50,6 +52,7 @@
&dev_attr_n_alarms.attr,
&dev_attr_n_external_timestamps.attr,
&dev_attr_n_periodic_outputs.attr,
+ &dev_attr_n_programmable_pins.attr,
&dev_attr_pps_available.attr,
NULL,
};
@@ -175,6 +178,63 @@
return err;
}
+static int ptp_pin_name2index(struct ptp_clock *ptp, const char *name)
+{
+ int i;
+ for (i = 0; i < ptp->info->n_pins; i++) {
+ if (!strcmp(ptp->info->pin_config[i].name, name))
+ return i;
+ }
+ return -1;
+}
+
+static ssize_t ptp_pin_show(struct device *dev, struct device_attribute *attr,
+ char *page)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+ unsigned int func, chan;
+ int index;
+
+ index = ptp_pin_name2index(ptp, attr->attr.name);
+ if (index < 0)
+ return -EINVAL;
+
+ if (mutex_lock_interruptible(&ptp->pincfg_mux))
+ return -ERESTARTSYS;
+
+ func = ptp->info->pin_config[index].func;
+ chan = ptp->info->pin_config[index].chan;
+
+ mutex_unlock(&ptp->pincfg_mux);
+
+ return snprintf(page, PAGE_SIZE, "%u %u\n", func, chan);
+}
+
+static ssize_t ptp_pin_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+ unsigned int func, chan;
+ int cnt, err, index;
+
+ cnt = sscanf(buf, "%u %u", &func, &chan);
+ if (cnt != 2)
+ return -EINVAL;
+
+ index = ptp_pin_name2index(ptp, attr->attr.name);
+ if (index < 0)
+ return -EINVAL;
+
+ if (mutex_lock_interruptible(&ptp->pincfg_mux))
+ return -ERESTARTSYS;
+ err = ptp_set_pinfunc(ptp, index, func, chan);
+ mutex_unlock(&ptp->pincfg_mux);
+ if (err)
+ return err;
+
+ return count;
+}
+
static DEVICE_ATTR(extts_enable, 0220, NULL, extts_enable_store);
static DEVICE_ATTR(fifo, 0444, extts_fifo_show, NULL);
static DEVICE_ATTR(period, 0220, NULL, period_store);
@@ -195,9 +255,56 @@
if (info->pps)
device_remove_file(dev, &dev_attr_pps_enable);
+ if (info->n_pins) {
+ sysfs_remove_group(&dev->kobj, &ptp->pin_attr_group);
+ kfree(ptp->pin_attr);
+ kfree(ptp->pin_dev_attr);
+ }
return 0;
}
+static int ptp_populate_pins(struct ptp_clock *ptp)
+{
+ struct device *dev = ptp->dev;
+ struct ptp_clock_info *info = ptp->info;
+ int err = -ENOMEM, i, n_pins = info->n_pins;
+
+ ptp->pin_dev_attr = kzalloc(n_pins * sizeof(*ptp->pin_dev_attr),
+ GFP_KERNEL);
+ if (!ptp->pin_dev_attr)
+ goto no_dev_attr;
+
+ ptp->pin_attr = kzalloc((1 + n_pins) * sizeof(struct attribute *),
+ GFP_KERNEL);
+ if (!ptp->pin_attr)
+ goto no_pin_attr;
+
+ for (i = 0; i < n_pins; i++) {
+ struct device_attribute *da = &ptp->pin_dev_attr[i];
+ sysfs_attr_init(&da->attr);
+ da->attr.name = info->pin_config[i].name;
+ da->attr.mode = 0644;
+ da->show = ptp_pin_show;
+ da->store = ptp_pin_store;
+ ptp->pin_attr[i] = &da->attr;
+ }
+
+ ptp->pin_attr_group.name = "pins";
+ ptp->pin_attr_group.attrs = ptp->pin_attr;
+
+ err = sysfs_create_group(&dev->kobj, &ptp->pin_attr_group);
+ if (err)
+ goto no_group;
+ return 0;
+
+no_group:
+ kfree(ptp->pin_attr);
+no_pin_attr:
+ kfree(ptp->pin_dev_attr);
+no_dev_attr:
+ return err;
+}
+
int ptp_populate_sysfs(struct ptp_clock *ptp)
{
struct device *dev = ptp->dev;
@@ -222,7 +329,15 @@
if (err)
goto out4;
}
+ if (info->n_pins) {
+ err = ptp_populate_pins(ptp);
+ if (err)
+ goto out5;
+ }
return 0;
+out5:
+ if (info->pps)
+ device_remove_file(dev, &dev_attr_pps_enable);
out4:
if (info->n_per_out)
device_remove_file(dev, &dev_attr_period);
diff --git a/drivers/pwm/pwm-lp3943.c b/drivers/pwm/pwm-lp3943.c
index 8a843a0..a40b9c3 100644
--- a/drivers/pwm/pwm-lp3943.c
+++ b/drivers/pwm/pwm-lp3943.c
@@ -52,8 +52,10 @@
offset = pwm_map->output[i];
/* Return an error if the pin is already assigned */
- if (test_and_set_bit(offset, &lp3943->pin_used))
+ if (test_and_set_bit(offset, &lp3943->pin_used)) {
+ kfree(pwm_map);
return ERR_PTR(-EBUSY);
+ }
}
return pwm_map;
diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h
index b4b0d83..7061ac0 100644
--- a/drivers/rapidio/devices/tsi721.h
+++ b/drivers/rapidio/devices/tsi721.h
@@ -678,6 +678,7 @@
struct list_head free_list;
dma_cookie_t completed_cookie;
struct tasklet_struct tasklet;
+ bool active;
};
#endif /* CONFIG_RAPIDIO_DMA_ENGINE */
diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c
index 502663f..91245f5 100644
--- a/drivers/rapidio/devices/tsi721_dma.c
+++ b/drivers/rapidio/devices/tsi721_dma.c
@@ -206,8 +206,8 @@
{
/* Disable BDMA channel interrupts */
iowrite32(0, bdma_chan->regs + TSI721_DMAC_INTE);
-
- tasklet_schedule(&bdma_chan->tasklet);
+ if (bdma_chan->active)
+ tasklet_schedule(&bdma_chan->tasklet);
}
#ifdef CONFIG_PCI_MSI
@@ -562,7 +562,7 @@
}
#endif /* CONFIG_PCI_MSI */
- tasklet_enable(&bdma_chan->tasklet);
+ bdma_chan->active = true;
tsi721_bdma_interrupt_enable(bdma_chan, 1);
return bdma_chan->bd_num - 1;
@@ -576,9 +576,7 @@
static void tsi721_free_chan_resources(struct dma_chan *dchan)
{
struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
-#ifdef CONFIG_PCI_MSI
struct tsi721_device *priv = to_tsi721(dchan->device);
-#endif
LIST_HEAD(list);
dev_dbg(dchan->device->dev, "%s: Entry\n", __func__);
@@ -589,14 +587,25 @@
BUG_ON(!list_empty(&bdma_chan->active_list));
BUG_ON(!list_empty(&bdma_chan->queue));
- tasklet_disable(&bdma_chan->tasklet);
+ tsi721_bdma_interrupt_enable(bdma_chan, 0);
+ bdma_chan->active = false;
+
+#ifdef CONFIG_PCI_MSI
+ if (priv->flags & TSI721_USING_MSIX) {
+ synchronize_irq(priv->msix[TSI721_VECT_DMA0_DONE +
+ bdma_chan->id].vector);
+ synchronize_irq(priv->msix[TSI721_VECT_DMA0_INT +
+ bdma_chan->id].vector);
+ } else
+#endif
+ synchronize_irq(priv->pdev->irq);
+
+ tasklet_kill(&bdma_chan->tasklet);
spin_lock_bh(&bdma_chan->lock);
list_splice_init(&bdma_chan->free_list, &list);
spin_unlock_bh(&bdma_chan->lock);
- tsi721_bdma_interrupt_enable(bdma_chan, 0);
-
#ifdef CONFIG_PCI_MSI
if (priv->flags & TSI721_USING_MSIX) {
free_irq(priv->msix[TSI721_VECT_DMA0_DONE +
@@ -790,6 +799,7 @@
bdma_chan->dchan.cookie = 1;
bdma_chan->dchan.chan_id = i;
bdma_chan->id = i;
+ bdma_chan->active = false;
spin_lock_init(&bdma_chan->lock);
@@ -799,7 +809,6 @@
tasklet_init(&bdma_chan->tasklet, tsi721_dma_tasklet,
(unsigned long)bdma_chan);
- tasklet_disable(&bdma_chan->tasklet);
list_add_tail(&bdma_chan->dchan.device_node,
&mport->dma.channels);
}
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 16a309e..afca1bc 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -953,6 +953,8 @@
return 0;
}
+static int _regulator_do_enable(struct regulator_dev *rdev);
+
/**
* set_machine_constraints - sets regulator constraints
* @rdev: regulator source
@@ -1013,10 +1015,9 @@
/* If the constraints say the regulator should be on at this point
* and we have control then make sure it is enabled.
*/
- if ((rdev->constraints->always_on || rdev->constraints->boot_on) &&
- ops->enable) {
- ret = ops->enable(rdev);
- if (ret < 0) {
+ if (rdev->constraints->always_on || rdev->constraints->boot_on) {
+ ret = _regulator_do_enable(rdev);
+ if (ret < 0 && ret != -EINVAL) {
rdev_err(rdev, "failed to enable\n");
goto out;
}
@@ -1359,7 +1360,7 @@
goto found;
/* Don't log an error when called from regulator_get_optional() */
} else if (!have_full_constraints() || exclusive) {
- dev_err(dev, "dummy supplies not allowed\n");
+ dev_warn(dev, "dummy supplies not allowed\n");
}
mutex_unlock(®ulator_list_mutex);
@@ -1907,8 +1908,6 @@
trace_regulator_disable_complete(rdev_get_name(rdev));
- _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
- NULL);
return 0;
}
@@ -1932,6 +1931,8 @@
rdev_err(rdev, "failed to disable\n");
return ret;
}
+ _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
+ NULL);
}
rdev->use_count = 0;
@@ -1984,20 +1985,16 @@
{
int ret = 0;
- /* force disable */
- if (rdev->desc->ops->disable) {
- /* ah well, who wants to live forever... */
- ret = rdev->desc->ops->disable(rdev);
- if (ret < 0) {
- rdev_err(rdev, "failed to force disable\n");
- return ret;
- }
- /* notify other consumers that power has been forced off */
- _notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE |
- REGULATOR_EVENT_DISABLE, NULL);
+ ret = _regulator_do_disable(rdev);
+ if (ret < 0) {
+ rdev_err(rdev, "failed to force disable\n");
+ return ret;
}
- return ret;
+ _notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE |
+ REGULATOR_EVENT_DISABLE, NULL);
+
+ return 0;
}
/**
@@ -3630,23 +3627,18 @@
mutex_lock(®ulator_list_mutex);
list_for_each_entry(rdev, ®ulator_list, list) {
- struct regulator_ops *ops = rdev->desc->ops;
-
mutex_lock(&rdev->mutex);
- if ((rdev->use_count > 0 || rdev->constraints->always_on) &&
- ops->enable) {
- error = ops->enable(rdev);
+ if (rdev->use_count > 0 || rdev->constraints->always_on) {
+ error = _regulator_do_enable(rdev);
if (error)
ret = error;
} else {
if (!have_full_constraints())
goto unlock;
- if (!ops->disable)
- goto unlock;
if (!_regulator_is_enabled(rdev))
goto unlock;
- error = ops->disable(rdev);
+ error = _regulator_do_disable(rdev);
if (error)
ret = error;
}
@@ -3820,7 +3812,7 @@
ops = rdev->desc->ops;
c = rdev->constraints;
- if (!ops->disable || (c && c->always_on))
+ if (c && c->always_on)
continue;
mutex_lock(&rdev->mutex);
@@ -3841,7 +3833,7 @@
/* We log since this may kill the system if it
* goes wrong. */
rdev_info(rdev, "disabling\n");
- ret = ops->disable(rdev);
+ ret = _regulator_do_disable(rdev);
if (ret != 0)
rdev_err(rdev, "couldn't disable: %d\n", ret);
} else {
diff --git a/drivers/regulator/da9055-regulator.c b/drivers/regulator/da9055-regulator.c
index 7f34020..b14ebda 100644
--- a/drivers/regulator/da9055-regulator.c
+++ b/drivers/regulator/da9055-regulator.c
@@ -576,7 +576,9 @@
/* Only LDO 5 and 6 has got the over current interrupt */
if (pdev->id == DA9055_ID_LDO5 || pdev->id == DA9055_ID_LDO6) {
irq = platform_get_irq_byname(pdev, "REGULATOR");
- irq = regmap_irq_get_virq(da9055->irq_data, irq);
+ if (irq < 0)
+ return irq;
+
ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
da9055_ldo5_6_oc_irq,
IRQF_TRIGGER_HIGH |
diff --git a/drivers/regulator/da9063-regulator.c b/drivers/regulator/da9063-regulator.c
index 56727eb..91e99a2 100644
--- a/drivers/regulator/da9063-regulator.c
+++ b/drivers/regulator/da9063-regulator.c
@@ -1,3 +1,4 @@
+
/*
* Regulator driver for DA9063 PMIC series
*
@@ -60,7 +61,8 @@
.desc.ops = &da9063_ldo_ops, \
.desc.min_uV = (min_mV) * 1000, \
.desc.uV_step = (step_mV) * 1000, \
- .desc.n_voltages = (((max_mV) - (min_mV))/(step_mV) + 1), \
+ .desc.n_voltages = (((max_mV) - (min_mV))/(step_mV) + 1 \
+ + (DA9063_V##regl_name##_BIAS)), \
.desc.enable_reg = DA9063_REG_##regl_name##_CONT, \
.desc.enable_mask = DA9063_LDO_EN, \
.desc.vsel_reg = DA9063_REG_V##regl_name##_A, \
diff --git a/drivers/regulator/max14577.c b/drivers/regulator/max14577.c
index b1078ba3..e061952 100644
--- a/drivers/regulator/max14577.c
+++ b/drivers/regulator/max14577.c
@@ -166,12 +166,14 @@
ret = of_regulator_match(&pdev->dev, np, max14577_regulator_matches,
MAX14577_REG_MAX);
- if (ret < 0) {
+ if (ret < 0)
dev_err(&pdev->dev, "Error parsing regulator init data: %d\n", ret);
- return ret;
- }
+ else
+ ret = 0;
- return 0;
+ of_node_put(np);
+
+ return ret;
}
static inline struct regulator_init_data *match_init_data(int index)
diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c
index d7164bb..d958dfa 100644
--- a/drivers/regulator/s5m8767.c
+++ b/drivers/regulator/s5m8767.c
@@ -535,7 +535,7 @@
return -ENODEV;
}
- regulators_np = of_find_node_by_name(pmic_np, "regulators");
+ regulators_np = of_get_child_by_name(pmic_np, "regulators");
if (!regulators_np) {
dev_err(iodev->dev, "could not find regulators sub-node\n");
return -EINVAL;
@@ -591,6 +591,8 @@
rmode++;
}
+ of_node_put(regulators_np);
+
if (of_get_property(pmic_np, "s5m8767,pmic-buck2-uses-gpio-dvs", NULL)) {
pdata->buck2_gpiodvs = true;
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index 7afd373..c4cde9c 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -580,10 +580,12 @@
clk_enable(rtc_clk);
/* save TICNT for anyone using periodic interrupts */
- ticnt_save = readb(s3c_rtc_base + S3C2410_TICNT);
if (s3c_rtc_cpu_type == TYPE_S3C64XX) {
ticnt_en_save = readw(s3c_rtc_base + S3C2410_RTCCON);
ticnt_en_save &= S3C64XX_RTCCON_TICEN;
+ ticnt_save = readl(s3c_rtc_base + S3C2410_TICNT);
+ } else {
+ ticnt_save = readb(s3c_rtc_base + S3C2410_TICNT);
}
s3c_rtc_enable(pdev, 0);
@@ -605,10 +607,15 @@
clk_enable(rtc_clk);
s3c_rtc_enable(pdev, 1);
- writeb(ticnt_save, s3c_rtc_base + S3C2410_TICNT);
- if (s3c_rtc_cpu_type == TYPE_S3C64XX && ticnt_en_save) {
- tmp = readw(s3c_rtc_base + S3C2410_RTCCON);
- writew(tmp | ticnt_en_save, s3c_rtc_base + S3C2410_RTCCON);
+ if (s3c_rtc_cpu_type == TYPE_S3C64XX) {
+ writel(ticnt_save, s3c_rtc_base + S3C2410_TICNT);
+ if (ticnt_en_save) {
+ tmp = readw(s3c_rtc_base + S3C2410_RTCCON);
+ writew(tmp | ticnt_en_save,
+ s3c_rtc_base + S3C2410_RTCCON);
+ }
+ } else {
+ writeb(ticnt_save, s3c_rtc_base + S3C2410_TICNT);
}
if (device_may_wakeup(dev) && wake_en) {
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index f6b9188..9f0ea6c 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -610,6 +610,7 @@
css_wait_for_slow_path();
for_each_subchannel_staged(__s390_process_res_acc, NULL,
&link);
+ css_schedule_reprobe();
}
}
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 88e35d8..8ee88c4 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -342,8 +342,9 @@
*/
int cio_commit_config(struct subchannel *sch)
{
- struct schib schib;
int ccode, retry, ret = 0;
+ struct schib schib;
+ struct irb irb;
if (stsch_err(sch->schid, &schib) || !css_sch_is_valid(&schib))
return -ENODEV;
@@ -367,7 +368,10 @@
ret = -EAGAIN;
break;
case 1: /* status pending */
- return -EBUSY;
+ ret = -EBUSY;
+ if (tsch(sch->schid, &irb))
+ return ret;
+ break;
case 2: /* busy */
udelay(100); /* allow for recovery */
ret = -EBUSY;
@@ -403,7 +407,6 @@
*/
int cio_enable_subchannel(struct subchannel *sch, u32 intparm)
{
- int retry;
int ret;
CIO_TRACE_EVENT(2, "ensch");
@@ -418,20 +421,14 @@
sch->config.isc = sch->isc;
sch->config.intparm = intparm;
- for (retry = 0; retry < 3; retry++) {
+ ret = cio_commit_config(sch);
+ if (ret == -EIO) {
+ /*
+ * Got a program check in msch. Try without
+ * the concurrent sense bit the next time.
+ */
+ sch->config.csense = 0;
ret = cio_commit_config(sch);
- if (ret == -EIO) {
- /*
- * Got a program check in msch. Try without
- * the concurrent sense bit the next time.
- */
- sch->config.csense = 0;
- } else if (ret == -EBUSY) {
- struct irb irb;
- if (tsch(sch->schid, &irb) != 0)
- break;
- } else
- break;
}
CIO_HEX_EVENT(2, &ret, sizeof(ret));
return ret;
@@ -444,7 +441,6 @@
*/
int cio_disable_subchannel(struct subchannel *sch)
{
- int retry;
int ret;
CIO_TRACE_EVENT(2, "dissch");
@@ -456,16 +452,8 @@
return -ENODEV;
sch->config.ena = 0;
+ ret = cio_commit_config(sch);
- for (retry = 0; retry < 3; retry++) {
- ret = cio_commit_config(sch);
- if (ret == -EBUSY) {
- struct irb irb;
- if (tsch(sch->schid, &irb) != 0)
- break;
- } else
- break;
- }
CIO_HEX_EVENT(2, &ret, sizeof(ret));
return ret;
}
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index 8acaae1..a563e4c 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -359,14 +359,12 @@
#define need_siga_sync_out_after_pci(q) \
(unlikely(q->irq_ptr->siga_flag.sync_out_after_pci))
-#define for_each_input_queue(irq_ptr, q, i) \
- for (i = 0, q = irq_ptr->input_qs[0]; \
- i < irq_ptr->nr_input_qs; \
- q = irq_ptr->input_qs[++i])
-#define for_each_output_queue(irq_ptr, q, i) \
- for (i = 0, q = irq_ptr->output_qs[0]; \
- i < irq_ptr->nr_output_qs; \
- q = irq_ptr->output_qs[++i])
+#define for_each_input_queue(irq_ptr, q, i) \
+ for (i = 0; i < irq_ptr->nr_input_qs && \
+ ({ q = irq_ptr->input_qs[i]; 1; }); i++)
+#define for_each_output_queue(irq_ptr, q, i) \
+ for (i = 0; i < irq_ptr->nr_output_qs && \
+ ({ q = irq_ptr->output_qs[i]; 1; }); i++)
#define prev_buf(bufnr) \
((bufnr + QDIO_MAX_BUFFERS_MASK) & QDIO_MAX_BUFFERS_MASK)
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index c883a08..77466c4 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -996,7 +996,7 @@
}
}
- if (!pci_out_supported(q))
+ if (!(irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED))
return;
for_each_output_queue(irq_ptr, q, i) {
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index dc542e0..0bc91e4 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -311,7 +311,7 @@
} __packed * msg = ap_msg->message;
int rcblen = CEIL4(xcRB->request_control_blk_length);
- int replylen;
+ int replylen, req_sumlen, resp_sumlen;
char *req_data = ap_msg->message + sizeof(struct type6_hdr) + rcblen;
char *function_code;
@@ -321,12 +321,34 @@
xcRB->request_data_length;
if (ap_msg->length > MSGTYPE06_MAX_MSG_SIZE)
return -EINVAL;
+
+ /* Overflow check
+ sum must be greater (or equal) than the largest operand */
+ req_sumlen = CEIL4(xcRB->request_control_blk_length) +
+ xcRB->request_data_length;
+ if ((CEIL4(xcRB->request_control_blk_length) <=
+ xcRB->request_data_length) ?
+ (req_sumlen < xcRB->request_data_length) :
+ (req_sumlen < CEIL4(xcRB->request_control_blk_length))) {
+ return -EINVAL;
+ }
+
replylen = sizeof(struct type86_fmt2_msg) +
CEIL4(xcRB->reply_control_blk_length) +
xcRB->reply_data_length;
if (replylen > MSGTYPE06_MAX_MSG_SIZE)
return -EINVAL;
+ /* Overflow check
+ sum must be greater (or equal) than the largest operand */
+ resp_sumlen = CEIL4(xcRB->reply_control_blk_length) +
+ xcRB->reply_data_length;
+ if ((CEIL4(xcRB->reply_control_blk_length) <= xcRB->reply_data_length) ?
+ (resp_sumlen < xcRB->reply_data_length) :
+ (resp_sumlen < CEIL4(xcRB->reply_control_blk_length))) {
+ return -EINVAL;
+ }
+
/* prepare type6 header */
msg->hdr = static_type6_hdrX;
memcpy(msg->hdr.agent_id , &(xcRB->agent_ID), sizeof(xcRB->agent_ID));
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index a0de045..5333b2c 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -854,8 +854,11 @@
static inline int qeth_get_ip_version(struct sk_buff *skb)
{
- struct ethhdr *ehdr = (struct ethhdr *)skb->data;
- switch (ehdr->h_proto) {
+ __be16 *p = &((struct ethhdr *)skb->data)->h_proto;
+
+ if (*p == ETH_P_8021Q)
+ p += 2;
+ switch (*p) {
case ETH_P_IPV6:
return 6;
case ETH_P_IP:
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index c3a83df..e1c3a38 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1660,7 +1660,6 @@
QDIO_FLAG_CLEANUP_USING_CLEAR);
if (rc)
QETH_CARD_TEXT_(card, 3, "1err%d", rc);
- qdio_free(CARD_DDEV(card));
atomic_set(&card->qdio.state, QETH_QDIO_ALLOCATED);
break;
case QETH_QDIO_CLEANING:
@@ -2605,6 +2604,7 @@
return 0;
out_qdio:
qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD);
+ qdio_free(CARD_DDEV(card));
return rc;
}
@@ -4610,8 +4610,8 @@
}
EXPORT_SYMBOL_GPL(qeth_query_oat_command);
-int qeth_query_card_info_cb(struct qeth_card *card,
- struct qeth_reply *reply, unsigned long data)
+static int qeth_query_card_info_cb(struct qeth_card *card,
+ struct qeth_reply *reply, unsigned long data)
{
struct qeth_ipa_cmd *cmd;
struct qeth_query_card_info *card_info;
@@ -4906,9 +4906,11 @@
if (retries < 3)
QETH_DBF_MESSAGE(2, "%s Retrying to do IDX activates.\n",
dev_name(&card->gdev->dev));
+ rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD);
ccw_device_set_offline(CARD_DDEV(card));
ccw_device_set_offline(CARD_WDEV(card));
ccw_device_set_offline(CARD_RDEV(card));
+ qdio_free(CARD_DDEV(card));
rc = ccw_device_set_online(CARD_RDEV(card));
if (rc)
goto retriable;
@@ -4918,7 +4920,6 @@
rc = ccw_device_set_online(CARD_DDEV(card));
if (rc)
goto retriable;
- rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD);
retriable:
if (rc == -ERESTARTSYS) {
QETH_DBF_TEXT(SETUP, 2, "break1");
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 0710550..8dea3f1 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -241,7 +241,7 @@
}
static void qeth_l2_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
- struct sk_buff *skb, int ipv, int cast_type)
+ struct sk_buff *skb, int cast_type)
{
struct vlan_ethhdr *veth = (struct vlan_ethhdr *)skb_mac_header(skb);
@@ -762,7 +762,7 @@
goto tx_drop;
elements_needed++;
skb_reset_mac_header(new_skb);
- qeth_l2_fill_header(card, hdr, new_skb, ipv, cast_type);
+ qeth_l2_fill_header(card, hdr, new_skb, cast_type);
hdr->hdr.l2.pkt_length = new_skb->len;
memcpy(((char *)hdr) + sizeof(struct qeth_hdr),
skb_mac_header(new_skb), ETH_HLEN);
@@ -775,7 +775,7 @@
hdr = (struct qeth_hdr *)skb_push(new_skb,
sizeof(struct qeth_hdr));
skb_set_mac_header(new_skb, sizeof(struct qeth_hdr));
- qeth_l2_fill_header(card, hdr, new_skb, ipv, cast_type);
+ qeth_l2_fill_header(card, hdr, new_skb, cast_type);
}
}
@@ -1091,6 +1091,7 @@
ccw_device_set_offline(CARD_DDEV(card));
ccw_device_set_offline(CARD_WDEV(card));
ccw_device_set_offline(CARD_RDEV(card));
+ qdio_free(CARD_DDEV(card));
if (recover_flag == CARD_STATE_RECOVER)
card->state = CARD_STATE_RECOVER;
else
@@ -1132,6 +1133,7 @@
rc = (rc2) ? rc2 : rc3;
if (rc)
QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc);
+ qdio_free(CARD_DDEV(card));
if (recover_flag == CARD_STATE_UP)
card->state = CARD_STATE_RECOVER;
/* let user_space know that device is offline */
@@ -1194,6 +1196,7 @@
qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
qeth_qdio_clear_card(card, 0);
qeth_clear_qdio_buffers(card);
+ qdio_free(CARD_DDEV(card));
}
static int qeth_l2_pm_suspend(struct ccwgroup_device *gdev)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 0f43042..3524d34 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3447,6 +3447,7 @@
ccw_device_set_offline(CARD_DDEV(card));
ccw_device_set_offline(CARD_WDEV(card));
ccw_device_set_offline(CARD_RDEV(card));
+ qdio_free(CARD_DDEV(card));
if (recover_flag == CARD_STATE_RECOVER)
card->state = CARD_STATE_RECOVER;
else
@@ -3493,6 +3494,7 @@
rc = (rc2) ? rc2 : rc3;
if (rc)
QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc);
+ qdio_free(CARD_DDEV(card));
if (recover_flag == CARD_STATE_UP)
card->state = CARD_STATE_RECOVER;
/* let user_space know that device is offline */
@@ -3545,6 +3547,7 @@
qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
qeth_qdio_clear_card(card, 0);
qeth_clear_qdio_buffers(card);
+ qdio_free(CARD_DDEV(card));
}
static int qeth_l3_pm_suspend(struct ccwgroup_device *gdev)
diff --git a/drivers/sbus/char/jsflash.c b/drivers/sbus/char/jsflash.c
index 6b4678a..4ccb5d8 100644
--- a/drivers/sbus/char/jsflash.c
+++ b/drivers/sbus/char/jsflash.c
@@ -507,7 +507,6 @@
}
/* Let us be really paranoid for modifications to probing code. */
- /* extern enum sparc_cpu sparc_cpu_model; */ /* in <asm/system.h> */
if (sparc_cpu_model != sun4m) {
/* We must be on sun4m because we use MMU Bypass ASI. */
return -ENXIO;
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 1f37505..5642a9b 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -325,7 +325,7 @@
if (!abrt_task->sc || abrt_task->state == ISCSI_TASK_FREE)
continue;
- if (abrt_task->sc->device->lun != abrt_task->sc->device->lun)
+ if (sc->device->lun != abrt_task->sc->device->lun)
continue;
/* Invalidate WRB Posted for this Task */
diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c
index ed88089..e9279a8 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_io.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_io.c
@@ -594,13 +594,13 @@
mp_req->mp_resp_bd = NULL;
}
if (mp_req->req_buf) {
- dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
mp_req->req_buf,
mp_req->req_buf_dma);
mp_req->req_buf = NULL;
}
if (mp_req->resp_buf) {
- dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
mp_req->resp_buf,
mp_req->resp_buf_dma);
mp_req->resp_buf = NULL;
@@ -622,7 +622,7 @@
mp_req->req_len = sizeof(struct fcp_cmnd);
io_req->data_xfer_len = mp_req->req_len;
- mp_req->req_buf = dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ mp_req->req_buf = dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
&mp_req->req_buf_dma,
GFP_ATOMIC);
if (!mp_req->req_buf) {
@@ -631,7 +631,7 @@
return FAILED;
}
- mp_req->resp_buf = dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ mp_req->resp_buf = dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
&mp_req->resp_buf_dma,
GFP_ATOMIC);
if (!mp_req->resp_buf) {
@@ -639,8 +639,8 @@
bnx2fc_free_mp_resc(io_req);
return FAILED;
}
- memset(mp_req->req_buf, 0, PAGE_SIZE);
- memset(mp_req->resp_buf, 0, PAGE_SIZE);
+ memset(mp_req->req_buf, 0, CNIC_PAGE_SIZE);
+ memset(mp_req->resp_buf, 0, CNIC_PAGE_SIZE);
/* Allocate and map mp_req_bd and mp_resp_bd */
sz = sizeof(struct fcoe_bd_ctx);
@@ -665,7 +665,7 @@
mp_req_bd = mp_req->mp_req_bd;
mp_req_bd->buf_addr_lo = (u32)addr & 0xffffffff;
mp_req_bd->buf_addr_hi = (u32)((u64)addr >> 32);
- mp_req_bd->buf_len = PAGE_SIZE;
+ mp_req_bd->buf_len = CNIC_PAGE_SIZE;
mp_req_bd->flags = 0;
/*
@@ -677,7 +677,7 @@
addr = mp_req->resp_buf_dma;
mp_resp_bd->buf_addr_lo = (u32)addr & 0xffffffff;
mp_resp_bd->buf_addr_hi = (u32)((u64)addr >> 32);
- mp_resp_bd->buf_len = PAGE_SIZE;
+ mp_resp_bd->buf_len = CNIC_PAGE_SIZE;
mp_resp_bd->flags = 0;
return SUCCESS;
diff --git a/drivers/scsi/bnx2fc/bnx2fc_tgt.c b/drivers/scsi/bnx2fc/bnx2fc_tgt.c
index 4d93177..d9bae56 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_tgt.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_tgt.c
@@ -673,7 +673,8 @@
/* Allocate and map SQ */
tgt->sq_mem_size = tgt->max_sqes * BNX2FC_SQ_WQE_SIZE;
- tgt->sq_mem_size = (tgt->sq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+ tgt->sq_mem_size = (tgt->sq_mem_size + (CNIC_PAGE_SIZE - 1)) &
+ CNIC_PAGE_MASK;
tgt->sq = dma_alloc_coherent(&hba->pcidev->dev, tgt->sq_mem_size,
&tgt->sq_dma, GFP_KERNEL);
@@ -686,7 +687,8 @@
/* Allocate and map CQ */
tgt->cq_mem_size = tgt->max_cqes * BNX2FC_CQ_WQE_SIZE;
- tgt->cq_mem_size = (tgt->cq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+ tgt->cq_mem_size = (tgt->cq_mem_size + (CNIC_PAGE_SIZE - 1)) &
+ CNIC_PAGE_MASK;
tgt->cq = dma_alloc_coherent(&hba->pcidev->dev, tgt->cq_mem_size,
&tgt->cq_dma, GFP_KERNEL);
@@ -699,7 +701,8 @@
/* Allocate and map RQ and RQ PBL */
tgt->rq_mem_size = tgt->max_rqes * BNX2FC_RQ_WQE_SIZE;
- tgt->rq_mem_size = (tgt->rq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+ tgt->rq_mem_size = (tgt->rq_mem_size + (CNIC_PAGE_SIZE - 1)) &
+ CNIC_PAGE_MASK;
tgt->rq = dma_alloc_coherent(&hba->pcidev->dev, tgt->rq_mem_size,
&tgt->rq_dma, GFP_KERNEL);
@@ -710,8 +713,9 @@
}
memset(tgt->rq, 0, tgt->rq_mem_size);
- tgt->rq_pbl_size = (tgt->rq_mem_size / PAGE_SIZE) * sizeof(void *);
- tgt->rq_pbl_size = (tgt->rq_pbl_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+ tgt->rq_pbl_size = (tgt->rq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *);
+ tgt->rq_pbl_size = (tgt->rq_pbl_size + (CNIC_PAGE_SIZE - 1)) &
+ CNIC_PAGE_MASK;
tgt->rq_pbl = dma_alloc_coherent(&hba->pcidev->dev, tgt->rq_pbl_size,
&tgt->rq_pbl_dma, GFP_KERNEL);
@@ -722,7 +726,7 @@
}
memset(tgt->rq_pbl, 0, tgt->rq_pbl_size);
- num_pages = tgt->rq_mem_size / PAGE_SIZE;
+ num_pages = tgt->rq_mem_size / CNIC_PAGE_SIZE;
page = tgt->rq_dma;
pbl = (u32 *)tgt->rq_pbl;
@@ -731,13 +735,13 @@
pbl++;
*pbl = (u32)((u64)page >> 32);
pbl++;
- page += PAGE_SIZE;
+ page += CNIC_PAGE_SIZE;
}
/* Allocate and map XFERQ */
tgt->xferq_mem_size = tgt->max_sqes * BNX2FC_XFERQ_WQE_SIZE;
- tgt->xferq_mem_size = (tgt->xferq_mem_size + (PAGE_SIZE - 1)) &
- PAGE_MASK;
+ tgt->xferq_mem_size = (tgt->xferq_mem_size + (CNIC_PAGE_SIZE - 1)) &
+ CNIC_PAGE_MASK;
tgt->xferq = dma_alloc_coherent(&hba->pcidev->dev, tgt->xferq_mem_size,
&tgt->xferq_dma, GFP_KERNEL);
@@ -750,8 +754,8 @@
/* Allocate and map CONFQ & CONFQ PBL */
tgt->confq_mem_size = tgt->max_sqes * BNX2FC_CONFQ_WQE_SIZE;
- tgt->confq_mem_size = (tgt->confq_mem_size + (PAGE_SIZE - 1)) &
- PAGE_MASK;
+ tgt->confq_mem_size = (tgt->confq_mem_size + (CNIC_PAGE_SIZE - 1)) &
+ CNIC_PAGE_MASK;
tgt->confq = dma_alloc_coherent(&hba->pcidev->dev, tgt->confq_mem_size,
&tgt->confq_dma, GFP_KERNEL);
@@ -763,9 +767,9 @@
memset(tgt->confq, 0, tgt->confq_mem_size);
tgt->confq_pbl_size =
- (tgt->confq_mem_size / PAGE_SIZE) * sizeof(void *);
+ (tgt->confq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *);
tgt->confq_pbl_size =
- (tgt->confq_pbl_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+ (tgt->confq_pbl_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
tgt->confq_pbl = dma_alloc_coherent(&hba->pcidev->dev,
tgt->confq_pbl_size,
@@ -777,7 +781,7 @@
}
memset(tgt->confq_pbl, 0, tgt->confq_pbl_size);
- num_pages = tgt->confq_mem_size / PAGE_SIZE;
+ num_pages = tgt->confq_mem_size / CNIC_PAGE_SIZE;
page = tgt->confq_dma;
pbl = (u32 *)tgt->confq_pbl;
@@ -786,7 +790,7 @@
pbl++;
*pbl = (u32)((u64)page >> 32);
pbl++;
- page += PAGE_SIZE;
+ page += CNIC_PAGE_SIZE;
}
/* Allocate and map ConnDB */
@@ -805,8 +809,8 @@
/* Allocate and map LCQ */
tgt->lcq_mem_size = (tgt->max_sqes + 8) * BNX2FC_SQ_WQE_SIZE;
- tgt->lcq_mem_size = (tgt->lcq_mem_size + (PAGE_SIZE - 1)) &
- PAGE_MASK;
+ tgt->lcq_mem_size = (tgt->lcq_mem_size + (CNIC_PAGE_SIZE - 1)) &
+ CNIC_PAGE_MASK;
tgt->lcq = dma_alloc_coherent(&hba->pcidev->dev, tgt->lcq_mem_size,
&tgt->lcq_dma, GFP_KERNEL);
diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index e4cf23d..b87a193 100644
--- a/drivers/scsi/bnx2i/bnx2i_hwi.c
+++ b/drivers/scsi/bnx2i/bnx2i_hwi.c
@@ -61,7 +61,7 @@
* yield integral num of page buffers
*/
/* adjust SQ */
- num_elements_per_pg = PAGE_SIZE / BNX2I_SQ_WQE_SIZE;
+ num_elements_per_pg = CNIC_PAGE_SIZE / BNX2I_SQ_WQE_SIZE;
if (hba->max_sqes < num_elements_per_pg)
hba->max_sqes = num_elements_per_pg;
else if (hba->max_sqes % num_elements_per_pg)
@@ -69,7 +69,7 @@
~(num_elements_per_pg - 1);
/* adjust CQ */
- num_elements_per_pg = PAGE_SIZE / BNX2I_CQE_SIZE;
+ num_elements_per_pg = CNIC_PAGE_SIZE / BNX2I_CQE_SIZE;
if (hba->max_cqes < num_elements_per_pg)
hba->max_cqes = num_elements_per_pg;
else if (hba->max_cqes % num_elements_per_pg)
@@ -77,7 +77,7 @@
~(num_elements_per_pg - 1);
/* adjust RQ */
- num_elements_per_pg = PAGE_SIZE / BNX2I_RQ_WQE_SIZE;
+ num_elements_per_pg = CNIC_PAGE_SIZE / BNX2I_RQ_WQE_SIZE;
if (hba->max_rqes < num_elements_per_pg)
hba->max_rqes = num_elements_per_pg;
else if (hba->max_rqes % num_elements_per_pg)
@@ -959,7 +959,7 @@
/* SQ page table */
memset(ep->qp.sq_pgtbl_virt, 0, ep->qp.sq_pgtbl_size);
- num_pages = ep->qp.sq_mem_size / PAGE_SIZE;
+ num_pages = ep->qp.sq_mem_size / CNIC_PAGE_SIZE;
page = ep->qp.sq_phys;
if (cnic_dev_10g)
@@ -973,7 +973,7 @@
ptbl++;
*ptbl = (u32) ((u64) page >> 32);
ptbl++;
- page += PAGE_SIZE;
+ page += CNIC_PAGE_SIZE;
} else {
/* PTE is written in big endian format for
* 5706/5708/5709 devices */
@@ -981,13 +981,13 @@
ptbl++;
*ptbl = (u32) page;
ptbl++;
- page += PAGE_SIZE;
+ page += CNIC_PAGE_SIZE;
}
}
/* RQ page table */
memset(ep->qp.rq_pgtbl_virt, 0, ep->qp.rq_pgtbl_size);
- num_pages = ep->qp.rq_mem_size / PAGE_SIZE;
+ num_pages = ep->qp.rq_mem_size / CNIC_PAGE_SIZE;
page = ep->qp.rq_phys;
if (cnic_dev_10g)
@@ -1001,7 +1001,7 @@
ptbl++;
*ptbl = (u32) ((u64) page >> 32);
ptbl++;
- page += PAGE_SIZE;
+ page += CNIC_PAGE_SIZE;
} else {
/* PTE is written in big endian format for
* 5706/5708/5709 devices */
@@ -1009,13 +1009,13 @@
ptbl++;
*ptbl = (u32) page;
ptbl++;
- page += PAGE_SIZE;
+ page += CNIC_PAGE_SIZE;
}
}
/* CQ page table */
memset(ep->qp.cq_pgtbl_virt, 0, ep->qp.cq_pgtbl_size);
- num_pages = ep->qp.cq_mem_size / PAGE_SIZE;
+ num_pages = ep->qp.cq_mem_size / CNIC_PAGE_SIZE;
page = ep->qp.cq_phys;
if (cnic_dev_10g)
@@ -1029,7 +1029,7 @@
ptbl++;
*ptbl = (u32) ((u64) page >> 32);
ptbl++;
- page += PAGE_SIZE;
+ page += CNIC_PAGE_SIZE;
} else {
/* PTE is written in big endian format for
* 5706/5708/5709 devices */
@@ -1037,7 +1037,7 @@
ptbl++;
*ptbl = (u32) page;
ptbl++;
- page += PAGE_SIZE;
+ page += CNIC_PAGE_SIZE;
}
}
}
@@ -1064,11 +1064,11 @@
/* Allocate page table memory for SQ which is page aligned */
ep->qp.sq_mem_size = hba->max_sqes * BNX2I_SQ_WQE_SIZE;
ep->qp.sq_mem_size =
- (ep->qp.sq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+ (ep->qp.sq_mem_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
ep->qp.sq_pgtbl_size =
- (ep->qp.sq_mem_size / PAGE_SIZE) * sizeof(void *);
+ (ep->qp.sq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *);
ep->qp.sq_pgtbl_size =
- (ep->qp.sq_pgtbl_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+ (ep->qp.sq_pgtbl_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
ep->qp.sq_pgtbl_virt =
dma_alloc_coherent(&hba->pcidev->dev, ep->qp.sq_pgtbl_size,
@@ -1101,11 +1101,11 @@
/* Allocate page table memory for CQ which is page aligned */
ep->qp.cq_mem_size = hba->max_cqes * BNX2I_CQE_SIZE;
ep->qp.cq_mem_size =
- (ep->qp.cq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+ (ep->qp.cq_mem_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
ep->qp.cq_pgtbl_size =
- (ep->qp.cq_mem_size / PAGE_SIZE) * sizeof(void *);
+ (ep->qp.cq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *);
ep->qp.cq_pgtbl_size =
- (ep->qp.cq_pgtbl_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+ (ep->qp.cq_pgtbl_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
ep->qp.cq_pgtbl_virt =
dma_alloc_coherent(&hba->pcidev->dev, ep->qp.cq_pgtbl_size,
@@ -1144,11 +1144,11 @@
/* Allocate page table memory for RQ which is page aligned */
ep->qp.rq_mem_size = hba->max_rqes * BNX2I_RQ_WQE_SIZE;
ep->qp.rq_mem_size =
- (ep->qp.rq_mem_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+ (ep->qp.rq_mem_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
ep->qp.rq_pgtbl_size =
- (ep->qp.rq_mem_size / PAGE_SIZE) * sizeof(void *);
+ (ep->qp.rq_mem_size / CNIC_PAGE_SIZE) * sizeof(void *);
ep->qp.rq_pgtbl_size =
- (ep->qp.rq_pgtbl_size + (PAGE_SIZE - 1)) & PAGE_MASK;
+ (ep->qp.rq_pgtbl_size + (CNIC_PAGE_SIZE - 1)) & CNIC_PAGE_MASK;
ep->qp.rq_pgtbl_virt =
dma_alloc_coherent(&hba->pcidev->dev, ep->qp.rq_pgtbl_size,
@@ -1270,7 +1270,7 @@
bnx2i_adjust_qp_size(hba);
iscsi_init.flags =
- ISCSI_PAGE_SIZE_4K << ISCSI_KWQE_INIT1_PAGE_SIZE_SHIFT;
+ (CNIC_PAGE_BITS - 8) << ISCSI_KWQE_INIT1_PAGE_SIZE_SHIFT;
if (en_tcp_dack)
iscsi_init.flags |= ISCSI_KWQE_INIT1_DELAYED_ACK_ENABLE;
iscsi_init.reserved0 = 0;
@@ -1288,15 +1288,15 @@
((hba->num_ccell & 0xFFFF) | (hba->max_sqes << 16));
iscsi_init.num_ccells_per_conn = hba->num_ccell;
iscsi_init.num_tasks_per_conn = hba->max_sqes;
- iscsi_init.sq_wqes_per_page = PAGE_SIZE / BNX2I_SQ_WQE_SIZE;
+ iscsi_init.sq_wqes_per_page = CNIC_PAGE_SIZE / BNX2I_SQ_WQE_SIZE;
iscsi_init.sq_num_wqes = hba->max_sqes;
iscsi_init.cq_log_wqes_per_page =
- (u8) bnx2i_power_of2(PAGE_SIZE / BNX2I_CQE_SIZE);
+ (u8) bnx2i_power_of2(CNIC_PAGE_SIZE / BNX2I_CQE_SIZE);
iscsi_init.cq_num_wqes = hba->max_cqes;
iscsi_init.cq_num_pages = (hba->max_cqes * BNX2I_CQE_SIZE +
- (PAGE_SIZE - 1)) / PAGE_SIZE;
+ (CNIC_PAGE_SIZE - 1)) / CNIC_PAGE_SIZE;
iscsi_init.sq_num_pages = (hba->max_sqes * BNX2I_SQ_WQE_SIZE +
- (PAGE_SIZE - 1)) / PAGE_SIZE;
+ (CNIC_PAGE_SIZE - 1)) / CNIC_PAGE_SIZE;
iscsi_init.rq_buffer_size = BNX2I_RQ_WQE_SIZE;
iscsi_init.rq_num_wqes = hba->max_rqes;
diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c
index 854dad7..c8b0aff 100644
--- a/drivers/scsi/bnx2i/bnx2i_iscsi.c
+++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c
@@ -525,7 +525,7 @@
struct iscsi_bd *mp_bdt;
u64 addr;
- hba->mp_bd_tbl = dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ hba->mp_bd_tbl = dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
&hba->mp_bd_dma, GFP_KERNEL);
if (!hba->mp_bd_tbl) {
printk(KERN_ERR "unable to allocate Middle Path BDT\n");
@@ -533,11 +533,12 @@
goto out;
}
- hba->dummy_buffer = dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ hba->dummy_buffer = dma_alloc_coherent(&hba->pcidev->dev,
+ CNIC_PAGE_SIZE,
&hba->dummy_buf_dma, GFP_KERNEL);
if (!hba->dummy_buffer) {
printk(KERN_ERR "unable to alloc Middle Path Dummy Buffer\n");
- dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
hba->mp_bd_tbl, hba->mp_bd_dma);
hba->mp_bd_tbl = NULL;
rc = -1;
@@ -548,7 +549,7 @@
addr = (unsigned long) hba->dummy_buf_dma;
mp_bdt->buffer_addr_lo = addr & 0xffffffff;
mp_bdt->buffer_addr_hi = addr >> 32;
- mp_bdt->buffer_length = PAGE_SIZE;
+ mp_bdt->buffer_length = CNIC_PAGE_SIZE;
mp_bdt->flags = ISCSI_BD_LAST_IN_BD_CHAIN |
ISCSI_BD_FIRST_IN_BD_CHAIN;
out:
@@ -565,12 +566,12 @@
static void bnx2i_free_mp_bdt(struct bnx2i_hba *hba)
{
if (hba->mp_bd_tbl) {
- dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
hba->mp_bd_tbl, hba->mp_bd_dma);
hba->mp_bd_tbl = NULL;
}
if (hba->dummy_buffer) {
- dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
hba->dummy_buffer, hba->dummy_buf_dma);
hba->dummy_buffer = NULL;
}
@@ -934,14 +935,14 @@
struct bnx2i_conn *bnx2i_conn)
{
if (bnx2i_conn->gen_pdu.resp_bd_tbl) {
- dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
bnx2i_conn->gen_pdu.resp_bd_tbl,
bnx2i_conn->gen_pdu.resp_bd_dma);
bnx2i_conn->gen_pdu.resp_bd_tbl = NULL;
}
if (bnx2i_conn->gen_pdu.req_bd_tbl) {
- dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
bnx2i_conn->gen_pdu.req_bd_tbl,
bnx2i_conn->gen_pdu.req_bd_dma);
bnx2i_conn->gen_pdu.req_bd_tbl = NULL;
@@ -998,13 +999,13 @@
bnx2i_conn->gen_pdu.resp_wr_ptr = bnx2i_conn->gen_pdu.resp_buf;
bnx2i_conn->gen_pdu.req_bd_tbl =
- dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
&bnx2i_conn->gen_pdu.req_bd_dma, GFP_KERNEL);
if (bnx2i_conn->gen_pdu.req_bd_tbl == NULL)
goto login_req_bd_tbl_failure;
bnx2i_conn->gen_pdu.resp_bd_tbl =
- dma_alloc_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ dma_alloc_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
&bnx2i_conn->gen_pdu.resp_bd_dma,
GFP_KERNEL);
if (bnx2i_conn->gen_pdu.resp_bd_tbl == NULL)
@@ -1013,7 +1014,7 @@
return 0;
login_resp_bd_tbl_failure:
- dma_free_coherent(&hba->pcidev->dev, PAGE_SIZE,
+ dma_free_coherent(&hba->pcidev->dev, CNIC_PAGE_SIZE,
bnx2i_conn->gen_pdu.req_bd_tbl,
bnx2i_conn->gen_pdu.req_bd_dma);
bnx2i_conn->gen_pdu.req_bd_tbl = NULL;
diff --git a/drivers/scsi/isci/host.h b/drivers/scsi/isci/host.h
index 4911310..22a9bb1 100644
--- a/drivers/scsi/isci/host.h
+++ b/drivers/scsi/isci/host.h
@@ -311,9 +311,8 @@
}
#define for_each_isci_host(id, ihost, pdev) \
- for (id = 0, ihost = to_pci_info(pdev)->hosts[id]; \
- id < ARRAY_SIZE(to_pci_info(pdev)->hosts) && ihost; \
- ihost = to_pci_info(pdev)->hosts[++id])
+ for (id = 0; id < SCI_MAX_CONTROLLERS && \
+ (ihost = to_pci_info(pdev)->hosts[id]); id++)
static inline void wait_for_start(struct isci_host *ihost)
{
diff --git a/drivers/scsi/isci/port_config.c b/drivers/scsi/isci/port_config.c
index 85c77f6..ac87974 100644
--- a/drivers/scsi/isci/port_config.c
+++ b/drivers/scsi/isci/port_config.c
@@ -615,13 +615,6 @@
SCIC_SDS_APC_WAIT_LINK_UP_NOTIFICATION);
} else {
/* the phy is already the part of the port */
- u32 port_state = iport->sm.current_state_id;
-
- /* if the PORT'S state is resetting then the link up is from
- * port hard reset in this case, we need to tell the port
- * that link up is recieved
- */
- BUG_ON(port_state != SCI_PORT_RESETTING);
port_agent->phy_ready_mask |= 1 << phy_index;
sci_port_link_up(iport, iphy);
}
diff --git a/drivers/scsi/isci/task.c b/drivers/scsi/isci/task.c
index 0d30ca8..5d6fda7 100644
--- a/drivers/scsi/isci/task.c
+++ b/drivers/scsi/isci/task.c
@@ -801,7 +801,7 @@
/* XXX: need to cleanup any ireqs targeting this
* domain_device
*/
- ret = TMF_RESP_FUNC_COMPLETE;
+ ret = -ENODEV;
goto out;
}
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index e1fe95e..266724b 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2996,8 +2996,7 @@
IS_QLA82XX(ha) || IS_QLA83XX(ha) || \
IS_QLA8044(ha))
#define IS_MSIX_NACK_CAPABLE(ha) (IS_QLA81XX(ha) || IS_QLA83XX(ha))
-#define IS_NOPOLLING_TYPE(ha) ((IS_QLA25XX(ha) || IS_QLA81XX(ha) || \
- IS_QLA83XX(ha)) && (ha)->flags.msix_enabled)
+#define IS_NOPOLLING_TYPE(ha) (IS_QLA81XX(ha) && (ha)->flags.msix_enabled)
#define IS_FAC_REQUIRED(ha) (IS_QLA81XX(ha) || IS_QLA83XX(ha))
#define IS_NOCACHE_VPD_TYPE(ha) (IS_QLA81XX(ha) || IS_QLA83XX(ha))
#define IS_ALOGIO_CAPABLE(ha) (IS_QLA23XX(ha) || IS_FWI2_CAPABLE(ha))
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 9bc86b9..0a1dcb4 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -2880,6 +2880,7 @@
qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
{
#define MIN_MSIX_COUNT 2
+#define ATIO_VECTOR 2
int i, ret;
struct msix_entry *entries;
struct qla_msix_entry *qentry;
@@ -2936,34 +2937,47 @@
}
/* Enable MSI-X vectors for the base queue */
- for (i = 0; i < ha->msix_count; i++) {
+ for (i = 0; i < 2; i++) {
qentry = &ha->msix_entries[i];
- if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha)) {
- ret = request_irq(qentry->vector,
- qla83xx_msix_entries[i].handler,
- 0, qla83xx_msix_entries[i].name, rsp);
- } else if (IS_P3P_TYPE(ha)) {
+ if (IS_P3P_TYPE(ha))
ret = request_irq(qentry->vector,
qla82xx_msix_entries[i].handler,
0, qla82xx_msix_entries[i].name, rsp);
- } else {
+ else
ret = request_irq(qentry->vector,
msix_entries[i].handler,
0, msix_entries[i].name, rsp);
- }
- if (ret) {
- ql_log(ql_log_fatal, vha, 0x00cb,
- "MSI-X: unable to register handler -- %x/%d.\n",
- qentry->vector, ret);
- qla24xx_disable_msix(ha);
- ha->mqenable = 0;
- goto msix_out;
- }
+ if (ret)
+ goto msix_register_fail;
qentry->have_irq = 1;
qentry->rsp = rsp;
rsp->msix = qentry;
}
+ /*
+ * If target mode is enable, also request the vector for the ATIO
+ * queue.
+ */
+ if (QLA_TGT_MODE_ENABLED() && IS_ATIO_MSIX_CAPABLE(ha)) {
+ qentry = &ha->msix_entries[ATIO_VECTOR];
+ ret = request_irq(qentry->vector,
+ qla83xx_msix_entries[ATIO_VECTOR].handler,
+ 0, qla83xx_msix_entries[ATIO_VECTOR].name, rsp);
+ qentry->have_irq = 1;
+ qentry->rsp = rsp;
+ rsp->msix = qentry;
+ }
+
+msix_register_fail:
+ if (ret) {
+ ql_log(ql_log_fatal, vha, 0x00cb,
+ "MSI-X: unable to register handler -- %x/%d.\n",
+ qentry->vector, ret);
+ qla24xx_disable_msix(ha);
+ ha->mqenable = 0;
+ goto msix_out;
+ }
+
/* Enable MSI-X vector for response queue update for queue 0 */
if (IS_QLA83XX(ha)) {
if (ha->msixbase && ha->mqiobase &&
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 9e80d61..0cb7307 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -790,17 +790,32 @@
}
/* Called by tcm_qla2xxx configfs code */
-void qlt_stop_phase1(struct qla_tgt *tgt)
+int qlt_stop_phase1(struct qla_tgt *tgt)
{
struct scsi_qla_host *vha = tgt->vha;
struct qla_hw_data *ha = tgt->ha;
unsigned long flags;
+ mutex_lock(&qla_tgt_mutex);
+ if (!vha->fc_vport) {
+ struct Scsi_Host *sh = vha->host;
+ struct fc_host_attrs *fc_host = shost_to_fc_host(sh);
+ bool npiv_vports;
+
+ spin_lock_irqsave(sh->host_lock, flags);
+ npiv_vports = (fc_host->npiv_vports_inuse);
+ spin_unlock_irqrestore(sh->host_lock, flags);
+
+ if (npiv_vports) {
+ mutex_unlock(&qla_tgt_mutex);
+ return -EPERM;
+ }
+ }
if (tgt->tgt_stop || tgt->tgt_stopped) {
ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04e,
"Already in tgt->tgt_stop or tgt_stopped state\n");
- dump_stack();
- return;
+ mutex_unlock(&qla_tgt_mutex);
+ return -EPERM;
}
ql_dbg(ql_dbg_tgt, vha, 0xe003, "Stopping target for host %ld(%p)\n",
@@ -815,6 +830,7 @@
qlt_clear_tgt_db(tgt, true);
spin_unlock_irqrestore(&ha->hardware_lock, flags);
mutex_unlock(&vha->vha_tgt.tgt_mutex);
+ mutex_unlock(&qla_tgt_mutex);
flush_delayed_work(&tgt->sess_del_work);
@@ -841,6 +857,7 @@
/* Wait for sessions to clear out (just in case) */
wait_event(tgt->waitQ, test_tgt_sess_count(tgt));
+ return 0;
}
EXPORT_SYMBOL(qlt_stop_phase1);
@@ -2595,8 +2612,6 @@
return -ENOMEM;
}
- INIT_LIST_HEAD(&cmd->cmd_list);
-
memcpy(&cmd->atio, atio, sizeof(*atio));
cmd->state = QLA_TGT_STATE_NEW;
cmd->tgt = vha->vha_tgt.qla_tgt;
@@ -3187,7 +3202,8 @@
ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02c,
"SRR cmd %p (se_cmd %p, tag %d, op %x), "
"sg_cnt=%d, offset=%d", cmd, &cmd->se_cmd, cmd->tag,
- se_cmd->t_task_cdb[0], cmd->sg_cnt, cmd->offset);
+ se_cmd->t_task_cdb ? se_cmd->t_task_cdb[0] : 0,
+ cmd->sg_cnt, cmd->offset);
qlt_handle_srr(vha, sctio, imm);
@@ -4183,6 +4199,9 @@
tgt->datasegs_per_cmd = QLA_TGT_DATASEGS_PER_CMD_24XX;
tgt->datasegs_per_cont = QLA_TGT_DATASEGS_PER_CONT_24XX;
+ if (base_vha->fc_vport)
+ return 0;
+
mutex_lock(&qla_tgt_mutex);
list_add_tail(&tgt->tgt_list_entry, &qla_tgt_glist);
mutex_unlock(&qla_tgt_mutex);
@@ -4196,6 +4215,10 @@
if (!vha->vha_tgt.qla_tgt)
return 0;
+ if (vha->fc_vport) {
+ qlt_release(vha->vha_tgt.qla_tgt);
+ return 0;
+ }
mutex_lock(&qla_tgt_mutex);
list_del(&vha->vha_tgt.qla_tgt->tgt_list_entry);
mutex_unlock(&qla_tgt_mutex);
@@ -4267,6 +4290,12 @@
spin_unlock_irqrestore(&ha->hardware_lock, flags);
continue;
}
+ if (tgt->tgt_stop) {
+ pr_debug("MODE_TARGET in shutdown on qla2xxx(%d)\n",
+ host->host_no);
+ spin_unlock_irqrestore(&ha->hardware_lock, flags);
+ continue;
+ }
spin_unlock_irqrestore(&ha->hardware_lock, flags);
if (!scsi_host_get(host)) {
@@ -4281,12 +4310,11 @@
scsi_host_put(host);
continue;
}
- mutex_unlock(&qla_tgt_mutex);
-
rc = (*callback)(vha, target_lport_ptr, npiv_wwpn, npiv_wwnn);
if (rc != 0)
scsi_host_put(host);
+ mutex_unlock(&qla_tgt_mutex);
return rc;
}
mutex_unlock(&qla_tgt_mutex);
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 1d10eec..ce33d8c 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -855,7 +855,6 @@
uint16_t loop_id; /* to save extra sess dereferences */
struct qla_tgt *tgt; /* to save extra sess dereferences */
struct scsi_qla_host *vha;
- struct list_head cmd_list;
struct atio_from_isp atio;
};
@@ -1002,7 +1001,7 @@
extern void qlt_probe_one_stage1(struct scsi_qla_host *, struct qla_hw_data *);
extern int qlt_mem_alloc(struct qla_hw_data *);
extern void qlt_mem_free(struct qla_hw_data *);
-extern void qlt_stop_phase1(struct qla_tgt *);
+extern int qlt_stop_phase1(struct qla_tgt *);
extern void qlt_stop_phase2(struct qla_tgt *);
extern irqreturn_t qla83xx_msix_atio_q(int, void *);
extern void qlt_83xx_iospace_config(struct qla_hw_data *);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 75a141b..788c4fe 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -182,20 +182,6 @@
return 0;
}
-static ssize_t tcm_qla2xxx_npiv_format_wwn(char *buf, size_t len,
- u64 wwpn, u64 wwnn)
-{
- u8 b[8], b2[8];
-
- put_unaligned_be64(wwpn, b);
- put_unaligned_be64(wwnn, b2);
- return snprintf(buf, len,
- "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x,"
- "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x",
- b[0], b[1], b[2], b[3], b[4], b[5], b[6], b[7],
- b2[0], b2[1], b2[2], b2[3], b2[4], b2[5], b2[6], b2[7]);
-}
-
static char *tcm_qla2xxx_npiv_get_fabric_name(void)
{
return "qla2xxx_npiv";
@@ -227,15 +213,6 @@
return lport->lport_naa_name;
}
-static char *tcm_qla2xxx_npiv_get_fabric_wwn(struct se_portal_group *se_tpg)
-{
- struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
- struct tcm_qla2xxx_tpg, se_tpg);
- struct tcm_qla2xxx_lport *lport = tpg->lport;
-
- return &lport->lport_npiv_name[0];
-}
-
static u16 tcm_qla2xxx_get_tag(struct se_portal_group *se_tpg)
{
struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
@@ -941,15 +918,41 @@
atomic_read(&tpg->lport_tpg_enabled));
}
+static void tcm_qla2xxx_depend_tpg(struct work_struct *work)
+{
+ struct tcm_qla2xxx_tpg *base_tpg = container_of(work,
+ struct tcm_qla2xxx_tpg, tpg_base_work);
+ struct se_portal_group *se_tpg = &base_tpg->se_tpg;
+ struct scsi_qla_host *base_vha = base_tpg->lport->qla_vha;
+
+ if (!configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys,
+ &se_tpg->tpg_group.cg_item)) {
+ atomic_set(&base_tpg->lport_tpg_enabled, 1);
+ qlt_enable_vha(base_vha);
+ }
+ complete(&base_tpg->tpg_base_comp);
+}
+
+static void tcm_qla2xxx_undepend_tpg(struct work_struct *work)
+{
+ struct tcm_qla2xxx_tpg *base_tpg = container_of(work,
+ struct tcm_qla2xxx_tpg, tpg_base_work);
+ struct se_portal_group *se_tpg = &base_tpg->se_tpg;
+ struct scsi_qla_host *base_vha = base_tpg->lport->qla_vha;
+
+ if (!qlt_stop_phase1(base_vha->vha_tgt.qla_tgt)) {
+ atomic_set(&base_tpg->lport_tpg_enabled, 0);
+ configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys,
+ &se_tpg->tpg_group.cg_item);
+ }
+ complete(&base_tpg->tpg_base_comp);
+}
+
static ssize_t tcm_qla2xxx_tpg_store_enable(
struct se_portal_group *se_tpg,
const char *page,
size_t count)
{
- struct se_wwn *se_wwn = se_tpg->se_tpg_wwn;
- struct tcm_qla2xxx_lport *lport = container_of(se_wwn,
- struct tcm_qla2xxx_lport, lport_wwn);
- struct scsi_qla_host *vha = lport->qla_vha;
struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
struct tcm_qla2xxx_tpg, se_tpg);
unsigned long op;
@@ -964,19 +967,28 @@
pr_err("Illegal value for tpg_enable: %lu\n", op);
return -EINVAL;
}
+ if (op) {
+ if (atomic_read(&tpg->lport_tpg_enabled))
+ return -EEXIST;
+
+ INIT_WORK(&tpg->tpg_base_work, tcm_qla2xxx_depend_tpg);
+ } else {
+ if (!atomic_read(&tpg->lport_tpg_enabled))
+ return count;
+
+ INIT_WORK(&tpg->tpg_base_work, tcm_qla2xxx_undepend_tpg);
+ }
+ init_completion(&tpg->tpg_base_comp);
+ schedule_work(&tpg->tpg_base_work);
+ wait_for_completion(&tpg->tpg_base_comp);
if (op) {
- atomic_set(&tpg->lport_tpg_enabled, 1);
- qlt_enable_vha(vha);
- } else {
- if (!vha->vha_tgt.qla_tgt) {
- pr_err("struct qla_hw_data *vha->vha_tgt.qla_tgt is NULL\n");
+ if (!atomic_read(&tpg->lport_tpg_enabled))
return -ENODEV;
- }
- atomic_set(&tpg->lport_tpg_enabled, 0);
- qlt_stop_phase1(vha->vha_tgt.qla_tgt);
+ } else {
+ if (atomic_read(&tpg->lport_tpg_enabled))
+ return -EPERM;
}
-
return count;
}
@@ -1053,11 +1065,64 @@
/*
* Clear local TPG=1 pointer for non NPIV mode.
*/
- lport->tpg_1 = NULL;
-
+ lport->tpg_1 = NULL;
kfree(tpg);
}
+static ssize_t tcm_qla2xxx_npiv_tpg_show_enable(
+ struct se_portal_group *se_tpg,
+ char *page)
+{
+ return tcm_qla2xxx_tpg_show_enable(se_tpg, page);
+}
+
+static ssize_t tcm_qla2xxx_npiv_tpg_store_enable(
+ struct se_portal_group *se_tpg,
+ const char *page,
+ size_t count)
+{
+ struct se_wwn *se_wwn = se_tpg->se_tpg_wwn;
+ struct tcm_qla2xxx_lport *lport = container_of(se_wwn,
+ struct tcm_qla2xxx_lport, lport_wwn);
+ struct scsi_qla_host *vha = lport->qla_vha;
+ struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg,
+ struct tcm_qla2xxx_tpg, se_tpg);
+ unsigned long op;
+ int rc;
+
+ rc = kstrtoul(page, 0, &op);
+ if (rc < 0) {
+ pr_err("kstrtoul() returned %d\n", rc);
+ return -EINVAL;
+ }
+ if ((op != 1) && (op != 0)) {
+ pr_err("Illegal value for tpg_enable: %lu\n", op);
+ return -EINVAL;
+ }
+ if (op) {
+ if (atomic_read(&tpg->lport_tpg_enabled))
+ return -EEXIST;
+
+ atomic_set(&tpg->lport_tpg_enabled, 1);
+ qlt_enable_vha(vha);
+ } else {
+ if (!atomic_read(&tpg->lport_tpg_enabled))
+ return count;
+
+ atomic_set(&tpg->lport_tpg_enabled, 0);
+ qlt_stop_phase1(vha->vha_tgt.qla_tgt);
+ }
+
+ return count;
+}
+
+TF_TPG_BASE_ATTR(tcm_qla2xxx_npiv, enable, S_IRUGO | S_IWUSR);
+
+static struct configfs_attribute *tcm_qla2xxx_npiv_tpg_attrs[] = {
+ &tcm_qla2xxx_npiv_tpg_enable.attr,
+ NULL,
+};
+
static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg(
struct se_wwn *wwn,
struct config_group *group,
@@ -1650,6 +1715,9 @@
struct scsi_qla_host *npiv_vha;
struct tcm_qla2xxx_lport *lport =
(struct tcm_qla2xxx_lport *)target_lport_ptr;
+ struct tcm_qla2xxx_lport *base_lport =
+ (struct tcm_qla2xxx_lport *)base_vha->vha_tgt.target_lport_ptr;
+ struct tcm_qla2xxx_tpg *base_tpg;
struct fc_vport_identifiers vport_id;
if (!qla_tgt_mode_enabled(base_vha)) {
@@ -1657,6 +1725,13 @@
return -EPERM;
}
+ if (!base_lport || !base_lport->tpg_1 ||
+ !atomic_read(&base_lport->tpg_1->lport_tpg_enabled)) {
+ pr_err("qla2xxx base_lport or tpg_1 not available\n");
+ return -EPERM;
+ }
+ base_tpg = base_lport->tpg_1;
+
memset(&vport_id, 0, sizeof(vport_id));
vport_id.port_name = npiv_wwpn;
vport_id.node_name = npiv_wwnn;
@@ -1675,7 +1750,6 @@
npiv_vha = (struct scsi_qla_host *)vport->dd_data;
npiv_vha->vha_tgt.target_lport_ptr = target_lport_ptr;
lport->qla_vha = npiv_vha;
-
scsi_host_get(npiv_vha->host);
return 0;
}
@@ -1714,8 +1788,6 @@
}
lport->lport_npiv_wwpn = npiv_wwpn;
lport->lport_npiv_wwnn = npiv_wwnn;
- tcm_qla2xxx_npiv_format_wwn(&lport->lport_npiv_name[0],
- TCM_QLA2XXX_NAMELEN, npiv_wwpn, npiv_wwnn);
sprintf(lport->lport_naa_name, "naa.%016llx", (unsigned long long) npiv_wwpn);
ret = tcm_qla2xxx_init_lport(lport);
@@ -1824,7 +1896,7 @@
static struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = {
.get_fabric_name = tcm_qla2xxx_npiv_get_fabric_name,
.get_fabric_proto_ident = tcm_qla2xxx_get_fabric_proto_ident,
- .tpg_get_wwn = tcm_qla2xxx_npiv_get_fabric_wwn,
+ .tpg_get_wwn = tcm_qla2xxx_get_fabric_wwn,
.tpg_get_tag = tcm_qla2xxx_get_tag,
.tpg_get_default_depth = tcm_qla2xxx_get_default_depth,
.tpg_get_pr_transport_id = tcm_qla2xxx_get_pr_transport_id,
@@ -1935,7 +2007,7 @@
*/
npiv_fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs;
npiv_fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs =
- tcm_qla2xxx_tpg_attrs;
+ tcm_qla2xxx_npiv_tpg_attrs;
npiv_fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
npiv_fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
npiv_fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
index 275d8b9..33aaac8 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
@@ -4,8 +4,6 @@
#define TCM_QLA2XXX_VERSION "v0.1"
/* length of ASCII WWPNs including pad */
#define TCM_QLA2XXX_NAMELEN 32
-/* lenth of ASCII NPIV 'WWPN+WWNN' including pad */
-#define TCM_QLA2XXX_NPIV_NAMELEN 66
#include "qla_target.h"
@@ -43,6 +41,9 @@
struct tcm_qla2xxx_tpg_attrib tpg_attrib;
/* Returned by tcm_qla2xxx_make_tpg() */
struct se_portal_group se_tpg;
+ /* Items for dealing with configfs_depend_item */
+ struct completion tpg_base_comp;
+ struct work_struct tpg_base_work;
};
struct tcm_qla2xxx_fc_loopid {
@@ -62,8 +63,6 @@
char lport_name[TCM_QLA2XXX_NAMELEN];
/* ASCII formatted naa WWPN for VPD page 83 etc */
char lport_naa_name[TCM_QLA2XXX_NAMELEN];
- /* ASCII formatted WWPN+WWNN for NPIV FC Target Lport */
- char lport_npiv_name[TCM_QLA2XXX_NPIV_NAMELEN];
/* map for fc_port pointers in 24-bit FC Port ID space */
struct btree_head32 lport_fcport_map;
/* vmalloc-ed memory for fc_port pointers for 16-bit FC loop ID */
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 7bd7f0d..62ec84b 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1684,7 +1684,7 @@
host_dev = scsi_get_device(shost);
if (host_dev && host_dev->dma_mask)
- bounce_limit = dma_max_pfn(host_dev) << PAGE_SHIFT;
+ bounce_limit = (u64)dma_max_pfn(host_dev) << PAGE_SHIFT;
return bounce_limit;
}
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 17d7404..9969fa1 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1419,6 +1419,9 @@
{
struct stor_mem_pools *memp = sdevice->hostdata;
+ if (!memp)
+ return;
+
mempool_destroy(memp->request_mempool);
kmem_cache_destroy(memp->request_pool);
kfree(memp);
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index ba9310b..581ee2a 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -376,10 +376,10 @@
def_tristate SPI_PXA2XX && PCI
config SPI_RSPI
- tristate "Renesas RSPI controller"
+ tristate "Renesas RSPI/QSPI controller"
depends on (SUPERH && SH_DMAE_BASE) || ARCH_SHMOBILE
help
- SPI driver for Renesas RSPI blocks.
+ SPI driver for Renesas RSPI and QSPI blocks.
config SPI_S3C24XX
tristate "Samsung S3C24XX series SPI"
diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c
index 31534b5..c3b2fb9 100644
--- a/drivers/spi/spi-ath79.c
+++ b/drivers/spi/spi-ath79.c
@@ -132,9 +132,9 @@
flags = GPIOF_DIR_OUT;
if (spi->mode & SPI_CS_HIGH)
- flags |= GPIOF_INIT_HIGH;
- else
flags |= GPIOF_INIT_LOW;
+ else
+ flags |= GPIOF_INIT_HIGH;
status = gpio_request_one(cdata->gpio, flags,
dev_name(&spi->dev));
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index b0842f7..5d7b07f 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -1455,6 +1455,14 @@
{
struct spi_master *master = dev_get_drvdata(dev);
struct atmel_spi *as = spi_master_get_devdata(master);
+ int ret;
+
+ /* Stop the queue running */
+ ret = spi_master_suspend(master);
+ if (ret) {
+ dev_warn(dev, "cannot suspend master\n");
+ return ret;
+ }
clk_disable_unprepare(as->clk);
return 0;
@@ -1464,9 +1472,16 @@
{
struct spi_master *master = dev_get_drvdata(dev);
struct atmel_spi *as = spi_master_get_devdata(master);
+ int ret;
clk_prepare_enable(as->clk);
- return 0;
+
+ /* Start the queue running */
+ ret = spi_master_resume(master);
+ if (ret)
+ dev_err(dev, "problem starting queue (%d)\n", ret);
+
+ return ret;
}
static SIMPLE_DEV_PM_OPS(atmel_spi_pm_ops, atmel_spi_suspend, atmel_spi_resume);
diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c
index cabed8f..28ae470 100644
--- a/drivers/spi/spi-coldfire-qspi.c
+++ b/drivers/spi/spi-coldfire-qspi.c
@@ -514,7 +514,8 @@
#ifdef CONFIG_PM_RUNTIME
static int mcfqspi_runtime_suspend(struct device *dev)
{
- struct mcfqspi *mcfqspi = dev_get_drvdata(dev);
+ struct spi_master *master = dev_get_drvdata(dev);
+ struct mcfqspi *mcfqspi = spi_master_get_devdata(master);
clk_disable(mcfqspi->clk);
@@ -523,7 +524,8 @@
static int mcfqspi_runtime_resume(struct device *dev)
{
- struct mcfqspi *mcfqspi = dev_get_drvdata(dev);
+ struct spi_master *master = dev_get_drvdata(dev);
+ struct mcfqspi *mcfqspi = spi_master_get_devdata(master);
clk_enable(mcfqspi->clk);
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index ec79f72..a253920 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -420,7 +420,6 @@
static int dspi_resume(struct device *dev)
{
-
struct spi_master *master = dev_get_drvdata(dev);
struct fsl_dspi *dspi = spi_master_get_devdata(master);
@@ -504,7 +503,7 @@
clk_prepare_enable(dspi->clk);
init_waitqueue_head(&dspi->waitq);
- platform_set_drvdata(pdev, dspi);
+ platform_set_drvdata(pdev, master);
ret = spi_bitbang_start(&dspi->bitbang);
if (ret != 0) {
@@ -525,7 +524,8 @@
static int dspi_remove(struct platform_device *pdev)
{
- struct fsl_dspi *dspi = platform_get_drvdata(pdev);
+ struct spi_master *master = platform_get_drvdata(pdev);
+ struct fsl_dspi *dspi = spi_master_get_devdata(master);
/* Disconnect from the SPI framework */
spi_bitbang_stop(&dspi->bitbang);
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index a5474ef..47f15d9 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -948,8 +948,8 @@
spi_bitbang_stop(&spi_imx->bitbang);
writel(0, spi_imx->base + MXC_CSPICTRL);
- clk_disable_unprepare(spi_imx->clk_ipg);
- clk_disable_unprepare(spi_imx->clk_per);
+ clk_unprepare(spi_imx->clk_ipg);
+ clk_unprepare(spi_imx->clk_per);
spi_master_put(master);
return 0;
diff --git a/drivers/spi/spi-nuc900.c b/drivers/spi/spi-nuc900.c
index 5040630..bae97ff 100644
--- a/drivers/spi/spi-nuc900.c
+++ b/drivers/spi/spi-nuc900.c
@@ -361,6 +361,8 @@
init_completion(&hw->done);
master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+ if (hw->pdata->lsb)
+ master->mode_bits |= SPI_LSB_FIRST;
master->num_chipselect = hw->pdata->num_cs;
master->bus_num = hw->pdata->bus_num;
hw->bitbang.master = hw->master;
diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c
index 2e7f38c..88eb57e 100644
--- a/drivers/spi/spi-topcliff-pch.c
+++ b/drivers/spi/spi-topcliff-pch.c
@@ -915,7 +915,7 @@
/* Set Tx DMA */
param = &dma->param_tx;
param->dma_dev = &dma_dev->dev;
- param->chan_id = data->master->bus_num * 2; /* Tx = 0, 2 */
+ param->chan_id = data->ch * 2; /* Tx = 0, 2 */;
param->tx_reg = data->io_base_addr + PCH_SPDWR;
param->width = width;
chan = dma_request_channel(mask, pch_spi_filter, param);
@@ -930,7 +930,7 @@
/* Set Rx DMA */
param = &dma->param_rx;
param->dma_dev = &dma_dev->dev;
- param->chan_id = data->master->bus_num * 2 + 1; /* Rx = Tx + 1 */
+ param->chan_id = data->ch * 2 + 1; /* Rx = Tx + 1 */;
param->rx_reg = data->io_base_addr + PCH_SPDRR;
param->width = width;
chan = dma_request_channel(mask, pch_spi_filter, param);
@@ -1452,6 +1452,11 @@
pch_spi_set_master_mode(master);
+ if (use_dma) {
+ dev_info(&plat_dev->dev, "Use DMA for data transfers\n");
+ pch_alloc_dma_buf(board_dat, data);
+ }
+
ret = spi_register_master(master);
if (ret != 0) {
dev_err(&plat_dev->dev,
@@ -1459,14 +1464,10 @@
goto err_spi_register_master;
}
- if (use_dma) {
- dev_info(&plat_dev->dev, "Use DMA for data transfers\n");
- pch_alloc_dma_buf(board_dat, data);
- }
-
return 0;
err_spi_register_master:
+ pch_free_dma_buf(board_dat, data);
free_irq(board_dat->pdev->irq, data);
err_request_irq:
pch_spi_free_resources(board_dat, data);
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 23756b0..d0b28bb 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -755,9 +755,7 @@
ret = master->transfer_one_message(master, master->cur_msg);
if (ret) {
dev_err(&master->dev,
- "failed to transfer one message from queue: %d\n", ret);
- master->cur_msg->status = ret;
- spi_finalize_current_message(master);
+ "failed to transfer one message from queue\n");
return;
}
}
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 23948f1..713a972 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -295,21 +295,29 @@
/* If size is not set, or set to 0, always return EOF. */
if (asma->size == 0)
- goto out;
+ goto out_unlock;
if (!asma->file) {
ret = -EBADF;
- goto out;
+ goto out_unlock;
}
+ mutex_unlock(&ashmem_mutex);
+
+ /*
+ * asma and asma->file are used outside the lock here. We assume
+ * once asma->file is set it will never be changed, and will not
+ * be destroyed until all references to the file are dropped and
+ * ashmem_release is called.
+ */
ret = asma->file->f_op->read(asma->file, buf, len, pos);
- if (ret < 0)
- goto out;
+ if (ret >= 0) {
+ /** Update backing file pos, since f_ops->read() doesn't */
+ asma->file->f_pos = *pos;
+ }
+ return ret;
- /** Update backing file pos, since f_ops->read() doesn't */
- asma->file->f_pos = *pos;
-
-out:
+out_unlock:
mutex_unlock(&ashmem_mutex);
return ret;
}
@@ -498,6 +506,7 @@
static int set_name(struct ashmem_area *asma, void __user *name)
{
+ int len;
int ret = 0;
char local_name[ASHMEM_NAME_LEN];
@@ -510,21 +519,19 @@
* variable that does not need protection and later copy the local
* variable to the structure member with lock held.
*/
- if (copy_from_user(local_name, name, ASHMEM_NAME_LEN))
- return -EFAULT;
-
+ len = strncpy_from_user(local_name, name, ASHMEM_NAME_LEN);
+ if (len < 0)
+ return len;
+ if (len == ASHMEM_NAME_LEN)
+ local_name[ASHMEM_NAME_LEN - 1] = '\0';
mutex_lock(&ashmem_mutex);
/* cannot change an existing mapping's name */
- if (unlikely(asma->file)) {
+ if (unlikely(asma->file))
ret = -EINVAL;
- goto out;
- }
- memcpy(asma->name + ASHMEM_NAME_PREFIX_LEN,
- local_name, ASHMEM_NAME_LEN);
- asma->name[ASHMEM_FULL_NAME_LEN-1] = '\0';
-out:
- mutex_unlock(&ashmem_mutex);
+ else
+ strcpy(asma->name + ASHMEM_NAME_PREFIX_LEN, local_name);
+ mutex_unlock(&ashmem_mutex);
return ret;
}
diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c
index eaec1da..1432d95 100644
--- a/drivers/staging/android/binder.c
+++ b/drivers/staging/android/binder.c
@@ -2904,7 +2904,7 @@
refs++;
if (!ref->death)
- goto out;
+ continue;
death++;
@@ -2917,7 +2917,6 @@
BUG();
}
-out:
binder_debug(BINDER_DEBUG_DEAD_BINDER,
"node %d now dead, refs %d, death %d\n",
node->debug_id, refs, death);
diff --git a/drivers/staging/android/ion/compat_ion.c b/drivers/staging/android/ion/compat_ion.c
index af6cd37..ee3a738 100644
--- a/drivers/staging/android/ion/compat_ion.c
+++ b/drivers/staging/android/ion/compat_ion.c
@@ -35,9 +35,14 @@
compat_ulong_t arg;
};
+struct compat_ion_handle_data {
+ compat_int_t handle;
+};
+
#define COMPAT_ION_IOC_ALLOC _IOWR(ION_IOC_MAGIC, 0, \
struct compat_ion_allocation_data)
-#define COMPAT_ION_IOC_FREE _IOWR(ION_IOC_MAGIC, 1, struct ion_handle_data)
+#define COMPAT_ION_IOC_FREE _IOWR(ION_IOC_MAGIC, 1, \
+ struct compat_ion_handle_data)
#define COMPAT_ION_IOC_CUSTOM _IOWR(ION_IOC_MAGIC, 6, \
struct compat_ion_custom_data)
@@ -64,6 +69,19 @@
return err;
}
+static int compat_get_ion_handle_data(
+ struct compat_ion_handle_data __user *data32,
+ struct ion_handle_data __user *data)
+{
+ compat_int_t i;
+ int err;
+
+ err = get_user(i, &data32->handle);
+ err |= put_user(i, &data->handle);
+
+ return err;
+}
+
static int compat_put_ion_allocation_data(
struct compat_ion_allocation_data __user *data32,
struct ion_allocation_data __user *data)
@@ -132,8 +150,8 @@
}
case COMPAT_ION_IOC_FREE:
{
- struct compat_ion_allocation_data __user *data32;
- struct ion_allocation_data __user *data;
+ struct compat_ion_handle_data __user *data32;
+ struct ion_handle_data __user *data;
int err;
data32 = compat_ptr(arg);
@@ -141,7 +159,7 @@
if (data == NULL)
return -EFAULT;
- err = compat_get_ion_allocation_data(data32, data);
+ err = compat_get_ion_handle_data(data32, data);
if (err)
return err;
diff --git a/drivers/staging/android/ion/ion_dummy_driver.c b/drivers/staging/android/ion/ion_dummy_driver.c
index 55b2002..01cdc8a 100644
--- a/drivers/staging/android/ion/ion_dummy_driver.c
+++ b/drivers/staging/android/ion/ion_dummy_driver.c
@@ -17,9 +17,11 @@
#include <linux/err.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
+#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/sizes.h>
+#include <linux/io.h>
#include "ion.h"
#include "ion_priv.h"
@@ -57,7 +59,7 @@
};
struct ion_platform_data dummy_ion_pdata = {
- .nr = 4,
+ .nr = ARRAY_SIZE(dummy_heaps),
.heaps = dummy_heaps,
};
@@ -69,7 +71,7 @@
heaps = kzalloc(sizeof(struct ion_heap *) * dummy_ion_pdata.nr,
GFP_KERNEL);
if (!heaps)
- return PTR_ERR(heaps);
+ return -ENOMEM;
/* Allocate a dummy carveout heap */
@@ -128,6 +130,7 @@
}
return err;
}
+device_initcall(ion_dummy_init);
static void __exit ion_dummy_exit(void)
{
@@ -152,7 +155,4 @@
return;
}
-
-module_init(ion_dummy_init);
-module_exit(ion_dummy_exit);
-
+__exitcall(ion_dummy_exit);
diff --git a/drivers/staging/android/ion/ion_heap.c b/drivers/staging/android/ion/ion_heap.c
index 296c74f..37e64d5 100644
--- a/drivers/staging/android/ion/ion_heap.c
+++ b/drivers/staging/android/ion/ion_heap.c
@@ -243,12 +243,12 @@
init_waitqueue_head(&heap->waitqueue);
heap->task = kthread_run(ion_heap_deferred_free, heap,
"%s", heap->name);
- sched_setscheduler(heap->task, SCHED_IDLE, ¶m);
if (IS_ERR(heap->task)) {
pr_err("%s: creating thread for deferred free failed\n",
__func__);
return PTR_RET(heap->task);
}
+ sched_setscheduler(heap->task, SCHED_IDLE, ¶m);
return 0;
}
diff --git a/drivers/staging/android/ion/ion_priv.h b/drivers/staging/android/ion/ion_priv.h
index d986739..fc2e4fc 100644
--- a/drivers/staging/android/ion/ion_priv.h
+++ b/drivers/staging/android/ion/ion_priv.h
@@ -17,6 +17,7 @@
#ifndef _ION_PRIV_H
#define _ION_PRIV_H
+#include <linux/device.h>
#include <linux/dma-direction.h>
#include <linux/kref.h>
#include <linux/mm_types.h>
diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c
index 7f07291..9849f39 100644
--- a/drivers/staging/android/ion/ion_system_heap.c
+++ b/drivers/staging/android/ion/ion_system_heap.c
@@ -124,6 +124,7 @@
info->page = page;
info->order = orders[i];
+ INIT_LIST_HEAD(&info->list);
return info;
}
kfree(info);
@@ -145,12 +146,15 @@
struct list_head pages;
struct page_info *info, *tmp_info;
int i = 0;
- long size_remaining = PAGE_ALIGN(size);
+ unsigned long size_remaining = PAGE_ALIGN(size);
unsigned int max_order = orders[0];
if (align > PAGE_SIZE)
return -EINVAL;
+ if (size / PAGE_SIZE > totalram_pages / 2)
+ return -ENOMEM;
+
INIT_LIST_HEAD(&pages);
while (size_remaining > 0) {
info = alloc_largest_available(sys_heap, buffer, size_remaining,
diff --git a/drivers/staging/android/sw_sync.h b/drivers/staging/android/sw_sync.h
index 585040b..5aaf71d 100644
--- a/drivers/staging/android/sw_sync.h
+++ b/drivers/staging/android/sw_sync.h
@@ -35,10 +35,27 @@
u32 value;
};
+#if IS_ENABLED(CONFIG_SW_SYNC)
struct sw_sync_timeline *sw_sync_timeline_create(const char *name);
void sw_sync_timeline_inc(struct sw_sync_timeline *obj, u32 inc);
struct sync_pt *sw_sync_pt_create(struct sw_sync_timeline *obj, u32 value);
+#else
+static inline struct sw_sync_timeline *sw_sync_timeline_create(const char *name)
+{
+ return NULL;
+}
+
+static inline void sw_sync_timeline_inc(struct sw_sync_timeline *obj, u32 inc)
+{
+}
+
+static inline struct sync_pt *sw_sync_pt_create(struct sw_sync_timeline *obj,
+ u32 value)
+{
+ return NULL;
+}
+#endif /* IS_ENABLED(CONFIG_SW_SYNC) */
#endif /* __KERNEL __ */
diff --git a/drivers/staging/android/sync.c b/drivers/staging/android/sync.c
index 38e5d3b..3d05f662 100644
--- a/drivers/staging/android/sync.c
+++ b/drivers/staging/android/sync.c
@@ -79,27 +79,27 @@
container_of(kref, struct sync_timeline, kref);
unsigned long flags;
- if (obj->ops->release_obj)
- obj->ops->release_obj(obj);
-
spin_lock_irqsave(&sync_timeline_list_lock, flags);
list_del(&obj->sync_timeline_list);
spin_unlock_irqrestore(&sync_timeline_list_lock, flags);
+ if (obj->ops->release_obj)
+ obj->ops->release_obj(obj);
+
kfree(obj);
}
void sync_timeline_destroy(struct sync_timeline *obj)
{
obj->destroyed = true;
+ smp_wmb();
/*
- * If this is not the last reference, signal any children
- * that their parent is going away.
+ * signal any children that their parent is going away.
*/
+ sync_timeline_signal(obj);
- if (!kref_put(&obj->kref, sync_timeline_free))
- sync_timeline_signal(obj);
+ kref_put(&obj->kref, sync_timeline_free);
}
EXPORT_SYMBOL(sync_timeline_destroy);
diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c
index 8dfdd27..95a2358 100644
--- a/drivers/staging/bcm/Bcmnet.c
+++ b/drivers/staging/bcm/Bcmnet.c
@@ -40,7 +40,7 @@
}
static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv, select_queue_fallback_t fallback)
{
return ClassifyPacket(netdev_priv(dev), skb);
}
diff --git a/drivers/staging/comedi/drivers.c b/drivers/staging/comedi/drivers.c
index 2460803..5b15033 100644
--- a/drivers/staging/comedi/drivers.c
+++ b/drivers/staging/comedi/drivers.c
@@ -616,8 +616,6 @@
ret = driver->auto_attach(dev, context);
if (ret >= 0)
ret = comedi_device_postconfig(dev);
- if (ret < 0)
- comedi_device_detach(dev);
mutex_unlock(&dev->mutex);
if (ret < 0) {
diff --git a/drivers/staging/comedi/drivers/adv_pci1710.c b/drivers/staging/comedi/drivers/adv_pci1710.c
index 593676c..d9ad2c0 100644
--- a/drivers/staging/comedi/drivers/adv_pci1710.c
+++ b/drivers/staging/comedi/drivers/adv_pci1710.c
@@ -494,6 +494,7 @@
struct comedi_insn *insn, unsigned int *data)
{
struct pci1710_private *devpriv = dev->private;
+ unsigned int val;
int n, chan, range, ofs;
chan = CR_CHAN(insn->chanspec);
@@ -509,11 +510,14 @@
outw(devpriv->da_ranges, dev->iobase + PCI171x_DAREF);
ofs = PCI171x_DA1;
}
+ val = devpriv->ao_data[chan];
- for (n = 0; n < insn->n; n++)
- outw(data[n], dev->iobase + ofs);
+ for (n = 0; n < insn->n; n++) {
+ val = data[n];
+ outw(val, dev->iobase + ofs);
+ }
- devpriv->ao_data[chan] = data[n];
+ devpriv->ao_data[chan] = val;
return n;
@@ -679,6 +683,7 @@
struct comedi_insn *insn, unsigned int *data)
{
struct pci1710_private *devpriv = dev->private;
+ unsigned int val;
int n, rangereg, chan;
chan = CR_CHAN(insn->chanspec);
@@ -688,13 +693,15 @@
outb(rangereg, dev->iobase + PCI1720_RANGE);
devpriv->da_ranges = rangereg;
}
+ val = devpriv->ao_data[chan];
for (n = 0; n < insn->n; n++) {
- outw(data[n], dev->iobase + PCI1720_DA0 + (chan << 1));
+ val = data[n];
+ outw(val, dev->iobase + PCI1720_DA0 + (chan << 1));
outb(0, dev->iobase + PCI1720_SYNCOUT); /* update outputs */
}
- devpriv->ao_data[chan] = data[n];
+ devpriv->ao_data[chan] = val;
return n;
}
diff --git a/drivers/staging/comedi/drivers/usbduxsigma.c b/drivers/staging/comedi/drivers/usbduxsigma.c
index 3beeb12..88c60b6 100644
--- a/drivers/staging/comedi/drivers/usbduxsigma.c
+++ b/drivers/staging/comedi/drivers/usbduxsigma.c
@@ -48,6 +48,7 @@
#include <linux/usb.h>
#include <linux/fcntl.h>
#include <linux/compiler.h>
+#include <asm/unaligned.h>
#include "comedi_fc.h"
#include "../comedidev.h"
@@ -792,7 +793,8 @@
}
/* 32 bits big endian from the A/D converter */
- val = be32_to_cpu(*((uint32_t *)((devpriv->insn_buf) + 1)));
+ val = be32_to_cpu(get_unaligned((uint32_t
+ *)(devpriv->insn_buf + 1)));
val &= 0x00ffffff; /* strip status byte */
val ^= 0x00800000; /* convert to unsigned */
@@ -1357,7 +1359,7 @@
return ret;
/* 32 bits big endian from the A/D converter */
- val = be32_to_cpu(*((uint32_t *)((devpriv->insn_buf)+1)));
+ val = be32_to_cpu(get_unaligned((uint32_t *)(devpriv->insn_buf + 1)));
val &= 0x00ffffff; /* strip status byte */
val ^= 0x00800000; /* convert to unsigned */
diff --git a/drivers/staging/cxt1e1/linux.c b/drivers/staging/cxt1e1/linux.c
index 4a08e16..79206cb 100644
--- a/drivers/staging/cxt1e1/linux.c
+++ b/drivers/staging/cxt1e1/linux.c
@@ -866,6 +866,8 @@
_IOC_SIZE (iocmd));
#endif
iolen = _IOC_SIZE (iocmd);
+ if (iolen > sizeof(arg))
+ return -EFAULT;
data = ifr->ifr_data + sizeof (iocmd);
if (copy_from_user (&arg, data, iolen))
return -EFAULT;
diff --git a/drivers/staging/dgrp/dgrp_net_ops.c b/drivers/staging/dgrp/dgrp_net_ops.c
index 1f61b89..33ac7fb 100644
--- a/drivers/staging/dgrp/dgrp_net_ops.c
+++ b/drivers/staging/dgrp/dgrp_net_ops.c
@@ -2232,177 +2232,6 @@
return rtn;
}
-/*
- * Common Packet Handling code
- */
-
-static void handle_data_in_packet(struct nd_struct *nd, struct ch_struct *ch,
- long dlen, long plen, int n1, u8 *dbuf)
-{
- char *error;
- long n;
- long remain;
- u8 *buf;
- u8 *b;
-
- remain = nd->nd_remain;
- nd->nd_tx_work = 1;
-
- /*
- * Otherwise data should appear only when we are
- * in the CS_READY state.
- */
-
- if (ch->ch_state < CS_READY) {
- error = "Data received before RWIN established";
- nd->nd_remain = 0;
- nd->nd_state = NS_SEND_ERROR;
- nd->nd_error = error;
- }
-
- /*
- * Assure that the data received is within the
- * allowable window.
- */
-
- n = (ch->ch_s_rwin - ch->ch_s_rin) & 0xffff;
-
- if (dlen > n) {
- error = "Receive data overrun";
- nd->nd_remain = 0;
- nd->nd_state = NS_SEND_ERROR;
- nd->nd_error = error;
- }
-
- /*
- * If we received 3 or less characters,
- * assume it is a human typing, and set RTIME
- * to 10 milliseconds.
- *
- * If we receive 10 or more characters,
- * assume its not a human typing, and set RTIME
- * to 100 milliseconds.
- */
-
- if (ch->ch_edelay != DGRP_RTIME) {
- if (ch->ch_rtime != ch->ch_edelay) {
- ch->ch_rtime = ch->ch_edelay;
- ch->ch_flag |= CH_PARAM;
- }
- } else if (dlen <= 3) {
- if (ch->ch_rtime != 10) {
- ch->ch_rtime = 10;
- ch->ch_flag |= CH_PARAM;
- }
- } else {
- if (ch->ch_rtime != DGRP_RTIME) {
- ch->ch_rtime = DGRP_RTIME;
- ch->ch_flag |= CH_PARAM;
- }
- }
-
- /*
- * If a portion of the packet is outside the
- * buffer, shorten the effective length of the
- * data packet to be the amount of data received.
- */
-
- if (remain < plen)
- dlen -= plen - remain;
-
- /*
- * Detect if receive flush is now complete.
- */
-
- if ((ch->ch_flag & CH_RX_FLUSH) != 0 &&
- ((ch->ch_flush_seq - nd->nd_seq_out) & SEQ_MASK) >=
- ((nd->nd_seq_in - nd->nd_seq_out) & SEQ_MASK)) {
- ch->ch_flag &= ~CH_RX_FLUSH;
- }
-
- /*
- * If we are ready to receive, move the data into
- * the receive buffer.
- */
-
- ch->ch_s_rin = (ch->ch_s_rin + dlen) & 0xffff;
-
- if (ch->ch_state == CS_READY &&
- (ch->ch_tun.un_open_count != 0) &&
- (ch->ch_tun.un_flag & UN_CLOSING) == 0 &&
- (ch->ch_cflag & CF_CREAD) != 0 &&
- (ch->ch_flag & (CH_BAUD0 | CH_RX_FLUSH)) == 0 &&
- (ch->ch_send & RR_RX_FLUSH) == 0) {
-
- if (ch->ch_rin + dlen >= RBUF_MAX) {
- n = RBUF_MAX - ch->ch_rin;
-
- memcpy(ch->ch_rbuf + ch->ch_rin, dbuf, n);
-
- ch->ch_rin = 0;
- dbuf += n;
- dlen -= n;
- }
-
- memcpy(ch->ch_rbuf + ch->ch_rin, dbuf, dlen);
-
- ch->ch_rin += dlen;
-
-
- /*
- * If we are not in fastcook mode, or
- * if there is a fastcook thread
- * waiting for data, send the data to
- * the line discipline.
- */
-
- if ((ch->ch_flag & CH_FAST_READ) == 0 ||
- ch->ch_inwait != 0) {
- dgrp_input(ch);
- }
-
- /*
- * If there is a read thread waiting
- * in select, and we are in fastcook
- * mode, wake him up.
- */
-
- if (waitqueue_active(&ch->ch_tun.un_tty->read_wait) &&
- (ch->ch_flag & CH_FAST_READ) != 0)
- wake_up_interruptible(&ch->ch_tun.un_tty->read_wait);
-
- /*
- * Wake any thread waiting in the
- * fastcook loop.
- */
-
- if ((ch->ch_flag & CH_INPUT) != 0) {
- ch->ch_flag &= ~CH_INPUT;
- wake_up_interruptible(&ch->ch_flag_wait);
- }
- }
-
- /*
- * Fabricate and insert a data packet header to
- * preced the remaining data when it comes in.
- */
-
- if (remain < plen) {
- dlen = plen - remain;
- b = buf;
-
- b[0] = 0x90 + n1;
- put_unaligned_be16(dlen, b + 1);
-
- remain = 3;
- if (remain > 0 && b != buf)
- memcpy(buf, b, remain);
-
- nd->nd_remain = remain;
- return;
- }
-}
-
/**
* dgrp_receive() -- decode data packets received from the remote PortServer.
* @nd: pointer to a node structure
@@ -2477,8 +2306,7 @@
plen = dlen + 1;
dbuf = b + 1;
- handle_data_in_packet(nd, ch, dlen, plen, n1, dbuf);
- break;
+ goto data;
/*
* Process 2-byte header data packet.
@@ -2492,8 +2320,7 @@
plen = dlen + 2;
dbuf = b + 2;
- handle_data_in_packet(nd, ch, dlen, plen, n1, dbuf);
- break;
+ goto data;
/*
* Process 3-byte header data packet.
@@ -2508,6 +2335,159 @@
dbuf = b + 3;
+ /*
+ * Common packet handling code.
+ */
+
+data:
+ nd->nd_tx_work = 1;
+
+ /*
+ * Otherwise data should appear only when we are
+ * in the CS_READY state.
+ */
+
+ if (ch->ch_state < CS_READY) {
+ error = "Data received before RWIN established";
+ goto prot_error;
+ }
+
+ /*
+ * Assure that the data received is within the
+ * allowable window.
+ */
+
+ n = (ch->ch_s_rwin - ch->ch_s_rin) & 0xffff;
+
+ if (dlen > n) {
+ error = "Receive data overrun";
+ goto prot_error;
+ }
+
+ /*
+ * If we received 3 or less characters,
+ * assume it is a human typing, and set RTIME
+ * to 10 milliseconds.
+ *
+ * If we receive 10 or more characters,
+ * assume its not a human typing, and set RTIME
+ * to 100 milliseconds.
+ */
+
+ if (ch->ch_edelay != DGRP_RTIME) {
+ if (ch->ch_rtime != ch->ch_edelay) {
+ ch->ch_rtime = ch->ch_edelay;
+ ch->ch_flag |= CH_PARAM;
+ }
+ } else if (dlen <= 3) {
+ if (ch->ch_rtime != 10) {
+ ch->ch_rtime = 10;
+ ch->ch_flag |= CH_PARAM;
+ }
+ } else {
+ if (ch->ch_rtime != DGRP_RTIME) {
+ ch->ch_rtime = DGRP_RTIME;
+ ch->ch_flag |= CH_PARAM;
+ }
+ }
+
+ /*
+ * If a portion of the packet is outside the
+ * buffer, shorten the effective length of the
+ * data packet to be the amount of data received.
+ */
+
+ if (remain < plen)
+ dlen -= plen - remain;
+
+ /*
+ * Detect if receive flush is now complete.
+ */
+
+ if ((ch->ch_flag & CH_RX_FLUSH) != 0 &&
+ ((ch->ch_flush_seq - nd->nd_seq_out) & SEQ_MASK) >=
+ ((nd->nd_seq_in - nd->nd_seq_out) & SEQ_MASK)) {
+ ch->ch_flag &= ~CH_RX_FLUSH;
+ }
+
+ /*
+ * If we are ready to receive, move the data into
+ * the receive buffer.
+ */
+
+ ch->ch_s_rin = (ch->ch_s_rin + dlen) & 0xffff;
+
+ if (ch->ch_state == CS_READY &&
+ (ch->ch_tun.un_open_count != 0) &&
+ (ch->ch_tun.un_flag & UN_CLOSING) == 0 &&
+ (ch->ch_cflag & CF_CREAD) != 0 &&
+ (ch->ch_flag & (CH_BAUD0 | CH_RX_FLUSH)) == 0 &&
+ (ch->ch_send & RR_RX_FLUSH) == 0) {
+
+ if (ch->ch_rin + dlen >= RBUF_MAX) {
+ n = RBUF_MAX - ch->ch_rin;
+
+ memcpy(ch->ch_rbuf + ch->ch_rin, dbuf, n);
+
+ ch->ch_rin = 0;
+ dbuf += n;
+ dlen -= n;
+ }
+
+ memcpy(ch->ch_rbuf + ch->ch_rin, dbuf, dlen);
+
+ ch->ch_rin += dlen;
+
+
+ /*
+ * If we are not in fastcook mode, or
+ * if there is a fastcook thread
+ * waiting for data, send the data to
+ * the line discipline.
+ */
+
+ if ((ch->ch_flag & CH_FAST_READ) == 0 ||
+ ch->ch_inwait != 0) {
+ dgrp_input(ch);
+ }
+
+ /*
+ * If there is a read thread waiting
+ * in select, and we are in fastcook
+ * mode, wake him up.
+ */
+
+ if (waitqueue_active(&ch->ch_tun.un_tty->read_wait) &&
+ (ch->ch_flag & CH_FAST_READ) != 0)
+ wake_up_interruptible(&ch->ch_tun.un_tty->read_wait);
+
+ /*
+ * Wake any thread waiting in the
+ * fastcook loop.
+ */
+
+ if ((ch->ch_flag & CH_INPUT) != 0) {
+ ch->ch_flag &= ~CH_INPUT;
+
+ wake_up_interruptible(&ch->ch_flag_wait);
+ }
+ }
+
+ /*
+ * Fabricate and insert a data packet header to
+ * preced the remaining data when it comes in.
+ */
+
+ if (remain < plen) {
+ dlen = plen - remain;
+ b = buf;
+
+ b[0] = 0x90 + n1;
+ put_unaligned_be16(dlen, b + 1);
+
+ remain = 3;
+ goto done;
+ }
break;
/*
diff --git a/drivers/staging/gdm72xx/gdm_usb.c b/drivers/staging/gdm72xx/gdm_usb.c
index f8788bf..cdeffe7 100644
--- a/drivers/staging/gdm72xx/gdm_usb.c
+++ b/drivers/staging/gdm72xx/gdm_usb.c
@@ -635,11 +635,14 @@
#endif /* CONFIG_WIMAX_GDM72XX_USB_PM */
ret = register_wimax_device(phy_dev, &intf->dev);
+ if (ret)
+ release_usb(udev);
out:
if (ret) {
kfree(phy_dev);
kfree(udev);
+ usb_put_dev(usbdev);
} else {
usb_set_intfdata(intf, phy_dev);
}
diff --git a/drivers/staging/iio/Documentation/iio_utils.h b/drivers/staging/iio/Documentation/iio_utils.h
index 35154d6..c9fedb7 100644
--- a/drivers/staging/iio/Documentation/iio_utils.h
+++ b/drivers/staging/iio/Documentation/iio_utils.h
@@ -77,7 +77,6 @@
uint64_t mask;
unsigned be;
unsigned is_signed;
- unsigned enabled;
unsigned location;
};
@@ -335,6 +334,7 @@
while (ent = readdir(dp), ent != NULL) {
if (strcmp(ent->d_name + strlen(ent->d_name) - strlen("_en"),
"_en") == 0) {
+ int current_enabled = 0;
current = &(*ci_array)[count++];
ret = asprintf(&filename,
"%s/%s", scan_el_dir, ent->d_name);
@@ -350,10 +350,10 @@
ret = -errno;
goto error_cleanup_array;
}
- fscanf(sysfsfp, "%u", ¤t->enabled);
+ fscanf(sysfsfp, "%u", ¤t_enabled);
fclose(sysfsfp);
- if (!current->enabled) {
+ if (!current_enabled) {
free(filename);
count--;
continue;
diff --git a/drivers/staging/iio/adc/ad799x_core.c b/drivers/staging/iio/adc/ad799x_core.c
index 5ea3641..5708ffc 100644
--- a/drivers/staging/iio/adc/ad799x_core.c
+++ b/drivers/staging/iio/adc/ad799x_core.c
@@ -393,7 +393,7 @@
}, {
.type = IIO_EV_TYPE_THRESH,
.dir = IIO_EV_DIR_FALLING,
- .mask_separate = BIT(IIO_EV_INFO_VALUE),
+ .mask_separate = BIT(IIO_EV_INFO_VALUE) |
BIT(IIO_EV_INFO_ENABLE),
}, {
.type = IIO_EV_TYPE_THRESH,
@@ -409,7 +409,13 @@
.info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \
.scan_index = (_index), \
- .scan_type = IIO_ST('u', _realbits, 16, 12 - (_realbits)), \
+ .scan_type = { \
+ .sign = 'u', \
+ .realbits = (_realbits), \
+ .storagebits = 16, \
+ .shift = 12 - (_realbits), \
+ .endianness = IIO_BE, \
+ }, \
.event_spec = _ev_spec, \
.num_event_specs = _num_ev_spec, \
}
@@ -588,7 +594,8 @@
return 0;
error_free_irq:
- free_irq(client->irq, indio_dev);
+ if (client->irq > 0)
+ free_irq(client->irq, indio_dev);
error_cleanup_ring:
ad799x_ring_cleanup(indio_dev);
error_disable_reg:
diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c
index df71669..514844e 100644
--- a/drivers/staging/iio/adc/mxs-lradc.c
+++ b/drivers/staging/iio/adc/mxs-lradc.c
@@ -757,6 +757,7 @@
}
/* if it is released, wait for the next touch via IRQ */
+ lradc->cur_plate = LRADC_TOUCH;
mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ, LRADC_CTRL1);
mxs_lradc_reg_set(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, LRADC_CTRL1);
}
@@ -1035,8 +1036,6 @@
SHOW_SCALE_AVAILABLE_ATTR(5);
SHOW_SCALE_AVAILABLE_ATTR(6);
SHOW_SCALE_AVAILABLE_ATTR(7);
-SHOW_SCALE_AVAILABLE_ATTR(8);
-SHOW_SCALE_AVAILABLE_ATTR(9);
SHOW_SCALE_AVAILABLE_ATTR(10);
SHOW_SCALE_AVAILABLE_ATTR(11);
SHOW_SCALE_AVAILABLE_ATTR(12);
@@ -1053,8 +1052,6 @@
&iio_dev_attr_in_voltage5_scale_available.dev_attr.attr,
&iio_dev_attr_in_voltage6_scale_available.dev_attr.attr,
&iio_dev_attr_in_voltage7_scale_available.dev_attr.attr,
- &iio_dev_attr_in_voltage8_scale_available.dev_attr.attr,
- &iio_dev_attr_in_voltage9_scale_available.dev_attr.attr,
&iio_dev_attr_in_voltage10_scale_available.dev_attr.attr,
&iio_dev_attr_in_voltage11_scale_available.dev_attr.attr,
&iio_dev_attr_in_voltage12_scale_available.dev_attr.attr,
@@ -1613,7 +1610,7 @@
* of the array.
*/
scale_uv = ((u64)lradc->vref_mv[i] * 100000000) >>
- (iio->channels[i].scan_type.realbits - s);
+ (LRADC_RESOLUTION - s);
lradc->scale_avail[i][s].nano =
do_div(scale_uv, 100000000) * 10;
lradc->scale_avail[i][s].integer = scale_uv;
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index 0a4298b..2b96665 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -629,7 +629,7 @@
struct iio_buffer *buffer;
buffer = iio_kfifo_allocate(indio_dev);
- if (buffer)
+ if (!buffer)
return -ENOMEM;
iio_device_attach_buffer(indio_dev, buffer);
diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c
index 09ef5fb8..236ed66 100644
--- a/drivers/staging/imx-drm/imx-drm-core.c
+++ b/drivers/staging/imx-drm/imx-drm-core.c
@@ -88,9 +88,9 @@
imx_drm_device_put();
- drm_vblank_cleanup(imxdrm->drm);
- drm_kms_helper_poll_fini(imxdrm->drm);
- drm_mode_config_cleanup(imxdrm->drm);
+ drm_vblank_cleanup(drm);
+ drm_kms_helper_poll_fini(drm);
+ drm_mode_config_cleanup(drm);
return 0;
}
@@ -142,19 +142,19 @@
int imx_drm_crtc_vblank_get(struct imx_drm_crtc *imx_drm_crtc)
{
- return drm_vblank_get(imx_drm_crtc->imxdrm->drm, imx_drm_crtc->pipe);
+ return drm_vblank_get(imx_drm_crtc->crtc->dev, imx_drm_crtc->pipe);
}
EXPORT_SYMBOL_GPL(imx_drm_crtc_vblank_get);
void imx_drm_crtc_vblank_put(struct imx_drm_crtc *imx_drm_crtc)
{
- drm_vblank_put(imx_drm_crtc->imxdrm->drm, imx_drm_crtc->pipe);
+ drm_vblank_put(imx_drm_crtc->crtc->dev, imx_drm_crtc->pipe);
}
EXPORT_SYMBOL_GPL(imx_drm_crtc_vblank_put);
void imx_drm_handle_vblank(struct imx_drm_crtc *imx_drm_crtc)
{
- drm_handle_vblank(imx_drm_crtc->imxdrm->drm, imx_drm_crtc->pipe);
+ drm_handle_vblank(imx_drm_crtc->crtc->dev, imx_drm_crtc->pipe);
}
EXPORT_SYMBOL_GPL(imx_drm_handle_vblank);
@@ -370,29 +370,6 @@
}
/*
- * register a crtc to the drm core
- */
-static int imx_drm_crtc_register(struct imx_drm_crtc *imx_drm_crtc)
-{
- struct imx_drm_device *imxdrm = __imx_drm_device();
- int ret;
-
- ret = drm_mode_crtc_set_gamma_size(imx_drm_crtc->crtc, 256);
- if (ret)
- return ret;
-
- drm_crtc_helper_add(imx_drm_crtc->crtc,
- imx_drm_crtc->imx_drm_helper_funcs.crtc_helper_funcs);
-
- drm_crtc_init(imxdrm->drm, imx_drm_crtc->crtc,
- imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs);
-
- drm_mode_group_reinit(imxdrm->drm);
-
- return 0;
-}
-
-/*
* Called by the CRTC driver when all CRTCs are registered. This
* puts all the pieces together and initializes the driver.
* Once this is called no more CRTCs can be registered since
@@ -424,15 +401,15 @@
mutex_lock(&imxdrm->mutex);
- drm_kms_helper_poll_init(imxdrm->drm);
+ drm_kms_helper_poll_init(drm);
/* setup the grouping for the legacy output */
- ret = drm_mode_group_init_legacy_group(imxdrm->drm,
- &imxdrm->drm->primary->mode_group);
+ ret = drm_mode_group_init_legacy_group(drm,
+ &drm->primary->mode_group);
if (ret)
goto err_kms;
- ret = drm_vblank_init(imxdrm->drm, MAX_CRTC);
+ ret = drm_vblank_init(drm, MAX_CRTC);
if (ret)
goto err_kms;
@@ -441,7 +418,7 @@
* by drm timer once a current process gives up ownership of
* vblank event.(after drm_vblank_put function is called)
*/
- imxdrm->drm->vblank_disable_allowed = true;
+ drm->vblank_disable_allowed = true;
if (!imx_drm_device_get()) {
ret = -EINVAL;
@@ -536,10 +513,18 @@
*new_crtc = imx_drm_crtc;
- ret = imx_drm_crtc_register(imx_drm_crtc);
+ ret = drm_mode_crtc_set_gamma_size(imx_drm_crtc->crtc, 256);
if (ret)
goto err_register;
+ drm_crtc_helper_add(crtc,
+ imx_drm_crtc->imx_drm_helper_funcs.crtc_helper_funcs);
+
+ drm_crtc_init(imxdrm->drm, crtc,
+ imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs);
+
+ drm_mode_group_reinit(imxdrm->drm);
+
imx_drm_update_possible_crtcs();
mutex_unlock(&imxdrm->mutex);
diff --git a/drivers/staging/imx-drm/imx-hdmi.c b/drivers/staging/imx-drm/imx-hdmi.c
index f3a1f5e..62ce0e8 100644
--- a/drivers/staging/imx-drm/imx-hdmi.c
+++ b/drivers/staging/imx-drm/imx-hdmi.c
@@ -16,6 +16,7 @@
#include <linux/delay.h>
#include <linux/err.h>
#include <linux/clk.h>
+#include <linux/hdmi.h>
#include <linux/regmap.h>
#include <linux/mfd/syscon.h>
#include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
@@ -52,11 +53,6 @@
YCbCr422_12B = 0x12,
};
-enum hdmi_colorimetry {
- ITU601,
- ITU709,
-};
-
enum imx_hdmi_devtype {
IMX6Q_HDMI,
IMX6DL_HDMI,
@@ -489,12 +485,12 @@
if (is_color_space_conversion(hdmi)) {
if (hdmi->hdmi_data.enc_out_format == RGB) {
- if (hdmi->hdmi_data.colorimetry == ITU601)
+ if (hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_601)
csc_coeff = &csc_coeff_rgb_out_eitu601;
else
csc_coeff = &csc_coeff_rgb_out_eitu709;
} else if (hdmi->hdmi_data.enc_in_format == RGB) {
- if (hdmi->hdmi_data.colorimetry == ITU601)
+ if (hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_601)
csc_coeff = &csc_coeff_rgb_in_eitu601;
else
csc_coeff = &csc_coeff_rgb_in_eitu709;
@@ -1140,16 +1136,16 @@
/* Set up colorimetry */
if (hdmi->hdmi_data.enc_out_format == XVYCC444) {
colorimetry = HDMI_FC_AVICONF1_COLORIMETRY_EXTENDED_INFO;
- if (hdmi->hdmi_data.colorimetry == ITU601)
+ if (hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_601)
ext_colorimetry =
HDMI_FC_AVICONF2_EXT_COLORIMETRY_XVYCC601;
- else /* hdmi->hdmi_data.colorimetry == ITU709 */
+ else /*hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_709*/
ext_colorimetry =
HDMI_FC_AVICONF2_EXT_COLORIMETRY_XVYCC709;
} else if (hdmi->hdmi_data.enc_out_format != RGB) {
- if (hdmi->hdmi_data.colorimetry == ITU601)
+ if (hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_601)
colorimetry = HDMI_FC_AVICONF1_COLORIMETRY_SMPTE;
- else /* hdmi->hdmi_data.colorimetry == ITU709 */
+ else /*hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_709*/
colorimetry = HDMI_FC_AVICONF1_COLORIMETRY_ITUR;
ext_colorimetry = HDMI_FC_AVICONF2_EXT_COLORIMETRY_XVYCC601;
} else { /* Carries no data */
@@ -1379,9 +1375,9 @@
(hdmi->vic == 21) || (hdmi->vic == 22) ||
(hdmi->vic == 2) || (hdmi->vic == 3) ||
(hdmi->vic == 17) || (hdmi->vic == 18))
- hdmi->hdmi_data.colorimetry = ITU601;
+ hdmi->hdmi_data.colorimetry = HDMI_COLORIMETRY_ITU_601;
else
- hdmi->hdmi_data.colorimetry = ITU709;
+ hdmi->hdmi_data.colorimetry = HDMI_COLORIMETRY_ITU_709;
if ((hdmi->vic == 10) || (hdmi->vic == 11) ||
(hdmi->vic == 12) || (hdmi->vic == 13) ||
diff --git a/drivers/staging/lustre/TODO b/drivers/staging/lustre/TODO
index 22742d6..0a2b6cb 100644
--- a/drivers/staging/lustre/TODO
+++ b/drivers/staging/lustre/TODO
@@ -9,5 +9,6 @@
* Other minor misc cleanups...
Please send any patches to Greg Kroah-Hartman <greg@kroah.com>, Andreas Dilger
-<andreas.dilger@intel.com> and Peng Tao <tao.peng@emc.com>. CCing
-hpdd-discuss <hpdd-discuss@lists.01.org> would be great too.
+<andreas.dilger@intel.com>, Oleg Drokin <oleg.drokin@intel.com> and
+Peng Tao <tao.peng@emc.com>. CCing hpdd-discuss <hpdd-discuss@lists.01.org>
+would be great too.
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_kernelcomm.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_kernelcomm.h
index 596a15f..037ae8a 100644
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_kernelcomm.h
+++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_kernelcomm.h
@@ -61,6 +61,8 @@
__u16 kuc_msglen; /* Including header */
} __attribute__((aligned(sizeof(__u64))));
+#define KUC_CHANGELOG_MSG_MAXSIZE (sizeof(struct kuc_hdr)+CR_MAXSIZE)
+
#define KUC_MAGIC 0x191C /*Lustre9etLinC */
#define KUC_FL_BLOCK 0x01 /* Wait for send */
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h
index d0d942c..dddccca1 100644
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h
+++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h
@@ -120,7 +120,7 @@
do { \
LASSERT(!in_interrupt() || \
((size) <= LIBCFS_VMALLOC_SIZE && \
- ((mask) & GFP_ATOMIC)) != 0); \
+ ((mask) & __GFP_WAIT) == 0)); \
} while (0)
#define LIBCFS_ALLOC_POST(ptr, size) \
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
index 9364863..6f58ead 100644
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
+++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
@@ -529,7 +529,7 @@
{
struct page *page;
- if (is_vmalloc_addr(vaddr)) {
+ if (is_vmalloc_addr((void *)vaddr)) {
page = vmalloc_to_page ((void *)vaddr);
LASSERT (page != NULL);
return page;
diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c
index 68a4f52..b7b53b5 100644
--- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c
+++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c
@@ -924,7 +924,7 @@
int
ksocknal_send(lnet_ni_t *ni, void *private, lnet_msg_t *lntmsg)
{
- int mpflag = 0;
+ int mpflag = 1;
int type = lntmsg->msg_type;
lnet_process_id_t target = lntmsg->msg_target;
unsigned int payload_niov = lntmsg->msg_niov;
@@ -993,8 +993,9 @@
/* The first fragment will be set later in pro_pack */
rc = ksocknal_launch_packet(ni, tx, target);
- if (lntmsg->msg_vmflush)
+ if (!mpflag)
cfs_memory_pressure_restore(mpflag);
+
if (rc == 0)
return (0);
diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
index 6b6c0240..7893d83 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h
@@ -760,7 +760,8 @@
*flags |= (error << CLF_HSM_ERR_L);
}
-#define CR_MAXSIZE cfs_size_round(2*NAME_MAX + 1 + sizeof(struct changelog_rec))
+#define CR_MAXSIZE cfs_size_round(2*NAME_MAX + 1 + \
+ sizeof(struct changelog_ext_rec))
struct changelog_rec {
__u16 cr_namelen;
diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 22d0acc9..52b7731 100644
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -1086,7 +1086,7 @@
break;
case Q_GETQUOTA:
if (((type == USRQUOTA &&
- uid_eq(current_euid(), make_kuid(&init_user_ns, id))) ||
+ !uid_eq(current_euid(), make_kuid(&init_user_ns, id))) ||
(type == GRPQUOTA &&
!in_egroup_p(make_kgid(&init_user_ns, id)))) &&
(!cfs_capable(CFS_CAP_SYS_ADMIN) ||
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c
index d1ad91c3..8301392 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_request.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c
@@ -1430,7 +1430,7 @@
{
struct kuc_hdr *lh = (struct kuc_hdr *)buf;
- LASSERT(len <= CR_MAXSIZE);
+ LASSERT(len <= KUC_CHANGELOG_MSG_MAXSIZE);
lh->kuc_magic = KUC_MAGIC;
lh->kuc_transport = KUC_TRANSPORT_CHANGELOG;
@@ -1503,7 +1503,7 @@
CDEBUG(D_CHANGELOG, "changelog to fp=%p start "LPU64"\n",
cs->cs_fp, cs->cs_startrec);
- OBD_ALLOC(cs->cs_buf, CR_MAXSIZE);
+ OBD_ALLOC(cs->cs_buf, KUC_CHANGELOG_MSG_MAXSIZE);
if (cs->cs_buf == NULL)
GOTO(out, rc = -ENOMEM);
@@ -1540,7 +1540,7 @@
if (ctxt)
llog_ctxt_put(ctxt);
if (cs->cs_buf)
- OBD_FREE(cs->cs_buf, CR_MAXSIZE);
+ OBD_FREE(cs->cs_buf, KUC_CHANGELOG_MSG_MAXSIZE);
OBD_FREE_PTR(cs);
return rc;
}
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
index eedffed..31b269a 100644
--- a/drivers/staging/netlogic/xlr_net.c
+++ b/drivers/staging/netlogic/xlr_net.c
@@ -307,7 +307,7 @@
}
static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv, select_queue_fallback_t fallback)
{
return (u16)smp_processor_id();
}
@@ -892,6 +892,11 @@
priv->mii_bus->write = xlr_mii_write;
priv->mii_bus->parent = &pdev->dev;
priv->mii_bus->irq = kmalloc(sizeof(int)*PHY_MAX_ADDR, GFP_KERNEL);
+ if (priv->mii_bus->irq == NULL) {
+ pr_err("irq alloc failed\n");
+ mdiobus_free(priv->mii_bus);
+ return -ENOMEM;
+ }
priv->mii_bus->irq[priv->phy_addr] = priv->ndev->irq;
/* Scan only the enabled address */
diff --git a/drivers/staging/octeon-usb/octeon-hcd.c b/drivers/staging/octeon-usb/octeon-hcd.c
index 47e0a91..5a001d9 100644
--- a/drivers/staging/octeon-usb/octeon-hcd.c
+++ b/drivers/staging/octeon-usb/octeon-hcd.c
@@ -275,13 +275,6 @@
*/
#define MAX_TRANSFER_PACKETS ((1<<10)-1)
-enum {
- USB_CLOCK_TYPE_REF_12,
- USB_CLOCK_TYPE_REF_24,
- USB_CLOCK_TYPE_REF_48,
- USB_CLOCK_TYPE_CRYSTAL_12,
-};
-
/**
* Logical transactions may take numerous low level
* transactions, especially when splits are concerned. This
@@ -471,19 +464,6 @@
/* Returns the IO address to push/pop stuff data from the FIFOs */
#define USB_FIFO_ADDRESS(channel, usb_index) (CVMX_USBCX_GOTGCTL(usb_index) + ((channel)+1)*0x1000)
-static int octeon_usb_get_clock_type(void)
-{
- switch (cvmx_sysinfo_get()->board_type) {
- case CVMX_BOARD_TYPE_BBGW_REF:
- case CVMX_BOARD_TYPE_LANAI2_A:
- case CVMX_BOARD_TYPE_LANAI2_U:
- case CVMX_BOARD_TYPE_LANAI2_G:
- case CVMX_BOARD_TYPE_UBNT_E100:
- return USB_CLOCK_TYPE_CRYSTAL_12;
- }
- return USB_CLOCK_TYPE_REF_48;
-}
-
/**
* Read a USB 32bit CSR. It performs the necessary address swizzle
* for 32bit CSRs and logs the value in a readable format if
@@ -582,37 +562,6 @@
return 0; /* Data0 */
}
-
-/**
- * Return the number of USB ports supported by this Octeon
- * chip. If the chip doesn't support USB, or is not supported
- * by this API, a zero will be returned. Most Octeon chips
- * support one usb port, but some support two ports.
- * cvmx_usb_initialize() must be called on independent
- * struct cvmx_usb_state.
- *
- * Returns: Number of port, zero if usb isn't supported
- */
-static int cvmx_usb_get_num_ports(void)
-{
- int arch_ports = 0;
-
- if (OCTEON_IS_MODEL(OCTEON_CN56XX))
- arch_ports = 1;
- else if (OCTEON_IS_MODEL(OCTEON_CN52XX))
- arch_ports = 2;
- else if (OCTEON_IS_MODEL(OCTEON_CN50XX))
- arch_ports = 1;
- else if (OCTEON_IS_MODEL(OCTEON_CN31XX))
- arch_ports = 1;
- else if (OCTEON_IS_MODEL(OCTEON_CN30XX))
- arch_ports = 1;
- else
- arch_ports = 0;
-
- return arch_ports;
-}
-
/**
* Initialize a USB port for use. This must be called before any
* other access to the Octeon USB port is made. The port starts
@@ -628,41 +577,16 @@
* Returns: 0 or a negative error code.
*/
static int cvmx_usb_initialize(struct cvmx_usb_state *usb,
- int usb_port_number)
+ int usb_port_number,
+ enum cvmx_usb_initialize_flags flags)
{
union cvmx_usbnx_clk_ctl usbn_clk_ctl;
union cvmx_usbnx_usbp_ctl_status usbn_usbp_ctl_status;
- enum cvmx_usb_initialize_flags flags = 0;
int i;
/* At first allow 0-1 for the usb port number */
if ((usb_port_number < 0) || (usb_port_number > 1))
return -EINVAL;
- /* For all chips except 52XX there is only one port */
- if (!OCTEON_IS_MODEL(OCTEON_CN52XX) && (usb_port_number > 0))
- return -EINVAL;
- /* Try to determine clock type automatically */
- if (octeon_usb_get_clock_type() == USB_CLOCK_TYPE_CRYSTAL_12) {
- /* Only 12 MHZ crystals are supported */
- flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_XO_XI;
- } else {
- flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_XO_GND;
-
- switch (octeon_usb_get_clock_type()) {
- case USB_CLOCK_TYPE_REF_12:
- flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_12MHZ;
- break;
- case USB_CLOCK_TYPE_REF_24:
- flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_24MHZ;
- break;
- case USB_CLOCK_TYPE_REF_48:
- flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_48MHZ;
- break;
- default:
- return -EINVAL;
- break;
- }
- }
memset(usb, 0, sizeof(*usb));
usb->init_flags = flags;
@@ -3431,7 +3355,6 @@
return 0;
}
-
static const struct hc_driver octeon_hc_driver = {
.description = "Octeon USB",
.product_desc = "Octeon Host Controller",
@@ -3448,15 +3371,74 @@
.hub_control = octeon_usb_hub_control,
};
-
-static int octeon_usb_driver_probe(struct device *dev)
+static int octeon_usb_probe(struct platform_device *pdev)
{
int status;
- int usb_num = to_platform_device(dev)->id;
- int irq = platform_get_irq(to_platform_device(dev), 0);
+ int initialize_flags;
+ int usb_num;
+ struct resource *res_mem;
+ struct device_node *usbn_node;
+ int irq = platform_get_irq(pdev, 0);
+ struct device *dev = &pdev->dev;
struct octeon_hcd *priv;
struct usb_hcd *hcd;
unsigned long flags;
+ u32 clock_rate = 48000000;
+ bool is_crystal_clock = false;
+ const char *clock_type;
+ int i;
+
+ if (dev->of_node == NULL) {
+ dev_err(dev, "Error: empty of_node\n");
+ return -ENXIO;
+ }
+ usbn_node = dev->of_node->parent;
+
+ i = of_property_read_u32(usbn_node,
+ "refclk-frequency", &clock_rate);
+ if (i) {
+ dev_err(dev, "No USBN \"refclk-frequency\"\n");
+ return -ENXIO;
+ }
+ switch (clock_rate) {
+ case 12000000:
+ initialize_flags = CVMX_USB_INITIALIZE_FLAGS_CLOCK_12MHZ;
+ break;
+ case 24000000:
+ initialize_flags = CVMX_USB_INITIALIZE_FLAGS_CLOCK_24MHZ;
+ break;
+ case 48000000:
+ initialize_flags = CVMX_USB_INITIALIZE_FLAGS_CLOCK_48MHZ;
+ break;
+ default:
+ dev_err(dev, "Illebal USBN \"refclk-frequency\" %u\n", clock_rate);
+ return -ENXIO;
+
+ }
+
+ i = of_property_read_string(usbn_node,
+ "refclk-type", &clock_type);
+
+ if (!i && strcmp("crystal", clock_type) == 0)
+ is_crystal_clock = true;
+
+ if (is_crystal_clock)
+ initialize_flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_XO_XI;
+ else
+ initialize_flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_XO_GND;
+
+ res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (res_mem == NULL) {
+ dev_err(dev, "found no memory resource\n");
+ return -ENXIO;
+ }
+ usb_num = (res_mem->start >> 44) & 1;
+
+ if (irq < 0) {
+ /* Defective device tree, but we know how to fix it. */
+ irq_hw_number_t hwirq = usb_num ? (1 << 6) + 17 : 56;
+ irq = irq_create_mapping(NULL, hwirq);
+ }
/*
* Set the DMA mask to 64bits so we get buffers already translated for
@@ -3465,90 +3447,6 @@
dev->coherent_dma_mask = ~0;
dev->dma_mask = &dev->coherent_dma_mask;
- hcd = usb_create_hcd(&octeon_hc_driver, dev, dev_name(dev));
- if (!hcd) {
- dev_dbg(dev, "Failed to allocate memory for HCD\n");
- return -1;
- }
- hcd->uses_new_polling = 1;
- priv = (struct octeon_hcd *)hcd->hcd_priv;
-
- spin_lock_init(&priv->lock);
-
- tasklet_init(&priv->dequeue_tasklet, octeon_usb_urb_dequeue_work, (unsigned long)priv);
- INIT_LIST_HEAD(&priv->dequeue_list);
-
- status = cvmx_usb_initialize(&priv->usb, usb_num);
- if (status) {
- dev_dbg(dev, "USB initialization failed with %d\n", status);
- kfree(hcd);
- return -1;
- }
-
- /* This delay is needed for CN3010, but I don't know why... */
- mdelay(10);
-
- spin_lock_irqsave(&priv->lock, flags);
- cvmx_usb_poll(&priv->usb);
- spin_unlock_irqrestore(&priv->lock, flags);
-
- status = usb_add_hcd(hcd, irq, IRQF_SHARED);
- if (status) {
- dev_dbg(dev, "USB add HCD failed with %d\n", status);
- kfree(hcd);
- return -1;
- }
- device_wakeup_enable(hcd->self.controller);
-
- dev_dbg(dev, "Registered HCD for port %d on irq %d\n", usb_num, irq);
-
- return 0;
-}
-
-static int octeon_usb_driver_remove(struct device *dev)
-{
- int status;
- struct usb_hcd *hcd = dev_get_drvdata(dev);
- struct octeon_hcd *priv = hcd_to_octeon(hcd);
- unsigned long flags;
-
- usb_remove_hcd(hcd);
- tasklet_kill(&priv->dequeue_tasklet);
- spin_lock_irqsave(&priv->lock, flags);
- status = cvmx_usb_shutdown(&priv->usb);
- spin_unlock_irqrestore(&priv->lock, flags);
- if (status)
- dev_dbg(dev, "USB shutdown failed with %d\n", status);
-
- kfree(hcd);
-
- return 0;
-}
-
-static struct device_driver octeon_usb_driver = {
- .name = "OcteonUSB",
- .bus = &platform_bus_type,
- .probe = octeon_usb_driver_probe,
- .remove = octeon_usb_driver_remove,
-};
-
-
-#define MAX_USB_PORTS 10
-static struct platform_device *pdev_glob[MAX_USB_PORTS];
-static int octeon_usb_registered;
-static int __init octeon_usb_module_init(void)
-{
- int num_devices = cvmx_usb_get_num_ports();
- int device;
-
- if (usb_disabled() || num_devices == 0)
- return -ENODEV;
-
- if (driver_register(&octeon_usb_driver))
- return -ENOMEM;
-
- octeon_usb_registered = 1;
-
/*
* Only cn52XX and cn56XX have DWC_OTG USB hardware and the
* IOB priority registers. Under heavy network load USB
@@ -3569,41 +3467,102 @@
cvmx_write_csr(CVMX_IOB_N2C_L2C_PRI_CNT, pri_cnt.u64);
}
- for (device = 0; device < num_devices; device++) {
- struct resource irq_resource;
- struct platform_device *pdev;
- memset(&irq_resource, 0, sizeof(irq_resource));
- irq_resource.start = (device == 0) ? OCTEON_IRQ_USB0 : OCTEON_IRQ_USB1;
- irq_resource.end = irq_resource.start;
- irq_resource.flags = IORESOURCE_IRQ;
- pdev = platform_device_register_simple((char *)octeon_usb_driver. name, device, &irq_resource, 1);
- if (IS_ERR(pdev)) {
- driver_unregister(&octeon_usb_driver);
- octeon_usb_registered = 0;
- return PTR_ERR(pdev);
- }
- if (device < MAX_USB_PORTS)
- pdev_glob[device] = pdev;
-
+ hcd = usb_create_hcd(&octeon_hc_driver, dev, dev_name(dev));
+ if (!hcd) {
+ dev_dbg(dev, "Failed to allocate memory for HCD\n");
+ return -1;
}
+ hcd->uses_new_polling = 1;
+ priv = (struct octeon_hcd *)hcd->hcd_priv;
+
+ spin_lock_init(&priv->lock);
+
+ tasklet_init(&priv->dequeue_tasklet, octeon_usb_urb_dequeue_work, (unsigned long)priv);
+ INIT_LIST_HEAD(&priv->dequeue_list);
+
+ status = cvmx_usb_initialize(&priv->usb, usb_num, initialize_flags);
+ if (status) {
+ dev_dbg(dev, "USB initialization failed with %d\n", status);
+ kfree(hcd);
+ return -1;
+ }
+
+ /* This delay is needed for CN3010, but I don't know why... */
+ mdelay(10);
+
+ spin_lock_irqsave(&priv->lock, flags);
+ cvmx_usb_poll(&priv->usb);
+ spin_unlock_irqrestore(&priv->lock, flags);
+
+ status = usb_add_hcd(hcd, irq, 0);
+ if (status) {
+ dev_dbg(dev, "USB add HCD failed with %d\n", status);
+ kfree(hcd);
+ return -1;
+ }
+ device_wakeup_enable(hcd->self.controller);
+
+ dev_info(dev, "Registered HCD for port %d on irq %d\n", usb_num, irq);
+
return 0;
}
-static void __exit octeon_usb_module_cleanup(void)
+static int octeon_usb_remove(struct platform_device *pdev)
{
- int i;
+ int status;
+ struct device *dev = &pdev->dev;
+ struct usb_hcd *hcd = dev_get_drvdata(dev);
+ struct octeon_hcd *priv = hcd_to_octeon(hcd);
+ unsigned long flags;
- for (i = 0; i < MAX_USB_PORTS; i++)
- if (pdev_glob[i]) {
- platform_device_unregister(pdev_glob[i]);
- pdev_glob[i] = NULL;
- }
- if (octeon_usb_registered)
- driver_unregister(&octeon_usb_driver);
+ usb_remove_hcd(hcd);
+ tasklet_kill(&priv->dequeue_tasklet);
+ spin_lock_irqsave(&priv->lock, flags);
+ status = cvmx_usb_shutdown(&priv->usb);
+ spin_unlock_irqrestore(&priv->lock, flags);
+ if (status)
+ dev_dbg(dev, "USB shutdown failed with %d\n", status);
+
+ kfree(hcd);
+
+ return 0;
}
+static struct of_device_id octeon_usb_match[] = {
+ {
+ .compatible = "cavium,octeon-5750-usbc",
+ },
+ {},
+};
+
+static struct platform_driver octeon_usb_driver = {
+ .driver = {
+ .name = "OcteonUSB",
+ .owner = THIS_MODULE,
+ .of_match_table = octeon_usb_match,
+ },
+ .probe = octeon_usb_probe,
+ .remove = octeon_usb_remove,
+};
+
+static int __init octeon_usb_driver_init(void)
+{
+ if (usb_disabled())
+ return 0;
+
+ return platform_driver_register(&octeon_usb_driver);
+}
+module_init(octeon_usb_driver_init);
+
+static void __exit octeon_usb_driver_exit(void)
+{
+ if (usb_disabled())
+ return;
+
+ platform_driver_unregister(&octeon_usb_driver);
+}
+module_exit(octeon_usb_driver_exit);
+
MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Cavium Networks <support@caviumnetworks.com>");
-MODULE_DESCRIPTION("Cavium Networks Octeon USB Host driver.");
-module_init(octeon_usb_module_init);
-module_exit(octeon_usb_module_cleanup);
+MODULE_AUTHOR("Cavium, Inc. <support@cavium.com>");
+MODULE_DESCRIPTION("Cavium Inc. OCTEON USB Host driver.");
diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c
index 47541e1..ebb3ebc 100644
--- a/drivers/staging/octeon/ethernet-tx.c
+++ b/drivers/staging/octeon/ethernet-tx.c
@@ -554,7 +554,7 @@
printk_ratelimited("%s: Failed to allocate a work queue entry\n",
dev->name);
priv->stats.tx_dropped++;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return 0;
}
@@ -565,7 +565,7 @@
dev->name);
cvmx_fpa_free(work, CVMX_FPA_WQE_POOL, DONT_WRITEBACK(1));
priv->stats.tx_dropped++;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return 0;
}
@@ -682,7 +682,7 @@
work->grp);
priv->stats.tx_packets++;
priv->stats.tx_bytes += skb->len;
- dev_kfree_skb(skb);
+ dev_consume_skb_any(skb);
return 0;
}
diff --git a/drivers/staging/ozwpan/ozproto.c b/drivers/staging/ozwpan/ozproto.c
index cb06036..5d965cf 100644
--- a/drivers/staging/ozwpan/ozproto.c
+++ b/drivers/staging/ozwpan/ozproto.c
@@ -668,8 +668,8 @@
if (binding) {
binding->ptype.type = __constant_htons(OZ_ETHERTYPE);
binding->ptype.func = oz_pkt_recv;
- memcpy(binding->name, net_dev, OZ_MAX_BINDING_LEN);
if (net_dev && *net_dev) {
+ memcpy(binding->name, net_dev, OZ_MAX_BINDING_LEN);
oz_dbg(ON, "Adding binding: %s\n", net_dev);
binding->ptype.dev =
dev_get_by_name(&init_net, net_dev);
@@ -680,6 +680,7 @@
}
} else {
oz_dbg(ON, "Binding to all netcards\n");
+ memset(binding->name, 0, OZ_MAX_BINDING_LEN);
binding->ptype.dev = NULL;
}
if (binding) {
diff --git a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c
index 153ec61..96df62f 100644
--- a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c
+++ b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c
@@ -912,12 +912,12 @@
unsigned char *pbuf;
u32 wpa_ielen = 0;
u8 *pbssid = GetAddr3Ptr(pframe);
- u32 hidden_ssid = 0;
struct HT_info_element *pht_info = NULL;
struct rtw_ieee80211_ht_cap *pht_cap = NULL;
u32 bcn_channel;
unsigned short ht_cap_info;
unsigned char ht_info_infos_0;
+ int ssid_len;
if (is_client_associated_to_ap(Adapter) == false)
return true;
@@ -999,21 +999,15 @@
}
/* checking SSID */
+ ssid_len = 0;
p = rtw_get_ie(bssid->IEs + _FIXED_IE_LENGTH_, _SSID_IE_, &len, bssid->IELength - _FIXED_IE_LENGTH_);
- if (p == NULL) {
- DBG_88E("%s marc: cannot find SSID for survey event\n", __func__);
- hidden_ssid = true;
- } else {
- hidden_ssid = false;
+ if (p) {
+ ssid_len = *(p + 1);
+ if (ssid_len > NDIS_802_11_LENGTH_SSID)
+ ssid_len = 0;
}
-
- if ((NULL != p) && (false == hidden_ssid && (*(p + 1)))) {
- memcpy(bssid->Ssid.Ssid, (p + 2), *(p + 1));
- bssid->Ssid.SsidLength = *(p + 1);
- } else {
- bssid->Ssid.SsidLength = 0;
- bssid->Ssid.Ssid[0] = '\0';
- }
+ memcpy(bssid->Ssid.Ssid, (p + 2), ssid_len);
+ bssid->Ssid.SsidLength = ssid_len;
RT_TRACE(_module_rtl871x_mlme_c_, _drv_info_, ("%s bssid.Ssid.Ssid:%s bssid.Ssid.SsidLength:%d "
"cur_network->network.Ssid.Ssid:%s len:%d\n", __func__, bssid->Ssid.Ssid,
diff --git a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
index dec9925..4ad80ae 100644
--- a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
+++ b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c
@@ -2500,7 +2500,7 @@
("rtw_mp_ioctl_hdl: subcode [%d], len[%d], buffer_len[%d]\r\n",
poidparam->subcode, poidparam->len, len));
- if (poidparam->subcode >= MAX_MP_IOCTL_SUBCODE) {
+ if (poidparam->subcode >= ARRAY_SIZE(mp_ioctl_hdl)) {
RT_TRACE(_module_rtl871x_ioctl_os_c, _drv_err_, ("no matching drvext subcodes\r\n"));
ret = -EINVAL;
goto _rtw_mp_ioctl_hdl_exit;
@@ -3164,9 +3164,7 @@
u8 *p2pie;
uint p2pielen = 0, attr_contentlen = 0;
u8 attr_content[100] = {0x00};
-
- u8 go_devadd_str[17 + 10] = {0x00};
- /* +10 is for the str "go_devadd =", we have to clear it at wrqu->data.pointer */
+ u8 go_devadd_str[17 + 12] = {};
/* Commented by Albert 20121209 */
/* The input data is the GO's interface address which the application wants to know its device address. */
@@ -3223,12 +3221,12 @@
spin_unlock_bh(&pmlmepriv->scanned_queue.lock);
if (!blnMatch)
- sprintf(go_devadd_str, "\n\ndev_add = NULL");
+ snprintf(go_devadd_str, sizeof(go_devadd_str), "\n\ndev_add = NULL");
else
- sprintf(go_devadd_str, "\n\ndev_add =%.2X:%.2X:%.2X:%.2X:%.2X:%.2X",
+ snprintf(go_devadd_str, sizeof(go_devadd_str), "\n\ndev_add =%.2X:%.2X:%.2X:%.2X:%.2X:%.2X",
attr_content[0], attr_content[1], attr_content[2], attr_content[3], attr_content[4], attr_content[5]);
- if (copy_to_user(wrqu->data.pointer, go_devadd_str, 10 + 17))
+ if (copy_to_user(wrqu->data.pointer, go_devadd_str, sizeof(go_devadd_str)))
return -EFAULT;
return ret;
}
diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
index 68f98fa..7c9ee58 100644
--- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
@@ -653,7 +653,7 @@
}
static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv, select_queue_fallback_t fallback)
{
struct adapter *padapter = rtw_netdev_priv(dev);
struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
index 0a341d6..2f40ff5 100644
--- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c
+++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
@@ -53,8 +53,9 @@
{USB_DEVICE(USB_VENDER_ID_REALTEK, 0x0179)}, /* 8188ETV */
/*=== Customer ID ===*/
/****** 8188EUS ********/
- {USB_DEVICE(0x8179, 0x07B8)}, /* Abocom - Abocom */
+ {USB_DEVICE(0x07b8, 0x8179)}, /* Abocom - Abocom */
{USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */
+ {USB_DEVICE(0x2001, 0x3310)}, /* Dlink DWA-123 REV D1 */
{} /* Terminating entry */
};
diff --git a/drivers/staging/rtl8821ae/Kconfig b/drivers/staging/rtl8821ae/Kconfig
index 2aa5dac2..abccc9d 100644
--- a/drivers/staging/rtl8821ae/Kconfig
+++ b/drivers/staging/rtl8821ae/Kconfig
@@ -1,6 +1,6 @@
config R8821AE
tristate "RealTek RTL8821AE Wireless LAN NIC driver"
- depends on PCI && WLAN
+ depends on PCI && WLAN && MAC80211
depends on m
select WIRELESS_EXT
select WEXT_PRIV
diff --git a/drivers/staging/rtl8821ae/wifi.h b/drivers/staging/rtl8821ae/wifi.h
index cfe88a1..76bef93 100644
--- a/drivers/staging/rtl8821ae/wifi.h
+++ b/drivers/staging/rtl8821ae/wifi.h
@@ -1414,7 +1414,7 @@
/*88e tx power tracking*/
- u8 bb_swing_idx_ofdm[2];
+ u8 bb_swing_idx_ofdm[MAX_RF_PATH];
u8 bb_swing_idx_ofdm_current;
u8 bb_swing_idx_ofdm_base[MAX_RF_PATH];
bool bb_swing_flag_Ofdm;
diff --git a/drivers/staging/usbip/userspace/libsrc/names.c b/drivers/staging/usbip/userspace/libsrc/names.c
index 3c8d28b..81ff852 100644
--- a/drivers/staging/usbip/userspace/libsrc/names.c
+++ b/drivers/staging/usbip/userspace/libsrc/names.c
@@ -169,15 +169,15 @@
struct pool *p;
p = calloc(1, sizeof(struct pool));
- if (!p) {
+ if (!p)
+ return NULL;
+
+ p->mem = calloc(1, size);
+ if (!p->mem) {
free(p);
return NULL;
}
- p->mem = calloc(1, size);
- if (!p->mem)
- return NULL;
-
p->next = pool_head;
pool_head = p;
diff --git a/drivers/staging/usbip/vhci_sysfs.c b/drivers/staging/usbip/vhci_sysfs.c
index 9b51586..0141bc3 100644
--- a/drivers/staging/usbip/vhci_sysfs.c
+++ b/drivers/staging/usbip/vhci_sysfs.c
@@ -149,7 +149,8 @@
case USB_SPEED_WIRELESS:
break;
default:
- pr_err("speed %d\n", speed);
+ pr_err("Failed attach request for unsupported USB speed: %s\n",
+ usb_speed_string(speed));
return -EINVAL;
}
diff --git a/drivers/staging/wlags49_h2/wl_netdev.c b/drivers/staging/wlags49_h2/wl_netdev.c
index 965b1c0..69bc0a0 100644
--- a/drivers/staging/wlags49_h2/wl_netdev.c
+++ b/drivers/staging/wlags49_h2/wl_netdev.c
@@ -715,7 +715,7 @@
/* Free the skb and perform queue cleanup, as the buffer was
transmitted successfully */
- dev_kfree_skb( lp->txF.skb );
+ dev_consume_skb_any( lp->txF.skb );
lp->txF.skb = NULL;
lp->txF.port = 0;
@@ -1730,7 +1730,7 @@
WL_WDS_NETIF_STOP_QUEUE( lp );
lp->netif_queue_on = FALSE;
- dev_kfree_skb( skb );
+ dev_kfree_skb_any( skb );
return 0;
}
}
@@ -1755,7 +1755,7 @@
/* Free the skb and perform queue cleanup, as the buffer was
transmitted successfully */
- dev_kfree_skb( skb );
+ dev_consume_skb_any( skb );
return TRUE;
} // wl_send_dma
diff --git a/drivers/staging/wlags49_h2/wl_wext.c b/drivers/staging/wlags49_h2/wl_wext.c
index 4a1ddaf..187fc06 100644
--- a/drivers/staging/wlags49_h2/wl_wext.c
+++ b/drivers/staging/wlags49_h2/wl_wext.c
@@ -1061,7 +1061,7 @@
goto out;
}
- if (data->flags != 0 && data->length > HCF_MAX_NAME_LEN + 1) {
+ if (data->flags != 0 && data->length > HCF_MAX_NAME_LEN) {
ret = -EINVAL;
goto out;
}
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 7f1a7ce..b83ec37 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -785,7 +785,7 @@
spin_unlock_bh(&conn->cmd_lock);
list_for_each_entry_safe(cmd, cmd_p, &ack_list, i_conn_node) {
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
iscsit_free_cmd(cmd, false);
}
}
@@ -3708,7 +3708,7 @@
break;
case ISTATE_REMOVE:
spin_lock_bh(&conn->cmd_lock);
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
iscsit_free_cmd(cmd, false);
@@ -4151,7 +4151,7 @@
spin_lock_bh(&conn->cmd_lock);
list_for_each_entry_safe(cmd, cmd_tmp, &conn->conn_cmd_list, i_conn_node) {
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
iscsit_increment_maxcmdsn(cmd, sess);
@@ -4196,6 +4196,10 @@
iscsit_stop_timers_for_cmds(conn);
iscsit_stop_nopin_response_timer(conn);
iscsit_stop_nopin_timer(conn);
+
+ if (conn->conn_transport->iscsit_wait_conn)
+ conn->conn_transport->iscsit_wait_conn(conn);
+
iscsit_free_queue_reqs_for_conn(conn);
/*
diff --git a/drivers/target/iscsi/iscsi_target_erl1.c b/drivers/target/iscsi/iscsi_target_erl1.c
index e048d64..cda4d80 100644
--- a/drivers/target/iscsi/iscsi_target_erl1.c
+++ b/drivers/target/iscsi/iscsi_target_erl1.c
@@ -507,7 +507,9 @@
u32 last_statsn;
int found_cmd;
- if (conn->exp_statsn > begrun) {
+ if (!begrun) {
+ begrun = conn->exp_statsn;
+ } else if (conn->exp_statsn > begrun) {
pr_err("Got Status SNACK Begrun: 0x%08x, RunLength:"
" 0x%08x but already got ExpStatSN: 0x%08x on CID:"
" %hu.\n", begrun, runlength, conn->exp_statsn,
diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c
index 33be1fb..4ca8fd2 100644
--- a/drivers/target/iscsi/iscsi_target_erl2.c
+++ b/drivers/target/iscsi/iscsi_target_erl2.c
@@ -138,7 +138,7 @@
list_for_each_entry_safe(cmd, cmd_tmp,
&cr->conn_recovery_cmd_list, i_conn_node) {
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
cmd->conn = NULL;
spin_unlock(&cr->conn_recovery_cmd_lock);
iscsit_free_cmd(cmd, true);
@@ -160,7 +160,7 @@
list_for_each_entry_safe(cmd, cmd_tmp,
&cr->conn_recovery_cmd_list, i_conn_node) {
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
cmd->conn = NULL;
spin_unlock(&cr->conn_recovery_cmd_lock);
iscsit_free_cmd(cmd, true);
@@ -216,7 +216,7 @@
}
cr = cmd->cr;
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
return --cr->cmd_count;
}
@@ -297,7 +297,7 @@
if (!(cmd->cmd_flags & ICF_OOO_CMDSN))
continue;
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
iscsit_free_cmd(cmd, true);
@@ -335,7 +335,7 @@
/*
* Only perform connection recovery on ISCSI_OP_SCSI_CMD or
* ISCSI_OP_NOOP_OUT opcodes. For all other opcodes call
- * list_del(&cmd->i_conn_node); to release the command to the
+ * list_del_init(&cmd->i_conn_node); to release the command to the
* session pool and remove it from the connection's list.
*
* Also stop the DataOUT timer, which will be restarted after
@@ -351,7 +351,7 @@
" CID: %hu\n", cmd->iscsi_opcode,
cmd->init_task_tag, cmd->cmd_sn, conn->cid);
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
iscsit_free_cmd(cmd, true);
spin_lock_bh(&conn->cmd_lock);
@@ -371,7 +371,7 @@
*/
if (!(cmd->cmd_flags & ICF_OOO_CMDSN) && !cmd->immediate_cmd &&
iscsi_sna_gte(cmd->cmd_sn, conn->sess->exp_cmd_sn)) {
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
iscsit_free_cmd(cmd, true);
spin_lock_bh(&conn->cmd_lock);
@@ -393,7 +393,7 @@
cmd->sess = conn->sess;
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
iscsit_free_all_datain_reqs(cmd);
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 3976183..44a5471 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -137,7 +137,7 @@
list_for_each_entry(tpg, &tiqn->tiqn_tpg_list, tpg_list) {
spin_lock(&tpg->tpg_state_lock);
- if (tpg->tpg_state == TPG_STATE_FREE) {
+ if (tpg->tpg_state != TPG_STATE_ACTIVE) {
spin_unlock(&tpg->tpg_state_lock);
continue;
}
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 12da9b38..c3d9df6 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -500,7 +500,7 @@
if (segment_mult) {
u64 tmp = lba;
- start_lba = sector_div(tmp, segment_size * segment_mult);
+ start_lba = do_div(tmp, segment_size * segment_mult);
last_lba = first_lba + segment_size - 1;
if (start_lba >= first_lba &&
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 2f5d779..3013287 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -2009,7 +2009,7 @@
struct t10_reservation *pr_tmpl = &dev->t10_pr;
unsigned char isid_buf[PR_REG_ISID_LEN], *isid_ptr = NULL;
sense_reason_t ret = TCM_NO_SENSE;
- int pr_holder = 0;
+ int pr_holder = 0, type;
if (!se_sess || !se_lun) {
pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n");
@@ -2131,6 +2131,7 @@
ret = TCM_RESERVATION_CONFLICT;
goto out;
}
+ type = pr_reg->pr_res_type;
spin_lock(&pr_tmpl->registration_lock);
/*
@@ -2161,6 +2162,7 @@
* Release the calling I_T Nexus registration now..
*/
__core_scsi3_free_registration(cmd->se_dev, pr_reg, NULL, 1);
+ pr_reg = NULL;
/*
* From spc4r17, section 5.7.11.3 Unregistering
@@ -2174,8 +2176,8 @@
* RESERVATIONS RELEASED.
*/
if (pr_holder &&
- (pr_reg->pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_REGONLY ||
- pr_reg->pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_REGONLY)) {
+ (type == PR_TYPE_WRITE_EXCLUSIVE_REGONLY ||
+ type == PR_TYPE_EXCLUSIVE_ACCESS_REGONLY)) {
list_for_each_entry(pr_reg_p,
&pr_tmpl->registration_list,
pr_reg_list) {
@@ -2194,7 +2196,8 @@
ret = core_scsi3_update_and_write_aptpl(dev, aptpl);
out:
- core_scsi3_put_pr_reg(pr_reg);
+ if (pr_reg)
+ core_scsi3_put_pr_reg(pr_reg);
return ret;
}
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index fa3cae3..77e6531 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -1074,23 +1074,36 @@
struct scatterlist *psg;
void *paddr, *addr;
unsigned int i, len, left;
+ unsigned int offset = sg_off;
left = sectors * dev->prot_length;
for_each_sg(cmd->t_prot_sg, psg, cmd->t_prot_nents, i) {
+ unsigned int psg_len, copied = 0;
- len = min(psg->length, left);
paddr = kmap_atomic(sg_page(psg)) + psg->offset;
- addr = kmap_atomic(sg_page(sg)) + sg_off;
+ psg_len = min(left, psg->length);
+ while (psg_len) {
+ len = min(psg_len, sg->length - offset);
+ addr = kmap_atomic(sg_page(sg)) + sg->offset + offset;
- if (read)
- memcpy(paddr, addr, len);
- else
- memcpy(addr, paddr, len);
+ if (read)
+ memcpy(paddr + copied, addr, len);
+ else
+ memcpy(addr, paddr + copied, len);
- left -= len;
+ left -= len;
+ offset += len;
+ copied += len;
+ psg_len -= len;
+
+ if (offset >= sg->length) {
+ sg = sg_next(sg);
+ offset = 0;
+ }
+ kunmap_atomic(addr);
+ }
kunmap_atomic(paddr);
- kunmap_atomic(addr);
}
}
@@ -1155,7 +1168,7 @@
{
struct se_device *dev = cmd->se_dev;
struct se_dif_v1_tuple *sdt;
- struct scatterlist *dsg;
+ struct scatterlist *dsg, *psg = sg;
sector_t sector = start;
void *daddr, *paddr;
int i, j, offset = sg_off;
@@ -1163,14 +1176,14 @@
for_each_sg(cmd->t_data_sg, dsg, cmd->t_data_nents, i) {
daddr = kmap_atomic(sg_page(dsg)) + dsg->offset;
- paddr = kmap_atomic(sg_page(sg)) + sg->offset;
+ paddr = kmap_atomic(sg_page(psg)) + sg->offset;
for (j = 0; j < dsg->length; j += dev->dev_attrib.block_size) {
- if (offset >= sg->length) {
+ if (offset >= psg->length) {
kunmap_atomic(paddr);
- sg = sg_next(sg);
- paddr = kmap_atomic(sg_page(sg)) + sg->offset;
+ psg = sg_next(psg);
+ paddr = kmap_atomic(sg_page(psg)) + psg->offset;
offset = 0;
}
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 43c5ca98..3bebc71 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -440,8 +440,8 @@
padding = ((-scsi_target_len) & 3);
if (padding)
scsi_target_len += padding;
- if (scsi_name_len > 256)
- scsi_name_len = 256;
+ if (scsi_target_len > 256)
+ scsi_target_len = 256;
buf[off-1] = scsi_target_len;
off += scsi_target_len;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index c50fd9f..2956250 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -669,9 +669,6 @@
return;
}
- if (!success)
- cmd->transport_state |= CMD_T_FAILED;
-
/*
* Check for case where an explicit ABORT_TASK has been received
* and transport_wait_for_tasks() will be waiting for completion..
@@ -681,7 +678,7 @@
spin_unlock_irqrestore(&cmd->t_state_lock, flags);
complete(&cmd->t_transport_stop_comp);
return;
- } else if (cmd->transport_state & CMD_T_FAILED) {
+ } else if (!success) {
INIT_WORK(&cmd->work, target_complete_failure_work);
} else {
INIT_WORK(&cmd->work, target_complete_ok_work);
@@ -1604,6 +1601,9 @@
case TCM_CHECK_CONDITION_ABORT_CMD:
case TCM_CHECK_CONDITION_UNIT_ATTENTION:
case TCM_CHECK_CONDITION_NOT_READY:
+ case TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED:
+ case TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED:
+ case TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED:
break;
case TCM_OUT_OF_RESOURCES:
sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 35c0664..5f88d76 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -136,6 +136,7 @@
config RCAR_THERMAL
tristate "Renesas R-Car thermal driver"
depends on ARCH_SHMOBILE || COMPILE_TEST
+ depends on HAS_IOMEM
help
Enable this to plug the R-Car thermal sensor driver into the Linux
thermal framework.
@@ -210,8 +211,16 @@
tristate "ACPI INT3403 thermal driver"
depends on X86 && ACPI
help
- This driver uses ACPI INT3403 device objects. If present, it will
- register each INT3403 thermal sensor as a thermal zone.
+ Newer laptops and tablets that use ACPI may have thermal sensors
+ outside the core CPU/SOC for thermal safety reasons. These
+ temperature sensors are also exposed for the OS to use via the so
+ called INT3403 ACPI object. This driver will, on devices that have
+ such sensors, expose the temperature information from these sensors
+ to userspace via the normal thermal framework. This means that a wide
+ range of applications and GUI widgets can show this information to
+ the user or use this information for making decisions. For example,
+ the Intel Thermal Daemon can use this information to allow the user
+ to select his laptop to run without turning on the fans.
menu "Texas Instruments thermal drivers"
source "drivers/thermal/ti-soc-thermal/Kconfig"
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 338a88b..71b0ec0 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -56,10 +56,15 @@
static DEFINE_MUTEX(thermal_list_lock);
static DEFINE_MUTEX(thermal_governor_lock);
+static struct thermal_governor *def_governor;
+
static struct thermal_governor *__find_governor(const char *name)
{
struct thermal_governor *pos;
+ if (!name || !name[0])
+ return def_governor;
+
list_for_each_entry(pos, &thermal_governor_list, governor_list)
if (!strnicmp(name, pos->name, THERMAL_NAME_LENGTH))
return pos;
@@ -82,17 +87,23 @@
if (__find_governor(governor->name) == NULL) {
err = 0;
list_add(&governor->governor_list, &thermal_governor_list);
+ if (!def_governor && !strncmp(governor->name,
+ DEFAULT_THERMAL_GOVERNOR, THERMAL_NAME_LENGTH))
+ def_governor = governor;
}
mutex_lock(&thermal_list_lock);
list_for_each_entry(pos, &thermal_tz_list, node) {
+ /*
+ * only thermal zones with specified tz->tzp->governor_name
+ * may run with tz->govenor unset
+ */
if (pos->governor)
continue;
- if (pos->tzp)
- name = pos->tzp->governor_name;
- else
- name = DEFAULT_THERMAL_GOVERNOR;
+
+ name = pos->tzp->governor_name;
+
if (!strnicmp(name, governor->name, THERMAL_NAME_LENGTH))
pos->governor = governor;
}
@@ -342,8 +353,8 @@
static void handle_non_critical_trips(struct thermal_zone_device *tz,
int trip, enum thermal_trip_type trip_type)
{
- if (tz->governor)
- tz->governor->throttle(tz, trip);
+ tz->governor ? tz->governor->throttle(tz, trip) :
+ def_governor->throttle(tz, trip);
}
static void handle_critical_trips(struct thermal_zone_device *tz,
@@ -1107,7 +1118,7 @@
INIT_LIST_HEAD(&cdev->thermal_instances);
cdev->np = np;
cdev->ops = ops;
- cdev->updated = true;
+ cdev->updated = false;
cdev->device.class = &thermal_class;
cdev->devdata = devdata;
dev_set_name(&cdev->device, "cooling_device%d", cdev->id);
@@ -1533,7 +1544,7 @@
if (tz->tzp)
tz->governor = __find_governor(tz->tzp->governor_name);
else
- tz->governor = __find_governor(DEFAULT_THERMAL_GOVERNOR);
+ tz->governor = def_governor;
mutex_unlock(&thermal_governor_lock);
diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c
index 972e1c7..081fd7e 100644
--- a/drivers/thermal/x86_pkg_temp_thermal.c
+++ b/drivers/thermal/x86_pkg_temp_thermal.c
@@ -68,6 +68,10 @@
struct thermal_zone_device *tzone;
};
+static const struct thermal_zone_params pkg_temp_tz_params = {
+ .no_hwmon = true,
+};
+
/* List maintaining number of package instances */
static LIST_HEAD(phy_dev_list);
static DEFINE_MUTEX(phy_dev_list_mutex);
@@ -394,7 +398,6 @@
int err;
u32 tj_max;
struct phy_dev_entry *phy_dev_entry;
- char buffer[30];
int thres_count;
u32 eax, ebx, ecx, edx;
u8 *temp;
@@ -440,13 +443,11 @@
phy_dev_entry->first_cpu = cpu;
phy_dev_entry->tj_max = tj_max;
phy_dev_entry->ref_cnt = 1;
- snprintf(buffer, sizeof(buffer), "pkg-temp-%d\n",
- phy_dev_entry->phys_proc_id);
- phy_dev_entry->tzone = thermal_zone_device_register(buffer,
+ phy_dev_entry->tzone = thermal_zone_device_register("x86_pkg_temp",
thres_count,
(thres_count == MAX_NUMBER_OF_TRIPS) ?
0x03 : 0x01,
- phy_dev_entry, &tzone_ops, NULL, 0, 0);
+ phy_dev_entry, &tzone_ops, &pkg_temp_tz_params, 0, 0);
if (IS_ERR(phy_dev_entry->tzone)) {
err = PTR_ERR(phy_dev_entry->tzone);
goto err_ret_free;
diff --git a/drivers/tty/hvc/hvc_opal.c b/drivers/tty/hvc/hvc_opal.c
index 6496872..b01659b 100644
--- a/drivers/tty/hvc/hvc_opal.c
+++ b/drivers/tty/hvc/hvc_opal.c
@@ -255,13 +255,7 @@
/* Register as a vio device to receive callbacks */
return platform_driver_register(&hvc_opal_driver);
}
-module_init(hvc_opal_init);
-
-static void __exit hvc_opal_exit(void)
-{
- platform_driver_unregister(&hvc_opal_driver);
-}
-module_exit(hvc_opal_exit);
+device_initcall(hvc_opal_init);
static void udbg_opal_putc(char c)
{
diff --git a/drivers/tty/hvc/hvc_rtas.c b/drivers/tty/hvc/hvc_rtas.c
index 0069bb8..08c8792 100644
--- a/drivers/tty/hvc/hvc_rtas.c
+++ b/drivers/tty/hvc/hvc_rtas.c
@@ -102,17 +102,7 @@
return 0;
}
-module_init(hvc_rtas_init);
-
-/* This will tear down the tty portion of the driver */
-static void __exit hvc_rtas_exit(void)
-{
- /* Really the fun isn't over until the worker thread breaks down and
- * the tty cleans up */
- if (hvc_rtas_dev)
- hvc_remove(hvc_rtas_dev);
-}
-module_exit(hvc_rtas_exit);
+device_initcall(hvc_rtas_init);
/* This will happen prior to module init. There is no tty at this time? */
static int __init hvc_rtas_console_init(void)
diff --git a/drivers/tty/hvc/hvc_udbg.c b/drivers/tty/hvc/hvc_udbg.c
index 7222827..9cf573d 100644
--- a/drivers/tty/hvc/hvc_udbg.c
+++ b/drivers/tty/hvc/hvc_udbg.c
@@ -80,14 +80,7 @@
return 0;
}
-module_init(hvc_udbg_init);
-
-static void __exit hvc_udbg_exit(void)
-{
- if (hvc_udbg_dev)
- hvc_remove(hvc_udbg_dev);
-}
-module_exit(hvc_udbg_exit);
+device_initcall(hvc_udbg_init);
static int __init hvc_udbg_console_init(void)
{
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 636c9ba..2dc2831 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -561,18 +561,7 @@
#endif
return r;
}
-
-static void __exit xen_hvc_fini(void)
-{
- struct xencons_info *entry, *next;
-
- if (list_empty(&xenconsoles))
- return;
-
- list_for_each_entry_safe(entry, next, &xenconsoles, list) {
- xen_console_remove(entry);
- }
-}
+device_initcall(xen_hvc_init);
static int xen_cons_init(void)
{
@@ -598,10 +587,6 @@
hvc_instantiate(HVC_COOKIE, 0, ops);
return 0;
}
-
-
-module_init(xen_hvc_init);
-module_exit(xen_hvc_fini);
console_initcall(xen_cons_init);
#ifdef CONFIG_EARLY_PRINTK
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index f34461c..2ebe47b 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -1090,6 +1090,7 @@
{
unsigned int addr = 0;
unsigned int modem = 0;
+ unsigned int brk = 0;
struct gsm_dlci *dlci;
int len = clen;
u8 *dp = data;
@@ -1116,6 +1117,16 @@
if (len == 0)
return;
}
+ len--;
+ if (len > 0) {
+ while (gsm_read_ea(&brk, *dp++) == 0) {
+ len--;
+ if (len == 0)
+ return;
+ }
+ modem <<= 7;
+ modem |= (brk & 0x7f);
+ }
tty = tty_port_tty_get(&dlci->port);
gsm_process_modem(tty, dlci, modem, clen);
if (tty) {
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index cb8017a..d15624c 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -817,8 +817,7 @@
struct n_tty_data *ldata = tty->disc_data;
size_t echoed;
- if ((!L_ECHO(tty) && !L_ECHONL(tty)) ||
- ldata->echo_mark == ldata->echo_tail)
+ if (ldata->echo_mark == ldata->echo_tail)
return;
mutex_lock(&ldata->output_lock);
@@ -1244,7 +1243,8 @@
if (L_ECHO(tty)) {
echo_char(c, tty);
commit_echoes(tty);
- }
+ } else
+ process_echoes(tty);
isig(signal, tty);
return;
}
@@ -1274,7 +1274,7 @@
if (I_IXON(tty)) {
if (c == START_CHAR(tty)) {
start_tty(tty);
- commit_echoes(tty);
+ process_echoes(tty);
return 0;
}
if (c == STOP_CHAR(tty)) {
@@ -1820,8 +1820,10 @@
* Fix tty hang when I_IXON(tty) is cleared, but the tty
* been stopped by STOP_CHAR(tty) before it.
*/
- if (!I_IXON(tty) && old && (old->c_iflag & IXON) && !tty->flow_stopped)
+ if (!I_IXON(tty) && old && (old->c_iflag & IXON) && !tty->flow_stopped) {
start_tty(tty);
+ process_echoes(tty);
+ }
/* The termios change make the tty ready for I/O */
if (waitqueue_active(&tty->write_wait))
@@ -1896,7 +1898,7 @@
static inline int input_available_p(struct tty_struct *tty, int poll)
{
struct n_tty_data *ldata = tty->disc_data;
- int amt = poll && !TIME_CHAR(tty) ? MIN_CHAR(tty) : 1;
+ int amt = poll && !TIME_CHAR(tty) && MIN_CHAR(tty) ? MIN_CHAR(tty) : 1;
if (ldata->icanon && !L_EXTPROC(tty)) {
if (ldata->canon_head != ldata->read_tail)
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 61ecd70..69932b7 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -2433,6 +2433,24 @@
serial_dl_write(up, quot);
/*
+ * XR17V35x UARTs have an extra fractional divisor register (DLD)
+ *
+ * We need to recalculate all of the registers, because DLM and DLL
+ * are already rounded to a whole integer.
+ *
+ * When recalculating we use a 32x clock instead of a 16x clock to
+ * allow 1-bit for rounding in the fractional part.
+ */
+ if (up->port.type == PORT_XR17V35X) {
+ unsigned int baud_x32 = (port->uartclk * 2) / baud;
+ u16 quot = baud_x32 / 32;
+ u8 quot_frac = DIV_ROUND_CLOSEST(baud_x32 % 32, 2);
+
+ serial_dl_write(up, quot);
+ serial_port_out(port, 0x2, quot_frac & 0xf);
+ }
+
+ /*
* LCR DLAB must be set to enable 64-byte FIFO mode. If the FCR
* is written without DLAB set, this mode will be disabled.
*/
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index faa64e6..ed31135 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -391,7 +391,7 @@
return 0;
}
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
static int dw8250_suspend(struct device *dev)
{
struct dw8250_data *data = dev_get_drvdata(dev);
@@ -409,7 +409,7 @@
return 0;
}
-#endif /* CONFIG_PM */
+#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_PM_RUNTIME
static int dw8250_runtime_suspend(struct device *dev)
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 50228ee..0ff3e36 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -783,7 +783,8 @@
{
unsigned int bar;
- if ((priv->dev->subsystem_device & 0xff00) == 0x3000) {
+ if ((priv->dev->device != PCI_DEVICE_ID_NETMOS_9865) &&
+ (priv->dev->subsystem_device & 0xff00) == 0x3000) {
/* netmos apparently orders BARs by datasheet layout, so serial
* ports get BARs 0 and 3 (or 1 and 4 for memmapped)
*/
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index fa511eb..77f0351 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -738,9 +738,6 @@
return retval;
}
disable_irq(up->wakeirq);
- } else {
- dev_info(up->port.dev, "no wakeirq for uart%d\n",
- up->port.line);
}
dev_dbg(up->port.dev, "serial_omap_startup+%d\n", up->port.line);
@@ -1604,8 +1601,11 @@
flags & SER_RS485_RTS_AFTER_SEND);
if (ret < 0)
return ret;
- } else
+ } else if (up->rts_gpio == -EPROBE_DEFER) {
+ return -EPROBE_DEFER;
+ } else {
up->rts_gpio = -EINVAL;
+ }
if (of_property_read_u32_array(np, "rs485-rts-delay",
rs485_delay, 2) == 0) {
@@ -1687,6 +1687,9 @@
up->port.iotype = UPIO_MEM;
up->port.irq = uartirq;
up->wakeirq = wakeirq;
+ if (!up->wakeirq)
+ dev_info(up->port.dev, "no wakeirq for uart%d\n",
+ up->port.line);
up->port.regshift = 2;
up->port.fifosize = 64;
diff --git a/drivers/tty/serial/sirfsoc_uart.c b/drivers/tty/serial/sirfsoc_uart.c
index 49a2ffd..b7bfe24 100644
--- a/drivers/tty/serial/sirfsoc_uart.c
+++ b/drivers/tty/serial/sirfsoc_uart.c
@@ -542,8 +542,10 @@
wr_regl(port, ureg->sirfsoc_rx_dma_io_ctrl,
rd_regl(port, ureg->sirfsoc_rx_dma_io_ctrl) |
SIRFUART_IO_MODE);
- sirfsoc_uart_pio_rx_chars(port, 4 - sirfport->rx_io_count);
spin_unlock_irqrestore(&sirfport->rx_lock, flags);
+ spin_lock(&port->lock);
+ sirfsoc_uart_pio_rx_chars(port, 4 - sirfport->rx_io_count);
+ spin_unlock(&port->lock);
if (sirfport->rx_io_count == 4) {
spin_lock_irqsave(&sirfport->rx_lock, flags);
sirfport->rx_io_count = 0;
diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c
index cf86e72..dc697ce 100644
--- a/drivers/tty/serial/sunhv.c
+++ b/drivers/tty/serial/sunhv.c
@@ -433,13 +433,10 @@
unsigned long flags;
int locked = 1;
- local_irq_save(flags);
- if (port->sysrq) {
- locked = 0;
- } else if (oops_in_progress) {
- locked = spin_trylock(&port->lock);
- } else
- spin_lock(&port->lock);
+ if (port->sysrq || oops_in_progress)
+ locked = spin_trylock_irqsave(&port->lock, flags);
+ else
+ spin_lock_irqsave(&port->lock, flags);
while (n > 0) {
unsigned long ra = __pa(con_write_page);
@@ -470,8 +467,7 @@
}
if (locked)
- spin_unlock(&port->lock);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&port->lock, flags);
}
static inline void sunhv_console_putchar(struct uart_port *port, char c)
@@ -492,7 +488,10 @@
unsigned long flags;
int i, locked = 1;
- local_irq_save(flags);
+ if (port->sysrq || oops_in_progress)
+ locked = spin_trylock_irqsave(&port->lock, flags);
+ else
+ spin_lock_irqsave(&port->lock, flags);
if (port->sysrq) {
locked = 0;
} else if (oops_in_progress) {
@@ -507,8 +506,7 @@
}
if (locked)
- spin_unlock(&port->lock);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&port->lock, flags);
}
static struct console sunhv_console = {
diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index 380fb53..5faa8e9 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -844,20 +844,16 @@
unsigned long flags;
int locked = 1;
- local_irq_save(flags);
- if (up->port.sysrq) {
- locked = 0;
- } else if (oops_in_progress) {
- locked = spin_trylock(&up->port.lock);
- } else
- spin_lock(&up->port.lock);
+ if (up->port.sysrq || oops_in_progress)
+ locked = spin_trylock_irqsave(&up->port.lock, flags);
+ else
+ spin_lock_irqsave(&up->port.lock, flags);
uart_console_write(&up->port, s, n, sunsab_console_putchar);
sunsab_tec_wait(up);
if (locked)
- spin_unlock(&up->port.lock);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&up->port.lock, flags);
}
static int sunsab_console_setup(struct console *con, char *options)
diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c
index db79b76..9a0f24f 100644
--- a/drivers/tty/serial/sunsu.c
+++ b/drivers/tty/serial/sunsu.c
@@ -1295,13 +1295,10 @@
unsigned int ier;
int locked = 1;
- local_irq_save(flags);
- if (up->port.sysrq) {
- locked = 0;
- } else if (oops_in_progress) {
- locked = spin_trylock(&up->port.lock);
- } else
- spin_lock(&up->port.lock);
+ if (up->port.sysrq || oops_in_progress)
+ locked = spin_trylock_irqsave(&up->port.lock, flags);
+ else
+ spin_lock_irqsave(&up->port.lock, flags);
/*
* First save the UER then disable the interrupts
@@ -1319,8 +1316,7 @@
serial_out(up, UART_IER, ier);
if (locked)
- spin_unlock(&up->port.lock);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&up->port.lock, flags);
}
/*
diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c
index 45a8c6a..a2c40ed 100644
--- a/drivers/tty/serial/sunzilog.c
+++ b/drivers/tty/serial/sunzilog.c
@@ -1195,20 +1195,16 @@
unsigned long flags;
int locked = 1;
- local_irq_save(flags);
- if (up->port.sysrq) {
- locked = 0;
- } else if (oops_in_progress) {
- locked = spin_trylock(&up->port.lock);
- } else
- spin_lock(&up->port.lock);
+ if (up->port.sysrq || oops_in_progress)
+ locked = spin_trylock_irqsave(&up->port.lock, flags);
+ else
+ spin_lock_irqsave(&up->port.lock, flags);
uart_console_write(&up->port, s, count, sunzilog_putchar);
udelay(2);
if (locked)
- spin_unlock(&up->port.lock);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&up->port.lock, flags);
}
static int __init sunzilog_console_setup(struct console *con, char *options)
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 61b1137..23b5d32 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1164,6 +1164,8 @@
scr_memsetw(vc->vc_screenbuf, vc->vc_video_erase_char,
vc->vc_screenbuf_size >> 1);
set_origin(vc);
+ if (CON_IS_VISIBLE(vc))
+ update_screen(vc);
/* fall through */
case 2: /* erase whole display */
count = vc->vc_cols * vc->vc_rows;
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 80de2f8..4ab2cb6 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -105,7 +105,7 @@
do {
/* flush any pending transfer */
- hw_write(ci, OP_ENDPTFLUSH, BIT(n), BIT(n));
+ hw_write(ci, OP_ENDPTFLUSH, ~0, BIT(n));
while (hw_read(ci, OP_ENDPTFLUSH, BIT(n)))
cpu_relax();
} while (hw_read(ci, OP_ENDPTSTAT, BIT(n)));
@@ -205,7 +205,7 @@
if (is_ctrl && dir == RX && hw_read(ci, OP_ENDPTSETUPSTAT, BIT(num)))
return -EAGAIN;
- hw_write(ci, OP_ENDPTPRIME, BIT(n), BIT(n));
+ hw_write(ci, OP_ENDPTPRIME, ~0, BIT(n));
while (hw_read(ci, OP_ENDPTPRIME, BIT(n)))
cpu_relax();
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 8d72f0c..062967c 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -717,6 +717,10 @@
result = -ENOMEM;
goto err;
}
+
+ if (dev->quirks & USB_QUIRK_DELAY_INIT)
+ msleep(100);
+
result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno,
bigbuffer, length);
if (result < 0) {
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 5d01558..ab90a01 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -63,8 +63,10 @@
dynid->id.idProduct = idProduct;
dynid->id.match_flags = USB_DEVICE_ID_MATCH_DEVICE;
if (fields > 2 && bInterfaceClass) {
- if (bInterfaceClass > 255)
- return -EINVAL;
+ if (bInterfaceClass > 255) {
+ retval = -EINVAL;
+ goto fail;
+ }
dynid->id.bInterfaceClass = (u8)bInterfaceClass;
dynid->id.match_flags |= USB_DEVICE_ID_MATCH_INT_CLASS;
@@ -73,17 +75,21 @@
if (fields > 4) {
const struct usb_device_id *id = id_table;
- if (!id)
- return -ENODEV;
+ if (!id) {
+ retval = -ENODEV;
+ goto fail;
+ }
for (; id->match_flags; id++)
if (id->idVendor == refVendor && id->idProduct == refProduct)
break;
- if (id->match_flags)
+ if (id->match_flags) {
dynid->id.driver_info = id->driver_info;
- else
- return -ENODEV;
+ } else {
+ retval = -ENODEV;
+ goto fail;
+ }
}
spin_lock(&dynids->lock);
@@ -95,6 +101,10 @@
if (retval)
return retval;
return count;
+
+fail:
+ kfree(dynid);
+ return retval;
}
EXPORT_SYMBOL_GPL(usb_store_new_id);
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 199aaea..2518c32 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1032,7 +1032,6 @@
dev_name(&usb_dev->dev), retval);
return retval;
}
- usb_dev->lpm_capable = usb_device_supports_lpm(usb_dev);
}
retval = usb_new_device (usb_dev);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index babba88..64ea219 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -128,7 +128,7 @@
return usb_get_intfdata(hdev->actconfig->interface[0]);
}
-int usb_device_supports_lpm(struct usb_device *udev)
+static int usb_device_supports_lpm(struct usb_device *udev)
{
/* USB 2.1 (and greater) devices indicate LPM support through
* their USB 2.0 Extended Capabilities BOS descriptor.
@@ -149,11 +149,6 @@
"Power management will be impacted.\n");
return 0;
}
-
- /* udev is root hub */
- if (!udev->parent)
- return 1;
-
if (udev->parent->lpm_capable)
return 1;
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 8f37063..739ee8e 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -47,6 +47,10 @@
/* Microsoft LifeCam-VX700 v2.0 */
{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* Logitech HD Pro Webcams C920 and C930e */
+ { USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
+ { USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
+
/* Logitech Quickcam Fusion */
{ USB_DEVICE(0x046d, 0x08c1), .driver_info = USB_QUIRK_RESET_RESUME },
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index c493836..8238577 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -35,7 +35,6 @@
unsigned int size);
extern int usb_get_bos_descriptor(struct usb_device *dev);
extern void usb_release_bos_descriptor(struct usb_device *dev);
-extern int usb_device_supports_lpm(struct usb_device *udev);
extern char *usb_cache_string(struct usb_device *udev, int index);
extern int usb_set_configuration(struct usb_device *dev, int configuration);
extern int usb_choose_configuration(struct usb_device *udev);
diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c
index 8565d87..1d12988 100644
--- a/drivers/usb/dwc2/core.c
+++ b/drivers/usb/dwc2/core.c
@@ -216,7 +216,7 @@
int retval = 0;
if (!select_phy)
- return -ENODEV;
+ return 0;
usbcfg = readl(hsotg->regs + GUSBCFG);
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index f59484d..4d918ed 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -2565,25 +2565,14 @@
struct usb_host_endpoint *ep)
{
struct dwc2_hsotg *hsotg = dwc2_hcd_to_hsotg(hcd);
- int is_control = usb_endpoint_xfer_control(&ep->desc);
- int is_out = usb_endpoint_dir_out(&ep->desc);
- int epnum = usb_endpoint_num(&ep->desc);
- struct usb_device *udev;
unsigned long flags;
dev_dbg(hsotg->dev,
"DWC OTG HCD EP RESET: bEndpointAddress=0x%02x\n",
ep->desc.bEndpointAddress);
- udev = to_usb_device(hsotg->dev);
-
spin_lock_irqsave(&hsotg->lock, flags);
-
- usb_settoggle(udev, epnum, is_out, 0);
- if (is_control)
- usb_settoggle(udev, epnum, !is_out, 0);
dwc2_hcd_endpoint_reset(hsotg, ep);
-
spin_unlock_irqrestore(&hsotg->lock, flags);
}
diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c
index d01d0d3..eaba547 100644
--- a/drivers/usb/dwc2/platform.c
+++ b/drivers/usb/dwc2/platform.c
@@ -124,6 +124,9 @@
int retval;
int irq;
+ if (usb_disabled())
+ return -ENODEV;
+
match = of_match_device(dwc2_of_match_table, &dev->dev);
if (match && match->data) {
params = match->data;
diff --git a/drivers/usb/gadget/bcm63xx_udc.c b/drivers/usb/gadget/bcm63xx_udc.c
index 888fbb4..e969eb8 100644
--- a/drivers/usb/gadget/bcm63xx_udc.c
+++ b/drivers/usb/gadget/bcm63xx_udc.c
@@ -360,24 +360,30 @@
bcm_writel(val, udc->iudma_regs + off);
}
-static inline u32 usb_dmac_readl(struct bcm63xx_udc *udc, u32 off)
+static inline u32 usb_dmac_readl(struct bcm63xx_udc *udc, u32 off, int chan)
{
- return bcm_readl(udc->iudma_regs + IUDMA_DMAC_OFFSET + off);
+ return bcm_readl(udc->iudma_regs + IUDMA_DMAC_OFFSET + off +
+ (ENETDMA_CHAN_WIDTH * chan));
}
-static inline void usb_dmac_writel(struct bcm63xx_udc *udc, u32 val, u32 off)
+static inline void usb_dmac_writel(struct bcm63xx_udc *udc, u32 val, u32 off,
+ int chan)
{
- bcm_writel(val, udc->iudma_regs + IUDMA_DMAC_OFFSET + off);
+ bcm_writel(val, udc->iudma_regs + IUDMA_DMAC_OFFSET + off +
+ (ENETDMA_CHAN_WIDTH * chan));
}
-static inline u32 usb_dmas_readl(struct bcm63xx_udc *udc, u32 off)
+static inline u32 usb_dmas_readl(struct bcm63xx_udc *udc, u32 off, int chan)
{
- return bcm_readl(udc->iudma_regs + IUDMA_DMAS_OFFSET + off);
+ return bcm_readl(udc->iudma_regs + IUDMA_DMAS_OFFSET + off +
+ (ENETDMA_CHAN_WIDTH * chan));
}
-static inline void usb_dmas_writel(struct bcm63xx_udc *udc, u32 val, u32 off)
+static inline void usb_dmas_writel(struct bcm63xx_udc *udc, u32 val, u32 off,
+ int chan)
{
- bcm_writel(val, udc->iudma_regs + IUDMA_DMAS_OFFSET + off);
+ bcm_writel(val, udc->iudma_regs + IUDMA_DMAS_OFFSET + off +
+ (ENETDMA_CHAN_WIDTH * chan));
}
static inline void set_clocks(struct bcm63xx_udc *udc, bool is_enabled)
@@ -638,7 +644,7 @@
} while (!last_bd);
usb_dmac_writel(udc, ENETDMAC_CHANCFG_EN_MASK,
- ENETDMAC_CHANCFG_REG(iudma->ch_idx));
+ ENETDMAC_CHANCFG_REG, iudma->ch_idx);
}
/**
@@ -694,9 +700,9 @@
bcm63xx_fifo_reset_ep(udc, max(0, iudma->ep_num));
/* stop DMA, then wait for the hardware to wrap up */
- usb_dmac_writel(udc, 0, ENETDMAC_CHANCFG_REG(ch_idx));
+ usb_dmac_writel(udc, 0, ENETDMAC_CHANCFG_REG, ch_idx);
- while (usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG(ch_idx)) &
+ while (usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG, ch_idx) &
ENETDMAC_CHANCFG_EN_MASK) {
udelay(1);
@@ -713,10 +719,10 @@
dev_warn(udc->dev, "forcibly halting IUDMA channel %d\n",
ch_idx);
usb_dmac_writel(udc, ENETDMAC_CHANCFG_BUFHALT_MASK,
- ENETDMAC_CHANCFG_REG(ch_idx));
+ ENETDMAC_CHANCFG_REG, ch_idx);
}
}
- usb_dmac_writel(udc, ~0, ENETDMAC_IR_REG(ch_idx));
+ usb_dmac_writel(udc, ~0, ENETDMAC_IR_REG, ch_idx);
/* don't leave "live" HW-owned entries for the next guy to step on */
for (d = iudma->bd_ring; d <= iudma->end_bd; d++)
@@ -728,11 +734,11 @@
/* set up IRQs, UBUS burst size, and BD base for this channel */
usb_dmac_writel(udc, ENETDMAC_IR_BUFDONE_MASK,
- ENETDMAC_IRMASK_REG(ch_idx));
- usb_dmac_writel(udc, 8, ENETDMAC_MAXBURST_REG(ch_idx));
+ ENETDMAC_IRMASK_REG, ch_idx);
+ usb_dmac_writel(udc, 8, ENETDMAC_MAXBURST_REG, ch_idx);
- usb_dmas_writel(udc, iudma->bd_ring_dma, ENETDMAS_RSTART_REG(ch_idx));
- usb_dmas_writel(udc, 0, ENETDMAS_SRAM2_REG(ch_idx));
+ usb_dmas_writel(udc, iudma->bd_ring_dma, ENETDMAS_RSTART_REG, ch_idx);
+ usb_dmas_writel(udc, 0, ENETDMAS_SRAM2_REG, ch_idx);
}
/**
@@ -2035,7 +2041,7 @@
spin_lock(&udc->lock);
usb_dmac_writel(udc, ENETDMAC_IR_BUFDONE_MASK,
- ENETDMAC_IR_REG(iudma->ch_idx));
+ ENETDMAC_IR_REG, iudma->ch_idx);
bep = iudma->bep;
rc = iudma_read(udc, iudma);
@@ -2175,18 +2181,18 @@
seq_printf(s, " [ep%d]:\n",
max_t(int, iudma_defaults[ch_idx].ep_num, 0));
seq_printf(s, " cfg: %08x; irqstat: %08x; irqmask: %08x; maxburst: %08x\n",
- usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG(ch_idx)),
- usb_dmac_readl(udc, ENETDMAC_IR_REG(ch_idx)),
- usb_dmac_readl(udc, ENETDMAC_IRMASK_REG(ch_idx)),
- usb_dmac_readl(udc, ENETDMAC_MAXBURST_REG(ch_idx)));
+ usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG, ch_idx),
+ usb_dmac_readl(udc, ENETDMAC_IR_REG, ch_idx),
+ usb_dmac_readl(udc, ENETDMAC_IRMASK_REG, ch_idx),
+ usb_dmac_readl(udc, ENETDMAC_MAXBURST_REG, ch_idx));
- sram2 = usb_dmas_readl(udc, ENETDMAS_SRAM2_REG(ch_idx));
- sram3 = usb_dmas_readl(udc, ENETDMAS_SRAM3_REG(ch_idx));
+ sram2 = usb_dmas_readl(udc, ENETDMAS_SRAM2_REG, ch_idx);
+ sram3 = usb_dmas_readl(udc, ENETDMAS_SRAM3_REG, ch_idx);
seq_printf(s, " base: %08x; index: %04x_%04x; desc: %04x_%04x %08x\n",
- usb_dmas_readl(udc, ENETDMAS_RSTART_REG(ch_idx)),
+ usb_dmas_readl(udc, ENETDMAS_RSTART_REG, ch_idx),
sram2 >> 16, sram2 & 0xffff,
sram3 >> 16, sram3 & 0xffff,
- usb_dmas_readl(udc, ENETDMAS_SRAM4_REG(ch_idx)));
+ usb_dmas_readl(udc, ENETDMAS_SRAM4_REG, ch_idx));
seq_printf(s, " desc: %d/%d used", iudma->n_bds_used,
iudma->n_bds);
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index 306a2b5..2b43343 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -585,7 +585,6 @@
char __user *buf, size_t len, int read)
{
struct ffs_epfile *epfile = file->private_data;
- struct usb_gadget *gadget = epfile->ffs->gadget;
struct ffs_ep *ep;
char *data = NULL;
ssize_t ret, data_len;
@@ -622,6 +621,12 @@
/* Allocate & copy */
if (!halt) {
/*
+ * if we _do_ wait above, the epfile->ffs->gadget might be NULL
+ * before the waiting completes, so do not assign to 'gadget' earlier
+ */
+ struct usb_gadget *gadget = epfile->ffs->gadget;
+
+ /*
* Controller may require buffer size to be aligned to
* maxpacketsize of an out endpoint.
*/
diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c
index bf7a56b..69b76ef 100644
--- a/drivers/usb/gadget/printer.c
+++ b/drivers/usb/gadget/printer.c
@@ -1157,7 +1157,7 @@
usb_gadget_set_selfpowered(gadget);
- if (gadget->is_otg) {
+ if (gadget_is_otg(gadget)) {
otg_descriptor.bmAttributes |= USB_OTG_HNP;
printer_cfg_driver.descriptors = otg_desc;
printer_cfg_driver.bmAttributes |= USB_CONFIG_ATT_WAKEUP;
diff --git a/drivers/usb/gadget/s3c2410_udc.c b/drivers/usb/gadget/s3c2410_udc.c
index f04b2c3..dd9678f 100644
--- a/drivers/usb/gadget/s3c2410_udc.c
+++ b/drivers/usb/gadget/s3c2410_udc.c
@@ -1629,7 +1629,7 @@
ep->ep.desc = NULL;
ep->halted = 0;
INIT_LIST_HEAD(&ep->queue);
- usb_ep_set_maxpacket_limit(&ep->ep, &ep->ep.maxpacket);
+ usb_ep_set_maxpacket_limit(&ep->ep, ep->ep.maxpacket);
}
}
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 4711427..81cda09 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -685,8 +685,15 @@
struct ehci_hcd *ehci = hcd_to_ehci (hcd);
u32 status, masked_status, pcd_status = 0, cmd;
int bh;
+ unsigned long flags;
- spin_lock (&ehci->lock);
+ /*
+ * For threadirqs option we use spin_lock_irqsave() variant to prevent
+ * deadlock with ehci hrtimer callback, because hrtimer callbacks run
+ * in interrupt context even when threadirqs is specified. We can go
+ * back to spin_lock() variant when hrtimer callbacks become threaded.
+ */
+ spin_lock_irqsave(&ehci->lock, flags);
status = ehci_readl(ehci, &ehci->regs->status);
@@ -704,7 +711,7 @@
/* Shared IRQ? */
if (!masked_status || unlikely(ehci->rh_state == EHCI_RH_HALTED)) {
- spin_unlock(&ehci->lock);
+ spin_unlock_irqrestore(&ehci->lock, flags);
return IRQ_NONE;
}
@@ -815,7 +822,7 @@
if (bh)
ehci_work (ehci);
- spin_unlock (&ehci->lock);
+ spin_unlock_irqrestore(&ehci->lock, flags);
if (pcd_status)
usb_hcd_poll_rh_status(hcd);
return IRQ_HANDLED;
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index 47b858f..7ae0c4d 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -238,6 +238,7 @@
int port;
int mask;
int changed;
+ bool fs_idle_delay;
ehci_dbg(ehci, "suspend root hub\n");
@@ -272,6 +273,7 @@
ehci->bus_suspended = 0;
ehci->owned_ports = 0;
changed = 0;
+ fs_idle_delay = false;
port = HCS_N_PORTS(ehci->hcs_params);
while (port--) {
u32 __iomem *reg = &ehci->regs->port_status [port];
@@ -300,16 +302,32 @@
}
if (t1 != t2) {
+ /*
+ * On some controllers, Wake-On-Disconnect will
+ * generate false wakeup signals until the bus
+ * switches over to full-speed idle. For their
+ * sake, add a delay if we need one.
+ */
+ if ((t2 & PORT_WKDISC_E) &&
+ ehci_port_speed(ehci, t2) ==
+ USB_PORT_STAT_HIGH_SPEED)
+ fs_idle_delay = true;
ehci_writel(ehci, t2, reg);
changed = 1;
}
}
+ spin_unlock_irq(&ehci->lock);
+
+ if ((changed && ehci->has_tdi_phy_lpm) || fs_idle_delay) {
+ /*
+ * Wait for HCD to enter low-power mode or for the bus
+ * to switch to full-speed idle.
+ */
+ usleep_range(5000, 5500);
+ }
if (changed && ehci->has_tdi_phy_lpm) {
- spin_unlock_irq(&ehci->lock);
- msleep(5); /* 5 ms for HCD to enter low-power mode */
spin_lock_irq(&ehci->lock);
-
port = HCS_N_PORTS(ehci->hcs_params);
while (port--) {
u32 __iomem *hostpc_reg = &ehci->regs->hostpc[port];
@@ -322,8 +340,8 @@
port, (t3 & HOSTPC_PHCD) ?
"succeeded" : "failed");
}
+ spin_unlock_irq(&ehci->lock);
}
- spin_unlock_irq(&ehci->lock);
/* Apparently some devices need a >= 1-uframe delay here */
if (ehci->bus_suspended)
diff --git a/drivers/usb/host/xhci-dbg.c b/drivers/usb/host/xhci-dbg.c
index b016d38..eb009a4 100644
--- a/drivers/usb/host/xhci-dbg.c
+++ b/drivers/usb/host/xhci-dbg.c
@@ -203,12 +203,12 @@
addr, (unsigned int)temp);
addr = &ir_set->erst_base;
- temp_64 = readq(addr);
+ temp_64 = xhci_read_64(xhci, addr);
xhci_dbg(xhci, " %p: ir_set.erst_base = @%08llx\n",
addr, temp_64);
addr = &ir_set->erst_dequeue;
- temp_64 = readq(addr);
+ temp_64 = xhci_read_64(xhci, addr);
xhci_dbg(xhci, " %p: ir_set.erst_dequeue = @%08llx\n",
addr, temp_64);
}
@@ -412,7 +412,7 @@
{
u64 val;
- val = readq(&xhci->op_regs->cmd_ring);
+ val = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
xhci_dbg(xhci, "// xHC command ring deq ptr low bits + flags = @%08x\n",
lower_32_bits(val));
xhci_dbg(xhci, "// xHC command ring deq ptr high bits = @%08x\n",
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 873c272..bce4391 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1958,7 +1958,7 @@
xhci_warn(xhci, "WARN something wrong with SW event ring "
"dequeue ptr.\n");
/* Update HC event ring dequeue pointer */
- temp = readq(&xhci->ir_set->erst_dequeue);
+ temp = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
temp &= ERST_PTR_MASK;
/* Don't clear the EHB bit (which is RW1C) because
* there might be more events to service.
@@ -1967,7 +1967,7 @@
xhci_dbg_trace(xhci, trace_xhci_dbg_init,
"// Write event ring dequeue pointer, "
"preserving EHB bit");
- writeq(((u64) deq & (u64) ~ERST_PTR_MASK) | temp,
+ xhci_write_64(xhci, ((u64) deq & (u64) ~ERST_PTR_MASK) | temp,
&xhci->ir_set->erst_dequeue);
}
@@ -2269,7 +2269,7 @@
xhci_dbg_trace(xhci, trace_xhci_dbg_init,
"// Device context base array address = 0x%llx (DMA), %p (virt)",
(unsigned long long)xhci->dcbaa->dma, xhci->dcbaa);
- writeq(dma, &xhci->op_regs->dcbaa_ptr);
+ xhci_write_64(xhci, dma, &xhci->op_regs->dcbaa_ptr);
/*
* Initialize the ring segment pool. The ring must be a contiguous
@@ -2312,13 +2312,13 @@
(unsigned long long)xhci->cmd_ring->first_seg->dma);
/* Set the address in the Command Ring Control register */
- val_64 = readq(&xhci->op_regs->cmd_ring);
+ val_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
val_64 = (val_64 & (u64) CMD_RING_RSVD_BITS) |
(xhci->cmd_ring->first_seg->dma & (u64) ~CMD_RING_RSVD_BITS) |
xhci->cmd_ring->cycle_state;
xhci_dbg_trace(xhci, trace_xhci_dbg_init,
"// Setting command ring address to 0x%x", val);
- writeq(val_64, &xhci->op_regs->cmd_ring);
+ xhci_write_64(xhci, val_64, &xhci->op_regs->cmd_ring);
xhci_dbg_cmd_ptrs(xhci);
xhci->lpm_command = xhci_alloc_command(xhci, true, true, flags);
@@ -2396,10 +2396,10 @@
xhci_dbg_trace(xhci, trace_xhci_dbg_init,
"// Set ERST base address for ir_set 0 = 0x%llx",
(unsigned long long)xhci->erst.erst_dma_addr);
- val_64 = readq(&xhci->ir_set->erst_base);
+ val_64 = xhci_read_64(xhci, &xhci->ir_set->erst_base);
val_64 &= ERST_PTR_MASK;
val_64 |= (xhci->erst.erst_dma_addr & (u64) ~ERST_PTR_MASK);
- writeq(val_64, &xhci->ir_set->erst_base);
+ xhci_write_64(xhci, val_64, &xhci->ir_set->erst_base);
/* Set the event ring dequeue address */
xhci_set_hc_event_deq(xhci);
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 3c898c1..04f986d 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -142,6 +142,11 @@
"QUIRK: Resetting on resume");
xhci->quirks |= XHCI_TRUST_TX_LENGTH;
}
+ if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
+ pdev->device == 0x0015 &&
+ pdev->subsystem_vendor == PCI_VENDOR_ID_SAMSUNG &&
+ pdev->subsystem_device == 0xc0cd)
+ xhci->quirks |= XHCI_RESET_ON_RESUME;
if (pdev->vendor == PCI_VENDOR_ID_VIA)
xhci->quirks |= XHCI_RESET_ON_RESUME;
}
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index a0b248c..0ed64eb 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -307,13 +307,14 @@
return 0;
}
- temp_64 = readq(&xhci->op_regs->cmd_ring);
+ temp_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
if (!(temp_64 & CMD_RING_RUNNING)) {
xhci_dbg(xhci, "Command ring had been stopped\n");
return 0;
}
xhci->cmd_ring_state = CMD_RING_STATE_ABORTED;
- writeq(temp_64 | CMD_RING_ABORT, &xhci->op_regs->cmd_ring);
+ xhci_write_64(xhci, temp_64 | CMD_RING_ABORT,
+ &xhci->op_regs->cmd_ring);
/* Section 4.6.1.2 of xHCI 1.0 spec says software should
* time the completion od all xHCI commands, including
@@ -2864,8 +2865,9 @@
/* Clear the event handler busy flag (RW1C);
* the event ring should be empty.
*/
- temp_64 = readq(&xhci->ir_set->erst_dequeue);
- writeq(temp_64 | ERST_EHB, &xhci->ir_set->erst_dequeue);
+ temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
+ xhci_write_64(xhci, temp_64 | ERST_EHB,
+ &xhci->ir_set->erst_dequeue);
spin_unlock(&xhci->lock);
return IRQ_HANDLED;
@@ -2877,7 +2879,7 @@
*/
while (xhci_handle_event(xhci) > 0) {}
- temp_64 = readq(&xhci->ir_set->erst_dequeue);
+ temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
/* If necessary, update the HW's version of the event ring deq ptr. */
if (event_ring_deq != xhci->event_ring->dequeue) {
deq = xhci_trb_virt_to_dma(xhci->event_ring->deq_seg,
@@ -2892,7 +2894,7 @@
/* Clear the event handler busy flag (RW1C); event ring is empty. */
temp_64 |= ERST_EHB;
- writeq(temp_64, &xhci->ir_set->erst_dequeue);
+ xhci_write_64(xhci, temp_64, &xhci->ir_set->erst_dequeue);
spin_unlock(&xhci->lock);
@@ -2965,58 +2967,8 @@
}
while (1) {
- if (room_on_ring(xhci, ep_ring, num_trbs)) {
- union xhci_trb *trb = ep_ring->enqueue;
- unsigned int usable = ep_ring->enq_seg->trbs +
- TRBS_PER_SEGMENT - 1 - trb;
- u32 nop_cmd;
-
- /*
- * Section 4.11.7.1 TD Fragments states that a link
- * TRB must only occur at the boundary between
- * data bursts (eg 512 bytes for 480M).
- * While it is possible to split a large fragment
- * we don't know the size yet.
- * Simplest solution is to fill the trb before the
- * LINK with nop commands.
- */
- if (num_trbs == 1 || num_trbs <= usable || usable == 0)
- break;
-
- if (ep_ring->type != TYPE_BULK)
- /*
- * While isoc transfers might have a buffer that
- * crosses a 64k boundary it is unlikely.
- * Since we can't add NOPs without generating
- * gaps in the traffic just hope it never
- * happens at the end of the ring.
- * This could be fixed by writing a LINK TRB
- * instead of the first NOP - however the
- * TRB_TYPE_LINK_LE32() calls would all need
- * changing to check the ring length.
- */
- break;
-
- if (num_trbs >= TRBS_PER_SEGMENT) {
- xhci_err(xhci, "Too many fragments %d, max %d\n",
- num_trbs, TRBS_PER_SEGMENT - 1);
- return -EINVAL;
- }
-
- nop_cmd = cpu_to_le32(TRB_TYPE(TRB_TR_NOOP) |
- ep_ring->cycle_state);
- ep_ring->num_trbs_free -= usable;
- do {
- trb->generic.field[0] = 0;
- trb->generic.field[1] = 0;
- trb->generic.field[2] = 0;
- trb->generic.field[3] = nop_cmd;
- trb++;
- } while (--usable);
- ep_ring->enqueue = trb;
- if (room_on_ring(xhci, ep_ring, num_trbs))
- break;
- }
+ if (room_on_ring(xhci, ep_ring, num_trbs))
+ break;
if (ep_ring == xhci->cmd_ring) {
xhci_err(xhci, "Do not support expand command ring\n");
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index ad36439..924a6cc 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -611,7 +611,7 @@
xhci_dbg(xhci, "Event ring:\n");
xhci_debug_ring(xhci, xhci->event_ring);
xhci_dbg_ring_ptrs(xhci, xhci->event_ring);
- temp_64 = readq(&xhci->ir_set->erst_dequeue);
+ temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
temp_64 &= ~ERST_PTR_MASK;
xhci_dbg_trace(xhci, trace_xhci_dbg_init,
"ERST deq = 64'h%0lx", (long unsigned int) temp_64);
@@ -756,11 +756,11 @@
{
xhci->s3.command = readl(&xhci->op_regs->command);
xhci->s3.dev_nt = readl(&xhci->op_regs->dev_notification);
- xhci->s3.dcbaa_ptr = readq(&xhci->op_regs->dcbaa_ptr);
+ xhci->s3.dcbaa_ptr = xhci_read_64(xhci, &xhci->op_regs->dcbaa_ptr);
xhci->s3.config_reg = readl(&xhci->op_regs->config_reg);
xhci->s3.erst_size = readl(&xhci->ir_set->erst_size);
- xhci->s3.erst_base = readq(&xhci->ir_set->erst_base);
- xhci->s3.erst_dequeue = readq(&xhci->ir_set->erst_dequeue);
+ xhci->s3.erst_base = xhci_read_64(xhci, &xhci->ir_set->erst_base);
+ xhci->s3.erst_dequeue = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
xhci->s3.irq_pending = readl(&xhci->ir_set->irq_pending);
xhci->s3.irq_control = readl(&xhci->ir_set->irq_control);
}
@@ -769,11 +769,11 @@
{
writel(xhci->s3.command, &xhci->op_regs->command);
writel(xhci->s3.dev_nt, &xhci->op_regs->dev_notification);
- writeq(xhci->s3.dcbaa_ptr, &xhci->op_regs->dcbaa_ptr);
+ xhci_write_64(xhci, xhci->s3.dcbaa_ptr, &xhci->op_regs->dcbaa_ptr);
writel(xhci->s3.config_reg, &xhci->op_regs->config_reg);
writel(xhci->s3.erst_size, &xhci->ir_set->erst_size);
- writeq(xhci->s3.erst_base, &xhci->ir_set->erst_base);
- writeq(xhci->s3.erst_dequeue, &xhci->ir_set->erst_dequeue);
+ xhci_write_64(xhci, xhci->s3.erst_base, &xhci->ir_set->erst_base);
+ xhci_write_64(xhci, xhci->s3.erst_dequeue, &xhci->ir_set->erst_dequeue);
writel(xhci->s3.irq_pending, &xhci->ir_set->irq_pending);
writel(xhci->s3.irq_control, &xhci->ir_set->irq_control);
}
@@ -783,7 +783,7 @@
u64 val_64;
/* step 2: initialize command ring buffer */
- val_64 = readq(&xhci->op_regs->cmd_ring);
+ val_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
val_64 = (val_64 & (u64) CMD_RING_RSVD_BITS) |
(xhci_trb_virt_to_dma(xhci->cmd_ring->deq_seg,
xhci->cmd_ring->dequeue) &
@@ -792,7 +792,7 @@
xhci_dbg_trace(xhci, trace_xhci_dbg_init,
"// Setting command ring address to 0x%llx",
(long unsigned long) val_64);
- writeq(val_64, &xhci->op_regs->cmd_ring);
+ xhci_write_64(xhci, val_64, &xhci->op_regs->cmd_ring);
}
/*
@@ -3842,7 +3842,7 @@
if (ret) {
return ret;
}
- temp_64 = readq(&xhci->op_regs->dcbaa_ptr);
+ temp_64 = xhci_read_64(xhci, &xhci->op_regs->dcbaa_ptr);
xhci_dbg_trace(xhci, trace_xhci_dbg_address,
"Op regs DCBAA ptr = %#016llx", temp_64);
xhci_dbg_trace(xhci, trace_xhci_dbg_address,
@@ -4730,8 +4730,8 @@
struct device *dev = hcd->self.controller;
int retval;
- /* Limit the block layer scatter-gather lists to half a segment. */
- hcd->self.sg_tablesize = TRBS_PER_SEGMENT / 2;
+ /* Accept arbitrarily long scatter-gather lists */
+ hcd->self.sg_tablesize = ~0;
/* support to build packet from discontinuous buffers */
hcd->self.no_sg_constraint = 1;
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index f8416639..58ed9d0 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -28,17 +28,6 @@
#include <linux/kernel.h>
#include <linux/usb/hcd.h>
-/*
- * Registers should always be accessed with double word or quad word accesses.
- *
- * Some xHCI implementations may support 64-bit address pointers. Registers
- * with 64-bit address pointers should be written to with dword accesses by
- * writing the low dword first (ptr[0]), then the high dword (ptr[1]) second.
- * xHCI implementations that do not support 64-bit address pointers will ignore
- * the high dword, and write order is irrelevant.
- */
-#include <asm-generic/io-64-nonatomic-lo-hi.h>
-
/* Code sharing between pci-quirks and xhci hcd */
#include "xhci-ext-caps.h"
#include "pci-quirks.h"
@@ -1279,7 +1268,7 @@
* since the command ring is 64-byte aligned.
* It must also be greater than 16.
*/
-#define TRBS_PER_SEGMENT 256
+#define TRBS_PER_SEGMENT 64
/* Allow two commands + a link TRB, along with any reserved command TRBs */
#define MAX_RSVD_CMD_TRBS (TRBS_PER_SEGMENT - 3)
#define TRB_SEGMENT_SIZE (TRBS_PER_SEGMENT*16)
@@ -1614,6 +1603,34 @@
#define xhci_warn_ratelimited(xhci, fmt, args...) \
dev_warn_ratelimited(xhci_to_hcd(xhci)->self.controller , fmt , ## args)
+/*
+ * Registers should always be accessed with double word or quad word accesses.
+ *
+ * Some xHCI implementations may support 64-bit address pointers. Registers
+ * with 64-bit address pointers should be written to with dword accesses by
+ * writing the low dword first (ptr[0]), then the high dword (ptr[1]) second.
+ * xHCI implementations that do not support 64-bit address pointers will ignore
+ * the high dword, and write order is irrelevant.
+ */
+static inline u64 xhci_read_64(const struct xhci_hcd *xhci,
+ __le64 __iomem *regs)
+{
+ __u32 __iomem *ptr = (__u32 __iomem *) regs;
+ u64 val_lo = readl(ptr);
+ u64 val_hi = readl(ptr + 1);
+ return val_lo + (val_hi << 32);
+}
+static inline void xhci_write_64(struct xhci_hcd *xhci,
+ const u64 val, __le64 __iomem *regs)
+{
+ __u32 __iomem *ptr = (__u32 __iomem *) regs;
+ u32 val_lo = lower_32_bits(val);
+ u32 val_hi = upper_32_bits(val);
+
+ writel(val_lo, ptr);
+ writel(val_hi, ptr + 1);
+}
+
static inline int xhci_link_trb_quirk(struct xhci_hcd *xhci)
{
return xhci->quirks & XHCI_LINK_TRB_QUIRK;
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index fc192ad..239ad0b 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -477,8 +477,11 @@
musb->port1_status |=
(USB_PORT_STAT_C_SUSPEND << 16)
| MUSB_PORT_STAT_RESUME;
+ musb->rh_timer = jiffies
+ + msecs_to_jiffies(20);
schedule_delayed_work(
- &musb->finish_resume_work, 20);
+ &musb->finish_resume_work,
+ msecs_to_jiffies(20));
musb->xceiv->state = OTG_STATE_A_HOST;
musb->is_active = 1;
@@ -2157,11 +2160,19 @@
void __iomem *musb_base = musb->mregs;
void __iomem *ep_target_regs;
void __iomem *epio;
+ u8 power;
musb_writew(musb_base, MUSB_FRAME, musb->context.frame);
musb_writeb(musb_base, MUSB_TESTMODE, musb->context.testmode);
musb_write_ulpi_buscontrol(musb->mregs, musb->context.busctl);
- musb_writeb(musb_base, MUSB_POWER, musb->context.power);
+
+ /* Don't affect SUSPENDM/RESUME bits in POWER reg */
+ power = musb_readb(musb_base, MUSB_POWER);
+ power &= MUSB_POWER_SUSPENDM | MUSB_POWER_RESUME;
+ musb->context.power &= ~(MUSB_POWER_SUSPENDM | MUSB_POWER_RESUME);
+ power |= musb->context.power;
+ musb_writeb(musb_base, MUSB_POWER, power);
+
musb_writew(musb_base, MUSB_INTRTXE, musb->intrtxe);
musb_writew(musb_base, MUSB_INTRRXE, musb->intrrxe);
musb_writeb(musb_base, MUSB_INTRUSBE, musb->context.intrusbe);
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index ed45572..abb38c3 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -1183,6 +1183,9 @@
csr = MUSB_CSR0_H_STATUSPKT
| MUSB_CSR0_TXPKTRDY;
+ /* disable ping token in status phase */
+ csr |= MUSB_CSR0_H_DIS_PING;
+
/* flag status stage */
musb->ep0_stage = MUSB_EP0_STATUS;
diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c
index eb63443..e2d2d8c 100644
--- a/drivers/usb/musb/musb_virthub.c
+++ b/drivers/usb/musb/musb_virthub.c
@@ -135,7 +135,8 @@
/* later, GetPortStatus will stop RESUME signaling */
musb->port1_status |= MUSB_PORT_STAT_RESUME;
- schedule_delayed_work(&musb->finish_resume_work, 20);
+ schedule_delayed_work(&musb->finish_resume_work,
+ msecs_to_jiffies(20));
}
}
@@ -158,7 +159,6 @@
*/
power = musb_readb(mbase, MUSB_POWER);
if (do_reset) {
-
/*
* If RESUME is set, we must make sure it stays minimum 20 ms.
* Then we must clear RESUME and wait a bit to let musb start
@@ -167,11 +167,22 @@
* detected".
*/
if (power & MUSB_POWER_RESUME) {
- while (time_before(jiffies, musb->rh_timer))
- msleep(1);
+ long remain = (unsigned long) musb->rh_timer - jiffies;
+
+ if (musb->rh_timer > 0 && remain > 0) {
+ /* take into account the minimum delay after resume */
+ schedule_delayed_work(
+ &musb->deassert_reset_work, remain);
+ return;
+ }
+
musb_writeb(mbase, MUSB_POWER,
- power & ~MUSB_POWER_RESUME);
- msleep(1);
+ power & ~MUSB_POWER_RESUME);
+
+ /* Give the core 1 ms to clear MUSB_POWER_RESUME */
+ schedule_delayed_work(&musb->deassert_reset_work,
+ msecs_to_jiffies(1));
+ return;
}
power &= 0xf0;
@@ -180,7 +191,8 @@
musb->port1_status |= USB_PORT_STAT_RESET;
musb->port1_status &= ~USB_PORT_STAT_ENABLE;
- schedule_delayed_work(&musb->deassert_reset_work, 50);
+ schedule_delayed_work(&musb->deassert_reset_work,
+ msecs_to_jiffies(50));
} else {
dev_dbg(musb->controller, "root port reset stopped\n");
musb_writeb(mbase, MUSB_POWER,
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index 2a408cd..8aa59a2 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -659,7 +659,6 @@
OTG_INTERFSEL);
omap2430_low_level_exit(musb);
- phy_power_off(musb->phy);
}
return 0;
@@ -674,7 +673,6 @@
omap2430_low_level_init(musb);
musb_writel(musb->mregs, OTG_INTERFSEL,
musb->context.otg_interfsel);
- phy_power_on(musb->phy);
}
return 0;
diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c
index 8546c8d..d204f74 100644
--- a/drivers/usb/phy/phy-msm-usb.c
+++ b/drivers/usb/phy/phy-msm-usb.c
@@ -159,32 +159,6 @@
return rc;
}
-#ifdef CONFIG_PM_SLEEP
-#define USB_PHY_SUSP_DIG_VOL 500000
-static int msm_hsusb_config_vddcx(int high)
-{
- int max_vol = USB_PHY_VDD_DIG_VOL_MAX;
- int min_vol;
- int ret;
-
- if (high)
- min_vol = USB_PHY_VDD_DIG_VOL_MIN;
- else
- min_vol = USB_PHY_SUSP_DIG_VOL;
-
- ret = regulator_set_voltage(hsusb_vddcx, min_vol, max_vol);
- if (ret) {
- pr_err("%s: unable to set the voltage for regulator "
- "HSUSB_VDDCX\n", __func__);
- return ret;
- }
-
- pr_debug("%s: min_vol:%d max_vol:%d\n", __func__, min_vol, max_vol);
-
- return ret;
-}
-#endif
-
static int msm_hsusb_ldo_set_mode(int on)
{
int ret = 0;
@@ -440,7 +414,32 @@
#define PHY_SUSPEND_TIMEOUT_USEC (500 * 1000)
#define PHY_RESUME_TIMEOUT_USEC (100 * 1000)
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
+
+#define USB_PHY_SUSP_DIG_VOL 500000
+static int msm_hsusb_config_vddcx(int high)
+{
+ int max_vol = USB_PHY_VDD_DIG_VOL_MAX;
+ int min_vol;
+ int ret;
+
+ if (high)
+ min_vol = USB_PHY_VDD_DIG_VOL_MIN;
+ else
+ min_vol = USB_PHY_SUSP_DIG_VOL;
+
+ ret = regulator_set_voltage(hsusb_vddcx, min_vol, max_vol);
+ if (ret) {
+ pr_err("%s: unable to set the voltage for regulator "
+ "HSUSB_VDDCX\n", __func__);
+ return ret;
+ }
+
+ pr_debug("%s: min_vol:%d max_vol:%d\n", __func__, min_vol, max_vol);
+
+ return ret;
+}
+
static int msm_otg_suspend(struct msm_otg *motg)
{
struct usb_phy *phy = &motg->phy;
@@ -1733,22 +1732,18 @@
}
#endif
-#ifdef CONFIG_PM
static const struct dev_pm_ops msm_otg_dev_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(msm_otg_pm_suspend, msm_otg_pm_resume)
SET_RUNTIME_PM_OPS(msm_otg_runtime_suspend, msm_otg_runtime_resume,
msm_otg_runtime_idle)
};
-#endif
static struct platform_driver msm_otg_driver = {
.remove = msm_otg_remove,
.driver = {
.name = DRIVER_NAME,
.owner = THIS_MODULE,
-#ifdef CONFIG_PM
.pm = &msm_otg_dev_pm_ops,
-#endif
},
};
diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c
index e6f61e4..8afa813 100644
--- a/drivers/usb/phy/phy.c
+++ b/drivers/usb/phy/phy.c
@@ -130,7 +130,7 @@
phy = __usb_find_phy(&phy_list, type);
if (IS_ERR(phy) || !try_module_get(phy->dev->driver->owner)) {
- pr_err("unable to find transceiver of type %s\n",
+ pr_debug("PHY: unable to find transceiver of type %s\n",
usb_phy_type_string(type));
goto err0;
}
@@ -228,7 +228,7 @@
phy = __usb_find_phy_dev(dev, &phy_bind_list, index);
if (IS_ERR(phy) || !try_module_get(phy->dev->driver->owner)) {
- pr_err("unable to find transceiver\n");
+ dev_dbg(dev, "unable to find transceiver\n");
goto err0;
}
@@ -424,10 +424,8 @@
unsigned long flags;
phy_bind = kzalloc(sizeof(*phy_bind), GFP_KERNEL);
- if (!phy_bind) {
- pr_err("phy_bind(): No memory for phy_bind");
+ if (!phy_bind)
return -ENOMEM;
- }
phy_bind->dev_name = dev_name;
phy_bind->phy_dev_name = phy_dev_name;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index ce0d7b0..44ab129 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -152,6 +152,7 @@
{ USB_DEVICE(FTDI_VID, FTDI_CANUSB_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_CANDAPTER_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_NXTCAM_PID) },
+ { USB_DEVICE(FTDI_VID, FTDI_EV3CON_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_0_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_1_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_2_PID) },
@@ -191,6 +192,8 @@
{ USB_DEVICE(INTERBIOMETRICS_VID, INTERBIOMETRICS_IOBOARD_PID) },
{ USB_DEVICE(INTERBIOMETRICS_VID, INTERBIOMETRICS_MINI_IOBOARD_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_SPROG_II) },
+ { USB_DEVICE(FTDI_VID, FTDI_TAGSYS_LP101_PID) },
+ { USB_DEVICE(FTDI_VID, FTDI_TAGSYS_P200X_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_LENZ_LIUSB_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_XF_632_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_XF_634_PID) },
@@ -904,6 +907,8 @@
/* Crucible Devices */
{ USB_DEVICE(FTDI_VID, FTDI_CT_COMET_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_Z3X_PID) },
+ /* Cressi Devices */
+ { USB_DEVICE(FTDI_VID, FTDI_CRESSI_PID) },
{ } /* Terminating entry */
};
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index a7019d1..e599fbf 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -50,6 +50,7 @@
#define TI_XDS100V2_PID 0xa6d0
#define FTDI_NXTCAM_PID 0xABB8 /* NXTCam for Mindstorms NXT */
+#define FTDI_EV3CON_PID 0xABB9 /* Mindstorms EV3 Console Adapter */
/* US Interface Navigator (http://www.usinterface.com/) */
#define FTDI_USINT_CAT_PID 0xb810 /* Navigator CAT and 2nd PTT lines */
@@ -363,6 +364,12 @@
/* Sprog II (Andrew Crosland's SprogII DCC interface) */
#define FTDI_SPROG_II 0xF0C8
+/*
+ * Two of the Tagsys RFID Readers
+ */
+#define FTDI_TAGSYS_LP101_PID 0xF0E9 /* Tagsys L-P101 RFID*/
+#define FTDI_TAGSYS_P200X_PID 0xF0EE /* Tagsys Medio P200x RFID*/
+
/* an infrared receiver for user access control with IR tags */
#define FTDI_PIEGROUP_PID 0xF208 /* Product Id */
@@ -1313,3 +1320,9 @@
* Manufacturer: Smart GSM Team
*/
#define FTDI_Z3X_PID 0x0011
+
+/*
+ * Product: Cressi PC Interface
+ * Manufacturer: Cressi
+ */
+#define FTDI_CRESSI_PID 0x87d0
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 5c86f57..68fc9fe 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1362,7 +1362,8 @@
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1267, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1268, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1269, 0xff, 0xff, 0xff) },
- { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1270, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1270, 0xff, 0xff, 0xff),
+ .driver_info = (kernel_ulong_t)&net_intf5_blacklist },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1271, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1272, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1273, 0xff, 0xff, 0xff) },
@@ -1525,7 +1526,8 @@
/* Cinterion */
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_E) },
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_P) },
- { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8) },
+ { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8),
+ .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX) },
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PLXX),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index c65437c..968a402 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -139,6 +139,9 @@
{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 0)}, /* Sierra Wireless EM7700 Device Management */
{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 2)}, /* Sierra Wireless EM7700 NMEA */
{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 3)}, /* Sierra Wireless EM7700 Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 0)}, /* Netgear AirCard 340U Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 2)}, /* Netgear AirCard 340U NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 3)}, /* Netgear AirCard 340U Modem */
{ } /* Terminating entry */
};
diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c
index f112b07..fb79775 100644
--- a/drivers/usb/serial/usb-serial-simple.c
+++ b/drivers/usb/serial/usb-serial-simple.c
@@ -71,7 +71,8 @@
/* Suunto ANT+ USB Driver */
#define SUUNTO_IDS() \
- { USB_DEVICE(0x0fcf, 0x1008) }
+ { USB_DEVICE(0x0fcf, 0x1008) }, \
+ { USB_DEVICE(0x0fcf, 0x1009) } /* Dynastream ANT USB-m Stick */
DEVICE(suunto, SUUNTO_IDS);
/* Siemens USB/MPI adapter */
diff --git a/drivers/usb/storage/Kconfig b/drivers/usb/storage/Kconfig
index 8470e1b..1dd0604 100644
--- a/drivers/usb/storage/Kconfig
+++ b/drivers/usb/storage/Kconfig
@@ -18,7 +18,9 @@
This option depends on 'SCSI' support being enabled, but you
probably also need 'SCSI device support: SCSI disk support'
- (BLK_DEV_SD) for most USB storage devices.
+ (BLK_DEV_SD) for most USB storage devices. Some devices also
+ will require 'Probe all LUNs on each SCSI device'
+ (SCSI_MULTI_LUN).
To compile this driver as a module, choose M here: the
module will be called usb-storage.
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index 18509e6..9d38ddc 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -78,6 +78,8 @@
static int slave_alloc (struct scsi_device *sdev)
{
+ struct us_data *us = host_to_us(sdev->host);
+
/*
* Set the INQUIRY transfer length to 36. We don't use any of
* the extra data and many devices choke if asked for more or
@@ -102,6 +104,10 @@
*/
blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1));
+ /* Tell the SCSI layer if we know there is more than one LUN */
+ if (us->protocol == USB_PR_BULK && us->max_lun > 0)
+ sdev->sdev_bflags |= BLIST_FORCELUN;
+
return 0;
}
diff --git a/drivers/usb/storage/unusual_cypress.h b/drivers/usb/storage/unusual_cypress.h
index 65a6a75..82e8ed0 100644
--- a/drivers/usb/storage/unusual_cypress.h
+++ b/drivers/usb/storage/unusual_cypress.h
@@ -31,7 +31,7 @@
"Cypress ISD-300LP",
USB_SC_CYP_ATACB, USB_PR_DEVICE, NULL, 0),
-UNUSUAL_DEV( 0x14cd, 0x6116, 0x0000, 0x0219,
+UNUSUAL_DEV( 0x14cd, 0x6116, 0x0160, 0x0160,
"Super Top",
"USB 2.0 SATA BRIDGE",
USB_SC_CYP_ATACB, USB_PR_DEVICE, NULL, 0),
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index ad06255..adbeb25 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1455,6 +1455,13 @@
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_FIX_CAPACITY ),
+/* Reported by Moritz Moeller-Herrmann <moritz-kernel@moeller-herrmann.de> */
+UNUSUAL_DEV( 0x0fca, 0x8004, 0x0201, 0x0201,
+ "Research In Motion",
+ "BlackBerry Bold 9000",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_MAX_SECTORS_64 ),
+
/* Reported by Michael Stattmann <michael@stattmann.com> */
UNUSUAL_DEV( 0x0fce, 0xd008, 0x0000, 0x0000,
"Sony Ericsson",
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 4fb7a8f..54af4e9 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -186,12 +186,12 @@
if (pfn_valid(pfn)) {
bool reserved;
struct page *tail = pfn_to_page(pfn);
- struct page *head = compound_trans_head(tail);
+ struct page *head = compound_head(tail);
reserved = !!(PageReserved(head));
if (head != tail) {
/*
* "head" is not a dangling pointer
- * (compound_trans_head takes care of that)
+ * (compound_head takes care of that)
* but the hugepage may have been split
* from under us (and we may not hold a
* reference count on the head page so it can
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 9a68409..e1e22e0 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -70,7 +70,12 @@
};
struct vhost_net_ubuf_ref {
- struct kref kref;
+ /* refcount follows semantics similar to kref:
+ * 0: object is released
+ * 1: no outstanding ubufs
+ * >1: outstanding ubufs
+ */
+ atomic_t refcount;
wait_queue_head_t wait;
struct vhost_virtqueue *vq;
};
@@ -116,14 +121,6 @@
vhost_net_zcopy_mask |= 0x1 << vq;
}
-static void vhost_net_zerocopy_done_signal(struct kref *kref)
-{
- struct vhost_net_ubuf_ref *ubufs;
-
- ubufs = container_of(kref, struct vhost_net_ubuf_ref, kref);
- wake_up(&ubufs->wait);
-}
-
static struct vhost_net_ubuf_ref *
vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy)
{
@@ -134,21 +131,24 @@
ubufs = kmalloc(sizeof(*ubufs), GFP_KERNEL);
if (!ubufs)
return ERR_PTR(-ENOMEM);
- kref_init(&ubufs->kref);
+ atomic_set(&ubufs->refcount, 1);
init_waitqueue_head(&ubufs->wait);
ubufs->vq = vq;
return ubufs;
}
-static void vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs)
+static int vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs)
{
- kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal);
+ int r = atomic_sub_return(1, &ubufs->refcount);
+ if (unlikely(!r))
+ wake_up(&ubufs->wait);
+ return r;
}
static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs)
{
- kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal);
- wait_event(ubufs->wait, !atomic_read(&ubufs->kref.refcount));
+ vhost_net_ubuf_put(ubufs);
+ wait_event(ubufs->wait, !atomic_read(&ubufs->refcount));
}
static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs)
@@ -306,23 +306,26 @@
{
struct vhost_net_ubuf_ref *ubufs = ubuf->ctx;
struct vhost_virtqueue *vq = ubufs->vq;
- int cnt = atomic_read(&ubufs->kref.refcount);
+ int cnt;
+
+ rcu_read_lock_bh();
/* set len to mark this desc buffers done DMA */
vq->heads[ubuf->desc].len = success ?
VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
- vhost_net_ubuf_put(ubufs);
+ cnt = vhost_net_ubuf_put(ubufs);
/*
* Trigger polling thread if guest stopped submitting new buffers:
- * in this case, the refcount after decrement will eventually reach 1
- * so here it is 2.
+ * in this case, the refcount after decrement will eventually reach 1.
* We also trigger polling periodically after each 16 packets
* (the value 16 here is more or less arbitrary, it's tuned to trigger
* less than 10% of times).
*/
- if (cnt <= 2 || !(cnt % 16))
+ if (cnt <= 1 || !(cnt % 16))
vhost_poll_queue(&vq->poll);
+
+ rcu_read_unlock_bh();
}
/* Expects to be always run from workqueue - which acts as
@@ -420,7 +423,7 @@
msg.msg_control = ubuf;
msg.msg_controllen = sizeof(ubuf);
ubufs = nvq->ubufs;
- kref_get(&ubufs->kref);
+ atomic_inc(&ubufs->refcount);
nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
} else {
msg.msg_control = NULL;
@@ -502,9 +505,13 @@
r = -ENOBUFS;
goto err;
}
- d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
+ r = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
ARRAY_SIZE(vq->iov) - seg, &out,
&in, log, log_num);
+ if (unlikely(r < 0))
+ goto err;
+
+ d = r;
if (d == vq->num) {
r = 0;
goto err;
@@ -529,6 +536,12 @@
*iovcount = seg;
if (unlikely(log))
*log_num = nlogs;
+
+ /* Detect overrun */
+ if (unlikely(datalen > 0)) {
+ r = UIO_MAXIOV + 1;
+ goto err;
+ }
return headcount;
err:
vhost_discard_vq_desc(vq, headcount);
@@ -584,6 +597,14 @@
/* On error, stop handling until the next kick. */
if (unlikely(headcount < 0))
break;
+ /* On overrun, truncate and discard */
+ if (unlikely(headcount > UIO_MAXIOV)) {
+ msg.msg_iovlen = 1;
+ err = sock->ops->recvmsg(NULL, sock, &msg,
+ 1, MSG_DONTWAIT | MSG_TRUNC);
+ pr_debug("Discarded rx packet: len %zd\n", sock_len);
+ continue;
+ }
/* OK, now we need to know about added descriptors. */
if (!headcount) {
if (unlikely(vhost_enable_notify(&net->dev, vq))) {
@@ -780,7 +801,7 @@
vhost_net_ubuf_put_and_wait(n->vqs[VHOST_NET_VQ_TX].ubufs);
mutex_lock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex);
n->tx_flush = false;
- kref_init(&n->vqs[VHOST_NET_VQ_TX].ubufs->kref);
+ atomic_set(&n->vqs[VHOST_NET_VQ_TX].ubufs->refcount, 1);
mutex_unlock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex);
}
}
@@ -800,6 +821,8 @@
fput(tx_sock->file);
if (rx_sock)
fput(rx_sock->file);
+ /* Make sure no callbacks are outstanding */
+ synchronize_rcu_bh();
/* We do an extra flush before freeing memory,
* since jobs can re-queue themselves. */
vhost_net_flush(n);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 0a025b8..e48d4a6 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1001,6 +1001,12 @@
break;
}
+ /* virtio-scsi spec requires byte 0 of the lun to be 1 */
+ if (unlikely(v_req.lun[0] != 1)) {
+ vhost_scsi_send_bad_target(vs, vq, head, out);
+ continue;
+ }
+
/* Extract the tpgt */
target = v_req.lun[1];
tpg = ACCESS_ONCE(vs_tpg[target]);
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 22262a3..dade5b7 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -364,7 +364,7 @@
config FB_IMX
tristate "Freescale i.MX1/21/25/27 LCD support"
- depends on FB && IMX_HAVE_PLATFORM_IMX_FB
+ depends on FB && ARCH_MXC
select FB_CFB_FILLRECT
select FB_CFB_COPYAREA
select FB_CFB_IMAGEBLIT
diff --git a/drivers/video/exynos/Kconfig b/drivers/video/exynos/Kconfig
index 1129d0e..75c8a8e 100644
--- a/drivers/video/exynos/Kconfig
+++ b/drivers/video/exynos/Kconfig
@@ -22,7 +22,8 @@
config EXYNOS_LCD_S6E8AX0
bool "S6E8AX0 MIPI AMOLED LCD Driver"
- depends on (EXYNOS_MIPI_DSI && BACKLIGHT_CLASS_DEVICE && LCD_CLASS_DEVICE)
+ depends on EXYNOS_MIPI_DSI && BACKLIGHT_CLASS_DEVICE
+ depends on (LCD_CLASS_DEVICE = y)
default n
help
If you have an S6E8AX0 MIPI AMOLED LCD Panel, say Y to enable its
diff --git a/drivers/video/omap2/dss/dispc.c b/drivers/video/omap2/dss/dispc.c
index bbeb8dd..77d6221 100644
--- a/drivers/video/omap2/dss/dispc.c
+++ b/drivers/video/omap2/dss/dispc.c
@@ -2160,8 +2160,8 @@
*five_taps = false;
do {
- in_height = DIV_ROUND_UP(height, *decim_y);
- in_width = DIV_ROUND_UP(width, *decim_x);
+ in_height = height / *decim_y;
+ in_width = width / *decim_x;
*core_clk = dispc.feat->calc_core_clk(pclk, in_width,
in_height, out_width, out_height, mem_to_mem);
error = (in_width > maxsinglelinewidth || !*core_clk ||
@@ -2199,8 +2199,8 @@
dss_feat_get_param_max(FEAT_PARAM_LINEWIDTH);
do {
- in_height = DIV_ROUND_UP(height, *decim_y);
- in_width = DIV_ROUND_UP(width, *decim_x);
+ in_height = height / *decim_y;
+ in_width = width / *decim_x;
*five_taps = in_height > out_height;
if (in_width > maxsinglelinewidth)
@@ -2268,7 +2268,7 @@
{
u16 in_width, in_width_max;
int decim_x_min = *decim_x;
- u16 in_height = DIV_ROUND_UP(height, *decim_y);
+ u16 in_height = height / *decim_y;
const int maxsinglelinewidth =
dss_feat_get_param_max(FEAT_PARAM_LINEWIDTH);
const int maxdownscale = dss_feat_get_param_max(FEAT_PARAM_DOWNSCALE);
@@ -2287,7 +2287,7 @@
return -EINVAL;
do {
- in_width = DIV_ROUND_UP(width, *decim_x);
+ in_width = width / *decim_x;
} while (*decim_x <= *x_predecim &&
in_width > maxsinglelinewidth && ++*decim_x);
@@ -2466,8 +2466,8 @@
if (r)
return r;
- in_width = DIV_ROUND_UP(in_width, x_predecim);
- in_height = DIV_ROUND_UP(in_height, y_predecim);
+ in_width = in_width / x_predecim;
+ in_height = in_height / y_predecim;
if (color_mode == OMAP_DSS_COLOR_YUV2 ||
color_mode == OMAP_DSS_COLOR_UYVY ||
diff --git a/drivers/video/omap2/dss/dpi.c b/drivers/video/omap2/dss/dpi.c
index 7411f26..23ef21f 100644
--- a/drivers/video/omap2/dss/dpi.c
+++ b/drivers/video/omap2/dss/dpi.c
@@ -117,7 +117,7 @@
/* outputs */
struct dsi_clock_info dsi_cinfo;
- unsigned long long fck;
+ unsigned long fck;
struct dispc_clock_info dispc_cinfo;
};
diff --git a/drivers/video/omap2/dss/sdi.c b/drivers/video/omap2/dss/sdi.c
index efb9ee9..ba806c9 100644
--- a/drivers/video/omap2/dss/sdi.c
+++ b/drivers/video/omap2/dss/sdi.c
@@ -46,7 +46,7 @@
struct sdi_clk_calc_ctx {
unsigned long pck_min, pck_max;
- unsigned long long fck;
+ unsigned long fck;
struct dispc_clock_info dispc_cinfo;
};
diff --git a/drivers/vme/bridges/vme_ca91cx42.c b/drivers/vme/bridges/vme_ca91cx42.c
index a06edbf..1b5d48c 100644
--- a/drivers/vme/bridges/vme_ca91cx42.c
+++ b/drivers/vme/bridges/vme_ca91cx42.c
@@ -884,7 +884,7 @@
if (done == count)
goto out;
}
- if ((uintptr_t)addr & 0x2) {
+ if ((uintptr_t)(addr + done) & 0x2) {
if ((count - done) < 2) {
*(u8 *)(buf + done) = ioread8(addr + done);
done += 1;
@@ -938,7 +938,7 @@
if (done == count)
goto out;
}
- if ((uintptr_t)addr & 0x2) {
+ if ((uintptr_t)(addr + done) & 0x2) {
if ((count - done) < 2) {
iowrite8(*(u8 *)(buf + done), addr + done);
done += 1;
diff --git a/drivers/vme/bridges/vme_tsi148.c b/drivers/vme/bridges/vme_tsi148.c
index 16830d8..9911cd5 100644
--- a/drivers/vme/bridges/vme_tsi148.c
+++ b/drivers/vme/bridges/vme_tsi148.c
@@ -1289,7 +1289,7 @@
if (done == count)
goto out;
}
- if ((uintptr_t)addr & 0x2) {
+ if ((uintptr_t)(addr + done) & 0x2) {
if ((count - done) < 2) {
*(u8 *)(buf + done) = ioread8(addr + done);
done += 1;
@@ -1371,7 +1371,7 @@
if (done == count)
goto out;
}
- if ((uintptr_t)addr & 0x2) {
+ if ((uintptr_t)(addr + done) & 0x2) {
if ((count - done) < 2) {
iowrite8(*(u8 *)(buf + done), addr + done);
done += 1;
diff --git a/drivers/watchdog/w83697hf_wdt.c b/drivers/watchdog/w83697hf_wdt.c
index aaf2995..68b45fc 100644
--- a/drivers/watchdog/w83697hf_wdt.c
+++ b/drivers/watchdog/w83697hf_wdt.c
@@ -402,7 +402,7 @@
if (!found) {
pr_err("No W83697HF/HG could be found\n");
- ret = -EIO;
+ ret = -ENODEV;
goto out;
}
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index d75c811..45e00af 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -16,7 +16,6 @@
dom0-$(CONFIG_X86) += pcpu.o
obj-$(CONFIG_XEN_DOM0) += $(dom0-y)
obj-$(CONFIG_BLOCK) += biomerge.o
-obj-$(CONFIG_XEN_XENCOMM) += xencomm.o
obj-$(CONFIG_XEN_BALLOON) += xen-balloon.o
obj-$(CONFIG_XEN_SELFBALLOONING) += xen-selfballoon.o
obj-$(CONFIG_XEN_DEV_EVTCHN) += xen-evtchn.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 37d06ea..61a6ac8 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -399,12 +399,26 @@
state = BP_EAGAIN;
break;
}
-
- pfn = page_to_pfn(page);
- frame_list[i] = pfn_to_mfn(pfn);
-
scrub_page(page);
+ frame_list[i] = page_to_pfn(page);
+ }
+
+ /*
+ * Ensure that ballooned highmem pages don't have kmaps.
+ *
+ * Do this before changing the p2m as kmap_flush_unused()
+ * reads PTEs to obtain pages (and hence needs the original
+ * p2m entry).
+ */
+ kmap_flush_unused();
+
+ /* Update direct mapping, invalidate P2M, and add to balloon. */
+ for (i = 0; i < nr_pages; i++) {
+ pfn = frame_list[i];
+ frame_list[i] = pfn_to_mfn(pfn);
+ page = pfn_to_page(pfn);
+
#ifdef CONFIG_XEN_HAVE_PVMMU
/*
* Ballooned out frames are effectively replaced with
@@ -429,11 +443,9 @@
}
#endif
- balloon_append(pfn_to_page(pfn));
+ balloon_append(page);
}
- /* Ensure that ballooned highmem pages don't have kmaps. */
- kmap_flush_unused();
flush_tlb_all();
set_xen_guest_handle(reservation.extent_start, frame_list);
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 4672e00..f4a9e33 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -862,6 +862,8 @@
irq = ret;
goto out;
}
+ /* New interdomain events are bound to VCPU 0. */
+ bind_evtchn_to_cpu(evtchn, 0);
} else {
struct irq_info *info = info_for_irq(irq);
WARN_ON(info == NULL || info->type != IRQT_EVTCHN);
diff --git a/drivers/xen/xencomm.c b/drivers/xen/xencomm.c
deleted file mode 100644
index 4793fc5..0000000
--- a/drivers/xen/xencomm.c
+++ /dev/null
@@ -1,219 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- * Copyright (C) IBM Corp. 2006
- *
- * Authors: Hollis Blanchard <hollisb@us.ibm.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/mm.h>
-#include <linux/slab.h>
-#include <asm/page.h>
-#include <xen/xencomm.h>
-#include <xen/interface/xen.h>
-#include <asm/xen/xencomm.h> /* for xencomm_is_phys_contiguous() */
-
-static int xencomm_init(struct xencomm_desc *desc,
- void *buffer, unsigned long bytes)
-{
- unsigned long recorded = 0;
- int i = 0;
-
- while ((recorded < bytes) && (i < desc->nr_addrs)) {
- unsigned long vaddr = (unsigned long)buffer + recorded;
- unsigned long paddr;
- int offset;
- int chunksz;
-
- offset = vaddr % PAGE_SIZE; /* handle partial pages */
- chunksz = min(PAGE_SIZE - offset, bytes - recorded);
-
- paddr = xencomm_vtop(vaddr);
- if (paddr == ~0UL) {
- printk(KERN_DEBUG "%s: couldn't translate vaddr %lx\n",
- __func__, vaddr);
- return -EINVAL;
- }
-
- desc->address[i++] = paddr;
- recorded += chunksz;
- }
-
- if (recorded < bytes) {
- printk(KERN_DEBUG
- "%s: could only translate %ld of %ld bytes\n",
- __func__, recorded, bytes);
- return -ENOSPC;
- }
-
- /* mark remaining addresses invalid (just for safety) */
- while (i < desc->nr_addrs)
- desc->address[i++] = XENCOMM_INVALID;
-
- desc->magic = XENCOMM_MAGIC;
-
- return 0;
-}
-
-static struct xencomm_desc *xencomm_alloc(gfp_t gfp_mask,
- void *buffer, unsigned long bytes)
-{
- struct xencomm_desc *desc;
- unsigned long buffer_ulong = (unsigned long)buffer;
- unsigned long start = buffer_ulong & PAGE_MASK;
- unsigned long end = (buffer_ulong + bytes) | ~PAGE_MASK;
- unsigned long nr_addrs = (end - start + 1) >> PAGE_SHIFT;
- unsigned long size = sizeof(*desc) +
- sizeof(desc->address[0]) * nr_addrs;
-
- /*
- * slab allocator returns at least sizeof(void*) aligned pointer.
- * When sizeof(*desc) > sizeof(void*), struct xencomm_desc might
- * cross page boundary.
- */
- if (sizeof(*desc) > sizeof(void *)) {
- unsigned long order = get_order(size);
- desc = (struct xencomm_desc *)__get_free_pages(gfp_mask,
- order);
- if (desc == NULL)
- return NULL;
-
- desc->nr_addrs =
- ((PAGE_SIZE << order) - sizeof(struct xencomm_desc)) /
- sizeof(*desc->address);
- } else {
- desc = kmalloc(size, gfp_mask);
- if (desc == NULL)
- return NULL;
-
- desc->nr_addrs = nr_addrs;
- }
- return desc;
-}
-
-void xencomm_free(struct xencomm_handle *desc)
-{
- if (desc && !((ulong)desc & XENCOMM_INLINE_FLAG)) {
- struct xencomm_desc *desc__ = (struct xencomm_desc *)desc;
- if (sizeof(*desc__) > sizeof(void *)) {
- unsigned long size = sizeof(*desc__) +
- sizeof(desc__->address[0]) * desc__->nr_addrs;
- unsigned long order = get_order(size);
- free_pages((unsigned long)__va(desc), order);
- } else
- kfree(__va(desc));
- }
-}
-
-static int xencomm_create(void *buffer, unsigned long bytes,
- struct xencomm_desc **ret, gfp_t gfp_mask)
-{
- struct xencomm_desc *desc;
- int rc;
-
- pr_debug("%s: %p[%ld]\n", __func__, buffer, bytes);
-
- if (bytes == 0) {
- /* don't create a descriptor; Xen recognizes NULL. */
- BUG_ON(buffer != NULL);
- *ret = NULL;
- return 0;
- }
-
- BUG_ON(buffer == NULL); /* 'bytes' is non-zero */
-
- desc = xencomm_alloc(gfp_mask, buffer, bytes);
- if (!desc) {
- printk(KERN_DEBUG "%s failure\n", "xencomm_alloc");
- return -ENOMEM;
- }
-
- rc = xencomm_init(desc, buffer, bytes);
- if (rc) {
- printk(KERN_DEBUG "%s failure: %d\n", "xencomm_init", rc);
- xencomm_free((struct xencomm_handle *)__pa(desc));
- return rc;
- }
-
- *ret = desc;
- return 0;
-}
-
-static struct xencomm_handle *xencomm_create_inline(void *ptr)
-{
- unsigned long paddr;
-
- BUG_ON(!xencomm_is_phys_contiguous((unsigned long)ptr));
-
- paddr = (unsigned long)xencomm_pa(ptr);
- BUG_ON(paddr & XENCOMM_INLINE_FLAG);
- return (struct xencomm_handle *)(paddr | XENCOMM_INLINE_FLAG);
-}
-
-/* "mini" routine, for stack-based communications: */
-static int xencomm_create_mini(void *buffer,
- unsigned long bytes, struct xencomm_mini *xc_desc,
- struct xencomm_desc **ret)
-{
- int rc = 0;
- struct xencomm_desc *desc;
- BUG_ON(((unsigned long)xc_desc) % sizeof(*xc_desc) != 0);
-
- desc = (void *)xc_desc;
-
- desc->nr_addrs = XENCOMM_MINI_ADDRS;
-
- rc = xencomm_init(desc, buffer, bytes);
- if (!rc)
- *ret = desc;
-
- return rc;
-}
-
-struct xencomm_handle *xencomm_map(void *ptr, unsigned long bytes)
-{
- int rc;
- struct xencomm_desc *desc;
-
- if (xencomm_is_phys_contiguous((unsigned long)ptr))
- return xencomm_create_inline(ptr);
-
- rc = xencomm_create(ptr, bytes, &desc, GFP_KERNEL);
-
- if (rc || desc == NULL)
- return NULL;
-
- return xencomm_pa(desc);
-}
-
-struct xencomm_handle *__xencomm_map_no_alloc(void *ptr, unsigned long bytes,
- struct xencomm_mini *xc_desc)
-{
- int rc;
- struct xencomm_desc *desc = NULL;
-
- if (xencomm_is_phys_contiguous((unsigned long)ptr))
- return xencomm_create_inline(ptr);
-
- rc = xencomm_create_mini(ptr, bytes, xc_desc,
- &desc);
-
- if (rc)
- return NULL;
-
- return xencomm_pa(desc);
-}
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 2408473..80ef38c 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -41,19 +41,8 @@
static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
- struct dentry *root;
- root = mount_pseudo(fs_type, "anon_inode:", NULL,
+ return mount_pseudo(fs_type, "anon_inode:", NULL,
&anon_inodefs_dentry_operations, ANON_INODE_FS_MAGIC);
- if (!IS_ERR(root)) {
- struct super_block *s = root->d_sb;
- anon_inode_inode = alloc_anon_inode(s);
- if (IS_ERR(anon_inode_inode)) {
- dput(root);
- deactivate_locked_super(s);
- root = ERR_CAST(anon_inode_inode);
- }
- }
- return root;
}
static struct file_system_type anon_inode_fs_type = {
@@ -175,22 +164,15 @@
static int __init anon_inode_init(void)
{
- int error;
-
- error = register_filesystem(&anon_inode_fs_type);
- if (error)
- goto err_exit;
anon_inode_mnt = kern_mount(&anon_inode_fs_type);
- if (IS_ERR(anon_inode_mnt)) {
- error = PTR_ERR(anon_inode_mnt);
- goto err_unregister_filesystem;
- }
- return 0;
+ if (IS_ERR(anon_inode_mnt))
+ panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt));
-err_unregister_filesystem:
- unregister_filesystem(&anon_inode_fs_type);
-err_exit:
- panic(KERN_ERR "anon_inode_init() failed (%d)\n", error);
+ anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb);
+ if (IS_ERR(anon_inode_inode))
+ panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode));
+
+ return 0;
}
fs_initcall(anon_inode_init);
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 0bad24d..4f70f38 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -114,6 +114,14 @@
}
EXPORT_SYMBOL(bio_integrity_free);
+static inline unsigned int bip_integrity_vecs(struct bio_integrity_payload *bip)
+{
+ if (bip->bip_slab == BIO_POOL_NONE)
+ return BIP_INLINE_VECS;
+
+ return bvec_nr_vecs(bip->bip_slab);
+}
+
/**
* bio_integrity_add_page - Attach integrity metadata
* @bio: bio to update
@@ -129,7 +137,7 @@
struct bio_integrity_payload *bip = bio->bi_integrity;
struct bio_vec *iv;
- if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_slab)) {
+ if (bip->bip_vcnt >= bip_integrity_vecs(bip)) {
printk(KERN_ERR "%s: bip_vec full\n", __func__);
return 0;
}
@@ -226,7 +234,8 @@
}
EXPORT_SYMBOL(bio_integrity_tag_size);
-int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len, int set)
+static int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len,
+ int set)
{
struct bio_integrity_payload *bip = bio->bi_integrity;
struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
@@ -449,11 +458,10 @@
struct blk_integrity_exchg bix;
struct bio_vec *bv;
sector_t sector = bio->bi_integrity->bip_iter.bi_sector;
- unsigned int sectors, total, ret;
+ unsigned int sectors, ret = 0;
void *prot_buf = bio->bi_integrity->bip_buf;
int i;
- ret = total = 0;
bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
bix.sector_size = bi->sector_size;
@@ -475,8 +483,6 @@
sectors = bv->bv_len / bi->sector_size;
sector += sectors;
prot_buf += sectors * bi->tuple_size;
- total += sectors * bi->tuple_size;
- BUG_ON(total > bio->bi_integrity->bip_iter.bi_size);
kunmap_atomic(kaddr);
}
diff --git a/fs/bio.c b/fs/bio.c
index 75c49a3..8754e7b 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -611,7 +611,6 @@
struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
struct bio_set *bs)
{
- unsigned nr_iovecs = 0;
struct bvec_iter iter;
struct bio_vec bv;
struct bio *bio;
@@ -638,10 +637,7 @@
* __bio_clone_fast() anyways.
*/
- bio_for_each_segment(bv, bio_src, iter)
- nr_iovecs++;
-
- bio = bio_alloc_bioset(gfp_mask, nr_iovecs, bs);
+ bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
if (!bio)
return NULL;
@@ -650,9 +646,18 @@
bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector;
bio->bi_iter.bi_size = bio_src->bi_iter.bi_size;
+ if (bio->bi_rw & REQ_DISCARD)
+ goto integrity_clone;
+
+ if (bio->bi_rw & REQ_WRITE_SAME) {
+ bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
+ goto integrity_clone;
+ }
+
bio_for_each_segment(bv, bio_src, iter)
bio->bi_io_vec[bio->bi_vcnt++] = bv;
+integrity_clone:
if (bio_integrity(bio_src)) {
int ret;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 5215f04..81ea553 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3839,7 +3839,6 @@
rb_erase(&ref->rb_node, &head->ref_root);
atomic_dec(&delayed_refs->num_entries);
btrfs_put_delayed_ref(ref);
- cond_resched_lock(&head->lock);
}
if (head->must_insert_reserved)
pin_bytes = true;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 184e9cb..d3d4448 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5154,7 +5154,7 @@
return ERR_CAST(inode);
}
- return d_splice_alias(inode, dentry);
+ return d_materialise_unique(dentry, inode);
}
unsigned char btrfs_filetype_table[] = {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 383ab45..a6d8efa 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3537,20 +3537,6 @@
return ret;
}
-static long btrfs_ioctl_global_rsv(struct btrfs_root *root, void __user *arg)
-{
- struct btrfs_block_rsv *block_rsv = &root->fs_info->global_block_rsv;
- u64 reserved;
-
- spin_lock(&block_rsv->lock);
- reserved = block_rsv->reserved;
- spin_unlock(&block_rsv->lock);
-
- if (arg && copy_to_user(arg, &reserved, sizeof(reserved)))
- return -EFAULT;
- return 0;
-}
-
/*
* there are many ways the trans_start and trans_end ioctls can lead
* to deadlocks. They should only be used by applications that
@@ -4757,8 +4743,6 @@
return btrfs_ioctl_logical_to_ino(root, argp);
case BTRFS_IOC_SPACE_INFO:
return btrfs_ioctl_space_info(root, argp);
- case BTRFS_IOC_GLOBAL_RSV:
- return btrfs_ioctl_global_rsv(root, argp);
case BTRFS_IOC_SYNC: {
int ret;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 9c8d1a3..9dde971 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1332,6 +1332,16 @@
}
if (cur_clone_root) {
+ if (compressed != BTRFS_COMPRESS_NONE) {
+ /*
+ * Offsets given by iterate_extent_inodes() are relative
+ * to the start of the extent, we need to add logical
+ * offset from the file extent item.
+ * (See why at backref.c:check_extent_in_eb())
+ */
+ cur_clone_root->offset += btrfs_file_extent_offset(eb,
+ fi);
+ }
*found = cur_clone_root;
ret = 0;
} else {
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 97cc241..d04db81 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -566,7 +566,7 @@
kfree(num);
if (info->max_inline) {
- info->max_inline = max_t(u64,
+ info->max_inline = min_t(u64,
info->max_inline,
root->sectorsize);
}
@@ -855,6 +855,7 @@
struct btrfs_path *path;
struct btrfs_key location;
struct inode *inode;
+ struct dentry *dentry;
u64 dir_id;
int new = 0;
@@ -925,7 +926,13 @@
return dget(sb->s_root);
}
- return d_obtain_alias(inode);
+ dentry = d_obtain_alias(inode);
+ if (!IS_ERR(dentry)) {
+ spin_lock(&dentry->d_lock);
+ dentry->d_flags &= ~DCACHE_DISCONNECTED;
+ spin_unlock(&dentry->d_lock);
+ }
+ return dentry;
}
static int btrfs_fill_super(struct super_block *sb,
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 782374d..865f4cf 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -578,8 +578,14 @@
return -ENOMEM;
list_for_each_entry(dev, &fs_devices->devices, dev_list) {
- struct hd_struct *disk = dev->bdev->bd_part;
- struct kobject *disk_kobj = &part_to_dev(disk)->kobj;
+ struct hd_struct *disk;
+ struct kobject *disk_kobj;
+
+ if (!dev->bdev)
+ continue;
+
+ disk = dev->bdev->bd_part;
+ disk_kobj = &part_to_dev(disk)->kobj;
error = sysfs_create_link(fs_info->device_dir_kobj,
disk_kobj, disk_kobj->name);
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 4c2d452..21887d6 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -54,11 +54,6 @@
return acl;
}
-void ceph_forget_all_cached_acls(struct inode *inode)
-{
- forget_all_cached_acls(inode);
-}
-
struct posix_acl *ceph_get_acl(struct inode *inode, int type)
{
int size;
@@ -160,11 +155,7 @@
goto out_dput;
}
- if (value)
- ret = __ceph_setxattr(dentry, name, value, size, 0);
- else
- ret = __ceph_removexattr(dentry, name);
-
+ ret = __ceph_setxattr(dentry, name, value, size, 0);
if (ret) {
if (new_mode != old_mode) {
newattrs.ia_mode = old_mode;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 6da4df8..45eda6d 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -100,6 +100,14 @@
return p & 0xffffffff;
}
+static int fpos_cmp(loff_t l, loff_t r)
+{
+ int v = ceph_frag_compare(fpos_frag(l), fpos_frag(r));
+ if (v)
+ return v;
+ return (int)(fpos_off(l) - fpos_off(r));
+}
+
/*
* When possible, we try to satisfy a readdir by peeking at the
* dcache. We make this work by carefully ordering dentries on
@@ -156,7 +164,7 @@
if (!d_unhashed(dentry) && dentry->d_inode &&
ceph_snap(dentry->d_inode) != CEPH_SNAPDIR &&
ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
- ctx->pos <= di->offset)
+ fpos_cmp(ctx->pos, di->offset) <= 0)
break;
dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry,
dentry->d_name.len, dentry->d_name.name, di->offset,
@@ -695,9 +703,8 @@
ceph_mdsc_put_request(req);
if (!err)
- err = ceph_init_acl(dentry, dentry->d_inode, dir);
-
- if (err)
+ ceph_init_acl(dentry, dentry->d_inode, dir);
+ else
d_drop(dentry);
return err;
}
@@ -735,7 +742,9 @@
if (!err && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
ceph_mdsc_put_request(req);
- if (err)
+ if (!err)
+ ceph_init_acl(dentry, dentry->d_inode, dir);
+ else
d_drop(dentry);
return err;
}
@@ -776,7 +785,9 @@
err = ceph_handle_notrace_create(dir, dentry);
ceph_mdsc_put_request(req);
out:
- if (err < 0)
+ if (!err)
+ ceph_init_acl(dentry, dentry->d_inode, dir);
+ else
d_drop(dentry);
return err;
}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index dfd2ce3..09c7afe 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -286,6 +286,7 @@
} else {
dout("atomic_open finish_open on dn %p\n", dn);
if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
+ ceph_init_acl(dentry, dentry->d_inode, dir);
*opened |= FILE_CREATED;
}
err = finish_open(file, dentry, ceph_open, opened);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 2df963f..10a4ccb 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -144,7 +144,11 @@
Opt_ino32,
Opt_noino32,
Opt_fscache,
- Opt_nofscache
+ Opt_nofscache,
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ Opt_acl,
+#endif
+ Opt_noacl
};
static match_table_t fsopt_tokens = {
@@ -172,6 +176,10 @@
{Opt_noino32, "noino32"},
{Opt_fscache, "fsc"},
{Opt_nofscache, "nofsc"},
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ {Opt_acl, "acl"},
+#endif
+ {Opt_noacl, "noacl"},
{-1, NULL}
};
@@ -271,6 +279,14 @@
case Opt_nofscache:
fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
break;
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ case Opt_acl:
+ fsopt->sb_flags |= MS_POSIXACL;
+ break;
+#endif
+ case Opt_noacl:
+ fsopt->sb_flags &= ~MS_POSIXACL;
+ break;
default:
BUG_ON(token);
}
@@ -438,6 +454,13 @@
else
seq_puts(m, ",nofsc");
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ if (fsopt->sb_flags & MS_POSIXACL)
+ seq_puts(m, ",acl");
+ else
+ seq_puts(m, ",noacl");
+#endif
+
if (fsopt->wsize)
seq_printf(m, ",wsize=%d", fsopt->wsize);
if (fsopt->rsize != CEPH_RSIZE_DEFAULT)
@@ -819,9 +842,6 @@
s->s_flags = fsc->mount_options->sb_flags;
s->s_maxbytes = 1ULL << 40; /* temp value until we get mdsmap */
-#ifdef CONFIG_CEPH_FS_POSIX_ACL
- s->s_flags |= MS_POSIXACL;
-#endif
s->s_xattr = ceph_xattr_handlers;
s->s_fs_info = fsc;
@@ -911,6 +931,10 @@
struct ceph_options *opt = NULL;
dout("ceph_mount\n");
+
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ flags |= MS_POSIXACL;
+#endif
err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path);
if (err < 0) {
res = ERR_PTR(err);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 19793b5..d8801a9 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -13,6 +13,7 @@
#include <linux/wait.h>
#include <linux/writeback.h>
#include <linux/slab.h>
+#include <linux/posix_acl.h>
#include <linux/ceph/libceph.h>
@@ -743,7 +744,11 @@
struct posix_acl *ceph_get_acl(struct inode *, int);
int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type);
int ceph_init_acl(struct dentry *, struct inode *, struct inode *);
-void ceph_forget_all_cached_acls(struct inode *inode);
+
+static inline void ceph_forget_all_cached_acls(struct inode *inode)
+{
+ forget_all_cached_acls(inode);
+}
#else
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 898b656..a55ec37 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -12,6 +12,9 @@
#define XATTR_CEPH_PREFIX "ceph."
#define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1)
+static int __remove_xattr(struct ceph_inode_info *ci,
+ struct ceph_inode_xattr *xattr);
+
/*
* List of handlers for synthetic system.* attributes. Other
* attributes are handled directly.
@@ -319,8 +322,7 @@
static int __set_xattr(struct ceph_inode_info *ci,
const char *name, int name_len,
const char *val, int val_len,
- int dirty,
- int should_free_name, int should_free_val,
+ int flags, int update_xattr,
struct ceph_inode_xattr **newxattr)
{
struct rb_node **p;
@@ -349,12 +351,31 @@
xattr = NULL;
}
+ if (update_xattr) {
+ int err = 0;
+ if (xattr && (flags & XATTR_CREATE))
+ err = -EEXIST;
+ else if (!xattr && (flags & XATTR_REPLACE))
+ err = -ENODATA;
+ if (err) {
+ kfree(name);
+ kfree(val);
+ return err;
+ }
+ if (update_xattr < 0) {
+ if (xattr)
+ __remove_xattr(ci, xattr);
+ kfree(name);
+ return 0;
+ }
+ }
+
if (!xattr) {
new = 1;
xattr = *newxattr;
xattr->name = name;
xattr->name_len = name_len;
- xattr->should_free_name = should_free_name;
+ xattr->should_free_name = update_xattr;
ci->i_xattrs.count++;
dout("__set_xattr count=%d\n", ci->i_xattrs.count);
@@ -364,7 +385,7 @@
if (xattr->should_free_val)
kfree((void *)xattr->val);
- if (should_free_name) {
+ if (update_xattr) {
kfree((void *)name);
name = xattr->name;
}
@@ -379,8 +400,8 @@
xattr->val = "";
xattr->val_len = val_len;
- xattr->dirty = dirty;
- xattr->should_free_val = (val && should_free_val);
+ xattr->dirty = update_xattr;
+ xattr->should_free_val = (val && update_xattr);
if (new) {
rb_link_node(&xattr->node, parent, p);
@@ -442,7 +463,7 @@
struct ceph_inode_xattr *xattr)
{
if (!xattr)
- return -EOPNOTSUPP;
+ return -ENODATA;
rb_erase(&xattr->node, &ci->i_xattrs.index);
@@ -588,7 +609,7 @@
p += len;
err = __set_xattr(ci, name, namelen, val, len,
- 0, 0, 0, &xattrs[numattr]);
+ 0, 0, &xattrs[numattr]);
if (err < 0)
goto bad;
@@ -850,6 +871,9 @@
dout("setxattr value=%.*s\n", (int)size, value);
+ if (!value)
+ flags |= CEPH_XATTR_REMOVE;
+
/* do request */
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR,
USE_AUTH_MDS);
@@ -892,7 +916,7 @@
struct ceph_inode_info *ci = ceph_inode(inode);
int issued;
int err;
- int dirty;
+ int dirty = 0;
int name_len = strlen(name);
int val_len = size;
char *newname = NULL;
@@ -953,12 +977,14 @@
goto retry;
}
- err = __set_xattr(ci, newname, name_len, newval,
- val_len, 1, 1, 1, &xattr);
+ err = __set_xattr(ci, newname, name_len, newval, val_len,
+ flags, value ? 1 : -1, &xattr);
- dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
- ci->i_xattrs.dirty = true;
- inode->i_ctime = CURRENT_TIME;
+ if (!err) {
+ dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
+ ci->i_xattrs.dirty = true;
+ inode->i_ctime = CURRENT_TIME;
+ }
spin_unlock(&ci->i_ceph_lock);
if (dirty)
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 8f9b4f7..7ff866d 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -865,8 +865,8 @@
return rc;
}
-static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
- __u16 fid, u32 *pacllen)
+struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
+ const struct cifs_fid *cifsfid, u32 *pacllen)
{
struct cifs_ntsd *pntsd = NULL;
unsigned int xid;
@@ -877,7 +877,8 @@
return ERR_CAST(tlink);
xid = get_xid();
- rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), fid, &pntsd, pacllen);
+ rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), cifsfid->netfid, &pntsd,
+ pacllen);
free_xid(xid);
cifs_put_tlink(tlink);
@@ -946,7 +947,7 @@
if (!open_file)
return get_cifs_acl_by_path(cifs_sb, path, pacllen);
- pntsd = get_cifs_acl_by_fid(cifs_sb, open_file->fid.netfid, pacllen);
+ pntsd = get_cifs_acl_by_fid(cifs_sb, &open_file->fid, pacllen);
cifsFileInfo_put(open_file);
return pntsd;
}
@@ -1006,19 +1007,31 @@
/* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */
int
cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
- struct inode *inode, const char *path, const __u16 *pfid)
+ struct inode *inode, const char *path,
+ const struct cifs_fid *pfid)
{
struct cifs_ntsd *pntsd = NULL;
u32 acllen = 0;
int rc = 0;
+ struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+ struct cifs_tcon *tcon;
cifs_dbg(NOISY, "converting ACL to mode for %s\n", path);
- if (pfid)
- pntsd = get_cifs_acl_by_fid(cifs_sb, *pfid, &acllen);
- else
- pntsd = get_cifs_acl(cifs_sb, inode, path, &acllen);
+ if (IS_ERR(tlink))
+ return PTR_ERR(tlink);
+ tcon = tlink_tcon(tlink);
+ if (pfid && (tcon->ses->server->ops->get_acl_by_fid))
+ pntsd = tcon->ses->server->ops->get_acl_by_fid(cifs_sb, pfid,
+ &acllen);
+ else if (tcon->ses->server->ops->get_acl)
+ pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
+ &acllen);
+ else {
+ cifs_put_tlink(tlink);
+ return -EOPNOTSUPP;
+ }
/* if we can retrieve the ACL, now parse Access Control Entries, ACEs */
if (IS_ERR(pntsd)) {
rc = PTR_ERR(pntsd);
@@ -1030,6 +1043,8 @@
cifs_dbg(VFS, "parse sec desc failed rc = %d\n", rc);
}
+ cifs_put_tlink(tlink);
+
return rc;
}
@@ -1043,15 +1058,30 @@
__u32 secdesclen = 0;
struct cifs_ntsd *pntsd = NULL; /* acl obtained from server */
struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+ struct cifs_tcon *tcon;
+
+ if (IS_ERR(tlink))
+ return PTR_ERR(tlink);
+ tcon = tlink_tcon(tlink);
cifs_dbg(NOISY, "set ACL from mode for %s\n", path);
/* Get the security descriptor */
- pntsd = get_cifs_acl(CIFS_SB(inode->i_sb), inode, path, &secdesclen);
+
+ if (tcon->ses->server->ops->get_acl == NULL) {
+ cifs_put_tlink(tlink);
+ return -EOPNOTSUPP;
+ }
+
+ pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
+ &secdesclen);
if (IS_ERR(pntsd)) {
rc = PTR_ERR(pntsd);
cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc);
- goto out;
+ cifs_put_tlink(tlink);
+ return rc;
}
/*
@@ -1064,6 +1094,7 @@
pnntsd = kmalloc(secdesclen, GFP_KERNEL);
if (!pnntsd) {
kfree(pntsd);
+ cifs_put_tlink(tlink);
return -ENOMEM;
}
@@ -1072,14 +1103,18 @@
cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc);
+ if (tcon->ses->server->ops->set_acl == NULL)
+ rc = -EOPNOTSUPP;
+
if (!rc) {
/* Set the security descriptor */
- rc = set_cifs_acl(pnntsd, secdesclen, inode, path, aclflag);
+ rc = tcon->ses->server->ops->set_acl(pnntsd, secdesclen, inode,
+ path, aclflag);
cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc);
}
+ cifs_put_tlink(tlink);
kfree(pnntsd);
kfree(pntsd);
-out:
return rc;
}
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index a245d18..c0f3718 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -323,7 +323,8 @@
/* async read from the server */
int (*async_readv)(struct cifs_readdata *);
/* async write to the server */
- int (*async_writev)(struct cifs_writedata *);
+ int (*async_writev)(struct cifs_writedata *,
+ void (*release)(struct kref *));
/* sync read from the server */
int (*sync_read)(const unsigned int, struct cifsFileInfo *,
struct cifs_io_parms *, unsigned int *, char **,
@@ -395,6 +396,12 @@
int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *,
const char *, const void *, const __u16,
const struct nls_table *, int);
+ struct cifs_ntsd * (*get_acl)(struct cifs_sb_info *, struct inode *,
+ const char *, u32 *);
+ struct cifs_ntsd * (*get_acl_by_fid)(struct cifs_sb_info *,
+ const struct cifs_fid *, u32 *);
+ int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *,
+ int);
};
struct smb_version_values {
@@ -506,7 +513,7 @@
static inline unsigned int
get_rfc1002_length(void *buf)
{
- return be32_to_cpu(*((__be32 *)buf));
+ return be32_to_cpu(*((__be32 *)buf)) & 0xffffff;
}
static inline void
@@ -1064,7 +1071,7 @@
unsigned int pagesz;
unsigned int tailsz;
unsigned int nr_pages;
- struct page *pages[1];
+ struct page *pages[];
};
/*
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 79e6e9a..acc4ee8 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -151,7 +151,7 @@
extern int cifs_get_inode_info(struct inode **inode, const char *full_path,
FILE_ALL_INFO *data, struct super_block *sb,
- int xid, const __u16 *fid);
+ int xid, const struct cifs_fid *fid);
extern int cifs_get_inode_info_unix(struct inode **pinode,
const unsigned char *search_path,
struct super_block *sb, unsigned int xid);
@@ -162,11 +162,13 @@
const unsigned int xid);
extern int cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb,
struct cifs_fattr *fattr, struct inode *inode,
- const char *path, const __u16 *pfid);
+ const char *path, const struct cifs_fid *pfid);
extern int id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64,
kuid_t, kgid_t);
extern struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *, struct inode *,
const char *, u32 *);
+extern struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *,
+ const struct cifs_fid *, u32 *);
extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *,
const char *, int);
@@ -488,7 +490,8 @@
int cifs_async_readv(struct cifs_readdata *rdata);
int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid);
-int cifs_async_writev(struct cifs_writedata *wdata);
+int cifs_async_writev(struct cifs_writedata *wdata,
+ void (*release)(struct kref *kref));
void cifs_writev_complete(struct work_struct *work);
struct cifs_writedata *cifs_writedata_alloc(unsigned int nr_pages,
work_func_t complete);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 4d881c3..f3264bd 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1910,7 +1910,7 @@
do {
server = tlink_tcon(wdata->cfile->tlink)->ses->server;
- rc = server->ops->async_writev(wdata);
+ rc = server->ops->async_writev(wdata, cifs_writedata_release);
} while (rc == -EAGAIN);
for (i = 0; i < wdata->nr_pages; i++) {
@@ -1962,15 +1962,9 @@
{
struct cifs_writedata *wdata;
- /* this would overflow */
- if (nr_pages == 0) {
- cifs_dbg(VFS, "%s: called with nr_pages == 0!\n", __func__);
- return NULL;
- }
-
/* writedata + number of page pointers */
wdata = kzalloc(sizeof(*wdata) +
- sizeof(struct page *) * (nr_pages - 1), GFP_NOFS);
+ sizeof(struct page *) * nr_pages, GFP_NOFS);
if (wdata != NULL) {
kref_init(&wdata->refcount);
INIT_LIST_HEAD(&wdata->list);
@@ -2031,7 +2025,8 @@
/* cifs_async_writev - send an async write, and set up mid to handle result */
int
-cifs_async_writev(struct cifs_writedata *wdata)
+cifs_async_writev(struct cifs_writedata *wdata,
+ void (*release)(struct kref *kref))
{
int rc = -EACCES;
WRITE_REQ *smb = NULL;
@@ -2105,7 +2100,7 @@
if (rc == 0)
cifs_stats_inc(&tcon->stats.cifs_stats.num_writes);
else
- kref_put(&wdata->refcount, cifs_writedata_release);
+ kref_put(&wdata->refcount, release);
async_writev_out:
cifs_small_buf_release(smb);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index d3a6796..3db0c5f 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -378,7 +378,7 @@
xid);
else {
rc = cifs_get_inode_info(&newinode, full_path, buf, inode->i_sb,
- xid, &fid->netfid);
+ xid, fid);
if (newinode) {
if (server->ops->set_lease_key)
server->ops->set_lease_key(newinode, fid);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index a7eda8e..834fce7 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -244,7 +244,7 @@
xid);
else
rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb,
- xid, &fid->netfid);
+ xid, fid);
out:
kfree(buf);
@@ -2043,7 +2043,8 @@
}
wdata->pid = wdata->cfile->pid;
server = tlink_tcon(wdata->cfile->tlink)->ses->server;
- rc = server->ops->async_writev(wdata);
+ rc = server->ops->async_writev(wdata,
+ cifs_writedata_release);
} while (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN);
for (i = 0; i < nr_pages; ++i)
@@ -2331,9 +2332,20 @@
}
static void
-cifs_uncached_writev_complete(struct work_struct *work)
+cifs_uncached_writedata_release(struct kref *refcount)
{
int i;
+ struct cifs_writedata *wdata = container_of(refcount,
+ struct cifs_writedata, refcount);
+
+ for (i = 0; i < wdata->nr_pages; i++)
+ put_page(wdata->pages[i]);
+ cifs_writedata_release(refcount);
+}
+
+static void
+cifs_uncached_writev_complete(struct work_struct *work)
+{
struct cifs_writedata *wdata = container_of(work,
struct cifs_writedata, work);
struct inode *inode = wdata->cfile->dentry->d_inode;
@@ -2347,12 +2359,7 @@
complete(&wdata->done);
- if (wdata->result != -EAGAIN) {
- for (i = 0; i < wdata->nr_pages; i++)
- put_page(wdata->pages[i]);
- }
-
- kref_put(&wdata->refcount, cifs_writedata_release);
+ kref_put(&wdata->refcount, cifs_uncached_writedata_release);
}
/* attempt to send write to server, retry on any -EAGAIN errors */
@@ -2370,7 +2377,8 @@
if (rc != 0)
continue;
}
- rc = server->ops->async_writev(wdata);
+ rc = server->ops->async_writev(wdata,
+ cifs_uncached_writedata_release);
} while (rc == -EAGAIN);
return rc;
@@ -2381,7 +2389,7 @@
unsigned long nr_segs, loff_t *poffset)
{
unsigned long nr_pages, i;
- size_t copied, len, cur_len;
+ size_t bytes, copied, len, cur_len;
ssize_t total_written = 0;
loff_t offset;
struct iov_iter it;
@@ -2436,14 +2444,45 @@
save_len = cur_len;
for (i = 0; i < nr_pages; i++) {
- copied = min_t(const size_t, cur_len, PAGE_SIZE);
+ bytes = min_t(const size_t, cur_len, PAGE_SIZE);
copied = iov_iter_copy_from_user(wdata->pages[i], &it,
- 0, copied);
+ 0, bytes);
cur_len -= copied;
iov_iter_advance(&it, copied);
+ /*
+ * If we didn't copy as much as we expected, then that
+ * may mean we trod into an unmapped area. Stop copying
+ * at that point. On the next pass through the big
+ * loop, we'll likely end up getting a zero-length
+ * write and bailing out of it.
+ */
+ if (copied < bytes)
+ break;
}
cur_len = save_len - cur_len;
+ /*
+ * If we have no data to send, then that probably means that
+ * the copy above failed altogether. That's most likely because
+ * the address in the iovec was bogus. Set the rc to -EFAULT,
+ * free anything we allocated and bail out.
+ */
+ if (!cur_len) {
+ for (i = 0; i < nr_pages; i++)
+ put_page(wdata->pages[i]);
+ kfree(wdata);
+ rc = -EFAULT;
+ break;
+ }
+
+ /*
+ * i + 1 now represents the number of pages we actually used in
+ * the copy phase above. Bring nr_pages down to that, and free
+ * any pages that we didn't use.
+ */
+ for ( ; nr_pages > i + 1; nr_pages--)
+ put_page(wdata->pages[nr_pages - 1]);
+
wdata->sync_mode = WB_SYNC_ALL;
wdata->nr_pages = nr_pages;
wdata->offset = (__u64)offset;
@@ -2454,7 +2493,8 @@
wdata->tailsz = cur_len - ((nr_pages - 1) * PAGE_SIZE);
rc = cifs_uncached_retry_writev(wdata);
if (rc) {
- kref_put(&wdata->refcount, cifs_writedata_release);
+ kref_put(&wdata->refcount,
+ cifs_uncached_writedata_release);
break;
}
@@ -2496,7 +2536,7 @@
}
}
list_del_init(&wdata->list);
- kref_put(&wdata->refcount, cifs_writedata_release);
+ kref_put(&wdata->refcount, cifs_uncached_writedata_release);
}
if (total_written > 0)
@@ -2539,31 +2579,19 @@
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
ssize_t rc = -EACCES;
+ loff_t lock_pos = pos;
- BUG_ON(iocb->ki_pos != pos);
-
+ if (file->f_flags & O_APPEND)
+ lock_pos = i_size_read(inode);
/*
* We need to hold the sem to be sure nobody modifies lock list
* with a brlock that prevents writing.
*/
down_read(&cinode->lock_sem);
- if (!cifs_find_lock_conflict(cfile, pos, iov_length(iov, nr_segs),
+ if (!cifs_find_lock_conflict(cfile, lock_pos, iov_length(iov, nr_segs),
server->vals->exclusive_lock_type, NULL,
- CIFS_WRITE_OP)) {
- mutex_lock(&inode->i_mutex);
- rc = __generic_file_aio_write(iocb, iov, nr_segs,
- &iocb->ki_pos);
- mutex_unlock(&inode->i_mutex);
- }
-
- if (rc > 0) {
- ssize_t err;
-
- err = generic_write_sync(file, iocb->ki_pos - rc, rc);
- if (err < 0)
- rc = err;
- }
-
+ CIFS_WRITE_OP))
+ rc = generic_file_aio_write(iocb, iov, nr_segs, pos);
up_read(&cinode->lock_sem);
return rc;
}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 9cb9679..aadc2b6 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -527,10 +527,15 @@
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
- rc = CIFSSMBQAllEAs(xid, tcon, path, "SETFILEBITS",
- ea_value, 4 /* size of buf */, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (tcon->ses->server->ops->query_all_EAs == NULL) {
+ cifs_put_tlink(tlink);
+ return -EOPNOTSUPP;
+ }
+
+ rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path,
+ "SETFILEBITS", ea_value, 4 /* size of buf */,
+ cifs_sb->local_nls,
+ cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
cifs_put_tlink(tlink);
if (rc < 0)
return (int)rc;
@@ -672,7 +677,7 @@
int
cifs_get_inode_info(struct inode **inode, const char *full_path,
FILE_ALL_INFO *data, struct super_block *sb, int xid,
- const __u16 *fid)
+ const struct cifs_fid *fid)
{
bool validinum = false;
__u16 srchflgs;
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 9ac5bfc..526fb89 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -1067,6 +1067,15 @@
.query_mf_symlink = cifs_query_mf_symlink,
.create_mf_symlink = cifs_create_mf_symlink,
.is_read_op = cifs_is_read_op,
+#ifdef CONFIG_CIFS_XATTR
+ .query_all_EAs = CIFSSMBQAllEAs,
+ .set_EA = CIFSSMBSetEA,
+#endif /* CIFS_XATTR */
+#ifdef CONFIG_CIFS_ACL
+ .get_acl = get_cifs_acl,
+ .get_acl_by_fid = get_cifs_acl_by_fid,
+ .set_acl = set_cifs_acl,
+#endif /* CIFS_ACL */
};
struct smb_version_values smb1_values = {
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index c383508..bc0bb9c 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -57,4 +57,7 @@
#define SMB2_CMACAES_SIZE (16)
#define SMB3_SIGNKEY_SIZE (16)
+/* Maximum buffer size value we can send with 1 credit */
+#define SMB2_MAX_BUFFER_SIZE 65536
+
#endif /* _SMB2_GLOB_H */
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 757da3e..192f51a 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -182,11 +182,8 @@
/* start with specified wsize, or default */
wsize = volume_info->wsize ? volume_info->wsize : CIFS_DEFAULT_IOSIZE;
wsize = min_t(unsigned int, wsize, server->max_write);
- /*
- * limit write size to 2 ** 16, because we don't support multicredit
- * requests now.
- */
- wsize = min_t(unsigned int, wsize, 2 << 15);
+ /* set it to the maximum buffer size value we can send with 1 credit */
+ wsize = min_t(unsigned int, wsize, SMB2_MAX_BUFFER_SIZE);
return wsize;
}
@@ -200,11 +197,8 @@
/* start with specified rsize, or default */
rsize = volume_info->rsize ? volume_info->rsize : CIFS_DEFAULT_IOSIZE;
rsize = min_t(unsigned int, rsize, server->max_read);
- /*
- * limit write size to 2 ** 16, because we don't support multicredit
- * requests now.
- */
- rsize = min_t(unsigned int, rsize, 2 << 15);
+ /* set it to the maximum buffer size value we can send with 1 credit */
+ rsize = min_t(unsigned int, rsize, SMB2_MAX_BUFFER_SIZE);
return rsize;
}
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 2013234..8603447 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -413,7 +413,9 @@
/* SMB2 only has an extended negflavor */
server->negflavor = CIFS_NEGFLAVOR_EXTENDED;
- server->maxBuf = le32_to_cpu(rsp->MaxTransactSize);
+ /* set it to the maximum buffer size value we can send with 1 credit */
+ server->maxBuf = min_t(unsigned int, le32_to_cpu(rsp->MaxTransactSize),
+ SMB2_MAX_BUFFER_SIZE);
server->max_read = le32_to_cpu(rsp->MaxReadSize);
server->max_write = le32_to_cpu(rsp->MaxWriteSize);
/* BB Do we need to validate the SecurityMode? */
@@ -1890,7 +1892,8 @@
/* smb2_async_writev - send an async write, and set up mid to handle result */
int
-smb2_async_writev(struct cifs_writedata *wdata)
+smb2_async_writev(struct cifs_writedata *wdata,
+ void (*release)(struct kref *kref))
{
int rc = -EACCES;
struct smb2_write_req *req = NULL;
@@ -1938,7 +1941,7 @@
smb2_writev_callback, wdata, 0);
if (rc) {
- kref_put(&wdata->refcount, cifs_writedata_release);
+ kref_put(&wdata->refcount, release);
cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
}
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 93adc64..0ce48db 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -123,7 +123,8 @@
extern int smb2_async_readv(struct cifs_readdata *rdata);
extern int SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
unsigned int *nbytes, char **buf, int *buf_type);
-extern int smb2_async_writev(struct cifs_writedata *wdata);
+extern int smb2_async_writev(struct cifs_writedata *wdata,
+ void (*release)(struct kref *kref));
extern int SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
unsigned int *nbytes, struct kvec *iov, int n_vec);
extern int SMB2_echo(struct TCP_Server_Info *server);
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index b375709..18cd565 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -270,6 +270,26 @@
iov->iov_len = rqst->rq_pagesz;
}
+static unsigned long
+rqst_len(struct smb_rqst *rqst)
+{
+ unsigned int i;
+ struct kvec *iov = rqst->rq_iov;
+ unsigned long buflen = 0;
+
+ /* total up iov array first */
+ for (i = 0; i < rqst->rq_nvec; i++)
+ buflen += iov[i].iov_len;
+
+ /* add in the page array if there is one */
+ if (rqst->rq_npages) {
+ buflen += rqst->rq_pagesz * (rqst->rq_npages - 1);
+ buflen += rqst->rq_tailsz;
+ }
+
+ return buflen;
+}
+
static int
smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
{
@@ -277,6 +297,7 @@
struct kvec *iov = rqst->rq_iov;
int n_vec = rqst->rq_nvec;
unsigned int smb_buf_length = get_rfc1002_length(iov[0].iov_base);
+ unsigned long send_length;
unsigned int i;
size_t total_len = 0, sent;
struct socket *ssocket = server->ssocket;
@@ -285,6 +306,14 @@
if (ssocket == NULL)
return -ENOTSOCK;
+ /* sanity check send length */
+ send_length = rqst_len(rqst);
+ if (send_length != smb_buf_length + 4) {
+ WARN(1, "Send length mismatch(send_length=%lu smb_buf_length=%u)\n",
+ send_length, smb_buf_length);
+ return -EIO;
+ }
+
cifs_dbg(FYI, "Sending smb: smb_len=%u\n", smb_buf_length);
dump_smb(iov[0].iov_base, iov[0].iov_len);
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 95c43bb..5ac836a 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -176,8 +176,12 @@
rc = -ENOMEM;
} else {
memcpy(pacl, ea_value, value_size);
- rc = set_cifs_acl(pacl, value_size,
- direntry->d_inode, full_path, CIFS_ACL_DACL);
+ if (pTcon->ses->server->ops->set_acl)
+ rc = pTcon->ses->server->ops->set_acl(pacl,
+ value_size, direntry->d_inode,
+ full_path, CIFS_ACL_DACL);
+ else
+ rc = -EOPNOTSUPP;
if (rc == 0) /* force revalidate of the inode */
CIFS_I(direntry->d_inode)->time = 0;
kfree(pacl);
@@ -323,8 +327,11 @@
u32 acllen;
struct cifs_ntsd *pacl;
- pacl = get_cifs_acl(cifs_sb, direntry->d_inode,
- full_path, &acllen);
+ if (pTcon->ses->server->ops->get_acl == NULL)
+ goto get_ea_exit; /* rc already EOPNOTSUPP */
+
+ pacl = pTcon->ses->server->ops->get_acl(cifs_sb,
+ direntry->d_inode, full_path, &acllen);
if (IS_ERR(pacl)) {
rc = PTR_ERR(pacl);
cifs_dbg(VFS, "%s: error %zd getting sec desc\n",
diff --git a/fs/dcache.c b/fs/dcache.c
index 265e0ce..ca02c13 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2833,9 +2833,9 @@
u32 dlen = ACCESS_ONCE(name->len);
char *p;
- if (*buflen < dlen + 1)
- return -ENAMETOOLONG;
*buflen -= dlen + 1;
+ if (*buflen < 0)
+ return -ENAMETOOLONG;
p = *buffer -= dlen + 1;
*p++ = '/';
while (dlen--) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index ece5556..d3a534f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -771,6 +771,8 @@
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \
(einode)->xtime.tv_sec = \
(signed)le32_to_cpu((raw_inode)->xtime); \
+ else \
+ (einode)->xtime.tv_sec = 0; \
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \
ext4_decode_extra_time(&(einode)->xtime, \
raw_inode->xtime ## _extra); \
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 10cff47..74bc2d5 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3906,6 +3906,7 @@
} else
err = ret;
map->m_flags |= EXT4_MAP_MAPPED;
+ map->m_pblk = newblock;
if (allocated > map->m_len)
allocated = map->m_len;
map->m_len = allocated;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 6bea806..a2a837f 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -140,7 +140,7 @@
handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
if (IS_ERR(handle)) {
err = -EINVAL;
- goto swap_boot_out;
+ goto journal_err_out;
}
/* Protect extent tree against block allocations via delalloc */
@@ -198,6 +198,7 @@
ext4_double_up_write_data_sem(inode, inode_bl);
+journal_err_out:
ext4_inode_resume_unlocked_dio(inode);
ext4_inode_resume_unlocked_dio(inode_bl);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index c5adbb3..f3b84cd 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -243,6 +243,7 @@
ext4_group_t group;
ext4_group_t last_group;
unsigned overhead;
+ __u16 uninit_mask = (flexbg_size > 1) ? ~EXT4_BG_BLOCK_UNINIT : ~0;
BUG_ON(flex_gd->count == 0 || group_data == NULL);
@@ -266,7 +267,7 @@
src_group++;
for (; src_group <= last_group; src_group++) {
overhead = ext4_group_overhead_blocks(sb, src_group);
- if (overhead != 0)
+ if (overhead == 0)
last_blk += group_data[src_group - group].blocks_count;
else
break;
@@ -280,8 +281,7 @@
group = ext4_get_group_number(sb, start_blk - 1);
group -= group_data[0].group;
group_data[group].free_blocks_count--;
- if (flexbg_size > 1)
- flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+ flex_gd->bg_flags[group] &= uninit_mask;
}
/* Allocate inode bitmaps */
@@ -292,22 +292,30 @@
group = ext4_get_group_number(sb, start_blk - 1);
group -= group_data[0].group;
group_data[group].free_blocks_count--;
- if (flexbg_size > 1)
- flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+ flex_gd->bg_flags[group] &= uninit_mask;
}
/* Allocate inode tables */
for (; it_index < flex_gd->count; it_index++) {
- if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk)
+ unsigned int itb = EXT4_SB(sb)->s_itb_per_group;
+ ext4_fsblk_t next_group_start;
+
+ if (start_blk + itb > last_blk)
goto next_group;
group_data[it_index].inode_table = start_blk;
- group = ext4_get_group_number(sb, start_blk - 1);
+ group = ext4_get_group_number(sb, start_blk);
+ next_group_start = ext4_group_first_block_no(sb, group + 1);
group -= group_data[0].group;
- group_data[group].free_blocks_count -=
- EXT4_SB(sb)->s_itb_per_group;
- if (flexbg_size > 1)
- flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+ if (start_blk + itb > next_group_start) {
+ flex_gd->bg_flags[group + 1] &= uninit_mask;
+ overhead = start_blk + itb - next_group_start;
+ group_data[group + 1].free_blocks_count -= overhead;
+ itb -= overhead;
+ }
+
+ group_data[group].free_blocks_count -= itb;
+ flex_gd->bg_flags[group] &= uninit_mask;
start_blk += EXT4_SB(sb)->s_itb_per_group;
}
@@ -401,7 +409,7 @@
start = ext4_group_first_block_no(sb, group);
group -= flex_gd->groups[0].group;
- count2 = sb->s_blocksize * 8 - (block - start);
+ count2 = EXT4_BLOCKS_PER_GROUP(sb) - (block - start);
if (count2 > count)
count2 = count;
@@ -620,7 +628,7 @@
if (err)
goto out;
count = group_table_count[j];
- start = group_data[i].block_bitmap;
+ start = (&group_data[i].block_bitmap)[j];
block = start;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 1f7784d..710fed2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3695,16 +3695,22 @@
for (i = 0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
- i = le32_to_cpu(es->s_flags);
- if (i & EXT2_FLAGS_UNSIGNED_HASH)
- sbi->s_hash_unsigned = 3;
- else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+ if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) {
+ i = le32_to_cpu(es->s_flags);
+ if (i & EXT2_FLAGS_UNSIGNED_HASH)
+ sbi->s_hash_unsigned = 3;
+ else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
#ifdef __CHAR_UNSIGNED__
- es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
- sbi->s_hash_unsigned = 3;
+ if (!(sb->s_flags & MS_RDONLY))
+ es->s_flags |=
+ cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+ sbi->s_hash_unsigned = 3;
#else
- es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+ if (!(sb->s_flags & MS_RDONLY))
+ es->s_flags |=
+ cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
#endif
+ }
}
/* Handle clustersize */
diff --git a/fs/file.c b/fs/file.c
index 771578b..eb56a13 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -34,7 +34,7 @@
* vmalloc() if the allocation size will be considered "large" by the VM.
*/
if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
- void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN);
+ void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY);
if (data != NULL)
return data;
}
@@ -683,35 +683,54 @@
* The fput_needed flag returned by fget_light should be passed to the
* corresponding fput_light.
*/
-struct file *__fget_light(unsigned int fd, fmode_t mask, int *fput_needed)
+static unsigned long __fget_light(unsigned int fd, fmode_t mask)
{
struct files_struct *files = current->files;
struct file *file;
- *fput_needed = 0;
if (atomic_read(&files->count) == 1) {
file = __fcheck_files(files, fd);
- if (file && (file->f_mode & mask))
- file = NULL;
+ if (!file || unlikely(file->f_mode & mask))
+ return 0;
+ return (unsigned long)file;
} else {
file = __fget(fd, mask);
- if (file)
- *fput_needed = 1;
+ if (!file)
+ return 0;
+ return FDPUT_FPUT | (unsigned long)file;
}
-
- return file;
}
-struct file *fget_light(unsigned int fd, int *fput_needed)
+unsigned long __fdget(unsigned int fd)
{
- return __fget_light(fd, FMODE_PATH, fput_needed);
+ return __fget_light(fd, FMODE_PATH);
}
-EXPORT_SYMBOL(fget_light);
+EXPORT_SYMBOL(__fdget);
-struct file *fget_raw_light(unsigned int fd, int *fput_needed)
+unsigned long __fdget_raw(unsigned int fd)
{
- return __fget_light(fd, 0, fput_needed);
+ return __fget_light(fd, 0);
}
+unsigned long __fdget_pos(unsigned int fd)
+{
+ unsigned long v = __fdget(fd);
+ struct file *file = (struct file *)(v & ~3);
+
+ if (file && (file->f_mode & FMODE_ATOMIC_POS)) {
+ if (file_count(file) > 1) {
+ v |= FDPUT_POS_UNLOCK;
+ mutex_lock(&file->f_pos_lock);
+ }
+ }
+ return v;
+}
+
+/*
+ * We only lock f_pos if we have threads or if the file might be
+ * shared with another process. In both cases we'll have an elevated
+ * file count (done either by fdget() or by fork()).
+ */
+
void set_close_on_exec(unsigned int fd, int flag)
{
struct files_struct *files = current->files;
diff --git a/fs/file_table.c b/fs/file_table.c
index 5fff903..5b24008 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -135,6 +135,7 @@
atomic_long_set(&f->f_count, 1);
rwlock_init(&f->f_owner.lock);
spin_lock_init(&f->f_lock);
+ mutex_init(&f->f_pos_lock);
eventpoll_init_file(f);
/* f->f_version: 0 */
return f;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e0259a1..d754e3c 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -40,18 +40,13 @@
struct wb_writeback_work {
long nr_pages;
struct super_block *sb;
- /*
- * Write only inodes dirtied before this time. Don't forget to set
- * older_than_this_is_set when you set this.
- */
- unsigned long older_than_this;
+ unsigned long *older_than_this;
enum writeback_sync_modes sync_mode;
unsigned int tagged_writepages:1;
unsigned int for_kupdate:1;
unsigned int range_cyclic:1;
unsigned int for_background:1;
unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */
- unsigned int older_than_this_is_set:1;
enum wb_reason reason; /* why was writeback initiated? */
struct list_head list; /* pending work list */
@@ -252,10 +247,10 @@
int do_sb_sort = 0;
int moved = 0;
- WARN_ON_ONCE(!work->older_than_this_is_set);
while (!list_empty(delaying_queue)) {
inode = wb_inode(delaying_queue->prev);
- if (inode_dirtied_after(inode, work->older_than_this))
+ if (work->older_than_this &&
+ inode_dirtied_after(inode, *work->older_than_this))
break;
list_move(&inode->i_wb_list, &tmp);
moved++;
@@ -742,8 +737,6 @@
.sync_mode = WB_SYNC_NONE,
.range_cyclic = 1,
.reason = reason,
- .older_than_this = jiffies,
- .older_than_this_is_set = 1,
};
spin_lock(&wb->list_lock);
@@ -802,13 +795,12 @@
{
unsigned long wb_start = jiffies;
long nr_pages = work->nr_pages;
+ unsigned long oldest_jif;
struct inode *inode;
long progress;
- if (!work->older_than_this_is_set) {
- work->older_than_this = jiffies;
- work->older_than_this_is_set = 1;
- }
+ oldest_jif = jiffies;
+ work->older_than_this = &oldest_jif;
spin_lock(&wb->list_lock);
for (;;) {
@@ -842,10 +834,10 @@
* safe.
*/
if (work->for_kupdate) {
- work->older_than_this = jiffies -
+ oldest_jif = jiffies -
msecs_to_jiffies(dirty_expire_interval * 10);
} else if (work->for_background)
- work->older_than_this = jiffies;
+ oldest_jif = jiffies;
trace_writeback_start(wb->bdi, work);
if (list_empty(&wb->b_io))
@@ -1357,21 +1349,18 @@
/**
* sync_inodes_sb - sync sb inode pages
- * @sb: the superblock
- * @older_than_this: timestamp
+ * @sb: the superblock
*
* This function writes and waits on any dirty inode belonging to this
- * superblock that has been dirtied before given timestamp.
+ * super_block.
*/
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this)
+void sync_inodes_sb(struct super_block *sb)
{
DECLARE_COMPLETION_ONSTACK(done);
struct wb_writeback_work work = {
.sb = sb,
.sync_mode = WB_SYNC_ALL,
.nr_pages = LONG_MAX,
- .older_than_this = older_than_this,
- .older_than_this_is_set = 1,
.range_cyclic = 0,
.done = &done,
.reason = WB_REASON_SYNC,
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index e1959ef..b5ebc2d 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -50,6 +50,8 @@
struct fscache_object *xobj;
struct rb_node **p = &fscache_object_list.rb_node, *parent = NULL;
+ ASSERT(RB_EMPTY_NODE(&obj->objlist_link));
+
write_lock(&fscache_object_list_lock);
while (*p) {
@@ -75,6 +77,9 @@
*/
void fscache_objlist_remove(struct fscache_object *obj)
{
+ if (RB_EMPTY_NODE(&obj->objlist_link))
+ return;
+
write_lock(&fscache_object_list_lock);
BUG_ON(RB_EMPTY_ROOT(&fscache_object_list));
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 53d35c5..d3b4539 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -314,6 +314,9 @@
object->cache = cache;
object->cookie = cookie;
object->parent = NULL;
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+ RB_CLEAR_NODE(&object->objlist_link);
+#endif
object->oob_event_mask = 0;
for (t = object->oob_table; t->events; t++)
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index 968ce41..32602c6 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -103,6 +103,8 @@
folder = &entry->folder;
memset(folder, 0, sizeof(*folder));
folder->type = cpu_to_be16(HFSPLUS_FOLDER);
+ if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags))
+ folder->flags |= cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT);
folder->id = cpu_to_be32(inode->i_ino);
HFSPLUS_I(inode)->create_date =
folder->create_date =
@@ -203,6 +205,36 @@
return hfs_brec_find(fd, hfs_find_rec_by_key);
}
+static void hfsplus_subfolders_inc(struct inode *dir)
+{
+ struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
+
+ if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) {
+ /*
+ * Increment subfolder count. Note, the value is only meaningful
+ * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set.
+ */
+ HFSPLUS_I(dir)->subfolders++;
+ }
+}
+
+static void hfsplus_subfolders_dec(struct inode *dir)
+{
+ struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
+
+ if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) {
+ /*
+ * Decrement subfolder count. Note, the value is only meaningful
+ * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set.
+ *
+ * Check for zero. Some subfolders may have been created
+ * by an implementation ignorant of this counter.
+ */
+ if (HFSPLUS_I(dir)->subfolders)
+ HFSPLUS_I(dir)->subfolders--;
+ }
+}
+
int hfsplus_create_cat(u32 cnid, struct inode *dir,
struct qstr *str, struct inode *inode)
{
@@ -247,6 +279,8 @@
goto err1;
dir->i_size++;
+ if (S_ISDIR(inode->i_mode))
+ hfsplus_subfolders_inc(dir);
dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY);
@@ -336,6 +370,8 @@
goto out;
dir->i_size--;
+ if (type == HFSPLUS_FOLDER)
+ hfsplus_subfolders_dec(dir);
dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY);
@@ -380,6 +416,7 @@
hfs_bnode_read(src_fd.bnode, &entry, src_fd.entryoffset,
src_fd.entrylength);
+ type = be16_to_cpu(entry.type);
/* create new dir entry with the data from the old entry */
hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name);
@@ -394,6 +431,8 @@
if (err)
goto out;
dst_dir->i_size++;
+ if (type == HFSPLUS_FOLDER)
+ hfsplus_subfolders_inc(dst_dir);
dst_dir->i_mtime = dst_dir->i_ctime = CURRENT_TIME_SEC;
/* finally remove the old entry */
@@ -405,6 +444,8 @@
if (err)
goto out;
src_dir->i_size--;
+ if (type == HFSPLUS_FOLDER)
+ hfsplus_subfolders_dec(src_dir);
src_dir->i_mtime = src_dir->i_ctime = CURRENT_TIME_SEC;
/* remove old thread entry */
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 08846425b..62d571e 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -242,6 +242,7 @@
*/
sector_t fs_blocks;
u8 userflags; /* BSD user file flags */
+ u32 subfolders; /* Subfolder count (HFSX only) */
struct list_head open_dir_list;
loff_t phys_size;
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index 8ffb3a8..5a12682 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -261,7 +261,7 @@
struct DInfo user_info;
struct DXInfo finder_info;
__be32 text_encoding;
- u32 reserved;
+ __be32 subfolders; /* Subfolder count in HFSX. Reserved in HFS+. */
} __packed;
/* HFS file info (stolen from hfs.h) */
@@ -301,11 +301,13 @@
struct hfsplus_fork_raw rsrc_fork;
} __packed;
-/* File attribute bits */
+/* File and folder flag bits */
#define HFSPLUS_FILE_LOCKED 0x0001
#define HFSPLUS_FILE_THREAD_EXISTS 0x0002
#define HFSPLUS_XATTR_EXISTS 0x0004
#define HFSPLUS_ACL_EXISTS 0x0008
+#define HFSPLUS_HAS_FOLDER_COUNT 0x0010 /* Folder has subfolder count
+ * (HFSX only) */
/* HFS+ catalog thread (part of a cat_entry) */
struct hfsplus_cat_thread {
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index fa929f3..a4f45bd 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -375,6 +375,7 @@
hip->extent_state = 0;
hip->flags = 0;
hip->userflags = 0;
+ hip->subfolders = 0;
memset(hip->first_extents, 0, sizeof(hfsplus_extent_rec));
memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
hip->alloc_blocks = 0;
@@ -494,6 +495,10 @@
inode->i_ctime = hfsp_mt2ut(folder->attribute_mod_date);
HFSPLUS_I(inode)->create_date = folder->create_date;
HFSPLUS_I(inode)->fs_blocks = 0;
+ if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) {
+ HFSPLUS_I(inode)->subfolders =
+ be32_to_cpu(folder->subfolders);
+ }
inode->i_op = &hfsplus_dir_inode_operations;
inode->i_fop = &hfsplus_dir_operations;
} else if (type == HFSPLUS_FILE) {
@@ -566,6 +571,10 @@
folder->content_mod_date = hfsp_ut2mt(inode->i_mtime);
folder->attribute_mod_date = hfsp_ut2mt(inode->i_ctime);
folder->valence = cpu_to_be32(inode->i_size - 2);
+ if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) {
+ folder->subfolders =
+ cpu_to_be32(HFSPLUS_I(inode)->subfolders);
+ }
hfs_bnode_write(fd.bnode, &entry, fd.entryoffset,
sizeof(struct hfsplus_cat_folder));
} else if (HFSPLUS_IS_RSRC(inode)) {
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index 968eab5..68537e8 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -75,7 +75,7 @@
int token;
if (!input)
- return 0;
+ return 1;
while ((p = strsep(&input, ",")) != NULL) {
if (!*p)
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 8360674..60bb365 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -514,11 +514,13 @@
* similarly constrained call sites
*/
ret = start_this_handle(journal, handle, GFP_NOFS);
- if (ret < 0)
+ if (ret < 0) {
jbd2_journal_free_reserved(handle);
+ return ret;
+ }
handle->h_type = type;
handle->h_line_no = line_no;
- return ret;
+ return 0;
}
EXPORT_SYMBOL(jbd2_journal_start_reserved);
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index e973b85..5a8ea16 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -86,6 +86,8 @@
rc = posix_acl_equiv_mode(acl, &inode->i_mode);
if (rc < 0)
return rc;
+ inode->i_ctime = CURRENT_TIME;
+ mark_inode_dirty(inode);
if (rc == 0)
acl = NULL;
break;
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 0d6ce89..0f4152d 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -94,6 +94,7 @@
* @fs_type: file_system_type of the fs being mounted
* @flags: mount flags specified for the mount
* @root: kernfs_root of the hierarchy being mounted
+ * @new_sb_created: tell the caller if we allocated a new superblock
* @ns: optional namespace tag of the mount
*
* This is to be called from each kernfs user's file_system_type->mount()
@@ -104,7 +105,8 @@
* The return value can be passed to the vfs layer verbatim.
*/
struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
- struct kernfs_root *root, const void *ns)
+ struct kernfs_root *root, bool *new_sb_created,
+ const void *ns)
{
struct super_block *sb;
struct kernfs_super_info *info;
@@ -122,6 +124,10 @@
kfree(info);
if (IS_ERR(sb))
return ERR_CAST(sb);
+
+ if (new_sb_created)
+ *new_sb_created = !sb->s_root;
+
if (!sb->s_root) {
error = kernfs_fill_super(sb);
if (error) {
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index e066a39..ab798a88 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -779,6 +779,7 @@
struct nlm_file *file = block->b_file;
struct nlm_lock *lock = &block->b_call->a_args.lock;
int error;
+ loff_t fl_start, fl_end;
dprintk("lockd: grant blocked lock %p\n", block);
@@ -796,9 +797,16 @@
}
/* Try the lock operation again */
+ /* vfs_lock_file() can mangle fl_start and fl_end, but we need
+ * them unchanged for the GRANT_MSG
+ */
lock->fl.fl_flags |= FL_SLEEP;
+ fl_start = lock->fl.fl_start;
+ fl_end = lock->fl.fl_end;
error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
lock->fl.fl_flags &= ~FL_SLEEP;
+ lock->fl.fl_start = fl_start;
+ lock->fl.fl_end = fl_end;
switch (error) {
case 0:
diff --git a/fs/namei.c b/fs/namei.c
index 385f781..4b491b4 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1109,7 +1109,7 @@
return false;
if (!d_mountpoint(path->dentry))
- break;
+ return true;
mounted = __lookup_mnt(path->mnt, path->dentry);
if (!mounted)
@@ -1125,20 +1125,7 @@
*/
*inode = path->dentry->d_inode;
}
- return true;
-}
-
-static void follow_mount_rcu(struct nameidata *nd)
-{
- while (d_mountpoint(nd->path.dentry)) {
- struct mount *mounted;
- mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
- if (!mounted)
- break;
- nd->path.mnt = &mounted->mnt;
- nd->path.dentry = mounted->mnt.mnt_root;
- nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
- }
+ return read_seqretry(&mount_lock, nd->m_seq);
}
static int follow_dotdot_rcu(struct nameidata *nd)
@@ -1166,7 +1153,17 @@
break;
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
}
- follow_mount_rcu(nd);
+ while (d_mountpoint(nd->path.dentry)) {
+ struct mount *mounted;
+ mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
+ if (!mounted)
+ break;
+ nd->path.mnt = &mounted->mnt;
+ nd->path.dentry = mounted->mnt.mnt_root;
+ nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
+ if (!read_seqretry(&mount_lock, nd->m_seq))
+ goto failed;
+ }
nd->inode = nd->path.dentry->d_inode;
return 0;
@@ -1884,7 +1881,7 @@
nd->path = f.file->f_path;
if (flags & LOOKUP_RCU) {
- if (f.need_put)
+ if (f.flags & FDPUT_FPUT)
*fp = f.file;
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
rcu_read_lock();
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index ef792f2..5d8ccec 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -659,16 +659,19 @@
rcu_read_lock();
delegation = rcu_dereference(NFS_I(inode)->delegation);
+ if (delegation == NULL)
+ goto out_enoent;
- if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) {
- rcu_read_unlock();
- return -ENOENT;
- }
+ if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid))
+ goto out_enoent;
nfs_mark_return_delegation(server, delegation);
rcu_read_unlock();
nfs_delegation_run_state_manager(clp);
return 0;
+out_enoent:
+ rcu_read_unlock();
+ return -ENOENT;
}
static struct inode *
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index be38b57..4a48fe4 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1846,6 +1846,11 @@
GFP_KERNEL)) {
SetPageUptodate(page);
unlock_page(page);
+ /*
+ * add_to_page_cache_lru() grabs an extra page refcount.
+ * Drop it here to avoid leaking this page later.
+ */
+ page_cache_release(page);
} else
__free_page(page);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 28a0a3c..360114a 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -164,17 +164,16 @@
if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
nfs_fscache_invalidate(inode);
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
- | NFS_INO_INVALID_LABEL
| NFS_INO_INVALID_DATA
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_PAGECACHE;
} else
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
- | NFS_INO_INVALID_LABEL
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_PAGECACHE;
+ nfs_zap_label_cache_locked(nfsi);
}
void nfs_zap_caches(struct inode *inode)
@@ -266,6 +265,13 @@
}
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
+static void nfs_clear_label_invalid(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL;
+ spin_unlock(&inode->i_lock);
+}
+
void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
struct nfs4_label *label)
{
@@ -283,6 +289,7 @@
__func__,
(char *)label->label,
label->len, error);
+ nfs_clear_label_invalid(inode);
}
}
@@ -1648,7 +1655,7 @@
inode->i_blocks = fattr->du.nfs2.blocks;
/* Update attrtimeo value if we're out of the unstable period */
- if (invalid & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL)) {
+ if (invalid & NFS_INO_INVALID_ATTR) {
nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
nfsi->attrtimeo_timestamp = now;
@@ -1661,7 +1668,6 @@
}
}
invalid &= ~NFS_INO_INVALID_ATTR;
- invalid &= ~NFS_INO_INVALID_LABEL;
/* Don't invalidate the data if we were to blame */
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
|| S_ISLNK(inode->i_mode)))
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 8b5cc04..b46cf5a 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -176,7 +176,8 @@
extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
struct nfs_fh *);
extern int nfs4_update_server(struct nfs_server *server, const char *hostname,
- struct sockaddr *sap, size_t salen);
+ struct sockaddr *sap, size_t salen,
+ struct net *net);
extern void nfs_free_server(struct nfs_server *server);
extern struct nfs_server *nfs_clone_server(struct nfs_server *,
struct nfs_fh *,
@@ -279,9 +280,18 @@
}
return;
}
+
+static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
+{
+ if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL))
+ nfsi->cache_validity |= NFS_INO_INVALID_LABEL;
+}
#else
static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; }
static inline void nfs4_label_free(void *label) {}
+static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
+{
+}
#endif /* CONFIG_NFS_V4_SECURITY_LABEL */
/* proc.c */
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index aa9bc97..a462ef0 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -18,6 +18,7 @@
#include <linux/lockd/bind.h>
#include <linux/nfs_mount.h>
#include <linux/freezer.h>
+#include <linux/xattr.h>
#include "iostat.h"
#include "internal.h"
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 860ad26..0e46d3d 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1135,6 +1135,7 @@
* @hostname: new end-point's hostname
* @sap: new end-point's socket address
* @salen: size of "sap"
+ * @net: net namespace
*
* The nfs_server must be quiescent before this function is invoked.
* Either its session is drained (NFSv4.1+), or its transport is
@@ -1143,13 +1144,13 @@
* Returns zero on success, or a negative errno value.
*/
int nfs4_update_server(struct nfs_server *server, const char *hostname,
- struct sockaddr *sap, size_t salen)
+ struct sockaddr *sap, size_t salen, struct net *net)
{
struct nfs_client *clp = server->nfs_client;
struct rpc_clnt *clnt = server->client;
struct xprt_create xargs = {
.ident = clp->cl_proto,
- .net = &init_net,
+ .net = net,
.dstaddr = sap,
.addrlen = salen,
.servername = hostname,
@@ -1189,7 +1190,7 @@
error = nfs4_set_client(server, hostname, sap, salen, buf,
clp->cl_rpcclient->cl_auth->au_flavor,
clp->cl_proto, clnt->cl_timeout,
- clp->cl_minorversion, clp->cl_net);
+ clp->cl_minorversion, net);
nfs_put_client(clp);
if (error != 0) {
nfs_server_insert_lists(server);
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 12c8132..b9a35c0 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -324,8 +324,9 @@
&rdata->res.seq_res,
task))
return;
- nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
- rdata->args.lock_context, FMODE_READ);
+ if (nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
+ rdata->args.lock_context, FMODE_READ) == -EIO)
+ rpc_exit(task, -EIO); /* lost lock, terminate I/O */
}
static void filelayout_read_call_done(struct rpc_task *task, void *data)
@@ -435,8 +436,9 @@
&wdata->res.seq_res,
task))
return;
- nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
- wdata->args.lock_context, FMODE_WRITE);
+ if (nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
+ wdata->args.lock_context, FMODE_WRITE) == -EIO)
+ rpc_exit(task, -EIO); /* lost lock, terminate I/O */
}
static void filelayout_write_call_done(struct rpc_task *task, void *data)
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 4e7f05d..3d5dbf8 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -121,9 +121,8 @@
}
static size_t nfs_parse_server_name(char *string, size_t len,
- struct sockaddr *sa, size_t salen, struct nfs_server *server)
+ struct sockaddr *sa, size_t salen, struct net *net)
{
- struct net *net = rpc_net_ns(server->client);
ssize_t ret;
ret = rpc_pton(net, string, len, sa, salen);
@@ -223,6 +222,7 @@
const struct nfs4_fs_location *location)
{
const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+ struct net *net = rpc_net_ns(NFS_SB(mountdata->sb)->client);
struct vfsmount *mnt = ERR_PTR(-ENOENT);
char *mnt_path;
unsigned int maxbuflen;
@@ -248,8 +248,7 @@
continue;
mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len,
- mountdata->addr, addr_bufsize,
- NFS_SB(mountdata->sb));
+ mountdata->addr, addr_bufsize, net);
if (mountdata->addrlen == 0)
continue;
@@ -419,6 +418,7 @@
const struct nfs4_fs_location *location)
{
const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+ struct net *net = rpc_net_ns(server->client);
struct sockaddr *sap;
unsigned int s;
size_t salen;
@@ -440,7 +440,7 @@
continue;
salen = nfs_parse_server_name(buf->data, buf->len,
- sap, addr_bufsize, server);
+ sap, addr_bufsize, net);
if (salen == 0)
continue;
rpc_set_port(sap, NFS_PORT);
@@ -450,7 +450,7 @@
if (hostname == NULL)
break;
- error = nfs4_update_server(server, hostname, sap, salen);
+ error = nfs4_update_server(server, hostname, sap, salen, net);
kfree(hostname);
if (error == 0)
break;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 2da6a69..450bfed 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2398,13 +2398,16 @@
if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) {
/* Use that stateid */
- } else if (truncate && state != NULL && nfs4_valid_open_stateid(state)) {
+ } else if (truncate && state != NULL) {
struct nfs_lockowner lockowner = {
.l_owner = current->files,
.l_pid = current->tgid,
};
- nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
- &lockowner);
+ if (!nfs4_valid_open_stateid(state))
+ return -EBADF;
+ if (nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
+ &lockowner) == -EIO)
+ return -EBADF;
} else
nfs4_stateid_copy(&arg.stateid, &zero_stateid);
@@ -4011,8 +4014,9 @@
{
nfs4_stateid current_stateid;
- if (nfs4_set_rw_stateid(¤t_stateid, ctx, l_ctx, fmode))
- return false;
+ /* If the current stateid represents a lost lock, then exit */
+ if (nfs4_set_rw_stateid(¤t_stateid, ctx, l_ctx, fmode) == -EIO)
+ return true;
return nfs4_stateid_match(stateid, ¤t_stateid);
}
@@ -5828,8 +5832,7 @@
struct nfs4_lock_state *lsp;
struct nfs_server *server;
struct nfs_release_lockowner_args args;
- struct nfs4_sequence_args seq_args;
- struct nfs4_sequence_res seq_res;
+ struct nfs_release_lockowner_res res;
unsigned long timestamp;
};
@@ -5837,7 +5840,7 @@
{
struct nfs_release_lockowner_data *data = calldata;
nfs40_setup_sequence(data->server,
- &data->seq_args, &data->seq_res, task);
+ &data->args.seq_args, &data->res.seq_res, task);
data->timestamp = jiffies;
}
@@ -5846,7 +5849,7 @@
struct nfs_release_lockowner_data *data = calldata;
struct nfs_server *server = data->server;
- nfs40_sequence_done(task, &data->seq_res);
+ nfs40_sequence_done(task, &data->res.seq_res);
switch (task->tk_status) {
case 0:
@@ -5887,7 +5890,6 @@
data = kmalloc(sizeof(*data), GFP_NOFS);
if (!data)
return -ENOMEM;
- nfs4_init_sequence(&data->seq_args, &data->seq_res, 0);
data->lsp = lsp;
data->server = server;
data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
@@ -5895,6 +5897,8 @@
data->args.lock_owner.s_dev = server->s_dev;
msg.rpc_argp = &data->args;
+ msg.rpc_resp = &data->res;
+ nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data);
return 0;
}
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e5be725..0deb321 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -974,9 +974,6 @@
else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
nfs4_stateid_copy(dst, &lsp->ls_stateid);
ret = 0;
- smp_rmb();
- if (!list_empty(&lsp->ls_seqid.list))
- ret = -EWOULDBLOCK;
}
spin_unlock(&state->state_lock);
nfs4_put_lock_state(lsp);
@@ -984,10 +981,9 @@
return ret;
}
-static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
+static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
{
const nfs4_stateid *src;
- int ret;
int seq;
do {
@@ -996,12 +992,7 @@
if (test_bit(NFS_OPEN_STATE, &state->flags))
src = &state->open_stateid;
nfs4_stateid_copy(dst, src);
- ret = 0;
- smp_rmb();
- if (!list_empty(&state->owner->so_seqid.list))
- ret = -EWOULDBLOCK;
} while (read_seqretry(&state->seqlock, seq));
- return ret;
}
/*
@@ -1015,15 +1006,19 @@
if (ret == -EIO)
/* A lost lock - don't even consider delegations */
goto out;
- if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
+ /* returns true if delegation stateid found and copied */
+ if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) {
+ ret = 0;
goto out;
+ }
if (ret != -ENOENT)
/* nfs4_copy_delegation_stateid() didn't over-write
* dst, so it still has the lock stateid which we now
* choose to use.
*/
goto out;
- ret = nfs4_copy_open_stateid(dst, state);
+ nfs4_copy_open_stateid(dst, state);
+ ret = 0;
out:
if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41))
dst->seqid = 0;
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index d3a5871..d190e33 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -151,17 +151,15 @@
pacl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
if (IS_ERR(pacl))
return PTR_ERR(pacl);
- /* allocate for worst case: one (deny, allow) pair each: */
- size += 2 * pacl->a_count;
}
+ /* allocate for worst case: one (deny, allow) pair each: */
+ size += 2 * pacl->a_count;
if (S_ISDIR(inode->i_mode)) {
flags = NFS4_ACL_DIR;
dpacl = get_acl(inode, ACL_TYPE_DEFAULT);
if (dpacl)
size += 2 * dpacl->a_count;
- } else {
- dpacl = NULL;
}
*acl = nfs4_acl_new(size);
@@ -170,8 +168,7 @@
goto out;
}
- if (pacl)
- _posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT);
+ _posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT);
if (dpacl)
_posix_to_nfsv4_one(dpacl, *acl, flags | NFS4_ACL_TYPE_DEFAULT);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 017d3cb..6d7be3f 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -449,6 +449,7 @@
fh_lock(fhp);
host_err = notify_change(dentry, iap, NULL);
fh_unlock(fhp);
+ err = nfserrno(host_err);
out_put_write_access:
if (size_change)
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 0b9ff43..abc8cbc 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -86,7 +86,7 @@
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name)
+ const unsigned char *file_name, u32 cookie)
{
struct dnotify_mark *dn_mark;
struct dnotify_struct *dn;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 0e792f5..dc638f7 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -147,7 +147,7 @@
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *fanotify_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name)
+ const unsigned char *file_name, u32 cookie)
{
int ret = 0;
struct fanotify_event_info *event;
@@ -192,10 +192,12 @@
ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge);
if (ret) {
- BUG_ON(mask & FAN_ALL_PERM_EVENTS);
+ /* Permission events shouldn't be merged */
+ BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS);
/* Our event wasn't used in the end. Free it. */
fsnotify_destroy_event(group, fsn_event);
- ret = 0;
+
+ return 0;
}
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index b6175fa..287a22c 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -698,6 +698,7 @@
struct fsnotify_group *group;
int f_flags, fd;
struct user_struct *user;
+ struct fanotify_event_info *oevent;
pr_debug("%s: flags=%d event_f_flags=%d\n",
__func__, flags, event_f_flags);
@@ -730,8 +731,20 @@
group->fanotify_data.user = user;
atomic_inc(&user->fanotify_listeners);
+ oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+ if (unlikely(!oevent)) {
+ fd = -ENOMEM;
+ goto out_destroy_group;
+ }
+ group->overflow_event = &oevent->fse;
+ fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+ oevent->tgid = get_pid(task_tgid(current));
+ oevent->path.mnt = NULL;
+ oevent->path.dentry = NULL;
+
group->fanotify_data.f_flags = event_f_flags;
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+ oevent->response = 0;
mutex_init(&group->fanotify_data.access_mutex);
init_waitqueue_head(&group->fanotify_data.access_waitq);
INIT_LIST_HEAD(&group->fanotify_data.access_list);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 1d4e1ea..9d3e9c5 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -179,7 +179,7 @@
return group->ops->handle_event(group, to_tell, inode_mark,
vfsmount_mark, mask, data, data_is,
- file_name);
+ file_name, cookie);
}
/*
diff --git a/fs/notify/group.c b/fs/notify/group.c
index ee674fe..ad19959 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -55,6 +55,13 @@
/* clear the notification queue of all events */
fsnotify_flush_notify(group);
+ /*
+ * Destroy overflow event (we cannot use fsnotify_destroy_event() as
+ * that deliberately ignores overflow events.
+ */
+ if (group->overflow_event)
+ group->ops->free_event(group->overflow_event);
+
fsnotify_put_group(group);
}
@@ -99,7 +106,6 @@
INIT_LIST_HEAD(&group->marks_list);
group->ops = ops;
- fsnotify_init_event(&group->overflow_event, NULL, FS_Q_OVERFLOW);
return group;
}
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
index 485eef3..ed855ef 100644
--- a/fs/notify/inotify/inotify.h
+++ b/fs/notify/inotify/inotify.h
@@ -27,6 +27,6 @@
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name);
+ const unsigned char *file_name, u32 cookie);
extern const struct fsnotify_ops inotify_fsnotify_ops;
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index d5ee563..43ab1e1 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -67,7 +67,7 @@
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name)
+ const unsigned char *file_name, u32 cookie)
{
struct inotify_inode_mark *i_mark;
struct inotify_event_info *event;
@@ -103,6 +103,7 @@
fsn_event = &event->fse;
fsnotify_init_event(fsn_event, inode, mask);
event->wd = i_mark->wd;
+ event->sync_cookie = cookie;
event->name_len = len;
if (len)
strcpy(event->name, file_name);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 497395c..78a2ca3 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -495,7 +495,7 @@
/* Queue ignore event for the watch */
inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED,
- NULL, FSNOTIFY_EVENT_NONE, NULL);
+ NULL, FSNOTIFY_EVENT_NONE, NULL, 0);
i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
/* remove this mark from the idr */
@@ -633,11 +633,23 @@
static struct fsnotify_group *inotify_new_group(unsigned int max_events)
{
struct fsnotify_group *group;
+ struct inotify_event_info *oevent;
group = fsnotify_alloc_group(&inotify_fsnotify_ops);
if (IS_ERR(group))
return group;
+ oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL);
+ if (unlikely(!oevent)) {
+ fsnotify_destroy_group(group);
+ return ERR_PTR(-ENOMEM);
+ }
+ group->overflow_event = &oevent->fse;
+ fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+ oevent->wd = -1;
+ oevent->sync_cookie = 0;
+ oevent->name_len = 0;
+
group->max_events = max_events;
spin_lock_init(&group->inotify_data.idr_lock);
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index 18b3c44..1e58402 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -80,7 +80,8 @@
/*
* Add an event to the group notification queue. The group can later pull this
* event off the queue to deal with. The function returns 0 if the event was
- * added to the queue, 1 if the event was merged with some other queued event.
+ * added to the queue, 1 if the event was merged with some other queued event,
+ * 2 if the queue of events has overflown.
*/
int fsnotify_add_notify_event(struct fsnotify_group *group,
struct fsnotify_event *event,
@@ -95,10 +96,14 @@
mutex_lock(&group->notification_mutex);
if (group->q_len >= group->max_events) {
+ ret = 2;
/* Queue overflow event only if it isn't already queued */
- if (list_empty(&group->overflow_event.list))
- event = &group->overflow_event;
- ret = 1;
+ if (!list_empty(&group->overflow_event->list)) {
+ mutex_unlock(&group->notification_mutex);
+ return ret;
+ }
+ event = group->overflow_event;
+ goto queue;
}
if (!list_empty(list) && merge) {
@@ -109,6 +114,7 @@
}
}
+queue:
group->q_len++;
list_add_tail(&event->list, list);
mutex_unlock(&group->notification_mutex);
@@ -132,7 +138,11 @@
event = list_first_entry(&group->notification_list,
struct fsnotify_event, list);
- list_del(&event->list);
+ /*
+ * We need to init list head for the case of overflow event so that
+ * check in fsnotify_add_notify_events() works
+ */
+ list_del_init(&event->list);
group->q_len--;
return event;
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index aada580..e2edff3 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -7158,7 +7158,7 @@
if (end > i_size_read(inode))
end = i_size_read(inode);
- BUG_ON(start >= end);
+ BUG_ON(start > end);
if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) ||
!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) ||
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index d77d71e..51632c4 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -185,6 +185,9 @@
file->f_path.dentry->d_name.name,
(unsigned long long)datasync);
+ if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
+ return -EROFS;
+
err = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (err)
return err;
@@ -474,11 +477,6 @@
goto bail;
}
- /* lets handle the simple truncate cases before doing any more
- * cluster locking. */
- if (new_i_size == le64_to_cpu(fe->i_size))
- goto bail;
-
down_write(&OCFS2_I(inode)->ip_alloc_sem);
ocfs2_resv_discard(&osb->osb_la_resmap,
@@ -718,7 +716,8 @@
* While a write will already be ordering the data, a truncate will not.
* Thus, we need to explicitly order the zeroed pages.
*/
-static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode)
+static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode,
+ struct buffer_head *di_bh)
{
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
handle_t *handle = NULL;
@@ -735,7 +734,14 @@
}
ret = ocfs2_jbd2_file_inode(handle, inode);
- if (ret < 0)
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (ret)
mlog_errno(ret);
out:
@@ -751,7 +757,7 @@
* to be too fragile to do exactly what we need without us having to
* worry about recursive locking in ->write_begin() and ->write_end(). */
static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
- u64 abs_to)
+ u64 abs_to, struct buffer_head *di_bh)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
@@ -759,6 +765,7 @@
handle_t *handle = NULL;
int ret = 0;
unsigned zero_from, zero_to, block_start, block_end;
+ struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
BUG_ON(abs_from >= abs_to);
BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT));
@@ -801,7 +808,8 @@
}
if (!handle) {
- handle = ocfs2_zero_start_ordered_transaction(inode);
+ handle = ocfs2_zero_start_ordered_transaction(inode,
+ di_bh);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
handle = NULL;
@@ -818,8 +826,22 @@
ret = 0;
}
- if (handle)
+ if (handle) {
+ /*
+ * fs-writeback will release the dirty pages without page lock
+ * whose offset are over inode size, the release happens at
+ * block_write_full_page_endio().
+ */
+ i_size_write(inode, abs_to);
+ inode->i_blocks = ocfs2_inode_sector_count(inode);
+ di->i_size = cpu_to_le64((u64)i_size_read(inode));
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+ di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+ di->i_mtime_nsec = di->i_ctime_nsec;
+ ocfs2_journal_dirty(handle, di_bh);
ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+ }
out_unlock:
unlock_page(page);
@@ -915,7 +937,7 @@
* has made sure that the entire range needs zeroing.
*/
static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start,
- u64 range_end)
+ u64 range_end, struct buffer_head *di_bh)
{
int rc = 0;
u64 next_pos;
@@ -931,7 +953,7 @@
next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE;
if (next_pos > range_end)
next_pos = range_end;
- rc = ocfs2_write_zero_page(inode, zero_pos, next_pos);
+ rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh);
if (rc < 0) {
mlog_errno(rc);
break;
@@ -977,7 +999,7 @@
range_end = zero_to_size;
ret = ocfs2_zero_extend_range(inode, range_start,
- range_end);
+ range_end, di_bh);
if (ret) {
mlog_errno(ret);
break;
@@ -1145,14 +1167,14 @@
goto bail_unlock_rw;
}
- if (size_change && attr->ia_size != i_size_read(inode)) {
+ if (size_change) {
status = inode_newsize_ok(inode, attr->ia_size);
if (status)
goto bail_unlock;
inode_dio_wait(inode);
- if (i_size_read(inode) > attr->ia_size) {
+ if (i_size_read(inode) >= attr->ia_size) {
if (ocfs2_should_order_data(inode)) {
status = ocfs2_begin_ordered_truncate(inode,
attr->ia_size);
@@ -2371,8 +2393,8 @@
if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) ||
((file->f_flags & O_DIRECT) && !direct_io)) {
- ret = filemap_fdatawrite_range(file->f_mapping, pos,
- pos + count - 1);
+ ret = filemap_fdatawrite_range(file->f_mapping, *ppos,
+ *ppos + count - 1);
if (ret < 0)
written = ret;
@@ -2385,8 +2407,8 @@
}
if (!ret)
- ret = filemap_fdatawait_range(file->f_mapping, pos,
- pos + count - 1);
+ ret = filemap_fdatawait_range(file->f_mapping, *ppos,
+ *ppos + count - 1);
}
/*
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index f4d609b..3683643 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -664,6 +664,7 @@
struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
struct ocfs2_dir_lookup_result lookup = { NULL, };
sigset_t oldset;
+ u64 old_de_ino;
trace_ocfs2_link((unsigned long long)OCFS2_I(inode)->ip_blkno,
old_dentry->d_name.len, old_dentry->d_name.name,
@@ -686,6 +687,22 @@
goto out;
}
+ err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name,
+ old_dentry->d_name.len, &old_de_ino);
+ if (err) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ /*
+ * Check whether another node removed the source inode while we
+ * were in the vfs.
+ */
+ if (old_de_ino != OCFS2_I(inode)->ip_blkno) {
+ err = -ENOENT;
+ goto out;
+ }
+
err = ocfs2_check_dir_for_entry(dir, dentry->d_name.name,
dentry->d_name.len);
if (err)
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index aaa5061..d7b5108 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -717,6 +717,12 @@
*/
if (status < 0)
mlog_errno(status);
+ /*
+ * Clear dq_off so that we search for the structure in quota file next
+ * time we acquire it. The structure might be deleted and reallocated
+ * elsewhere by another node while our dquot structure is on freelist.
+ */
+ dquot->dq_off = 0;
clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
out_trans:
ocfs2_commit_trans(osb, handle);
@@ -756,16 +762,17 @@
status = ocfs2_lock_global_qf(info, 1);
if (status < 0)
goto out;
- if (!test_bit(DQ_READ_B, &dquot->dq_flags)) {
- status = ocfs2_qinfo_lock(info, 0);
- if (status < 0)
- goto out_dq;
- status = qtree_read_dquot(&info->dqi_gi, dquot);
- ocfs2_qinfo_unlock(info, 0);
- if (status < 0)
- goto out_dq;
- }
- set_bit(DQ_READ_B, &dquot->dq_flags);
+ status = ocfs2_qinfo_lock(info, 0);
+ if (status < 0)
+ goto out_dq;
+ /*
+ * We always want to read dquot structure from disk because we don't
+ * know what happened with it while it was on freelist.
+ */
+ status = qtree_read_dquot(&info->dqi_gi, dquot);
+ ocfs2_qinfo_unlock(info, 0);
+ if (status < 0)
+ goto out_dq;
OCFS2_DQUOT(dquot)->dq_use_count++;
OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2e4344b..2001862 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -1303,10 +1303,6 @@
ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh);
out:
- /* Clear the read bit so that next time someone uses this
- * dquot he reads fresh info from disk and allocates local
- * dquot structure */
- clear_bit(DQ_READ_B, &dquot->dq_flags);
return status;
}
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 1324e66..ca5ce14 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -346,7 +346,9 @@
strlcpy(new_conn->cc_name, group, GROUP_NAME_MAX + 1);
new_conn->cc_namelen = grouplen;
- strlcpy(new_conn->cc_cluster_name, cluster_name, CLUSTER_NAME_MAX + 1);
+ if (cluster_name_len)
+ strlcpy(new_conn->cc_cluster_name, cluster_name,
+ CLUSTER_NAME_MAX + 1);
new_conn->cc_cluster_name_len = cluster_name_len;
new_conn->cc_recovery_handler = recovery_handler;
new_conn->cc_recovery_data = recovery_data;
diff --git a/fs/open.c b/fs/open.c
index 4b3e1ed..b9ed8b2 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -705,6 +705,10 @@
return 0;
}
+ /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
+ if (S_ISREG(inode->i_mode))
+ f->f_mode |= FMODE_ATOMIC_POS;
+
f->f_op = fops_get(inode->i_fop);
if (unlikely(WARN_ON(!f->f_op))) {
error = -ENODEV;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 5150706..b976062 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1824,6 +1824,7 @@
if (rc)
goto out_mmput;
+ rc = -ENOENT;
down_read(&mm->mmap_sem);
vma = find_exact_vma(mm, vm_start, vm_end);
if (vma && vma->vm_file) {
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 02174a6..e647c55 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -121,9 +121,8 @@
* just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
* to make sure a given page is a thp, not a non-huge compound page.
*/
- else if (PageTransCompound(page) &&
- (PageLRU(compound_trans_head(page)) ||
- PageAnon(compound_trans_head(page))))
+ else if (PageTransCompound(page) && (PageLRU(compound_head(page)) ||
+ PageAnon(compound_head(page))))
u |= 1 << KPF_THP;
/*
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 2ca7ba0..88d4585 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -468,17 +468,24 @@
return rc;
}
nhdr_ptr = notes_section;
- while (real_sz < max_sz) {
- if (nhdr_ptr->n_namesz == 0)
- break;
+ while (nhdr_ptr->n_namesz != 0) {
sz = sizeof(Elf64_Nhdr) +
((nhdr_ptr->n_namesz + 3) & ~3) +
((nhdr_ptr->n_descsz + 3) & ~3);
+ if ((real_sz + sz) > max_sz) {
+ pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
+ nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
+ break;
+ }
real_sz += sz;
nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz);
}
kfree(notes_section);
phdr_ptr->p_memsz = real_sz;
+ if (real_sz == 0) {
+ pr_warn("Warning: Zero PT_NOTE entries found\n");
+ return -EINVAL;
+ }
}
return 0;
@@ -648,17 +655,24 @@
return rc;
}
nhdr_ptr = notes_section;
- while (real_sz < max_sz) {
- if (nhdr_ptr->n_namesz == 0)
- break;
+ while (nhdr_ptr->n_namesz != 0) {
sz = sizeof(Elf32_Nhdr) +
((nhdr_ptr->n_namesz + 3) & ~3) +
((nhdr_ptr->n_descsz + 3) & ~3);
+ if ((real_sz + sz) > max_sz) {
+ pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
+ nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
+ break;
+ }
real_sz += sz;
nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz);
}
kfree(notes_section);
phdr_ptr->p_memsz = real_sz;
+ if (real_sz == 0) {
+ pr_warn("Warning: Zero PT_NOTE entries found\n");
+ return -EINVAL;
+ }
}
return 0;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 831d49a..cfc8dcc 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -581,9 +581,17 @@
dqstats_inc(DQST_LOOKUPS);
dqput(old_dquot);
old_dquot = dquot;
- ret = fn(dquot, priv);
- if (ret < 0)
- goto out;
+ /*
+ * ->release_dquot() can be racing with us. Our reference
+ * protects us from new calls to it so just wait for any
+ * outstanding call and recheck the DQ_ACTIVE_B after that.
+ */
+ wait_on_dquot(dquot);
+ if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+ ret = fn(dquot, priv);
+ if (ret < 0)
+ goto out;
+ }
spin_lock(&dq_list_lock);
/* We are safe to continue now because our dquot could not
* be moved out of the inuse list while we hold the reference */
diff --git a/fs/read_write.c b/fs/read_write.c
index edc5746..28cc9c8 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -264,10 +264,22 @@
}
EXPORT_SYMBOL(vfs_llseek);
+static inline struct fd fdget_pos(int fd)
+{
+ return __to_fd(__fdget_pos(fd));
+}
+
+static inline void fdput_pos(struct fd f)
+{
+ if (f.flags & FDPUT_POS_UNLOCK)
+ mutex_unlock(&f.file->f_pos_lock);
+ fdput(f);
+}
+
SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
{
off_t retval;
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
if (!f.file)
return -EBADF;
@@ -278,7 +290,7 @@
if (res != (loff_t)retval)
retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */
}
- fdput(f);
+ fdput_pos(f);
return retval;
}
@@ -295,7 +307,7 @@
unsigned int, whence)
{
int retval;
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
loff_t offset;
if (!f.file)
@@ -315,7 +327,7 @@
retval = 0;
}
out_putf:
- fdput(f);
+ fdput_pos(f);
return retval;
}
#endif
@@ -498,7 +510,7 @@
SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
@@ -506,7 +518,7 @@
ret = vfs_read(f.file, buf, count, &pos);
if (ret >= 0)
file_pos_write(f.file, pos);
- fdput(f);
+ fdput_pos(f);
}
return ret;
}
@@ -514,7 +526,7 @@
SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
size_t, count)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
@@ -522,7 +534,7 @@
ret = vfs_write(f.file, buf, count, &pos);
if (ret >= 0)
file_pos_write(f.file, pos);
- fdput(f);
+ fdput_pos(f);
}
return ret;
@@ -797,7 +809,7 @@
SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
@@ -805,7 +817,7 @@
ret = vfs_readv(f.file, vec, vlen, &pos);
if (ret >= 0)
file_pos_write(f.file, pos);
- fdput(f);
+ fdput_pos(f);
}
if (ret > 0)
@@ -817,7 +829,7 @@
SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
@@ -825,7 +837,7 @@
ret = vfs_writev(f.file, vec, vlen, &pos);
if (ret >= 0)
file_pos_write(f.file, pos);
- fdput(f);
+ fdput_pos(f);
}
if (ret > 0)
@@ -968,7 +980,7 @@
const struct compat_iovec __user *,vec,
compat_ulong_t, vlen)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret;
loff_t pos;
@@ -978,7 +990,7 @@
ret = compat_readv(f.file, vec, vlen, &pos);
if (ret >= 0)
f.file->f_pos = pos;
- fdput(f);
+ fdput_pos(f);
return ret;
}
@@ -1035,7 +1047,7 @@
const struct compat_iovec __user *, vec,
compat_ulong_t, vlen)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret;
loff_t pos;
@@ -1045,7 +1057,7 @@
ret = compat_writev(f.file, vec, vlen, &pos);
if (ret >= 0)
f.file->f_pos = pos;
- fdput(f);
+ fdput_pos(f);
return ret;
}
diff --git a/fs/reiserfs/do_balan.c b/fs/reiserfs/do_balan.c
index 2b7882b..9a3c68c 100644
--- a/fs/reiserfs/do_balan.c
+++ b/fs/reiserfs/do_balan.c
@@ -324,23 +324,17 @@
switch (flag) {
case M_INSERT: /* insert item into L[0] */
- if (item_pos == tb->lnum[0] - 1
- && tb->lbytes != -1) {
+ if (item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) {
/* part of new item falls into L[0] */
int new_item_len;
int version;
- ret_val =
- leaf_shift_left(tb, tb->lnum[0] - 1,
- -1);
+ ret_val = leaf_shift_left(tb, tb->lnum[0] - 1, -1);
/* Calculate item length to insert to S[0] */
- new_item_len =
- ih_item_len(ih) - tb->lbytes;
+ new_item_len = ih_item_len(ih) - tb->lbytes;
/* Calculate and check item length to insert to L[0] */
- put_ih_item_len(ih,
- ih_item_len(ih) -
- new_item_len);
+ put_ih_item_len(ih, ih_item_len(ih) - new_item_len);
RFALSE(ih_item_len(ih) <= 0,
"PAP-12080: there is nothing to insert into L[0]: ih_item_len=%d",
@@ -349,30 +343,18 @@
/* Insert new item into L[0] */
buffer_info_init_left(tb, &bi);
leaf_insert_into_buf(&bi,
- n + item_pos -
- ret_val, ih, body,
- zeros_num >
- ih_item_len(ih) ?
- ih_item_len(ih) :
- zeros_num);
+ n + item_pos - ret_val, ih, body,
+ zeros_num > ih_item_len(ih) ? ih_item_len(ih) : zeros_num);
version = ih_version(ih);
/* Calculate key component, item length and body to insert into S[0] */
- set_le_ih_k_offset(ih,
- le_ih_k_offset(ih) +
- (tb->
- lbytes <<
- (is_indirect_le_ih
- (ih) ? tb->tb_sb->
- s_blocksize_bits -
- UNFM_P_SHIFT :
- 0)));
+ set_le_ih_k_offset(ih, le_ih_k_offset(ih) +
+ (tb-> lbytes << (is_indirect_le_ih(ih) ? tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT : 0)));
put_ih_item_len(ih, new_item_len);
if (tb->lbytes > zeros_num) {
- body +=
- (tb->lbytes - zeros_num);
+ body += (tb->lbytes - zeros_num);
zeros_num = 0;
} else
zeros_num -= tb->lbytes;
@@ -383,15 +365,10 @@
} else {
/* new item in whole falls into L[0] */
/* Shift lnum[0]-1 items to L[0] */
- ret_val =
- leaf_shift_left(tb, tb->lnum[0] - 1,
- tb->lbytes);
+ ret_val = leaf_shift_left(tb, tb->lnum[0] - 1, tb->lbytes);
/* Insert new item into L[0] */
buffer_info_init_left(tb, &bi);
- leaf_insert_into_buf(&bi,
- n + item_pos -
- ret_val, ih, body,
- zeros_num);
+ leaf_insert_into_buf(&bi, n + item_pos - ret_val, ih, body, zeros_num);
tb->insert_size[0] = 0;
zeros_num = 0;
}
@@ -399,264 +376,117 @@
case M_PASTE: /* append item in L[0] */
- if (item_pos == tb->lnum[0] - 1
- && tb->lbytes != -1) {
+ if (item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) {
/* we must shift the part of the appended item */
- if (is_direntry_le_ih
- (B_N_PITEM_HEAD(tbS0, item_pos))) {
+ if (is_direntry_le_ih(B_N_PITEM_HEAD(tbS0, item_pos))) {
RFALSE(zeros_num,
"PAP-12090: invalid parameter in case of a directory");
/* directory item */
if (tb->lbytes > pos_in_item) {
/* new directory entry falls into L[0] */
- struct item_head
- *pasted;
- int l_pos_in_item =
- pos_in_item;
+ struct item_head *pasted;
+ int l_pos_in_item = pos_in_item;
/* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 entries from given directory item */
- ret_val =
- leaf_shift_left(tb,
- tb->
- lnum
- [0],
- tb->
- lbytes
- -
- 1);
- if (ret_val
- && !item_pos) {
- pasted =
- B_N_PITEM_HEAD
- (tb->L[0],
- B_NR_ITEMS
- (tb->
- L[0]) -
- 1);
- l_pos_in_item +=
- I_ENTRY_COUNT
- (pasted) -
- (tb->
- lbytes -
- 1);
+ ret_val = leaf_shift_left(tb, tb->lnum[0], tb->lbytes-1);
+ if (ret_val && !item_pos) {
+ pasted = B_N_PITEM_HEAD(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1);
+ l_pos_in_item += I_ENTRY_COUNT(pasted) - (tb->lbytes -1);
}
/* Append given directory entry to directory item */
buffer_info_init_left(tb, &bi);
- leaf_paste_in_buffer
- (&bi,
- n + item_pos -
- ret_val,
- l_pos_in_item,
- tb->insert_size[0],
- body, zeros_num);
+ leaf_paste_in_buffer(&bi, n + item_pos - ret_val, l_pos_in_item, tb->insert_size[0], body, zeros_num);
/* previous string prepared space for pasting new entry, following string pastes this entry */
/* when we have merge directory item, pos_in_item has been changed too */
/* paste new directory entry. 1 is entry number */
- leaf_paste_entries(&bi,
- n +
- item_pos
- -
- ret_val,
- l_pos_in_item,
- 1,
- (struct
- reiserfs_de_head
- *)
- body,
- body
- +
- DEH_SIZE,
- tb->
- insert_size
- [0]
- );
+ leaf_paste_entries(&bi, n + item_pos - ret_val, l_pos_in_item,
+ 1, (struct reiserfs_de_head *) body,
+ body + DEH_SIZE, tb->insert_size[0]);
tb->insert_size[0] = 0;
} else {
/* new directory item doesn't fall into L[0] */
/* Shift lnum[0]-1 items in whole. Shift lbytes directory entries from directory item number lnum[0] */
- leaf_shift_left(tb,
- tb->
- lnum[0],
- tb->
- lbytes);
+ leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
}
/* Calculate new position to append in item body */
pos_in_item -= tb->lbytes;
} else {
/* regular object */
- RFALSE(tb->lbytes <= 0,
- "PAP-12095: there is nothing to shift to L[0]. lbytes=%d",
- tb->lbytes);
- RFALSE(pos_in_item !=
- ih_item_len
- (B_N_PITEM_HEAD
- (tbS0, item_pos)),
+ RFALSE(tb->lbytes <= 0, "PAP-12095: there is nothing to shift to L[0]. lbytes=%d", tb->lbytes);
+ RFALSE(pos_in_item != ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)),
"PAP-12100: incorrect position to paste: item_len=%d, pos_in_item=%d",
- ih_item_len
- (B_N_PITEM_HEAD
- (tbS0, item_pos)),
- pos_in_item);
+ ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)),pos_in_item);
if (tb->lbytes >= pos_in_item) {
/* appended item will be in L[0] in whole */
int l_n;
/* this bytes number must be appended to the last item of L[h] */
- l_n =
- tb->lbytes -
- pos_in_item;
+ l_n = tb->lbytes - pos_in_item;
/* Calculate new insert_size[0] */
- tb->insert_size[0] -=
- l_n;
+ tb->insert_size[0] -= l_n;
- RFALSE(tb->
- insert_size[0] <=
- 0,
+ RFALSE(tb->insert_size[0] <= 0,
"PAP-12105: there is nothing to paste into L[0]. insert_size=%d",
- tb->
- insert_size[0]);
- ret_val =
- leaf_shift_left(tb,
- tb->
- lnum
- [0],
- ih_item_len
- (B_N_PITEM_HEAD
- (tbS0,
- item_pos)));
+ tb->insert_size[0]);
+ ret_val = leaf_shift_left(tb, tb->lnum[0], ih_item_len
+ (B_N_PITEM_HEAD(tbS0, item_pos)));
/* Append to body of item in L[0] */
buffer_info_init_left(tb, &bi);
leaf_paste_in_buffer
- (&bi,
- n + item_pos -
- ret_val,
- ih_item_len
- (B_N_PITEM_HEAD
- (tb->L[0],
- n + item_pos -
- ret_val)), l_n,
- body,
- zeros_num >
- l_n ? l_n :
- zeros_num);
+ (&bi, n + item_pos - ret_val, ih_item_len
+ (B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val)),
+ l_n, body,
+ zeros_num > l_n ? l_n : zeros_num);
/* 0-th item in S0 can be only of DIRECT type when l_n != 0 */
{
int version;
- int temp_l =
- l_n;
+ int temp_l = l_n;
- RFALSE
- (ih_item_len
- (B_N_PITEM_HEAD
- (tbS0,
- 0)),
+ RFALSE(ih_item_len(B_N_PITEM_HEAD(tbS0, 0)),
"PAP-12106: item length must be 0");
- RFALSE
- (comp_short_le_keys
- (B_N_PKEY
- (tbS0, 0),
- B_N_PKEY
- (tb->L[0],
- n +
- item_pos
- -
- ret_val)),
+ RFALSE(comp_short_le_keys(B_N_PKEY(tbS0, 0), B_N_PKEY
+ (tb->L[0], n + item_pos - ret_val)),
"PAP-12107: items must be of the same file");
if (is_indirect_le_ih(B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val))) {
- temp_l =
- l_n
- <<
- (tb->
- tb_sb->
- s_blocksize_bits
- -
- UNFM_P_SHIFT);
+ temp_l = l_n << (tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT);
}
/* update key of first item in S0 */
- version =
- ih_version
- (B_N_PITEM_HEAD
- (tbS0, 0));
- set_le_key_k_offset
- (version,
- B_N_PKEY
- (tbS0, 0),
- le_key_k_offset
- (version,
- B_N_PKEY
- (tbS0,
- 0)) +
- temp_l);
+ version = ih_version(B_N_PITEM_HEAD(tbS0, 0));
+ set_le_key_k_offset(version, B_N_PKEY(tbS0, 0),
+ le_key_k_offset(version,B_N_PKEY(tbS0, 0)) + temp_l);
/* update left delimiting key */
- set_le_key_k_offset
- (version,
- B_N_PDELIM_KEY
- (tb->
- CFL[0],
- tb->
- lkey[0]),
- le_key_k_offset
- (version,
- B_N_PDELIM_KEY
- (tb->
- CFL[0],
- tb->
- lkey[0]))
- + temp_l);
+ set_le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]),
+ le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0])) + temp_l);
}
/* Calculate new body, position in item and insert_size[0] */
if (l_n > zeros_num) {
- body +=
- (l_n -
- zeros_num);
+ body += (l_n - zeros_num);
zeros_num = 0;
} else
- zeros_num -=
- l_n;
+ zeros_num -= l_n;
pos_in_item = 0;
- RFALSE
- (comp_short_le_keys
- (B_N_PKEY(tbS0, 0),
- B_N_PKEY(tb->L[0],
- B_NR_ITEMS
- (tb->
- L[0]) -
- 1))
- ||
- !op_is_left_mergeable
- (B_N_PKEY(tbS0, 0),
- tbS0->b_size)
- ||
- !op_is_left_mergeable
- (B_N_PDELIM_KEY
- (tb->CFL[0],
- tb->lkey[0]),
- tbS0->b_size),
+ RFALSE(comp_short_le_keys(B_N_PKEY(tbS0, 0), B_N_PKEY(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1))
+ || !op_is_left_mergeable(B_N_PKEY(tbS0, 0), tbS0->b_size)
+ || !op_is_left_mergeable(B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]), tbS0->b_size),
"PAP-12120: item must be merge-able with left neighboring item");
} else { /* only part of the appended item will be in L[0] */
/* Calculate position in item for append in S[0] */
- pos_in_item -=
- tb->lbytes;
+ pos_in_item -= tb->lbytes;
- RFALSE(pos_in_item <= 0,
- "PAP-12125: no place for paste. pos_in_item=%d",
- pos_in_item);
+ RFALSE(pos_in_item <= 0, "PAP-12125: no place for paste. pos_in_item=%d", pos_in_item);
/* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 byte from item number lnum[0] */
- leaf_shift_left(tb,
- tb->
- lnum[0],
- tb->
- lbytes);
+ leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
}
}
} else { /* appended item will be in L[0] in whole */
@@ -665,52 +495,30 @@
if (!item_pos && op_is_left_mergeable(B_N_PKEY(tbS0, 0), tbS0->b_size)) { /* if we paste into first item of S[0] and it is left mergable */
/* then increment pos_in_item by the size of the last item in L[0] */
- pasted =
- B_N_PITEM_HEAD(tb->L[0],
- n - 1);
+ pasted = B_N_PITEM_HEAD(tb->L[0], n - 1);
if (is_direntry_le_ih(pasted))
- pos_in_item +=
- ih_entry_count
- (pasted);
+ pos_in_item += ih_entry_count(pasted);
else
- pos_in_item +=
- ih_item_len(pasted);
+ pos_in_item += ih_item_len(pasted);
}
/* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 byte from item number lnum[0] */
- ret_val =
- leaf_shift_left(tb, tb->lnum[0],
- tb->lbytes);
+ ret_val = leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
/* Append to body of item in L[0] */
buffer_info_init_left(tb, &bi);
- leaf_paste_in_buffer(&bi,
- n + item_pos -
- ret_val,
+ leaf_paste_in_buffer(&bi, n + item_pos - ret_val,
pos_in_item,
tb->insert_size[0],
body, zeros_num);
/* if appended item is directory, paste entry */
- pasted =
- B_N_PITEM_HEAD(tb->L[0],
- n + item_pos -
- ret_val);
+ pasted = B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val);
if (is_direntry_le_ih(pasted))
- leaf_paste_entries(&bi,
- n +
- item_pos -
- ret_val,
- pos_in_item,
- 1,
- (struct
- reiserfs_de_head
- *)body,
- body +
- DEH_SIZE,
- tb->
- insert_size
- [0]
- );
+ leaf_paste_entries(&bi, n + item_pos - ret_val,
+ pos_in_item, 1,
+ (struct reiserfs_de_head *) body,
+ body + DEH_SIZE,
+ tb->insert_size[0]);
/* if appended item is indirect item, put unformatted node into un list */
if (is_indirect_le_ih(pasted))
set_ih_free_space(pasted, 0);
@@ -722,13 +530,7 @@
reiserfs_panic(tb->tb_sb, "PAP-12130",
"lnum > 0: unexpected mode: "
" %s(%d)",
- (flag ==
- M_DELETE) ? "DELETE" : ((flag ==
- M_CUT)
- ? "CUT"
- :
- "UNKNOWN"),
- flag);
+ (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag);
}
} else {
/* new item doesn't fall into L[0] */
@@ -748,14 +550,12 @@
case M_INSERT: /* insert item */
if (n - tb->rnum[0] < item_pos) { /* new item or its part falls to R[0] */
if (item_pos == n - tb->rnum[0] + 1 && tb->rbytes != -1) { /* part of new item falls into R[0] */
- loff_t old_key_comp, old_len,
- r_zeros_number;
+ loff_t old_key_comp, old_len, r_zeros_number;
const char *r_body;
int version;
loff_t offset;
- leaf_shift_right(tb, tb->rnum[0] - 1,
- -1);
+ leaf_shift_right(tb, tb->rnum[0] - 1, -1);
version = ih_version(ih);
/* Remember key component and item length */
@@ -763,29 +563,17 @@
old_len = ih_item_len(ih);
/* Calculate key component and item length to insert into R[0] */
- offset =
- le_ih_k_offset(ih) +
- ((old_len -
- tb->
- rbytes) << (is_indirect_le_ih(ih)
- ? tb->tb_sb->
- s_blocksize_bits -
- UNFM_P_SHIFT : 0));
+ offset = le_ih_k_offset(ih) + ((old_len - tb->rbytes) << (is_indirect_le_ih(ih) ? tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT : 0));
set_le_ih_k_offset(ih, offset);
put_ih_item_len(ih, tb->rbytes);
/* Insert part of the item into R[0] */
buffer_info_init_right(tb, &bi);
if ((old_len - tb->rbytes) > zeros_num) {
r_zeros_number = 0;
- r_body =
- body + (old_len -
- tb->rbytes) -
- zeros_num;
+ r_body = body + (old_len - tb->rbytes) - zeros_num;
} else {
r_body = body;
- r_zeros_number =
- zeros_num - (old_len -
- tb->rbytes);
+ r_zeros_number = zeros_num - (old_len - tb->rbytes);
zeros_num -= r_zeros_number;
}
@@ -798,25 +586,18 @@
/* Calculate key component and item length to insert into S[0] */
set_le_ih_k_offset(ih, old_key_comp);
- put_ih_item_len(ih,
- old_len - tb->rbytes);
+ put_ih_item_len(ih, old_len - tb->rbytes);
tb->insert_size[0] -= tb->rbytes;
} else { /* whole new item falls into R[0] */
/* Shift rnum[0]-1 items to R[0] */
- ret_val =
- leaf_shift_right(tb,
- tb->rnum[0] - 1,
- tb->rbytes);
+ ret_val = leaf_shift_right(tb, tb->rnum[0] - 1, tb->rbytes);
/* Insert new item into R[0] */
buffer_info_init_right(tb, &bi);
- leaf_insert_into_buf(&bi,
- item_pos - n +
- tb->rnum[0] - 1,
- ih, body,
- zeros_num);
+ leaf_insert_into_buf(&bi, item_pos - n + tb->rnum[0] - 1,
+ ih, body, zeros_num);
if (item_pos - n + tb->rnum[0] - 1 == 0) {
replace_key(tb, tb->CFR[0],
@@ -841,200 +622,97 @@
RFALSE(zeros_num,
"PAP-12145: invalid parameter in case of a directory");
- entry_count =
- I_ENTRY_COUNT(B_N_PITEM_HEAD
- (tbS0,
- item_pos));
+ entry_count = I_ENTRY_COUNT(B_N_PITEM_HEAD
+ (tbS0, item_pos));
if (entry_count - tb->rbytes <
pos_in_item)
/* new directory entry falls into R[0] */
{
int paste_entry_position;
- RFALSE(tb->rbytes - 1 >=
- entry_count
- || !tb->
- insert_size[0],
+ RFALSE(tb->rbytes - 1 >= entry_count || !tb-> insert_size[0],
"PAP-12150: no enough of entries to shift to R[0]: rbytes=%d, entry_count=%d",
- tb->rbytes,
- entry_count);
+ tb->rbytes, entry_count);
/* Shift rnum[0]-1 items in whole. Shift rbytes-1 directory entries from directory item number rnum[0] */
- leaf_shift_right(tb,
- tb->
- rnum
- [0],
- tb->
- rbytes
- - 1);
+ leaf_shift_right(tb, tb->rnum[0], tb->rbytes - 1);
/* Paste given directory entry to directory item */
- paste_entry_position =
- pos_in_item -
- entry_count +
- tb->rbytes - 1;
+ paste_entry_position = pos_in_item - entry_count + tb->rbytes - 1;
buffer_info_init_right(tb, &bi);
- leaf_paste_in_buffer
- (&bi, 0,
- paste_entry_position,
- tb->insert_size[0],
- body, zeros_num);
+ leaf_paste_in_buffer(&bi, 0, paste_entry_position, tb->insert_size[0], body, zeros_num);
/* paste entry */
- leaf_paste_entries(&bi,
- 0,
- paste_entry_position,
- 1,
- (struct
- reiserfs_de_head
- *)
- body,
- body
- +
- DEH_SIZE,
- tb->
- insert_size
- [0]
- );
+ leaf_paste_entries(&bi, 0, paste_entry_position, 1,
+ (struct reiserfs_de_head *) body,
+ body + DEH_SIZE, tb->insert_size[0]);
- if (paste_entry_position
- == 0) {
+ if (paste_entry_position == 0) {
/* change delimiting keys */
- replace_key(tb,
- tb->
- CFR
- [0],
- tb->
- rkey
- [0],
- tb->
- R
- [0],
- 0);
+ replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0],0);
}
tb->insert_size[0] = 0;
pos_in_item++;
} else { /* new directory entry doesn't fall into R[0] */
- leaf_shift_right(tb,
- tb->
- rnum
- [0],
- tb->
- rbytes);
+ leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
}
} else { /* regular object */
- int n_shift, n_rem,
- r_zeros_number;
+ int n_shift, n_rem, r_zeros_number;
const char *r_body;
/* Calculate number of bytes which must be shifted from appended item */
- if ((n_shift =
- tb->rbytes -
- tb->insert_size[0]) < 0)
+ if ((n_shift = tb->rbytes - tb->insert_size[0]) < 0)
n_shift = 0;
- RFALSE(pos_in_item !=
- ih_item_len
- (B_N_PITEM_HEAD
- (tbS0, item_pos)),
+ RFALSE(pos_in_item != ih_item_len
+ (B_N_PITEM_HEAD(tbS0, item_pos)),
"PAP-12155: invalid position to paste. ih_item_len=%d, pos_in_item=%d",
- pos_in_item,
- ih_item_len
- (B_N_PITEM_HEAD
- (tbS0, item_pos)));
+ pos_in_item, ih_item_len
+ (B_N_PITEM_HEAD(tbS0, item_pos)));
- leaf_shift_right(tb,
- tb->rnum[0],
- n_shift);
+ leaf_shift_right(tb, tb->rnum[0], n_shift);
/* Calculate number of bytes which must remain in body after appending to R[0] */
- if ((n_rem =
- tb->insert_size[0] -
- tb->rbytes) < 0)
+ if ((n_rem = tb->insert_size[0] - tb->rbytes) < 0)
n_rem = 0;
{
int version;
- unsigned long temp_rem =
- n_rem;
+ unsigned long temp_rem = n_rem;
- version =
- ih_version
- (B_N_PITEM_HEAD
- (tb->R[0], 0));
- if (is_indirect_le_key
- (version,
- B_N_PKEY(tb->R[0],
- 0))) {
- temp_rem =
- n_rem <<
- (tb->tb_sb->
- s_blocksize_bits
- -
- UNFM_P_SHIFT);
+ version = ih_version(B_N_PITEM_HEAD(tb->R[0], 0));
+ if (is_indirect_le_key(version, B_N_PKEY(tb->R[0], 0))) {
+ temp_rem = n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT);
}
- set_le_key_k_offset
- (version,
- B_N_PKEY(tb->R[0],
- 0),
- le_key_k_offset
- (version,
- B_N_PKEY(tb->R[0],
- 0)) +
- temp_rem);
- set_le_key_k_offset
- (version,
- B_N_PDELIM_KEY(tb->
- CFR
- [0],
- tb->
- rkey
- [0]),
- le_key_k_offset
- (version,
- B_N_PDELIM_KEY
- (tb->CFR[0],
- tb->rkey[0])) +
- temp_rem);
+ set_le_key_k_offset(version, B_N_PKEY(tb->R[0], 0),
+ le_key_k_offset(version, B_N_PKEY(tb->R[0], 0)) + temp_rem);
+ set_le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0]),
+ le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0])) + temp_rem);
}
/* k_offset (B_N_PKEY(tb->R[0],0)) += n_rem;
k_offset (B_N_PDELIM_KEY(tb->CFR[0],tb->rkey[0])) += n_rem;*/
- do_balance_mark_internal_dirty
- (tb, tb->CFR[0], 0);
+ do_balance_mark_internal_dirty(tb, tb->CFR[0], 0);
/* Append part of body into R[0] */
buffer_info_init_right(tb, &bi);
if (n_rem > zeros_num) {
r_zeros_number = 0;
- r_body =
- body + n_rem -
- zeros_num;
+ r_body = body + n_rem - zeros_num;
} else {
r_body = body;
- r_zeros_number =
- zeros_num - n_rem;
- zeros_num -=
- r_zeros_number;
+ r_zeros_number = zeros_num - n_rem;
+ zeros_num -= r_zeros_number;
}
- leaf_paste_in_buffer(&bi, 0,
- n_shift,
- tb->
- insert_size
- [0] -
- n_rem,
- r_body,
- r_zeros_number);
+ leaf_paste_in_buffer(&bi, 0, n_shift,
+ tb->insert_size[0] - n_rem,
+ r_body, r_zeros_number);
- if (is_indirect_le_ih
- (B_N_PITEM_HEAD
- (tb->R[0], 0))) {
+ if (is_indirect_le_ih(B_N_PITEM_HEAD(tb->R[0], 0))) {
#if 0
RFALSE(n_rem,
"PAP-12160: paste more than one unformatted node pointer");
#endif
- set_ih_free_space
- (B_N_PITEM_HEAD
- (tb->R[0], 0), 0);
+ set_ih_free_space(B_N_PITEM_HEAD(tb->R[0], 0), 0);
}
tb->insert_size[0] = n_rem;
if (!n_rem)
@@ -1044,58 +722,28 @@
struct item_head *pasted;
- ret_val =
- leaf_shift_right(tb, tb->rnum[0],
- tb->rbytes);
+ ret_val = leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
/* append item in R[0] */
if (pos_in_item >= 0) {
buffer_info_init_right(tb, &bi);
- leaf_paste_in_buffer(&bi,
- item_pos -
- n +
- tb->
- rnum[0],
- pos_in_item,
- tb->
- insert_size
- [0], body,
- zeros_num);
+ leaf_paste_in_buffer(&bi, item_pos - n + tb->rnum[0], pos_in_item,
+ tb->insert_size[0], body, zeros_num);
}
/* paste new entry, if item is directory item */
- pasted =
- B_N_PITEM_HEAD(tb->R[0],
- item_pos - n +
- tb->rnum[0]);
- if (is_direntry_le_ih(pasted)
- && pos_in_item >= 0) {
- leaf_paste_entries(&bi,
- item_pos -
- n +
- tb->rnum[0],
- pos_in_item,
- 1,
- (struct
- reiserfs_de_head
- *)body,
- body +
- DEH_SIZE,
- tb->
- insert_size
- [0]
- );
+ pasted = B_N_PITEM_HEAD(tb->R[0], item_pos - n + tb->rnum[0]);
+ if (is_direntry_le_ih(pasted) && pos_in_item >= 0) {
+ leaf_paste_entries(&bi, item_pos - n + tb->rnum[0],
+ pos_in_item, 1,
+ (struct reiserfs_de_head *) body,
+ body + DEH_SIZE, tb->insert_size[0]);
if (!pos_in_item) {
- RFALSE(item_pos - n +
- tb->rnum[0],
+ RFALSE(item_pos - n + tb->rnum[0],
"PAP-12165: directory item must be first item of node when pasting is in 0th position");
/* update delimiting keys */
- replace_key(tb,
- tb->CFR[0],
- tb->rkey[0],
- tb->R[0],
- 0);
+ replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0], 0);
}
}
@@ -1111,22 +759,16 @@
default: /* cases d and t */
reiserfs_panic(tb->tb_sb, "PAP-12175",
"rnum > 0: unexpected mode: %s(%d)",
- (flag ==
- M_DELETE) ? "DELETE" : ((flag ==
- M_CUT) ? "CUT"
- : "UNKNOWN"),
- flag);
+ (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag);
}
}
/* tb->rnum[0] > 0 */
RFALSE(tb->blknum[0] > 3,
- "PAP-12180: blknum can not be %d. It must be <= 3",
- tb->blknum[0]);
+ "PAP-12180: blknum can not be %d. It must be <= 3", tb->blknum[0]);
RFALSE(tb->blknum[0] < 0,
- "PAP-12185: blknum can not be %d. It must be >= 0",
- tb->blknum[0]);
+ "PAP-12185: blknum can not be %d. It must be >= 0", tb->blknum[0]);
/* if while adding to a node we discover that it is possible to split
it in two, and merge the left part into the left neighbor and the
@@ -1177,8 +819,7 @@
if (n - snum[i] < item_pos) { /* new item or it's part falls to first new node S_new[i] */
if (item_pos == n - snum[i] + 1 && sbytes[i] != -1) { /* part of new item falls into S_new[i] */
- int old_key_comp, old_len,
- r_zeros_number;
+ int old_key_comp, old_len, r_zeros_number;
const char *r_body;
int version;
@@ -1192,15 +833,8 @@
old_len = ih_item_len(ih);
/* Calculate key component and item length to insert into S_new[i] */
- set_le_ih_k_offset(ih,
- le_ih_k_offset(ih) +
- ((old_len -
- sbytes[i]) <<
- (is_indirect_le_ih
- (ih) ? tb->tb_sb->
- s_blocksize_bits -
- UNFM_P_SHIFT :
- 0)));
+ set_le_ih_k_offset(ih, le_ih_k_offset(ih) +
+ ((old_len - sbytes[i]) << (is_indirect_le_ih(ih) ? tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT : 0)));
put_ih_item_len(ih, sbytes[i]);
@@ -1209,39 +843,29 @@
if ((old_len - sbytes[i]) > zeros_num) {
r_zeros_number = 0;
- r_body =
- body + (old_len -
- sbytes[i]) -
- zeros_num;
+ r_body = body + (old_len - sbytes[i]) - zeros_num;
} else {
r_body = body;
- r_zeros_number =
- zeros_num - (old_len -
- sbytes[i]);
+ r_zeros_number = zeros_num - (old_len - sbytes[i]);
zeros_num -= r_zeros_number;
}
- leaf_insert_into_buf(&bi, 0, ih, r_body,
- r_zeros_number);
+ leaf_insert_into_buf(&bi, 0, ih, r_body, r_zeros_number);
/* Calculate key component and item length to insert into S[i] */
set_le_ih_k_offset(ih, old_key_comp);
- put_ih_item_len(ih,
- old_len - sbytes[i]);
+ put_ih_item_len(ih, old_len - sbytes[i]);
tb->insert_size[0] -= sbytes[i];
} else { /* whole new item falls into S_new[i] */
/* Shift snum[0] - 1 items to S_new[i] (sbytes[i] of split item) */
leaf_move_items(LEAF_FROM_S_TO_SNEW, tb,
- snum[i] - 1, sbytes[i],
- S_new[i]);
+ snum[i] - 1, sbytes[i], S_new[i]);
/* Insert new item into S_new[i] */
buffer_info_init_bh(tb, &bi, S_new[i]);
- leaf_insert_into_buf(&bi,
- item_pos - n +
- snum[i] - 1, ih,
- body, zeros_num);
+ leaf_insert_into_buf(&bi, item_pos - n + snum[i] - 1,
+ ih, body, zeros_num);
zeros_num = tb->insert_size[0] = 0;
}
@@ -1268,150 +892,73 @@
int entry_count;
- entry_count =
- ih_entry_count(aux_ih);
+ entry_count = ih_entry_count(aux_ih);
- if (entry_count - sbytes[i] <
- pos_in_item
- && pos_in_item <=
- entry_count) {
+ if (entry_count - sbytes[i] < pos_in_item && pos_in_item <= entry_count) {
/* new directory entry falls into S_new[i] */
- RFALSE(!tb->
- insert_size[0],
- "PAP-12215: insert_size is already 0");
- RFALSE(sbytes[i] - 1 >=
- entry_count,
+ RFALSE(!tb->insert_size[0], "PAP-12215: insert_size is already 0");
+ RFALSE(sbytes[i] - 1 >= entry_count,
"PAP-12220: there are no so much entries (%d), only %d",
- sbytes[i] - 1,
- entry_count);
+ sbytes[i] - 1, entry_count);
/* Shift snum[i]-1 items in whole. Shift sbytes[i] directory entries from directory item number snum[i] */
- leaf_move_items
- (LEAF_FROM_S_TO_SNEW,
- tb, snum[i],
- sbytes[i] - 1,
- S_new[i]);
+ leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], sbytes[i] - 1, S_new[i]);
/* Paste given directory entry to directory item */
buffer_info_init_bh(tb, &bi, S_new[i]);
- leaf_paste_in_buffer
- (&bi, 0,
- pos_in_item -
- entry_count +
- sbytes[i] - 1,
- tb->insert_size[0],
- body, zeros_num);
+ leaf_paste_in_buffer(&bi, 0, pos_in_item - entry_count + sbytes[i] - 1,
+ tb->insert_size[0], body, zeros_num);
/* paste new directory entry */
- leaf_paste_entries(&bi,
- 0,
- pos_in_item
- -
- entry_count
- +
- sbytes
- [i] -
- 1, 1,
- (struct
- reiserfs_de_head
- *)
- body,
- body
- +
- DEH_SIZE,
- tb->
- insert_size
- [0]
- );
+ leaf_paste_entries(&bi, 0, pos_in_item - entry_count + sbytes[i] - 1, 1,
+ (struct reiserfs_de_head *) body,
+ body + DEH_SIZE, tb->insert_size[0]);
tb->insert_size[0] = 0;
pos_in_item++;
} else { /* new directory entry doesn't fall into S_new[i] */
- leaf_move_items
- (LEAF_FROM_S_TO_SNEW,
- tb, snum[i],
- sbytes[i],
- S_new[i]);
+ leaf_move_items(LEAF_FROM_S_TO_SNEW,tb, snum[i], sbytes[i], S_new[i]);
}
} else { /* regular object */
- int n_shift, n_rem,
- r_zeros_number;
+ int n_shift, n_rem, r_zeros_number;
const char *r_body;
- RFALSE(pos_in_item !=
- ih_item_len
- (B_N_PITEM_HEAD
- (tbS0, item_pos))
- || tb->insert_size[0] <=
- 0,
+ RFALSE(pos_in_item != ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)) || tb->insert_size[0] <= 0,
"PAP-12225: item too short or insert_size <= 0");
/* Calculate number of bytes which must be shifted from appended item */
- n_shift =
- sbytes[i] -
- tb->insert_size[0];
+ n_shift = sbytes[i] - tb->insert_size[0];
if (n_shift < 0)
n_shift = 0;
- leaf_move_items
- (LEAF_FROM_S_TO_SNEW, tb,
- snum[i], n_shift,
- S_new[i]);
+ leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], n_shift, S_new[i]);
/* Calculate number of bytes which must remain in body after append to S_new[i] */
- n_rem =
- tb->insert_size[0] -
- sbytes[i];
+ n_rem = tb->insert_size[0] - sbytes[i];
if (n_rem < 0)
n_rem = 0;
/* Append part of body into S_new[0] */
buffer_info_init_bh(tb, &bi, S_new[i]);
if (n_rem > zeros_num) {
r_zeros_number = 0;
- r_body =
- body + n_rem -
- zeros_num;
+ r_body = body + n_rem - zeros_num;
} else {
r_body = body;
- r_zeros_number =
- zeros_num - n_rem;
- zeros_num -=
- r_zeros_number;
+ r_zeros_number = zeros_num - n_rem;
+ zeros_num -= r_zeros_number;
}
- leaf_paste_in_buffer(&bi, 0,
- n_shift,
- tb->
- insert_size
- [0] -
- n_rem,
- r_body,
- r_zeros_number);
+ leaf_paste_in_buffer(&bi, 0, n_shift,
+ tb->insert_size[0] - n_rem,
+ r_body, r_zeros_number);
{
struct item_head *tmp;
- tmp =
- B_N_PITEM_HEAD(S_new
- [i],
- 0);
+ tmp = B_N_PITEM_HEAD(S_new[i], 0);
if (is_indirect_le_ih
(tmp)) {
- set_ih_free_space
- (tmp, 0);
- set_le_ih_k_offset
- (tmp,
- le_ih_k_offset
- (tmp) +
- (n_rem <<
- (tb->
- tb_sb->
- s_blocksize_bits
- -
- UNFM_P_SHIFT)));
+ set_ih_free_space(tmp, 0);
+ set_le_ih_k_offset(tmp, le_ih_k_offset(tmp) + (n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT)));
} else {
- set_le_ih_k_offset
- (tmp,
- le_ih_k_offset
- (tmp) +
- n_rem);
+ set_le_ih_k_offset(tmp, le_ih_k_offset(tmp) + n_rem);
}
}
@@ -1426,8 +973,7 @@
struct item_head *pasted;
#ifdef CONFIG_REISERFS_CHECK
- struct item_head *ih_check =
- B_N_PITEM_HEAD(tbS0, item_pos);
+ struct item_head *ih_check = B_N_PITEM_HEAD(tbS0, item_pos);
if (!is_direntry_le_ih(ih_check)
&& (pos_in_item != ih_item_len(ih_check)
@@ -1439,8 +985,7 @@
"to ih_item_len");
#endif /* CONFIG_REISERFS_CHECK */
- leaf_mi =
- leaf_move_items(LEAF_FROM_S_TO_SNEW,
+ leaf_mi = leaf_move_items(LEAF_FROM_S_TO_SNEW,
tb, snum[i],
sbytes[i],
S_new[i]);
@@ -1452,30 +997,19 @@
/* paste into item */
buffer_info_init_bh(tb, &bi, S_new[i]);
leaf_paste_in_buffer(&bi,
- item_pos - n +
- snum[i],
+ item_pos - n + snum[i],
pos_in_item,
tb->insert_size[0],
body, zeros_num);
- pasted =
- B_N_PITEM_HEAD(S_new[i],
- item_pos - n +
- snum[i]);
+ pasted = B_N_PITEM_HEAD(S_new[i], item_pos - n + snum[i]);
if (is_direntry_le_ih(pasted)) {
leaf_paste_entries(&bi,
- item_pos -
- n + snum[i],
- pos_in_item,
- 1,
- (struct
- reiserfs_de_head
- *)body,
- body +
- DEH_SIZE,
- tb->
- insert_size
- [0]
+ item_pos - n + snum[i],
+ pos_in_item, 1,
+ (struct reiserfs_de_head *)body,
+ body + DEH_SIZE,
+ tb->insert_size[0]
);
}
@@ -1495,11 +1029,7 @@
default: /* cases d and t */
reiserfs_panic(tb->tb_sb, "PAP-12245",
"blknum > 2: unexpected mode: %s(%d)",
- (flag ==
- M_DELETE) ? "DELETE" : ((flag ==
- M_CUT) ? "CUT"
- : "UNKNOWN"),
- flag);
+ (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag);
}
memcpy(insert_key + i, B_N_PKEY(S_new[i], 0), KEY_SIZE);
@@ -1524,9 +1054,7 @@
/* If we insert the first key change the delimiting key */
if (item_pos == 0) {
if (tb->CFL[0]) /* can be 0 in reiserfsck */
- replace_key(tb, tb->CFL[0], tb->lkey[0],
- tbS0, 0);
-
+ replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0);
}
break;
@@ -1536,53 +1064,27 @@
pasted = B_N_PITEM_HEAD(tbS0, item_pos);
/* when directory, may be new entry already pasted */
if (is_direntry_le_ih(pasted)) {
- if (pos_in_item >= 0 &&
- pos_in_item <=
- ih_entry_count(pasted)) {
+ if (pos_in_item >= 0 && pos_in_item <= ih_entry_count(pasted)) {
RFALSE(!tb->insert_size[0],
"PAP-12260: insert_size is 0 already");
/* prepare space */
buffer_info_init_tbS0(tb, &bi);
- leaf_paste_in_buffer(&bi,
- item_pos,
- pos_in_item,
- tb->
- insert_size
- [0], body,
+ leaf_paste_in_buffer(&bi, item_pos, pos_in_item,
+ tb->insert_size[0], body,
zeros_num);
/* paste entry */
- leaf_paste_entries(&bi,
- item_pos,
- pos_in_item,
- 1,
- (struct
- reiserfs_de_head
- *)body,
- body +
- DEH_SIZE,
- tb->
- insert_size
- [0]
- );
+ leaf_paste_entries(&bi, item_pos, pos_in_item, 1,
+ (struct reiserfs_de_head *)body,
+ body + DEH_SIZE,
+ tb->insert_size[0]);
if (!item_pos && !pos_in_item) {
- RFALSE(!tb->CFL[0]
- || !tb->L[0],
+ RFALSE(!tb->CFL[0] || !tb->L[0],
"PAP-12270: CFL[0]/L[0] must be specified");
- if (tb->CFL[0]) {
- replace_key(tb,
- tb->
- CFL
- [0],
- tb->
- lkey
- [0],
- tbS0,
- 0);
-
- }
+ if (tb->CFL[0])
+ replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0);
}
tb->insert_size[0] = 0;
}
@@ -1593,13 +1095,8 @@
"PAP-12275: insert size must not be %d",
tb->insert_size[0]);
buffer_info_init_tbS0(tb, &bi);
- leaf_paste_in_buffer(&bi,
- item_pos,
- pos_in_item,
- tb->
- insert_size
- [0], body,
- zeros_num);
+ leaf_paste_in_buffer(&bi, item_pos, pos_in_item,
+ tb->insert_size[0], body, zeros_num);
if (is_indirect_le_ih(pasted)) {
#if 0
@@ -1611,8 +1108,7 @@
tb->
insert_size[0]);
#endif
- set_ih_free_space
- (pasted, 0);
+ set_ih_free_space(pasted, 0);
}
tb->insert_size[0] = 0;
}
@@ -1620,8 +1116,7 @@
else {
if (tb->insert_size[0]) {
print_cur_tb("12285");
- reiserfs_panic(tb->
- tb_sb,
+ reiserfs_panic(tb->tb_sb,
"PAP-12285",
"insert_size "
"must be 0 "
diff --git a/fs/sync.c b/fs/sync.c
index e8ba024..b28d1dd 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -27,11 +27,10 @@
* wait == 1 case since in that case write_inode() functions do
* sync_dirty_buffer() and thus effectively write one block at a time.
*/
-static int __sync_filesystem(struct super_block *sb, int wait,
- unsigned long start)
+static int __sync_filesystem(struct super_block *sb, int wait)
{
if (wait)
- sync_inodes_sb(sb, start);
+ sync_inodes_sb(sb);
else
writeback_inodes_sb(sb, WB_REASON_SYNC);
@@ -48,7 +47,6 @@
int sync_filesystem(struct super_block *sb)
{
int ret;
- unsigned long start = jiffies;
/*
* We need to be protected against the filesystem going from
@@ -62,17 +60,17 @@
if (sb->s_flags & MS_RDONLY)
return 0;
- ret = __sync_filesystem(sb, 0, start);
+ ret = __sync_filesystem(sb, 0);
if (ret < 0)
return ret;
- return __sync_filesystem(sb, 1, start);
+ return __sync_filesystem(sb, 1);
}
EXPORT_SYMBOL_GPL(sync_filesystem);
static void sync_inodes_one_sb(struct super_block *sb, void *arg)
{
if (!(sb->s_flags & MS_RDONLY))
- sync_inodes_sb(sb, *((unsigned long *)arg));
+ sync_inodes_sb(sb);
}
static void sync_fs_one_sb(struct super_block *sb, void *arg)
@@ -104,10 +102,9 @@
SYSCALL_DEFINE0(sync)
{
int nowait = 0, wait = 1;
- unsigned long start = jiffies;
wakeup_flusher_threads(0, WB_REASON_SYNC);
- iterate_supers(sync_inodes_one_sb, &start);
+ iterate_supers(sync_inodes_one_sb, NULL);
iterate_supers(sync_fs_one_sb, &nowait);
iterate_supers(sync_fs_one_sb, &wait);
iterate_bdevs(fdatawrite_one_bdev, NULL);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 6211230..3eaf5c6 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -27,6 +27,7 @@
{
struct dentry *root;
void *ns;
+ bool new_sb;
if (!(flags & MS_KERNMOUNT)) {
if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
@@ -37,8 +38,8 @@
}
ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
- root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns);
- if (IS_ERR(root))
+ root = kernfs_mount_ns(fs_type, flags, sysfs_root, &new_sb, ns);
+ if (IS_ERR(root) || !new_sb)
kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
return root;
}
diff --git a/fs/udf/file.c b/fs/udf/file.c
index c02a27a..1037637 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -144,6 +144,7 @@
size_t count = iocb->ki_nbytes;
struct udf_inode_info *iinfo = UDF_I(inode);
+ mutex_lock(&inode->i_mutex);
down_write(&iinfo->i_data_sem);
if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
if (file->f_flags & O_APPEND)
@@ -156,6 +157,7 @@
pos + count)) {
err = udf_expand_file_adinicb(inode);
if (err) {
+ mutex_unlock(&inode->i_mutex);
udf_debug("udf_expand_adinicb: err=%d\n", err);
return err;
}
@@ -169,9 +171,17 @@
} else
up_write(&iinfo->i_data_sem);
- retval = generic_file_aio_write(iocb, iov, nr_segs, ppos);
- if (retval > 0)
+ retval = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+ mutex_unlock(&inode->i_mutex);
+
+ if (retval > 0) {
+ ssize_t err;
+
mark_inode_dirty(inode);
+ err = generic_write_sync(file, iocb->ki_pos - retval, retval);
+ if (err < 0)
+ retval = err;
+ }
return retval;
}
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 062b792..982ce05 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -265,6 +265,7 @@
.nr_to_write = 1,
};
+ WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
if (!iinfo->i_lenAlloc) {
if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD))
iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index f35d5c9..9ddfb81 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -705,7 +705,6 @@
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
- int mask = iattr->ia_valid;
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
@@ -726,8 +725,8 @@
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(S_ISREG(ip->i_d.di_mode));
- ASSERT((mask & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
- ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
+ ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
+ ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
oldsize = inode->i_size;
newsize = iattr->ia_size;
@@ -736,7 +735,7 @@
* Short circuit the truncate case for zero length files.
*/
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
- if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
+ if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
/*
@@ -824,10 +823,11 @@
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
- if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
+ if (newsize != oldsize &&
+ !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
- mask |= ATTR_CTIME | ATTR_MTIME;
+ iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
/*
@@ -863,9 +863,9 @@
xfs_inode_clear_eofblocks_tag(ip);
}
- if (mask & ATTR_MODE)
+ if (iattr->ia_valid & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
- if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
+ if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index cdebd83..4ef6fdb 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -205,16 +205,25 @@
/*
* We 64-bit align the length of each iovec so that the start
* of the next one is naturally aligned. We'll need to
- * account for that slack space here.
+ * account for that slack space here. Then round nbytes up
+ * to 64-bit alignment so that the initial buffer alignment is
+ * easy to calculate and verify.
*/
nbytes += niovecs * sizeof(uint64_t);
+ nbytes = round_up(nbytes, sizeof(uint64_t));
/* grab the old item if it exists for reservation accounting */
old_lv = lip->li_lv;
- /* calc buffer size */
- buf_size = sizeof(struct xfs_log_vec) + nbytes +
- niovecs * sizeof(struct xfs_log_iovec);
+ /*
+ * The data buffer needs to start 64-bit aligned, so round up
+ * that space to ensure we can align it appropriately and not
+ * overrun the buffer.
+ */
+ buf_size = nbytes +
+ round_up((sizeof(struct xfs_log_vec) +
+ niovecs * sizeof(struct xfs_log_iovec)),
+ sizeof(uint64_t));
/* compare to existing item size */
if (lip->li_lv && buf_size <= lip->li_lv->lv_size) {
@@ -251,6 +260,8 @@
/* The allocated data region lies beyond the iovec region */
lv->lv_buf_len = 0;
lv->lv_buf = (char *)lv + buf_size - nbytes;
+ ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
+
lip->li_ops->iop_format(lip, lv);
insert:
ASSERT(lv->lv_buf_len <= nbytes);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 02df7b4..f96c056 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -282,22 +282,29 @@
struct xfs_sb *sbp = &mp->m_sb;
int error;
int loud = !(flags & XFS_MFSI_QUIET);
+ const struct xfs_buf_ops *buf_ops;
ASSERT(mp->m_sb_bp == NULL);
ASSERT(mp->m_ddev_targp != NULL);
/*
+ * For the initial read, we must guess at the sector
+ * size based on the block device. It's enough to
+ * get the sb_sectsize out of the superblock and
+ * then reread with the proper length.
+ * We don't verify it yet, because it may not be complete.
+ */
+ sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
+ buf_ops = NULL;
+
+ /*
* Allocate a (locked) buffer to hold the superblock.
* This will be kept around at all times to optimize
* access to the superblock.
*/
- sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
-
reread:
bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
- BTOBB(sector_size), 0,
- loud ? &xfs_sb_buf_ops
- : &xfs_sb_quiet_buf_ops);
+ BTOBB(sector_size), 0, buf_ops);
if (!bp) {
if (loud)
xfs_warn(mp, "SB buffer read failed");
@@ -328,12 +335,13 @@
}
/*
- * If device sector size is smaller than the superblock size,
- * re-read the superblock so the buffer is correctly sized.
+ * Re-read the superblock so the buffer is correctly sized,
+ * and properly verified.
*/
- if (sector_size < sbp->sb_sectsize) {
+ if (buf_ops == NULL) {
xfs_buf_relse(bp);
sector_size = sbp->sb_sectsize;
+ buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops;
goto reread;
}
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index b7c9aea..1e11679 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -295,8 +295,7 @@
sbp->sb_dblocks == 0 ||
sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp) ||
sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp))) {
- XFS_CORRUPTION_ERROR("SB sanity check failed",
- XFS_ERRLEVEL_LOW, mp, sbp);
+ xfs_notice(mp, "SB sanity check failed");
return XFS_ERROR(EFSCORRUPTED);
}
@@ -611,10 +610,10 @@
XFS_SB_VERSION_5) ||
dsb->sb_crc != 0)) {
- if (!xfs_verify_cksum(bp->b_addr, be16_to_cpu(dsb->sb_sectsize),
+ if (!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
offsetof(struct xfs_sb, sb_crc))) {
/* Only fail bad secondaries on a known V5 filesystem */
- if (bp->b_bn != XFS_SB_DADDR &&
+ if (bp->b_bn == XFS_SB_DADDR ||
xfs_sb_version_hascrc(&mp->m_sb)) {
error = EFSCORRUPTED;
goto out_error;
@@ -625,7 +624,7 @@
out_error:
if (error) {
- if (error != EWRONGFS)
+ if (error == EFSCORRUPTED)
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
mp, bp->b_addr);
xfs_buf_ioerror(bp, error);
@@ -644,7 +643,6 @@
{
struct xfs_dsb *dsb = XFS_BUF_TO_SBP(bp);
-
if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) {
/* XFS filesystem, verify noisily! */
xfs_sb_read_verify(bp);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index f317488..d971f49 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -913,7 +913,7 @@
struct super_block *sb = mp->m_super;
if (down_read_trylock(&sb->s_umount)) {
- sync_inodes_sb(sb, jiffies);
+ sync_inodes_sb(sb);
up_read(&sb->s_umount);
}
}
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 8e4f41d..34c7bdc 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -701,6 +701,18 @@
}
#endif
+#ifndef ptep_set_numa
+static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep)
+{
+ pte_t ptent = *ptep;
+
+ ptent = pte_mknuma(ptent);
+ set_pte_at(mm, addr, ptep, ptent);
+ return;
+}
+#endif
+
#ifndef pmd_mknuma
static inline pmd_t pmd_mknuma(pmd_t pmd)
{
@@ -708,6 +720,18 @@
return pmd_clear_flags(pmd, _PAGE_PRESENT);
}
#endif
+
+#ifndef pmdp_set_numa
+static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp)
+{
+ pmd_t pmd = *pmdp;
+
+ pmd = pmd_mknuma(pmd);
+ set_pmd_at(mm, addr, pmdp, pmd);
+ return;
+}
+#endif
#else
extern int pte_numa(pte_t pte);
extern int pmd_numa(pmd_t pmd);
@@ -715,6 +739,8 @@
extern pmd_t pmd_mknonnuma(pmd_t pmd);
extern pte_t pte_mknuma(pte_t pte);
extern pmd_t pmd_mknuma(pmd_t pmd);
+extern void ptep_set_numa(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+extern void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp);
#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
#else
static inline int pmd_numa(pmd_t pmd)
@@ -742,10 +768,23 @@
return pte;
}
+static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep)
+{
+ return;
+}
+
+
static inline pmd_t pmd_mknuma(pmd_t pmd)
{
return pmd;
}
+
+static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp)
+{
+ return ;
+}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_MMU */
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 04086c5..04a7f31 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -199,6 +199,9 @@
#define DRM_INFO(fmt, ...) \
printk(KERN_INFO "[" DRM_NAME "] " fmt, ##__VA_ARGS__)
+#define DRM_INFO_ONCE(fmt, ...) \
+ printk_once(KERN_INFO "[" DRM_NAME "] " fmt, ##__VA_ARGS__)
+
/**
* Debug output.
*
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 71727b6..8f3dee0 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -907,6 +907,9 @@
/* whether async page flip is supported or not */
bool async_page_flip;
+
+ /* cursor size */
+ uint32_t cursor_width, cursor_height;
};
#define obj_to_crtc(x) container_of(x, struct drm_crtc, base)
diff --git a/include/drm/ttm/ttm_page_alloc.h b/include/drm/ttm/ttm_page_alloc.h
index d1f61bf..49a8284 100644
--- a/include/drm/ttm/ttm_page_alloc.h
+++ b/include/drm/ttm/ttm_page_alloc.h
@@ -29,6 +29,8 @@
#include <drm/ttm/ttm_bo_driver.h>
#include <drm/ttm/ttm_memory.h>
+struct device;
+
/**
* Initialize pool allocator.
*/
diff --git a/include/dt-bindings/clock/tegra124-car.h b/include/dt-bindings/clock/tegra124-car.h
index a1116a3..8c1603b 100644
--- a/include/dt-bindings/clock/tegra124-car.h
+++ b/include/dt-bindings/clock/tegra124-car.h
@@ -36,10 +36,10 @@
#define TEGRA124_CLK_PWM 17
#define TEGRA124_CLK_I2S2 18
/* 20 (register bit affects vi and vi_sensor) */
-#define TEGRA124_CLK_GR_2D 21
+/* 21 */
#define TEGRA124_CLK_USBD 22
#define TEGRA124_CLK_ISP 23
-#define TEGRA124_CLK_GR_3D 24
+/* 26 */
/* 25 */
#define TEGRA124_CLK_DISP2 26
#define TEGRA124_CLK_DISP1 27
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index be85127..f27000f 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -171,6 +171,11 @@
return 0;
}
+static inline int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
+{
+ return -ENXIO;
+}
+
static inline int kvm_vgic_init(struct kvm *kvm)
{
return 0;
diff --git a/include/linux/audit.h b/include/linux/audit.h
index aa865a9..ec1464d 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -43,6 +43,7 @@
struct mqstat;
struct audit_watch;
struct audit_tree;
+struct sk_buff;
struct audit_krule {
int vers_ops;
@@ -463,7 +464,7 @@
extern int audit_filter_type(int type);
extern int audit_rule_change(int type, __u32 portid, int seq,
void *data, size_t datasz);
-extern int audit_list_rules_send(__u32 portid, int seq);
+extern int audit_list_rules_send(struct sk_buff *request_skb, int seq);
extern u32 audit_enabled;
#else /* CONFIG_AUDIT */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 7065452..5a4d39b 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -250,6 +250,17 @@
struct bio_vec bv;
struct bvec_iter iter;
+ /*
+ * We special case discard/write same, because they interpret bi_size
+ * differently:
+ */
+
+ if (bio->bi_rw & REQ_DISCARD)
+ return 1;
+
+ if (bio->bi_rw & REQ_WRITE_SAME)
+ return 1;
+
bio_for_each_segment(bv, bio, iter)
segs++;
@@ -332,6 +343,7 @@
extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
extern struct bio_set *fs_bio_set;
+unsigned int bio_integrity_tag_size(struct bio *bio);
static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
{
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 161b231..2ff2e8d 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -83,6 +83,8 @@
*/
rq_timed_out_fn *timeout;
+ softirq_done_fn *complete;
+
/*
* Override for hctx allocations (should probably go)
*/
@@ -119,11 +121,11 @@
void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
-void blk_mq_insert_request(struct request_queue *, struct request *, bool);
+void blk_mq_insert_request(struct request *, bool, bool, bool);
void blk_mq_run_queues(struct request_queue *q, bool async);
void blk_mq_free_request(struct request *rq);
bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, bool reserved);
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp);
struct request *blk_mq_alloc_reserved_request(struct request_queue *q, int rw, gfp_t gfp);
struct request *blk_mq_rq_from_tag(struct request_queue *q, unsigned int tag);
@@ -131,7 +133,15 @@
struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_reg *, unsigned int);
void blk_mq_free_single_hw_queue(struct blk_mq_hw_ctx *, unsigned int);
-void blk_mq_end_io(struct request *rq, int error);
+bool blk_mq_end_io_partial(struct request *rq, int error,
+ unsigned int nr_bytes);
+static inline void blk_mq_end_io(struct request *rq, int error)
+{
+ bool done = !blk_mq_end_io_partial(rq, error, blk_rq_bytes(rq));
+ BUG_ON(!done);
+}
+
+void blk_mq_complete_request(struct request *rq);
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8678c43..4afa4f8 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -98,7 +98,7 @@
struct list_head queuelist;
union {
struct call_single_data csd;
- struct work_struct mq_flush_data;
+ struct work_struct mq_flush_work;
};
struct request_queue *q;
@@ -448,13 +448,8 @@
unsigned long flush_pending_since;
struct list_head flush_queue[2];
struct list_head flush_data_in_flight;
- union {
- struct request flush_rq;
- struct {
- spinlock_t mq_flush_lock;
- struct work_struct mq_flush_work;
- };
- };
+ struct request *flush_rq;
+ spinlock_t mq_flush_lock;
struct mutex sysfs_lock;
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 677b4f0..6f76277 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -13,10 +13,17 @@
#define PHY_ID_BCM5461 0x002060c0
#define PHY_ID_BCM57780 0x03625d90
+#define PHY_ID_BCM7366 0x600d8490
+#define PHY_ID_BCM7439 0x600d8480
+#define PHY_ID_BCM7445 0x600d8510
+#define PHY_ID_BCM7XXX_28 0x600d8400
+
#define PHY_BCM_OUI_MASK 0xfffffc00
#define PHY_BCM_OUI_1 0x00206000
#define PHY_BCM_OUI_2 0x0143bc00
#define PHY_BCM_OUI_3 0x03625c00
+#define PHY_BCM_OUI_4 0x600d0000
+#define PHY_BCM_OUI_5 0x03625e00
#define PHY_BCM_FLAGS_MODE_COPPER 0x00000001
@@ -31,6 +38,59 @@
#define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00002000
#define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000
#define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000
+/* Broadcom BCM7xxx specific workarounds */
+#define PHY_BRCM_100MBPS_WAR 0x00010000
#define PHY_BCM_FLAGS_VALID 0x80000000
+/* Broadcom BCM54XX register definitions, common to most Broadcom PHYs */
+#define MII_BCM54XX_ECR 0x10 /* BCM54xx extended control register */
+#define MII_BCM54XX_ECR_IM 0x1000 /* Interrupt mask */
+#define MII_BCM54XX_ECR_IF 0x0800 /* Interrupt force */
+
+#define MII_BCM54XX_ESR 0x11 /* BCM54xx extended status register */
+#define MII_BCM54XX_ESR_IS 0x1000 /* Interrupt status */
+
+#define MII_BCM54XX_EXP_DATA 0x15 /* Expansion register data */
+#define MII_BCM54XX_EXP_SEL 0x17 /* Expansion register select */
+#define MII_BCM54XX_EXP_SEL_SSD 0x0e00 /* Secondary SerDes select */
+#define MII_BCM54XX_EXP_SEL_ER 0x0f00 /* Expansion register select */
+
+#define MII_BCM54XX_AUX_CTL 0x18 /* Auxiliary control register */
+#define MII_BCM54XX_ISR 0x1a /* BCM54xx interrupt status register */
+#define MII_BCM54XX_IMR 0x1b /* BCM54xx interrupt mask register */
+#define MII_BCM54XX_INT_CRCERR 0x0001 /* CRC error */
+#define MII_BCM54XX_INT_LINK 0x0002 /* Link status changed */
+#define MII_BCM54XX_INT_SPEED 0x0004 /* Link speed change */
+#define MII_BCM54XX_INT_DUPLEX 0x0008 /* Duplex mode changed */
+#define MII_BCM54XX_INT_LRS 0x0010 /* Local receiver status changed */
+#define MII_BCM54XX_INT_RRS 0x0020 /* Remote receiver status changed */
+#define MII_BCM54XX_INT_SSERR 0x0040 /* Scrambler synchronization error */
+#define MII_BCM54XX_INT_UHCD 0x0080 /* Unsupported HCD negotiated */
+#define MII_BCM54XX_INT_NHCD 0x0100 /* No HCD */
+#define MII_BCM54XX_INT_NHCDL 0x0200 /* No HCD link */
+#define MII_BCM54XX_INT_ANPR 0x0400 /* Auto-negotiation page received */
+#define MII_BCM54XX_INT_LC 0x0800 /* All counters below 128 */
+#define MII_BCM54XX_INT_HC 0x1000 /* Counter above 32768 */
+#define MII_BCM54XX_INT_MDIX 0x2000 /* MDIX status change */
+#define MII_BCM54XX_INT_PSERR 0x4000 /* Pair swap error */
+
+#define MII_BCM54XX_SHD 0x1c /* 0x1c shadow registers */
+#define MII_BCM54XX_SHD_WRITE 0x8000
+#define MII_BCM54XX_SHD_VAL(x) ((x & 0x1f) << 10)
+#define MII_BCM54XX_SHD_DATA(x) ((x & 0x3ff) << 0)
+
+/*
+ * AUXILIARY CONTROL SHADOW ACCESS REGISTERS. (PHY REG 0x18)
+ */
+#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000
+#define MII_BCM54XX_AUXCTL_ACTL_TX_6DB 0x0400
+#define MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA 0x0800
+
+#define MII_BCM54XX_AUXCTL_MISC_WREN 0x8000
+#define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200
+#define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC 0x7000
+#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x0007
+
+#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000
+
#endif /* _LINUX_BRCMPHY_H */
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index fb0ab65..3ce5e52 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -33,8 +33,9 @@
struct can_priv {
struct can_device_stats can_stats;
- struct can_bittiming bittiming;
- const struct can_bittiming_const *bittiming_const;
+ struct can_bittiming bittiming, data_bittiming;
+ const struct can_bittiming_const *bittiming_const,
+ *data_bittiming_const;
struct can_clock clock;
enum can_state state;
@@ -45,6 +46,7 @@
struct timer_list restart_timer;
int (*do_set_bittiming)(struct net_device *dev);
+ int (*do_set_data_bittiming)(struct net_device *dev);
int (*do_set_mode)(struct net_device *dev, enum can_mode mode);
int (*do_get_state)(const struct net_device *dev,
enum can_state *state);
@@ -111,6 +113,7 @@
int open_candev(struct net_device *dev);
void close_candev(struct net_device *dev);
+int can_change_mtu(struct net_device *dev, int new_mtu);
int register_candev(struct net_device *dev);
void unregister_candev(struct net_device *dev);
@@ -124,6 +127,8 @@
void can_free_echo_skb(struct net_device *dev, unsigned int idx);
struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf);
+struct sk_buff *alloc_canfd_skb(struct net_device *dev,
+ struct canfd_frame **cfd);
struct sk_buff *alloc_can_err_skb(struct net_device *dev,
struct can_frame **cf);
diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index 2f0543f..f9bbbb4 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -11,7 +11,9 @@
#define CAN_SKB_H
#include <linux/types.h>
+#include <linux/skbuff.h>
#include <linux/can.h>
+#include <net/sock.h>
/*
* The struct can_skb_priv is used to transport additional information along
@@ -42,4 +44,40 @@
skb_reserve(skb, sizeof(struct can_skb_priv));
}
+static inline void can_skb_destructor(struct sk_buff *skb)
+{
+ sock_put(skb->sk);
+}
+
+static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk)
+{
+ if (sk) {
+ sock_hold(sk);
+ skb->destructor = can_skb_destructor;
+ skb->sk = sk;
+ }
+}
+
+/*
+ * returns an unshared skb owned by the original sock to be echo'ed back
+ */
+static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb)
+{
+ if (skb_shared(skb)) {
+ struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+ if (likely(nskb)) {
+ can_skb_set_owner(nskb, skb->sk);
+ consume_skb(skb);
+ return nskb;
+ } else {
+ kfree_skb(skb);
+ return NULL;
+ }
+ }
+
+ /* we can assume to have an unshared skb with proper owner */
+ return skb;
+}
+
#endif /* CAN_SKB_H */
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 2623cff..25bfb0e 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -373,8 +373,9 @@
/*
* Ceph setxattr request flags.
*/
-#define CEPH_XATTR_CREATE 1
-#define CEPH_XATTR_REPLACE 2
+#define CEPH_XATTR_CREATE (1 << 0)
+#define CEPH_XATTR_REPLACE (1 << 1)
+#define CEPH_XATTR_REMOVE (1 << 31)
union ceph_mds_request_args {
struct {
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 5c09759..9450f02 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -166,6 +166,8 @@
*
* The ID of the root cgroup is always 0, and a new cgroup
* will be assigned with a smallest available ID.
+ *
+ * Allocating/Removing ID must be protected by cgroup_mutex.
*/
int id;
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index 092b641..4a21a87 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -245,6 +245,10 @@
void omap2_init_clk_clkdm(struct clk_hw *clk);
unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
unsigned long parent_rate);
+int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate,
+ unsigned long parent_rate);
+long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate,
+ unsigned long *prate);
int omap2_clkops_enable_clkdm(struct clk_hw *hw);
void omap2_clkops_disable_clkdm(struct clk_hw *hw);
int omap2_clk_disable_autoidle_all(void);
diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h
index ded4299..2507fd2 100644
--- a/include/linux/compiler-gcc4.h
+++ b/include/linux/compiler-gcc4.h
@@ -75,11 +75,7 @@
*
* (asm goto is automatically volatile - the naming reflects this.)
*/
-#if GCC_VERSION <= 40801
-# define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0)
-#else
-# define asm_volatile_goto(x...) do { asm goto(x); } while (0)
-#endif
+#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0)
#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
#if GCC_VERSION >= 40400
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index dfac5ed..f886985 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -171,7 +171,7 @@
size_t size, int flags, const char *);
#define dma_buf_export(priv, ops, size, flags) \
- dma_buf_export_named(priv, ops, size, flags, __FILE__)
+ dma_buf_export_named(priv, ops, size, flags, KBUILD_MODNAME)
int dma_buf_fd(struct dma_buf *dmabuf, int flags);
struct dma_buf *dma_buf_get(int fd);
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index c8e3e7e3..0a114d0 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -183,6 +183,9 @@
* hold the RTNL lock.
*
* See the structures used by these operations for further documentation.
+ * Note that for all operations using a structure ending with a zero-
+ * length array, the array is allocated separately in the kernel and
+ * is passed to the driver as an additional parameter.
*
* See &struct net_device and &struct net_device_ops for documentation
* of the generic netdev features interface.
diff --git a/include/linux/file.h b/include/linux/file.h
index cbacf4f..4d69123 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -28,33 +28,36 @@
struct fd {
struct file *file;
- int need_put;
+ unsigned int flags;
};
+#define FDPUT_FPUT 1
+#define FDPUT_POS_UNLOCK 2
static inline void fdput(struct fd fd)
{
- if (fd.need_put)
+ if (fd.flags & FDPUT_FPUT)
fput(fd.file);
}
extern struct file *fget(unsigned int fd);
-extern struct file *fget_light(unsigned int fd, int *fput_needed);
+extern struct file *fget_raw(unsigned int fd);
+extern unsigned long __fdget(unsigned int fd);
+extern unsigned long __fdget_raw(unsigned int fd);
+extern unsigned long __fdget_pos(unsigned int fd);
+
+static inline struct fd __to_fd(unsigned long v)
+{
+ return (struct fd){(struct file *)(v & ~3),v & 3};
+}
static inline struct fd fdget(unsigned int fd)
{
- int b;
- struct file *f = fget_light(fd, &b);
- return (struct fd){f,b};
+ return __to_fd(__fdget(fd));
}
-extern struct file *fget_raw(unsigned int fd);
-extern struct file *fget_raw_light(unsigned int fd, int *fput_needed);
-
static inline struct fd fdget_raw(unsigned int fd)
{
- int b;
- struct file *f = fget_raw_light(fd, &b);
- return (struct fd){f,b};
+ return __to_fd(__fdget_raw(fd));
}
extern int f_dupfd(unsigned int from, struct file *file, unsigned flags);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index e568c8e..262dcbb 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -9,28 +9,81 @@
#include <linux/workqueue.h>
#include <uapi/linux/filter.h>
-#ifdef CONFIG_COMPAT
-/*
- * A struct sock_filter is architecture independent.
+/* Internally used and optimized filter representation with extended
+ * instruction set based on top of classic BPF.
*/
+
+/* instruction classes */
+#define BPF_ALU64 0x07 /* alu mode in double word width */
+
+/* ld/ldx fields */
+#define BPF_DW 0x18 /* double word */
+#define BPF_XADD 0xc0 /* exclusive add */
+
+/* alu/jmp fields */
+#define BPF_MOV 0xb0 /* mov reg to reg */
+#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */
+
+/* change endianness of a register */
+#define BPF_END 0xd0 /* flags for endianness conversion: */
+#define BPF_TO_LE 0x00 /* convert to little-endian */
+#define BPF_TO_BE 0x08 /* convert to big-endian */
+#define BPF_FROM_LE BPF_TO_LE
+#define BPF_FROM_BE BPF_TO_BE
+
+#define BPF_JNE 0x50 /* jump != */
+#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */
+#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */
+#define BPF_CALL 0x80 /* function call */
+#define BPF_EXIT 0x90 /* function return */
+
+/* BPF has 10 general purpose 64-bit registers and stack frame. */
+#define MAX_BPF_REG 11
+
+/* BPF program can access up to 512 bytes of stack space. */
+#define MAX_BPF_STACK 512
+
+/* Arg1, context and stack frame pointer register positions. */
+#define ARG1_REG 1
+#define CTX_REG 6
+#define FP_REG 10
+
+struct sock_filter_int {
+ __u8 code; /* opcode */
+ __u8 a_reg:4; /* dest register */
+ __u8 x_reg:4; /* source register */
+ __s16 off; /* signed offset */
+ __s32 imm; /* signed immediate constant */
+};
+
+#ifdef CONFIG_COMPAT
+/* A struct sock_filter is architecture independent. */
struct compat_sock_fprog {
u16 len;
- compat_uptr_t filter; /* struct sock_filter * */
+ compat_uptr_t filter; /* struct sock_filter * */
};
#endif
+struct sock_fprog_kern {
+ u16 len;
+ struct sock_filter *filter;
+};
+
struct sk_buff;
struct sock;
+struct seccomp_data;
-struct sk_filter
-{
+struct sk_filter {
atomic_t refcnt;
- unsigned int len; /* Number of filter blocks */
+ u32 jited:1, /* Is our filter JIT'ed? */
+ len:31; /* Number of filter blocks */
+ struct sock_fprog_kern *orig_prog; /* Original BPF program */
struct rcu_head rcu;
unsigned int (*bpf_func)(const struct sk_buff *skb,
- const struct sock_filter *filter);
+ const struct sock_filter_int *filter);
union {
- struct sock_filter insns[0];
+ struct sock_filter insns[0];
+ struct sock_filter_int insnsi[0];
struct work_struct work;
};
};
@@ -41,25 +94,44 @@
offsetof(struct sk_filter, insns[proglen]));
}
-extern int sk_filter(struct sock *sk, struct sk_buff *skb);
-extern unsigned int sk_run_filter(const struct sk_buff *skb,
- const struct sock_filter *filter);
-extern int sk_unattached_filter_create(struct sk_filter **pfp,
- struct sock_fprog *fprog);
-extern void sk_unattached_filter_destroy(struct sk_filter *fp);
-extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
-extern int sk_detach_filter(struct sock *sk);
-extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen);
-extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len);
-extern void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to);
+#define sk_filter_proglen(fprog) \
+ (fprog->len * sizeof(fprog->filter[0]))
+
+#define SK_RUN_FILTER(filter, ctx) \
+ (*filter->bpf_func)(ctx, filter->insnsi)
+
+int sk_filter(struct sock *sk, struct sk_buff *skb);
+
+u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx,
+ const struct sock_filter_int *insni);
+u32 sk_run_filter_int_skb(const struct sk_buff *ctx,
+ const struct sock_filter_int *insni);
+
+int sk_convert_filter(struct sock_filter *prog, int len,
+ struct sock_filter_int *new_prog, int *new_len);
+
+int sk_unattached_filter_create(struct sk_filter **pfp,
+ struct sock_fprog *fprog);
+void sk_unattached_filter_destroy(struct sk_filter *fp);
+
+int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
+int sk_detach_filter(struct sock *sk);
+
+int sk_chk_filter(struct sock_filter *filter, unsigned int flen);
+int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
+ unsigned int len);
+void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to);
+
+void sk_filter_charge(struct sock *sk, struct sk_filter *fp);
+void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
#ifdef CONFIG_BPF_JIT
#include <stdarg.h>
#include <linux/linkage.h>
#include <linux/printk.h>
-extern void bpf_jit_compile(struct sk_filter *fp);
-extern void bpf_jit_free(struct sk_filter *fp);
+void bpf_jit_compile(struct sk_filter *fp);
+void bpf_jit_free(struct sk_filter *fp);
static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
u32 pass, void *image)
@@ -70,7 +142,6 @@
print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
16, 1, image, proglen, false);
}
-#define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns)
#else
#include <linux/slab.h>
static inline void bpf_jit_compile(struct sk_filter *fp)
@@ -80,7 +151,6 @@
{
kfree(fp);
}
-#define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns)
#endif
static inline int bpf_tell_extensions(void)
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 5d7782e..c3683bd 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -200,6 +200,7 @@
unsigned irmc:1;
unsigned bc_implemented:2;
+ work_func_t workfn;
struct delayed_work work;
struct fw_attribute_group attribute_group;
};
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6082956..23b2a35 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -123,6 +123,9 @@
/* File is opened with O_PATH; almost nothing can be done with it */
#define FMODE_PATH ((__force fmode_t)0x4000)
+/* File needs atomic accesses to f_pos */
+#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000)
+
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x1000000)
@@ -780,13 +783,14 @@
const struct file_operations *f_op;
/*
- * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR.
+ * Protects f_ep_links, f_flags.
* Must not be taken from IRQ context.
*/
spinlock_t f_lock;
atomic_long_t f_count;
unsigned int f_flags;
fmode_t f_mode;
+ struct mutex f_pos_lock;
loff_t f_pos;
struct fown_struct f_owner;
const struct cred *f_cred;
@@ -808,7 +812,7 @@
#ifdef CONFIG_DEBUG_WRITECOUNT
unsigned long f_mnt_write_state;
#endif
-};
+} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */
struct file_handle {
__u32 handle_bytes;
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 3d286ff..64cf3ef 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -99,7 +99,7 @@
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name);
+ const unsigned char *file_name, u32 cookie);
void (*free_group_priv)(struct fsnotify_group *group);
void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
void (*free_event)(struct fsnotify_event *event);
@@ -160,7 +160,7 @@
struct fasync_struct *fsn_fa; /* async notification */
- struct fsnotify_event overflow_event; /* Event we queue when the
+ struct fsnotify_event *overflow_event; /* Event we queue when the
* notification list is too
* full */
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 4e4cc28..4cdb3a1 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -495,10 +495,6 @@
FILTER_TRACE_FN,
};
-#define EVENT_STORAGE_SIZE 128
-extern struct mutex event_storage_mutex;
-extern char event_storage[EVENT_STORAGE_SIZE];
-
extern int trace_event_raw_init(struct ftrace_event_call *call);
extern int trace_define_field(struct ftrace_event_call *call, const char *type,
const char *name, int offset, int size,
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 0437439..39b81dc 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -123,6 +123,10 @@
__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
__GFP_NO_KSWAPD)
+/*
+ * GFP_THISNODE does not perform any reclaim, you most likely want to
+ * use __GFP_THISNODE to allocate from a given node without fallback!
+ */
#ifdef CONFIG_NUMA
#define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
#else
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 4d34dbb..7a8144f 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -4,8 +4,6 @@
#include <linux/err.h>
#include <linux/kernel.h>
-#ifdef CONFIG_GPIOLIB
-
struct device;
struct gpio_chip;
@@ -18,6 +16,8 @@
*/
struct gpio_desc;
+#ifdef CONFIG_GPIOLIB
+
/* Acquire and dispose GPIOs */
struct gpio_desc *__must_check gpiod_get(struct device *dev,
const char *con_id);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index db51201..b826239 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -157,46 +157,6 @@
return HPAGE_PMD_NR;
return 1;
}
-/*
- * compound_trans_head() should be used instead of compound_head(),
- * whenever the "page" passed as parameter could be the tail of a
- * transparent hugepage that could be undergoing a
- * __split_huge_page_refcount(). The page structure layout often
- * changes across releases and it makes extensive use of unions. So if
- * the page structure layout will change in a way that
- * page->first_page gets clobbered by __split_huge_page_refcount, the
- * implementation making use of smp_rmb() will be required.
- *
- * Currently we define compound_trans_head as compound_head, because
- * page->private is in the same union with page->first_page, and
- * page->private isn't clobbered. However this also means we're
- * currently leaving dirt into the page->private field of anonymous
- * pages resulting from a THP split, instead of setting page->private
- * to zero like for every other page that has PG_private not set. But
- * anonymous pages don't use page->private so this is not a problem.
- */
-#if 0
-/* This will be needed if page->private will be clobbered in split_huge_page */
-static inline struct page *compound_trans_head(struct page *page)
-{
- if (PageTail(page)) {
- struct page *head;
- head = page->first_page;
- smp_rmb();
- /*
- * head may be a dangling pointer.
- * __split_huge_page_refcount clears PageTail before
- * overwriting first_page, so if PageTail is still
- * there it means the head pointer isn't dangling.
- */
- if (PageTail(page))
- return head;
- }
- return page;
-}
-#else
-#define compound_trans_head(page) compound_head(page)
-#endif
extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pmd_t pmd, pmd_t *pmdp);
@@ -226,7 +186,6 @@
do { } while (0)
#define split_huge_page_pmd_mm(__mm, __address, __pmd) \
do { } while (0)
-#define compound_trans_head(page) compound_head(page)
static inline int hugepage_madvise(struct vm_area_struct *vma,
unsigned long *vm_flags, int advice)
{
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 15da677..344883d 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -875,7 +875,7 @@
struct vmbus_channel_initiate_contact {
struct vmbus_channel_message_header header;
u32 vmbus_version_requested;
- u32 padding2;
+ u32 target_vcpu; /* The VCPU the host should respond to */
u64 interrupt_page;
u64 monitor_page1;
u64 monitor_page2;
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index bbedfb5..13bbbde 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -110,6 +110,7 @@
__be16 vlan_proto, u16 vlan_id);
extern struct net_device *vlan_dev_real_dev(const struct net_device *dev);
extern u16 vlan_dev_vlan_id(const struct net_device *dev);
+extern __be16 vlan_dev_vlan_proto(const struct net_device *dev);
/**
* struct vlan_priority_tci_mapping - vlan egress priority mappings
@@ -216,6 +217,12 @@
return 0;
}
+static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev)
+{
+ BUG();
+ return 0;
+}
+
static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev,
u32 skprio)
{
@@ -288,7 +295,7 @@
struct vlan_ethhdr *veth;
if (skb_cow_head(skb, VLAN_HLEN) < 0) {
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NULL;
}
veth = (struct vlan_ethhdr *)skb_push(skb, VLAN_HLEN);
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 0053add..a2678d3 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -158,6 +158,11 @@
devname, dev_id);
}
+extern int __must_check
+devm_request_any_context_irq(struct device *dev, unsigned int irq,
+ irq_handler_t handler, unsigned long irqflags,
+ const char *devname, void *dev_id);
+
extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
/*
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index e7831d2..35e7eca 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -118,9 +118,7 @@
* the new maximum will handle anyone else. I may have to revisit this
* in the future.
*/
-#define MIN_QUEUESMAX 1
#define DFLT_QUEUESMAX 256
-#define HARD_QUEUESMAX 1024
#define MIN_MSGMAX 1
#define DFLT_MSG 10U
#define DFLT_MSGMAX 10
diff --git a/include/linux/isdn_ppp.h b/include/linux/isdn_ppp.h
index d5f62bc..8e10f57 100644
--- a/include/linux/isdn_ppp.h
+++ b/include/linux/isdn_ppp.h
@@ -180,9 +180,8 @@
struct slcompress *slcomp;
#endif
#ifdef CONFIG_IPPP_FILTER
- struct sock_filter *pass_filter; /* filter for packets to pass */
- struct sock_filter *active_filter; /* filter for pkts to reset idle */
- unsigned pass_len, active_len;
+ struct sk_filter *pass_filter; /* filter for packets to pass */
+ struct sk_filter *active_filter; /* filter for pkts to reset idle */
#endif
unsigned long debug;
struct isdn_ppp_compressor *compressor,*decompressor;
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 5be9f02..d267623 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -249,7 +249,8 @@
const void *kernfs_super_ns(struct super_block *sb);
struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
- struct kernfs_root *root, const void *ns);
+ struct kernfs_root *root, bool *new_sb_created,
+ const void *ns);
void kernfs_kill_sb(struct super_block *sb);
void kernfs_init(void);
@@ -317,7 +318,7 @@
static inline struct dentry *
kernfs_mount_ns(struct file_system_type *fs_type, int flags,
- struct kernfs_root *root, const void *ns)
+ struct kernfs_root *root, bool *new_sb_created, const void *ns)
{ return ERR_PTR(-ENOSYS); }
static inline void kernfs_kill_sb(struct super_block *sb) { }
@@ -368,9 +369,9 @@
static inline struct dentry *
kernfs_mount(struct file_system_type *fs_type, int flags,
- struct kernfs_root *root)
+ struct kernfs_root *root, bool *new_sb_created)
{
- return kernfs_mount_ns(fs_type, flags, root, NULL);
+ return kernfs_mount_ns(fs_type, flags, root, new_sb_created, NULL);
}
#endif /* __LINUX_KERNFS_H */
diff --git a/include/linux/mfd/max8997-private.h b/include/linux/mfd/max8997-private.h
index ad1ae7f..78c76cd 100644
--- a/include/linux/mfd/max8997-private.h
+++ b/include/linux/mfd/max8997-private.h
@@ -387,7 +387,7 @@
struct i2c_client *muic; /* slave addr 0x4a */
struct mutex iolock;
- int type;
+ unsigned long type;
struct platform_device *battery; /* battery control (not fuel gauge) */
int irq;
diff --git a/include/linux/mfd/max8998-private.h b/include/linux/mfd/max8998-private.h
index 4ecb24b..d68ada5 100644
--- a/include/linux/mfd/max8998-private.h
+++ b/include/linux/mfd/max8998-private.h
@@ -163,7 +163,7 @@
int ono;
u8 irq_masks_cur[MAX8998_NUM_IRQ_REGS];
u8 irq_masks_cache[MAX8998_NUM_IRQ_REGS];
- int type;
+ unsigned long type;
bool wakeup;
};
diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h
index a5a7f01..54b5458 100644
--- a/include/linux/mfd/tps65217.h
+++ b/include/linux/mfd/tps65217.h
@@ -252,7 +252,7 @@
struct tps65217 {
struct device *dev;
struct tps65217_board *pdata;
- unsigned int id;
+ unsigned long id;
struct regulator_desc desc[TPS65217_NUM_REGULATOR];
struct regulator_dev *rdev[TPS65217_NUM_REGULATOR];
struct regmap *regmap;
@@ -263,7 +263,7 @@
return dev_get_drvdata(dev);
}
-static inline int tps65217_chip_id(struct tps65217 *tps65217)
+static inline unsigned long tps65217_chip_id(struct tps65217 *tps65217)
{
return tps65217->id;
}
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index 79a3472..c845036 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -125,6 +125,7 @@
/* miscellaneous commands */
MLX4_CMD_DIAG_RPRT = 0x30,
MLX4_CMD_NOP = 0x31,
+ MLX4_CMD_CONFIG_DEV = 0x3a,
MLX4_CMD_ACCESS_MEM = 0x2e,
MLX4_CMD_SET_VEP = 0x52,
@@ -240,6 +241,13 @@
int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting);
int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_info *ivf);
int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_state);
+/*
+ * mlx4_get_slave_default_vlan -
+ * return true if VST ( default vlan)
+ * if VST, will return vlan & qos (if not NULL)
+ */
+bool mlx4_get_slave_default_vlan(struct mlx4_dev *dev, int port, int slave,
+ u16 *vlan, u8 *qos);
#define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8)
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 5edd2c6..ba87bd2 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -48,6 +48,9 @@
#define MSIX_LEGACY_SZ 4
#define MIN_MSIX_P_PORT 5
+#define MLX4_ROCE_MAX_GIDS 128
+#define MLX4_ROCE_PF_GIDS 16
+
enum {
MLX4_FLAG_MSI_X = 1 << 0,
MLX4_FLAG_OLD_PORT_CMDS = 1 << 1,
@@ -81,6 +84,7 @@
enum {
MLX4_MAX_NUM_PF = 16,
MLX4_MAX_NUM_VF = 64,
+ MLX4_MAX_NUM_VF_P_PORT = 64,
MLX4_MFUNC_MAX = 80,
MLX4_MAX_EQ_NUM = 1024,
MLX4_MFUNC_EQ_NUM = 4,
@@ -629,7 +633,8 @@
u8 hop_limit;
__be32 sl_tclass_flowlabel;
u8 dgid[16];
- u32 reserved4[2];
+ u8 s_mac[6];
+ u8 reserved4[2];
__be16 vlan;
u8 mac[ETH_ALEN];
};
@@ -660,6 +665,11 @@
int xrcd;
};
+struct mlx4_vf_dev {
+ u8 min_port;
+ u8 n_ports;
+};
+
struct mlx4_dev {
struct pci_dev *pdev;
unsigned long flags;
@@ -675,6 +685,7 @@
int oper_log_mgm_entry_size;
u64 regid_promisc_array[MLX4_MAX_PORTS + 1];
u64 regid_allmulti_array[MLX4_MAX_PORTS + 1];
+ struct mlx4_vf_dev *dev_vfs;
};
struct mlx4_eqe {
@@ -1131,7 +1142,7 @@
int mlx4_SET_PORT_PRIO2TC(struct mlx4_dev *dev, u8 port, u8 *prio2tc);
int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw,
u8 *pg, u16 *ratelimit);
-int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering);
+int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering, int enable);
int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx);
int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
@@ -1183,9 +1194,44 @@
void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid);
__be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave);
+int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
+ int *slave_id);
+int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id,
+ u8 *gid);
+
int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn,
u32 max_range_qpn);
cycle_t mlx4_read_clock(struct mlx4_dev *dev);
+struct mlx4_active_ports {
+ DECLARE_BITMAP(ports, MLX4_MAX_PORTS);
+};
+/* Returns a bitmap of the physical ports which are assigned to slave */
+struct mlx4_active_ports mlx4_get_active_ports(struct mlx4_dev *dev, int slave);
+
+/* Returns the physical port that represents the virtual port of the slave, */
+/* or a value < 0 in case of an error. If a slave has 2 ports, the identity */
+/* mapping is returned. */
+int mlx4_slave_convert_port(struct mlx4_dev *dev, int slave, int port);
+
+struct mlx4_slaves_pport {
+ DECLARE_BITMAP(slaves, MLX4_MFUNC_MAX);
+};
+/* Returns a bitmap of all slaves that are assigned to port. */
+struct mlx4_slaves_pport mlx4_phys_to_slaves_pport(struct mlx4_dev *dev,
+ int port);
+
+/* Returns a bitmap of all slaves that are assigned exactly to all the */
+/* the ports that are set in crit_ports. */
+struct mlx4_slaves_pport mlx4_phys_to_slaves_pport_actv(
+ struct mlx4_dev *dev,
+ const struct mlx4_active_ports *crit_ports);
+
+/* Returns the slave's virtual port that represents the physical port. */
+int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port);
+
+int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port);
+
+int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port);
#endif /* MLX4_DEVICE_H */
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index c257e1b..022055c 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -64,4 +64,16 @@
void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port);
+static inline u64 mlx4_mac_to_u64(u8 *addr)
+{
+ u64 mac = 0;
+ int i;
+
+ for (i = 0; i < ETH_ALEN; i++) {
+ mac <<= 8;
+ mac |= addr[i];
+ }
+ return mac;
+}
+
#endif /* MLX4_DRIVER_H */
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 59f8ba8..b66e761 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -270,9 +270,14 @@
struct mlx4_wqe_ctrl_seg {
__be32 owner_opcode;
- __be16 vlan_tag;
- u8 ins_vlan;
- u8 fence_size;
+ union {
+ struct {
+ __be16 vlan_tag;
+ u8 ins_vlan;
+ u8 fence_size;
+ };
+ __be32 bf_qpn;
+ };
/*
* High 24 bits are SRC remote buffer; low 8 bits are flags:
* [7] SO (strong ordering)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 554548c..130bc8d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -38,8 +38,10 @@
#include <linux/pci.h>
#include <linux/spinlock_types.h>
#include <linux/semaphore.h>
+#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/radix-tree.h>
+
#include <linux/mlx5/device.h>
#include <linux/mlx5/doorbell.h>
@@ -227,6 +229,7 @@
* protect uuar allocation data structs
*/
struct mutex lock;
+ u32 ver;
};
struct mlx5_bf {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f28f46e..c1b7414 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -175,7 +175,7 @@
* Special vmas that are non-mergable, non-mlock()able.
* Note: mm/huge_memory.c VM_NO_THP depends on this definition.
*/
-#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP)
+#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
/*
* mapping from the currently active vm_flags protection bits (the
@@ -399,8 +399,18 @@
static inline struct page *compound_head(struct page *page)
{
- if (unlikely(PageTail(page)))
- return page->first_page;
+ if (unlikely(PageTail(page))) {
+ struct page *head = page->first_page;
+
+ /*
+ * page->first_page may be a dangling pointer to an old
+ * compound page, so recheck that it is still a tail
+ * page before returning.
+ */
+ smp_rmb();
+ if (likely(PageTail(page)))
+ return head;
+ }
return page;
}
@@ -757,7 +767,7 @@
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
{
- return xchg(&page->_last_cpupid, cpupid);
+ return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK);
}
static inline int page_cpupid_last(struct page *page)
@@ -766,7 +776,7 @@
}
static inline void page_cpupid_reset_last(struct page *page)
{
- page->_last_cpupid = -1;
+ page->_last_cpupid = -1 & LAST_CPUPID_MASK;
}
#else
static inline int page_cpupid_last(struct page *page)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5f2052c..9b61b9b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -590,10 +590,10 @@
/*
* The NUMA zonelists are doubled because we need zonelists that restrict the
- * allocations to a single node for GFP_THISNODE.
+ * allocations to a single node for __GFP_THISNODE.
*
* [0] : Zonelist with fallback
- * [1] : No fallback (GFP_THISNODE)
+ * [1] : No fallback (__GFP_THISNODE)
*/
#define MAX_ZONELISTS 2
diff --git a/include/linux/mpls.h b/include/linux/mpls.h
new file mode 100644
index 0000000..9999145
--- /dev/null
+++ b/include/linux/mpls.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_MPLS_H
+#define _LINUX_MPLS_H
+
+#include <uapi/linux/mpls.h>
+
+#endif /* _LINUX_MPLS_H */
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 1005ebf..5a09a48 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -163,4 +163,11 @@
/* changeable features with no special hardware requirements */
#define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO)
+#define NETIF_F_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \
+ NETIF_F_HW_VLAN_CTAG_RX | \
+ NETIF_F_HW_VLAN_CTAG_TX | \
+ NETIF_F_HW_VLAN_STAG_FILTER | \
+ NETIF_F_HW_VLAN_STAG_RX | \
+ NETIF_F_HW_VLAN_STAG_TX)
+
#endif /* _LINUX_NETDEV_FEATURES_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 440a02e..06287c1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -752,6 +752,9 @@
unsigned char id_len;
};
+typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
+ struct sk_buff *skb);
+
/*
* This structure defines the management hooks for network devices.
* The following hooks can be defined; unless noted otherwise, they are
@@ -783,7 +786,7 @@
* Required can not be NULL.
*
* u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
- * void *accel_priv);
+ * void *accel_priv, select_queue_fallback_t fallback);
* Called to decide which queue to when device supports multiple
* transmit queues.
*
@@ -1005,7 +1008,8 @@
struct net_device *dev);
u16 (*ndo_select_queue)(struct net_device *dev,
struct sk_buff *skb,
- void *accel_priv);
+ void *accel_priv,
+ select_queue_fallback_t fallback);
void (*ndo_change_rx_flags)(struct net_device *dev,
int flags);
void (*ndo_set_rx_mode)(struct net_device *dev);
@@ -1033,8 +1037,7 @@
#ifdef CONFIG_NET_POLL_CONTROLLER
void (*ndo_poll_controller)(struct net_device *dev);
int (*ndo_netpoll_setup)(struct net_device *dev,
- struct netpoll_info *info,
- gfp_t gfp);
+ struct netpoll_info *info);
void (*ndo_netpoll_cleanup)(struct net_device *dev);
#endif
#ifdef CONFIG_NET_RX_BUSY_POLL
@@ -1143,6 +1146,89 @@
void *priv);
};
+/**
+ * enum net_device_priv_flags - &struct net_device priv_flags
+ *
+ * These are the &struct net_device, they are only set internally
+ * by drivers and used in the kernel. These flags are invisible to
+ * userspace, this means that the order of these flags can change
+ * during any kernel release.
+ *
+ * You should have a pretty good reason to be extending these flags.
+ *
+ * @IFF_802_1Q_VLAN: 802.1Q VLAN device
+ * @IFF_EBRIDGE: Ethernet bridging device
+ * @IFF_SLAVE_INACTIVE: bonding slave not the curr. active
+ * @IFF_MASTER_8023AD: bonding master, 802.3ad
+ * @IFF_MASTER_ALB: bonding master, balance-alb
+ * @IFF_BONDING: bonding master or slave
+ * @IFF_SLAVE_NEEDARP: need ARPs for validation
+ * @IFF_ISATAP: ISATAP interface (RFC4214)
+ * @IFF_MASTER_ARPMON: bonding master, ARP mon in use
+ * @IFF_WAN_HDLC: WAN HDLC device
+ * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to
+ * release skb->dst
+ * @IFF_DONT_BRIDGE: disallow bridging this ether dev
+ * @IFF_DISABLE_NETPOLL: disable netpoll at run-time
+ * @IFF_MACVLAN_PORT: device used as macvlan port
+ * @IFF_BRIDGE_PORT: device used as bridge port
+ * @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port
+ * @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit
+ * @IFF_UNICAST_FLT: Supports unicast filtering
+ * @IFF_TEAM_PORT: device used as team port
+ * @IFF_SUPP_NOFCS: device supports sending custom FCS
+ * @IFF_LIVE_ADDR_CHANGE: device supports hardware address
+ * change when it's running
+ * @IFF_MACVLAN: Macvlan device
+ */
+enum netdev_priv_flags {
+ IFF_802_1Q_VLAN = 1<<0,
+ IFF_EBRIDGE = 1<<1,
+ IFF_SLAVE_INACTIVE = 1<<2,
+ IFF_MASTER_8023AD = 1<<3,
+ IFF_MASTER_ALB = 1<<4,
+ IFF_BONDING = 1<<5,
+ IFF_SLAVE_NEEDARP = 1<<6,
+ IFF_ISATAP = 1<<7,
+ IFF_MASTER_ARPMON = 1<<8,
+ IFF_WAN_HDLC = 1<<9,
+ IFF_XMIT_DST_RELEASE = 1<<10,
+ IFF_DONT_BRIDGE = 1<<11,
+ IFF_DISABLE_NETPOLL = 1<<12,
+ IFF_MACVLAN_PORT = 1<<13,
+ IFF_BRIDGE_PORT = 1<<14,
+ IFF_OVS_DATAPATH = 1<<15,
+ IFF_TX_SKB_SHARING = 1<<16,
+ IFF_UNICAST_FLT = 1<<17,
+ IFF_TEAM_PORT = 1<<18,
+ IFF_SUPP_NOFCS = 1<<19,
+ IFF_LIVE_ADDR_CHANGE = 1<<20,
+ IFF_MACVLAN = 1<<21,
+};
+
+#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN
+#define IFF_EBRIDGE IFF_EBRIDGE
+#define IFF_SLAVE_INACTIVE IFF_SLAVE_INACTIVE
+#define IFF_MASTER_8023AD IFF_MASTER_8023AD
+#define IFF_MASTER_ALB IFF_MASTER_ALB
+#define IFF_BONDING IFF_BONDING
+#define IFF_SLAVE_NEEDARP IFF_SLAVE_NEEDARP
+#define IFF_ISATAP IFF_ISATAP
+#define IFF_MASTER_ARPMON IFF_MASTER_ARPMON
+#define IFF_WAN_HDLC IFF_WAN_HDLC
+#define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE
+#define IFF_DONT_BRIDGE IFF_DONT_BRIDGE
+#define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL
+#define IFF_MACVLAN_PORT IFF_MACVLAN_PORT
+#define IFF_BRIDGE_PORT IFF_BRIDGE_PORT
+#define IFF_OVS_DATAPATH IFF_OVS_DATAPATH
+#define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING
+#define IFF_UNICAST_FLT IFF_UNICAST_FLT
+#define IFF_TEAM_PORT IFF_TEAM_PORT
+#define IFF_SUPP_NOFCS IFF_SUPP_NOFCS
+#define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE
+#define IFF_MACVLAN IFF_MACVLAN
+
/*
* The DEVICE structure.
* Actually, this whole structure is a big mistake. It mixes I/O
@@ -1224,9 +1310,10 @@
int iflink;
struct net_device_stats stats;
- atomic_long_t rx_dropped; /* dropped packets by core network
- * Do not use this in drivers.
- */
+
+ /* dropped packets by core network, Do not use this in drivers */
+ atomic_long_t rx_dropped;
+ atomic_long_t tx_dropped;
#ifdef CONFIG_WIRELESS_EXT
/* List of functions to handle Wireless Extensions (instead of ioctl).
@@ -1275,6 +1362,10 @@
* that share the same link
* layer address
*/
+ unsigned short dev_port; /* Used to differentiate
+ * devices that share the same
+ * function
+ */
spinlock_t addr_list_lock;
struct netdev_hw_addr_list uc; /* Unicast mac addresses */
struct netdev_hw_addr_list mc; /* Multicast mac addresses */
@@ -1312,13 +1403,7 @@
/*
* Cache lines mostly used on receive path (including eth_type_trans())
*/
- unsigned long last_rx; /* Time of last Rx
- * This should not be set in
- * drivers, unless really needed,
- * because network stack (bonding)
- * use it if/when necessary, to
- * avoid dirtying this cache line.
- */
+ unsigned long last_rx; /* Time of last Rx */
/* Interface address info used in eth_type_trans() */
unsigned char *dev_addr; /* hw address, (before bcast
@@ -1551,7 +1636,6 @@
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
struct sk_buff *skb,
void *accel_priv);
-u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb);
/*
* Net namespace inlines
@@ -1726,6 +1810,20 @@
struct u64_stats_sync syncp;
};
+#define netdev_alloc_pcpu_stats(type) \
+({ \
+ typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \
+ if (pcpu_stats) { \
+ int i; \
+ for_each_possible_cpu(i) { \
+ typeof(type) *stat; \
+ stat = per_cpu_ptr(pcpu_stats, i); \
+ u64_stats_init(&stat->syncp); \
+ } \
+ } \
+ pcpu_stats; \
+})
+
#include <linux/notifier.h>
/* netdevice notifier chain. Please remember to update the rtnetlink
@@ -1881,9 +1979,6 @@
struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
int netdev_get_name(struct net *net, char *name, int ifindex);
int dev_restart(struct net_device *dev);
-#ifdef CONFIG_NETPOLL_TRAP
-int netpoll_trap(void);
-#endif
int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb);
static inline unsigned int skb_gro_offset(const struct sk_buff *skb)
@@ -2088,12 +2183,6 @@
static inline void netif_tx_wake_queue(struct netdev_queue *dev_queue)
{
-#ifdef CONFIG_NETPOLL_TRAP
- if (netpoll_trap()) {
- netif_tx_start_queue(dev_queue);
- return;
- }
-#endif
if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state))
__netif_schedule(dev_queue->qdisc);
}
@@ -2276,6 +2365,26 @@
}
/**
+ * netdev_cap_txqueue - check if selected tx queue exceeds device queues
+ * @dev: network device
+ * @queue_index: given tx queue index
+ *
+ * Returns 0 if given tx queue index >= number of device tx queues,
+ * otherwise returns the originally passed tx queue index.
+ */
+static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index)
+{
+ if (unlikely(queue_index >= dev->real_num_tx_queues)) {
+ net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
+ dev->name, queue_index,
+ dev->real_num_tx_queues);
+ return 0;
+ }
+
+ return queue_index;
+}
+
+/**
* netif_running - test if up
* @dev: network device
*
@@ -2317,10 +2426,6 @@
static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
-#ifdef CONFIG_NETPOLL_TRAP
- if (netpoll_trap())
- return;
-#endif
netif_tx_stop_queue(txq);
}
@@ -2355,10 +2460,6 @@
static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
{
struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
-#ifdef CONFIG_NETPOLL_TRAP
- if (netpoll_trap())
- return;
-#endif
if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state))
__netif_schedule(txq->qdisc);
}
@@ -2808,6 +2909,11 @@
} \
}
+#define HARD_TX_TRYLOCK(dev, txq) \
+ (((dev->features & NETIF_F_LLTX) == 0) ? \
+ __netif_tx_trylock(txq) : \
+ true )
+
#define HARD_TX_UNLOCK(dev, txq) { \
if ((dev->features & NETIF_F_LLTX) == 0) { \
__netif_tx_unlock(txq); \
@@ -2991,7 +3097,7 @@
{
return __skb_gso_segment(skb, features, true);
}
-__be16 skb_network_protocol(struct sk_buff *skb);
+__be16 skb_network_protocol(struct sk_buff *skb, int *depth);
static inline bool can_checksum_protocol(netdev_features_t features,
__be16 protocol)
@@ -3068,7 +3174,12 @@
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
struct net_device *dev);
-netdev_features_t netif_skb_features(struct sk_buff *skb);
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+ const struct net_device *dev);
+static inline netdev_features_t netif_skb_features(struct sk_buff *skb)
+{
+ return netif_skb_dev_features(skb, skb->dev);
+}
static inline bool net_gso_ok(netdev_features_t features, int gso_type)
{
diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 0c7d01e..96afc29 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -39,11 +39,13 @@
IPSET_TYPE_NAME = (1 << IPSET_TYPE_NAME_FLAG),
IPSET_TYPE_IFACE_FLAG = 5,
IPSET_TYPE_IFACE = (1 << IPSET_TYPE_IFACE_FLAG),
- IPSET_TYPE_NOMATCH_FLAG = 6,
+ IPSET_TYPE_MARK_FLAG = 6,
+ IPSET_TYPE_MARK = (1 << IPSET_TYPE_MARK_FLAG),
+ IPSET_TYPE_NOMATCH_FLAG = 7,
IPSET_TYPE_NOMATCH = (1 << IPSET_TYPE_NOMATCH_FLAG),
/* Strictly speaking not a feature, but a flag for dumping:
* this settype must be dumped last */
- IPSET_DUMP_LAST_FLAG = 7,
+ IPSET_DUMP_LAST_FLAG = 8,
IPSET_DUMP_LAST = (1 << IPSET_DUMP_LAST_FLAG),
};
@@ -63,6 +65,7 @@
#define SET_WITH_TIMEOUT(s) ((s)->extensions & IPSET_EXT_TIMEOUT)
#define SET_WITH_COUNTER(s) ((s)->extensions & IPSET_EXT_COUNTER)
#define SET_WITH_COMMENT(s) ((s)->extensions & IPSET_EXT_COMMENT)
+#define SET_WITH_FORCEADD(s) ((s)->flags & IPSET_CREATE_FLAG_FORCEADD)
/* Extension id, in size order */
enum ip_set_ext_id {
@@ -171,8 +174,6 @@
char name[IPSET_MAXNAMELEN];
/* Protocol version */
u8 protocol;
- /* Set features to control swapping */
- u8 features;
/* Set type dimension */
u8 dimension;
/*
@@ -182,6 +183,8 @@
u8 family;
/* Type revisions */
u8 revision_min, revision_max;
+ /* Set features to control swapping */
+ u16 features;
/* Create set */
int (*create)(struct net *net, struct ip_set *set,
@@ -217,6 +220,8 @@
u8 revision;
/* Extensions */
u8 extensions;
+ /* Create flags */
+ u8 flags;
/* Default timeout value, if enabled */
u32 timeout;
/* Element data size */
@@ -251,6 +256,8 @@
cadt_flags |= IPSET_FLAG_WITH_COUNTERS;
if (SET_WITH_COMMENT(set))
cadt_flags |= IPSET_FLAG_WITH_COMMENT;
+ if (SET_WITH_FORCEADD(set))
+ cadt_flags |= IPSET_FLAG_WITH_FORCEADD;
if (!cadt_flags)
return 0;
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 28c7436..e955d47 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -44,6 +44,27 @@
void nfnl_lock(__u8 subsys_id);
void nfnl_unlock(__u8 subsys_id);
+#ifdef CONFIG_PROVE_LOCKING
+int lockdep_nfnl_is_held(__u8 subsys_id);
+#else
+static inline int lockdep_nfnl_is_held(__u8 subsys_id)
+{
+ return 1;
+}
+#endif /* CONFIG_PROVE_LOCKING */
+
+/*
+ * nfnl_dereference - fetch RCU pointer when updates are prevented by subsys mutex
+ *
+ * @p: The pointer to read, prior to dereferencing
+ * @ss: The nfnetlink subsystem ID
+ *
+ * Return the value of the specified RCU-protected pointer, but omit
+ * both the smp_read_barrier_depends() and the ACCESS_ONCE(), because
+ * caller holds the NFNL subsystem mutex.
+ */
+#define nfnl_dereference(p, ss) \
+ rcu_dereference_protected(p, lockdep_nfnl_is_held(ss))
#define MODULE_ALIAS_NFNL_SUBSYS(subsys) \
MODULE_ALIAS("nfnetlink-subsys-" __stringify(subsys))
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index fbfdb9d..b25ee9f 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -24,27 +24,20 @@
struct net_device *dev;
char dev_name[IFNAMSIZ];
const char *name;
- void (*rx_skb_hook)(struct netpoll *np, int source, struct sk_buff *skb,
- int offset, int len);
union inet_addr local_ip, remote_ip;
bool ipv6;
u16 local_port, remote_port;
u8 remote_mac[ETH_ALEN];
- struct list_head rx; /* rx_np list element */
struct work_struct cleanup_work;
};
struct netpoll_info {
atomic_t refcnt;
- unsigned long rx_flags;
- spinlock_t rx_lock;
struct semaphore dev_lock;
- struct list_head rx_np; /* netpolls that registered an rx_skb_hook */
- struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */
struct sk_buff_head txq;
struct delayed_work tx_work;
@@ -54,24 +47,21 @@
};
#ifdef CONFIG_NETPOLL
-extern void netpoll_rx_disable(struct net_device *dev);
-extern void netpoll_rx_enable(struct net_device *dev);
+extern void netpoll_poll_disable(struct net_device *dev);
+extern void netpoll_poll_enable(struct net_device *dev);
#else
-static inline void netpoll_rx_disable(struct net_device *dev) { return; }
-static inline void netpoll_rx_enable(struct net_device *dev) { return; }
+static inline void netpoll_poll_disable(struct net_device *dev) { return; }
+static inline void netpoll_poll_enable(struct net_device *dev) { return; }
#endif
void netpoll_send_udp(struct netpoll *np, const char *msg, int len);
void netpoll_print_options(struct netpoll *np);
int netpoll_parse_options(struct netpoll *np, char *opt);
-int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp);
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev);
int netpoll_setup(struct netpoll *np);
-int netpoll_trap(void);
-void netpoll_set_trap(int trap);
void __netpoll_cleanup(struct netpoll *np);
void __netpoll_free_async(struct netpoll *np);
void netpoll_cleanup(struct netpoll *np);
-int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo);
void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
struct net_device *dev);
static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
@@ -82,46 +72,7 @@
local_irq_restore(flags);
}
-
-
#ifdef CONFIG_NETPOLL
-static inline bool netpoll_rx_on(struct sk_buff *skb)
-{
- struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo);
-
- return npinfo && (!list_empty(&npinfo->rx_np) || npinfo->rx_flags);
-}
-
-static inline bool netpoll_rx(struct sk_buff *skb)
-{
- struct netpoll_info *npinfo;
- unsigned long flags;
- bool ret = false;
-
- local_irq_save(flags);
-
- if (!netpoll_rx_on(skb))
- goto out;
-
- npinfo = rcu_dereference_bh(skb->dev->npinfo);
- spin_lock(&npinfo->rx_lock);
- /* check rx_flags again with the lock held */
- if (npinfo->rx_flags && __netpoll_rx(skb, npinfo))
- ret = true;
- spin_unlock(&npinfo->rx_lock);
-
-out:
- local_irq_restore(flags);
- return ret;
-}
-
-static inline int netpoll_receive_skb(struct sk_buff *skb)
-{
- if (!list_empty(&skb->dev->napi_list))
- return netpoll_rx(skb);
- return 0;
-}
-
static inline void *netpoll_poll_lock(struct napi_struct *napi)
{
struct net_device *dev = napi->dev;
@@ -150,18 +101,6 @@
}
#else
-static inline bool netpoll_rx(struct sk_buff *skb)
-{
- return false;
-}
-static inline bool netpoll_rx_on(struct sk_buff *skb)
-{
- return false;
-}
-static inline int netpoll_receive_skb(struct sk_buff *skb)
-{
- return 0;
-}
static inline void *netpoll_poll_lock(struct napi_struct *napi)
{
return NULL;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index b2fb167..5624e4e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -467,9 +467,14 @@
};
struct nfs_release_lockowner_args {
+ struct nfs4_sequence_args seq_args;
struct nfs_lowner lock_owner;
};
+struct nfs_release_lockowner_res {
+ struct nfs4_sequence_res seq_res;
+};
+
struct nfs4_delegreturnargs {
struct nfs4_sequence_args seq_args;
const struct nfs_fh *fhandle;
diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h
index fd4f2d1..e110b8c 100644
--- a/include/linux/nl802154.h
+++ b/include/linux/nl802154.h
@@ -70,6 +70,16 @@
IEEE802154_ATTR_PHY_NAME,
IEEE802154_ATTR_DEV_TYPE,
+ IEEE802154_ATTR_TXPOWER,
+ IEEE802154_ATTR_LBT_ENABLED,
+ IEEE802154_ATTR_CCA_MODE,
+ IEEE802154_ATTR_CCA_ED_LEVEL,
+ IEEE802154_ATTR_CSMA_RETRIES,
+ IEEE802154_ATTR_CSMA_MIN_BE,
+ IEEE802154_ATTR_CSMA_MAX_BE,
+
+ IEEE802154_ATTR_FRAME_RETRIES,
+
__IEEE802154_ATTR_MAX,
};
@@ -122,6 +132,8 @@
IEEE802154_ADD_IFACE,
IEEE802154_DEL_IFACE,
+ IEEE802154_SET_PHYPARAMS,
+
__IEEE802154_CMD_MAX,
};
diff --git a/include/linux/of.h b/include/linux/of.h
index 70c64ba..435cb99 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -169,35 +169,15 @@
extern struct device_node *of_find_node_by_name(struct device_node *from,
const char *name);
-#define for_each_node_by_name(dn, name) \
- for (dn = of_find_node_by_name(NULL, name); dn; \
- dn = of_find_node_by_name(dn, name))
extern struct device_node *of_find_node_by_type(struct device_node *from,
const char *type);
-#define for_each_node_by_type(dn, type) \
- for (dn = of_find_node_by_type(NULL, type); dn; \
- dn = of_find_node_by_type(dn, type))
extern struct device_node *of_find_compatible_node(struct device_node *from,
const char *type, const char *compat);
-#define for_each_compatible_node(dn, type, compatible) \
- for (dn = of_find_compatible_node(NULL, type, compatible); dn; \
- dn = of_find_compatible_node(dn, type, compatible))
extern struct device_node *of_find_matching_node_and_match(
struct device_node *from,
const struct of_device_id *matches,
const struct of_device_id **match);
-static inline struct device_node *of_find_matching_node(
- struct device_node *from,
- const struct of_device_id *matches)
-{
- return of_find_matching_node_and_match(from, matches, NULL);
-}
-#define for_each_matching_node(dn, matches) \
- for (dn = of_find_matching_node(NULL, matches); dn; \
- dn = of_find_matching_node(dn, matches))
-#define for_each_matching_node_and_match(dn, matches, match) \
- for (dn = of_find_matching_node_and_match(NULL, matches, match); \
- dn; dn = of_find_matching_node_and_match(dn, matches, match))
+
extern struct device_node *of_find_node_by_path(const char *path);
extern struct device_node *of_find_node_by_phandle(phandle handle);
extern struct device_node *of_get_parent(const struct device_node *node);
@@ -209,43 +189,11 @@
extern struct device_node *of_get_child_by_name(const struct device_node *node,
const char *name);
-#define for_each_child_of_node(parent, child) \
- for (child = of_get_next_child(parent, NULL); child != NULL; \
- child = of_get_next_child(parent, child))
-
-#define for_each_available_child_of_node(parent, child) \
- for (child = of_get_next_available_child(parent, NULL); child != NULL; \
- child = of_get_next_available_child(parent, child))
-
-static inline int of_get_child_count(const struct device_node *np)
-{
- struct device_node *child;
- int num = 0;
-
- for_each_child_of_node(np, child)
- num++;
-
- return num;
-}
-
-static inline int of_get_available_child_count(const struct device_node *np)
-{
- struct device_node *child;
- int num = 0;
-
- for_each_available_child_of_node(np, child)
- num++;
-
- return num;
-}
/* cache lookup */
extern struct device_node *of_find_next_cache_node(const struct device_node *);
extern struct device_node *of_find_node_with_property(
struct device_node *from, const char *prop_name);
-#define for_each_node_with_property(dn, prop_name) \
- for (dn = of_find_node_with_property(NULL, prop_name); dn; \
- dn = of_find_node_with_property(dn, prop_name))
extern struct property *of_find_property(const struct device_node *np,
const char *name,
@@ -367,27 +315,48 @@
return NULL;
}
+static inline struct device_node *of_find_node_by_type(struct device_node *from,
+ const char *type)
+{
+ return NULL;
+}
+
+static inline struct device_node *of_find_matching_node_and_match(
+ struct device_node *from,
+ const struct of_device_id *matches,
+ const struct of_device_id **match)
+{
+ return NULL;
+}
+
static inline struct device_node *of_get_parent(const struct device_node *node)
{
return NULL;
}
+static inline struct device_node *of_get_next_child(
+ const struct device_node *node, struct device_node *prev)
+{
+ return NULL;
+}
+
+static inline struct device_node *of_get_next_available_child(
+ const struct device_node *node, struct device_node *prev)
+{
+ return NULL;
+}
+
+static inline struct device_node *of_find_node_with_property(
+ struct device_node *from, const char *prop_name)
+{
+ return NULL;
+}
+
static inline bool of_have_populated_dt(void)
{
return false;
}
-/* Kill an unused variable warning on a device_node pointer */
-static inline void __of_use_dn(const struct device_node *np)
-{
-}
-
-#define for_each_child_of_node(parent, child) \
- while (__of_use_dn(parent), __of_use_dn(child), 0)
-
-#define for_each_available_child_of_node(parent, child) \
- while (0)
-
static inline struct device_node *of_get_child_by_name(
const struct device_node *node,
const char *name)
@@ -395,16 +364,6 @@
return NULL;
}
-static inline int of_get_child_count(const struct device_node *np)
-{
- return 0;
-}
-
-static inline int of_get_available_child_count(const struct device_node *np)
-{
- return 0;
-}
-
static inline int of_device_is_compatible(const struct device_node *device,
const char *name)
{
@@ -569,6 +528,13 @@
static inline int of_node_to_nid(struct device_node *device) { return 0; }
#endif
+static inline struct device_node *of_find_matching_node(
+ struct device_node *from,
+ const struct of_device_id *matches)
+{
+ return of_find_matching_node_and_match(from, matches, NULL);
+}
+
/**
* of_property_read_bool - Findfrom a property
* @np: device node from which the property value is to be read.
@@ -618,6 +584,55 @@
s; \
s = of_prop_next_string(prop, s))
+#define for_each_node_by_name(dn, name) \
+ for (dn = of_find_node_by_name(NULL, name); dn; \
+ dn = of_find_node_by_name(dn, name))
+#define for_each_node_by_type(dn, type) \
+ for (dn = of_find_node_by_type(NULL, type); dn; \
+ dn = of_find_node_by_type(dn, type))
+#define for_each_compatible_node(dn, type, compatible) \
+ for (dn = of_find_compatible_node(NULL, type, compatible); dn; \
+ dn = of_find_compatible_node(dn, type, compatible))
+#define for_each_matching_node(dn, matches) \
+ for (dn = of_find_matching_node(NULL, matches); dn; \
+ dn = of_find_matching_node(dn, matches))
+#define for_each_matching_node_and_match(dn, matches, match) \
+ for (dn = of_find_matching_node_and_match(NULL, matches, match); \
+ dn; dn = of_find_matching_node_and_match(dn, matches, match))
+
+#define for_each_child_of_node(parent, child) \
+ for (child = of_get_next_child(parent, NULL); child != NULL; \
+ child = of_get_next_child(parent, child))
+#define for_each_available_child_of_node(parent, child) \
+ for (child = of_get_next_available_child(parent, NULL); child != NULL; \
+ child = of_get_next_available_child(parent, child))
+
+#define for_each_node_with_property(dn, prop_name) \
+ for (dn = of_find_node_with_property(NULL, prop_name); dn; \
+ dn = of_find_node_with_property(dn, prop_name))
+
+static inline int of_get_child_count(const struct device_node *np)
+{
+ struct device_node *child;
+ int num = 0;
+
+ for_each_child_of_node(np, child)
+ num++;
+
+ return num;
+}
+
+static inline int of_get_available_child_count(const struct device_node *np)
+{
+ struct device_node *child;
+ int num = 0;
+
+ for_each_available_child_of_node(np, child)
+ num++;
+
+ return num;
+}
+
#if defined(CONFIG_PROC_FS) && defined(CONFIG_PROC_DEVICETREE)
extern void proc_device_tree_add_node(struct device_node *, struct proc_dir_entry *);
extern void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop);
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 8d7dd67..ef37021 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -78,11 +78,13 @@
static inline void of_device_node_put(struct device *dev) { }
-static inline const struct of_device_id *of_match_device(
+static inline const struct of_device_id *__of_match_device(
const struct of_device_id *matches, const struct device *dev)
{
return NULL;
}
+#define of_match_device(matches, dev) \
+ __of_match_device(of_match_ptr(matches), (dev))
static inline struct device_node *of_cpu_device_node_get(int cpu)
{
diff --git a/include/linux/pci.h b/include/linux/pci.h
index fb57c89..33aa2ca 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1169,8 +1169,23 @@
void pci_restore_msi_state(struct pci_dev *dev);
int pci_msi_enabled(void);
int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec);
+static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec)
+{
+ int rc = pci_enable_msi_range(dev, nvec, nvec);
+ if (rc < 0)
+ return rc;
+ return 0;
+}
int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
int minvec, int maxvec);
+static inline int pci_enable_msix_exact(struct pci_dev *dev,
+ struct msix_entry *entries, int nvec)
+{
+ int rc = pci_enable_msix_range(dev, entries, nvec, nvec);
+ if (rc < 0)
+ return rc;
+ return 0;
+}
#else
static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; }
static inline int pci_enable_msi_block(struct pci_dev *dev, int nvec)
@@ -1189,9 +1204,14 @@
static inline int pci_enable_msi_range(struct pci_dev *dev, int minvec,
int maxvec)
{ return -ENOSYS; }
+static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec)
+{ return -ENOSYS; }
static inline int pci_enable_msix_range(struct pci_dev *dev,
struct msix_entry *entries, int minvec, int maxvec)
{ return -ENOSYS; }
+static inline int pci_enable_msix_exact(struct pci_dev *dev,
+ struct msix_entry *entries, int nvec)
+{ return -ENOSYS; }
#endif
#ifdef CONFIG_PCIEPORTBUS
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 565188c..24126c4 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -74,8 +74,53 @@
PHY_INTERFACE_MODE_RTBI,
PHY_INTERFACE_MODE_SMII,
PHY_INTERFACE_MODE_XGMII,
+ PHY_INTERFACE_MODE_MOCA,
+ PHY_INTERFACE_MODE_MAX,
} phy_interface_t;
+/**
+ * It maps 'enum phy_interface_t' found in include/linux/phy.h
+ * into the device tree binding of 'phy-mode', so that Ethernet
+ * device driver can get phy interface from device tree.
+ */
+static inline const char *phy_modes(phy_interface_t interface)
+{
+ switch (interface) {
+ case PHY_INTERFACE_MODE_NA:
+ return "";
+ case PHY_INTERFACE_MODE_MII:
+ return "mii";
+ case PHY_INTERFACE_MODE_GMII:
+ return "gmii";
+ case PHY_INTERFACE_MODE_SGMII:
+ return "sgmii";
+ case PHY_INTERFACE_MODE_TBI:
+ return "tbi";
+ case PHY_INTERFACE_MODE_REVMII:
+ return "rev-mii";
+ case PHY_INTERFACE_MODE_RMII:
+ return "rmii";
+ case PHY_INTERFACE_MODE_RGMII:
+ return "rgmii";
+ case PHY_INTERFACE_MODE_RGMII_ID:
+ return "rgmii-id";
+ case PHY_INTERFACE_MODE_RGMII_RXID:
+ return "rgmii-rxid";
+ case PHY_INTERFACE_MODE_RGMII_TXID:
+ return "rgmii-txid";
+ case PHY_INTERFACE_MODE_RTBI:
+ return "rtbi";
+ case PHY_INTERFACE_MODE_SMII:
+ return "smii";
+ case PHY_INTERFACE_MODE_XGMII:
+ return "xgmii";
+ case PHY_INTERFACE_MODE_MOCA:
+ return "moca";
+ default:
+ return "unknown";
+ }
+}
+
#define PHY_INIT_TIMEOUT 100000
#define PHY_STATE_TIME 1
@@ -308,6 +353,7 @@
struct phy_c45_device_ids c45_ids;
bool is_c45;
bool is_internal;
+ bool has_fixups;
enum phy_state state;
@@ -394,6 +440,11 @@
u32 flags;
/*
+ * Called to issue a PHY software reset
+ */
+ int (*soft_reset)(struct phy_device *phydev);
+
+ /*
* Called to initialize the PHY,
* including after a reset
*/
@@ -417,6 +468,9 @@
*/
int (*config_aneg)(struct phy_device *phydev);
+ /* Determines the auto negotiation result */
+ int (*aneg_done)(struct phy_device *phydev);
+
/* Determines the negotiated speed and duplex */
int (*read_status)(struct phy_device *phydev);
@@ -612,10 +666,12 @@
int genphy_setup_forced(struct phy_device *phydev);
int genphy_restart_aneg(struct phy_device *phydev);
int genphy_config_aneg(struct phy_device *phydev);
+int genphy_aneg_done(struct phy_device *phydev);
int genphy_update_link(struct phy_device *phydev);
int genphy_read_status(struct phy_device *phydev);
int genphy_suspend(struct phy_device *phydev);
int genphy_resume(struct phy_device *phydev);
+int genphy_soft_reset(struct phy_device *phydev);
void phy_driver_unregister(struct phy_driver *drv);
void phy_drivers_unregister(struct phy_driver *drv, int n);
int phy_driver_register(struct phy_driver *new_driver);
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index e273e5a..3f83459 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -146,7 +146,9 @@
phy->attrs.bus_width = bus_width;
}
struct phy *phy_get(struct device *dev, const char *string);
+struct phy *phy_optional_get(struct device *dev, const char *string);
struct phy *devm_phy_get(struct device *dev, const char *string);
+struct phy *devm_phy_optional_get(struct device *dev, const char *string);
void phy_put(struct phy *phy);
void devm_phy_put(struct device *dev, struct phy *phy);
struct phy *of_phy_simple_xlate(struct device *dev,
@@ -232,11 +234,23 @@
return ERR_PTR(-ENOSYS);
}
+static inline struct phy *phy_optional_get(struct device *dev,
+ const char *string)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
static inline struct phy *devm_phy_get(struct device *dev, const char *string)
{
return ERR_PTR(-ENOSYS);
}
+static inline struct phy *devm_phy_optional_get(struct device *dev,
+ const char *string)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
static inline void phy_put(struct phy *phy)
{
}
diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index 1dc420b..6d3b0a2 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -27,11 +27,7 @@
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/filter.h>
-#ifdef __KERNEL__
#include <linux/in.h>
-#else
-#include <netinet/in.h>
-#endif
#define PTP_CLASS_NONE 0x00 /* not a PTP event message */
#define PTP_CLASS_V1 0x01 /* protocol version 1 */
@@ -84,14 +80,6 @@
#define OP_RETA (BPF_RET | BPF_A)
#define OP_RETK (BPF_RET | BPF_K)
-static inline int ptp_filter_init(struct sock_filter *f, int len)
-{
- if (OP_LDH == f[0].code)
- return sk_chk_filter(f, len);
- else
- return 0;
-}
-
#define PTP_FILTER \
{OP_LDH, 0, 0, OFF_ETYPE }, /* */ \
{OP_JEQ, 0, 12, ETH_P_IP }, /* f goto L20 */ \
@@ -137,4 +125,6 @@
{OP_RETA, 0, 0, 0 }, /* */ \
/*L6x*/ {OP_RETK, 0, 0, PTP_CLASS_NONE },
+unsigned int ptp_classify_raw(const struct sk_buff *skb);
+
#endif
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index 38a9935..0d8ff3f 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -49,7 +49,11 @@
* @n_alarm: The number of programmable alarms.
* @n_ext_ts: The number of external time stamp channels.
* @n_per_out: The number of programmable periodic signals.
+ * @n_pins: The number of programmable pins.
* @pps: Indicates whether the clock supports a PPS callback.
+ * @pin_config: Array of length 'n_pins'. If the number of
+ * programmable pins is nonzero, then drivers must
+ * allocate and initialize this array.
*
* clock operations
*
@@ -70,6 +74,18 @@
* parameter request: Desired resource to enable or disable.
* parameter on: Caller passes one to enable or zero to disable.
*
+ * @verify: Confirm that a pin can perform a given function. The PTP
+ * Hardware Clock subsystem maintains the 'pin_config'
+ * array on behalf of the drivers, but the PHC subsystem
+ * assumes that every pin can perform every function. This
+ * hook gives drivers a way of telling the core about
+ * limitations on specific pins. This function must return
+ * zero if the function can be assigned to this pin, and
+ * nonzero otherwise.
+ * parameter pin: index of the pin in question.
+ * parameter func: the desired function to use.
+ * parameter chan: the function channel index to use.
+ *
* Drivers should embed their ptp_clock_info within a private
* structure, obtaining a reference to it using container_of().
*
@@ -83,13 +99,17 @@
int n_alarm;
int n_ext_ts;
int n_per_out;
+ int n_pins;
int pps;
+ struct ptp_pin_desc *pin_config;
int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta);
int (*adjtime)(struct ptp_clock_info *ptp, s64 delta);
int (*gettime)(struct ptp_clock_info *ptp, struct timespec *ts);
int (*settime)(struct ptp_clock_info *ptp, const struct timespec *ts);
int (*enable)(struct ptp_clock_info *ptp,
struct ptp_clock_request *request, int on);
+ int (*verify)(struct ptp_clock_info *ptp, unsigned int pin,
+ enum ptp_pin_function func, unsigned int chan);
};
struct ptp_clock;
@@ -156,4 +176,17 @@
extern int ptp_clock_index(struct ptp_clock *ptp);
+/**
+ * ptp_find_pin() - obtain the pin index of a given auxiliary function
+ *
+ * @ptp: The clock obtained from ptp_clock_register().
+ * @func: One of the ptp_pin_function enumerated values.
+ * @chan: The particular functional channel to find.
+ * Return: Pin index in the range of zero to ptp_clock_caps.n_pins - 1,
+ * or -1 if the auxiliary function cannot be found.
+ */
+
+int ptp_find_pin(struct ptp_clock *ptp,
+ enum ptp_pin_function func, unsigned int chan);
+
#endif
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 1da693d..b66c211 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -250,8 +250,7 @@
int (*rmap_one)(struct page *page, struct vm_area_struct *vma,
unsigned long addr, void *arg);
int (*done)(struct page *page);
- int (*file_nonlinear)(struct page *, struct address_space *,
- struct vm_area_struct *vma);
+ int (*file_nonlinear)(struct page *, struct address_space *, void *arg);
struct anon_vma *(*anon_lock)(struct page *page);
bool (*invalid_vma)(struct vm_area_struct *vma, void *arg);
};
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 6f19cfd..4054b09 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -76,7 +76,6 @@
#ifdef CONFIG_SECCOMP_FILTER
extern void put_seccomp_filter(struct task_struct *tsk);
extern void get_seccomp_filter(struct task_struct *tsk);
-extern u32 seccomp_bpf_load(int off);
#else /* CONFIG_SECCOMP_FILTER */
static inline void put_seccomp_filter(struct task_struct *tsk)
{
diff --git a/include/linux/security.h b/include/linux/security.h
index 5623a7f..2fc42d1 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1040,6 +1040,7 @@
* Allocate a security structure to the xp->security field; the security
* field is initialized to NULL when the xfrm_policy is allocated.
* Return 0 if operation was successful (memory to allocate, legal context)
+ * @gfp is to specify the context for the allocation
* @xfrm_policy_clone_security:
* @old_ctx contains an existing xfrm_sec_ctx.
* @new_ctxp contains a new xfrm_sec_ctx being cloned from old.
@@ -1683,7 +1684,7 @@
#ifdef CONFIG_SECURITY_NETWORK_XFRM
int (*xfrm_policy_alloc_security) (struct xfrm_sec_ctx **ctxp,
- struct xfrm_user_sec_ctx *sec_ctx);
+ struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp);
int (*xfrm_policy_clone_security) (struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctx);
void (*xfrm_policy_free_security) (struct xfrm_sec_ctx *ctx);
int (*xfrm_policy_delete_security) (struct xfrm_sec_ctx *ctx);
@@ -2859,7 +2860,8 @@
#ifdef CONFIG_SECURITY_NETWORK_XFRM
-int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx);
+int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
+ struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp);
int security_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctxp);
void security_xfrm_policy_free(struct xfrm_sec_ctx *ctx);
int security_xfrm_policy_delete(struct xfrm_sec_ctx *ctx);
@@ -2877,7 +2879,9 @@
#else /* CONFIG_SECURITY_NETWORK_XFRM */
-static inline int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx)
+static inline int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
+ struct xfrm_user_sec_ctx *sec_ctx,
+ gfp_t gfp)
{
return 0;
}
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f589c9af..18ef022 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -32,6 +32,7 @@
#include <linux/hrtimer.h>
#include <linux/dma-mapping.h>
#include <linux/netdev_features.h>
+#include <linux/sched.h>
#include <net/flow_keys.h>
/* A. Checksumming of received packets by device.
@@ -356,11 +357,62 @@
typedef unsigned char *sk_buff_data_t;
#endif
+/**
+ * struct skb_mstamp - multi resolution time stamps
+ * @stamp_us: timestamp in us resolution
+ * @stamp_jiffies: timestamp in jiffies
+ */
+struct skb_mstamp {
+ union {
+ u64 v64;
+ struct {
+ u32 stamp_us;
+ u32 stamp_jiffies;
+ };
+ };
+};
+
+/**
+ * skb_mstamp_get - get current timestamp
+ * @cl: place to store timestamps
+ */
+static inline void skb_mstamp_get(struct skb_mstamp *cl)
+{
+ u64 val = local_clock();
+
+ do_div(val, NSEC_PER_USEC);
+ cl->stamp_us = (u32)val;
+ cl->stamp_jiffies = (u32)jiffies;
+}
+
+/**
+ * skb_mstamp_delta - compute the difference in usec between two skb_mstamp
+ * @t1: pointer to newest sample
+ * @t0: pointer to oldest sample
+ */
+static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1,
+ const struct skb_mstamp *t0)
+{
+ s32 delta_us = t1->stamp_us - t0->stamp_us;
+ u32 delta_jiffies = t1->stamp_jiffies - t0->stamp_jiffies;
+
+ /* If delta_us is negative, this might be because interval is too big,
+ * or local_clock() drift is too big : fallback using jiffies.
+ */
+ if (delta_us <= 0 ||
+ delta_jiffies >= (INT_MAX / (USEC_PER_SEC / HZ)))
+
+ delta_us = jiffies_to_usecs(delta_jiffies);
+
+ return delta_us;
+}
+
+
/**
* struct sk_buff - socket buffer
* @next: Next buffer in list
* @prev: Previous buffer in list
- * @tstamp: Time we arrived
+ * @tstamp: Time we arrived/left
* @sk: Socket we are owned by
* @dev: Device we arrived on/are leaving by
* @cb: Control buffer. Free for use by every layer. Put private vars here
@@ -392,11 +444,11 @@
* @skb_iif: ifindex of device we arrived on
* @tc_index: Traffic control index
* @tc_verd: traffic control verdict
- * @rxhash: the packet hash computed on receive
+ * @hash: the packet hash
* @queue_mapping: Queue mapping for multiqueue devices
* @ndisc_nodetype: router type (from link layer)
* @ooo_okay: allow the mapping of a socket to a queue to be changed
- * @l4_rxhash: indicate rxhash is a canonical 4-tuple hash over transport
+ * @l4_hash: indicate hash is a canonical 4-tuple hash over transport
* ports.
* @wifi_acked_valid: wifi_acked was set
* @wifi_acked: whether frame was acked on wifi or not
@@ -429,7 +481,10 @@
struct sk_buff *next;
struct sk_buff *prev;
- ktime_t tstamp;
+ union {
+ ktime_t tstamp;
+ struct skb_mstamp skb_mstamp;
+ };
struct sock *sk;
struct net_device *dev;
@@ -482,7 +537,7 @@
int skb_iif;
- __u32 rxhash;
+ __u32 hash;
__be16 vlan_proto;
__u16 vlan_tci;
@@ -501,7 +556,7 @@
#endif
__u8 pfmemalloc:1;
__u8 ooo_okay:1;
- __u8 l4_rxhash:1;
+ __u8 l4_hash:1;
__u8 wifi_acked_valid:1;
__u8 wifi_acked:1;
__u8 no_fcs:1;
@@ -691,6 +746,8 @@
unsigned int headroom);
struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom,
int newtailroom, gfp_t priority);
+int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
+ int offset, int len);
int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset,
int len);
int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer);
@@ -758,40 +815,40 @@
static inline void
skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type)
{
- skb->l4_rxhash = (type == PKT_HASH_TYPE_L4);
- skb->rxhash = hash;
+ skb->l4_hash = (type == PKT_HASH_TYPE_L4);
+ skb->hash = hash;
}
void __skb_get_hash(struct sk_buff *skb);
static inline __u32 skb_get_hash(struct sk_buff *skb)
{
- if (!skb->l4_rxhash)
+ if (!skb->l4_hash)
__skb_get_hash(skb);
- return skb->rxhash;
+ return skb->hash;
}
static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
{
- return skb->rxhash;
+ return skb->hash;
}
static inline void skb_clear_hash(struct sk_buff *skb)
{
- skb->rxhash = 0;
- skb->l4_rxhash = 0;
+ skb->hash = 0;
+ skb->l4_hash = 0;
}
static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb)
{
- if (!skb->l4_rxhash)
+ if (!skb->l4_hash)
skb_clear_hash(skb);
}
static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from)
{
- to->rxhash = from->rxhash;
- to->l4_rxhash = from->l4_rxhash;
+ to->hash = from->hash;
+ to->l4_hash = from->l4_hash;
};
#ifdef NET_SKBUFF_DATA_USES_OFFSET
@@ -2451,8 +2508,8 @@
unsigned int flags);
void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
unsigned int skb_zerocopy_headlen(const struct sk_buff *from);
-void skb_zerocopy(struct sk_buff *to, const struct sk_buff *from,
- int len, int hlen);
+int skb_zerocopy(struct sk_buff *to, struct sk_buff *from,
+ int len, int hlen);
void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len);
int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen);
void skb_scrub_packet(struct sk_buff *skb, bool xnet);
@@ -2725,7 +2782,7 @@
static inline void nf_reset_trace(struct sk_buff *skb)
{
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES)
skb->nf_trace = 0;
#endif
}
@@ -2742,6 +2799,9 @@
dst->nf_bridge = src->nf_bridge;
nf_bridge_get(src->nf_bridge);
#endif
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES)
+ dst->nf_trace = src->nf_trace;
+#endif
}
static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
@@ -2916,5 +2976,22 @@
{
return !skb->head_frag || skb_cloned(skb);
}
+
+/**
+ * skb_gso_network_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_network_seglen is used to determine the real size of the
+ * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP).
+ *
+ * The MAC/L2 header is not accounted for.
+ */
+static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
+{
+ unsigned int hdr_len = skb_transport_header(skb) -
+ skb_network_header(skb);
+ return hdr_len + skb_gso_transport_seglen(skb);
+}
#endif /* __KERNEL__ */
#endif /* _LINUX_SKBUFF_H */
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 9260abd..b5b2df6 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -410,7 +410,7 @@
*
* %GFP_NOWAIT - Allocation will not sleep.
*
- * %GFP_THISNODE - Allocate node-local memory only.
+ * %__GFP_THISNODE - Allocate node-local memory only.
*
* %GFP_DMA - Allocation suitable for DMA.
* Should only be used for kmalloc() caches. Otherwise, use a
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 3834f43..6ae004e 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -188,6 +188,9 @@
*/
extern void arch_disable_smp_support(void);
+extern void arch_enable_nonboot_cpus_begin(void);
+extern void arch_enable_nonboot_cpus_end(void);
+
void smp_setup_processor_id(void);
#endif /* __LINUX_SMP_H */
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index a1d4ca2..4203c66 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -273,7 +273,7 @@
* message while queuing transfers that arrive in the meantime. When the
* driver is finished with this message, it must call
* spi_finalize_current_message() so the subsystem can issue the next
- * transfer
+ * message
* @unprepare_transfer_hardware: there are currently no more messages on the
* queue so the subsystem notifies the driver that it may relax the
* hardware by issuing this call
@@ -287,7 +287,10 @@
* - return 1 if the transfer is still in progress. When
* the driver is finished with this transfer it must
* call spi_finalize_current_transfer() so the subsystem
- * can issue the next transfer
+ * can issue the next transfer. Note: transfer_one and
+ * transfer_one_message are mutually exclusive; when both
+ * are set, the generic subsystem does not call your
+ * transfer_one callback.
* @unprepare_message: undo any work done by prepare_message().
* @cs_gpios: Array of GPIOs to use as chip select lines; one per CS
* number. Any individual value may be -ENOENT for CS lines that
diff --git a/include/linux/sxgbe_platform.h b/include/linux/sxgbe_platform.h
new file mode 100644
index 0000000..a62442c
--- /dev/null
+++ b/include/linux/sxgbe_platform.h
@@ -0,0 +1,54 @@
+/*
+ * 10G controller driver for Samsung EXYNOS SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SXGBE_PLATFORM_H__
+#define __SXGBE_PLATFORM_H__
+
+/* MDC Clock Selection define*/
+#define SXGBE_CSR_100_150M 0x0 /* MDC = clk_scr_i/62 */
+#define SXGBE_CSR_150_250M 0x1 /* MDC = clk_scr_i/102 */
+#define SXGBE_CSR_250_300M 0x2 /* MDC = clk_scr_i/122 */
+#define SXGBE_CSR_300_350M 0x3 /* MDC = clk_scr_i/142 */
+#define SXGBE_CSR_350_400M 0x4 /* MDC = clk_scr_i/162 */
+#define SXGBE_CSR_400_500M 0x5 /* MDC = clk_scr_i/202 */
+
+/* Platfrom data for platform device structure's
+ * platform_data field
+ */
+struct sxgbe_mdio_bus_data {
+ unsigned int phy_mask;
+ int *irqs;
+ int probed_phy_irq;
+};
+
+struct sxgbe_dma_cfg {
+ int pbl;
+ int fixed_burst;
+ int burst_map;
+ int adv_addr_mode;
+};
+
+struct sxgbe_plat_data {
+ char *phy_bus_name;
+ int bus_id;
+ int phy_addr;
+ int interface;
+ struct sxgbe_mdio_bus_data *mdio_bus_data;
+ struct sxgbe_dma_cfg *dma_cfg;
+ int clk_csr;
+ int pmt;
+ int force_sf_dma_mode;
+ int force_thresh_dma_mode;
+ int riwt_off;
+};
+
+#endif /* __SXGBE_PLATFORM_H__ */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 40ed9e9..a747a77 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -281,13 +281,15 @@
asmlinkage long sys_sched_setparam(pid_t pid,
struct sched_param __user *param);
asmlinkage long sys_sched_setattr(pid_t pid,
- struct sched_attr __user *attr);
+ struct sched_attr __user *attr,
+ unsigned int flags);
asmlinkage long sys_sched_getscheduler(pid_t pid);
asmlinkage long sys_sched_getparam(pid_t pid,
struct sched_param __user *param);
asmlinkage long sys_sched_getattr(pid_t pid,
struct sched_attr __user *attr,
- unsigned int size);
+ unsigned int size,
+ unsigned int flags);
asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
unsigned long __user *user_mask_ptr);
asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4ad0706..2399468 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -201,10 +201,10 @@
u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */
/* RTT measurement */
- u32 srtt; /* smoothed round trip time << 3 */
- u32 mdev; /* medium deviation */
- u32 mdev_max; /* maximal mdev for the last rtt period */
- u32 rttvar; /* smoothed mdev_max */
+ u32 srtt_us; /* smoothed round trip time << 3 in usecs */
+ u32 mdev_us; /* medium deviation */
+ u32 mdev_max_us; /* maximal mdev for the last rtt period */
+ u32 rttvar_us; /* smoothed mdev_max */
u32 rtt_seq; /* sequence number to update rttvar */
u32 packets_out; /* Packets which are "in flight" */
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index accc497..7159a0a 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -60,6 +60,12 @@
unsigned int num_tracepoints;
struct tracepoint * const *tracepoints_ptrs;
};
+bool trace_module_has_bad_taint(struct module *mod);
+#else
+static inline bool trace_module_has_bad_taint(struct module *mod)
+{
+ return false;
+}
#endif /* CONFIG_MODULES */
struct tracepoint_iter {
diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h
index 7bfabd2..4b4439e 100644
--- a/include/linux/u64_stats_sync.h
+++ b/include/linux/u64_stats_sync.h
@@ -27,8 +27,8 @@
* (On UP, there is no seqcount_t protection, a reader allowing interrupts could
* read partial values)
*
- * 7) For softirq uses, readers can use u64_stats_fetch_begin_bh() and
- * u64_stats_fetch_retry_bh() helpers
+ * 7) For irq and softirq uses, readers can use u64_stats_fetch_begin_irq() and
+ * u64_stats_fetch_retry_irq() helpers
*
* Usage :
*
@@ -114,31 +114,31 @@
}
/*
- * In case softirq handlers can update u64 counters, readers can use following helpers
+ * In case irq handlers can update u64 counters, readers can use following helpers
* - SMP 32bit arches use seqcount protection, irq safe.
- * - UP 32bit must disable BH.
+ * - UP 32bit must disable irqs.
* - 64bit have no problem atomically reading u64 values, irq safe.
*/
-static inline unsigned int u64_stats_fetch_begin_bh(const struct u64_stats_sync *syncp)
+static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
return read_seqcount_begin(&syncp->seq);
#else
#if BITS_PER_LONG==32
- local_bh_disable();
+ local_irq_disable();
#endif
return 0;
#endif
}
-static inline bool u64_stats_fetch_retry_bh(const struct u64_stats_sync *syncp,
+static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp,
unsigned int start)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
return read_seqcount_retry(&syncp->seq, start);
#else
#if BITS_PER_LONG==32
- local_bh_enable();
+ local_irq_enable();
#endif
return false;
#endif
diff --git a/include/linux/usb.h b/include/linux/usb.h
index c716da1..7f6eb85 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1265,8 +1265,6 @@
* @sg: scatter gather buffer list, the buffer size of each element in
* the list (except the last) must be divisible by the endpoint's
* max packet size if no_sg_constraint isn't set in 'struct usb_bus'
- * (FIXME: scatter-gather under xHCI is broken for periodic transfers.
- * Do not use urb->sg for interrupt endpoints for now, only bulk.)
* @num_mapped_sgs: (internal) number of mapped sg entries
* @num_sgs: number of entries in the sg list
* @transfer_buffer_length: How big is transfer_buffer. The transfer may
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index c3fa807..44b38b9 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -88,11 +88,13 @@
#define cdc_ncm_data_intf_is_mbim(x) ((x)->desc.bInterfaceProtocol == USB_CDC_MBIM_PROTO_NTB)
struct cdc_ncm_ctx {
+ struct usb_cdc_ncm_ntb_parameters ncm_parm;
struct hrtimer tx_timer;
struct tasklet_struct bh;
const struct usb_cdc_ncm_desc *func_desc;
const struct usb_cdc_mbim_desc *mbim_desc;
+ const struct usb_cdc_mbim_extended_desc *mbim_extended_desc;
const struct usb_cdc_ether_desc *ether_desc;
struct usb_interface *control;
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index e303eef..0662e98 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -30,7 +30,7 @@
struct driver_info *driver_info;
const char *driver_name;
void *driver_priv;
- wait_queue_head_t *wait;
+ wait_queue_head_t wait;
struct mutex phy_mutex;
unsigned char suspend_count;
unsigned char pkt_cnt, pkt_err;
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 594521b..704f4f6 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -419,10 +419,7 @@
static struct lock_class_key __key; \
const char *__lock_name; \
\
- if (__builtin_constant_p(fmt)) \
- __lock_name = (fmt); \
- else \
- __lock_name = #fmt; \
+ __lock_name = #fmt#args; \
\
__alloc_workqueue_key((fmt), (flags), (max_active), \
&__key, __lock_name, ##args); \
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index fc0e432..021b8a3 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -97,7 +97,7 @@
int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason);
int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
enum wb_reason reason);
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this);
+void sync_inodes_sb(struct super_block *);
void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
void inode_wait_for_writeback(struct inode *inode);
diff --git a/net/ieee802154/6lowpan.h b/include/net/6lowpan.h
similarity index 81%
rename from net/ieee802154/6lowpan.h
rename to include/net/6lowpan.h
index 2b835db..f7d372b 100644
--- a/net/ieee802154/6lowpan.h
+++ b/include/net/6lowpan.h
@@ -53,6 +53,8 @@
#ifndef __6LOWPAN_H__
#define __6LOWPAN_H__
+#include <net/ipv6.h>
+
#define UIP_802154_SHORTADDR_LEN 2 /* compressed ipv6 address length */
#define UIP_IPH_LEN 40 /* ipv6 fixed header size */
#define UIP_PROTO_UDP 17 /* ipv6 next header value for UDP */
@@ -306,6 +308,119 @@
*hc_ptr += len;
}
+static inline u8 lowpan_addr_mode_size(const u8 addr_mode)
+{
+ static const u8 addr_sizes[] = {
+ [LOWPAN_IPHC_ADDR_00] = 16,
+ [LOWPAN_IPHC_ADDR_01] = 8,
+ [LOWPAN_IPHC_ADDR_02] = 2,
+ [LOWPAN_IPHC_ADDR_03] = 0,
+ };
+ return addr_sizes[addr_mode];
+}
+
+static inline u8 lowpan_next_hdr_size(const u8 h_enc, u16 *uncomp_header)
+{
+ u8 ret = 1;
+
+ if ((h_enc & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) {
+ *uncomp_header += sizeof(struct udphdr);
+
+ switch (h_enc & LOWPAN_NHC_UDP_CS_P_11) {
+ case LOWPAN_NHC_UDP_CS_P_00:
+ ret += 4;
+ break;
+ case LOWPAN_NHC_UDP_CS_P_01:
+ case LOWPAN_NHC_UDP_CS_P_10:
+ ret += 3;
+ break;
+ case LOWPAN_NHC_UDP_CS_P_11:
+ ret++;
+ break;
+ default:
+ break;
+ }
+
+ if (!(h_enc & LOWPAN_NHC_UDP_CS_C))
+ ret += 2;
+ }
+
+ return ret;
+}
+
+/**
+ * lowpan_uncompress_size - returns skb->len size with uncompressed header
+ * @skb: sk_buff with 6lowpan header inside
+ * @datagram_offset: optional to get the datagram_offset value
+ *
+ * Returns the skb->len with uncompressed header
+ */
+static inline u16
+lowpan_uncompress_size(const struct sk_buff *skb, u16 *dgram_offset)
+{
+ u16 ret = 2, uncomp_header = sizeof(struct ipv6hdr);
+ u8 iphc0, iphc1, h_enc;
+
+ iphc0 = skb_network_header(skb)[0];
+ iphc1 = skb_network_header(skb)[1];
+
+ switch ((iphc0 & LOWPAN_IPHC_TF) >> 3) {
+ case 0:
+ ret += 4;
+ break;
+ case 1:
+ ret += 3;
+ break;
+ case 2:
+ ret++;
+ break;
+ default:
+ break;
+ }
+
+ if (!(iphc0 & LOWPAN_IPHC_NH_C))
+ ret++;
+
+ if (!(iphc0 & 0x03))
+ ret++;
+
+ ret += lowpan_addr_mode_size((iphc1 & LOWPAN_IPHC_SAM) >>
+ LOWPAN_IPHC_SAM_BIT);
+
+ if (iphc1 & LOWPAN_IPHC_M) {
+ switch ((iphc1 & LOWPAN_IPHC_DAM_11) >>
+ LOWPAN_IPHC_DAM_BIT) {
+ case LOWPAN_IPHC_DAM_00:
+ ret += 16;
+ break;
+ case LOWPAN_IPHC_DAM_01:
+ ret += 6;
+ break;
+ case LOWPAN_IPHC_DAM_10:
+ ret += 4;
+ break;
+ case LOWPAN_IPHC_DAM_11:
+ ret++;
+ break;
+ default:
+ break;
+ }
+ } else {
+ ret += lowpan_addr_mode_size((iphc1 & LOWPAN_IPHC_DAM_11) >>
+ LOWPAN_IPHC_DAM_BIT);
+ }
+
+ if (iphc0 & LOWPAN_IPHC_NH_C) {
+ h_enc = skb_network_header(skb)[ret];
+ ret += lowpan_next_hdr_size(h_enc, &uncomp_header);
+ }
+
+ if (dgram_offset)
+ *dgram_offset = uncomp_header;
+
+ return skb->len + uncomp_header - ret;
+}
+
typedef int (*skb_delivery_cb)(struct sk_buff *skb, struct net_device *dev);
int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 788d837..3ee4c92 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -89,7 +89,7 @@
struct module *owner;
int (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *);
int (*dump)(struct sk_buff *, struct tc_action *, int, int);
- int (*cleanup)(struct tc_action *, int bind);
+ void (*cleanup)(struct tc_action *, int bind);
int (*lookup)(struct tc_action *, u32);
int (*init)(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action *act, int ovr,
@@ -98,20 +98,18 @@
};
int tcf_hash_search(struct tc_action *a, u32 index);
-void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo);
-int tcf_hash_release(struct tcf_common *p, int bind,
- struct tcf_hashinfo *hinfo);
+void tcf_hash_destroy(struct tc_action *a);
+int tcf_hash_release(struct tc_action *a, int bind);
u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo);
-struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a,
- int bind);
-struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est,
- struct tc_action *a, int size,
- int bind);
-void tcf_hash_insert(struct tcf_common *p, struct tcf_hashinfo *hinfo);
+int tcf_hash_check(u32 index, struct tc_action *a, int bind);
+int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
+ int size, int bind);
+void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est);
+void tcf_hash_insert(struct tc_action *a);
-int tcf_register_action(struct tc_action_ops *a);
+int tcf_register_action(struct tc_action_ops *a, unsigned int mask);
int tcf_unregister_action(struct tc_action_ops *a);
-void tcf_action_destroy(struct list_head *actions, int bind);
+int tcf_action_destroy(struct list_head *actions, int bind);
int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions,
struct tcf_result *res);
int tcf_action_init(struct net *net, struct nlattr *nla,
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 50e39a8..933a9f2 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -314,7 +314,7 @@
static inline bool ipv6_addr_is_ll_all_nodes(const struct in6_addr *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
- __u64 *p = (__u64 *)addr;
+ __be64 *p = (__be64 *)addr;
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(1))) == 0UL;
#else
return ((addr->s6_addr32[0] ^ htonl(0xff020000)) |
@@ -326,7 +326,7 @@
static inline bool ipv6_addr_is_ll_all_routers(const struct in6_addr *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
- __u64 *p = (__u64 *)addr;
+ __be64 *p = (__be64 *)addr;
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(2))) == 0UL;
#else
return ((addr->s6_addr32[0] ^ htonl(0xff020000)) |
@@ -343,7 +343,7 @@
static inline bool ipv6_addr_is_solict_mult(const struct in6_addr *addr)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
- __u64 *p = (__u64 *)addr;
+ __be64 *p = (__be64 *)addr;
return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) |
((p[1] ^ cpu_to_be64(0x00000001ff000000UL)) &
cpu_to_be64(0xffffffffff000000UL))) == 0UL;
diff --git a/include/net/af_ieee802154.h b/include/net/af_ieee802154.h
index 75e64c7..f79ae2a 100644
--- a/include/net/af_ieee802154.h
+++ b/include/net/af_ieee802154.h
@@ -36,7 +36,7 @@
/* address length, octets */
#define IEEE802154_ADDR_LEN 8
-struct ieee802154_addr {
+struct ieee802154_addr_sa {
int addr_type;
u16 pan_id;
union {
@@ -51,7 +51,7 @@
struct sockaddr_ieee802154 {
sa_family_t family; /* AF_IEEE802154 */
- struct ieee802154_addr addr;
+ struct ieee802154_addr_sa addr;
};
/* get/setsockopt */
diff --git a/include/net/checksum.h b/include/net/checksum.h
index 37a0e24..a28f4e0 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -69,6 +69,19 @@
return csum_add(csum, ~addend);
}
+static inline __sum16 csum16_add(__sum16 csum, __be16 addend)
+{
+ u16 res = (__force u16)csum;
+
+ res += (__force u16)addend;
+ return (__force __sum16)(res + (res < (__force u16)addend));
+}
+
+static inline __sum16 csum16_sub(__sum16 csum, __be16 addend)
+{
+ return csum16_add(csum, ~addend);
+}
+
static inline __wsum
csum_block_add(__wsum csum, __wsum csum2, int offset)
{
@@ -112,9 +125,15 @@
*sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum)));
}
-static inline void csum_replace2(__sum16 *sum, __be16 from, __be16 to)
+/* Implements RFC 1624 (Incremental Internet Checksum)
+ * 3. Discussion states :
+ * HC' = ~(~HC + ~m + m')
+ * m : old value of a 16bit field
+ * m' : new value of a 16bit field
+ */
+static inline void csum_replace2(__sum16 *sum, __be16 old, __be16 new)
{
- csum_replace4(sum, (__force __be32)from, (__force __be32)to);
+ *sum = ~csum16_add(csum16_sub(~(*sum), old), new);
}
struct sk_buff;
diff --git a/include/net/datalink.h b/include/net/datalink.h
index deb7ca7..93cb18f 100644
--- a/include/net/datalink.h
+++ b/include/net/datalink.h
@@ -15,4 +15,6 @@
struct list_head node;
};
+struct datalink_proto *make_EII_client(void);
+void destroy_EII_client(struct datalink_proto *dl);
#endif
diff --git a/include/net/dn.h b/include/net/dn.h
index ccc1558..913b73d 100644
--- a/include/net/dn.h
+++ b/include/net/dn.h
@@ -200,6 +200,8 @@
}
unsigned int dn_mss_from_pmtu(struct net_device *dev, int mtu);
+void dn_register_sysctl(void);
+void dn_unregister_sysctl(void);
#define DN_MENUVER_ACC 0x01
#define DN_MENUVER_USR 0x02
diff --git a/include/net/dn_route.h b/include/net/dn_route.h
index b409ad6..55df993 100644
--- a/include/net/dn_route.h
+++ b/include/net/dn_route.h
@@ -20,6 +20,8 @@
struct sock *sk, int flags);
int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb);
void dn_rt_cache_flush(int delay);
+int dn_route_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt, struct net_device *orig_dev);
/* Masks for flags field */
#define DN_RT_F_PID 0x07 /* Mask for packet type */
diff --git a/include/net/dst.h b/include/net/dst.h
index 77eb53f..46ed958 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -54,10 +54,9 @@
#define DST_NOHASH 0x0008
#define DST_NOCACHE 0x0010
#define DST_NOCOUNT 0x0020
-#define DST_NOPEER 0x0040
-#define DST_FAKE_RTABLE 0x0080
-#define DST_XFRM_TUNNEL 0x0100
-#define DST_XFRM_QUEUE 0x0200
+#define DST_FAKE_RTABLE 0x0040
+#define DST_XFRM_TUNNEL 0x0080
+#define DST_XFRM_QUEUE 0x0100
unsigned short pending_confirm;
@@ -109,9 +108,11 @@
u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
extern const u32 dst_default_metrics[];
-#define DST_METRICS_READ_ONLY 0x1UL
+#define DST_METRICS_READ_ONLY 0x1UL
+#define DST_METRICS_FORCE_OVERWRITE 0x2UL
+#define DST_METRICS_FLAGS 0x3UL
#define __DST_METRICS_PTR(Y) \
- ((u32 *)((Y) & ~DST_METRICS_READ_ONLY))
+ ((u32 *)((Y) & ~DST_METRICS_FLAGS))
#define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics)
static inline bool dst_metrics_read_only(const struct dst_entry *dst)
@@ -119,6 +120,11 @@
return dst->_metrics & DST_METRICS_READ_ONLY;
}
+static inline void dst_metrics_set_force_overwrite(struct dst_entry *dst)
+{
+ dst->_metrics |= DST_METRICS_FORCE_OVERWRITE;
+}
+
void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old);
static inline void dst_destroy_metrics_generic(struct dst_entry *dst)
diff --git a/include/net/ethoc.h b/include/net/ethoc.h
index 96f3789..2a2d6bb 100644
--- a/include/net/ethoc.h
+++ b/include/net/ethoc.h
@@ -16,6 +16,7 @@
struct ethoc_platform_data {
u8 hwaddr[IFHWADDRLEN];
s8 phy_id;
+ u32 eth_clkfreq;
};
#endif /* !LINUX_NET_ETHOC_H */
diff --git a/include/net/flow.h b/include/net/flow.h
index d23e7fa..64fd248 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -218,9 +218,11 @@
const struct flowi *key, u16 family,
u8 dir, flow_resolve_t resolver,
void *ctx);
+int flow_cache_init(struct net *net);
+void flow_cache_fini(struct net *net);
-void flow_cache_flush(void);
-void flow_cache_flush_deferred(void);
+void flow_cache_flush(struct net *net);
+void flow_cache_flush_deferred(struct net *net);
extern atomic_t flow_cache_genid;
#endif
diff --git a/include/net/flowcache.h b/include/net/flowcache.h
new file mode 100644
index 0000000..c8f665e
--- /dev/null
+++ b/include/net/flowcache.h
@@ -0,0 +1,25 @@
+#ifndef _NET_FLOWCACHE_H
+#define _NET_FLOWCACHE_H
+
+#include <linux/interrupt.h>
+#include <linux/types.h>
+#include <linux/timer.h>
+#include <linux/notifier.h>
+
+struct flow_cache_percpu {
+ struct hlist_head *hash_table;
+ int hash_count;
+ u32 hash_rnd;
+ int hash_rnd_recalc;
+ struct tasklet_struct flush_tasklet;
+};
+
+struct flow_cache {
+ u32 hash_shift;
+ struct flow_cache_percpu __percpu *percpu;
+ struct notifier_block hotcpu_notifier;
+ int low_watermark;
+ int high_watermark;
+ struct timer_list rnd_timer;
+};
+#endif /* _NET_FLOWCACHE_H */
diff --git a/include/net/ieee802154.h b/include/net/ieee802154.h
index ee59f8b..c7ae0ac 100644
--- a/include/net/ieee802154.h
+++ b/include/net/ieee802154.h
@@ -42,22 +42,42 @@
(((x) << IEEE802154_FC_TYPE_SHIFT) & IEEE802154_FC_TYPE_MASK)); \
} while (0)
-#define IEEE802154_FC_SECEN (1 << 3)
-#define IEEE802154_FC_FRPEND (1 << 4)
-#define IEEE802154_FC_ACK_REQ (1 << 5)
-#define IEEE802154_FC_INTRA_PAN (1 << 6)
+#define IEEE802154_FC_SECEN_SHIFT 3
+#define IEEE802154_FC_SECEN (1 << IEEE802154_FC_SECEN_SHIFT)
+#define IEEE802154_FC_FRPEND_SHIFT 4
+#define IEEE802154_FC_FRPEND (1 << IEEE802154_FC_FRPEND_SHIFT)
+#define IEEE802154_FC_ACK_REQ_SHIFT 5
+#define IEEE802154_FC_ACK_REQ (1 << IEEE802154_FC_ACK_REQ_SHIFT)
+#define IEEE802154_FC_INTRA_PAN_SHIFT 6
+#define IEEE802154_FC_INTRA_PAN (1 << IEEE802154_FC_INTRA_PAN_SHIFT)
#define IEEE802154_FC_SAMODE_SHIFT 14
#define IEEE802154_FC_SAMODE_MASK (3 << IEEE802154_FC_SAMODE_SHIFT)
#define IEEE802154_FC_DAMODE_SHIFT 10
#define IEEE802154_FC_DAMODE_MASK (3 << IEEE802154_FC_DAMODE_SHIFT)
+#define IEEE802154_FC_VERSION_SHIFT 12
+#define IEEE802154_FC_VERSION_MASK (3 << IEEE802154_FC_VERSION_SHIFT)
+#define IEEE802154_FC_VERSION(x) ((x & IEEE802154_FC_VERSION_MASK) >> IEEE802154_FC_VERSION_SHIFT)
+
#define IEEE802154_FC_SAMODE(x) \
(((x) & IEEE802154_FC_SAMODE_MASK) >> IEEE802154_FC_SAMODE_SHIFT)
#define IEEE802154_FC_DAMODE(x) \
(((x) & IEEE802154_FC_DAMODE_MASK) >> IEEE802154_FC_DAMODE_SHIFT)
+#define IEEE802154_SCF_SECLEVEL_MASK 7
+#define IEEE802154_SCF_SECLEVEL_SHIFT 0
+#define IEEE802154_SCF_SECLEVEL(x) (x & IEEE802154_SCF_SECLEVEL_MASK)
+#define IEEE802154_SCF_KEY_ID_MODE_SHIFT 3
+#define IEEE802154_SCF_KEY_ID_MODE_MASK (3 << IEEE802154_SCF_KEY_ID_MODE_SHIFT)
+#define IEEE802154_SCF_KEY_ID_MODE(x) \
+ ((x & IEEE802154_SCF_KEY_ID_MODE_MASK) >> IEEE802154_SCF_KEY_ID_MODE_SHIFT)
+
+#define IEEE802154_SCF_KEY_IMPLICIT 0
+#define IEEE802154_SCF_KEY_INDEX 1
+#define IEEE802154_SCF_KEY_SHORT_INDEX 2
+#define IEEE802154_SCF_KEY_HW_INDEX 3
/* MAC footer size */
#define IEEE802154_MFR_SIZE 2 /* 2 octets */
diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index 8196d5d..e1717cb 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -28,6 +28,164 @@
#define IEEE802154_NETDEVICE_H
#include <net/af_ieee802154.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+
+struct ieee802154_sechdr {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ u8 level:3,
+ key_id_mode:2,
+ reserved:3;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ u8 reserved:3,
+ key_id_mode:2,
+ level:3;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+ u8 key_id;
+ __le32 frame_counter;
+ union {
+ __le32 short_src;
+ __le64 extended_src;
+ };
+};
+
+struct ieee802154_addr {
+ u8 mode;
+ __le16 pan_id;
+ union {
+ __le16 short_addr;
+ __le64 extended_addr;
+ };
+};
+
+struct ieee802154_hdr_fc {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ u16 type:3,
+ security_enabled:1,
+ frame_pending:1,
+ ack_request:1,
+ intra_pan:1,
+ reserved:3,
+ dest_addr_mode:2,
+ version:2,
+ source_addr_mode:2;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ u16 reserved:1,
+ intra_pan:1,
+ ack_request:1,
+ frame_pending:1,
+ security_enabled:1,
+ type:3,
+ source_addr_mode:2,
+ version:2,
+ dest_addr_mode:2,
+ reserved2:2;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+};
+
+struct ieee802154_hdr {
+ struct ieee802154_hdr_fc fc;
+ u8 seq;
+ struct ieee802154_addr source;
+ struct ieee802154_addr dest;
+ struct ieee802154_sechdr sec;
+};
+
+/* pushes hdr onto the skb. fields of hdr->fc that can be calculated from
+ * the contents of hdr will be, and the actual value of those bits in
+ * hdr->fc will be ignored. this includes the INTRA_PAN bit and the frame
+ * version, if SECEN is set.
+ */
+int ieee802154_hdr_push(struct sk_buff *skb, const struct ieee802154_hdr *hdr);
+
+/* pulls the entire 802.15.4 header off of the skb, including the security
+ * header, and performs pan id decompression
+ */
+int ieee802154_hdr_pull(struct sk_buff *skb, struct ieee802154_hdr *hdr);
+
+/* parses the frame control, sequence number of address fields in a given skb
+ * and stores them into hdr, performing pan id decompression and length checks
+ * to be suitable for use in header_ops.parse
+ */
+int ieee802154_hdr_peek_addrs(const struct sk_buff *skb,
+ struct ieee802154_hdr *hdr);
+
+static inline int ieee802154_hdr_length(struct sk_buff *skb)
+{
+ struct ieee802154_hdr hdr;
+ int len = ieee802154_hdr_pull(skb, &hdr);
+
+ if (len > 0)
+ skb_push(skb, len);
+
+ return len;
+}
+
+static inline bool ieee802154_addr_equal(const struct ieee802154_addr *a1,
+ const struct ieee802154_addr *a2)
+{
+ if (a1->pan_id != a2->pan_id || a1->mode != a2->mode)
+ return false;
+
+ if ((a1->mode == IEEE802154_ADDR_LONG &&
+ a1->extended_addr != a2->extended_addr) ||
+ (a1->mode == IEEE802154_ADDR_SHORT &&
+ a1->short_addr != a2->short_addr))
+ return false;
+
+ return true;
+}
+
+static inline __le64 ieee802154_devaddr_from_raw(const void *raw)
+{
+ u64 temp;
+
+ memcpy(&temp, raw, IEEE802154_ADDR_LEN);
+ return (__force __le64)swab64(temp);
+}
+
+static inline void ieee802154_devaddr_to_raw(void *raw, __le64 addr)
+{
+ u64 temp = swab64((__force u64)addr);
+
+ memcpy(raw, &temp, IEEE802154_ADDR_LEN);
+}
+
+static inline void ieee802154_addr_from_sa(struct ieee802154_addr *a,
+ const struct ieee802154_addr_sa *sa)
+{
+ a->mode = sa->addr_type;
+ a->pan_id = cpu_to_le16(sa->pan_id);
+
+ switch (a->mode) {
+ case IEEE802154_ADDR_SHORT:
+ a->short_addr = cpu_to_le16(sa->short_addr);
+ break;
+ case IEEE802154_ADDR_LONG:
+ a->extended_addr = ieee802154_devaddr_from_raw(sa->hwaddr);
+ break;
+ }
+}
+
+static inline void ieee802154_addr_to_sa(struct ieee802154_addr_sa *sa,
+ const struct ieee802154_addr *a)
+{
+ sa->addr_type = a->mode;
+ sa->pan_id = le16_to_cpu(a->pan_id);
+
+ switch (a->mode) {
+ case IEEE802154_ADDR_SHORT:
+ sa->short_addr = le16_to_cpu(a->short_addr);
+ break;
+ case IEEE802154_ADDR_LONG:
+ ieee802154_devaddr_to_raw(sa->hwaddr, a->extended_addr);
+ break;
+ }
+}
/*
* A control block of skb passed between the ARPHRD_IEEE802154 device
@@ -35,10 +193,10 @@
*/
struct ieee802154_mac_cb {
u8 lqi;
- struct ieee802154_addr sa;
- struct ieee802154_addr da;
u8 flags;
u8 seq;
+ struct ieee802154_addr source;
+ struct ieee802154_addr dest;
};
static inline struct ieee802154_mac_cb *mac_cb(struct sk_buff *skb)
@@ -50,23 +208,17 @@
#define MAC_CB_FLAG_ACKREQ (1 << 3)
#define MAC_CB_FLAG_SECEN (1 << 4)
-#define MAC_CB_FLAG_INTRAPAN (1 << 5)
-static inline int mac_cb_is_ackreq(struct sk_buff *skb)
+static inline bool mac_cb_is_ackreq(struct sk_buff *skb)
{
return mac_cb(skb)->flags & MAC_CB_FLAG_ACKREQ;
}
-static inline int mac_cb_is_secen(struct sk_buff *skb)
+static inline bool mac_cb_is_secen(struct sk_buff *skb)
{
return mac_cb(skb)->flags & MAC_CB_FLAG_SECEN;
}
-static inline int mac_cb_is_intrapan(struct sk_buff *skb)
-{
- return mac_cb(skb)->flags & MAC_CB_FLAG_INTRAPAN;
-}
-
static inline int mac_cb_type(struct sk_buff *skb)
{
return mac_cb(skb)->flags & MAC_CB_FLAG_TYPEMASK;
@@ -92,7 +244,7 @@
u8 channel, u8 page, u8 cap);
int (*assoc_resp)(struct net_device *dev,
struct ieee802154_addr *addr,
- u16 short_addr, u8 status);
+ __le16 short_addr, u8 status);
int (*disassoc_req)(struct net_device *dev,
struct ieee802154_addr *addr,
u8 reason);
@@ -111,8 +263,8 @@
* FIXME: these should become the part of PIB/MIB interface.
* However we still don't have IB interface of any kind
*/
- u16 (*get_pan_id)(const struct net_device *dev);
- u16 (*get_short_addr)(const struct net_device *dev);
+ __le16 (*get_pan_id)(const struct net_device *dev);
+ __le16 (*get_short_addr)(const struct net_device *dev);
u8 (*get_dsn)(const struct net_device *dev);
};
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 9650a3f..b4956a5 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -31,8 +31,10 @@
#define IF_PREFIX_AUTOCONF 0x02
enum {
+ INET6_IFADDR_STATE_PREDAD,
INET6_IFADDR_STATE_DAD,
INET6_IFADDR_STATE_POSTDAD,
+ INET6_IFADDR_STATE_ERRDAD,
INET6_IFADDR_STATE_UP,
INET6_IFADDR_STATE_DEAD,
};
@@ -58,7 +60,7 @@
unsigned long cstamp; /* created timestamp */
unsigned long tstamp; /* updated timestamp */
- struct timer_list dad_timer;
+ struct delayed_work dad_work;
struct inet6_dev *idev;
struct rt6_info *rt;
diff --git a/include/net/ip.h b/include/net/ip.h
index 23be0fd..25064c2 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -187,6 +187,7 @@
#define NET_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.net_statistics, field)
#define NET_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.net_statistics, field)
#define NET_INC_STATS_USER(net, field) SNMP_INC_STATS_USER((net)->mib.net_statistics, field)
+#define NET_ADD_STATS(net, field, adnd) SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd)
#define NET_ADD_STATS_BH(net, field, adnd) SNMP_ADD_STATS_BH((net)->mib.net_statistics, field, adnd)
#define NET_ADD_STATS_USER(net, field, adnd) SNMP_ADD_STATS_USER((net)->mib.net_statistics, field, adnd)
@@ -266,7 +267,8 @@
static inline bool ip_sk_accept_pmtu(const struct sock *sk)
{
- return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE;
+ return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE &&
+ inet_sk(sk)->pmtudisc != IP_PMTUDISC_OMIT;
}
static inline bool ip_sk_use_pmtu(const struct sock *sk)
@@ -274,6 +276,12 @@
return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE;
}
+static inline bool ip_sk_local_df(const struct sock *sk)
+{
+ return inet_sk(sk)->pmtudisc < IP_PMTUDISC_DO ||
+ inet_sk(sk)->pmtudisc == IP_PMTUDISC_OMIT;
+}
+
static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
bool forwarding)
{
@@ -489,7 +497,8 @@
void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb);
-int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc);
+int ip_cmsg_send(struct net *net, struct msghdr *msg,
+ struct ipcm_cookie *ipc, bool allow_ipv6);
int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
unsigned int optlen);
int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index aca0c27..9bcb220 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -284,7 +284,8 @@
void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
void *arg);
-int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info);
+int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
+ struct nlattr *mx, int mx_len);
int fib6_del(struct rt6_info *rt, struct nl_info *info);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 017badb..00e3f12 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -171,7 +171,14 @@
static inline bool ip6_sk_accept_pmtu(const struct sock *sk)
{
- return inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_INTERFACE;
+ return inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_INTERFACE &&
+ inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_OMIT;
+}
+
+static inline bool ip6_sk_local_df(const struct sock *sk)
+{
+ return inet6_sk(sk)->pmtudisc < IPV6_PMTUDISC_DO ||
+ inet6_sk(sk)->pmtudisc == IPV6_PMTUDISC_OMIT;
}
static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt)
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 48ed75c..e77c104 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -129,6 +129,7 @@
int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p);
void ip_tunnel_setup(struct net_device *dev, int net_id);
+void ip_tunnel_dst_reset_all(struct ip_tunnel *t);
/* Extract dsfield from inner protocol */
static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
diff --git a/include/net/ipx.h b/include/net/ipx.h
index 9e9e354..0143180 100644
--- a/include/net/ipx.h
+++ b/include/net/ipx.h
@@ -140,6 +140,17 @@
}
void ipxitf_down(struct ipx_interface *intrfc);
+struct ipx_interface *ipxitf_find_using_net(__be32 net);
+int ipxitf_send(struct ipx_interface *intrfc, struct sk_buff *skb, char *node);
+__be16 ipx_cksum(struct ipxhdr *packet, int length);
+int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc,
+ unsigned char *node);
+void ipxrtr_del_routes(struct ipx_interface *intrfc);
+int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx,
+ struct iovec *iov, size_t len, int noblock);
+int ipxrtr_route_skb(struct sk_buff *skb);
+struct ipx_route *ipxrtr_lookup(__be32 net);
+int ipxrtr_ioctl(unsigned int cmd, void __user *arg);
static __inline__ void ipxitf_put(struct ipx_interface *intrfc)
{
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 807d6b7..a591053 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -20,6 +20,7 @@
#define NET_MAC802154_H
#include <net/af_ieee802154.h>
+#include <linux/skbuff.h>
/* General MAC frame format:
* 2 bytes: Frame Control
@@ -50,7 +51,7 @@
* devices across independent networks.
*/
__le16 short_addr;
- u8 ieee_addr[IEEE802154_ADDR_LEN];
+ __le64 ieee_addr;
u8 pan_coord;
};
@@ -113,6 +114,32 @@
* Set radio for listening on specific address.
* Set the device for listening on specified address.
* Returns either zero, or negative errno.
+ *
+ * set_txpower:
+ * Set radio transmit power in dB. Called with pib_lock held.
+ * Returns either zero, or negative errno.
+ *
+ * set_lbt
+ * Enables or disables listen before talk on the device. Called with
+ * pib_lock held.
+ * Returns either zero, or negative errno.
+ *
+ * set_cca_mode
+ * Sets the CCA mode used by the device. Called with pib_lock held.
+ * Returns either zero, or negative errno.
+ *
+ * set_cca_ed_level
+ * Sets the CCA energy detection threshold in dBm. Called with pib_lock
+ * held.
+ * Returns either zero, or negative errno.
+ *
+ * set_csma_params
+ * Sets the CSMA parameter set for the PHY. Called with pib_lock held.
+ * Returns either zero, or negative errno.
+ *
+ * set_frame_retries
+ * Sets the retransmission attempt limit. Called with pib_lock held.
+ * Returns either zero, or negative errno.
*/
struct ieee802154_ops {
struct module *owner;
@@ -127,8 +154,16 @@
int (*set_hw_addr_filt)(struct ieee802154_dev *dev,
struct ieee802154_hw_addr_filt *filt,
unsigned long changed);
- int (*ieee_addr)(struct ieee802154_dev *dev,
- u8 addr[IEEE802154_ADDR_LEN]);
+ int (*ieee_addr)(struct ieee802154_dev *dev, __le64 addr);
+ int (*set_txpower)(struct ieee802154_dev *dev, int db);
+ int (*set_lbt)(struct ieee802154_dev *dev, bool on);
+ int (*set_cca_mode)(struct ieee802154_dev *dev, u8 mode);
+ int (*set_cca_ed_level)(struct ieee802154_dev *dev,
+ s32 level);
+ int (*set_csma_params)(struct ieee802154_dev *dev,
+ u8 min_be, u8 max_be, u8 retries);
+ int (*set_frame_retries)(struct ieee802154_dev *dev,
+ s8 retries);
};
/* Basic interface to register ieee802154 device */
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index da68c9a..79387f7 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -15,6 +15,7 @@
#include <net/netns/packet.h>
#include <net/netns/ipv4.h>
#include <net/netns/ipv6.h>
+#include <net/netns/ieee802154_6lowpan.h>
#include <net/netns/sctp.h>
#include <net/netns/dccp.h>
#include <net/netns/netfilter.h>
@@ -90,6 +91,9 @@
#if IS_ENABLED(CONFIG_IPV6)
struct netns_ipv6 ipv6;
#endif
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+ struct netns_ieee802154_lowpan ieee802154_lowpan;
+#endif
#if defined(CONFIG_IP_SCTP) || defined(CONFIG_IP_SCTP_MODULE)
struct netns_sctp sctp;
#endif
@@ -162,6 +166,14 @@
struct net *get_net_ns_by_pid(pid_t pid);
struct net *get_net_ns_by_fd(int pid);
+#ifdef CONFIG_SYSCTL
+void ipx_register_sysctl(void);
+void ipx_unregister_sysctl(void);
+#else
+#define ipx_register_sysctl()
+#define ipx_unregister_sysctl()
+#endif
+
#ifdef CONFIG_NET_NS
void __put_net(struct net *net);
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 01ea6ee..37252f7 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -73,10 +73,17 @@
struct nf_conn {
/* Usage count in here is 1 for hash table/destruct timer, 1 per skb,
- plus 1 for any connection(s) we are `master' for */
+ * plus 1 for any connection(s) we are `master' for
+ *
+ * Hint, SKB address this struct and refcnt via skb->nfct and
+ * helpers nf_conntrack_get() and nf_conntrack_put().
+ * Helper nf_ct_put() equals nf_conntrack_put() by dec refcnt,
+ * beware nf_ct_get() is different and don't inc refcnt.
+ */
struct nf_conntrack ct_general;
- spinlock_t lock;
+ spinlock_t lock;
+ u16 cpu;
/* XXX should I move this to the tail ? - Y.K */
/* These are my tuples; original and reply */
@@ -284,6 +291,8 @@
extern unsigned int nf_conntrack_hash_rnd;
void init_nf_conntrack_hash_rnd(void);
+void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl);
+
#define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count)
#define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 15308b8..cc0c188 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -77,6 +77,13 @@
const struct nf_conntrack_l3proto *l3proto,
const struct nf_conntrack_l4proto *proto);
-extern spinlock_t nf_conntrack_lock ;
+#ifdef CONFIG_LOCKDEP
+# define CONNTRACK_LOCKS 8
+#else
+# define CONNTRACK_LOCKS 1024
+#endif
+extern spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
+
+extern spinlock_t nf_conntrack_expect_lock;
#endif /* _NF_CONNTRACK_CORE_H */
diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h
index c985695..dec6336 100644
--- a/include/net/netfilter/nf_conntrack_labels.h
+++ b/include/net/netfilter/nf_conntrack_labels.h
@@ -7,6 +7,8 @@
#include <uapi/linux/netfilter/xt_connlabel.h>
+#define NF_CT_LABELS_MAX_SIZE ((XT_CONNLABEL_MAXBIT + 1) / BITS_PER_BYTE)
+
struct nf_conn_labels {
u8 words;
unsigned long bits[];
@@ -29,7 +31,7 @@
u8 words;
words = ACCESS_ONCE(net->ct.label_words);
- if (words == 0 || WARN_ON_ONCE(words > 8))
+ if (words == 0)
return NULL;
cl_ext = nf_ct_ext_add_length(ct, NF_CT_EXT_LABELS,
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 57c8ff7..e6bc14d 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -3,6 +3,7 @@
#include <linux/list.h>
#include <linux/netfilter.h>
+#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netlink.h>
@@ -252,6 +253,7 @@
* @owner: module reference
* @policy: netlink attribute policy
* @maxattr: highest netlink attribute number
+ * @family: address family for AF-specific types
*/
struct nft_expr_type {
const struct nft_expr_ops *(*select_ops)(const struct nft_ctx *,
@@ -262,6 +264,7 @@
struct module *owner;
const struct nla_policy *policy;
unsigned int maxattr;
+ u8 family;
};
/**
@@ -286,7 +289,8 @@
int (*init)(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[]);
- void (*destroy)(const struct nft_expr *expr);
+ void (*destroy)(const struct nft_ctx *ctx,
+ const struct nft_expr *expr);
int (*dump)(struct sk_buff *skb,
const struct nft_expr *expr);
int (*validate)(const struct nft_ctx *ctx,
@@ -320,18 +324,18 @@
* struct nft_rule - nf_tables rule
*
* @list: used internally
- * @rcu_head: used internally for rcu
* @handle: rule handle
* @genmask: generation mask
* @dlen: length of expression data
+ * @ulen: length of user data (used for comments)
* @data: expression data
*/
struct nft_rule {
struct list_head list;
- struct rcu_head rcu_head;
- u64 handle:46,
+ u64 handle:42,
genmask:2,
- dlen:16;
+ dlen:12,
+ ulen:8;
unsigned char data[]
__attribute__((aligned(__alignof__(struct nft_expr))));
};
@@ -340,19 +344,13 @@
* struct nft_rule_trans - nf_tables rule update in transaction
*
* @list: used internally
+ * @ctx: rule context
* @rule: rule that needs to be updated
- * @chain: chain that this rule belongs to
- * @table: table for which this chain applies
- * @nlh: netlink header of the message that contain this update
- * @family: family expressesed as AF_*
*/
struct nft_rule_trans {
struct list_head list;
+ struct nft_ctx ctx;
struct nft_rule *rule;
- const struct nft_chain *chain;
- const struct nft_table *table;
- const struct nlmsghdr *nlh;
- u8 family;
};
static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule)
@@ -370,6 +368,11 @@
return (struct nft_expr *)&rule->data[rule->dlen];
}
+static inline void *nft_userdata(const struct nft_rule *rule)
+{
+ return (void *)&rule->data[rule->dlen];
+}
+
/*
* The last pointer isn't really necessary, but the compiler isn't able to
* determine that the result of nft_expr_last() is always the same since it
@@ -389,7 +392,6 @@
*
* @rules: list of rules in the chain
* @list: used internally
- * @rcu_head: used internally
* @net: net namespace that this chain belongs to
* @table: table that this chain belongs to
* @handle: chain handle
@@ -401,7 +403,6 @@
struct nft_chain {
struct list_head rules;
struct list_head list;
- struct rcu_head rcu_head;
struct net *net;
struct nft_table *table;
u64 handle;
@@ -523,12 +524,18 @@
int nft_register_expr(struct nft_expr_type *);
void nft_unregister_expr(struct nft_expr_type *);
+#define nft_dereference(p) \
+ nfnl_dereference(p, NFNL_SUBSYS_NFTABLES)
+
#define MODULE_ALIAS_NFT_FAMILY(family) \
MODULE_ALIAS("nft-afinfo-" __stringify(family))
#define MODULE_ALIAS_NFT_CHAIN(family, name) \
MODULE_ALIAS("nft-chain-" __stringify(family) "-" name)
+#define MODULE_ALIAS_NFT_AF_EXPR(family, name) \
+ MODULE_ALIAS("nft-expr-" __stringify(family) "-" name)
+
#define MODULE_ALIAS_NFT_EXPR(name) \
MODULE_ALIAS("nft-expr-" name)
diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h
new file mode 100644
index 0000000..36b0da2
--- /dev/null
+++ b/include/net/netfilter/nft_reject.h
@@ -0,0 +1,25 @@
+#ifndef _NFT_REJECT_H_
+#define _NFT_REJECT_H_
+
+struct nft_reject {
+ enum nft_reject_types type:8;
+ u8 icmp_code;
+};
+
+extern const struct nla_policy nft_reject_policy[];
+
+int nft_reject_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[]);
+
+int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr);
+
+void nft_reject_ipv4_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt);
+
+void nft_reject_ipv6_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt);
+
+#endif
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index fbcc7fa..773cce3 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -5,6 +5,7 @@
#include <linux/list_nulls.h>
#include <linux/atomic.h>
#include <linux/netfilter/nf_conntrack_tcp.h>
+#include <linux/seqlock.h>
struct ctl_table_header;
struct nf_conntrack_ecache;
@@ -62,6 +63,13 @@
#endif
};
+struct ct_pcpu {
+ spinlock_t lock;
+ struct hlist_nulls_head unconfirmed;
+ struct hlist_nulls_head dying;
+ struct hlist_nulls_head tmpl;
+};
+
struct netns_ct {
atomic_t count;
unsigned int expect_count;
@@ -83,12 +91,11 @@
int sysctl_checksum;
unsigned int htable_size;
+ seqcount_t generation;
struct kmem_cache *nf_conntrack_cachep;
struct hlist_nulls_head *hash;
struct hlist_head *expect_hash;
- struct hlist_nulls_head unconfirmed;
- struct hlist_nulls_head dying;
- struct hlist_nulls_head tmpl;
+ struct ct_pcpu __percpu *pcpu_lists;
struct ip_conntrack_stat __percpu *stat;
struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
struct nf_exp_event_notifier __rcu *nf_expect_event_cb;
diff --git a/include/net/netns/ieee802154_6lowpan.h b/include/net/netns/ieee802154_6lowpan.h
new file mode 100644
index 0000000..079030c
--- /dev/null
+++ b/include/net/netns/ieee802154_6lowpan.h
@@ -0,0 +1,22 @@
+/*
+ * ieee802154 6lowpan in net namespaces
+ */
+
+#include <net/inet_frag.h>
+
+#ifndef __NETNS_IEEE802154_6LOWPAN_H__
+#define __NETNS_IEEE802154_6LOWPAN_H__
+
+struct netns_sysctl_lowpan {
+#ifdef CONFIG_SYSCTL
+ struct ctl_table_header *frags_hdr;
+#endif
+};
+
+struct netns_ieee802154_lowpan {
+ struct netns_sysctl_lowpan sysctl;
+ struct netns_frags frags;
+ u16 max_dsize;
+};
+
+#endif
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 1006a26..3492434 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -6,6 +6,7 @@
#include <linux/workqueue.h>
#include <linux/xfrm.h>
#include <net/dst_ops.h>
+#include <net/flowcache.h>
struct ctl_table_header;
@@ -58,9 +59,17 @@
struct dst_ops xfrm6_dst_ops;
#endif
spinlock_t xfrm_state_lock;
- spinlock_t xfrm_policy_sk_bundle_lock;
rwlock_t xfrm_policy_lock;
struct mutex xfrm_cfg_mutex;
+
+ /* flow cache part */
+ struct flow_cache flow_cache_global;
+ atomic_t flow_cache_genid;
+ struct list_head flow_cache_gc_list;
+ spinlock_t flow_cache_gc_lock;
+ struct work_struct flow_cache_gc_work;
+ struct work_struct flow_cache_flush_work;
+ struct mutex flow_flush_sem;
};
#endif
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index 99d2ba1..b23548e 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -52,7 +52,7 @@
* Note: This is in section 7.3.2 of the IEEE 802.15.4 document.
*/
int ieee802154_nl_assoc_confirm(struct net_device *dev,
- u16 short_addr, u8 status);
+ __le16 short_addr, u8 status);
/**
* ieee802154_nl_disassoc_indic - Notify userland of disassociation.
@@ -111,8 +111,8 @@
* Note: This API cannot indicate a beacon frame for a coordinator
* operating in long addressing mode.
*/
-int ieee802154_nl_beacon_indic(struct net_device *dev, u16 panid,
- u16 coord_addr);
+int ieee802154_nl_beacon_indic(struct net_device *dev, __le16 panid,
+ __le16 coord_addr);
/**
* ieee802154_nl_start_confirm - Notify userland of completion of start.
diff --git a/include/net/route.h b/include/net/route.h
index 9d1f423..b17cf28 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -191,7 +191,6 @@
void ip_rt_multicast_event(struct in_device *);
int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg);
void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
-int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb);
struct in_ifaddr;
void fib_add_ifaddr(struct in_ifaddr *);
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 661e45d..72240e5a 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -140,7 +140,7 @@
struct nlattr *tb[]);
int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm);
-extern const struct nla_policy ifla_policy[IFLA_MAX+1];
+int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len);
#define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind)
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index d992ca3..6ee76c8 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1653,17 +1653,6 @@
/* This is the last advertised value of rwnd over a SACK chunk. */
__u32 a_rwnd;
- /* Number of bytes by which the rwnd has slopped. The rwnd is allowed
- * to slop over a maximum of the association's frag_point.
- */
- __u32 rwnd_over;
-
- /* Keeps treack of rwnd pressure. This happens when we have
- * a window, but not recevie buffer (i.e small packets). This one
- * is releases slowly (1 PMTU at a time ).
- */
- __u32 rwnd_press;
-
/* This is the sndbuf size in use for the association.
* This corresponds to the sndbuf size for the association,
* as specified in the sk->sndbuf.
@@ -1892,8 +1881,7 @@
__u32 sctp_association_get_next_tsn(struct sctp_association *);
void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *);
-void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int);
-void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int);
+void sctp_assoc_rwnd_update(struct sctp_association *, bool);
void sctp_assoc_set_primary(struct sctp_association *,
struct sctp_transport *);
void sctp_assoc_del_nonprimary_peers(struct sctp_association *,
diff --git a/include/net/sock.h b/include/net/sock.h
index 5c3f7c3..06a5668 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -862,9 +862,9 @@
const struct sk_buff *skb)
{
#ifdef CONFIG_RPS
- if (unlikely(sk->sk_rxhash != skb->rxhash)) {
+ if (unlikely(sk->sk_rxhash != skb->hash)) {
sock_rps_reset_flow(sk);
- sk->sk_rxhash = skb->rxhash;
+ sk->sk_rxhash = skb->hash;
}
#endif
}
@@ -1488,6 +1488,11 @@
*/
#define sock_owned_by_user(sk) ((sk)->sk_lock.owned)
+static inline void sock_release_ownership(struct sock *sk)
+{
+ sk->sk_lock.owned = 0;
+}
+
/*
* Macro so as to not evaluate some arguments when
* lockdep is not enabled.
@@ -1616,33 +1621,6 @@
/* Initialise core socket variables */
void sock_init_data(struct socket *sock, struct sock *sk);
-void sk_filter_release_rcu(struct rcu_head *rcu);
-
-/**
- * sk_filter_release - release a socket filter
- * @fp: filter to remove
- *
- * Remove a filter from a socket and release its resources.
- */
-
-static inline void sk_filter_release(struct sk_filter *fp)
-{
- if (atomic_dec_and_test(&fp->refcnt))
- call_rcu(&fp->rcu, sk_filter_release_rcu);
-}
-
-static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
-{
- atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc);
- sk_filter_release(fp);
-}
-
-static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
-{
- atomic_inc(&fp->refcnt);
- atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc);
-}
-
/*
* Socket reference counting postulates.
*
@@ -2186,7 +2164,6 @@
{
#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \
(1UL << SOCK_RCVTSTAMP) | \
- (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \
(1UL << SOCK_TIMESTAMPING_SOFTWARE) | \
(1UL << SOCK_TIMESTAMPING_RAW_HARDWARE) | \
(1UL << SOCK_TIMESTAMPING_SYS_HARDWARE))
@@ -2252,8 +2229,12 @@
*/
static inline void sk_change_net(struct sock *sk, struct net *net)
{
- put_net(sock_net(sk));
- sock_net_set(sk, hold_net(net));
+ struct net *current_net = sock_net(sk);
+
+ if (!net_eq(current_net, net)) {
+ put_net(current_net);
+ sock_net_set(sk, hold_net(net));
+ }
}
static inline struct sock *skb_steal_sock(struct sk_buff *skb)
diff --git a/include/net/tc_act/tc_csum.h b/include/net/tc_act/tc_csum.h
index 9e8710b..fa8f5fa 100644
--- a/include/net/tc_act/tc_csum.h
+++ b/include/net/tc_act/tc_csum.h
@@ -9,7 +9,7 @@
u32 update_flags;
};
-#define to_tcf_csum(pc) \
- container_of(pc,struct tcf_csum,common)
+#define to_tcf_csum(a) \
+ container_of(a->priv,struct tcf_csum,common)
#endif /* __NET_TC_CSUM_H */
diff --git a/include/net/tc_act/tc_defact.h b/include/net/tc_act/tc_defact.h
index 65f024b..9763dcb 100644
--- a/include/net/tc_act/tc_defact.h
+++ b/include/net/tc_act/tc_defact.h
@@ -8,7 +8,7 @@
u32 tcfd_datalen;
void *tcfd_defdata;
};
-#define to_defact(pc) \
- container_of(pc, struct tcf_defact, common)
+#define to_defact(a) \
+ container_of(a->priv, struct tcf_defact, common)
#endif /* __NET_TC_DEF_H */
diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h
index 9e3f676..9fc9b57 100644
--- a/include/net/tc_act/tc_gact.h
+++ b/include/net/tc_act/tc_gact.h
@@ -11,7 +11,7 @@
int tcfg_paction;
#endif
};
-#define to_gact(pc) \
- container_of(pc, struct tcf_gact, common)
+#define to_gact(a) \
+ container_of(a->priv, struct tcf_gact, common)
#endif /* __NET_TC_GACT_H */
diff --git a/include/net/tc_act/tc_ipt.h b/include/net/tc_act/tc_ipt.h
index f7d25df..c0f4193 100644
--- a/include/net/tc_act/tc_ipt.h
+++ b/include/net/tc_act/tc_ipt.h
@@ -11,7 +11,7 @@
char *tcfi_tname;
struct xt_entry_target *tcfi_t;
};
-#define to_ipt(pc) \
- container_of(pc, struct tcf_ipt, common)
+#define to_ipt(a) \
+ container_of(a->priv, struct tcf_ipt, common)
#endif /* __NET_TC_IPT_H */
diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h
index cfe2943..4dd77a1 100644
--- a/include/net/tc_act/tc_mirred.h
+++ b/include/net/tc_act/tc_mirred.h
@@ -11,7 +11,7 @@
struct net_device *tcfm_dev;
struct list_head tcfm_list;
};
-#define to_mirred(pc) \
- container_of(pc, struct tcf_mirred, common)
+#define to_mirred(a) \
+ container_of(a->priv, struct tcf_mirred, common)
#endif /* __NET_TC_MIR_H */
diff --git a/include/net/tc_act/tc_nat.h b/include/net/tc_act/tc_nat.h
index 4a691f3..63d8e9c 100644
--- a/include/net/tc_act/tc_nat.h
+++ b/include/net/tc_act/tc_nat.h
@@ -13,9 +13,9 @@
u32 flags;
};
-static inline struct tcf_nat *to_tcf_nat(struct tcf_common *pc)
+static inline struct tcf_nat *to_tcf_nat(struct tc_action *a)
{
- return container_of(pc, struct tcf_nat, common);
+ return container_of(a->priv, struct tcf_nat, common);
}
#endif /* __NET_TC_NAT_H */
diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h
index e6f6e15..5b80998 100644
--- a/include/net/tc_act/tc_pedit.h
+++ b/include/net/tc_act/tc_pedit.h
@@ -9,7 +9,7 @@
unsigned char tcfp_flags;
struct tc_pedit_key *tcfp_keys;
};
-#define to_pedit(pc) \
- container_of(pc, struct tcf_pedit, common)
+#define to_pedit(a) \
+ container_of(a->priv, struct tcf_pedit, common)
#endif /* __NET_TC_PED_H */
diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h
index dd5d86f..0df9a0d 100644
--- a/include/net/tc_act/tc_skbedit.h
+++ b/include/net/tc_act/tc_skbedit.h
@@ -29,7 +29,7 @@
u16 queue_mapping;
/* XXX: 16-bit pad here? */
};
-#define to_skbedit(pc) \
- container_of(pc, struct tcf_skbedit, common)
+#define to_skbedit(a) \
+ container_of(a->priv, struct tcf_skbedit, common)
#endif /* __NET_TC_SKBEDIT_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 56fc366..87d8774 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -31,6 +31,7 @@
#include <linux/crypto.h>
#include <linux/cryptohash.h>
#include <linux/kref.h>
+#include <linux/ktime.h>
#include <net/inet_connection_sock.h>
#include <net/inet_timewait_sock.h>
@@ -478,22 +479,22 @@
struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
struct ip_options *opt);
#ifdef CONFIG_SYN_COOKIES
-#include <linux/ktime.h>
-/* Syncookies use a monotonic timer which increments every 64 seconds.
+/* Syncookies use a monotonic timer which increments every 60 seconds.
* This counter is used both as a hash input and partially encoded into
* the cookie value. A cookie is only validated further if the delta
* between the current counter value and the encoded one is less than this,
- * i.e. a sent cookie is valid only at most for 128 seconds (or less if
+ * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if
* the counter advances immediately after a cookie is generated).
*/
#define MAX_SYNCOOKIE_AGE 2
static inline u32 tcp_cookie_time(void)
{
- struct timespec now;
- getnstimeofday(&now);
- return now.tv_sec >> 6; /* 64 seconds granularity */
+ u64 val = get_jiffies_64();
+
+ do_div(val, 60 * HZ);
+ return val;
}
u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
@@ -619,7 +620,7 @@
static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
{
- return (tp->srtt >> 3) + tp->rttvar;
+ return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us);
}
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
@@ -656,6 +657,11 @@
return rto_min;
}
+static inline u32 tcp_rto_min_us(struct sock *sk)
+{
+ return jiffies_to_usecs(tcp_rto_min(sk));
+}
+
/* Compute the actual receive window we are currently advertising.
* Rcv_nxt can be after the window if our peer push more data
* than the offered window.
@@ -778,7 +784,6 @@
#define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX)
#define TCP_CONG_NON_RESTRICTED 0x1
-#define TCP_CONG_RTT_STAMP 0x2
struct tcp_congestion_ops {
struct list_head list;
@@ -791,8 +796,6 @@
/* return slow start threshold (required) */
u32 (*ssthresh)(struct sock *sk);
- /* lower bound for congestion window (optional) */
- u32 (*min_cwnd)(const struct sock *sk);
/* do new cwnd calculation (required) */
void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked, u32 in_flight);
/* call before changing ca_state (optional) */
@@ -827,7 +830,6 @@
extern struct tcp_congestion_ops tcp_init_congestion_ops;
u32 tcp_reno_ssthresh(struct sock *sk);
void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight);
-u32 tcp_reno_min_cwnd(const struct sock *sk);
extern struct tcp_congestion_ops tcp_reno;
static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
@@ -1303,7 +1305,8 @@
/* Fast Open cookie. Size 0 means a cookie request */
struct tcp_fastopen_cookie cookie;
struct msghdr *data; /* data in MSG_FASTOPEN */
- u16 copied; /* queued in tcp_connect() */
+ size_t size;
+ int copied; /* queued in tcp_connect() */
};
void tcp_free_fastopen_req(struct tcp_sock *tp);
diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h
index b52bda8..10ab0fc 100644
--- a/include/net/wpan-phy.h
+++ b/include/net/wpan-phy.h
@@ -37,15 +37,22 @@
struct mutex pib_lock;
/*
- * This is a PIB according to 802.15.4-2006.
+ * This is a PIB according to 802.15.4-2011.
* We do not provide timing-related variables, as they
* aren't used outside of driver
*/
u8 current_channel;
u8 current_page;
u32 channels_supported[32];
- u8 transmit_power;
+ s8 transmit_power;
u8 cca_mode;
+ u8 min_be;
+ u8 max_be;
+ u8 csma_retries;
+ s8 frame_retries;
+
+ bool lbt;
+ s32 cca_ed_level;
struct device dev;
int idx;
@@ -54,6 +61,14 @@
const char *name, int type);
void (*del_iface)(struct wpan_phy *phy, struct net_device *dev);
+ int (*set_txpower)(struct wpan_phy *phy, int db);
+ int (*set_lbt)(struct wpan_phy *phy, bool on);
+ int (*set_cca_mode)(struct wpan_phy *phy, u8 cca_mode);
+ int (*set_cca_ed_level)(struct wpan_phy *phy, int level);
+ int (*set_csma_params)(struct wpan_phy *phy, u8 min_be, u8 max_be,
+ u8 retries);
+ int (*set_frame_retries)(struct wpan_phy *phy, s8 retries);
+
char priv[0] __attribute__((__aligned__(NETDEV_ALIGN)));
};
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index afa5730..32682ae 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -118,11 +118,10 @@
struct xfrm_state_walk {
struct list_head all;
u8 state;
- union {
- u8 dying;
- u8 proto;
- };
+ u8 dying;
+ u8 proto;
u32 seq;
+ struct xfrm_address_filter *filter;
};
/* Full description of state of transformer. */
@@ -350,6 +349,16 @@
struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family);
void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo);
+struct xfrm_input_afinfo {
+ unsigned int family;
+ struct module *owner;
+ int (*callback)(struct sk_buff *skb, u8 protocol,
+ int err);
+};
+
+int xfrm_input_register_afinfo(struct xfrm_input_afinfo *afinfo);
+int xfrm_input_unregister_afinfo(struct xfrm_input_afinfo *afinfo);
+
void xfrm_state_delete_tunnel(struct xfrm_state *x);
struct xfrm_type {
@@ -594,21 +603,33 @@
const struct xfrm_migrate *m,
int num_bundles,
const struct xfrm_kmaddress *k);
+ bool (*is_alive)(const struct km_event *c);
};
int xfrm_register_km(struct xfrm_mgr *km);
int xfrm_unregister_km(struct xfrm_mgr *km);
+struct xfrm_tunnel_skb_cb {
+ union {
+ struct inet_skb_parm h4;
+ struct inet6_skb_parm h6;
+ } header;
+
+ union {
+ struct ip_tunnel *ip4;
+ struct ip6_tnl *ip6;
+ } tunnel;
+};
+
+#define XFRM_TUNNEL_SKB_CB(__skb) ((struct xfrm_tunnel_skb_cb *)&((__skb)->cb[0]))
+
/*
* This structure is used for the duration where packets are being
* transformed by IPsec. As soon as the packet leaves IPsec the
* area beyond the generic IP part may be overwritten.
*/
struct xfrm_skb_cb {
- union {
- struct inet_skb_parm h4;
- struct inet6_skb_parm h6;
- } header;
+ struct xfrm_tunnel_skb_cb header;
/* Sequence number for replay protection. */
union {
@@ -630,10 +651,7 @@
* to transmit header information to the mode input/output functions.
*/
struct xfrm_mode_skb_cb {
- union {
- struct inet_skb_parm h4;
- struct inet6_skb_parm h6;
- } header;
+ struct xfrm_tunnel_skb_cb header;
/* Copied from header for IPv4, always set to zero and DF for IPv6. */
__be16 id;
@@ -665,10 +683,7 @@
* related information.
*/
struct xfrm_spi_skb_cb {
- union {
- struct inet_skb_parm h4;
- struct inet6_skb_parm h6;
- } header;
+ struct xfrm_tunnel_skb_cb header;
unsigned int daddroff;
unsigned int family;
@@ -1347,6 +1362,28 @@
struct sadb_alg desc;
};
+/* XFRM protocol handlers. */
+struct xfrm4_protocol {
+ int (*handler)(struct sk_buff *skb);
+ int (*input_handler)(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type);
+ int (*cb_handler)(struct sk_buff *skb, int err);
+ int (*err_handler)(struct sk_buff *skb, u32 info);
+
+ struct xfrm4_protocol __rcu *next;
+ int priority;
+};
+
+struct xfrm6_protocol {
+ int (*handler)(struct sk_buff *skb);
+ int (*cb_handler)(struct sk_buff *skb, int err);
+ int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info);
+
+ struct xfrm6_protocol __rcu *next;
+ int priority;
+};
+
/* XFRM tunnel handlers. */
struct xfrm_tunnel {
int (*handler)(struct sk_buff *skb);
@@ -1356,12 +1393,6 @@
int priority;
};
-struct xfrm_tunnel_notifier {
- int (*handler)(struct sk_buff *skb);
- struct xfrm_tunnel_notifier __rcu *next;
- int priority;
-};
-
struct xfrm6_tunnel {
int (*handler)(struct sk_buff *skb);
int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
@@ -1375,11 +1406,14 @@
int xfrm_state_init(struct net *net);
void xfrm_state_fini(struct net *net);
void xfrm4_state_init(void);
+void xfrm4_protocol_init(void);
#ifdef CONFIG_XFRM
int xfrm6_init(void);
void xfrm6_fini(void);
int xfrm6_state_init(void);
void xfrm6_state_fini(void);
+int xfrm6_protocol_init(void);
+void xfrm6_protocol_fini(void);
#else
static inline int xfrm6_init(void)
{
@@ -1405,7 +1439,8 @@
}
#endif
-void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto);
+void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto,
+ struct xfrm_address_filter *filter);
int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
int (*func)(struct xfrm_state *, int, void*), void *);
void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net);
@@ -1497,20 +1532,22 @@
static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
{
- return xfrm4_rcv_encap(skb, nexthdr, spi, 0);
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+ XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+ XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+ return xfrm_input(skb, nexthdr, spi, 0);
}
int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb);
int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
int xfrm4_output(struct sk_buff *skb);
int xfrm4_output_finish(struct sk_buff *skb);
+int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err);
+int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol);
+int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol);
int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family);
int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family);
void xfrm4_local_error(struct sk_buff *skb, u32 mtu);
-int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler);
-int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler);
-int xfrm6_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler);
-int xfrm6_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler);
int xfrm6_extract_header(struct sk_buff *skb);
int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb);
int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi);
@@ -1519,6 +1556,9 @@
int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
xfrm_address_t *saddr, u8 proto);
void xfrm6_local_error(struct sk_buff *skb, u32 mtu);
+int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err);
+int xfrm6_protocol_register(struct xfrm6_protocol *handler, unsigned char protocol);
+int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, unsigned char protocol);
int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family);
int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family);
__be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr);
@@ -1646,8 +1686,27 @@
rcu_read_unlock();
return ret;
}
+
+static inline int xfrm_acquire_is_on(struct net *net)
+{
+ struct sock *nlsk;
+ int ret = 0;
+
+ rcu_read_lock();
+ nlsk = rcu_dereference(net->xfrm.nlsk);
+ if (nlsk)
+ ret = netlink_has_listeners(nlsk, XFRMNLGRP_ACQUIRE);
+ rcu_read_unlock();
+
+ return ret;
+}
#endif
+static inline int aead_len(struct xfrm_algo_aead *alg)
+{
+ return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
+}
+
static inline int xfrm_alg_len(const struct xfrm_algo *alg)
{
return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
@@ -1686,6 +1745,12 @@
return 0;
}
+static inline struct xfrm_algo_aead *xfrm_algo_aead_clone(struct xfrm_algo_aead *orig)
+{
+ return kmemdup(orig, aead_len(orig), GFP_KERNEL);
+}
+
+
static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig)
{
return kmemdup(orig, xfrm_alg_len(orig), GFP_KERNEL);
@@ -1737,4 +1802,24 @@
return ret;
}
+static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x,
+ unsigned int family)
+{
+ bool tunnel = false;
+
+ switch(family) {
+ case AF_INET:
+ if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4)
+ tunnel = true;
+ break;
+ case AF_INET6:
+ if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6)
+ tunnel = true;
+ break;
+ }
+ if (tunnel && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL))
+ return -EINVAL;
+
+ return 0;
+}
#endif /* _NET_XFRM_H */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 8d4a1c0..6793f32 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -226,7 +226,8 @@
IB_PORT_CAP_MASK_NOTICE_SUP = 1 << 22,
IB_PORT_BOOT_MGMT_SUP = 1 << 23,
IB_PORT_LINK_LATENCY_SUP = 1 << 24,
- IB_PORT_CLIENT_REG_SUP = 1 << 25
+ IB_PORT_CLIENT_REG_SUP = 1 << 25,
+ IB_PORT_IP_BASED_GIDS = 1 << 26
};
enum ib_port_width {
diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 68d92e3..6e89ef6 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -449,14 +449,22 @@
/* dapm audio pin control and status */
int snd_soc_dapm_enable_pin(struct snd_soc_dapm_context *dapm,
const char *pin);
+int snd_soc_dapm_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+ const char *pin);
int snd_soc_dapm_disable_pin(struct snd_soc_dapm_context *dapm,
const char *pin);
+int snd_soc_dapm_disable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+ const char *pin);
int snd_soc_dapm_nc_pin(struct snd_soc_dapm_context *dapm, const char *pin);
+int snd_soc_dapm_nc_pin_unlocked(struct snd_soc_dapm_context *dapm,
+ const char *pin);
int snd_soc_dapm_get_pin_status(struct snd_soc_dapm_context *dapm,
const char *pin);
int snd_soc_dapm_sync(struct snd_soc_dapm_context *dapm);
int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm,
const char *pin);
+int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+ const char *pin);
int snd_soc_dapm_ignore_suspend(struct snd_soc_dapm_context *dapm,
const char *pin);
void snd_soc_dapm_auto_nc_codec_pins(struct snd_soc_codec *codec);
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index ae5a171..4483fad 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -12,6 +12,7 @@
int (*iscsit_setup_np)(struct iscsi_np *, struct __kernel_sockaddr_storage *);
int (*iscsit_accept_np)(struct iscsi_np *, struct iscsi_conn *);
void (*iscsit_free_np)(struct iscsi_np *);
+ void (*iscsit_wait_conn)(struct iscsi_conn *);
void (*iscsit_free_conn)(struct iscsi_conn *);
int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *);
int (*iscsit_put_login_tx)(struct iscsi_conn *, struct iscsi_login *, u32);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index c9c7912..1772fad 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -525,7 +525,6 @@
#define CMD_T_COMPLETE (1 << 2)
#define CMD_T_SENT (1 << 4)
#define CMD_T_STOP (1 << 5)
-#define CMD_T_FAILED (1 << 6)
#define CMD_T_DEV_ACTIVE (1 << 7)
#define CMD_T_REQUEST_STOP (1 << 8)
#define CMD_T_BUSY (1 << 9)
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index a34f27b..1de256b 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -153,8 +153,8 @@
__field( u16, vlan_tci )
__field( u16, protocol )
__field( u8, ip_summed )
- __field( u32, rxhash )
- __field( bool, l4_rxhash )
+ __field( u32, hash )
+ __field( bool, l4_hash )
__field( unsigned int, len )
__field( unsigned int, data_len )
__field( unsigned int, truesize )
@@ -179,8 +179,8 @@
__entry->vlan_tci = vlan_tx_tag_get(skb);
__entry->protocol = ntohs(skb->protocol);
__entry->ip_summed = skb->ip_summed;
- __entry->rxhash = skb->rxhash;
- __entry->l4_rxhash = skb->l4_rxhash;
+ __entry->hash = skb->hash;
+ __entry->l4_hash = skb->l4_hash;
__entry->len = skb->len;
__entry->data_len = skb->data_len;
__entry->truesize = skb->truesize;
@@ -191,11 +191,11 @@
__entry->gso_type = skb_shinfo(skb)->gso_type;
),
- TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d rxhash=0x%08x l4_rxhash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x",
+ TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x",
__get_str(name), __entry->napi_id, __entry->queue_mapping,
__entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto,
__entry->vlan_tci, __entry->protocol, __entry->ip_summed,
- __entry->rxhash, __entry->l4_rxhash, __entry->len,
+ __entry->hash, __entry->l4_hash, __entry->len,
__entry->data_len, __entry->truesize,
__entry->mac_header_valid, __entry->mac_header,
__entry->nr_frags, __entry->gso_size, __entry->gso_type)
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 9e9475c..e5bf9a7 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -42,7 +42,6 @@
u32 state,
u64 mperf,
u64 aperf,
- u32 energy,
u32 freq
),
@@ -51,7 +50,6 @@
state,
mperf,
aperf,
- energy,
freq
),
@@ -61,7 +59,6 @@
__field(u32, state)
__field(u64, mperf)
__field(u64, aperf)
- __field(u32, energy)
__field(u32, freq)
),
@@ -72,17 +69,15 @@
__entry->state = state;
__entry->mperf = mperf;
__entry->aperf = aperf;
- __entry->energy = energy;
__entry->freq = freq;
),
- TP_printk("core_busy=%lu scaled=%lu state=%lu mperf=%llu aperf=%llu energy=%lu freq=%lu ",
+ TP_printk("core_busy=%lu scaled=%lu state=%lu mperf=%llu aperf=%llu freq=%lu ",
(unsigned long)__entry->core_busy,
(unsigned long)__entry->scaled_busy,
(unsigned long)__entry->state,
(unsigned long long)__entry->mperf,
(unsigned long long)__entry->aperf,
- (unsigned long)__entry->energy,
(unsigned long)__entry->freq
)
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index ddc179b..1fef3e6 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -83,7 +83,7 @@
),
TP_fast_assign(
- __entry->client_id = clnt->cl_clid;
+ __entry->client_id = clnt ? clnt->cl_clid : -1;
__entry->task_id = task->tk_pid;
__entry->action = action;
__entry->runstate = task->tk_runstate;
@@ -91,7 +91,7 @@
__entry->flags = task->tk_flags;
),
- TP_printk("task:%u@%u flags=%4.4x state=%4.4lx status=%d action=%pf",
+ TP_printk("task:%u@%d flags=%4.4x state=%4.4lx status=%d action=%pf",
__entry->task_id, __entry->client_id,
__entry->flags,
__entry->runstate,
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index c7bbbe7..464ea82 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -287,11 +287,11 @@
__field(int, reason)
),
TP_fast_assign(
- unsigned long older_than_this = work->older_than_this;
+ unsigned long *older_than_this = work->older_than_this;
strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
- __entry->older = older_than_this;
+ __entry->older = older_than_this ? *older_than_this : 0;
__entry->age = older_than_this ?
- (jiffies - older_than_this) * 1000 / HZ : -1;
+ (jiffies - *older_than_this) * 1000 / HZ : -1;
__entry->moved = moved;
__entry->reason = work->reason;
),
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 1a8b28d..1ee19a2 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -310,15 +310,12 @@
#undef __array
#define __array(type, item, len) \
do { \
- mutex_lock(&event_storage_mutex); \
+ char *type_str = #type"["__stringify(len)"]"; \
BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
- snprintf(event_storage, sizeof(event_storage), \
- "%s[%d]", #type, len); \
- ret = trace_define_field(event_call, event_storage, #item, \
+ ret = trace_define_field(event_call, type_str, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), FILTER_OTHER); \
- mutex_unlock(&event_storage_mutex); \
if (ret) \
return ret; \
} while (0);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index a20a9b4..dde8041 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -692,9 +692,13 @@
__SYSCALL(__NR_kcmp, sys_kcmp)
#define __NR_finit_module 273
__SYSCALL(__NR_finit_module, sys_finit_module)
+#define __NR_sched_setattr 274
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+#define __NR_sched_getattr 275
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
#undef __NR_syscalls
-#define __NR_syscalls 274
+#define __NR_syscalls 276
/*
* All syscalls below here should go away really,
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 3c9a833..b06c8ed 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -619,6 +619,8 @@
#define DRM_PRIME_CAP_EXPORT 0x2
#define DRM_CAP_TIMESTAMP_MONOTONIC 0x6
#define DRM_CAP_ASYNC_PAGE_FLIP 0x7
+#define DRM_CAP_CURSOR_WIDTH 0x8
+#define DRM_CAP_CURSOR_HEIGHT 0x9
/** DRM_IOCTL_GET_CAP ioctl argument type */
struct drm_get_cap {
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 9971c56..87792a5 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -87,6 +87,7 @@
#define DRM_VMW_PARAM_MAX_SURF_MEMORY 7
#define DRM_VMW_PARAM_3D_CAPS_SIZE 8
#define DRM_VMW_PARAM_MAX_MOB_MEMORY 9
+#define DRM_VMW_PARAM_MAX_MOB_SIZE 10
/**
* struct drm_vmw_getparam_arg
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 1b8a0f4..b4d6909 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -558,7 +558,6 @@
#define BTRFS_IOC_DEFAULT_SUBVOL _IOW(BTRFS_IOCTL_MAGIC, 19, __u64)
#define BTRFS_IOC_SPACE_INFO _IOWR(BTRFS_IOCTL_MAGIC, 20, \
struct btrfs_ioctl_space_args)
-#define BTRFS_IOC_GLOBAL_RSV _IOR(BTRFS_IOCTL_MAGIC, 20, __u64)
#define BTRFS_IOC_START_SYNC _IOR(BTRFS_IOCTL_MAGIC, 24, __u64)
#define BTRFS_IOC_WAIT_SYNC _IOW(BTRFS_IOCTL_MAGIC, 22, __u64)
#define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \
diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h
index e52958d..5d9d1d1 100644
--- a/include/uapi/linux/can.h
+++ b/include/uapi/linux/can.h
@@ -8,6 +8,38 @@
* Copyright (c) 2002-2007 Volkswagen Group Electronic Research
* All rights reserved.
*
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of Volkswagen nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * The provided data structures and external interfaces from this code
+ * are not restricted to be used by modules with a GPL compatible license.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
*/
#ifndef CAN_H
diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h
index df944ed..7e2e186 100644
--- a/include/uapi/linux/can/netlink.h
+++ b/include/uapi/linux/can/netlink.h
@@ -96,6 +96,7 @@
#define CAN_CTRLMODE_3_SAMPLES 0x04 /* Triple sampling mode */
#define CAN_CTRLMODE_ONE_SHOT 0x08 /* One-Shot mode */
#define CAN_CTRLMODE_BERR_REPORTING 0x10 /* Bus-error reporting */
+#define CAN_CTRLMODE_FD 0x20 /* CAN FD mode */
/*
* CAN device statistics
@@ -122,6 +123,8 @@
IFLA_CAN_RESTART_MS,
IFLA_CAN_RESTART,
IFLA_CAN_BERR_COUNTER,
+ IFLA_CAN_DATA_BITTIMING,
+ IFLA_CAN_DATA_BITTIMING_CONST,
__IFLA_CAN_MAX
};
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 38dbafa..fd161e9 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -16,37 +16,97 @@
#include <linux/types.h>
#include <linux/if_ether.h>
-/* This should work for both 32 and 64 bit userland. */
+/* All structures exposed to userland should be defined such that they
+ * have the same layout for 32-bit and 64-bit userland.
+ */
+
+/**
+ * struct ethtool_cmd - link control and status
+ * @cmd: Command number = %ETHTOOL_GSET or %ETHTOOL_SSET
+ * @supported: Bitmask of %SUPPORTED_* flags for the link modes,
+ * physical connectors and other link features for which the
+ * interface supports autonegotiation or auto-detection.
+ * Read-only.
+ * @advertising: Bitmask of %ADVERTISED_* flags for the link modes,
+ * physical connectors and other link features that are
+ * advertised through autonegotiation or enabled for
+ * auto-detection.
+ * @speed: Low bits of the speed
+ * @duplex: Duplex mode; one of %DUPLEX_*
+ * @port: Physical connector type; one of %PORT_*
+ * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not
+ * applicable. For clause 45 PHYs this is the PRTAD.
+ * @transceiver: Historically used to distinguish different possible
+ * PHY types, but not in a consistent way. Deprecated.
+ * @autoneg: Enable/disable autonegotiation and auto-detection;
+ * either %AUTONEG_DISABLE or %AUTONEG_ENABLE
+ * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO
+ * protocols supported by the interface; 0 if unknown.
+ * Read-only.
+ * @maxtxpkt: Historically used to report TX IRQ coalescing; now
+ * obsoleted by &struct ethtool_coalesce. Read-only; deprecated.
+ * @maxrxpkt: Historically used to report RX IRQ coalescing; now
+ * obsoleted by &struct ethtool_coalesce. Read-only; deprecated.
+ * @speed_hi: High bits of the speed
+ * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of
+ * %ETH_TP_MDI_*. If the status is unknown or not applicable, the
+ * value will be %ETH_TP_MDI_INVALID. Read-only.
+ * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of
+ * %ETH_TP_MDI_*. If MDI(-X) control is not implemented, reads
+ * yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected.
+ * When written successfully, the link should be renegotiated if
+ * necessary.
+ * @lp_advertising: Bitmask of %ADVERTISED_* flags for the link modes
+ * and other link features that the link partner advertised
+ * through autonegotiation; 0 if unknown or not applicable.
+ * Read-only.
+ *
+ * The link speed in Mbps is split between @speed and @speed_hi. Use
+ * the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to
+ * access it.
+ *
+ * If autonegotiation is disabled, the speed and @duplex represent the
+ * fixed link mode and are writable if the driver supports multiple
+ * link modes. If it is enabled then they are read-only; if the link
+ * is up they represent the negotiated link mode; if the link is down,
+ * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and
+ * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode.
+ *
+ * Some hardware interfaces may have multiple PHYs and/or physical
+ * connectors fitted or do not allow the driver to detect which are
+ * fitted. For these interfaces @port and/or @phy_address may be
+ * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE.
+ * Otherwise, attempts to write different values may be ignored or
+ * rejected.
+ *
+ * Users should assume that all fields not marked read-only are
+ * writable and subject to validation by the driver. They should use
+ * %ETHTOOL_GSET to get the current values before making specific
+ * changes and then applying them with %ETHTOOL_SSET.
+ *
+ * Drivers that implement set_settings() should validate all fields
+ * other than @cmd that are not described as read-only or deprecated,
+ * and must ignore all fields described as read-only.
+ *
+ * Deprecated fields should be ignored by both users and drivers.
+ */
struct ethtool_cmd {
__u32 cmd;
- __u32 supported; /* Features this interface supports */
- __u32 advertising; /* Features this interface advertises */
- __u16 speed; /* The forced speed (lower bits) in
- * Mbps. Please use
- * ethtool_cmd_speed()/_set() to
- * access it */
- __u8 duplex; /* Duplex, half or full */
- __u8 port; /* Which connector port */
- __u8 phy_address; /* MDIO PHY address (PRTAD for clause 45).
- * May be read-only or read-write
- * depending on the driver.
- */
- __u8 transceiver; /* Which transceiver to use */
- __u8 autoneg; /* Enable or disable autonegotiation */
- __u8 mdio_support; /* MDIO protocols supported. Read-only.
- * Not set by all drivers.
- */
- __u32 maxtxpkt; /* Tx pkts before generating tx int */
- __u32 maxrxpkt; /* Rx pkts before generating rx int */
- __u16 speed_hi; /* The forced speed (upper
- * bits) in Mbps. Please use
- * ethtool_cmd_speed()/_set() to
- * access it */
- __u8 eth_tp_mdix; /* twisted pair MDI-X status */
- __u8 eth_tp_mdix_ctrl; /* twisted pair MDI-X control, when set,
- * link should be renegotiated if necessary
- */
- __u32 lp_advertising; /* Features the link partner advertises */
+ __u32 supported;
+ __u32 advertising;
+ __u16 speed;
+ __u8 duplex;
+ __u8 port;
+ __u8 phy_address;
+ __u8 transceiver;
+ __u8 autoneg;
+ __u8 mdio_support;
+ __u32 maxtxpkt;
+ __u32 maxrxpkt;
+ __u16 speed_hi;
+ __u8 eth_tp_mdix;
+ __u8 eth_tp_mdix_ctrl;
+ __u32 lp_advertising;
__u32 reserved[2];
};
@@ -79,37 +139,68 @@
#define ETHTOOL_FWVERS_LEN 32
#define ETHTOOL_BUSINFO_LEN 32
-/* these strings are set to whatever the driver author decides... */
+
+/**
+ * struct ethtool_drvinfo - general driver and device information
+ * @cmd: Command number = %ETHTOOL_GDRVINFO
+ * @driver: Driver short name. This should normally match the name
+ * in its bus driver structure (e.g. pci_driver::name). Must
+ * not be an empty string.
+ * @version: Driver version string; may be an empty string
+ * @fw_version: Firmware version string; may be an empty string
+ * @bus_info: Device bus address. This should match the dev_name()
+ * string for the underlying bus device, if there is one. May be
+ * an empty string.
+ * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and
+ * %ETHTOOL_SPFLAGS commands; also the number of strings in the
+ * %ETH_SS_PRIV_FLAGS set
+ * @n_stats: Number of u64 statistics returned by the %ETHTOOL_GSTATS
+ * command; also the number of strings in the %ETH_SS_STATS set
+ * @testinfo_len: Number of results returned by the %ETHTOOL_TEST
+ * command; also the number of strings in the %ETH_SS_TEST set
+ * @eedump_len: Size of EEPROM accessible through the %ETHTOOL_GEEPROM
+ * and %ETHTOOL_SEEPROM commands, in bytes
+ * @regdump_len: Size of register dump returned by the %ETHTOOL_GREGS
+ * command, in bytes
+ *
+ * Users can use the %ETHTOOL_GSSET_INFO command to get the number of
+ * strings in any string set (from Linux 2.6.34).
+ *
+ * Drivers should set at most @driver, @version, @fw_version and
+ * @bus_info in their get_drvinfo() implementation. The ethtool
+ * core fills in the other fields using other driver operations.
+ */
struct ethtool_drvinfo {
__u32 cmd;
- char driver[32]; /* driver short name, "tulip", "eepro100" */
- char version[32]; /* driver version string */
- char fw_version[ETHTOOL_FWVERS_LEN]; /* firmware version string */
- char bus_info[ETHTOOL_BUSINFO_LEN]; /* Bus info for this IF. */
- /* For PCI devices, use pci_name(pci_dev). */
+ char driver[32];
+ char version[32];
+ char fw_version[ETHTOOL_FWVERS_LEN];
+ char bus_info[ETHTOOL_BUSINFO_LEN];
char reserved1[32];
char reserved2[12];
- /*
- * Some struct members below are filled in
- * using ops->get_sset_count(). Obtaining
- * this info from ethtool_drvinfo is now
- * deprecated; Use ETHTOOL_GSSET_INFO
- * instead.
- */
- __u32 n_priv_flags; /* number of flags valid in ETHTOOL_GPFLAGS */
- __u32 n_stats; /* number of u64's from ETHTOOL_GSTATS */
+ __u32 n_priv_flags;
+ __u32 n_stats;
__u32 testinfo_len;
- __u32 eedump_len; /* Size of data from ETHTOOL_GEEPROM (bytes) */
- __u32 regdump_len; /* Size of data from ETHTOOL_GREGS (bytes) */
+ __u32 eedump_len;
+ __u32 regdump_len;
};
#define SOPASS_MAX 6
-/* wake-on-lan settings */
+
+/**
+ * struct ethtool_wolinfo - Wake-On-Lan configuration
+ * @cmd: Command number = %ETHTOOL_GWOL or %ETHTOOL_SWOL
+ * @supported: Bitmask of %WAKE_* flags for supported Wake-On-Lan modes.
+ * Read-only.
+ * @wolopts: Bitmask of %WAKE_* flags for enabled Wake-On-Lan modes.
+ * @sopass: SecureOn(tm) password; meaningful only if %WAKE_MAGICSECURE
+ * is set in @wolopts.
+ */
struct ethtool_wolinfo {
__u32 cmd;
__u32 supported;
__u32 wolopts;
- __u8 sopass[SOPASS_MAX]; /* SecureOn(tm) password */
+ __u8 sopass[SOPASS_MAX];
};
/* for passing single values */
@@ -118,20 +209,51 @@
__u32 data;
};
-/* for passing big chunks of data */
+/**
+ * struct ethtool_regs - hardware register dump
+ * @cmd: Command number = %ETHTOOL_GREGS
+ * @version: Dump format version. This is driver-specific and may
+ * distinguish different chips/revisions. Drivers must use new
+ * version numbers whenever the dump format changes in an
+ * incompatible way.
+ * @len: On entry, the real length of @data. On return, the number of
+ * bytes used.
+ * @data: Buffer for the register dump
+ *
+ * Users should use %ETHTOOL_GDRVINFO to find the maximum length of
+ * a register dump for the interface. They must allocate the buffer
+ * immediately following this structure.
+ */
struct ethtool_regs {
__u32 cmd;
- __u32 version; /* driver-specific, indicates different chips/revs */
- __u32 len; /* bytes */
+ __u32 version;
+ __u32 len;
__u8 data[0];
};
-/* for passing EEPROM chunks */
+/**
+ * struct ethtool_eeprom - EEPROM dump
+ * @cmd: Command number = %ETHTOOL_GEEPROM, %ETHTOOL_GMODULEEEPROM or
+ * %ETHTOOL_SEEPROM
+ * @magic: A 'magic cookie' value to guard against accidental changes.
+ * The value passed in to %ETHTOOL_SEEPROM must match the value
+ * returned by %ETHTOOL_GEEPROM for the same device. This is
+ * unused when @cmd is %ETHTOOL_GMODULEEEPROM.
+ * @offset: Offset within the EEPROM to begin reading/writing, in bytes
+ * @len: On entry, number of bytes to read/write. On successful
+ * return, number of bytes actually read/written. In case of
+ * error, this may indicate at what point the error occurred.
+ * @data: Buffer to read/write from
+ *
+ * Users may use %ETHTOOL_GDRVINFO or %ETHTOOL_GMODULEINFO to find
+ * the length of an on-board or module EEPROM, respectively. They
+ * must allocate the buffer immediately following this structure.
+ */
struct ethtool_eeprom {
__u32 cmd;
__u32 magic;
- __u32 offset; /* in bytes */
- __u32 len; /* in bytes */
+ __u32 offset;
+ __u32 len;
__u8 data[0];
};
@@ -229,17 +351,18 @@
* @rate_sample_interval: How often to do adaptive coalescing packet rate
* sampling, measured in seconds. Must not be zero.
*
- * Each pair of (usecs, max_frames) fields specifies this exit
- * condition for interrupt coalescing:
+ * Each pair of (usecs, max_frames) fields specifies that interrupts
+ * should be coalesced until
* (usecs > 0 && time_since_first_completion >= usecs) ||
* (max_frames > 0 && completed_frames >= max_frames)
+ *
* It is illegal to set both usecs and max_frames to zero as this
* would cause interrupts to never be generated. To disable
* coalescing, set usecs = 0 and max_frames = 1.
*
* Some implementations ignore the value of max_frames and use the
- * condition:
- * time_since_first_completion >= usecs
+ * condition time_since_first_completion >= usecs
+ *
* This is deprecated. Drivers for hardware that does not support
* counting completions should validate that max_frames == !rx_usecs.
*
@@ -279,22 +402,37 @@
__u32 rate_sample_interval;
};
-/* for configuring RX/TX ring parameters */
+/**
+ * struct ethtool_ringparam - RX/TX ring parameters
+ * @cmd: Command number = %ETHTOOL_GRINGPARAM or %ETHTOOL_SRINGPARAM
+ * @rx_max_pending: Maximum supported number of pending entries per
+ * RX ring. Read-only.
+ * @rx_mini_max_pending: Maximum supported number of pending entries
+ * per RX mini ring. Read-only.
+ * @rx_jumbo_max_pending: Maximum supported number of pending entries
+ * per RX jumbo ring. Read-only.
+ * @tx_max_pending: Maximum supported number of pending entries per
+ * TX ring. Read-only.
+ * @rx_pending: Current maximum number of pending entries per RX ring
+ * @rx_mini_pending: Current maximum number of pending entries per RX
+ * mini ring
+ * @rx_jumbo_pending: Current maximum number of pending entries per RX
+ * jumbo ring
+ * @tx_pending: Current maximum supported number of pending entries
+ * per TX ring
+ *
+ * If the interface does not have separate RX mini and/or jumbo rings,
+ * @rx_mini_max_pending and/or @rx_jumbo_max_pending will be 0.
+ *
+ * There may also be driver-dependent minimum values for the number
+ * of entries per ring.
+ */
struct ethtool_ringparam {
- __u32 cmd; /* ETHTOOL_{G,S}RINGPARAM */
-
- /* Read only attributes. These indicate the maximum number
- * of pending RX/TX ring entries the driver will allow the
- * user to set.
- */
+ __u32 cmd;
__u32 rx_max_pending;
__u32 rx_mini_max_pending;
__u32 rx_jumbo_max_pending;
__u32 tx_max_pending;
-
- /* Values changeable by the user. The valid values are
- * in the range 1 to the "*_max_pending" counterpart above.
- */
__u32 rx_pending;
__u32 rx_mini_pending;
__u32 rx_jumbo_pending;
@@ -329,51 +467,96 @@
__u32 combined_count;
};
-/* for configuring link flow control parameters */
+/**
+ * struct ethtool_pauseparam - Ethernet pause (flow control) parameters
+ * @cmd: Command number = %ETHTOOL_GPAUSEPARAM or %ETHTOOL_SPAUSEPARAM
+ * @autoneg: Flag to enable autonegotiation of pause frame use
+ * @rx_pause: Flag to enable reception of pause frames
+ * @tx_pause: Flag to enable transmission of pause frames
+ *
+ * Drivers should reject a non-zero setting of @autoneg when
+ * autoneogotiation is disabled (or not supported) for the link.
+ *
+ * If the link is autonegotiated, drivers should use
+ * mii_advertise_flowctrl() or similar code to set the advertised
+ * pause frame capabilities based on the @rx_pause and @tx_pause flags,
+ * even if @autoneg is zero. They should also allow the advertised
+ * pause frame capabilities to be controlled directly through the
+ * advertising field of &struct ethtool_cmd.
+ *
+ * If @autoneg is non-zero, the MAC is configured to send and/or
+ * receive pause frames according to the result of autonegotiation.
+ * Otherwise, it is configured directly based on the @rx_pause and
+ * @tx_pause flags.
+ */
struct ethtool_pauseparam {
- __u32 cmd; /* ETHTOOL_{G,S}PAUSEPARAM */
-
- /* If the link is being auto-negotiated (via ethtool_cmd.autoneg
- * being true) the user may set 'autoneg' here non-zero to have the
- * pause parameters be auto-negotiated too. In such a case, the
- * {rx,tx}_pause values below determine what capabilities are
- * advertised.
- *
- * If 'autoneg' is zero or the link is not being auto-negotiated,
- * then {rx,tx}_pause force the driver to use/not-use pause
- * flow control.
- */
+ __u32 cmd;
__u32 autoneg;
__u32 rx_pause;
__u32 tx_pause;
};
#define ETH_GSTRING_LEN 32
+
+/**
+ * enum ethtool_stringset - string set ID
+ * @ETH_SS_TEST: Self-test result names, for use with %ETHTOOL_TEST
+ * @ETH_SS_STATS: Statistic names, for use with %ETHTOOL_GSTATS
+ * @ETH_SS_PRIV_FLAGS: Driver private flag names, for use with
+ * %ETHTOOL_GPFLAGS and %ETHTOOL_SPFLAGS
+ * @ETH_SS_NTUPLE_FILTERS: Previously used with %ETHTOOL_GRXNTUPLE;
+ * now deprecated
+ * @ETH_SS_FEATURES: Device feature names
+ */
enum ethtool_stringset {
ETH_SS_TEST = 0,
ETH_SS_STATS,
ETH_SS_PRIV_FLAGS,
- ETH_SS_NTUPLE_FILTERS, /* Do not use, GRXNTUPLE is now deprecated */
+ ETH_SS_NTUPLE_FILTERS,
ETH_SS_FEATURES,
};
-/* for passing string sets for data tagging */
+/**
+ * struct ethtool_gstrings - string set for data tagging
+ * @cmd: Command number = %ETHTOOL_GSTRINGS
+ * @string_set: String set ID; one of &enum ethtool_stringset
+ * @len: On return, the number of strings in the string set
+ * @data: Buffer for strings. Each string is null-padded to a size of
+ * %ETH_GSTRING_LEN.
+ *
+ * Users must use %ETHTOOL_GSSET_INFO to find the number of strings in
+ * the string set. They must allocate a buffer of the appropriate
+ * size immediately following this structure.
+ */
struct ethtool_gstrings {
- __u32 cmd; /* ETHTOOL_GSTRINGS */
- __u32 string_set; /* string set id e.c. ETH_SS_TEST, etc*/
- __u32 len; /* number of strings in the string set */
+ __u32 cmd;
+ __u32 string_set;
+ __u32 len;
__u8 data[0];
};
+/**
+ * struct ethtool_sset_info - string set information
+ * @cmd: Command number = %ETHTOOL_GSSET_INFO
+ * @sset_mask: On entry, a bitmask of string sets to query, with bits
+ * numbered according to &enum ethtool_stringset. On return, a
+ * bitmask of those string sets queried that are supported.
+ * @data: Buffer for string set sizes. On return, this contains the
+ * size of each string set that was queried and supported, in
+ * order of ID.
+ *
+ * Example: The user passes in @sset_mask = 0x7 (sets 0, 1, 2) and on
+ * return @sset_mask == 0x6 (sets 1, 2). Then @data[0] contains the
+ * size of set 1 and @data[1] contains the size of set 2.
+ *
+ * Users must allocate a buffer of the appropriate size (4 * number of
+ * sets queried) immediately following this structure.
+ */
struct ethtool_sset_info {
- __u32 cmd; /* ETHTOOL_GSSET_INFO */
+ __u32 cmd;
__u32 reserved;
- __u64 sset_mask; /* input: each bit selects an sset to query */
- /* output: each bit a returned sset */
- __u32 data[0]; /* ETH_SS_xxx count, in order, based on bits
- in sset_mask. One bit implies one
- __u32, two bits implies two
- __u32's, etc. */
+ __u64 sset_mask;
+ __u32 data[0];
};
/**
@@ -393,24 +576,58 @@
ETH_TEST_FL_EXTERNAL_LB_DONE = (1 << 3),
};
-/* for requesting NIC test and getting results*/
+/**
+ * struct ethtool_test - device self-test invocation
+ * @cmd: Command number = %ETHTOOL_TEST
+ * @flags: A bitmask of flags from &enum ethtool_test_flags. Some
+ * flags may be set by the user on entry; others may be set by
+ * the driver on return.
+ * @len: On return, the number of test results
+ * @data: Array of test results
+ *
+ * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the
+ * number of test results that will be returned. They must allocate a
+ * buffer of the appropriate size (8 * number of results) immediately
+ * following this structure.
+ */
struct ethtool_test {
- __u32 cmd; /* ETHTOOL_TEST */
- __u32 flags; /* ETH_TEST_FL_xxx */
+ __u32 cmd;
+ __u32 flags;
__u32 reserved;
- __u32 len; /* result length, in number of u64 elements */
+ __u32 len;
__u64 data[0];
};
-/* for dumping NIC-specific statistics */
+/**
+ * struct ethtool_stats - device-specific statistics
+ * @cmd: Command number = %ETHTOOL_GSTATS
+ * @n_stats: On return, the number of statistics
+ * @data: Array of statistics
+ *
+ * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the
+ * number of statistics that will be returned. They must allocate a
+ * buffer of the appropriate size (8 * number of statistics)
+ * immediately following this structure.
+ */
struct ethtool_stats {
- __u32 cmd; /* ETHTOOL_GSTATS */
- __u32 n_stats; /* number of u64's being returned */
+ __u32 cmd;
+ __u32 n_stats;
__u64 data[0];
};
+/**
+ * struct ethtool_perm_addr - permanent hardware address
+ * @cmd: Command number = %ETHTOOL_GPERMADDR
+ * @size: On entry, the size of the buffer. On return, the size of the
+ * address. The command fails if the buffer is too small.
+ * @data: Buffer for the address
+ *
+ * Users must allocate the buffer immediately following this structure.
+ * A buffer size of %MAX_ADDR_LEN should be sufficient for any address
+ * type.
+ */
struct ethtool_perm_addr {
- __u32 cmd; /* ETHTOOL_GPERMADDR */
+ __u32 cmd;
__u32 size;
__u8 data[0];
};
@@ -593,7 +810,7 @@
* %ETHTOOL_SRXCLSRLINS may add the rule at any suitable unused
* location, and may remove a rule at a later location (lower
* priority) that matches exactly the same set of flows. The special
- * values are: %RX_CLS_LOC_ANY, selecting any location;
+ * values are %RX_CLS_LOC_ANY, selecting any location;
* %RX_CLS_LOC_FIRST, selecting the first suitable location (maximum
* priority); and %RX_CLS_LOC_LAST, selecting the last suitable
* location (minimum priority). Additional special values may be
@@ -704,9 +921,6 @@
* for %ETHTOOL_GET_DUMP_FLAG command
* @data: data collected for get dump data operation
*/
-
-#define ETH_FW_DUMP_DISABLE 0
-
struct ethtool_dump {
__u32 cmd;
__u32 version;
@@ -715,6 +929,8 @@
__u8 data[0];
};
+#define ETH_FW_DUMP_DISABLE 0
+
/* for returning and changing feature sets */
/**
@@ -734,8 +950,9 @@
/**
* struct ethtool_gfeatures - command to get state of device's features
* @cmd: command number = %ETHTOOL_GFEATURES
- * @size: in: number of elements in the features[] array;
- * out: number of elements in features[] needed to hold all features
+ * @size: On entry, the number of elements in the features[] array;
+ * on return, the number of elements in features[] needed to hold
+ * all features
* @features: state of features
*/
struct ethtool_gfeatures {
@@ -905,7 +1122,6 @@
#define SPARC_ETH_GSET ETHTOOL_GSET
#define SPARC_ETH_SSET ETHTOOL_SSET
-/* Indicates what features are supported by the interface. */
#define SUPPORTED_10baseT_Half (1 << 0)
#define SUPPORTED_10baseT_Full (1 << 1)
#define SUPPORTED_100baseT_Half (1 << 2)
@@ -934,7 +1150,6 @@
#define SUPPORTED_40000baseSR4_Full (1 << 25)
#define SUPPORTED_40000baseLR4_Full (1 << 26)
-/* Indicates what features are advertised by the interface. */
#define ADVERTISED_10baseT_Half (1 << 0)
#define ADVERTISED_10baseT_Full (1 << 1)
#define ADVERTISED_100baseT_Half (1 << 2)
@@ -999,9 +1214,7 @@
#define XCVR_DUMMY2 0x03
#define XCVR_DUMMY3 0x04
-/* Enable or disable autonegotiation. If this is set to enable,
- * the forced link modes above are completely ignored.
- */
+/* Enable or disable autonegotiation. */
#define AUTONEG_DISABLE 0x00
#define AUTONEG_ENABLE 0x01
diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h
index d758163..9cf2394 100644
--- a/include/uapi/linux/if.h
+++ b/include/uapi/linux/if.h
@@ -27,65 +27,91 @@
#define IFALIASZ 256
#include <linux/hdlc/ioctl.h>
-/* Standard interface flags (netdevice->flags). */
-#define IFF_UP 0x1 /* interface is up */
-#define IFF_BROADCAST 0x2 /* broadcast address valid */
-#define IFF_DEBUG 0x4 /* turn on debugging */
-#define IFF_LOOPBACK 0x8 /* is a loopback net */
-#define IFF_POINTOPOINT 0x10 /* interface is has p-p link */
-#define IFF_NOTRAILERS 0x20 /* avoid use of trailers */
-#define IFF_RUNNING 0x40 /* interface RFC2863 OPER_UP */
-#define IFF_NOARP 0x80 /* no ARP protocol */
-#define IFF_PROMISC 0x100 /* receive all packets */
-#define IFF_ALLMULTI 0x200 /* receive all multicast packets*/
+/**
+ * enum net_device_flags - &struct net_device flags
+ *
+ * These are the &struct net_device flags, they can be set by drivers, the
+ * kernel and some can be triggered by userspace. Userspace can query and
+ * set these flags using userspace utilities but there is also a sysfs
+ * entry available for all dev flags which can be queried and set. These flags
+ * are shared for all types of net_devices. The sysfs entries are available
+ * via /sys/class/net/<dev>/flags. Flags which can be toggled through sysfs
+ * are annotated below, note that only a few flags can be toggled and some
+ * other flags are always always preserved from the original net_device flags
+ * even if you try to set them via sysfs. Flags which are always preserved
+ * are kept under the flag grouping @IFF_VOLATILE. Flags which are volatile
+ * are annotated below as such.
+ *
+ * You should have a pretty good reason to be extending these flags.
+ *
+ * @IFF_UP: interface is up. Can be toggled through sysfs.
+ * @IFF_BROADCAST: broadcast address valid. Volatile.
+ * @IFF_DEBUG: turn on debugging. Can be toggled through sysfs.
+ * @IFF_LOOPBACK: is a loopback net. Volatile.
+ * @IFF_POINTOPOINT: interface is has p-p link. Volatile.
+ * @IFF_NOTRAILERS: avoid use of trailers. Can be toggled through sysfs.
+ * Volatile.
+ * @IFF_RUNNING: interface RFC2863 OPER_UP. Volatile.
+ * @IFF_NOARP: no ARP protocol. Can be toggled through sysfs. Volatile.
+ * @IFF_PROMISC: receive all packets. Can be toggled through sysfs.
+ * @IFF_ALLMULTI: receive all multicast packets. Can be toggled through
+ * sysfs.
+ * @IFF_MASTER: master of a load balancer. Volatile.
+ * @IFF_SLAVE: slave of a load balancer. Volatile.
+ * @IFF_MULTICAST: Supports multicast. Can be toggled through sysfs.
+ * @IFF_PORTSEL: can set media type. Can be toggled through sysfs.
+ * @IFF_AUTOMEDIA: auto media select active. Can be toggled through sysfs.
+ * @IFF_DYNAMIC: dialup device with changing addresses. Can be toggled
+ * through sysfs.
+ * @IFF_LOWER_UP: driver signals L1 up. Volatile.
+ * @IFF_DORMANT: driver signals dormant. Volatile.
+ * @IFF_ECHO: echo sent packets. Volatile.
+ */
+enum net_device_flags {
+ IFF_UP = 1<<0, /* sysfs */
+ IFF_BROADCAST = 1<<1, /* volatile */
+ IFF_DEBUG = 1<<2, /* sysfs */
+ IFF_LOOPBACK = 1<<3, /* volatile */
+ IFF_POINTOPOINT = 1<<4, /* volatile */
+ IFF_NOTRAILERS = 1<<5, /* sysfs */
+ IFF_RUNNING = 1<<6, /* volatile */
+ IFF_NOARP = 1<<7, /* sysfs */
+ IFF_PROMISC = 1<<8, /* sysfs */
+ IFF_ALLMULTI = 1<<9, /* sysfs */
+ IFF_MASTER = 1<<10, /* volatile */
+ IFF_SLAVE = 1<<11, /* volatile */
+ IFF_MULTICAST = 1<<12, /* sysfs */
+ IFF_PORTSEL = 1<<13, /* sysfs */
+ IFF_AUTOMEDIA = 1<<14, /* sysfs */
+ IFF_DYNAMIC = 1<<15, /* sysfs */
+ IFF_LOWER_UP = 1<<16, /* volatile */
+ IFF_DORMANT = 1<<17, /* volatile */
+ IFF_ECHO = 1<<18, /* volatile */
+};
-#define IFF_MASTER 0x400 /* master of a load balancer */
-#define IFF_SLAVE 0x800 /* slave of a load balancer */
-
-#define IFF_MULTICAST 0x1000 /* Supports multicast */
-
-#define IFF_PORTSEL 0x2000 /* can set media type */
-#define IFF_AUTOMEDIA 0x4000 /* auto media select active */
-#define IFF_DYNAMIC 0x8000 /* dialup device with changing addresses*/
-
-#define IFF_LOWER_UP 0x10000 /* driver signals L1 up */
-#define IFF_DORMANT 0x20000 /* driver signals dormant */
-
-#define IFF_ECHO 0x40000 /* echo sent packets */
+#define IFF_UP IFF_UP
+#define IFF_BROADCAST IFF_BROADCAST
+#define IFF_DEBUG IFF_DEBUG
+#define IFF_LOOPBACK IFF_LOOPBACK
+#define IFF_POINTOPOINT IFF_POINTOPOINT
+#define IFF_NOTRAILERS IFF_NOTRAILERS
+#define IFF_RUNNING IFF_RUNNING
+#define IFF_NOARP IFF_NOARP
+#define IFF_PROMISC IFF_PROMISC
+#define IFF_ALLMULTI IFF_ALLMULTI
+#define IFF_MASTER IFF_MASTER
+#define IFF_SLAVE IFF_SLAVE
+#define IFF_MULTICAST IFF_MULTICAST
+#define IFF_PORTSEL IFF_PORTSEL
+#define IFF_AUTOMEDIA IFF_AUTOMEDIA
+#define IFF_DYNAMIC IFF_DYNAMIC
+#define IFF_LOWER_UP IFF_LOWER_UP
+#define IFF_DORMANT IFF_DORMANT
+#define IFF_ECHO IFF_ECHO
#define IFF_VOLATILE (IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|IFF_ECHO|\
IFF_MASTER|IFF_SLAVE|IFF_RUNNING|IFF_LOWER_UP|IFF_DORMANT)
-/* Private (from user) interface flags (netdevice->priv_flags). */
-#define IFF_802_1Q_VLAN 0x1 /* 802.1Q VLAN device. */
-#define IFF_EBRIDGE 0x2 /* Ethernet bridging device. */
-#define IFF_SLAVE_INACTIVE 0x4 /* bonding slave not the curr. active */
-#define IFF_MASTER_8023AD 0x8 /* bonding master, 802.3ad. */
-#define IFF_MASTER_ALB 0x10 /* bonding master, balance-alb. */
-#define IFF_BONDING 0x20 /* bonding master or slave */
-#define IFF_SLAVE_NEEDARP 0x40 /* need ARPs for validation */
-#define IFF_ISATAP 0x80 /* ISATAP interface (RFC4214) */
-#define IFF_MASTER_ARPMON 0x100 /* bonding master, ARP mon in use */
-#define IFF_WAN_HDLC 0x200 /* WAN HDLC device */
-#define IFF_XMIT_DST_RELEASE 0x400 /* dev_hard_start_xmit() is allowed to
- * release skb->dst
- */
-#define IFF_DONT_BRIDGE 0x800 /* disallow bridging this ether dev */
-#define IFF_DISABLE_NETPOLL 0x1000 /* disable netpoll at run-time */
-#define IFF_MACVLAN_PORT 0x2000 /* device used as macvlan port */
-#define IFF_BRIDGE_PORT 0x4000 /* device used as bridge port */
-#define IFF_OVS_DATAPATH 0x8000 /* device used as Open vSwitch
- * datapath port */
-#define IFF_TX_SKB_SHARING 0x10000 /* The interface supports sharing
- * skbs on transmit */
-#define IFF_UNICAST_FLT 0x20000 /* Supports unicast filtering */
-#define IFF_TEAM_PORT 0x40000 /* device used as team port */
-#define IFF_SUPP_NOFCS 0x80000 /* device supports sending custom FCS */
-#define IFF_LIVE_ADDR_CHANGE 0x100000 /* device supports hardware address
- * change when it's running */
-#define IFF_MACVLAN 0x200000 /* Macvlan device */
-
-
#define IF_GET_IFACE 0x0001 /* for querying only */
#define IF_GET_PROTO 0x0002
diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h
index 2ce0f6a..0f8210b 100644
--- a/include/uapi/linux/if_ether.h
+++ b/include/uapi/linux/if_ether.h
@@ -68,11 +68,11 @@
#define ETH_P_SLOW 0x8809 /* Slow Protocol. See 802.3ad 43B */
#define ETH_P_WCCP 0x883E /* Web-cache coordination protocol
* defined in draft-wilson-wrec-wccp-v2-00.txt */
-#define ETH_P_PPP_DISC 0x8863 /* PPPoE discovery messages */
-#define ETH_P_PPP_SES 0x8864 /* PPPoE session messages */
#define ETH_P_MPLS_UC 0x8847 /* MPLS Unicast traffic */
#define ETH_P_MPLS_MC 0x8848 /* MPLS Multicast traffic */
#define ETH_P_ATMMPOA 0x884c /* MultiProtocol Over ATM */
+#define ETH_P_PPP_DISC 0x8863 /* PPPoE discovery messages */
+#define ETH_P_PPP_SES 0x8864 /* PPPoE session messages */
#define ETH_P_LINK_CTL 0x886c /* HPNA, wlan link local tunnel */
#define ETH_P_ATMFATE 0x8884 /* Frame-based ATM Transport
* over Ethernet
@@ -89,6 +89,8 @@
#define ETH_P_FCOE 0x8906 /* Fibre Channel over Ethernet */
#define ETH_P_TDLS 0x890D /* TDLS */
#define ETH_P_FIP 0x8914 /* FCoE Initialization Protocol */
+#define ETH_P_80221 0x8917 /* IEEE 802.21 Media Independent Handover Protocol */
+#define ETH_P_LOOPBACK 0x9000 /* Ethernet loopback packet, per IEEE 802.3 */
#define ETH_P_QINQ1 0x9100 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */
#define ETH_P_QINQ2 0x9200 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */
#define ETH_P_QINQ3 0x9300 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 393c5de..c33a65e 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -120,6 +120,10 @@
* this socket to prevent accepting spoofed ones.
*/
#define IP_PMTUDISC_INTERFACE 4
+/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+ * fragmented if they exeed the interface mtu
+ */
+#define IP_PMTUDISC_OMIT 5
#define IP_MULTICAST_IF 32
#define IP_MULTICAST_TTL 33
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index 633b93c..0d8e0f0 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -128,22 +128,13 @@
* IPV6 extension headers
*/
#if __UAPI_DEF_IPPROTO_V6
-enum {
- IPPROTO_HOPOPTS = 0, /* IPv6 hop-by-hop options */
-#define IPPROTO_HOPOPTS IPPROTO_HOPOPTS
- IPPROTO_ROUTING = 43, /* IPv6 routing header */
-#define IPPROTO_ROUTING IPPROTO_ROUTING
- IPPROTO_FRAGMENT = 44, /* IPv6 fragmentation header */
-#define IPPROTO_FRAGMENT IPPROTO_FRAGMENT
- IPPROTO_ICMPV6 = 58, /* ICMPv6 */
-#define IPPROTO_ICMPV6 IPPROTO_ICMPV6
- IPPROTO_NONE = 59, /* IPv6 no next header */
-#define IPPROTO_NONE IPPROTO_NONE
- IPPROTO_DSTOPTS = 60, /* IPv6 destination options */
-#define IPPROTO_DSTOPTS IPPROTO_DSTOPTS
- IPPROTO_MH = 135, /* IPv6 mobility header */
-#define IPPROTO_MH IPPROTO_MH
-};
+#define IPPROTO_HOPOPTS 0 /* IPv6 hop-by-hop options */
+#define IPPROTO_ROUTING 43 /* IPv6 routing header */
+#define IPPROTO_FRAGMENT 44 /* IPv6 fragmentation header */
+#define IPPROTO_ICMPV6 58 /* ICMPv6 */
+#define IPPROTO_NONE 59 /* IPv6 no next header */
+#define IPPROTO_DSTOPTS 60 /* IPv6 destination options */
+#define IPPROTO_MH 135 /* IPv6 mobility header */
#endif /* __UAPI_DEF_IPPROTO_V6 */
/*
@@ -194,6 +185,10 @@
* also see comments on IP_PMTUDISC_INTERFACE
*/
#define IPV6_PMTUDISC_INTERFACE 4
+/* weaker version of IPV6_PMTUDISC_INTERFACE, which allows packets to
+ * get fragmented if they exceed the interface mtu
+ */
+#define IPV6_PMTUDISC_OMIT 5
/* Flowlabel */
#define IPV6_FLOWLABEL_MGR 32
diff --git a/include/uapi/linux/mic_ioctl.h b/include/uapi/linux/mic_ioctl.h
index 7fabba5..feb0b4c 100644
--- a/include/uapi/linux/mic_ioctl.h
+++ b/include/uapi/linux/mic_ioctl.h
@@ -39,7 +39,7 @@
#else
struct iovec *iov;
#endif
- int iovcnt;
+ __u32 iovcnt;
__u8 vr_idx;
__u8 update_used;
__u32 out_len;
diff --git a/include/uapi/linux/mpls.h b/include/uapi/linux/mpls.h
new file mode 100644
index 0000000..bc9abfe
--- /dev/null
+++ b/include/uapi/linux/mpls.h
@@ -0,0 +1,34 @@
+#ifndef _UAPI_MPLS_H
+#define _UAPI_MPLS_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+/* Reference: RFC 5462, RFC 3032
+ *
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Label | TC |S| TTL |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * Label: Label Value, 20 bits
+ * TC: Traffic Class field, 3 bits
+ * S: Bottom of Stack, 1 bit
+ * TTL: Time to Live, 8 bits
+ */
+
+struct mpls_label {
+ __be32 entry;
+};
+
+#define MPLS_LS_LABEL_MASK 0xFFFFF000
+#define MPLS_LS_LABEL_SHIFT 12
+#define MPLS_LS_TC_MASK 0x00000E00
+#define MPLS_LS_TC_SHIFT 9
+#define MPLS_LS_S_MASK 0x00000100
+#define MPLS_LS_S_SHIFT 8
+#define MPLS_LS_TTL_MASK 0x000000FF
+#define MPLS_LS_TTL_SHIFT 0
+
+#endif /* _UAPI_MPLS_H */
diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h
index 25d3b2f..78c2f2e 100644
--- a/include/uapi/linux/netfilter/ipset/ip_set.h
+++ b/include/uapi/linux/netfilter/ipset/ip_set.h
@@ -82,6 +82,8 @@
IPSET_ATTR_PROTO, /* 7 */
IPSET_ATTR_CADT_FLAGS, /* 8 */
IPSET_ATTR_CADT_LINENO = IPSET_ATTR_LINENO, /* 9 */
+ IPSET_ATTR_MARK, /* 10 */
+ IPSET_ATTR_MARKMASK, /* 11 */
/* Reserve empty slots */
IPSET_ATTR_CADT_MAX = 16,
/* Create-only specific attributes */
@@ -144,6 +146,7 @@
IPSET_ERR_IPADDR_IPV6,
IPSET_ERR_COUNTER,
IPSET_ERR_COMMENT,
+ IPSET_ERR_INVALID_MARKMASK,
/* Type specific error codes */
IPSET_ERR_TYPE_SPECIFIC = 4352,
@@ -182,9 +185,18 @@
IPSET_FLAG_WITH_COUNTERS = (1 << IPSET_FLAG_BIT_WITH_COUNTERS),
IPSET_FLAG_BIT_WITH_COMMENT = 4,
IPSET_FLAG_WITH_COMMENT = (1 << IPSET_FLAG_BIT_WITH_COMMENT),
+ IPSET_FLAG_BIT_WITH_FORCEADD = 5,
+ IPSET_FLAG_WITH_FORCEADD = (1 << IPSET_FLAG_BIT_WITH_FORCEADD),
IPSET_FLAG_CADT_MAX = 15,
};
+/* The flag bits which correspond to the non-extension create flags */
+enum ipset_create_flags {
+ IPSET_CREATE_FLAG_BIT_FORCEADD = 0,
+ IPSET_CREATE_FLAG_FORCEADD = (1 << IPSET_CREATE_FLAG_BIT_FORCEADD),
+ IPSET_CREATE_FLAG_BIT_MAX = 7,
+};
+
/* Commands with settype-specific attributes */
enum ipset_adt {
IPSET_ADD,
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 83c985a..c88ccbf 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1,7 +1,8 @@
#ifndef _LINUX_NF_TABLES_H
#define _LINUX_NF_TABLES_H
-#define NFT_CHAIN_MAXNAMELEN 32
+#define NFT_CHAIN_MAXNAMELEN 32
+#define NFT_USERDATA_MAXLEN 256
enum nft_registers {
NFT_REG_VERDICT,
@@ -156,6 +157,7 @@
* @NFTA_RULE_EXPRESSIONS: list of expressions (NLA_NESTED: nft_expr_attributes)
* @NFTA_RULE_COMPAT: compatibility specifications of the rule (NLA_NESTED: nft_rule_compat_attributes)
* @NFTA_RULE_POSITION: numeric handle of the previous rule (NLA_U64)
+ * @NFTA_RULE_USERDATA: user data (NLA_BINARY, NFT_USERDATA_MAXLEN)
*/
enum nft_rule_attributes {
NFTA_RULE_UNSPEC,
@@ -165,6 +167,7 @@
NFTA_RULE_EXPRESSIONS,
NFTA_RULE_COMPAT,
NFTA_RULE_POSITION,
+ NFTA_RULE_USERDATA,
__NFTA_RULE_MAX
};
#define NFTA_RULE_MAX (__NFTA_RULE_MAX - 1)
@@ -601,6 +604,7 @@
NFT_CT_PROTOCOL,
NFT_CT_PROTO_SRC,
NFT_CT_PROTO_DST,
+ NFT_CT_LABELS,
};
/**
diff --git a/include/uapi/linux/pfkeyv2.h b/include/uapi/linux/pfkeyv2.h
index 0b80c80..ada7f01 100644
--- a/include/uapi/linux/pfkeyv2.h
+++ b/include/uapi/linux/pfkeyv2.h
@@ -235,6 +235,18 @@
} __attribute__((packed));
/* sizeof(struct sadb_x_kmaddress) == 8 */
+/* To specify the SA dump filter */
+struct sadb_x_filter {
+ __u16 sadb_x_filter_len;
+ __u16 sadb_x_filter_exttype;
+ __u32 sadb_x_filter_saddr[4];
+ __u32 sadb_x_filter_daddr[4];
+ __u16 sadb_x_filter_family;
+ __u8 sadb_x_filter_splen;
+ __u8 sadb_x_filter_dplen;
+} __attribute__((packed));
+/* sizeof(struct sadb_x_filter) == 40 */
+
/* Message types */
#define SADB_RESERVED 0
#define SADB_GETSPI 1
@@ -358,7 +370,8 @@
#define SADB_X_EXT_SEC_CTX 24
/* Used with MIGRATE to pass @ to IKE for negotiation */
#define SADB_X_EXT_KMADDRESS 25
-#define SADB_EXT_MAX 25
+#define SADB_X_EXT_FILTER 26
+#define SADB_EXT_MAX 26
/* Identity Extension values */
#define SADB_IDENTTYPE_RESERVED 0
diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h
index b65c834..f0b7bfe 100644
--- a/include/uapi/linux/ptp_clock.h
+++ b/include/uapi/linux/ptp_clock.h
@@ -50,7 +50,8 @@
int n_ext_ts; /* Number of external time stamp channels. */
int n_per_out; /* Number of programmable periodic signals. */
int pps; /* Whether the clock supports a PPS callback. */
- int rsv[15]; /* Reserved for future use. */
+ int n_pins; /* Number of input/output pins. */
+ int rsv[14]; /* Reserved for future use. */
};
struct ptp_extts_request {
@@ -80,6 +81,40 @@
struct ptp_clock_time ts[2 * PTP_MAX_SAMPLES + 1];
};
+enum ptp_pin_function {
+ PTP_PF_NONE,
+ PTP_PF_EXTTS,
+ PTP_PF_PEROUT,
+ PTP_PF_PHYSYNC,
+};
+
+struct ptp_pin_desc {
+ /*
+ * Hardware specific human readable pin name. This field is
+ * set by the kernel during the PTP_PIN_GETFUNC ioctl and is
+ * ignored for the PTP_PIN_SETFUNC ioctl.
+ */
+ char name[64];
+ /*
+ * Pin index in the range of zero to ptp_clock_caps.n_pins - 1.
+ */
+ unsigned int index;
+ /*
+ * Which of the PTP_PF_xxx functions to use on this pin.
+ */
+ unsigned int func;
+ /*
+ * The specific channel to use for this function.
+ * This corresponds to the 'index' field of the
+ * PTP_EXTTS_REQUEST and PTP_PEROUT_REQUEST ioctls.
+ */
+ unsigned int chan;
+ /*
+ * Reserved for future use.
+ */
+ unsigned int rsv[5];
+};
+
#define PTP_CLK_MAGIC '='
#define PTP_CLOCK_GETCAPS _IOR(PTP_CLK_MAGIC, 1, struct ptp_clock_caps)
@@ -87,6 +122,8 @@
#define PTP_PEROUT_REQUEST _IOW(PTP_CLK_MAGIC, 3, struct ptp_perout_request)
#define PTP_ENABLE_PPS _IOW(PTP_CLK_MAGIC, 4, int)
#define PTP_SYS_OFFSET _IOW(PTP_CLK_MAGIC, 5, struct ptp_sys_offset)
+#define PTP_PIN_GETFUNC _IOWR(PTP_CLK_MAGIC, 6, struct ptp_pin_desc)
+#define PTP_PIN_SETFUNC _IOW(PTP_CLK_MAGIC, 7, struct ptp_pin_desc)
struct ptp_extts_event {
struct ptp_clock_time t; /* Time event occured. */
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index bbaba22..df40137 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -252,6 +252,7 @@
LINUX_MIB_TCPCHALLENGEACK, /* TCPChallengeACK */
LINUX_MIB_TCPSYNCHALLENGE, /* TCPSYNChallenge */
LINUX_MIB_TCPFASTOPENACTIVE, /* TCPFastOpenActive */
+ LINUX_MIB_TCPFASTOPENACTIVEFAIL, /* TCPFastOpenActiveFail */
LINUX_MIB_TCPFASTOPENPASSIVE, /* TCPFastOpenPassive*/
LINUX_MIB_TCPFASTOPENPASSIVEFAIL, /* TCPFastOpenPassiveFail */
LINUX_MIB_TCPFASTOPENLISTENOVERFLOW, /* TCPFastOpenListenOverflow */
@@ -259,6 +260,11 @@
LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES, /* TCPSpuriousRtxHostQueues */
LINUX_MIB_BUSYPOLLRXPACKETS, /* BusyPollRxPackets */
LINUX_MIB_TCPAUTOCORKING, /* TCPAutoCorking */
+ LINUX_MIB_TCPFROMZEROWINDOWADV, /* TCPFromZeroWindowAdv */
+ LINUX_MIB_TCPTOZEROWINDOWADV, /* TCPToZeroWindowAdv */
+ LINUX_MIB_TCPWANTZEROWINDOWADV, /* TCPWantZeroWindowAdv */
+ LINUX_MIB_TCPSYNRETRANS, /* TCPSynRetrans */
+ LINUX_MIB_TCPORIGDATASENT, /* TCPOrigDataSent */
__LINUX_MIB_MAX
};
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 377f1e5..3b97183 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -186,6 +186,9 @@
__u32 tcpi_rcv_space;
__u32 tcpi_total_retrans;
+
+ __u64 tcpi_pacing_rate;
+ __u64 tcpi_max_pacing_rate;
};
/* for TCP_MD5SIG socket option */
diff --git a/include/uapi/linux/tcp_metrics.h b/include/uapi/linux/tcp_metrics.h
index 54a37b1..9353392 100644
--- a/include/uapi/linux/tcp_metrics.h
+++ b/include/uapi/linux/tcp_metrics.h
@@ -11,12 +11,15 @@
#define TCP_METRICS_GENL_VERSION 0x1
enum tcp_metric_index {
- TCP_METRIC_RTT,
- TCP_METRIC_RTTVAR,
+ TCP_METRIC_RTT, /* in ms units */
+ TCP_METRIC_RTTVAR, /* in ms units */
TCP_METRIC_SSTHRESH,
TCP_METRIC_CWND,
TCP_METRIC_REORDERING,
+ TCP_METRIC_RTT_US, /* in usec units */
+ TCP_METRIC_RTTVAR_US, /* in usec units */
+
/* Always last. */
__TCP_METRIC_MAX,
};
diff --git a/include/uapi/linux/usb/cdc.h b/include/uapi/linux/usb/cdc.h
index f35aa0a..b6a9cdd 100644
--- a/include/uapi/linux/usb/cdc.h
+++ b/include/uapi/linux/usb/cdc.h
@@ -56,6 +56,7 @@
#define USB_CDC_OBEX_TYPE 0x15
#define USB_CDC_NCM_TYPE 0x1a
#define USB_CDC_MBIM_TYPE 0x1b
+#define USB_CDC_MBIM_EXTENDED_TYPE 0x1c
/* "Header Functional Descriptor" from CDC spec 5.2.3.1 */
struct usb_cdc_header_desc {
@@ -205,6 +206,17 @@
__u8 bmNetworkCapabilities;
} __attribute__ ((packed));
+/* "MBIM Extended Functional Descriptor" from CDC MBIM spec 1.0 errata-1 */
+struct usb_cdc_mbim_extended_desc {
+ __u8 bLength;
+ __u8 bDescriptorType;
+ __u8 bDescriptorSubType;
+
+ __le16 bcdMBIMExtendedVersion;
+ __u8 bMaxOutstandingCommandMessages;
+ __le16 wMTU;
+} __attribute__ ((packed));
+
/*-------------------------------------------------------------------------*/
/*
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index a8cd6a4..25e5dd9 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -298,6 +298,8 @@
XFRMA_TFCPAD, /* __u32 */
XFRMA_REPLAY_ESN_VAL, /* struct xfrm_replay_esn */
XFRMA_SA_EXTRA_FLAGS, /* __u32 */
+ XFRMA_PROTO, /* __u8 */
+ XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */
__XFRMA_MAX
#define XFRMA_MAX (__XFRMA_MAX - 1)
@@ -474,6 +476,14 @@
__be16 new_sport;
};
+struct xfrm_address_filter {
+ xfrm_address_t saddr;
+ xfrm_address_t daddr;
+ __u16 family;
+ __u8 splen;
+ __u8 dplen;
+};
+
#ifndef __KERNEL__
/* backwards compatibility for userspace */
#define XFRMGRP_ACQUIRE 1
diff --git a/include/uapi/xen/Kbuild b/include/uapi/xen/Kbuild
index 61257cb..5c45962 100644
--- a/include/uapi/xen/Kbuild
+++ b/include/uapi/xen/Kbuild
@@ -1,3 +1,5 @@
# UAPI Header export list
header-y += evtchn.h
+header-y += gntalloc.h
+header-y += gntdev.h
header-y += privcmd.h
diff --git a/include/xen/gntalloc.h b/include/uapi/xen/gntalloc.h
similarity index 100%
rename from include/xen/gntalloc.h
rename to include/uapi/xen/gntalloc.h
diff --git a/include/xen/gntdev.h b/include/uapi/xen/gntdev.h
similarity index 100%
rename from include/xen/gntdev.h
rename to include/uapi/xen/gntdev.h
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index ae665ac..32ec05a 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -113,13 +113,13 @@
* it's less than the number provided by the backend. The indirect_grefs field
* in blkif_request_indirect should be filled by the frontend with the
* grant references of the pages that are holding the indirect segments.
- * This pages are filled with an array of blkif_request_segment_aligned
- * that hold the information about the segments. The number of indirect
- * pages to use is determined by the maximum number of segments
- * a indirect request contains. Every indirect page can contain a maximum
- * of 512 segments (PAGE_SIZE/sizeof(blkif_request_segment_aligned)),
- * so to calculate the number of indirect pages to use we have to do
- * ceil(indirect_segments/512).
+ * These pages are filled with an array of blkif_request_segment that hold the
+ * information about the segments. The number of indirect pages to use is
+ * determined by the number of segments an indirect request contains. Every
+ * indirect page can contain a maximum of
+ * (PAGE_SIZE / sizeof(struct blkif_request_segment)) segments, so to
+ * calculate the number of indirect pages to use we have to do
+ * ceil(indirect_segments / (PAGE_SIZE / sizeof(struct blkif_request_segment))).
*
* If a backend does not recognize BLKIF_OP_INDIRECT, it should *not*
* create the "feature-max-indirect-segments" node!
@@ -135,13 +135,12 @@
#define BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST 8
-struct blkif_request_segment_aligned {
- grant_ref_t gref; /* reference to I/O buffer frame */
- /* @first_sect: first sector in frame to transfer (inclusive). */
- /* @last_sect: last sector in frame to transfer (inclusive). */
- uint8_t first_sect, last_sect;
- uint16_t _pad; /* padding to make it 8 bytes, so it's cache-aligned */
-} __attribute__((__packed__));
+struct blkif_request_segment {
+ grant_ref_t gref; /* reference to I/O buffer frame */
+ /* @first_sect: first sector in frame to transfer (inclusive). */
+ /* @last_sect: last sector in frame to transfer (inclusive). */
+ uint8_t first_sect, last_sect;
+};
struct blkif_request_rw {
uint8_t nr_segments; /* number of segments */
@@ -151,12 +150,7 @@
#endif
uint64_t id; /* private guest value, echoed in resp */
blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */
- struct blkif_request_segment {
- grant_ref_t gref; /* reference to I/O buffer frame */
- /* @first_sect: first sector in frame to transfer (inclusive). */
- /* @last_sect: last sector in frame to transfer (inclusive). */
- uint8_t first_sect, last_sect;
- } seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
} __attribute__((__packed__));
struct blkif_request_discard {
diff --git a/include/xen/interface/xencomm.h b/include/xen/interface/xencomm.h
deleted file mode 100644
index ac45e07..0000000
--- a/include/xen/interface/xencomm.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/*
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to
- * deal in the Software without restriction, including without limitation the
- * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
- * sell copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- *
- * Copyright (C) IBM Corp. 2006
- */
-
-#ifndef _XEN_XENCOMM_H_
-#define _XEN_XENCOMM_H_
-
-/* A xencomm descriptor is a scatter/gather list containing physical
- * addresses corresponding to a virtually contiguous memory area. The
- * hypervisor translates these physical addresses to machine addresses to copy
- * to and from the virtually contiguous area.
- */
-
-#define XENCOMM_MAGIC 0x58434F4D /* 'XCOM' */
-#define XENCOMM_INVALID (~0UL)
-
-struct xencomm_desc {
- uint32_t magic;
- uint32_t nr_addrs; /* the number of entries in address[] */
- uint64_t address[0];
-};
-
-#endif /* _XEN_XENCOMM_H_ */
diff --git a/include/xen/xencomm.h b/include/xen/xencomm.h
deleted file mode 100644
index e43b039..0000000
--- a/include/xen/xencomm.h
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- * Copyright (C) IBM Corp. 2006
- *
- * Authors: Hollis Blanchard <hollisb@us.ibm.com>
- * Jerone Young <jyoung5@us.ibm.com>
- */
-
-#ifndef _LINUX_XENCOMM_H_
-#define _LINUX_XENCOMM_H_
-
-#include <xen/interface/xencomm.h>
-
-#define XENCOMM_MINI_ADDRS 3
-struct xencomm_mini {
- struct xencomm_desc _desc;
- uint64_t address[XENCOMM_MINI_ADDRS];
-};
-
-/* To avoid additionnal virt to phys conversion, an opaque structure is
- presented. */
-struct xencomm_handle;
-
-extern void xencomm_free(struct xencomm_handle *desc);
-extern struct xencomm_handle *xencomm_map(void *ptr, unsigned long bytes);
-extern struct xencomm_handle *__xencomm_map_no_alloc(void *ptr,
- unsigned long bytes, struct xencomm_mini *xc_area);
-
-#if 0
-#define XENCOMM_MINI_ALIGNED(xc_desc, n) \
- struct xencomm_mini xc_desc ## _base[(n)] \
- __attribute__((__aligned__(sizeof(struct xencomm_mini)))); \
- struct xencomm_mini *xc_desc = &xc_desc ## _base[0];
-#else
-/*
- * gcc bug workaround:
- * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=16660
- * gcc doesn't handle properly stack variable with
- * __attribute__((__align__(sizeof(struct xencomm_mini))))
- */
-#define XENCOMM_MINI_ALIGNED(xc_desc, n) \
- unsigned char xc_desc ## _base[((n) + 1 ) * \
- sizeof(struct xencomm_mini)]; \
- struct xencomm_mini *xc_desc = (struct xencomm_mini *) \
- ((unsigned long)xc_desc ## _base + \
- (sizeof(struct xencomm_mini) - \
- ((unsigned long)xc_desc ## _base) % \
- sizeof(struct xencomm_mini)));
-#endif
-#define xencomm_map_no_alloc(ptr, bytes) \
- ({ XENCOMM_MINI_ALIGNED(xc_desc, 1); \
- __xencomm_map_no_alloc(ptr, bytes, xc_desc); })
-
-/* provided by architecture code: */
-extern unsigned long xencomm_vtop(unsigned long vaddr);
-
-static inline void *xencomm_pa(void *ptr)
-{
- return (void *)xencomm_vtop((unsigned long)ptr);
-}
-
-#define xen_guest_handle(hnd) ((hnd).p)
-
-#endif /* _LINUX_XENCOMM_H_ */
diff --git a/init/main.c b/init/main.c
index eb03090..9c7fd4c 100644
--- a/init/main.c
+++ b/init/main.c
@@ -561,7 +561,6 @@
init_timers();
hrtimers_init();
softirq_init();
- acpi_early_init();
timekeeping_init();
time_init();
sched_clock_postinit();
@@ -613,6 +612,7 @@
calibrate_delay();
pidmap_init();
anon_vma_init();
+ acpi_early_init();
#ifdef CONFIG_X86
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi_enter_virtual_mode();
diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c
index 383d638..5bb8bfe 100644
--- a/ipc/mq_sysctl.c
+++ b/ipc/mq_sysctl.c
@@ -22,6 +22,16 @@
return which;
}
+static int proc_mq_dointvec(ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table mq_table;
+ memcpy(&mq_table, table, sizeof(mq_table));
+ mq_table.data = get_mq(table);
+
+ return proc_dointvec(&mq_table, write, buffer, lenp, ppos);
+}
+
static int proc_mq_dointvec_minmax(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
@@ -33,12 +43,10 @@
lenp, ppos);
}
#else
+#define proc_mq_dointvec NULL
#define proc_mq_dointvec_minmax NULL
#endif
-static int msg_queues_limit_min = MIN_QUEUESMAX;
-static int msg_queues_limit_max = HARD_QUEUESMAX;
-
static int msg_max_limit_min = MIN_MSGMAX;
static int msg_max_limit_max = HARD_MSGMAX;
@@ -51,9 +59,7 @@
.data = &init_ipc_ns.mq_queues_max,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_mq_dointvec_minmax,
- .extra1 = &msg_queues_limit_min,
- .extra2 = &msg_queues_limit_max,
+ .proc_handler = proc_mq_dointvec,
},
{
.procname = "msg_max",
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index ccf1f9f..c3b3117 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -433,9 +433,9 @@
error = -EACCES;
goto out_unlock;
}
- if (ipc_ns->mq_queues_count >= HARD_QUEUESMAX ||
- (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
- !capable(CAP_SYS_RESOURCE))) {
+
+ if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
+ !capable(CAP_SYS_RESOURCE)) {
error = -ENOSPC;
goto out_unlock;
}
diff --git a/ipc/msg.c b/ipc/msg.c
index 245db11..6498531 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -901,6 +901,8 @@
return -EINVAL;
if (msgflg & MSG_COPY) {
+ if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT))
+ return -EINVAL;
copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax));
if (IS_ERR(copy))
return PTR_ERR(copy);
diff --git a/kernel/audit.c b/kernel/audit.c
index 34c5a23..3392d3e 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -182,7 +182,7 @@
struct audit_reply {
__u32 portid;
- pid_t pid;
+ struct net *net;
struct sk_buff *skb;
};
@@ -500,7 +500,7 @@
{
struct audit_netlink_list *dest = _dest;
struct sk_buff *skb;
- struct net *net = get_net_ns_by_pid(dest->pid);
+ struct net *net = dest->net;
struct audit_net *aunet = net_generic(net, audit_net_id);
/* wait for parent to finish and send an ACK */
@@ -510,6 +510,7 @@
while ((skb = __skb_dequeue(&dest->q)) != NULL)
netlink_unicast(aunet->nlsk, skb, dest->portid, 0);
+ put_net(net);
kfree(dest);
return 0;
@@ -543,7 +544,7 @@
static int audit_send_reply_thread(void *arg)
{
struct audit_reply *reply = (struct audit_reply *)arg;
- struct net *net = get_net_ns_by_pid(reply->pid);
+ struct net *net = reply->net;
struct audit_net *aunet = net_generic(net, audit_net_id);
mutex_lock(&audit_cmd_mutex);
@@ -552,12 +553,13 @@
/* Ignore failure. It'll only happen if the sender goes away,
because our timeout is set to infinite. */
netlink_unicast(aunet->nlsk , reply->skb, reply->portid, 0);
+ put_net(net);
kfree(reply);
return 0;
}
/**
* audit_send_reply - send an audit reply message via netlink
- * @portid: netlink port to which to send reply
+ * @request_skb: skb of request we are replying to (used to target the reply)
* @seq: sequence number
* @type: audit message type
* @done: done (last) flag
@@ -568,9 +570,11 @@
* Allocates an skb, builds the netlink message, and sends it to the port id.
* No failure notifications.
*/
-static void audit_send_reply(__u32 portid, int seq, int type, int done,
+static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done,
int multi, const void *payload, int size)
{
+ u32 portid = NETLINK_CB(request_skb).portid;
+ struct net *net = sock_net(NETLINK_CB(request_skb).sk);
struct sk_buff *skb;
struct task_struct *tsk;
struct audit_reply *reply = kmalloc(sizeof(struct audit_reply),
@@ -583,8 +587,8 @@
if (!skb)
goto out;
+ reply->net = get_net(net);
reply->portid = portid;
- reply->pid = task_pid_vnr(current);
reply->skb = skb;
tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply");
@@ -673,8 +677,7 @@
seq = nlmsg_hdr(skb)->nlmsg_seq;
- audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
- &af, sizeof(af));
+ audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af));
return 0;
}
@@ -794,8 +797,7 @@
s.backlog = skb_queue_len(&audit_skb_queue);
s.version = AUDIT_VERSION_LATEST;
s.backlog_wait_time = audit_backlog_wait_time;
- audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
- &s, sizeof(s));
+ audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s));
break;
}
case AUDIT_SET: {
@@ -905,7 +907,7 @@
seq, data, nlmsg_len(nlh));
break;
case AUDIT_LIST_RULES:
- err = audit_list_rules_send(NETLINK_CB(skb).portid, seq);
+ err = audit_list_rules_send(skb, seq);
break;
case AUDIT_TRIM:
audit_trim_trees();
@@ -970,8 +972,8 @@
memcpy(sig_data->ctx, ctx, len);
security_release_secctx(ctx, len);
}
- audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_SIGNAL_INFO,
- 0, 0, sig_data, sizeof(*sig_data) + len);
+ audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0,
+ sig_data, sizeof(*sig_data) + len);
kfree(sig_data);
break;
case AUDIT_TTY_GET: {
@@ -983,8 +985,7 @@
s.log_passwd = tsk->signal->audit_tty_log_passwd;
spin_unlock(&tsk->sighand->siglock);
- audit_send_reply(NETLINK_CB(skb).portid, seq,
- AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
+ audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
break;
}
case AUDIT_TTY_SET: {
diff --git a/kernel/audit.h b/kernel/audit.h
index 57cc64d..8df13221 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -247,7 +247,7 @@
struct audit_netlink_list {
__u32 portid;
- pid_t pid;
+ struct net *net;
struct sk_buff_head q;
};
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 67ccf0e..135944a 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -916,7 +916,7 @@
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name)
+ const unsigned char *file_name, u32 cookie)
{
return 0;
}
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 2596fac..70b4554 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -471,7 +471,7 @@
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *dname)
+ const unsigned char *dname, u32 cookie)
{
struct inode *inode;
struct audit_parent *parent;
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 14a78cc..92062fd 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -29,6 +29,8 @@
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/security.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
#include "audit.h"
/*
@@ -1065,11 +1067,13 @@
/**
* audit_list_rules_send - list the audit rules
- * @portid: target portid for netlink audit messages
+ * @request_skb: skb of request we are replying to (used to target the reply)
* @seq: netlink audit message sequence (serial) number
*/
-int audit_list_rules_send(__u32 portid, int seq)
+int audit_list_rules_send(struct sk_buff *request_skb, int seq)
{
+ u32 portid = NETLINK_CB(request_skb).portid;
+ struct net *net = sock_net(NETLINK_CB(request_skb).sk);
struct task_struct *tsk;
struct audit_netlink_list *dest;
int err = 0;
@@ -1083,8 +1087,8 @@
dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL);
if (!dest)
return -ENOMEM;
+ dest->net = get_net(net);
dest->portid = portid;
- dest->pid = task_pid_vnr(current);
skb_queue_head_init(&dest->q);
mutex_lock(&audit_filter_mutex);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e2f46ba..0c753dd 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -886,7 +886,9 @@
* per-subsystem and moved to css->id so that lookups are
* successful until the target css is released.
*/
+ mutex_lock(&cgroup_mutex);
idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+ mutex_unlock(&cgroup_mutex);
cgrp->id = -1;
call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
@@ -1566,10 +1568,10 @@
mutex_lock(&cgroup_mutex);
mutex_lock(&cgroup_root_mutex);
- root_cgrp->id = idr_alloc(&root->cgroup_idr, root_cgrp,
- 0, 1, GFP_KERNEL);
- if (root_cgrp->id < 0)
+ ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
+ if (ret < 0)
goto unlock_drop;
+ root_cgrp->id = ret;
/* Check for name clashes with existing mounts */
ret = -EBUSY;
@@ -2763,10 +2765,7 @@
*/
update_before = cgroup_serial_nr_next;
- mutex_unlock(&cgroup_mutex);
-
/* add/rm files for all cgroups created before */
- rcu_read_lock();
css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
struct cgroup *cgrp = css->cgroup;
@@ -2775,23 +2774,19 @@
inode = cgrp->dentry->d_inode;
dget(cgrp->dentry);
- rcu_read_unlock();
-
dput(prev);
prev = cgrp->dentry;
+ mutex_unlock(&cgroup_mutex);
mutex_lock(&inode->i_mutex);
mutex_lock(&cgroup_mutex);
if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp))
ret = cgroup_addrm_files(cgrp, cfts, is_add);
- mutex_unlock(&cgroup_mutex);
mutex_unlock(&inode->i_mutex);
-
- rcu_read_lock();
if (ret)
break;
}
- rcu_read_unlock();
+ mutex_unlock(&cgroup_mutex);
dput(prev);
deactivate_super(sb);
return ret;
@@ -2910,9 +2905,14 @@
* We should check if the process is exiting, otherwise
* it will race with cgroup_exit() in that the list
* entry won't be deleted though the process has exited.
+ * Do it while holding siglock so that we don't end up
+ * racing against cgroup_exit().
*/
+ spin_lock_irq(&p->sighand->siglock);
if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
list_add(&p->cg_list, &task_css_set(p)->tasks);
+ spin_unlock_irq(&p->sighand->siglock);
+
task_unlock(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
@@ -4112,17 +4112,17 @@
err = percpu_ref_init(&css->refcnt, css_release);
if (err)
- goto err_free;
+ goto err_free_css;
init_css(css, ss, cgrp);
err = cgroup_populate_dir(cgrp, 1 << ss->subsys_id);
if (err)
- goto err_free;
+ goto err_free_percpu_ref;
err = online_css(css);
if (err)
- goto err_free;
+ goto err_clear_dir;
dget(cgrp->dentry);
css_get(css->parent);
@@ -4138,8 +4138,11 @@
return 0;
-err_free:
+err_clear_dir:
+ cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id);
+err_free_percpu_ref:
percpu_ref_cancel_init(&css->refcnt);
+err_free_css:
ss->css_free(css);
return err;
}
@@ -4158,7 +4161,7 @@
struct cgroup *cgrp;
struct cgroup_name *name;
struct cgroupfs_root *root = parent->root;
- int ssid, err = 0;
+ int ssid, err;
struct cgroup_subsys *ss;
struct super_block *sb = root->sb;
@@ -4168,19 +4171,13 @@
return -ENOMEM;
name = cgroup_alloc_name(dentry);
- if (!name)
+ if (!name) {
+ err = -ENOMEM;
goto err_free_cgrp;
+ }
rcu_assign_pointer(cgrp->name, name);
/*
- * Temporarily set the pointer to NULL, so idr_find() won't return
- * a half-baked cgroup.
- */
- cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
- if (cgrp->id < 0)
- goto err_free_name;
-
- /*
* Only live parents can have children. Note that the liveliness
* check isn't strictly necessary because cgroup_mkdir() and
* cgroup_rmdir() are fully synchronized by i_mutex; however, do it
@@ -4189,7 +4186,17 @@
*/
if (!cgroup_lock_live_group(parent)) {
err = -ENODEV;
- goto err_free_id;
+ goto err_free_name;
+ }
+
+ /*
+ * Temporarily set the pointer to NULL, so idr_find() won't return
+ * a half-baked cgroup.
+ */
+ cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
+ if (cgrp->id < 0) {
+ err = -ENOMEM;
+ goto err_unlock;
}
/* Grab a reference on the superblock so the hierarchy doesn't
@@ -4221,7 +4228,7 @@
*/
err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
if (err < 0)
- goto err_unlock;
+ goto err_free_id;
lockdep_assert_held(&dentry->d_inode->i_mutex);
cgrp->serial_nr = cgroup_serial_nr_next++;
@@ -4257,12 +4264,12 @@
return 0;
-err_unlock:
- mutex_unlock(&cgroup_mutex);
- /* Release the reference count that we took on the superblock */
- deactivate_super(sb);
err_free_id:
idr_remove(&root->cgroup_idr, cgrp->id);
+ /* Release the reference count that we took on the superblock */
+ deactivate_super(sb);
+err_unlock:
+ mutex_unlock(&cgroup_mutex);
err_free_name:
kfree(rcu_dereference_raw(cgrp->name));
err_free_cgrp:
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4410ac6..e6b1b66 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -974,12 +974,6 @@
* Temporarilly set tasks mems_allowed to target nodes of migration,
* so that the migration code can allocate pages on these nodes.
*
- * Call holding cpuset_mutex, so current's cpuset won't change
- * during this call, as manage_mutex holds off any cpuset_attach()
- * calls. Therefore we don't need to take task_lock around the
- * call to guarantee_online_mems(), as we know no one is changing
- * our task's cpuset.
- *
* While the mm_struct we are migrating is typically from some
* other task, the task_struct mems_allowed that we are hacking
* is for our current task, which must allocate new pages for that
@@ -996,8 +990,10 @@
do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
+ rcu_read_lock();
mems_cs = effective_nodemask_cpuset(task_cs(tsk));
guarantee_online_mems(mems_cs, &tsk->mems_allowed);
+ rcu_read_unlock();
}
/*
@@ -2486,9 +2482,9 @@
task_lock(current);
cs = nearest_hardwall_ancestor(task_cs(current));
+ allowed = node_isset(node, cs->mems_allowed);
task_unlock(current);
- allowed = node_isset(node, cs->mems_allowed);
mutex_unlock(&callback_mutex);
return allowed;
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 56003c6..fa0b2d4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7856,14 +7856,14 @@
static void __perf_event_exit_context(void *__info)
{
struct perf_event_context *ctx = __info;
- struct perf_event *event, *tmp;
+ struct perf_event *event;
perf_pmu_rotate_stop(ctx->pmu);
- list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
+ rcu_read_lock();
+ list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
__perf_remove_from_context(event);
- list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
- __perf_remove_from_context(event);
+ rcu_read_unlock();
}
static void perf_event_exit_cpu_context(int cpu)
@@ -7887,11 +7887,11 @@
{
struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
+ perf_event_exit_cpu_context(cpu);
+
mutex_lock(&swhash->hlist_mutex);
swevent_hlist_release(swhash);
mutex_unlock(&swhash->hlist_mutex);
-
- perf_event_exit_cpu_context(cpu);
}
#else
static inline void perf_event_exit_cpu(int cpu) { }
diff --git a/kernel/futex.c b/kernel/futex.c
index 44a1261..08ec814 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -234,6 +234,7 @@
* waiting on a futex.
*/
struct futex_hash_bucket {
+ atomic_t waiters;
spinlock_t lock;
struct plist_head chain;
} ____cacheline_aligned_in_smp;
@@ -253,22 +254,37 @@
smp_mb__after_atomic_inc();
}
-static inline bool hb_waiters_pending(struct futex_hash_bucket *hb)
+/*
+ * Reflects a new waiter being added to the waitqueue.
+ */
+static inline void hb_waiters_inc(struct futex_hash_bucket *hb)
{
#ifdef CONFIG_SMP
+ atomic_inc(&hb->waiters);
/*
- * Tasks trying to enter the critical region are most likely
- * potential waiters that will be added to the plist. Ensure
- * that wakers won't miss to-be-slept tasks in the window between
- * the wait call and the actual plist_add.
+ * Full barrier (A), see the ordering comment above.
*/
- if (spin_is_locked(&hb->lock))
- return true;
- smp_rmb(); /* Make sure we check the lock state first */
+ smp_mb__after_atomic_inc();
+#endif
+}
- return !plist_head_empty(&hb->chain);
+/*
+ * Reflects a waiter being removed from the waitqueue by wakeup
+ * paths.
+ */
+static inline void hb_waiters_dec(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+ atomic_dec(&hb->waiters);
+#endif
+}
+
+static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+ return atomic_read(&hb->waiters);
#else
- return true;
+ return 1;
#endif
}
@@ -954,6 +970,7 @@
hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
plist_del(&q->list, &hb->chain);
+ hb_waiters_dec(hb);
}
/*
@@ -1257,7 +1274,9 @@
*/
if (likely(&hb1->chain != &hb2->chain)) {
plist_del(&q->list, &hb1->chain);
+ hb_waiters_dec(hb1);
plist_add(&q->list, &hb2->chain);
+ hb_waiters_inc(hb2);
q->lock_ptr = &hb2->lock;
}
get_futex_key_refs(key2);
@@ -1600,6 +1619,17 @@
struct futex_hash_bucket *hb;
hb = hash_futex(&q->key);
+
+ /*
+ * Increment the counter before taking the lock so that
+ * a potential waker won't miss a to-be-slept task that is
+ * waiting for the spinlock. This is safe as all queue_lock()
+ * users end up calling queue_me(). Similarly, for housekeeping,
+ * decrement the counter at queue_unlock() when some error has
+ * occurred and we don't end up adding the task to the list.
+ */
+ hb_waiters_inc(hb);
+
q->lock_ptr = &hb->lock;
spin_lock(&hb->lock); /* implies MB (A) */
@@ -1611,6 +1641,7 @@
__releases(&hb->lock)
{
spin_unlock(&hb->lock);
+ hb_waiters_dec(hb);
}
/**
@@ -2342,6 +2373,7 @@
* Unqueue the futex_q and determine which it was.
*/
plist_del(&q->list, &hb->chain);
+ hb_waiters_dec(hb);
/* Handle spurious wakeups gracefully */
ret = -EWOULDBLOCK;
@@ -2875,6 +2907,7 @@
futex_cmpxchg_enabled = 1;
for (i = 0; i < futex_hashsize; i++) {
+ atomic_set(&futex_queues[i].waiters, 0);
plist_head_init(&futex_queues[i].chain);
spin_lock_init(&futex_queues[i].lock);
}
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index bd8e788..1ef0606 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -73,6 +73,51 @@
EXPORT_SYMBOL(devm_request_threaded_irq);
/**
+ * devm_request_any_context_irq - allocate an interrupt line for a managed device
+ * @dev: device to request interrupt for
+ * @irq: Interrupt line to allocate
+ * @handler: Function to be called when the IRQ occurs
+ * @thread_fn: function to be called in a threaded interrupt context. NULL
+ * for devices which handle everything in @handler
+ * @irqflags: Interrupt type flags
+ * @devname: An ascii name for the claiming device
+ * @dev_id: A cookie passed back to the handler function
+ *
+ * Except for the extra @dev argument, this function takes the
+ * same arguments and performs the same function as
+ * request_any_context_irq(). IRQs requested with this function will be
+ * automatically freed on driver detach.
+ *
+ * If an IRQ allocated with this function needs to be freed
+ * separately, devm_free_irq() must be used.
+ */
+int devm_request_any_context_irq(struct device *dev, unsigned int irq,
+ irq_handler_t handler, unsigned long irqflags,
+ const char *devname, void *dev_id)
+{
+ struct irq_devres *dr;
+ int rc;
+
+ dr = devres_alloc(devm_irq_release, sizeof(struct irq_devres),
+ GFP_KERNEL);
+ if (!dr)
+ return -ENOMEM;
+
+ rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id);
+ if (rc) {
+ devres_free(dr);
+ return rc;
+ }
+
+ dr->irq = irq;
+ dr->dev_id = dev_id;
+ devres_add(dev, dr);
+
+ return 0;
+}
+EXPORT_SYMBOL(devm_request_any_context_irq);
+
+/**
* devm_free_irq - free an interrupt
* @dev: device to free interrupt for
* @irq: Interrupt line to free
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 192a302..8ab8e93 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -274,6 +274,7 @@
{
return (irq < NR_IRQS) ? irq_desc + irq : NULL;
}
+EXPORT_SYMBOL(irq_to_desc);
static void free_desc(unsigned int irq)
{
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index cf68bb3..f140337 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -10,6 +10,7 @@
#include <linux/mutex.h>
#include <linux/of.h>
#include <linux/of_address.h>
+#include <linux/of_irq.h>
#include <linux/topology.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 481a13c..d3bf660 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -802,8 +802,7 @@
static void wake_threads_waitq(struct irq_desc *desc)
{
- if (atomic_dec_and_test(&desc->threads_active) &&
- waitqueue_active(&desc->wait_for_threads))
+ if (atomic_dec_and_test(&desc->threads_active))
wake_up(&desc->wait_for_threads);
}
diff --git a/kernel/power/console.c b/kernel/power/console.c
index eacb8bd..aba9c54 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -9,6 +9,7 @@
#include <linux/kbd_kern.h>
#include <linux/vt.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include "power.h"
#define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1)
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index b1d255f..4dae9cb 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1076,7 +1076,6 @@
next_seq = log_next_seq;
len = 0;
- prev = 0;
while (len >= 0 && seq < next_seq) {
struct printk_log *msg = log_from_idx(idx);
int textlen;
@@ -2788,7 +2787,6 @@
next_idx = idx;
l = 0;
- prev = 0;
while (seq < dumper->next_seq) {
struct printk_log *msg = log_from_idx(idx);
diff --git a/kernel/profile.c b/kernel/profile.c
index 6631e1e..ebdd9c1 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -549,14 +549,14 @@
struct page *page;
page = alloc_pages_exact_node(node,
- GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
0);
if (!page)
goto out_cleanup;
per_cpu(cpu_profile_hits, cpu)[1]
= (struct profile_hit *)page_address(page);
page = alloc_pages_exact_node(node,
- GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
0);
if (!page)
goto out_cleanup;
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 43c2bcc..b30a292 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -301,14 +301,14 @@
if (unlikely(!sched_clock_running))
return 0ull;
- preempt_disable();
+ preempt_disable_notrace();
scd = cpu_sdc(cpu);
if (cpu != smp_processor_id())
clock = sched_clock_remote(scd);
else
clock = sched_clock_local(scd);
- preempt_enable();
+ preempt_enable_notrace();
return clock;
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b46131e..f5c6635 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1952,7 +1952,7 @@
{
struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
- u64 period = attr->sched_period;
+ u64 period = attr->sched_period ?: attr->sched_deadline;
u64 runtime = attr->sched_runtime;
u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
int cpus, err = -1;
@@ -3338,6 +3338,15 @@
return -EPERM;
}
+ /*
+ * Can't set/change SCHED_DEADLINE policy at all for now
+ * (safest behavior); in the future we would like to allow
+ * unprivileged DL tasks to increase their relative deadline
+ * or reduce their runtime (both ways reducing utilization)
+ */
+ if (dl_policy(policy))
+ return -EPERM;
+
/*
* Treat SCHED_IDLE as nice 20. Only allow a switch to
* SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
@@ -3661,13 +3670,14 @@
* @pid: the pid in question.
* @uattr: structure containing the extended parameters.
*/
-SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
+SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
+ unsigned int, flags)
{
struct sched_attr attr;
struct task_struct *p;
int retval;
- if (!uattr || pid < 0)
+ if (!uattr || pid < 0 || flags)
return -EINVAL;
if (sched_copy_attr(uattr, &attr))
@@ -3786,7 +3796,7 @@
attr->size = usize;
}
- ret = copy_to_user(uattr, attr, usize);
+ ret = copy_to_user(uattr, attr, attr->size);
if (ret)
return -EFAULT;
@@ -3804,8 +3814,8 @@
* @uattr: structure containing the extended parameters.
* @size: sizeof(attr) for fwd/bwd comp.
*/
-SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
- unsigned int, size)
+SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+ unsigned int, size, unsigned int, flags)
{
struct sched_attr attr = {
.size = sizeof(struct sched_attr),
@@ -3814,7 +3824,7 @@
int retval;
if (!uattr || pid < 0 || size > PAGE_SIZE ||
- size < SCHED_ATTR_SIZE_VER0)
+ size < SCHED_ATTR_SIZE_VER0 || flags)
return -EINVAL;
rcu_read_lock();
@@ -7422,6 +7432,7 @@
u64 period = global_rt_period();
u64 new_bw = to_ratio(period, runtime);
int cpu, ret = 0;
+ unsigned long flags;
/*
* Here we want to check the bandwidth not being set to some
@@ -7435,10 +7446,10 @@
for_each_possible_cpu(cpu) {
struct dl_bw *dl_b = dl_bw_of(cpu);
- raw_spin_lock(&dl_b->lock);
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
if (new_bw < dl_b->total_bw)
ret = -EBUSY;
- raw_spin_unlock(&dl_b->lock);
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
if (ret)
break;
@@ -7451,6 +7462,7 @@
{
u64 new_bw = -1;
int cpu;
+ unsigned long flags;
def_dl_bandwidth.dl_period = global_rt_period();
def_dl_bandwidth.dl_runtime = global_rt_runtime();
@@ -7464,9 +7476,9 @@
for_each_possible_cpu(cpu) {
struct dl_bw *dl_b = dl_bw_of(cpu);
- raw_spin_lock(&dl_b->lock);
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
dl_b->bw = new_bw;
- raw_spin_unlock(&dl_b->lock);
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
}
}
@@ -7475,7 +7487,8 @@
if (sysctl_sched_rt_period <= 0)
return -EINVAL;
- if (sysctl_sched_rt_runtime > sysctl_sched_rt_period)
+ if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
+ (sysctl_sched_rt_runtime > sysctl_sched_rt_period))
return -EINVAL;
return 0;
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 045fc74..5b9bb42 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -70,7 +70,7 @@
static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
{
- WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID);
+ WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
if (dl_time_before(new_dl, cp->elements[idx].dl)) {
cp->elements[idx].dl = new_dl;
@@ -117,7 +117,7 @@
}
out:
- WARN_ON(best_cpu > num_present_cpus() && best_cpu != -1);
+ WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
return best_cpu;
}
@@ -137,7 +137,7 @@
int old_idx, new_cpu;
unsigned long flags;
- WARN_ON(cpu > num_present_cpus());
+ WARN_ON(!cpu_present(cpu));
raw_spin_lock_irqsave(&cp->lock, flags);
old_idx = cp->cpu_to_idx[cpu];
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0dd5e09..6e79b3f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -121,7 +121,7 @@
static void update_dl_migration(struct dl_rq *dl_rq)
{
- if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) {
+ if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) {
if (!dl_rq->overloaded) {
dl_set_overload(rq_of_dl_rq(dl_rq));
dl_rq->overloaded = 1;
@@ -135,9 +135,7 @@
static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
struct task_struct *p = dl_task_of(dl_se);
- dl_rq = &rq_of_dl_rq(dl_rq)->dl;
- dl_rq->dl_nr_total++;
if (p->nr_cpus_allowed > 1)
dl_rq->dl_nr_migratory++;
@@ -147,9 +145,7 @@
static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
struct task_struct *p = dl_task_of(dl_se);
- dl_rq = &rq_of_dl_rq(dl_rq)->dl;
- dl_rq->dl_nr_total--;
if (p->nr_cpus_allowed > 1)
dl_rq->dl_nr_migratory--;
@@ -566,6 +562,8 @@
return 1;
}
+extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
+
/*
* Update the current task's runtime statistics (provided it is still
* a -deadline task and has not been removed from the dl_rq).
@@ -629,11 +627,13 @@
struct rt_rq *rt_rq = &rq->rt;
raw_spin_lock(&rt_rq->rt_runtime_lock);
- rt_rq->rt_time += delta_exec;
/*
* We'll let actual RT tasks worry about the overflow here, we
- * have our own CBS to keep us inline -- see above.
+ * have our own CBS to keep us inline; only account when RT
+ * bandwidth is relevant.
*/
+ if (sched_rt_bandwidth_account(rt_rq))
+ rt_rq->rt_time += delta_exec;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
}
}
@@ -717,6 +717,7 @@
WARN_ON(!dl_prio(prio));
dl_rq->dl_nr_running++;
+ inc_nr_running(rq_of_dl_rq(dl_rq));
inc_dl_deadline(dl_rq, deadline);
inc_dl_migration(dl_se, dl_rq);
@@ -730,6 +731,7 @@
WARN_ON(!dl_prio(prio));
WARN_ON(!dl_rq->dl_nr_running);
dl_rq->dl_nr_running--;
+ dec_nr_running(rq_of_dl_rq(dl_rq));
dec_dl_deadline(dl_rq, dl_se->deadline);
dec_dl_migration(dl_se, dl_rq);
@@ -836,8 +838,6 @@
if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
enqueue_pushable_dl_task(rq, p);
-
- inc_nr_running(rq);
}
static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -850,8 +850,6 @@
{
update_curr_dl(rq);
__dequeue_task_dl(rq, p, flags);
-
- dec_nr_running(rq);
}
/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 966cc2b..9b4c4f3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1757,6 +1757,8 @@
start = end;
if (pages <= 0)
goto out;
+
+ cond_resched();
} while (end != vma->vm_end);
}
@@ -6999,15 +7001,15 @@
struct cfs_rq *cfs_rq = cfs_rq_of(se);
/*
- * Ensure the task's vruntime is normalized, so that when its
+ * Ensure the task's vruntime is normalized, so that when it's
* switched back to the fair class the enqueue_entity(.flags=0) will
* do the right thing.
*
- * If it was on_rq, then the dequeue_entity(.flags=0) will already
- * have normalized the vruntime, if it was !on_rq, then only when
+ * If it's on_rq, then the dequeue_entity(.flags=0) will already
+ * have normalized the vruntime, if it's !on_rq, then only when
* the task is sleeping will it still have non-normalized vruntime.
*/
- if (!se->on_rq && p->state != TASK_RUNNING) {
+ if (!p->on_rq && p->state != TASK_RUNNING) {
/*
* Fix up our vruntime so that the current sleep doesn't
* cause 'unlimited' sleep bonus.
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a2740b7..1999021 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -538,6 +538,14 @@
#endif /* CONFIG_RT_GROUP_SCHED */
+bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
+{
+ struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+ return (hrtimer_active(&rt_b->rt_period_timer) ||
+ rt_rq->rt_time < rt_b->rt_runtime);
+}
+
#ifdef CONFIG_SMP
/*
* We ran out of runtime, see if we can borrow some from our neighbours.
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c2119fd..f964add 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -462,7 +462,6 @@
} earliest_dl;
unsigned long dl_nr_migratory;
- unsigned long dl_nr_total;
int overloaded;
/*
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index b7a1004..4f18e75 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -55,60 +55,33 @@
atomic_t usage;
struct seccomp_filter *prev;
unsigned short len; /* Instruction count */
- struct sock_filter insns[];
+ struct sock_filter_int insnsi[];
};
/* Limit any path through the tree to 256KB worth of instructions. */
#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))
-/**
- * get_u32 - returns a u32 offset into data
- * @data: a unsigned 64 bit value
- * @index: 0 or 1 to return the first or second 32-bits
- *
- * This inline exists to hide the length of unsigned long. If a 32-bit
- * unsigned long is passed in, it will be extended and the top 32-bits will be
- * 0. If it is a 64-bit unsigned long, then whatever data is resident will be
- * properly returned.
- *
+/*
* Endianness is explicitly ignored and left for BPF program authors to manage
* as per the specific architecture.
*/
-static inline u32 get_u32(u64 data, int index)
+static void populate_seccomp_data(struct seccomp_data *sd)
{
- return ((u32 *)&data)[index];
-}
+ struct task_struct *task = current;
+ struct pt_regs *regs = task_pt_regs(task);
-/* Helper for bpf_load below. */
-#define BPF_DATA(_name) offsetof(struct seccomp_data, _name)
-/**
- * bpf_load: checks and returns a pointer to the requested offset
- * @off: offset into struct seccomp_data to load from
- *
- * Returns the requested 32-bits of data.
- * seccomp_check_filter() should assure that @off is 32-bit aligned
- * and not out of bounds. Failure to do so is a BUG.
- */
-u32 seccomp_bpf_load(int off)
-{
- struct pt_regs *regs = task_pt_regs(current);
- if (off == BPF_DATA(nr))
- return syscall_get_nr(current, regs);
- if (off == BPF_DATA(arch))
- return syscall_get_arch(current, regs);
- if (off >= BPF_DATA(args[0]) && off < BPF_DATA(args[6])) {
- unsigned long value;
- int arg = (off - BPF_DATA(args[0])) / sizeof(u64);
- int index = !!(off % sizeof(u64));
- syscall_get_arguments(current, regs, arg, 1, &value);
- return get_u32(value, index);
- }
- if (off == BPF_DATA(instruction_pointer))
- return get_u32(KSTK_EIP(current), 0);
- if (off == BPF_DATA(instruction_pointer) + sizeof(u32))
- return get_u32(KSTK_EIP(current), 1);
- /* seccomp_check_filter should make this impossible. */
- BUG();
+ sd->nr = syscall_get_nr(task, regs);
+ sd->arch = syscall_get_arch(task, regs);
+
+ /* Unroll syscall_get_args to help gcc on arm. */
+ syscall_get_arguments(task, regs, 0, 1, (unsigned long *) &sd->args[0]);
+ syscall_get_arguments(task, regs, 1, 1, (unsigned long *) &sd->args[1]);
+ syscall_get_arguments(task, regs, 2, 1, (unsigned long *) &sd->args[2]);
+ syscall_get_arguments(task, regs, 3, 1, (unsigned long *) &sd->args[3]);
+ syscall_get_arguments(task, regs, 4, 1, (unsigned long *) &sd->args[4]);
+ syscall_get_arguments(task, regs, 5, 1, (unsigned long *) &sd->args[5]);
+
+ sd->instruction_pointer = KSTK_EIP(task);
}
/**
@@ -133,17 +106,17 @@
switch (code) {
case BPF_S_LD_W_ABS:
- ftest->code = BPF_S_ANC_SECCOMP_LD_W;
+ ftest->code = BPF_LDX | BPF_W | BPF_ABS;
/* 32-bit aligned and not out of bounds. */
if (k >= sizeof(struct seccomp_data) || k & 3)
return -EINVAL;
continue;
case BPF_S_LD_W_LEN:
- ftest->code = BPF_S_LD_IMM;
+ ftest->code = BPF_LD | BPF_IMM;
ftest->k = sizeof(struct seccomp_data);
continue;
case BPF_S_LDX_W_LEN:
- ftest->code = BPF_S_LDX_IMM;
+ ftest->code = BPF_LDX | BPF_IMM;
ftest->k = sizeof(struct seccomp_data);
continue;
/* Explicitly include allowed calls. */
@@ -185,6 +158,7 @@
case BPF_S_JMP_JGT_X:
case BPF_S_JMP_JSET_K:
case BPF_S_JMP_JSET_X:
+ sk_decode_filter(ftest, ftest);
continue;
default:
return -EINVAL;
@@ -202,18 +176,21 @@
static u32 seccomp_run_filters(int syscall)
{
struct seccomp_filter *f;
+ struct seccomp_data sd;
u32 ret = SECCOMP_RET_ALLOW;
/* Ensure unexpected behavior doesn't result in failing open. */
if (WARN_ON(current->seccomp.filter == NULL))
return SECCOMP_RET_KILL;
+ populate_seccomp_data(&sd);
+
/*
* All filters in the list are evaluated and the lowest BPF return
* value always takes priority (ignoring the DATA).
*/
for (f = current->seccomp.filter; f; f = f->prev) {
- u32 cur_ret = sk_run_filter(NULL, f->insns);
+ u32 cur_ret = sk_run_filter_int_seccomp(&sd, f->insnsi);
if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
ret = cur_ret;
}
@@ -231,6 +208,8 @@
struct seccomp_filter *filter;
unsigned long fp_size = fprog->len * sizeof(struct sock_filter);
unsigned long total_insns = fprog->len;
+ struct sock_filter *fp;
+ int new_len;
long ret;
if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
@@ -252,28 +231,43 @@
CAP_SYS_ADMIN) != 0)
return -EACCES;
- /* Allocate a new seccomp_filter */
- filter = kzalloc(sizeof(struct seccomp_filter) + fp_size,
- GFP_KERNEL|__GFP_NOWARN);
- if (!filter)
+ fp = kzalloc(fp_size, GFP_KERNEL|__GFP_NOWARN);
+ if (!fp)
return -ENOMEM;
- atomic_set(&filter->usage, 1);
- filter->len = fprog->len;
/* Copy the instructions from fprog. */
ret = -EFAULT;
- if (copy_from_user(filter->insns, fprog->filter, fp_size))
- goto fail;
+ if (copy_from_user(fp, fprog->filter, fp_size))
+ goto free_prog;
/* Check and rewrite the fprog via the skb checker */
- ret = sk_chk_filter(filter->insns, filter->len);
+ ret = sk_chk_filter(fp, fprog->len);
if (ret)
- goto fail;
+ goto free_prog;
/* Check and rewrite the fprog for seccomp use */
- ret = seccomp_check_filter(filter->insns, filter->len);
+ ret = seccomp_check_filter(fp, fprog->len);
if (ret)
- goto fail;
+ goto free_prog;
+
+ /* Convert 'sock_filter' insns to 'sock_filter_int' insns */
+ ret = sk_convert_filter(fp, fprog->len, NULL, &new_len);
+ if (ret)
+ goto free_prog;
+
+ /* Allocate a new seccomp_filter */
+ filter = kzalloc(sizeof(struct seccomp_filter) +
+ sizeof(struct sock_filter_int) * new_len,
+ GFP_KERNEL|__GFP_NOWARN);
+ if (!filter)
+ goto free_prog;
+
+ ret = sk_convert_filter(fp, fprog->len, filter->insnsi, &new_len);
+ if (ret)
+ goto free_filter;
+
+ atomic_set(&filter->usage, 1);
+ filter->len = new_len;
/*
* If there is an existing filter, make it the prev and don't drop its
@@ -282,8 +276,11 @@
filter->prev = current->seccomp.filter;
current->seccomp.filter = filter;
return 0;
-fail:
+
+free_filter:
kfree(filter);
+free_prog:
+ kfree(fp);
return ret;
}
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 84571e0..01fbae5 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -293,7 +293,7 @@
*/
smp_call_function_single(min(cpu1, cpu2),
&irq_cpu_stop_queue_work,
- &call_args, 0);
+ &call_args, 1);
lg_local_unlock(&stop_cpus_lock);
preempt_enable();
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7a925ba..a6a5bf5 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -51,7 +51,13 @@
* HZ shrinks, so values greater than 8 overflow 32bits when
* HZ=100.
*/
+#if HZ < 34
+#define JIFFIES_SHIFT 6
+#elif HZ < 67
+#define JIFFIES_SHIFT 7
+#else
#define JIFFIES_SHIFT 8
+#endif
static cycle_t jiffies_read(struct clocksource *cs)
{
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 0abb364..4d23dc4 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -116,20 +116,42 @@
void __init sched_clock_register(u64 (*read)(void), int bits,
unsigned long rate)
{
+ u64 res, wrap, new_mask, new_epoch, cyc, ns;
+ u32 new_mult, new_shift;
+ ktime_t new_wrap_kt;
unsigned long r;
- u64 res, wrap;
char r_unit;
if (cd.rate > rate)
return;
WARN_ON(!irqs_disabled());
- read_sched_clock = read;
- sched_clock_mask = CLOCKSOURCE_MASK(bits);
- cd.rate = rate;
/* calculate the mult/shift to convert counter ticks to ns. */
- clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 3600);
+ clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
+
+ new_mask = CLOCKSOURCE_MASK(bits);
+
+ /* calculate how many ns until we wrap */
+ wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask);
+ new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
+
+ /* update epoch for new counter and update epoch_ns from old counter*/
+ new_epoch = read();
+ cyc = read_sched_clock();
+ ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
+ cd.mult, cd.shift);
+
+ raw_write_seqcount_begin(&cd.seq);
+ read_sched_clock = read;
+ sched_clock_mask = new_mask;
+ cd.rate = rate;
+ cd.wrap_kt = new_wrap_kt;
+ cd.mult = new_mult;
+ cd.shift = new_shift;
+ cd.epoch_cyc = new_epoch;
+ cd.epoch_ns = ns;
+ raw_write_seqcount_end(&cd.seq);
r = rate;
if (r >= 4000000) {
@@ -141,22 +163,12 @@
} else
r_unit = ' ';
- /* calculate how many ns until we wrap */
- wrap = clocks_calc_max_nsecs(cd.mult, cd.shift, 0, sched_clock_mask);
- cd.wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
-
/* calculate the ns resolution of this counter */
- res = cyc_to_ns(1ULL, cd.mult, cd.shift);
+ res = cyc_to_ns(1ULL, new_mult, new_shift);
+
pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
bits, r, r_unit, res, wrap);
- update_sched_clock();
-
- /*
- * Ensure that sched_clock() starts off at 0ns
- */
- cd.epoch_ns = 0;
-
/* Enable IRQ time accounting if we have a fast enough sched_clock */
if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
enable_sched_clock_irqtime();
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 43780ab..98977a5 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -756,6 +756,7 @@
static void tick_broadcast_clear_oneshot(int cpu)
{
cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
}
static void tick_broadcast_init_next_event(struct cpumask *mask,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 294b8a2..fc4da2d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2397,6 +2397,13 @@
write &= RB_WRITE_MASK;
tail = write - length;
+ /*
+ * If this is the first commit on the page, then it has the same
+ * timestamp as the page itself.
+ */
+ if (!tail)
+ delta = 0;
+
/* See if we shot pass the end of this buffer page */
if (unlikely(write > BUF_PAGE_SIZE))
return rb_move_tail(cpu_buffer, length, tail,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 815c878..24c1f23 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1600,15 +1600,31 @@
}
EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
+static struct ring_buffer *temp_buffer;
+
struct ring_buffer_event *
trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
struct ftrace_event_file *ftrace_file,
int type, unsigned long len,
unsigned long flags, int pc)
{
+ struct ring_buffer_event *entry;
+
*current_rb = ftrace_file->tr->trace_buffer.buffer;
- return trace_buffer_lock_reserve(*current_rb,
+ entry = trace_buffer_lock_reserve(*current_rb,
type, len, flags, pc);
+ /*
+ * If tracing is off, but we have triggers enabled
+ * we still need to look at the event data. Use the temp_buffer
+ * to store the trace event for the tigger to use. It's recusive
+ * safe and will not be recorded anywhere.
+ */
+ if (!entry && ftrace_file->flags & FTRACE_EVENT_FL_TRIGGER_COND) {
+ *current_rb = temp_buffer;
+ entry = trace_buffer_lock_reserve(*current_rb,
+ type, len, flags, pc);
+ }
+ return entry;
}
EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
@@ -6494,11 +6510,16 @@
raw_spin_lock_init(&global_trace.start_lock);
+ /* Used for event triggers */
+ temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE);
+ if (!temp_buffer)
+ goto out_free_cpumask;
+
/* TODO: make the number of buffers hot pluggable with CPUS */
if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
WARN_ON(1);
- goto out_free_cpumask;
+ goto out_free_temp_buffer;
}
if (global_trace.buffer_disabled)
@@ -6540,6 +6561,8 @@
return 0;
+out_free_temp_buffer:
+ ring_buffer_free(temp_buffer);
out_free_cpumask:
free_percpu(global_trace.trace_buffer.data);
#ifdef CONFIG_TRACER_MAX_TRACE
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e71ffd4..7b16d40 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,12 +27,6 @@
DEFINE_MUTEX(event_mutex);
-DEFINE_MUTEX(event_storage_mutex);
-EXPORT_SYMBOL_GPL(event_storage_mutex);
-
-char event_storage[EVENT_STORAGE_SIZE];
-EXPORT_SYMBOL_GPL(event_storage);
-
LIST_HEAD(ftrace_events);
static LIST_HEAD(ftrace_common_fields);
@@ -1777,6 +1771,16 @@
{
struct ftrace_event_call **call, **start, **end;
+ if (!mod->num_trace_events)
+ return;
+
+ /* Don't add infrastructure for mods without tracepoints */
+ if (trace_module_has_bad_taint(mod)) {
+ pr_err("%s: module has bad taint, not creating trace events\n",
+ mod->name);
+ return;
+ }
+
start = mod->trace_events;
end = mod->trace_events + mod->num_trace_events;
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 7c3e3e7..ee0a509 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -95,15 +95,12 @@
#undef __array
#define __array(type, item, len) \
do { \
+ char *type_str = #type"["__stringify(len)"]"; \
BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
- mutex_lock(&event_storage_mutex); \
- snprintf(event_storage, sizeof(event_storage), \
- "%s[%d]", #type, len); \
- ret = trace_define_field(event_call, event_storage, #item, \
+ ret = trace_define_field(event_call, type_str, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), filter_type); \
- mutex_unlock(&event_storage_mutex); \
if (ret) \
return ret; \
} while (0);
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 29f2654..031cc56 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -631,6 +631,11 @@
EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
#ifdef CONFIG_MODULES
+bool trace_module_has_bad_taint(struct module *mod)
+{
+ return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP));
+}
+
static int tracepoint_module_coming(struct module *mod)
{
struct tp_module *tp_mod, *iter;
@@ -641,7 +646,7 @@
* module headers (for forced load), to make sure we don't cause a crash.
* Staging and out-of-tree GPL modules are fine.
*/
- if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)))
+ if (trace_module_has_bad_taint(mod))
return 0;
mutex_lock(&tracepoints_mutex);
tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 240fb62..dd06439 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -225,7 +225,7 @@
*
* When there is no mapping defined for the user-namespace uid
* pair INVALID_UID is returned. Callers are expected to test
- * for and handle handle INVALID_UID being returned. INVALID_UID
+ * for and handle INVALID_UID being returned. INVALID_UID
* may be tested for using uid_valid().
*/
kuid_t make_kuid(struct user_namespace *ns, uid_t uid)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 82ef9f3..193e977 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1851,6 +1851,12 @@
if (worker->flags & WORKER_IDLE)
pool->nr_idle--;
+ /*
+ * Once WORKER_DIE is set, the kworker may destroy itself at any
+ * point. Pin to ensure the task stays until we're done with it.
+ */
+ get_task_struct(worker->task);
+
list_del_init(&worker->entry);
worker->flags |= WORKER_DIE;
@@ -1859,6 +1865,7 @@
spin_unlock_irq(&pool->lock);
kthread_stop(worker->task);
+ put_task_struct(worker->task);
kfree(worker);
spin_lock_irq(&pool->lock);
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 2defd13..98f2d7e 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -424,111 +424,134 @@
EXPORT_SYMBOL(debug_dma_dump_mappings);
/*
- * For each page mapped (initial page in the case of
- * dma_alloc_coherent/dma_map_{single|page}, or each page in a
- * scatterlist) insert into this tree using the pfn as the key. At
+ * For each mapping (initial cacheline in the case of
+ * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a
+ * scatterlist, or the cacheline specified in dma_map_single) insert
+ * into this tree using the cacheline as the key. At
* dma_unmap_{single|sg|page} or dma_free_coherent delete the entry. If
- * the pfn already exists at insertion time add a tag as a reference
+ * the entry already exists at insertion time add a tag as a reference
* count for the overlapping mappings. For now, the overlap tracking
- * just ensures that 'unmaps' balance 'maps' before marking the pfn
- * idle, but we should also be flagging overlaps as an API violation.
+ * just ensures that 'unmaps' balance 'maps' before marking the
+ * cacheline idle, but we should also be flagging overlaps as an API
+ * violation.
*
* Memory usage is mostly constrained by the maximum number of available
* dma-debug entries in that we need a free dma_debug_entry before
- * inserting into the tree. In the case of dma_map_{single|page} and
- * dma_alloc_coherent there is only one dma_debug_entry and one pfn to
- * track per event. dma_map_sg(), on the other hand,
- * consumes a single dma_debug_entry, but inserts 'nents' entries into
- * the tree.
+ * inserting into the tree. In the case of dma_map_page and
+ * dma_alloc_coherent there is only one dma_debug_entry and one
+ * dma_active_cacheline entry to track per event. dma_map_sg(), on the
+ * other hand, consumes a single dma_debug_entry, but inserts 'nents'
+ * entries into the tree.
*
* At any time debug_dma_assert_idle() can be called to trigger a
- * warning if the given page is in the active set.
+ * warning if any cachelines in the given page are in the active set.
*/
-static RADIX_TREE(dma_active_pfn, GFP_NOWAIT);
+static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT);
static DEFINE_SPINLOCK(radix_lock);
-#define ACTIVE_PFN_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
+#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
+#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT)
+#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT)
-static int active_pfn_read_overlap(unsigned long pfn)
+static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry)
+{
+ return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) +
+ (entry->offset >> L1_CACHE_SHIFT);
+}
+
+static int active_cacheline_read_overlap(phys_addr_t cln)
{
int overlap = 0, i;
for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
- if (radix_tree_tag_get(&dma_active_pfn, pfn, i))
+ if (radix_tree_tag_get(&dma_active_cacheline, cln, i))
overlap |= 1 << i;
return overlap;
}
-static int active_pfn_set_overlap(unsigned long pfn, int overlap)
+static int active_cacheline_set_overlap(phys_addr_t cln, int overlap)
{
int i;
- if (overlap > ACTIVE_PFN_MAX_OVERLAP || overlap < 0)
+ if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0)
return overlap;
for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
if (overlap & 1 << i)
- radix_tree_tag_set(&dma_active_pfn, pfn, i);
+ radix_tree_tag_set(&dma_active_cacheline, cln, i);
else
- radix_tree_tag_clear(&dma_active_pfn, pfn, i);
+ radix_tree_tag_clear(&dma_active_cacheline, cln, i);
return overlap;
}
-static void active_pfn_inc_overlap(unsigned long pfn)
+static void active_cacheline_inc_overlap(phys_addr_t cln)
{
- int overlap = active_pfn_read_overlap(pfn);
+ int overlap = active_cacheline_read_overlap(cln);
- overlap = active_pfn_set_overlap(pfn, ++overlap);
+ overlap = active_cacheline_set_overlap(cln, ++overlap);
/* If we overflowed the overlap counter then we're potentially
* leaking dma-mappings. Otherwise, if maps and unmaps are
* balanced then this overflow may cause false negatives in
- * debug_dma_assert_idle() as the pfn may be marked idle
+ * debug_dma_assert_idle() as the cacheline may be marked idle
* prematurely.
*/
- WARN_ONCE(overlap > ACTIVE_PFN_MAX_OVERLAP,
- "DMA-API: exceeded %d overlapping mappings of pfn %lx\n",
- ACTIVE_PFN_MAX_OVERLAP, pfn);
+ WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
+ "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n",
+ ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
}
-static int active_pfn_dec_overlap(unsigned long pfn)
+static int active_cacheline_dec_overlap(phys_addr_t cln)
{
- int overlap = active_pfn_read_overlap(pfn);
+ int overlap = active_cacheline_read_overlap(cln);
- return active_pfn_set_overlap(pfn, --overlap);
+ return active_cacheline_set_overlap(cln, --overlap);
}
-static int active_pfn_insert(struct dma_debug_entry *entry)
+static int active_cacheline_insert(struct dma_debug_entry *entry)
{
+ phys_addr_t cln = to_cacheline_number(entry);
unsigned long flags;
int rc;
+ /* If the device is not writing memory then we don't have any
+ * concerns about the cpu consuming stale data. This mitigates
+ * legitimate usages of overlapping mappings.
+ */
+ if (entry->direction == DMA_TO_DEVICE)
+ return 0;
+
spin_lock_irqsave(&radix_lock, flags);
- rc = radix_tree_insert(&dma_active_pfn, entry->pfn, entry);
+ rc = radix_tree_insert(&dma_active_cacheline, cln, entry);
if (rc == -EEXIST)
- active_pfn_inc_overlap(entry->pfn);
+ active_cacheline_inc_overlap(cln);
spin_unlock_irqrestore(&radix_lock, flags);
return rc;
}
-static void active_pfn_remove(struct dma_debug_entry *entry)
+static void active_cacheline_remove(struct dma_debug_entry *entry)
{
+ phys_addr_t cln = to_cacheline_number(entry);
unsigned long flags;
+ /* ...mirror the insert case */
+ if (entry->direction == DMA_TO_DEVICE)
+ return;
+
spin_lock_irqsave(&radix_lock, flags);
/* since we are counting overlaps the final put of the
- * entry->pfn will occur when the overlap count is 0.
- * active_pfn_dec_overlap() returns -1 in that case
+ * cacheline will occur when the overlap count is 0.
+ * active_cacheline_dec_overlap() returns -1 in that case
*/
- if (active_pfn_dec_overlap(entry->pfn) < 0)
- radix_tree_delete(&dma_active_pfn, entry->pfn);
+ if (active_cacheline_dec_overlap(cln) < 0)
+ radix_tree_delete(&dma_active_cacheline, cln);
spin_unlock_irqrestore(&radix_lock, flags);
}
/**
* debug_dma_assert_idle() - assert that a page is not undergoing dma
- * @page: page to lookup in the dma_active_pfn tree
+ * @page: page to lookup in the dma_active_cacheline tree
*
* Place a call to this routine in cases where the cpu touching the page
* before the dma completes (page is dma_unmapped) will lead to data
@@ -536,22 +559,38 @@
*/
void debug_dma_assert_idle(struct page *page)
{
+ static struct dma_debug_entry *ents[CACHELINES_PER_PAGE];
+ struct dma_debug_entry *entry = NULL;
+ void **results = (void **) &ents;
+ unsigned int nents, i;
unsigned long flags;
- struct dma_debug_entry *entry;
+ phys_addr_t cln;
if (!page)
return;
+ cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT;
spin_lock_irqsave(&radix_lock, flags);
- entry = radix_tree_lookup(&dma_active_pfn, page_to_pfn(page));
+ nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln,
+ CACHELINES_PER_PAGE);
+ for (i = 0; i < nents; i++) {
+ phys_addr_t ent_cln = to_cacheline_number(ents[i]);
+
+ if (ent_cln == cln) {
+ entry = ents[i];
+ break;
+ } else if (ent_cln >= cln + CACHELINES_PER_PAGE)
+ break;
+ }
spin_unlock_irqrestore(&radix_lock, flags);
if (!entry)
return;
+ cln = to_cacheline_number(entry);
err_printk(entry->dev, entry,
- "DMA-API: cpu touching an active dma mapped page "
- "[pfn=0x%lx]\n", entry->pfn);
+ "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n",
+ &cln);
}
/*
@@ -568,9 +607,9 @@
hash_bucket_add(bucket, entry);
put_hash_bucket(bucket, &flags);
- rc = active_pfn_insert(entry);
+ rc = active_cacheline_insert(entry);
if (rc == -ENOMEM) {
- pr_err("DMA-API: pfn tracking ENOMEM, dma-debug disabled\n");
+ pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n");
global_disable = true;
}
@@ -631,7 +670,7 @@
{
unsigned long flags;
- active_pfn_remove(entry);
+ active_cacheline_remove(entry);
/*
* add to beginning of the list - this way the entries are
diff --git a/lib/fonts/Kconfig b/lib/fonts/Kconfig
index 4dc1b99..34fd931 100644
--- a/lib/fonts/Kconfig
+++ b/lib/fonts/Kconfig
@@ -9,7 +9,7 @@
config FONTS
bool "Select compiled-in fonts"
- depends on FRAMEBUFFER_CONSOLE
+ depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE
help
Say Y here if you would like to use fonts other than the default
your frame buffer console usually use.
@@ -22,7 +22,7 @@
config FONT_8x8
bool "VGA 8x8 font" if FONTS
- depends on FRAMEBUFFER_CONSOLE
+ depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE
default y if !SPARC && !FONTS
help
This is the "high resolution" font for the VGA frame buffer (the one
@@ -45,7 +45,7 @@
config FONT_6x11
bool "Mac console 6x11 font (not supported by all drivers)" if FONTS
- depends on FRAMEBUFFER_CONSOLE
+ depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE
default y if !SPARC && !FONTS && MAC
help
Small console font with Macintosh-style high-half glyphs. Some Mac
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 7be235f..93d145e 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -54,9 +54,7 @@
/*
* Try to steal tags from a remote cpu's percpu freelist.
*
- * We first check how many percpu freelists have tags - we don't steal tags
- * unless enough percpu freelists have tags on them that it's possible more than
- * half the total tags could be stuck on remote percpu freelists.
+ * We first check how many percpu freelists have tags
*
* Then we iterate through the cpus until we find some tags - we don't attempt
* to find the "best" cpu to steal from, to keep cacheline bouncing to a
@@ -69,8 +67,7 @@
struct percpu_ida_cpu *remote;
for (cpus_have_tags = cpumask_weight(&pool->cpus_have_tags);
- cpus_have_tags * pool->percpu_max_size > pool->nr_tags / 2;
- cpus_have_tags--) {
+ cpus_have_tags; cpus_have_tags--) {
cpu = cpumask_next(cpu, &pool->cpus_have_tags);
if (cpu >= nr_cpu_ids) {
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 7811ed3..bd4a8df 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1253,8 +1253,10 @@
node = indirect_to_ptr(node);
max_index = radix_tree_maxindex(node->height);
- if (cur_index > max_index)
+ if (cur_index > max_index) {
+ rcu_read_unlock();
break;
+ }
cur_index = __locate(node, item, cur_index, &found_index);
rcu_read_unlock();
diff --git a/lib/random32.c b/lib/random32.c
index 1e5b2df..6148967 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -244,8 +244,19 @@
static bool latch = false;
static DEFINE_SPINLOCK(lock);
+ /* Asking for random bytes might result in bytes getting
+ * moved into the nonblocking pool and thus marking it
+ * as initialized. In this case we would double back into
+ * this function and attempt to do a late reseed.
+ * Ignore the pointless attempt to reseed again if we're
+ * already waiting for bytes when the nonblocking pool
+ * got initialized.
+ */
+
/* only allow initial seeding (late == false) once */
- spin_lock_irqsave(&lock, flags);
+ if (!spin_trylock_irqsave(&lock, flags))
+ return;
+
if (latch && !late)
goto out;
latch = true;
diff --git a/mm/Kconfig b/mm/Kconfig
index 2d9f150..2888024 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -575,5 +575,5 @@
then you should select this. This causes zsmalloc to use page table
mapping rather than copying for object mapping.
- You can check speed with zsmalloc benchmark[1].
- [1] https://github.com/spartacus06/zsmalloc
+ You can check speed with zsmalloc benchmark:
+ https://github.com/spartacus06/zsmapbench
diff --git a/mm/compaction.c b/mm/compaction.c
index b48c525..9185775 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -251,7 +251,6 @@
{
int nr_scanned = 0, total_isolated = 0;
struct page *cursor, *valid_page = NULL;
- unsigned long nr_strict_required = end_pfn - blockpfn;
unsigned long flags;
bool locked = false;
@@ -264,11 +263,12 @@
nr_scanned++;
if (!pfn_valid_within(blockpfn))
- continue;
+ goto isolate_fail;
+
if (!valid_page)
valid_page = page;
if (!PageBuddy(page))
- continue;
+ goto isolate_fail;
/*
* The zone lock must be held to isolate freepages.
@@ -289,12 +289,10 @@
/* Recheck this is a buddy page under lock */
if (!PageBuddy(page))
- continue;
+ goto isolate_fail;
/* Found a free page, break it into order-0 pages */
isolated = split_free_page(page);
- if (!isolated && strict)
- break;
total_isolated += isolated;
for (i = 0; i < isolated; i++) {
list_add(&page->lru, freelist);
@@ -305,7 +303,15 @@
if (isolated) {
blockpfn += isolated - 1;
cursor += isolated - 1;
+ continue;
}
+
+isolate_fail:
+ if (strict)
+ break;
+ else
+ continue;
+
}
trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
@@ -315,7 +321,7 @@
* pages requested were isolated. If there were any failures, 0 is
* returned and CMA will fail.
*/
- if (strict && nr_strict_required > total_isolated)
+ if (strict && blockpfn < end_pfn)
total_isolated = 0;
if (locked)
diff --git a/mm/fremap.c b/mm/fremap.c
index bbc4d66..34feba6 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -23,28 +23,44 @@
#include "internal.h"
+static int mm_counter(struct page *page)
+{
+ return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES;
+}
+
static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
pte_t pte = *ptep;
+ struct page *page;
+ swp_entry_t entry;
if (pte_present(pte)) {
- struct page *page;
-
flush_cache_page(vma, addr, pte_pfn(pte));
pte = ptep_clear_flush(vma, addr, ptep);
page = vm_normal_page(vma, addr, pte);
if (page) {
if (pte_dirty(pte))
set_page_dirty(page);
+ update_hiwater_rss(mm);
+ dec_mm_counter(mm, mm_counter(page));
page_remove_rmap(page);
page_cache_release(page);
- update_hiwater_rss(mm);
- dec_mm_counter(mm, MM_FILEPAGES);
}
- } else {
- if (!pte_file(pte))
- free_swap_and_cache(pte_to_swp_entry(pte));
+ } else { /* zap_pte() is not called when pte_none() */
+ if (!pte_file(pte)) {
+ update_hiwater_rss(mm);
+ entry = pte_to_swp_entry(pte);
+ if (non_swap_entry(entry)) {
+ if (is_migration_entry(entry)) {
+ page = migration_entry_to_page(entry);
+ dec_mm_counter(mm, mm_counter(page));
+ }
+ } else {
+ free_swap_and_cache(entry);
+ dec_mm_counter(mm, MM_SWAPENTS);
+ }
+ }
pte_clear_not_present_full(mm, addr, ptep, 0);
}
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 82166bf..1546655 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1166,8 +1166,10 @@
} else {
ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
pmd, orig_pmd, page, haddr);
- if (ret & VM_FAULT_OOM)
+ if (ret & VM_FAULT_OOM) {
split_huge_page(page);
+ ret |= VM_FAULT_FALLBACK;
+ }
put_page(page);
}
count_vm_event(THP_FAULT_FALLBACK);
@@ -1179,9 +1181,10 @@
if (page) {
split_huge_page(page);
put_page(page);
- }
+ } else
+ split_huge_page_pmd(vma, address, pmd);
+ ret |= VM_FAULT_FALLBACK;
count_vm_event(THP_FAULT_FALLBACK);
- ret |= VM_FAULT_OOM;
goto out;
}
@@ -1545,6 +1548,7 @@
entry = pmd_mknonnuma(entry);
entry = pmd_modify(entry, newprot);
ret = HPAGE_PMD_NR;
+ set_pmd_at(mm, addr, pmd, entry);
BUG_ON(pmd_write(entry));
} else {
struct page *page = pmd_page(*pmd);
@@ -1557,16 +1561,10 @@
*/
if (!is_huge_zero_page(page) &&
!pmd_numa(*pmd)) {
- entry = *pmd;
- entry = pmd_mknuma(entry);
+ pmdp_set_numa(mm, addr, pmd);
ret = HPAGE_PMD_NR;
}
}
-
- /* Set PMD if cleared earlier */
- if (ret == HPAGE_PMD_NR)
- set_pmd_at(mm, addr, pmd, entry);
-
spin_unlock(ptl);
}
@@ -1963,7 +1961,7 @@
return ret;
}
-#define VM_NO_THP (VM_SPECIAL|VM_MIXEDMAP|VM_HUGETLB|VM_SHARED|VM_MAYSHARE)
+#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)
int hugepage_madvise(struct vm_area_struct *vma,
unsigned long *vm_flags, int advice)
diff --git a/mm/ksm.c b/mm/ksm.c
index aa4c7c7..68710e8 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -444,7 +444,7 @@
static struct page *page_trans_compound_anon(struct page *page)
{
if (PageTransCompound(page)) {
- struct page *head = compound_trans_head(page);
+ struct page *head = compound_head(page);
/*
* head may actually be splitted and freed from under
* us but it's ok here.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 53385cd..5b6b003 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1127,8 +1127,8 @@
* skipping css reference should be safe.
*/
if (next_css) {
- if ((next_css->flags & CSS_ONLINE) &&
- (next_css == &root->css || css_tryget(next_css)))
+ if ((next_css == &root->css) ||
+ ((next_css->flags & CSS_ONLINE) && css_tryget(next_css)))
return mem_cgroup_from_css(next_css);
prev_css = next_css;
@@ -1687,7 +1687,7 @@
* protects memcg_name and makes sure that parallel ooms do not
* interleave
*/
- static DEFINE_SPINLOCK(oom_info_lock);
+ static DEFINE_MUTEX(oom_info_lock);
struct cgroup *task_cgrp;
struct cgroup *mem_cgrp;
static char memcg_name[PATH_MAX];
@@ -1698,7 +1698,7 @@
if (!p)
return;
- spin_lock(&oom_info_lock);
+ mutex_lock(&oom_info_lock);
rcu_read_lock();
mem_cgrp = memcg->css.cgroup;
@@ -1767,7 +1767,7 @@
pr_cont("\n");
}
- spin_unlock(&oom_info_lock);
+ mutex_unlock(&oom_info_lock);
}
/*
@@ -6595,6 +6595,7 @@
{
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup_event *event, *tmp;
+ struct cgroup_subsys_state *iter;
/*
* Unregister events and notify userspace.
@@ -6611,7 +6612,14 @@
kmem_cgroup_css_offline(memcg);
mem_cgroup_invalidate_reclaim_iterators(memcg);
- mem_cgroup_reparent_charges(memcg);
+
+ /*
+ * This requires that offlining is serialized. Right now that is
+ * guaranteed because css_killed_work_fn() holds the cgroup_mutex.
+ */
+ css_for_each_descendant_post(iter, css)
+ mem_cgroup_reparent_charges(mem_cgroup_from_css(iter));
+
mem_cgroup_destroy_all_caches(memcg);
vmpressure_cleanup(&memcg->vmpressure);
}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4f08a2d..90002ea 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -945,8 +945,10 @@
* to it. Similarly, page lock is shifted.
*/
if (hpage != p) {
- put_page(hpage);
- get_page(p);
+ if (!(flags & MF_COUNT_INCREASED)) {
+ put_page(hpage);
+ get_page(p);
+ }
lock_page(p);
unlock_page(hpage);
*hpagep = p;
@@ -1649,7 +1651,7 @@
{
int ret;
unsigned long pfn = page_to_pfn(page);
- struct page *hpage = compound_trans_head(page);
+ struct page *hpage = compound_head(page);
if (PageHWPoison(page)) {
pr_info("soft offline: %#lx page already poisoned\n", pfn);
diff --git a/mm/memory.c b/mm/memory.c
index be6a0c0..22dfa61 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3348,6 +3348,7 @@
if (ret & VM_FAULT_LOCKED)
unlock_page(vmf.page);
ret = VM_FAULT_HWPOISON;
+ page_cache_release(vmf.page);
goto uncharge_out;
}
@@ -3703,7 +3704,6 @@
if (unlikely(is_vm_hugetlb_page(vma)))
return hugetlb_fault(mm, vma, address, flags);
-retry:
pgd = pgd_offset(mm, address);
pud = pud_alloc(mm, pgd, address);
if (!pud)
@@ -3741,20 +3741,13 @@
if (dirty && !pmd_write(orig_pmd)) {
ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
orig_pmd);
- /*
- * If COW results in an oom, the huge pmd will
- * have been split, so retry the fault on the
- * pte for a smaller charge.
- */
- if (unlikely(ret & VM_FAULT_OOM))
- goto retry;
- return ret;
+ if (!(ret & VM_FAULT_FALLBACK))
+ return ret;
} else {
huge_pmd_set_accessed(mm, vma, address, pmd,
orig_pmd, dirty);
+ return 0;
}
-
- return 0;
}
}
diff --git a/mm/migrate.c b/mm/migrate.c
index 482a33d..bed4880 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -178,6 +178,37 @@
}
/*
+ * Congratulations to trinity for discovering this bug.
+ * mm/fremap.c's remap_file_pages() accepts any range within a single vma to
+ * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then
+ * replace the specified range by file ptes throughout (maybe populated after).
+ * If page migration finds a page within that range, while it's still located
+ * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem:
+ * zap_pte() clears the temporary migration entry before mmap_sem is dropped.
+ * But if the migrating page is in a part of the vma outside the range to be
+ * remapped, then it will not be cleared, and remove_migration_ptes() needs to
+ * deal with it. Fortunately, this part of the vma is of course still linear,
+ * so we just need to use linear location on the nonlinear list.
+ */
+static int remove_linear_migration_ptes_from_nonlinear(struct page *page,
+ struct address_space *mapping, void *arg)
+{
+ struct vm_area_struct *vma;
+ /* hugetlbfs does not support remap_pages, so no huge pgoff worries */
+ pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+ unsigned long addr;
+
+ list_for_each_entry(vma,
+ &mapping->i_mmap_nonlinear, shared.nonlinear) {
+
+ addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+ if (addr >= vma->vm_start && addr < vma->vm_end)
+ remove_migration_pte(page, vma, addr, arg);
+ }
+ return SWAP_AGAIN;
+}
+
+/*
* Get rid of all migration entries and replace them by
* references to the indicated page.
*/
@@ -186,6 +217,7 @@
struct rmap_walk_control rwc = {
.rmap_one = remove_migration_pte,
.arg = old,
+ .file_nonlinear = remove_linear_migration_ptes_from_nonlinear,
};
rmap_walk(new, &rwc);
@@ -1158,7 +1190,7 @@
pm->node);
else
return alloc_pages_exact_node(pm->node,
- GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
+ GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0);
}
/*
@@ -1544,9 +1576,9 @@
struct page *newpage;
newpage = alloc_pages_exact_node(nid,
- (GFP_HIGHUSER_MOVABLE | GFP_THISNODE |
- __GFP_NOMEMALLOC | __GFP_NORETRY |
- __GFP_NOWARN) &
+ (GFP_HIGHUSER_MOVABLE |
+ __GFP_THISNODE | __GFP_NOMEMALLOC |
+ __GFP_NORETRY | __GFP_NOWARN) &
~GFP_IOFS, 0);
return newpage;
@@ -1747,7 +1779,8 @@
goto out_dropref;
new_page = alloc_pages_node(node,
- (GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER);
+ (GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT,
+ HPAGE_PMD_ORDER);
if (!new_page)
goto out_fail;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 7332c17..769a67a 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -58,36 +58,27 @@
if (pte_numa(ptent))
ptent = pte_mknonnuma(ptent);
ptent = pte_modify(ptent, newprot);
+ /*
+ * Avoid taking write faults for pages we
+ * know to be dirty.
+ */
+ if (dirty_accountable && pte_dirty(ptent))
+ ptent = pte_mkwrite(ptent);
+ ptep_modify_prot_commit(mm, addr, pte, ptent);
updated = true;
} else {
struct page *page;
- ptent = *pte;
page = vm_normal_page(vma, addr, oldpte);
if (page && !PageKsm(page)) {
if (!pte_numa(oldpte)) {
- ptent = pte_mknuma(ptent);
- set_pte_at(mm, addr, pte, ptent);
+ ptep_set_numa(mm, addr, pte);
updated = true;
}
}
}
-
- /*
- * Avoid taking write faults for pages we know to be
- * dirty.
- */
- if (dirty_accountable && pte_dirty(ptent)) {
- ptent = pte_mkwrite(ptent);
- updated = true;
- }
-
if (updated)
pages++;
-
- /* Only !prot_numa always clears the pte */
- if (!prot_numa)
- ptep_modify_prot_commit(mm, addr, pte, ptent);
} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
swp_entry_t entry = pte_to_swp_entry(oldpte);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e3758a0..3bac76a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -369,9 +369,11 @@
__SetPageHead(page);
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
- __SetPageTail(p);
set_page_count(p, 0);
p->first_page = page;
+ /* Make sure p->first_page is always valid for PageTail() */
+ smp_wmb();
+ __SetPageTail(p);
}
}
@@ -1236,6 +1238,15 @@
}
local_irq_restore(flags);
}
+static bool gfp_thisnode_allocation(gfp_t gfp_mask)
+{
+ return (gfp_mask & GFP_THISNODE) == GFP_THISNODE;
+}
+#else
+static bool gfp_thisnode_allocation(gfp_t gfp_mask)
+{
+ return false;
+}
#endif
/*
@@ -1572,7 +1583,13 @@
get_pageblock_migratetype(page));
}
- __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+ /*
+ * NOTE: GFP_THISNODE allocations do not partake in the kswapd
+ * aging protocol, so they can't be fair.
+ */
+ if (!gfp_thisnode_allocation(gfp_flags))
+ __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+
__count_zone_vm_events(PGALLOC, zone, 1 << order);
zone_statistics(preferred_zone, zone, gfp_flags);
local_irq_restore(flags);
@@ -1944,8 +1961,12 @@
* ultimately fall back to remote zones that do not
* partake in the fairness round-robin cycle of this
* zonelist.
+ *
+ * NOTE: GFP_THISNODE allocations do not partake in
+ * the kswapd aging protocol, so they can't be fair.
*/
- if (alloc_flags & ALLOC_WMARK_LOW) {
+ if ((alloc_flags & ALLOC_WMARK_LOW) &&
+ !gfp_thisnode_allocation(gfp_mask)) {
if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
continue;
if (!zone_local(preferred_zone, zone))
@@ -2501,8 +2522,7 @@
* allowed per node queues are empty and that nodes are
* over allocated.
*/
- if (IS_ENABLED(CONFIG_NUMA) &&
- (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
+ if (gfp_thisnode_allocation(gfp_mask))
goto nopage;
restart:
diff --git a/mm/rmap.c b/mm/rmap.c
index d9d4231..8fc049f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1360,8 +1360,9 @@
}
static int try_to_unmap_nonlinear(struct page *page,
- struct address_space *mapping, struct vm_area_struct *vma)
+ struct address_space *mapping, void *arg)
{
+ struct vm_area_struct *vma;
int ret = SWAP_AGAIN;
unsigned long cursor;
unsigned long max_nl_cursor = 0;
@@ -1663,7 +1664,7 @@
if (list_empty(&mapping->i_mmap_nonlinear))
goto done;
- ret = rwc->file_nonlinear(page, mapping, vma);
+ ret = rwc->file_nonlinear(page, mapping, rwc->arg);
done:
mutex_unlock(&mapping->i_mmap_mutex);
diff --git a/mm/slub.c b/mm/slub.c
index 7e3e045..25f14ad 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1004,21 +1004,19 @@
static void add_full(struct kmem_cache *s,
struct kmem_cache_node *n, struct page *page)
{
- lockdep_assert_held(&n->list_lock);
-
if (!(s->flags & SLAB_STORE_USER))
return;
+ lockdep_assert_held(&n->list_lock);
list_add(&page->lru, &n->full);
}
static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page)
{
- lockdep_assert_held(&n->list_lock);
-
if (!(s->flags & SLAB_STORE_USER))
return;
+ lockdep_assert_held(&n->list_lock);
list_del(&page->lru);
}
@@ -1520,11 +1518,9 @@
/*
* Management of partially allocated slabs.
*/
-static inline void add_partial(struct kmem_cache_node *n,
- struct page *page, int tail)
+static inline void
+__add_partial(struct kmem_cache_node *n, struct page *page, int tail)
{
- lockdep_assert_held(&n->list_lock);
-
n->nr_partial++;
if (tail == DEACTIVATE_TO_TAIL)
list_add_tail(&page->lru, &n->partial);
@@ -1532,13 +1528,25 @@
list_add(&page->lru, &n->partial);
}
+static inline void add_partial(struct kmem_cache_node *n,
+ struct page *page, int tail)
+{
+ lockdep_assert_held(&n->list_lock);
+ __add_partial(n, page, tail);
+}
+
+static inline void
+__remove_partial(struct kmem_cache_node *n, struct page *page)
+{
+ list_del(&page->lru);
+ n->nr_partial--;
+}
+
static inline void remove_partial(struct kmem_cache_node *n,
struct page *page)
{
lockdep_assert_held(&n->list_lock);
-
- list_del(&page->lru);
- n->nr_partial--;
+ __remove_partial(n, page);
}
/*
@@ -2906,12 +2914,10 @@
inc_slabs_node(kmem_cache_node, node, page->objects);
/*
- * the lock is for lockdep's sake, not for any actual
- * race protection
+ * No locks need to be taken here as it has just been
+ * initialized and there is no concurrent access.
*/
- spin_lock(&n->list_lock);
- add_partial(n, page, DEACTIVATE_TO_HEAD);
- spin_unlock(&n->list_lock);
+ __add_partial(n, page, DEACTIVATE_TO_HEAD);
}
static void free_kmem_cache_nodes(struct kmem_cache *s)
@@ -3197,7 +3203,7 @@
list_for_each_entry_safe(page, h, &n->partial, lru) {
if (!page->inuse) {
- remove_partial(n, page);
+ __remove_partial(n, page);
discard_slab(s, page);
} else {
list_slab_objects(s, page,
diff --git a/mm/swap.c b/mm/swap.c
index b31ba67..0092097 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -98,7 +98,7 @@
}
/* __split_huge_page_refcount can run under us */
- page_head = compound_trans_head(page);
+ page_head = compound_head(page);
/*
* THP can not break up slab pages so avoid taking
@@ -253,7 +253,7 @@
*/
unsigned long flags;
bool got;
- struct page *page_head = compound_trans_head(page);
+ struct page *page_head = compound_head(page);
/* Ref to put_compound_page() comment. */
if (!__compound_tail_refcounted(page_head)) {
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 196970a..d4042e7 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -19,6 +19,7 @@
#include <linux/mm.h>
#include <linux/vmstat.h>
#include <linux/eventfd.h>
+#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/printk.h>
#include <linux/vmpressure.h>
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index ec99099..175273f 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -307,9 +307,11 @@
static void vlan_transfer_features(struct net_device *dev,
struct net_device *vlandev)
{
+ struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
+
vlandev->gso_max_size = dev->gso_max_size;
- if (dev->features & NETIF_F_HW_VLAN_CTAG_TX)
+ if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto))
vlandev->hard_header_len = dev->hard_header_len;
else
vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 5704ed9..9d010a09 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -38,9 +38,9 @@
static inline unsigned int vlan_proto_idx(__be16 proto)
{
switch (proto) {
- case __constant_htons(ETH_P_8021Q):
+ case htons(ETH_P_8021Q):
return VLAN_PROTO_8021Q;
- case __constant_htons(ETH_P_8021AD):
+ case htons(ETH_P_8021AD):
return VLAN_PROTO_8021AD;
default:
BUG();
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 6ee48aa..3c32bd2 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -22,11 +22,11 @@
return false;
skb->dev = vlan_dev;
- if (skb->pkt_type == PACKET_OTHERHOST) {
+ if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) {
/* Our lower layer thinks this is not local, let's make sure.
* This allows the VLAN to have a different MAC than the
* underlying device, and still route correctly. */
- if (ether_addr_equal(eth_hdr(skb)->h_dest, vlan_dev->dev_addr))
+ if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, vlan_dev->dev_addr))
skb->pkt_type = PACKET_HOST;
}
@@ -106,6 +106,12 @@
}
EXPORT_SYMBOL(vlan_dev_vlan_id);
+__be16 vlan_dev_vlan_proto(const struct net_device *dev)
+{
+ return vlan_dev_priv(dev)->vlan_proto;
+}
+EXPORT_SYMBOL(vlan_dev_vlan_proto);
+
static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
{
if (skb_cow(skb, skb_headroom(skb)) < 0)
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index de51c48..6f142f0 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -538,6 +538,9 @@
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct net_device *real_dev = vlan->real_dev;
+ if (saddr == NULL)
+ saddr = dev->dev_addr;
+
return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
}
@@ -556,7 +559,7 @@
static int vlan_dev_init(struct net_device *dev)
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
- int subclass = 0, i;
+ int subclass = 0;
netif_carrier_off(dev);
@@ -575,6 +578,9 @@
dev->features |= real_dev->vlan_features | NETIF_F_LLTX;
dev->gso_max_size = real_dev->gso_max_size;
+ if (dev->features & NETIF_F_VLAN_FEATURES)
+ netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n");
+
/* ipv6 shared card related stuff */
dev->dev_id = real_dev->dev_id;
@@ -589,7 +595,8 @@
#endif
dev->needed_headroom = real_dev->needed_headroom;
- if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) {
+ if (vlan_hw_offload_capable(real_dev->features,
+ vlan_dev_priv(dev)->vlan_proto)) {
dev->header_ops = &vlan_passthru_header_ops;
dev->hard_header_len = real_dev->hard_header_len;
} else {
@@ -606,17 +613,10 @@
vlan_dev_set_lockdep_class(dev, subclass);
- vlan_dev_priv(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats);
+ vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct vlan_pcpu_stats *vlan_stat;
- vlan_stat = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
- u64_stats_init(&vlan_stat->syncp);
- }
-
-
return 0;
}
@@ -682,13 +682,13 @@
p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
do {
- start = u64_stats_fetch_begin_bh(&p->syncp);
+ start = u64_stats_fetch_begin_irq(&p->syncp);
rxpackets = p->rx_packets;
rxbytes = p->rx_bytes;
rxmulticast = p->rx_multicast;
txpackets = p->tx_packets;
txbytes = p->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&p->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&p->syncp, start));
stats->rx_packets += rxpackets;
stats->rx_bytes += rxbytes;
@@ -711,20 +711,19 @@
return;
}
-static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo,
- gfp_t gfp)
+static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct net_device *real_dev = vlan->real_dev;
struct netpoll *netpoll;
int err = 0;
- netpoll = kzalloc(sizeof(*netpoll), gfp);
+ netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
err = -ENOMEM;
if (!netpoll)
goto out;
- err = __netpoll_setup(netpoll, real_dev, gfp);
+ err = __netpoll_setup(netpoll, real_dev);
if (err) {
kfree(netpoll);
goto out;
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index c7e634a..8ac8a5c 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -56,8 +56,8 @@
if (data[IFLA_VLAN_PROTOCOL]) {
switch (nla_get_be16(data[IFLA_VLAN_PROTOCOL])) {
- case __constant_htons(ETH_P_8021Q):
- case __constant_htons(ETH_P_8021AD):
+ case htons(ETH_P_8021Q):
+ case htons(ETH_P_8021AD):
break;
default:
return -EPROTONOSUPPORT;
diff --git a/net/9p/client.c b/net/9p/client.c
index a5e4d2d..9186550 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -204,7 +204,7 @@
return ret;
}
-struct p9_fcall *p9_fcall_alloc(int alloc_msize)
+static struct p9_fcall *p9_fcall_alloc(int alloc_msize)
{
struct p9_fcall *fc;
fc = kmalloc(sizeof(struct p9_fcall) + alloc_msize, GFP_NOFS);
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index cd1e1ed..ac2666c 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -340,7 +340,10 @@
int count = nr_pages;
while (nr_pages) {
s = rest_of_page(data);
- pages[index++] = kmap_to_page(data);
+ if (is_vmalloc_addr(data))
+ pages[index++] = vmalloc_to_page(data);
+ else
+ pages[index++] = kmap_to_page(data);
data += s;
nr_pages--;
}
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index d27b86d..d1c55d8 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -926,7 +926,7 @@
struct aarp_entry *entry;
rescan:
- while(ct < AARP_HASH_SIZE) {
+ while (ct < AARP_HASH_SIZE) {
for (entry = table[ct]; entry; entry = entry->next) {
if (!pos || ++off == *pos) {
iter->table = table;
@@ -995,7 +995,7 @@
{
static char buf[32];
- sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100 ) / HZ);
+ sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100) / HZ);
return buf;
}
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 02806c6..786ee2f 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -293,7 +293,7 @@
/* Perform AARP probing for a proxy address */
static int atif_proxy_probe_device(struct atalk_iface *atif,
- struct atalk_addr* proxy_addr)
+ struct atalk_addr *proxy_addr)
{
int netrange = ntohs(atif->nets.nr_lastnet) -
ntohs(atif->nets.nr_firstnet) + 1;
@@ -581,7 +581,7 @@
}
/* Delete a route. Find it and discard it */
-static int atrtr_delete(struct atalk_addr * addr)
+static int atrtr_delete(struct atalk_addr *addr)
{
struct atalk_route **r = &atalk_routes;
int retval = 0;
@@ -936,11 +936,11 @@
int i, copy;
/* checksum stuff in header space */
- if ( (copy = start - offset) > 0) {
+ if ((copy = start - offset) > 0) {
if (copy > len)
copy = len;
sum = atalk_sum_partial(skb->data + offset, copy, sum);
- if ( (len -= copy) == 0)
+ if ((len -= copy) == 0)
return sum;
offset += copy;
@@ -1151,7 +1151,7 @@
goto out;
at->src_net = addr->sat_addr.s_net = ap->s_net;
- at->src_node = addr->sat_addr.s_node= ap->s_node;
+ at->src_node = addr->sat_addr.s_node = ap->s_node;
} else {
err = -EADDRNOTAVAIL;
if (!atalk_find_interface(addr->sat_addr.s_net,
@@ -1790,53 +1790,53 @@
void __user *argp = (void __user *)arg;
switch (cmd) {
- /* Protocol layer */
- case TIOCOUTQ: {
- long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk);
+ /* Protocol layer */
+ case TIOCOUTQ: {
+ long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk);
- if (amount < 0)
- amount = 0;
- rc = put_user(amount, (int __user *)argp);
- break;
- }
- case TIOCINQ: {
- /*
- * These two are safe on a single CPU system as only
- * user tasks fiddle here
- */
- struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
- long amount = 0;
+ if (amount < 0)
+ amount = 0;
+ rc = put_user(amount, (int __user *)argp);
+ break;
+ }
+ case TIOCINQ: {
+ /*
+ * These two are safe on a single CPU system as only
+ * user tasks fiddle here
+ */
+ struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+ long amount = 0;
- if (skb)
- amount = skb->len - sizeof(struct ddpehdr);
- rc = put_user(amount, (int __user *)argp);
- break;
- }
- case SIOCGSTAMP:
- rc = sock_get_timestamp(sk, argp);
- break;
- case SIOCGSTAMPNS:
- rc = sock_get_timestampns(sk, argp);
- break;
- /* Routing */
- case SIOCADDRT:
- case SIOCDELRT:
- rc = -EPERM;
- if (capable(CAP_NET_ADMIN))
- rc = atrtr_ioctl(cmd, argp);
- break;
- /* Interface */
- case SIOCGIFADDR:
- case SIOCSIFADDR:
- case SIOCGIFBRDADDR:
- case SIOCATALKDIFADDR:
- case SIOCDIFADDR:
- case SIOCSARP: /* proxy AARP */
- case SIOCDARP: /* proxy AARP */
- rtnl_lock();
- rc = atif_ioctl(cmd, argp);
- rtnl_unlock();
- break;
+ if (skb)
+ amount = skb->len - sizeof(struct ddpehdr);
+ rc = put_user(amount, (int __user *)argp);
+ break;
+ }
+ case SIOCGSTAMP:
+ rc = sock_get_timestamp(sk, argp);
+ break;
+ case SIOCGSTAMPNS:
+ rc = sock_get_timestampns(sk, argp);
+ break;
+ /* Routing */
+ case SIOCADDRT:
+ case SIOCDELRT:
+ rc = -EPERM;
+ if (capable(CAP_NET_ADMIN))
+ rc = atrtr_ioctl(cmd, argp);
+ break;
+ /* Interface */
+ case SIOCGIFADDR:
+ case SIOCSIFADDR:
+ case SIOCGIFBRDADDR:
+ case SIOCATALKDIFADDR:
+ case SIOCDIFADDR:
+ case SIOCSARP: /* proxy AARP */
+ case SIOCDARP: /* proxy AARP */
+ rtnl_lock();
+ rc = atif_ioctl(cmd, argp);
+ rtnl_unlock();
+ break;
}
return rc;
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index b71ff6b..91dc58f 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -1492,7 +1492,7 @@
mpc_proc_clean();
- del_timer(&mpc_timer);
+ del_timer_sync(&mpc_timer);
unregister_netdevice_notifier(&mpoa_notifier);
deregister_atm_ioctl(&atm_ioctl_ops);
diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index fa780b7..11660a3 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -50,6 +50,15 @@
If you think that your network does not need this feature you
can safely disable it and save some space.
+config BATMAN_ADV_MCAST
+ bool "Multicast optimisation"
+ depends on BATMAN_ADV
+ default n
+ help
+ This option enables the multicast optimisation which aims to
+ reduce the air overhead while improving the reliability of
+ multicast messages.
+
config BATMAN_ADV_DEBUG
bool "B.A.T.M.A.N. debugging"
depends on BATMAN_ADV
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index 42df18f..eb7d8c03 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -36,3 +36,4 @@
batman-adv-y += soft-interface.o
batman-adv-y += sysfs.o
batman-adv-y += translation-table.o
+batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 512159b..b3bd4ec 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -241,19 +241,19 @@
size = bat_priv->num_ifaces * sizeof(uint8_t);
orig_node->bat_iv.bcast_own_sum = kzalloc(size, GFP_ATOMIC);
if (!orig_node->bat_iv.bcast_own_sum)
- goto free_bcast_own;
+ goto free_orig_node;
hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig,
batadv_choose_orig, orig_node,
&orig_node->hash_entry);
if (hash_added != 0)
- goto free_bcast_own;
+ goto free_orig_node;
return orig_node;
-free_bcast_own:
- kfree(orig_node->bat_iv.bcast_own);
free_orig_node:
+ /* free twice, as batadv_orig_node_new sets refcount to 2 */
+ batadv_orig_node_free_ref(orig_node);
batadv_orig_node_free_ref(orig_node);
return NULL;
@@ -266,7 +266,7 @@
struct batadv_orig_node *orig_neigh)
{
struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
- struct batadv_neigh_node *neigh_node;
+ struct batadv_neigh_node *neigh_node, *tmp_neigh_node;
neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, orig_node);
if (!neigh_node)
@@ -281,14 +281,24 @@
neigh_node->orig_node = orig_neigh;
neigh_node->if_incoming = hard_iface;
- batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
- "Creating new neighbor %pM for orig_node %pM on interface %s\n",
- neigh_addr, orig_node->orig, hard_iface->net_dev->name);
-
spin_lock_bh(&orig_node->neigh_list_lock);
- hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list);
+ tmp_neigh_node = batadv_neigh_node_get(orig_node, hard_iface,
+ neigh_addr);
+ if (!tmp_neigh_node) {
+ hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list);
+ } else {
+ kfree(neigh_node);
+ batadv_hardif_free_ref(hard_iface);
+ neigh_node = tmp_neigh_node;
+ }
spin_unlock_bh(&orig_node->neigh_list_lock);
+ if (!tmp_neigh_node)
+ batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+ "Creating new neighbor %pM for orig_node %pM on interface %s\n",
+ neigh_addr, orig_node->orig,
+ hard_iface->net_dev->name);
+
out:
return neigh_node;
}
@@ -337,10 +347,10 @@
unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff;
batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff;
- memcpy(batadv_ogm_packet->orig,
- hard_iface->net_dev->dev_addr, ETH_ALEN);
- memcpy(batadv_ogm_packet->prev_sender,
- hard_iface->net_dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(batadv_ogm_packet->orig,
+ hard_iface->net_dev->dev_addr);
+ ether_addr_copy(batadv_ogm_packet->prev_sender,
+ hard_iface->net_dev->dev_addr);
}
static void
@@ -820,7 +830,7 @@
tvlv_len = ntohs(batadv_ogm_packet->tvlv_len);
batadv_ogm_packet->ttl--;
- memcpy(batadv_ogm_packet->prev_sender, ethhdr->h_source, ETH_ALEN);
+ ether_addr_copy(batadv_ogm_packet->prev_sender, ethhdr->h_source);
/* apply hop penalty */
batadv_ogm_packet->tq = batadv_hop_penalty(batadv_ogm_packet->tq,
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 05f0712..6f0d9ec 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -191,7 +191,7 @@
if (!hash)
return NULL;
- memcpy(search_entry.orig, addr, ETH_ALEN);
+ ether_addr_copy(search_entry.orig, addr);
search_entry.vid = vid;
index = batadv_choose_backbone_gw(&search_entry, hash->size);
@@ -305,7 +305,7 @@
/* normal claim frame
* set Ethernet SRC to the clients mac
*/
- memcpy(ethhdr->h_source, mac, ETH_ALEN);
+ ether_addr_copy(ethhdr->h_source, mac);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_send_claim(): CLAIM %pM on vid %d\n", mac,
BATADV_PRINT_VID(vid));
@@ -314,7 +314,7 @@
/* unclaim frame
* set HW SRC to the clients mac
*/
- memcpy(hw_src, mac, ETH_ALEN);
+ ether_addr_copy(hw_src, mac);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_send_claim(): UNCLAIM %pM on vid %d\n", mac,
BATADV_PRINT_VID(vid));
@@ -323,7 +323,7 @@
/* announcement frame
* set HW SRC to the special mac containg the crc
*/
- memcpy(hw_src, mac, ETH_ALEN);
+ ether_addr_copy(hw_src, mac);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_send_claim(): ANNOUNCE of %pM on vid %d\n",
ethhdr->h_source, BATADV_PRINT_VID(vid));
@@ -333,8 +333,8 @@
* set HW SRC and header destination to the receiving backbone
* gws mac
*/
- memcpy(hw_src, mac, ETH_ALEN);
- memcpy(ethhdr->h_dest, mac, ETH_ALEN);
+ ether_addr_copy(hw_src, mac);
+ ether_addr_copy(ethhdr->h_dest, mac);
batadv_dbg(BATADV_DBG_BLA, bat_priv,
"bla_send_claim(): REQUEST of %pM to %pM on vid %d\n",
ethhdr->h_source, ethhdr->h_dest,
@@ -395,7 +395,7 @@
entry->bat_priv = bat_priv;
atomic_set(&entry->request_sent, 0);
atomic_set(&entry->wait_periods, 0);
- memcpy(entry->orig, orig, ETH_ALEN);
+ ether_addr_copy(entry->orig, orig);
/* one for the hash, one for returning */
atomic_set(&entry->refcount, 2);
@@ -563,7 +563,7 @@
struct batadv_bla_claim search_claim;
int hash_added;
- memcpy(search_claim.addr, mac, ETH_ALEN);
+ ether_addr_copy(search_claim.addr, mac);
search_claim.vid = vid;
claim = batadv_claim_hash_find(bat_priv, &search_claim);
@@ -573,7 +573,7 @@
if (!claim)
return;
- memcpy(claim->addr, mac, ETH_ALEN);
+ ether_addr_copy(claim->addr, mac);
claim->vid = vid;
claim->lasttime = jiffies;
claim->backbone_gw = backbone_gw;
@@ -624,7 +624,7 @@
{
struct batadv_bla_claim search_claim, *claim;
- memcpy(search_claim.addr, mac, ETH_ALEN);
+ ether_addr_copy(search_claim.addr, mac);
search_claim.vid = vid;
claim = batadv_claim_hash_find(bat_priv, &search_claim);
if (!claim)
@@ -882,7 +882,7 @@
proto = ethhdr->h_proto;
headlen = ETH_HLEN;
if (vid & BATADV_VLAN_HAS_TAG) {
- vhdr = (struct vlan_ethhdr *)ethhdr;
+ vhdr = vlan_eth_hdr(skb);
proto = vhdr->h_vlan_encapsulated_proto;
headlen += VLAN_HLEN;
}
@@ -1103,8 +1103,8 @@
oldif->net_dev->dev_addr))
continue;
- memcpy(backbone_gw->orig,
- primary_if->net_dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(backbone_gw->orig,
+ primary_if->net_dev->dev_addr);
/* send an announce frame so others will ask for our
* claims and update their tables.
*/
@@ -1310,7 +1310,7 @@
entry = &bat_priv->bla.bcast_duplist[curr];
entry->crc = crc;
entry->entrytime = jiffies;
- memcpy(entry->orig, bcast_packet->orig, ETH_ALEN);
+ ether_addr_copy(entry->orig, bcast_packet->orig);
bat_priv->bla.bcast_duplist_curr = curr;
out:
@@ -1458,7 +1458,7 @@
if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast)
goto handled;
- memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN);
+ ether_addr_copy(search_claim.addr, ethhdr->h_source);
search_claim.vid = vid;
claim = batadv_claim_hash_find(bat_priv, &search_claim);
@@ -1547,9 +1547,6 @@
if (!atomic_read(&bat_priv->bridge_loop_avoidance))
goto allow;
- /* in VLAN case, the mac header might not be set. */
- skb_reset_mac_header(skb);
-
if (batadv_bla_process_claim(bat_priv, primary_if, skb))
goto handled;
@@ -1560,7 +1557,7 @@
if (is_multicast_ether_addr(ethhdr->h_dest))
goto handled;
- memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN);
+ ether_addr_copy(search_claim.addr, ethhdr->h_source);
search_claim.vid = vid;
claim = batadv_claim_hash_find(bat_priv, &search_claim);
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index edee504..b25fd64 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -277,7 +277,7 @@
/* if this entry is already known, just update it */
if (dat_entry) {
if (!batadv_compare_eth(dat_entry->mac_addr, mac_addr))
- memcpy(dat_entry->mac_addr, mac_addr, ETH_ALEN);
+ ether_addr_copy(dat_entry->mac_addr, mac_addr);
dat_entry->last_update = jiffies;
batadv_dbg(BATADV_DBG_DAT, bat_priv,
"Entry updated: %pI4 %pM (vid: %d)\n",
@@ -292,7 +292,7 @@
dat_entry->ip = ip;
dat_entry->vid = vid;
- memcpy(dat_entry->mac_addr, mac_addr, ETH_ALEN);
+ ether_addr_copy(dat_entry->mac_addr, mac_addr);
dat_entry->last_update = jiffies;
atomic_set(&dat_entry->refcount, 2);
@@ -1027,6 +1027,11 @@
if (!skb_new)
goto out;
+ /* the rest of the TX path assumes that the mac_header offset pointing
+ * to the inner Ethernet header has been set, therefore reset it now.
+ */
+ skb_reset_mac_header(skb_new);
+
if (vid & BATADV_VLAN_HAS_TAG)
skb_new = vlan_insert_tag(skb_new, htons(ETH_P_8021Q),
vid & VLAN_VID_MASK);
diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h
index ac9be9b..d76e1d0 100644
--- a/net/batman-adv/distributed-arp-table.h
+++ b/net/batman-adv/distributed-arp-table.h
@@ -25,6 +25,9 @@
#include <linux/if_arp.h>
+/**
+ * BATADV_DAT_ADDR_MAX - maximum address value in the DHT space
+ */
#define BATADV_DAT_ADDR_MAX ((batadv_dat_addr_t)~(batadv_dat_addr_t)0)
void batadv_dat_status_update(struct net_device *net_dev);
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 88df9b1..bcc4bea 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -449,8 +449,8 @@
frag_header.reserved = 0;
frag_header.no = 0;
frag_header.total_size = htons(skb->len);
- memcpy(frag_header.orig, primary_if->net_dev->dev_addr, ETH_ALEN);
- memcpy(frag_header.dest, orig_node->orig, ETH_ALEN);
+ ether_addr_copy(frag_header.orig, primary_if->net_dev->dev_addr);
+ ether_addr_copy(frag_header.dest, orig_node->orig);
/* Eat and send fragments from the tail of skb */
while (skb->len > max_fragment_size) {
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 55cf226..c835e13 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -389,8 +389,6 @@
batadv_neigh_ifinfo_free_ref(router_gw_tq);
if (router_orig_tq)
batadv_neigh_ifinfo_free_ref(router_orig_tq);
-
- return;
}
/**
@@ -680,7 +678,7 @@
if (!pskb_may_pull(skb, *header_len + ETH_HLEN))
return BATADV_DHCP_NO;
- ethhdr = (struct ethhdr *)skb->data;
+ ethhdr = eth_hdr(skb);
proto = ethhdr->h_proto;
*header_len += ETH_HLEN;
@@ -689,7 +687,7 @@
if (!pskb_may_pull(skb, *header_len + VLAN_HLEN))
return BATADV_DHCP_NO;
- vhdr = (struct vlan_ethhdr *)skb->data;
+ vhdr = vlan_eth_hdr(skb);
proto = vhdr->h_vlan_encapsulated_proto;
*header_len += VLAN_HLEN;
}
@@ -728,7 +726,7 @@
return BATADV_DHCP_NO;
/* skb->data might have been reallocated by pskb_may_pull() */
- ethhdr = (struct ethhdr *)skb->data;
+ ethhdr = eth_hdr(skb);
if (ntohs(ethhdr->h_proto) == ETH_P_8021Q)
ethhdr = (struct ethhdr *)(skb->data + VLAN_HLEN);
@@ -765,7 +763,7 @@
if (*p != ETH_ALEN)
return BATADV_DHCP_NO;
- memcpy(chaddr, skb->data + chaddr_offset, ETH_ALEN);
+ ether_addr_copy(chaddr, skb->data + chaddr_offset);
}
return ret;
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 3d417d3..b851cc5 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -241,7 +241,7 @@
{
struct batadv_priv *bat_priv = netdev_priv(soft_iface);
const struct batadv_hard_iface *hard_iface;
- int min_mtu = ETH_DATA_LEN;
+ int min_mtu = INT_MAX;
rcu_read_lock();
list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
@@ -256,8 +256,6 @@
}
rcu_read_unlock();
- atomic_set(&bat_priv->packet_size_max, min_mtu);
-
if (atomic_read(&bat_priv->fragmentation) == 0)
goto out;
@@ -268,13 +266,21 @@
min_mtu = min_t(int, min_mtu, BATADV_FRAG_MAX_FRAG_SIZE);
min_mtu -= sizeof(struct batadv_frag_packet);
min_mtu *= BATADV_FRAG_MAX_FRAGMENTS;
- atomic_set(&bat_priv->packet_size_max, min_mtu);
-
- /* with fragmentation enabled we can fragment external packets easily */
- min_mtu = min_t(int, min_mtu, ETH_DATA_LEN);
out:
- return min_mtu - batadv_max_header_len();
+ /* report to the other components the maximum amount of bytes that
+ * batman-adv can send over the wire (without considering the payload
+ * overhead). For example, this value is used by TT to compute the
+ * maximum local table table size
+ */
+ atomic_set(&bat_priv->packet_size_max, min_mtu);
+
+ /* the real soft-interface MTU is computed by removing the payload
+ * overhead from the maximum amount of bytes that was just computed.
+ *
+ * However batman-adv does not support MTUs bigger than ETH_DATA_LEN
+ */
+ return min_t(int, min_mtu - batadv_max_header_len(), ETH_DATA_LEN);
}
/* adjusts the MTU if a new interface with a smaller MTU appeared. */
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index abb9d6e..161ef8f 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -158,6 +158,7 @@
struct batadv_orig_node *orig_node = NULL;
struct batadv_neigh_node *neigh_node = NULL;
size_t packet_len = sizeof(struct batadv_icmp_packet);
+ uint8_t *addr;
if (len < sizeof(struct batadv_icmp_header)) {
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
@@ -227,10 +228,10 @@
goto dst_unreach;
icmp_packet_rr = (struct batadv_icmp_packet_rr *)icmp_header;
- if (packet_len == sizeof(*icmp_packet_rr))
- memcpy(icmp_packet_rr->rr,
- neigh_node->if_incoming->net_dev->dev_addr,
- ETH_ALEN);
+ if (packet_len == sizeof(*icmp_packet_rr)) {
+ addr = neigh_node->if_incoming->net_dev->dev_addr;
+ ether_addr_copy(icmp_packet_rr->rr[0], addr);
+ }
break;
default:
@@ -250,7 +251,7 @@
goto free_skb;
}
- memcpy(icmp_header->orig, primary_if->net_dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(icmp_header->orig, primary_if->net_dev->dev_addr);
batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
goto out;
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 66ae135..d1183e8 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -34,6 +34,7 @@
#include "gateway_client.h"
#include "bridge_loop_avoidance.h"
#include "distributed-arp-table.h"
+#include "multicast.h"
#include "gateway_common.h"
#include "hash.h"
#include "bat_algo.h"
@@ -110,6 +111,9 @@
spin_lock_init(&bat_priv->tt.last_changeset_lock);
spin_lock_init(&bat_priv->tt.commit_lock);
spin_lock_init(&bat_priv->gw.list_lock);
+#ifdef CONFIG_BATMAN_ADV_MCAST
+ spin_lock_init(&bat_priv->mcast.want_lists_lock);
+#endif
spin_lock_init(&bat_priv->tvlv.container_list_lock);
spin_lock_init(&bat_priv->tvlv.handler_list_lock);
spin_lock_init(&bat_priv->softif_vlan_list_lock);
@@ -117,9 +121,17 @@
INIT_HLIST_HEAD(&bat_priv->forw_bat_list);
INIT_HLIST_HEAD(&bat_priv->forw_bcast_list);
INIT_HLIST_HEAD(&bat_priv->gw.list);
+#ifdef CONFIG_BATMAN_ADV_MCAST
+ INIT_HLIST_HEAD(&bat_priv->mcast.want_all_unsnoopables_list);
+ INIT_HLIST_HEAD(&bat_priv->mcast.want_all_ipv4_list);
+ INIT_HLIST_HEAD(&bat_priv->mcast.want_all_ipv6_list);
+#endif
INIT_LIST_HEAD(&bat_priv->tt.changes_list);
INIT_LIST_HEAD(&bat_priv->tt.req_list);
INIT_LIST_HEAD(&bat_priv->tt.roam_list);
+#ifdef CONFIG_BATMAN_ADV_MCAST
+ INIT_HLIST_HEAD(&bat_priv->mcast.mla_list);
+#endif
INIT_HLIST_HEAD(&bat_priv->tvlv.container_list);
INIT_HLIST_HEAD(&bat_priv->tvlv.handler_list);
INIT_HLIST_HEAD(&bat_priv->softif_vlan_list);
@@ -145,6 +157,7 @@
goto err;
batadv_gw_init(bat_priv);
+ batadv_mcast_init(bat_priv);
atomic_set(&bat_priv->gw.reselect, 0);
atomic_set(&bat_priv->mesh_state, BATADV_MESH_ACTIVE);
@@ -169,6 +182,8 @@
batadv_dat_free(bat_priv);
batadv_bla_free(bat_priv);
+ batadv_mcast_free(bat_priv);
+
/* Free the TT and the originator tables only after having terminated
* all the other depending components which may use these structures for
* their purposes.
@@ -1133,8 +1148,8 @@
unicast_tvlv_packet->reserved = 0;
unicast_tvlv_packet->tvlv_len = htons(tvlv_len);
unicast_tvlv_packet->align = 0;
- memcpy(unicast_tvlv_packet->src, src, ETH_ALEN);
- memcpy(unicast_tvlv_packet->dst, dst, ETH_ALEN);
+ ether_addr_copy(unicast_tvlv_packet->src, src);
+ ether_addr_copy(unicast_tvlv_packet->dst, dst);
tvlv_buff = (unsigned char *)(unicast_tvlv_packet + 1);
tvlv_hdr = (struct batadv_tvlv_hdr *)tvlv_buff;
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 9374f1a..770dc89 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -24,7 +24,7 @@
#define BATADV_DRIVER_DEVICE "batman-adv"
#ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2014.1.0"
+#define BATADV_SOURCE_VERSION "2014.2.0"
#endif
/* B.A.T.M.A.N. parameters */
@@ -176,6 +176,8 @@
#include <linux/percpu.h>
#include <linux/slab.h>
#include <net/sock.h> /* struct sock */
+#include <net/addrconf.h> /* ipv6 address stuff */
+#include <linux/ip.h>
#include <net/rtnetlink.h>
#include <linux/jiffies.h>
#include <linux/seq_file.h>
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
new file mode 100644
index 0000000..8c7ca81
--- /dev/null
+++ b/net/batman-adv/multicast.c
@@ -0,0 +1,748 @@
+/* Copyright (C) 2014 B.A.T.M.A.N. contributors:
+ *
+ * Linus Lüssing
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+#include "multicast.h"
+#include "originator.h"
+#include "hard-interface.h"
+#include "translation-table.h"
+#include "multicast.h"
+
+/**
+ * batadv_mcast_mla_softif_get - get softif multicast listeners
+ * @dev: the device to collect multicast addresses from
+ * @mcast_list: a list to put found addresses into
+ *
+ * Collect multicast addresses of the local multicast listeners
+ * on the given soft interface, dev, in the given mcast_list.
+ *
+ * Returns -ENOMEM on memory allocation error or the number of
+ * items added to the mcast_list otherwise.
+ */
+static int batadv_mcast_mla_softif_get(struct net_device *dev,
+ struct hlist_head *mcast_list)
+{
+ struct netdev_hw_addr *mc_list_entry;
+ struct batadv_hw_addr *new;
+ int ret = 0;
+
+ netif_addr_lock_bh(dev);
+ netdev_for_each_mc_addr(mc_list_entry, dev) {
+ new = kmalloc(sizeof(*new), GFP_ATOMIC);
+ if (!new) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ ether_addr_copy(new->addr, mc_list_entry->addr);
+ hlist_add_head(&new->list, mcast_list);
+ ret++;
+ }
+ netif_addr_unlock_bh(dev);
+
+ return ret;
+}
+
+/**
+ * batadv_mcast_mla_is_duplicate - check whether an address is in a list
+ * @mcast_addr: the multicast address to check
+ * @mcast_list: the list with multicast addresses to search in
+ *
+ * Returns true if the given address is already in the given list.
+ * Otherwise returns false.
+ */
+static bool batadv_mcast_mla_is_duplicate(uint8_t *mcast_addr,
+ struct hlist_head *mcast_list)
+{
+ struct batadv_hw_addr *mcast_entry;
+
+ hlist_for_each_entry(mcast_entry, mcast_list, list)
+ if (batadv_compare_eth(mcast_entry->addr, mcast_addr))
+ return true;
+
+ return false;
+}
+
+/**
+ * batadv_mcast_mla_list_free - free a list of multicast addresses
+ * @mcast_list: the list to free
+ *
+ * Removes and frees all items in the given mcast_list.
+ */
+static void batadv_mcast_mla_list_free(struct hlist_head *mcast_list)
+{
+ struct batadv_hw_addr *mcast_entry;
+ struct hlist_node *tmp;
+
+ hlist_for_each_entry_safe(mcast_entry, tmp, mcast_list, list) {
+ hlist_del(&mcast_entry->list);
+ kfree(mcast_entry);
+ }
+}
+
+/**
+ * batadv_mcast_mla_tt_retract - clean up multicast listener announcements
+ * @bat_priv: the bat priv with all the soft interface information
+ * @mcast_list: a list of addresses which should _not_ be removed
+ *
+ * Retracts the announcement of any multicast listener from the
+ * translation table except the ones listed in the given mcast_list.
+ *
+ * If mcast_list is NULL then all are retracted.
+ */
+static void batadv_mcast_mla_tt_retract(struct batadv_priv *bat_priv,
+ struct hlist_head *mcast_list)
+{
+ struct batadv_hw_addr *mcast_entry;
+ struct hlist_node *tmp;
+
+ hlist_for_each_entry_safe(mcast_entry, tmp, &bat_priv->mcast.mla_list,
+ list) {
+ if (mcast_list &&
+ batadv_mcast_mla_is_duplicate(mcast_entry->addr,
+ mcast_list))
+ continue;
+
+ batadv_tt_local_remove(bat_priv, mcast_entry->addr,
+ BATADV_NO_FLAGS,
+ "mcast TT outdated", false);
+
+ hlist_del(&mcast_entry->list);
+ kfree(mcast_entry);
+ }
+}
+
+/**
+ * batadv_mcast_mla_tt_add - add multicast listener announcements
+ * @bat_priv: the bat priv with all the soft interface information
+ * @mcast_list: a list of addresses which are going to get added
+ *
+ * Adds multicast listener announcements from the given mcast_list to the
+ * translation table if they have not been added yet.
+ */
+static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv,
+ struct hlist_head *mcast_list)
+{
+ struct batadv_hw_addr *mcast_entry;
+ struct hlist_node *tmp;
+
+ if (!mcast_list)
+ return;
+
+ hlist_for_each_entry_safe(mcast_entry, tmp, mcast_list, list) {
+ if (batadv_mcast_mla_is_duplicate(mcast_entry->addr,
+ &bat_priv->mcast.mla_list))
+ continue;
+
+ if (!batadv_tt_local_add(bat_priv->soft_iface,
+ mcast_entry->addr, BATADV_NO_FLAGS,
+ BATADV_NULL_IFINDEX, BATADV_NO_MARK))
+ continue;
+
+ hlist_del(&mcast_entry->list);
+ hlist_add_head(&mcast_entry->list, &bat_priv->mcast.mla_list);
+ }
+}
+
+/**
+ * batadv_mcast_has_bridge - check whether the soft-iface is bridged
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Checks whether there is a bridge on top of our soft interface. Returns
+ * true if so, false otherwise.
+ */
+static bool batadv_mcast_has_bridge(struct batadv_priv *bat_priv)
+{
+ struct net_device *upper = bat_priv->soft_iface;
+
+ rcu_read_lock();
+ do {
+ upper = netdev_master_upper_dev_get_rcu(upper);
+ } while (upper && !(upper->priv_flags & IFF_EBRIDGE));
+ rcu_read_unlock();
+
+ return upper;
+}
+
+/**
+ * batadv_mcast_mla_tvlv_update - update multicast tvlv
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Updates the own multicast tvlv with our current multicast related settings,
+ * capabilities and inabilities.
+ *
+ * Returns true if the tvlv container is registered afterwards. Otherwise
+ * returns false.
+ */
+static bool batadv_mcast_mla_tvlv_update(struct batadv_priv *bat_priv)
+{
+ struct batadv_tvlv_mcast_data mcast_data;
+
+ mcast_data.flags = BATADV_NO_FLAGS;
+ memset(mcast_data.reserved, 0, sizeof(mcast_data.reserved));
+
+ /* Avoid attaching MLAs, if there is a bridge on top of our soft
+ * interface, we don't support that yet (TODO)
+ */
+ if (batadv_mcast_has_bridge(bat_priv)) {
+ if (bat_priv->mcast.enabled) {
+ batadv_tvlv_container_unregister(bat_priv,
+ BATADV_TVLV_MCAST, 1);
+ bat_priv->mcast.enabled = false;
+ }
+
+ return false;
+ }
+
+ if (!bat_priv->mcast.enabled ||
+ mcast_data.flags != bat_priv->mcast.flags) {
+ batadv_tvlv_container_register(bat_priv, BATADV_TVLV_MCAST, 1,
+ &mcast_data, sizeof(mcast_data));
+ bat_priv->mcast.flags = mcast_data.flags;
+ bat_priv->mcast.enabled = true;
+ }
+
+ return true;
+}
+
+/**
+ * batadv_mcast_mla_update - update the own MLAs
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Updates the own multicast listener announcements in the translation
+ * table as well as the own, announced multicast tvlv container.
+ */
+void batadv_mcast_mla_update(struct batadv_priv *bat_priv)
+{
+ struct net_device *soft_iface = bat_priv->soft_iface;
+ struct hlist_head mcast_list = HLIST_HEAD_INIT;
+ int ret;
+
+ if (!batadv_mcast_mla_tvlv_update(bat_priv))
+ goto update;
+
+ ret = batadv_mcast_mla_softif_get(soft_iface, &mcast_list);
+ if (ret < 0)
+ goto out;
+
+update:
+ batadv_mcast_mla_tt_retract(bat_priv, &mcast_list);
+ batadv_mcast_mla_tt_add(bat_priv, &mcast_list);
+
+out:
+ batadv_mcast_mla_list_free(&mcast_list);
+}
+
+/**
+ * batadv_mcast_forw_mode_check_ipv4 - check for optimized forwarding potential
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the IPv4 packet to check
+ * @is_unsnoopable: stores whether the destination is snoopable
+ *
+ * Checks whether the given IPv4 packet has the potential to be forwarded with a
+ * mode more optimal than classic flooding.
+ *
+ * If so then returns 0. Otherwise -EINVAL is returned or -ENOMEM in case of
+ * memory allocation failure.
+ */
+static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv,
+ struct sk_buff *skb,
+ bool *is_unsnoopable)
+{
+ struct iphdr *iphdr;
+
+ /* We might fail due to out-of-memory -> drop it */
+ if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*iphdr)))
+ return -ENOMEM;
+
+ iphdr = ip_hdr(skb);
+
+ /* TODO: Implement Multicast Router Discovery (RFC4286),
+ * then allow scope > link local, too
+ */
+ if (!ipv4_is_local_multicast(iphdr->daddr))
+ return -EINVAL;
+
+ /* link-local multicast listeners behind a bridge are
+ * not snoopable (see RFC4541, section 2.1.2.2)
+ */
+ *is_unsnoopable = true;
+
+ return 0;
+}
+
+/**
+ * batadv_mcast_forw_mode_check_ipv6 - check for optimized forwarding potential
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the IPv6 packet to check
+ * @is_unsnoopable: stores whether the destination is snoopable
+ *
+ * Checks whether the given IPv6 packet has the potential to be forwarded with a
+ * mode more optimal than classic flooding.
+ *
+ * If so then returns 0. Otherwise -EINVAL is returned or -ENOMEM if we are out
+ * of memory.
+ */
+static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
+ struct sk_buff *skb,
+ bool *is_unsnoopable)
+{
+ struct ipv6hdr *ip6hdr;
+
+ /* We might fail due to out-of-memory -> drop it */
+ if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*ip6hdr)))
+ return -ENOMEM;
+
+ ip6hdr = ipv6_hdr(skb);
+
+ /* TODO: Implement Multicast Router Discovery (RFC4286),
+ * then allow scope > link local, too
+ */
+ if (IPV6_ADDR_MC_SCOPE(&ip6hdr->daddr) != IPV6_ADDR_SCOPE_LINKLOCAL)
+ return -EINVAL;
+
+ /* link-local-all-nodes multicast listeners behind a bridge are
+ * not snoopable (see RFC4541, section 3, paragraph 3)
+ */
+ if (ipv6_addr_is_ll_all_nodes(&ip6hdr->daddr))
+ *is_unsnoopable = true;
+
+ return 0;
+}
+
+/**
+ * batadv_mcast_forw_mode_check - check for optimized forwarding potential
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast frame to check
+ * @is_unsnoopable: stores whether the destination is snoopable
+ *
+ * Checks whether the given multicast ethernet frame has the potential to be
+ * forwarded with a mode more optimal than classic flooding.
+ *
+ * If so then returns 0. Otherwise -EINVAL is returned or -ENOMEM if we are out
+ * of memory.
+ */
+static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv,
+ struct sk_buff *skb,
+ bool *is_unsnoopable)
+{
+ struct ethhdr *ethhdr = eth_hdr(skb);
+
+ if (!atomic_read(&bat_priv->multicast_mode))
+ return -EINVAL;
+
+ if (atomic_read(&bat_priv->mcast.num_disabled))
+ return -EINVAL;
+
+ switch (ntohs(ethhdr->h_proto)) {
+ case ETH_P_IP:
+ return batadv_mcast_forw_mode_check_ipv4(bat_priv, skb,
+ is_unsnoopable);
+ case ETH_P_IPV6:
+ return batadv_mcast_forw_mode_check_ipv6(bat_priv, skb,
+ is_unsnoopable);
+ default:
+ return -EINVAL;
+ }
+}
+
+/**
+ * batadv_mcast_want_all_ip_count - count nodes with unspecific mcast interest
+ * @bat_priv: the bat priv with all the soft interface information
+ * @ethhdr: ethernet header of a packet
+ *
+ * Returns the number of nodes which want all IPv4 multicast traffic if the
+ * given ethhdr is from an IPv4 packet or the number of nodes which want all
+ * IPv6 traffic if it matches an IPv6 packet.
+ */
+static int batadv_mcast_forw_want_all_ip_count(struct batadv_priv *bat_priv,
+ struct ethhdr *ethhdr)
+{
+ switch (ntohs(ethhdr->h_proto)) {
+ case ETH_P_IP:
+ return atomic_read(&bat_priv->mcast.num_want_all_ipv4);
+ case ETH_P_IPV6:
+ return atomic_read(&bat_priv->mcast.num_want_all_ipv6);
+ default:
+ /* we shouldn't be here... */
+ return 0;
+ }
+}
+
+/**
+ * batadv_mcast_forw_tt_node_get - get a multicast tt node
+ * @bat_priv: the bat priv with all the soft interface information
+ * @ethhdr: the ether header containing the multicast destination
+ *
+ * Returns an orig_node matching the multicast address provided by ethhdr
+ * via a translation table lookup. This increases the returned nodes refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_tt_node_get(struct batadv_priv *bat_priv,
+ struct ethhdr *ethhdr)
+{
+ return batadv_transtable_search(bat_priv, ethhdr->h_source,
+ ethhdr->h_dest, BATADV_NO_FLAGS);
+}
+
+/**
+ * batadv_mcast_want_forw_ipv4_node_get - get a node with an ipv4 flag
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 flag set and
+ * increases its refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_ipv4_node_get(struct batadv_priv *bat_priv)
+{
+ struct batadv_orig_node *tmp_orig_node, *orig_node = NULL;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(tmp_orig_node,
+ &bat_priv->mcast.want_all_ipv4_list,
+ mcast_want_all_ipv4_node) {
+ if (!atomic_inc_not_zero(&orig_node->refcount))
+ continue;
+
+ orig_node = tmp_orig_node;
+ break;
+ }
+ rcu_read_unlock();
+
+ return orig_node;
+}
+
+/**
+ * batadv_mcast_want_forw_ipv6_node_get - get a node with an ipv6 flag
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_IPV6 flag set
+ * and increases its refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_ipv6_node_get(struct batadv_priv *bat_priv)
+{
+ struct batadv_orig_node *tmp_orig_node, *orig_node = NULL;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(tmp_orig_node,
+ &bat_priv->mcast.want_all_ipv6_list,
+ mcast_want_all_ipv6_node) {
+ if (!atomic_inc_not_zero(&orig_node->refcount))
+ continue;
+
+ orig_node = tmp_orig_node;
+ break;
+ }
+ rcu_read_unlock();
+
+ return orig_node;
+}
+
+/**
+ * batadv_mcast_want_forw_ip_node_get - get a node with an ipv4/ipv6 flag
+ * @bat_priv: the bat priv with all the soft interface information
+ * @ethhdr: an ethernet header to determine the protocol family from
+ *
+ * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 or
+ * BATADV_MCAST_WANT_ALL_IPV6 flag, depending on the provided ethhdr, set and
+ * increases its refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_ip_node_get(struct batadv_priv *bat_priv,
+ struct ethhdr *ethhdr)
+{
+ switch (ntohs(ethhdr->h_proto)) {
+ case ETH_P_IP:
+ return batadv_mcast_forw_ipv4_node_get(bat_priv);
+ case ETH_P_IPV6:
+ return batadv_mcast_forw_ipv6_node_get(bat_priv);
+ default:
+ /* we shouldn't be here... */
+ return NULL;
+ }
+}
+
+/**
+ * batadv_mcast_want_forw_unsnoop_node_get - get a node with an unsnoopable flag
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag
+ * set and increases its refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_unsnoop_node_get(struct batadv_priv *bat_priv)
+{
+ struct batadv_orig_node *tmp_orig_node, *orig_node = NULL;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(tmp_orig_node,
+ &bat_priv->mcast.want_all_unsnoopables_list,
+ mcast_want_all_unsnoopables_node) {
+ if (!atomic_inc_not_zero(&orig_node->refcount))
+ continue;
+
+ orig_node = tmp_orig_node;
+ break;
+ }
+ rcu_read_unlock();
+
+ return orig_node;
+}
+
+/**
+ * batadv_mcast_forw_mode - check on how to forward a multicast packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: The multicast packet to check
+ * @orig: an originator to be set to forward the skb to
+ *
+ * Returns the forwarding mode as enum batadv_forw_mode and in case of
+ * BATADV_FORW_SINGLE set the orig to the single originator the skb
+ * should be forwarded to.
+ */
+enum batadv_forw_mode
+batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
+ struct batadv_orig_node **orig)
+{
+ int ret, tt_count, ip_count, unsnoop_count, total_count;
+ bool is_unsnoopable = false;
+ struct ethhdr *ethhdr;
+
+ ret = batadv_mcast_forw_mode_check(bat_priv, skb, &is_unsnoopable);
+ if (ret == -ENOMEM)
+ return BATADV_FORW_NONE;
+ else if (ret < 0)
+ return BATADV_FORW_ALL;
+
+ ethhdr = eth_hdr(skb);
+
+ tt_count = batadv_tt_global_hash_count(bat_priv, ethhdr->h_dest,
+ BATADV_NO_FLAGS);
+ ip_count = batadv_mcast_forw_want_all_ip_count(bat_priv, ethhdr);
+ unsnoop_count = !is_unsnoopable ? 0 :
+ atomic_read(&bat_priv->mcast.num_want_all_unsnoopables);
+
+ total_count = tt_count + ip_count + unsnoop_count;
+
+ switch (total_count) {
+ case 1:
+ if (tt_count)
+ *orig = batadv_mcast_forw_tt_node_get(bat_priv, ethhdr);
+ else if (ip_count)
+ *orig = batadv_mcast_forw_ip_node_get(bat_priv, ethhdr);
+ else if (unsnoop_count)
+ *orig = batadv_mcast_forw_unsnoop_node_get(bat_priv);
+
+ if (*orig)
+ return BATADV_FORW_SINGLE;
+
+ /* fall through */
+ case 0:
+ return BATADV_FORW_NONE;
+ default:
+ return BATADV_FORW_ALL;
+ }
+}
+
+/**
+ * batadv_mcast_want_unsnoop_update - update unsnoop counter and list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig: the orig_node which multicast state might have changed of
+ * @mcast_flags: flags indicating the new multicast state
+ *
+ * If the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag of this originator,
+ * orig, has toggled then this method updates counter and list accordingly.
+ */
+static void batadv_mcast_want_unsnoop_update(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig,
+ uint8_t mcast_flags)
+{
+ /* switched from flag unset to set */
+ if (mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
+ !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES)) {
+ atomic_inc(&bat_priv->mcast.num_want_all_unsnoopables);
+
+ spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+ hlist_add_head_rcu(&orig->mcast_want_all_unsnoopables_node,
+ &bat_priv->mcast.want_all_unsnoopables_list);
+ spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+ /* switched from flag set to unset */
+ } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) &&
+ orig->mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) {
+ atomic_dec(&bat_priv->mcast.num_want_all_unsnoopables);
+
+ spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+ hlist_del_rcu(&orig->mcast_want_all_unsnoopables_node);
+ spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+ }
+}
+
+/**
+ * batadv_mcast_want_ipv4_update - update want-all-ipv4 counter and list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig: the orig_node which multicast state might have changed of
+ * @mcast_flags: flags indicating the new multicast state
+ *
+ * If the BATADV_MCAST_WANT_ALL_IPV4 flag of this originator, orig, has
+ * toggled then this method updates counter and list accordingly.
+ */
+static void batadv_mcast_want_ipv4_update(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig,
+ uint8_t mcast_flags)
+{
+ /* switched from flag unset to set */
+ if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV4 &&
+ !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV4)) {
+ atomic_inc(&bat_priv->mcast.num_want_all_ipv4);
+
+ spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+ hlist_add_head_rcu(&orig->mcast_want_all_ipv4_node,
+ &bat_priv->mcast.want_all_ipv4_list);
+ spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+ /* switched from flag set to unset */
+ } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) &&
+ orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) {
+ atomic_dec(&bat_priv->mcast.num_want_all_ipv4);
+
+ spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+ hlist_del_rcu(&orig->mcast_want_all_ipv4_node);
+ spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+ }
+}
+
+/**
+ * batadv_mcast_want_ipv6_update - update want-all-ipv6 counter and list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig: the orig_node which multicast state might have changed of
+ * @mcast_flags: flags indicating the new multicast state
+ *
+ * If the BATADV_MCAST_WANT_ALL_IPV6 flag of this originator, orig, has
+ * toggled then this method updates counter and list accordingly.
+ */
+static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig,
+ uint8_t mcast_flags)
+{
+ /* switched from flag unset to set */
+ if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV6 &&
+ !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV6)) {
+ atomic_inc(&bat_priv->mcast.num_want_all_ipv6);
+
+ spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+ hlist_add_head_rcu(&orig->mcast_want_all_ipv6_node,
+ &bat_priv->mcast.want_all_ipv6_list);
+ spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+ /* switched from flag set to unset */
+ } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) &&
+ orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) {
+ atomic_dec(&bat_priv->mcast.num_want_all_ipv6);
+
+ spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+ hlist_del_rcu(&orig->mcast_want_all_ipv6_node);
+ spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+ }
+}
+
+/**
+ * batadv_mcast_tvlv_ogm_handler_v1 - process incoming multicast tvlv container
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig: the orig_node of the ogm
+ * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags)
+ * @tvlv_value: tvlv buffer containing the multicast data
+ * @tvlv_value_len: tvlv buffer length
+ */
+static void batadv_mcast_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig,
+ uint8_t flags,
+ void *tvlv_value,
+ uint16_t tvlv_value_len)
+{
+ bool orig_mcast_enabled = !(flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
+ uint8_t mcast_flags = BATADV_NO_FLAGS;
+ bool orig_initialized;
+
+ orig_initialized = orig->capa_initialized & BATADV_ORIG_CAPA_HAS_MCAST;
+
+ /* If mcast support is turned on decrease the disabled mcast node
+ * counter only if we had increased it for this node before. If this
+ * is a completely new orig_node no need to decrease the counter.
+ */
+ if (orig_mcast_enabled &&
+ !(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST)) {
+ if (orig_initialized)
+ atomic_dec(&bat_priv->mcast.num_disabled);
+ orig->capabilities |= BATADV_ORIG_CAPA_HAS_MCAST;
+ /* If mcast support is being switched off increase the disabled
+ * mcast node counter.
+ */
+ } else if (!orig_mcast_enabled &&
+ orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST) {
+ atomic_inc(&bat_priv->mcast.num_disabled);
+ orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_MCAST;
+ }
+
+ orig->capa_initialized |= BATADV_ORIG_CAPA_HAS_MCAST;
+
+ if (orig_mcast_enabled && tvlv_value &&
+ (tvlv_value_len >= sizeof(mcast_flags)))
+ mcast_flags = *(uint8_t *)tvlv_value;
+
+ batadv_mcast_want_unsnoop_update(bat_priv, orig, mcast_flags);
+ batadv_mcast_want_ipv4_update(bat_priv, orig, mcast_flags);
+ batadv_mcast_want_ipv6_update(bat_priv, orig, mcast_flags);
+
+ orig->mcast_flags = mcast_flags;
+}
+
+/**
+ * batadv_mcast_init - initialize the multicast optimizations structures
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+void batadv_mcast_init(struct batadv_priv *bat_priv)
+{
+ batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler_v1,
+ NULL, BATADV_TVLV_MCAST, 1,
+ BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
+}
+
+/**
+ * batadv_mcast_free - free the multicast optimizations structures
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+void batadv_mcast_free(struct batadv_priv *bat_priv)
+{
+ batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 1);
+ batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 1);
+
+ batadv_mcast_mla_tt_retract(bat_priv, NULL);
+}
+
+/**
+ * batadv_mcast_purge_orig - reset originator global mcast state modifications
+ * @orig: the originator which is going to get purged
+ */
+void batadv_mcast_purge_orig(struct batadv_orig_node *orig)
+{
+ struct batadv_priv *bat_priv = orig->bat_priv;
+
+ if (!(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST))
+ atomic_dec(&bat_priv->mcast.num_disabled);
+
+ batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS);
+ batadv_mcast_want_ipv4_update(bat_priv, orig, BATADV_NO_FLAGS);
+ batadv_mcast_want_ipv6_update(bat_priv, orig, BATADV_NO_FLAGS);
+}
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
new file mode 100644
index 0000000..73b5d45
--- /dev/null
+++ b/net/batman-adv/multicast.h
@@ -0,0 +1,80 @@
+/* Copyright (C) 2014 B.A.T.M.A.N. contributors:
+ *
+ * Linus Lüssing
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _NET_BATMAN_ADV_MULTICAST_H_
+#define _NET_BATMAN_ADV_MULTICAST_H_
+
+/**
+ * batadv_forw_mode - the way a packet should be forwarded as
+ * @BATADV_FORW_ALL: forward the packet to all nodes (currently via classic
+ * flooding)
+ * @BATADV_FORW_SINGLE: forward the packet to a single node (currently via the
+ * BATMAN unicast routing protocol)
+ * @BATADV_FORW_NONE: don't forward, drop it
+ */
+enum batadv_forw_mode {
+ BATADV_FORW_ALL,
+ BATADV_FORW_SINGLE,
+ BATADV_FORW_NONE,
+};
+
+#ifdef CONFIG_BATMAN_ADV_MCAST
+
+void batadv_mcast_mla_update(struct batadv_priv *bat_priv);
+
+enum batadv_forw_mode
+batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
+ struct batadv_orig_node **mcast_single_orig);
+
+void batadv_mcast_init(struct batadv_priv *bat_priv);
+
+void batadv_mcast_free(struct batadv_priv *bat_priv);
+
+void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node);
+
+#else
+
+static inline void batadv_mcast_mla_update(struct batadv_priv *bat_priv)
+{
+ return;
+}
+
+static inline enum batadv_forw_mode
+batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
+ struct batadv_orig_node **mcast_single_orig)
+{
+ return BATADV_FORW_ALL;
+}
+
+static inline int batadv_mcast_init(struct batadv_priv *bat_priv)
+{
+ return 0;
+}
+
+static inline void batadv_mcast_free(struct batadv_priv *bat_priv)
+{
+ return;
+}
+
+static inline void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node)
+{
+ return;
+}
+
+#endif /* CONFIG_BATMAN_ADV_MCAST */
+
+#endif /* _NET_BATMAN_ADV_MULTICAST_H_ */
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index f1b604d..a9546fe 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -819,7 +819,7 @@
/* Initialize nc_node */
INIT_LIST_HEAD(&nc_node->list);
- memcpy(nc_node->addr, orig_node->orig, ETH_ALEN);
+ ether_addr_copy(nc_node->addr, orig_node->orig);
nc_node->orig_node = orig_neigh_node;
atomic_set(&nc_node->refcount, 2);
@@ -941,8 +941,8 @@
spin_lock_init(&nc_path->packet_list_lock);
atomic_set(&nc_path->refcount, 2);
nc_path->last_valid = jiffies;
- memcpy(nc_path->next_hop, dst, ETH_ALEN);
- memcpy(nc_path->prev_hop, src, ETH_ALEN);
+ ether_addr_copy(nc_path->next_hop, dst);
+ ether_addr_copy(nc_path->prev_hop, src);
batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_path %pM -> %pM\n",
nc_path->prev_hop,
@@ -1114,15 +1114,15 @@
coded_packet->ttl = packet1->ttl;
/* Info about first unicast packet */
- memcpy(coded_packet->first_source, first_source, ETH_ALEN);
- memcpy(coded_packet->first_orig_dest, packet1->dest, ETH_ALEN);
+ ether_addr_copy(coded_packet->first_source, first_source);
+ ether_addr_copy(coded_packet->first_orig_dest, packet1->dest);
coded_packet->first_crc = packet_id1;
coded_packet->first_ttvn = packet1->ttvn;
/* Info about second unicast packet */
- memcpy(coded_packet->second_dest, second_dest, ETH_ALEN);
- memcpy(coded_packet->second_source, second_source, ETH_ALEN);
- memcpy(coded_packet->second_orig_dest, packet2->dest, ETH_ALEN);
+ ether_addr_copy(coded_packet->second_dest, second_dest);
+ ether_addr_copy(coded_packet->second_source, second_source);
+ ether_addr_copy(coded_packet->second_orig_dest, packet2->dest);
coded_packet->second_crc = packet_id2;
coded_packet->second_ttl = packet2->ttl;
coded_packet->second_ttvn = packet2->ttvn;
@@ -1349,8 +1349,8 @@
/* Set the mac header as if we actually sent the packet uncoded */
ethhdr = eth_hdr(skb);
- memcpy(ethhdr->h_source, ethhdr->h_dest, ETH_ALEN);
- memcpy(ethhdr->h_dest, eth_dst_new, ETH_ALEN);
+ ether_addr_copy(ethhdr->h_source, ethhdr->h_dest);
+ ether_addr_copy(ethhdr->h_dest, eth_dst_new);
/* Set data pointer to MAC header to mimic packets from our tx path */
skb_push(skb, ETH_HLEN);
@@ -1636,7 +1636,7 @@
/* Reconstruct original mac header */
ethhdr = eth_hdr(skb);
- memcpy(ethhdr, ðhdr_tmp, sizeof(*ethhdr));
+ *ethhdr = ethhdr_tmp;
/* Select the correct unicast header information based on the location
* of our mac address in the coded_packet header
@@ -1646,7 +1646,7 @@
* so the Ethernet address must be copied to h_dest and
* pkt_type changed from PACKET_OTHERHOST to PACKET_HOST
*/
- memcpy(ethhdr->h_dest, coded_packet_tmp.second_dest, ETH_ALEN);
+ ether_addr_copy(ethhdr->h_dest, coded_packet_tmp.second_dest);
skb->pkt_type = PACKET_HOST;
orig_dest = coded_packet_tmp.second_orig_dest;
@@ -1682,7 +1682,7 @@
unicast_packet->packet_type = BATADV_UNICAST;
unicast_packet->version = BATADV_COMPAT_VERSION;
unicast_packet->ttl = ttl;
- memcpy(unicast_packet->dest, orig_dest, ETH_ALEN);
+ ether_addr_copy(unicast_packet->dest, orig_dest);
unicast_packet->ttvn = ttvn;
batadv_nc_packet_free(nc_packet);
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 6df12a2..ffd9dfb 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -27,6 +27,7 @@
#include "bridge_loop_avoidance.h"
#include "network-coding.h"
#include "fragmentation.h"
+#include "multicast.h"
/* hash class keys */
static struct lock_class_key batadv_orig_hash_lock_class_key;
@@ -446,7 +447,7 @@
INIT_HLIST_HEAD(&neigh_node->ifinfo_list);
spin_lock_init(&neigh_node->ifinfo_lock);
- memcpy(neigh_node->addr, neigh_addr, ETH_ALEN);
+ ether_addr_copy(neigh_node->addr, neigh_addr);
neigh_node->if_incoming = hard_iface;
neigh_node->orig_node = orig_node;
@@ -458,6 +459,42 @@
}
/**
+ * batadv_neigh_node_get - retrieve a neighbour from the list
+ * @orig_node: originator which the neighbour belongs to
+ * @hard_iface: the interface where this neighbour is connected to
+ * @addr: the address of the neighbour
+ *
+ * Looks for and possibly returns a neighbour belonging to this originator list
+ * which is connected through the provided hard interface.
+ * Returns NULL if the neighbour is not found.
+ */
+struct batadv_neigh_node *
+batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
+ const struct batadv_hard_iface *hard_iface,
+ const uint8_t *addr)
+{
+ struct batadv_neigh_node *tmp_neigh_node, *res = NULL;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) {
+ if (!batadv_compare_eth(tmp_neigh_node->addr, addr))
+ continue;
+
+ if (tmp_neigh_node->if_incoming != hard_iface)
+ continue;
+
+ if (!atomic_inc_not_zero(&tmp_neigh_node->refcount))
+ continue;
+
+ res = tmp_neigh_node;
+ break;
+ }
+ rcu_read_unlock();
+
+ return res;
+}
+
+/**
* batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object
* @rcu: rcu pointer of the orig_ifinfo object
*/
@@ -521,6 +558,8 @@
}
spin_unlock_bh(&orig_node->neigh_list_lock);
+ batadv_mcast_purge_orig(orig_node);
+
/* Free nc_nodes */
batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL);
@@ -628,15 +667,17 @@
/* extra reference for return */
atomic_set(&orig_node->refcount, 2);
- orig_node->tt_initialised = false;
orig_node->bat_priv = bat_priv;
- memcpy(orig_node->orig, addr, ETH_ALEN);
+ ether_addr_copy(orig_node->orig, addr);
batadv_dat_init_orig_node_addr(orig_node);
atomic_set(&orig_node->last_ttvn, 0);
orig_node->tt_buff = NULL;
orig_node->tt_buff_len = 0;
reset_time = jiffies - 1 - msecs_to_jiffies(BATADV_RESET_PROTECTION_MS);
orig_node->bcast_seqno_reset = reset_time;
+#ifdef CONFIG_BATMAN_ADV_MCAST
+ orig_node->mcast_flags = BATADV_NO_FLAGS;
+#endif
/* create a vlan object for the "untagged" LAN */
vlan = batadv_orig_node_vlan_new(orig_node, BATADV_NO_FLAGS);
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index 37be290..db3a9ed 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -29,6 +29,10 @@
struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
const uint8_t *addr);
struct batadv_neigh_node *
+batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
+ const struct batadv_hard_iface *hard_iface,
+ const uint8_t *addr);
+struct batadv_neigh_node *
batadv_neigh_node_new(struct batadv_hard_iface *hard_iface,
const uint8_t *neigh_addr,
struct batadv_orig_node *orig_node);
diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index 0a381d1..34e096d 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -89,6 +89,19 @@
BATADV_PARAMETER_PROBLEM = 12,
};
+/**
+ * enum batadv_mcast_flags - flags for multicast capabilities and settings
+ * @BATADV_MCAST_WANT_ALL_UNSNOOPABLES: we want all packets destined for
+ * 224.0.0.0/24 or ff02::1
+ * @BATADV_MCAST_WANT_ALL_IPV4: we want all IPv4 multicast packets
+ * @BATADV_MCAST_WANT_ALL_IPV6: we want all IPv6 multicast packets
+ */
+enum batadv_mcast_flags {
+ BATADV_MCAST_WANT_ALL_UNSNOOPABLES = BIT(0),
+ BATADV_MCAST_WANT_ALL_IPV4 = BIT(1),
+ BATADV_MCAST_WANT_ALL_IPV6 = BIT(2),
+};
+
/* tt data subtypes */
#define BATADV_TT_DATA_TYPE_MASK 0x0F
@@ -106,10 +119,30 @@
BATADV_TT_FULL_TABLE = BIT(4),
};
-/* BATADV_TT_CLIENT flags.
- * Flags from BIT(0) to BIT(7) are sent on the wire, while flags from BIT(8) to
- * BIT(15) are used for local computation only.
- * Flags from BIT(4) to BIT(7) are kept in sync with the rest of the network.
+/**
+ * enum batadv_tt_client_flags - TT client specific flags
+ * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table
+ * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and the new
+ * update telling its new real location has not been received/sent yet
+ * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi interface.
+ * This information is used by the "AP Isolation" feature
+ * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This
+ * information is used by the Extended Isolation feature
+ * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from the table
+ * @BATADV_TT_CLIENT_NEW: this client has been added to the local table but has
+ * not been announced yet
+ * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it is kept
+ * in the table for one more originator interval for consistency purposes
+ * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be part of
+ * the network but no nnode has already announced it
+ *
+ * Bits from 0 to 7 are called _remote flags_ because they are sent on the wire.
+ * Bits from 8 to 15 are called _local flags_ because they are used for local
+ * computations only.
+ *
+ * Bits from 4 to 7 - a subset of remote flags - are ensured to be in sync with
+ * the other nodes in the network. To achieve this goal these flags are included
+ * in the TT CRC computation.
*/
enum batadv_tt_client_flags {
BATADV_TT_CLIENT_DEL = BIT(0),
@@ -145,6 +178,7 @@
* @BATADV_TVLV_NC: network coding tvlv
* @BATADV_TVLV_TT: translation table tvlv
* @BATADV_TVLV_ROAM: roaming advertisement tvlv
+ * @BATADV_TVLV_MCAST: multicast capability tvlv
*/
enum batadv_tvlv_type {
BATADV_TVLV_GW = 0x01,
@@ -152,6 +186,7 @@
BATADV_TVLV_NC = 0x03,
BATADV_TVLV_TT = 0x04,
BATADV_TVLV_ROAM = 0x05,
+ BATADV_TVLV_MCAST = 0x06,
};
#pragma pack(2)
@@ -504,4 +539,14 @@
__be16 vid;
};
+/**
+ * struct batadv_tvlv_mcast_data - payload of a multicast tvlv
+ * @flags: multicast flags announced by the orig node
+ * @reserved: reserved field
+ */
+struct batadv_tvlv_mcast_data {
+ uint8_t flags;
+ uint8_t reserved[3];
+};
+
#endif /* _NET_BATMAN_ADV_PACKET_H_ */
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 1ed9f7c..3514153 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -222,8 +222,8 @@
icmph = (struct batadv_icmp_header *)skb->data;
- memcpy(icmph->dst, icmph->orig, ETH_ALEN);
- memcpy(icmph->orig, primary_if->net_dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(icmph->dst, icmph->orig);
+ ether_addr_copy(icmph->orig, primary_if->net_dev->dev_addr);
icmph->msg_type = BATADV_ECHO_REPLY;
icmph->ttl = BATADV_TTL;
@@ -276,9 +276,8 @@
icmp_packet = (struct batadv_icmp_packet *)skb->data;
- memcpy(icmp_packet->dst, icmp_packet->orig, ETH_ALEN);
- memcpy(icmp_packet->orig, primary_if->net_dev->dev_addr,
- ETH_ALEN);
+ ether_addr_copy(icmp_packet->dst, icmp_packet->orig);
+ ether_addr_copy(icmp_packet->orig, primary_if->net_dev->dev_addr);
icmp_packet->msg_type = BATADV_TTL_EXCEEDED;
icmp_packet->ttl = BATADV_TTL;
@@ -341,8 +340,8 @@
if (icmp_packet_rr->rr_cur >= BATADV_RR_LEN)
goto out;
- memcpy(&(icmp_packet_rr->rr[icmp_packet_rr->rr_cur]),
- ethhdr->h_dest, ETH_ALEN);
+ ether_addr_copy(icmp_packet_rr->rr[icmp_packet_rr->rr_cur],
+ ethhdr->h_dest);
icmp_packet_rr->rr_cur++;
}
@@ -664,7 +663,7 @@
}
/* update the packet header */
- memcpy(unicast_packet->dest, orig_addr, ETH_ALEN);
+ ether_addr_copy(unicast_packet->dest, orig_addr);
unicast_packet->ttvn = orig_ttvn;
ret = true;
@@ -688,7 +687,7 @@
int is_old_ttvn;
/* check if there is enough data before accessing it */
- if (pskb_may_pull(skb, hdr_len + ETH_HLEN) < 0)
+ if (!pskb_may_pull(skb, hdr_len + ETH_HLEN))
return 0;
/* create a copy of the skb (in case of for re-routing) to modify it. */
@@ -774,7 +773,7 @@
if (!primary_if)
return 0;
- memcpy(unicast_packet->dest, primary_if->net_dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(unicast_packet->dest, primary_if->net_dev->dev_addr);
batadv_hardif_free_ref(primary_if);
@@ -918,6 +917,8 @@
if (ret != NET_RX_SUCCESS)
ret = batadv_route_unicast_packet(skb, recv_if);
+ else
+ consume_skb(skb);
return ret;
}
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 579f5f0..3d64ed2 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -27,6 +27,7 @@
#include "originator.h"
#include "network-coding.h"
#include "fragmentation.h"
+#include "multicast.h"
static void batadv_send_outstanding_bcast_packet(struct work_struct *work);
@@ -59,8 +60,8 @@
skb_reset_mac_header(skb);
ethhdr = eth_hdr(skb);
- memcpy(ethhdr->h_source, hard_iface->net_dev->dev_addr, ETH_ALEN);
- memcpy(ethhdr->h_dest, dst_addr, ETH_ALEN);
+ ether_addr_copy(ethhdr->h_source, hard_iface->net_dev->dev_addr);
+ ether_addr_copy(ethhdr->h_dest, dst_addr);
ethhdr->h_proto = htons(ETH_P_BATMAN);
skb_set_network_header(skb, ETH_HLEN);
@@ -165,7 +166,7 @@
/* set unicast ttl */
unicast_packet->ttl = BATADV_TTL;
/* copy the destination for faster routing */
- memcpy(unicast_packet->dest, orig_node->orig, ETH_ALEN);
+ ether_addr_copy(unicast_packet->dest, orig_node->orig);
/* set the destination tt version number */
unicast_packet->ttvn = ttvn;
@@ -220,7 +221,7 @@
uc_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
uc_4addr_packet->u.packet_type = BATADV_UNICAST_4ADDR;
- memcpy(uc_4addr_packet->src, primary_if->net_dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(uc_4addr_packet->src, primary_if->net_dev->dev_addr);
uc_4addr_packet->subtype = packet_subtype;
uc_4addr_packet->reserved = 0;
@@ -248,13 +249,13 @@
*
* Returns NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
*/
-static int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
- struct sk_buff *skb, int packet_type,
- int packet_subtype,
- struct batadv_orig_node *orig_node,
- unsigned short vid)
+int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
+ struct sk_buff *skb, int packet_type,
+ int packet_subtype,
+ struct batadv_orig_node *orig_node,
+ unsigned short vid)
{
- struct ethhdr *ethhdr = (struct ethhdr *)skb->data;
+ struct ethhdr *ethhdr;
struct batadv_unicast_packet *unicast_packet;
int ret = NET_XMIT_DROP;
@@ -279,6 +280,10 @@
goto out;
}
+ /* skb->data might have been reallocated by
+ * batadv_send_skb_prepare_unicast{,_4addr}()
+ */
+ ethhdr = eth_hdr(skb);
unicast_packet = (struct batadv_unicast_packet *)skb->data;
/* inform the destination node that we are still missing a correct route
@@ -307,6 +312,7 @@
* @packet_type: the batman unicast packet type to use
* @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast
* 4addr packets)
+ * @dst_hint: can be used to override the destination contained in the skb
* @vid: the vid to be used to search the translation table
*
* Look up the recipient node for the destination address in the ethernet
diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h
index aaddaa9..38d0ec1 100644
--- a/net/batman-adv/send.h
+++ b/net/batman-adv/send.h
@@ -36,6 +36,11 @@
struct sk_buff *skb,
struct batadv_orig_node *orig_node,
int packet_subtype);
+int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
+ struct sk_buff *skb, int packet_type,
+ int packet_subtype,
+ struct batadv_orig_node *orig_node,
+ unsigned short vid);
int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv,
struct sk_buff *skb, int packet_type,
int packet_subtype, uint8_t *dst_hint,
@@ -47,6 +52,7 @@
* batadv_send_skb_via_tt - send an skb via TT lookup
* @bat_priv: the bat priv with all the soft interface information
* @skb: the payload to send
+ * @dst_hint: can be used to override the destination contained in the skb
* @vid: the vid to be used to search the translation table
*
* Look up the recipient node for the destination address in the ethernet
@@ -68,6 +74,7 @@
* @bat_priv: the bat priv with all the soft interface information
* @skb: the payload to send
* @packet_subtype: the unicast 4addr packet subtype to use
+ * @dst_hint: can be used to override the destination contained in the skb
* @vid: the vid to be used to search the translation table
*
* Look up the recipient node for the destination address in the ethernet
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index f82c267..744a59b 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -32,6 +32,7 @@
#include <linux/ethtool.h>
#include <linux/etherdevice.h>
#include <linux/if_vlan.h>
+#include "multicast.h"
#include "bridge_loop_avoidance.h"
#include "network-coding.h"
@@ -111,8 +112,8 @@
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
- memcpy(old_addr, dev->dev_addr, ETH_ALEN);
- memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
+ ether_addr_copy(old_addr, dev->dev_addr);
+ ether_addr_copy(dev->dev_addr, addr->sa_data);
/* only modify transtable if it has been initialized before */
if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE) {
@@ -170,17 +171,19 @@
unsigned short vid;
uint32_t seqno;
int gw_mode;
+ enum batadv_forw_mode forw_mode;
+ struct batadv_orig_node *mcast_single_orig = NULL;
if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
goto dropped;
soft_iface->trans_start = jiffies;
vid = batadv_get_vid(skb, 0);
- ethhdr = (struct ethhdr *)skb->data;
+ ethhdr = eth_hdr(skb);
switch (ntohs(ethhdr->h_proto)) {
case ETH_P_8021Q:
- vhdr = (struct vlan_ethhdr *)skb->data;
+ vhdr = vlan_eth_hdr(skb);
if (vhdr->h_vlan_encapsulated_proto != ethertype)
break;
@@ -194,7 +197,7 @@
goto dropped;
/* skb->data might have been reallocated by batadv_bla_tx() */
- ethhdr = (struct ethhdr *)skb->data;
+ ethhdr = eth_hdr(skb);
/* Register the client MAC in the transtable */
if (!is_multicast_ether_addr(ethhdr->h_source)) {
@@ -230,7 +233,7 @@
/* skb->data may have been modified by
* batadv_gw_dhcp_recipient_get()
*/
- ethhdr = (struct ethhdr *)skb->data;
+ ethhdr = eth_hdr(skb);
/* if gw_mode is on, broadcast any non-DHCP message.
* All the DHCP packets are going to be sent as unicast
*/
@@ -247,9 +250,19 @@
* directed to a DHCP server
*/
goto dropped;
- }
send:
+ if (do_bcast && !is_broadcast_ether_addr(ethhdr->h_dest)) {
+ forw_mode = batadv_mcast_forw_mode(bat_priv, skb,
+ &mcast_single_orig);
+ if (forw_mode == BATADV_FORW_NONE)
+ goto dropped;
+
+ if (forw_mode == BATADV_FORW_SINGLE)
+ do_bcast = false;
+ }
+ }
+
batadv_skb_set_priority(skb, 0);
/* ethernet packet should be broadcasted */
@@ -279,8 +292,8 @@
/* hw address of first interface is the orig mac because only
* this mac is known throughout the mesh
*/
- memcpy(bcast_packet->orig,
- primary_if->net_dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(bcast_packet->orig,
+ primary_if->net_dev->dev_addr);
/* set broadcast sequence number */
seqno = atomic_inc_return(&bat_priv->bcast_seqno);
@@ -301,6 +314,10 @@
if (ret)
goto dropped;
ret = batadv_send_skb_via_gw(bat_priv, skb, vid);
+ } else if (mcast_single_orig) {
+ ret = batadv_send_skb_unicast(bat_priv, skb,
+ BATADV_UNICAST, 0,
+ mcast_single_orig, vid);
} else {
if (batadv_dat_snoop_outgoing_arp_request(bat_priv,
skb))
@@ -652,10 +669,7 @@
}
batadv_sysfs_del_meshif(soft_iface);
-
- rtnl_lock();
- unregister_netdevice(soft_iface);
- rtnl_unlock();
+ unregister_netdev(soft_iface);
}
/**
@@ -692,6 +706,14 @@
#ifdef CONFIG_BATMAN_ADV_DAT
atomic_set(&bat_priv->distributed_arp_table, 1);
#endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+ bat_priv->mcast.flags = BATADV_NO_FLAGS;
+ atomic_set(&bat_priv->multicast_mode, 1);
+ atomic_set(&bat_priv->mcast.num_disabled, 0);
+ atomic_set(&bat_priv->mcast.num_want_all_unsnoopables, 0);
+ atomic_set(&bat_priv->mcast.num_want_all_ipv4, 0);
+ atomic_set(&bat_priv->mcast.num_want_all_ipv6, 0);
+#endif
atomic_set(&bat_priv->gw_mode, BATADV_GW_MODE_OFF);
atomic_set(&bat_priv->gw_sel_class, 20);
atomic_set(&bat_priv->gw.bandwidth_down, 100);
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index e456bf6..1ebb0d9 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -539,6 +539,9 @@
batadv_post_gw_reselect);
static BATADV_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, batadv_show_gw_bwidth,
batadv_store_gw_bwidth);
+#ifdef CONFIG_BATMAN_ADV_MCAST
+BATADV_ATTR_SIF_BOOL(multicast_mode, S_IRUGO | S_IWUSR, NULL);
+#endif
#ifdef CONFIG_BATMAN_ADV_DEBUG
BATADV_ATTR_SIF_UINT(log_level, S_IRUGO | S_IWUSR, 0, BATADV_DBG_ALL, NULL);
#endif
@@ -558,6 +561,9 @@
#ifdef CONFIG_BATMAN_ADV_DAT
&batadv_attr_distributed_arp_table,
#endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+ &batadv_attr_multicast_mode,
+#endif
&batadv_attr_fragmentation,
&batadv_attr_routing_algo,
&batadv_attr_gw_mode,
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index b6071f6..d636bde 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -24,6 +24,7 @@
#include "originator.h"
#include "routing.h"
#include "bridge_loop_avoidance.h"
+#include "multicast.h"
#include <linux/crc32c.h>
@@ -96,7 +97,7 @@
if (!hash)
return NULL;
- memcpy(to_search.addr, addr, ETH_ALEN);
+ ether_addr_copy(to_search.addr, addr);
to_search.vid = vid;
index = batadv_choose_tt(&to_search, hash->size);
@@ -192,6 +193,31 @@
}
}
+/**
+ * batadv_tt_global_hash_count - count the number of orig entries
+ * @hash: hash table containing the tt entries
+ * @addr: the mac address of the client to count entries for
+ * @vid: VLAN identifier
+ *
+ * Return the number of originators advertising the given address/data
+ * (excluding ourself).
+ */
+int batadv_tt_global_hash_count(struct batadv_priv *bat_priv,
+ const uint8_t *addr, unsigned short vid)
+{
+ struct batadv_tt_global_entry *tt_global_entry;
+ int count;
+
+ tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr, vid);
+ if (!tt_global_entry)
+ return 0;
+
+ count = atomic_read(&tt_global_entry->orig_list_count);
+ batadv_tt_global_entry_free_ref(tt_global_entry);
+
+ return count;
+}
+
static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu)
{
struct batadv_tt_orig_list_entry *orig_entry;
@@ -333,7 +359,7 @@
tt_change_node->change.flags = flags;
memset(tt_change_node->change.reserved, 0,
sizeof(tt_change_node->change.reserved));
- memcpy(tt_change_node->change.addr, common->addr, ETH_ALEN);
+ ether_addr_copy(tt_change_node->change.addr, common->addr);
tt_change_node->change.vid = htons(common->vid);
del_op_requested = flags & BATADV_TT_CLIENT_DEL;
@@ -484,7 +510,7 @@
{
struct batadv_priv *bat_priv = netdev_priv(soft_iface);
struct batadv_tt_local_entry *tt_local;
- struct batadv_tt_global_entry *tt_global;
+ struct batadv_tt_global_entry *tt_global = NULL;
struct net_device *in_dev = NULL;
struct hlist_head *head;
struct batadv_tt_orig_list_entry *orig_entry;
@@ -497,7 +523,9 @@
in_dev = dev_get_by_index(&init_net, ifindex);
tt_local = batadv_tt_local_hash_find(bat_priv, addr, vid);
- tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid);
+
+ if (!is_multicast_ether_addr(addr))
+ tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid);
if (tt_local) {
tt_local->last_seen = jiffies;
@@ -549,7 +577,7 @@
addr, BATADV_PRINT_VID(vid),
(uint8_t)atomic_read(&bat_priv->tt.vn));
- memcpy(tt_local->common.addr, addr, ETH_ALEN);
+ ether_addr_copy(tt_local->common.addr, addr);
/* The local entry has to be marked as NEW to avoid to send it in
* a full table response going out before the next ttvn increment
* (consistency check)
@@ -562,8 +590,11 @@
tt_local->last_seen = jiffies;
tt_local->common.added_at = tt_local->last_seen;
- /* the batman interface mac address should never be purged */
- if (batadv_compare_eth(addr, soft_iface->dev_addr))
+ /* the batman interface mac and multicast addresses should never be
+ * purged
+ */
+ if (batadv_compare_eth(addr, soft_iface->dev_addr) ||
+ is_multicast_ether_addr(addr))
tt_local->common.flags |= BATADV_TT_CLIENT_NOPURGE;
hash_added = batadv_hash_add(bat_priv->tt.local_hash, batadv_compare_tt,
@@ -1219,6 +1250,8 @@
hlist_add_head_rcu(&orig_entry->list,
&tt_global->orig_list);
spin_unlock_bh(&tt_global->list_lock);
+ atomic_inc(&tt_global->orig_list_count);
+
out:
if (orig_entry)
batadv_tt_orig_list_entry_free_ref(orig_entry);
@@ -1277,7 +1310,7 @@
goto out;
common = &tt_global_entry->common;
- memcpy(common->addr, tt_addr, ETH_ALEN);
+ ether_addr_copy(common->addr, tt_addr);
common->vid = vid;
common->flags = flags;
@@ -1292,6 +1325,7 @@
common->added_at = jiffies;
INIT_HLIST_HEAD(&tt_global_entry->orig_list);
+ atomic_set(&tt_global_entry->orig_list_count, 0);
spin_lock_init(&tt_global_entry->list_lock);
hash_added = batadv_hash_add(bat_priv->tt.global_hash,
@@ -1361,6 +1395,11 @@
ret = true;
out_remove:
+ /* Do not remove multicast addresses from the local hash on
+ * global additions
+ */
+ if (is_multicast_ether_addr(tt_addr))
+ goto out;
/* remove address from local hash if present */
local_flags = batadv_tt_local_remove(bat_priv, tt_addr, vid,
@@ -1552,6 +1591,25 @@
return 0;
}
+/**
+ * batadv_tt_global_del_orig_entry - remove and free an orig_entry
+ * @tt_global_entry: the global entry to remove the orig_entry from
+ * @orig_entry: the orig entry to remove and free
+ *
+ * Remove an orig_entry from its list in the given tt_global_entry and
+ * free this orig_entry afterwards.
+ */
+static void
+batadv_tt_global_del_orig_entry(struct batadv_tt_global_entry *tt_global_entry,
+ struct batadv_tt_orig_list_entry *orig_entry)
+{
+ batadv_tt_global_size_dec(orig_entry->orig_node,
+ tt_global_entry->common.vid);
+ atomic_dec(&tt_global_entry->orig_list_count);
+ hlist_del_rcu(&orig_entry->list);
+ batadv_tt_orig_list_entry_free_ref(orig_entry);
+}
+
/* deletes the orig list of a tt_global_entry */
static void
batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry)
@@ -1562,20 +1620,26 @@
spin_lock_bh(&tt_global_entry->list_lock);
head = &tt_global_entry->orig_list;
- hlist_for_each_entry_safe(orig_entry, safe, head, list) {
- hlist_del_rcu(&orig_entry->list);
- batadv_tt_global_size_dec(orig_entry->orig_node,
- tt_global_entry->common.vid);
- batadv_tt_orig_list_entry_free_ref(orig_entry);
- }
+ hlist_for_each_entry_safe(orig_entry, safe, head, list)
+ batadv_tt_global_del_orig_entry(tt_global_entry, orig_entry);
spin_unlock_bh(&tt_global_entry->list_lock);
}
+/**
+ * batadv_tt_global_del_orig_node - remove orig_node from a global tt entry
+ * @bat_priv: the bat priv with all the soft interface information
+ * @tt_global_entry: the global entry to remove the orig_node from
+ * @orig_node: the originator announcing the client
+ * @message: message to append to the log on deletion
+ *
+ * Remove the given orig_node and its according orig_entry from the given
+ * global tt entry.
+ */
static void
-batadv_tt_global_del_orig_entry(struct batadv_priv *bat_priv,
- struct batadv_tt_global_entry *tt_global_entry,
- struct batadv_orig_node *orig_node,
- const char *message)
+batadv_tt_global_del_orig_node(struct batadv_priv *bat_priv,
+ struct batadv_tt_global_entry *tt_global_entry,
+ struct batadv_orig_node *orig_node,
+ const char *message)
{
struct hlist_head *head;
struct hlist_node *safe;
@@ -1592,10 +1656,8 @@
orig_node->orig,
tt_global_entry->common.addr,
BATADV_PRINT_VID(vid), message);
- hlist_del_rcu(&orig_entry->list);
- batadv_tt_global_size_dec(orig_node,
- tt_global_entry->common.vid);
- batadv_tt_orig_list_entry_free_ref(orig_entry);
+ batadv_tt_global_del_orig_entry(tt_global_entry,
+ orig_entry);
}
}
spin_unlock_bh(&tt_global_entry->list_lock);
@@ -1637,8 +1699,8 @@
/* there is another entry, we can simply delete this
* one and can still use the other one.
*/
- batadv_tt_global_del_orig_entry(bat_priv, tt_global_entry,
- orig_node, message);
+ batadv_tt_global_del_orig_node(bat_priv, tt_global_entry,
+ orig_node, message);
}
/**
@@ -1664,8 +1726,8 @@
goto out;
if (!roaming) {
- batadv_tt_global_del_orig_entry(bat_priv, tt_global_entry,
- orig_node, message);
+ batadv_tt_global_del_orig_node(bat_priv, tt_global_entry,
+ orig_node, message);
if (hlist_empty(&tt_global_entry->orig_list))
batadv_tt_global_free(bat_priv, tt_global_entry,
@@ -1748,8 +1810,8 @@
struct batadv_tt_global_entry,
common);
- batadv_tt_global_del_orig_entry(bat_priv, tt_global,
- orig_node, message);
+ batadv_tt_global_del_orig_node(bat_priv, tt_global,
+ orig_node, message);
if (hlist_empty(&tt_global->orig_list)) {
vid = tt_global->common.vid;
@@ -1763,7 +1825,7 @@
}
spin_unlock_bh(list_lock);
}
- orig_node->tt_initialised = false;
+ orig_node->capa_initialized &= ~BATADV_ORIG_CAPA_HAS_TT;
}
static bool batadv_tt_global_to_purge(struct batadv_tt_global_entry *tt_global,
@@ -1975,6 +2037,7 @@
struct hlist_head *head;
uint32_t i, crc_tmp, crc = 0;
uint8_t flags;
+ __be16 tmp_vid;
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
@@ -2011,8 +2074,11 @@
orig_node))
continue;
- crc_tmp = crc32c(0, &tt_common->vid,
- sizeof(tt_common->vid));
+ /* use network order to read the VID: this ensures that
+ * every node reads the bytes in the same order.
+ */
+ tmp_vid = htons(tt_common->vid);
+ crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid));
/* compute the CRC on flags that have to be kept in sync
* among nodes
@@ -2046,6 +2112,7 @@
struct hlist_head *head;
uint32_t i, crc_tmp, crc = 0;
uint8_t flags;
+ __be16 tmp_vid;
for (i = 0; i < hash->size; i++) {
head = &hash->table[i];
@@ -2064,8 +2131,11 @@
if (tt_common->flags & BATADV_TT_CLIENT_NEW)
continue;
- crc_tmp = crc32c(0, &tt_common->vid,
- sizeof(tt_common->vid));
+ /* use network order to read the VID: this ensures that
+ * every node reads the bytes in the same order.
+ */
+ tmp_vid = htons(tt_common->vid);
+ crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid));
/* compute the CRC on flags that have to be kept in sync
* among nodes
@@ -2152,7 +2222,7 @@
if (!tt_req_node)
goto unlock;
- memcpy(tt_req_node->addr, orig_node->orig, ETH_ALEN);
+ ether_addr_copy(tt_req_node->addr, orig_node->orig);
tt_req_node->issued_at = jiffies;
list_add(&tt_req_node->list, &bat_priv->tt.req_list);
@@ -2232,8 +2302,7 @@
if ((valid_cb) && (!valid_cb(tt_common_entry, cb_data)))
continue;
- memcpy(tt_change->addr, tt_common_entry->addr,
- ETH_ALEN);
+ ether_addr_copy(tt_change->addr, tt_common_entry->addr);
tt_change->flags = tt_common_entry->flags;
tt_change->vid = htons(tt_common_entry->vid);
memset(tt_change->reserved, 0,
@@ -2262,6 +2331,7 @@
{
struct batadv_tvlv_tt_vlan_data *tt_vlan_tmp;
struct batadv_orig_node_vlan *vlan;
+ uint32_t crc;
int i;
/* check if each received CRC matches the locally stored one */
@@ -2281,7 +2351,10 @@
if (!vlan)
return false;
- if (vlan->tt.crc != ntohl(tt_vlan_tmp->crc))
+ crc = vlan->tt.crc;
+ batadv_orig_node_vlan_free_ref(vlan);
+
+ if (crc != ntohl(tt_vlan_tmp->crc))
return false;
}
@@ -2712,7 +2785,7 @@
return;
}
}
- orig_node->tt_initialised = true;
+ orig_node->capa_initialized |= BATADV_ORIG_CAPA_HAS_TT;
}
static void batadv_tt_fill_gtable(struct batadv_priv *bat_priv,
@@ -2920,7 +2993,7 @@
tt_roam_node->first_time = jiffies;
atomic_set(&tt_roam_node->counter,
BATADV_ROAMING_MAX_COUNT - 1);
- memcpy(tt_roam_node->addr, client, ETH_ALEN);
+ ether_addr_copy(tt_roam_node->addr, client);
list_add(&tt_roam_node->list, &bat_priv->tt.roam_list);
ret = true;
@@ -3109,6 +3182,9 @@
*/
static void batadv_tt_local_commit_changes_nolock(struct batadv_priv *bat_priv)
{
+ /* Update multicast addresses in local translation table */
+ batadv_mcast_mla_update(bat_priv);
+
if (atomic_read(&bat_priv->tt.local_changes) < 1) {
if (!batadv_atomic_dec_not_zero(&bat_priv->tt.ogm_append_cnt))
batadv_tt_tvlv_container_update(bat_priv);
@@ -3199,13 +3275,15 @@
uint8_t orig_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn);
struct batadv_tvlv_tt_vlan_data *tt_vlan;
bool full_table = true;
+ bool has_tt_init;
tt_vlan = (struct batadv_tvlv_tt_vlan_data *)tt_buff;
+ has_tt_init = orig_node->capa_initialized & BATADV_ORIG_CAPA_HAS_TT;
+
/* orig table not initialised AND first diff is in the OGM OR the ttvn
* increased by one -> we can apply the attached changes
*/
- if ((!orig_node->tt_initialised && ttvn == 1) ||
- ttvn - orig_ttvn == 1) {
+ if ((!has_tt_init && ttvn == 1) || ttvn - orig_ttvn == 1) {
/* the OGM could not contain the changes due to their size or
* because they have already been sent BATADV_TT_OGM_APPEND_MAX
* times.
@@ -3218,7 +3296,6 @@
spin_lock_bh(&orig_node->tt_lock);
- tt_change = (struct batadv_tvlv_tt_change *)tt_buff;
batadv_tt_update_changes(bat_priv, orig_node, tt_num_changes,
ttvn, tt_change);
@@ -3246,7 +3323,7 @@
/* if we missed more than one change or our tables are not
* in sync anymore -> request fresh tt data
*/
- if (!orig_node->tt_initialised || ttvn != orig_ttvn ||
+ if (!has_tt_init || ttvn != orig_ttvn ||
!batadv_tt_global_check_crc(orig_node, tt_vlan,
tt_num_vlan)) {
request_table:
diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h
index 20a1d78..ad84d7b 100644
--- a/net/batman-adv/translation-table.h
+++ b/net/batman-adv/translation-table.h
@@ -29,6 +29,8 @@
void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node,
int32_t match_vid, const char *message);
+int batadv_tt_global_hash_count(struct batadv_priv *bat_priv,
+ const uint8_t *addr, unsigned short vid);
struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv,
const uint8_t *src,
const uint8_t *addr,
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 78370ab..34891a5 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -24,8 +24,9 @@
#ifdef CONFIG_BATMAN_ADV_DAT
-/* batadv_dat_addr_t is the type used for all DHT addresses. If it is changed,
- * BATADV_DAT_ADDR_MAX is changed as well.
+/**
+ * batadv_dat_addr_t - it is the type used for all DHT addresses. If it is
+ * changed, BATADV_DAT_ADDR_MAX is changed as well.
*
* *Please be careful: batadv_dat_addr_t must be UNSIGNED*
*/
@@ -163,7 +164,7 @@
};
/**
- * batadv_orig_node_vlan - VLAN specific data per orig_node
+ * struct batadv_orig_node_vlan - VLAN specific data per orig_node
* @vid: the VLAN identifier
* @tt: VLAN specific TT attributes
* @list: list node for orig_node::vlan_list
@@ -204,14 +205,18 @@
* @batadv_dat_addr_t: address of the orig node in the distributed hash
* @last_seen: time when last packet from this node was received
* @bcast_seqno_reset: time when the broadcast seqno window was reset
+ * @mcast_flags: multicast flags announced by the orig node
+ * @mcast_want_all_unsnoop_node: a list node for the
+ * mcast.want_all_unsnoopables list
+ * @mcast_want_all_ipv4_node: a list node for the mcast.want_all_ipv4 list
+ * @mcast_want_all_ipv6_node: a list node for the mcast.want_all_ipv6 list
* @capabilities: announced capabilities of this originator
+ * @capa_initialized: bitfield to remember whether a capability was initialized
* @last_ttvn: last seen translation table version number
* @tt_buff: last tt changeset this node received from the orig node
* @tt_buff_len: length of the last tt changeset this node received from the
* orig node
* @tt_buff_lock: lock that protects tt_buff and tt_buff_len
- * @tt_initialised: bool keeping track of whether or not this node have received
- * any translation table information from the orig node yet
* @tt_lock: prevents from updating the table while reading it. Table update is
* made up by two operations (data structure update and metdata -CRC/TTVN-
* recalculation) and they have to be executed atomically in order to avoid
@@ -247,12 +252,18 @@
#endif
unsigned long last_seen;
unsigned long bcast_seqno_reset;
+#ifdef CONFIG_BATMAN_ADV_MCAST
+ uint8_t mcast_flags;
+ struct hlist_node mcast_want_all_unsnoopables_node;
+ struct hlist_node mcast_want_all_ipv4_node;
+ struct hlist_node mcast_want_all_ipv6_node;
+#endif
uint8_t capabilities;
+ uint8_t capa_initialized;
atomic_t last_ttvn;
unsigned char *tt_buff;
int16_t tt_buff_len;
spinlock_t tt_buff_lock; /* protects tt_buff & tt_buff_len */
- bool tt_initialised;
/* prevents from changing the table while reading it */
spinlock_t tt_lock;
DECLARE_BITMAP(bcast_bits, BATADV_TQ_LOCAL_WINDOW_SIZE);
@@ -282,10 +293,15 @@
* enum batadv_orig_capabilities - orig node capabilities
* @BATADV_ORIG_CAPA_HAS_DAT: orig node has distributed arp table enabled
* @BATADV_ORIG_CAPA_HAS_NC: orig node has network coding enabled
+ * @BATADV_ORIG_CAPA_HAS_TT: orig node has tt capability
+ * @BATADV_ORIG_CAPA_HAS_MCAST: orig node has some multicast capability
+ * (= orig node announces a tvlv of type BATADV_TVLV_MCAST)
*/
enum batadv_orig_capabilities {
BATADV_ORIG_CAPA_HAS_DAT = BIT(0),
BATADV_ORIG_CAPA_HAS_NC = BIT(1),
+ BATADV_ORIG_CAPA_HAS_TT = BIT(2),
+ BATADV_ORIG_CAPA_HAS_MCAST = BIT(3),
};
/**
@@ -334,7 +350,7 @@
};
/**
- * struct batadv_neigh_node_bat_iv - neighbor information per outgoing
+ * struct batadv_neigh_ifinfo_bat_iv - neighbor information per outgoing
* interface for BATMAN IV
* @tq_recv: ring buffer of received TQ values from this neigh node
* @tq_index: ring buffer index
@@ -544,7 +560,7 @@
#endif
/**
- * struct batadv_debug_log - debug logging data
+ * struct batadv_priv_debug_log - debug logging data
* @log_buff: buffer holding the logs (ring bufer)
* @log_start: index of next character to read
* @log_end: index of next character to write
@@ -607,6 +623,39 @@
};
#endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+/**
+ * struct batadv_priv_mcast - per mesh interface mcast data
+ * @mla_list: list of multicast addresses we are currently announcing via TT
+ * @want_all_unsnoopables_list: a list of orig_nodes wanting all unsnoopable
+ * multicast traffic
+ * @want_all_ipv4_list: a list of orig_nodes wanting all IPv4 multicast traffic
+ * @want_all_ipv6_list: a list of orig_nodes wanting all IPv6 multicast traffic
+ * @flags: the flags we have last sent in our mcast tvlv
+ * @enabled: whether the multicast tvlv is currently enabled
+ * @num_disabled: number of nodes that have no mcast tvlv
+ * @num_want_all_unsnoopables: number of nodes wanting unsnoopable IP traffic
+ * @num_want_all_ipv4: counter for items in want_all_ipv4_list
+ * @num_want_all_ipv6: counter for items in want_all_ipv6_list
+ * @want_lists_lock: lock for protecting modifications to mcast want lists
+ * (traversals are rcu-locked)
+ */
+struct batadv_priv_mcast {
+ struct hlist_head mla_list;
+ struct hlist_head want_all_unsnoopables_list;
+ struct hlist_head want_all_ipv4_list;
+ struct hlist_head want_all_ipv6_list;
+ uint8_t flags;
+ bool enabled;
+ atomic_t num_disabled;
+ atomic_t num_want_all_unsnoopables;
+ atomic_t num_want_all_ipv4;
+ atomic_t num_want_all_ipv6;
+ /* protects want_all_{unsnoopables,ipv4,ipv6}_list */
+ spinlock_t want_lists_lock;
+};
+#endif
+
/**
* struct batadv_priv_nc - per mesh interface network coding private data
* @work: work queue callback item for cleanup
@@ -672,6 +721,8 @@
* enabled
* @distributed_arp_table: bool indicating whether distributed ARP table is
* enabled
+ * @multicast_mode: Enable or disable multicast optimizations on this node's
+ * sender/originating side
* @gw_mode: gateway operation: off, client or server (see batadv_gw_modes)
* @gw_sel_class: gateway selection class (applies if gw_mode client)
* @orig_interval: OGM broadcast interval in milliseconds
@@ -702,6 +753,7 @@
* @tt: translation table data
* @tvlv: type-version-length-value data
* @dat: distributed arp table data
+ * @mcast: multicast data
* @network_coding: bool indicating whether network coding is enabled
* @batadv_priv_nc: network coding data
*/
@@ -721,6 +773,9 @@
#ifdef CONFIG_BATMAN_ADV_DAT
atomic_t distributed_arp_table;
#endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+ atomic_t multicast_mode;
+#endif
atomic_t gw_mode;
atomic_t gw_sel_class;
atomic_t orig_interval;
@@ -759,6 +814,9 @@
#ifdef CONFIG_BATMAN_ADV_DAT
struct batadv_priv_dat dat;
#endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+ struct batadv_priv_mcast mcast;
+#endif
#ifdef CONFIG_BATMAN_ADV_NC
atomic_t network_coding;
struct batadv_priv_nc nc;
@@ -881,12 +939,14 @@
* struct batadv_tt_global_entry - translation table global entry data
* @common: general translation table data
* @orig_list: list of orig nodes announcing this non-mesh client
+ * @orig_list_count: number of items in the orig_list
* @list_lock: lock protecting orig_list
* @roam_at: time at which TT_GLOBAL_ROAM was set
*/
struct batadv_tt_global_entry {
struct batadv_tt_common_entry common;
struct hlist_head orig_list;
+ atomic_t orig_list_count;
spinlock_t list_lock; /* protects orig_list */
unsigned long roam_at;
};
@@ -1004,8 +1064,8 @@
};
/**
- * batadv_skb_cb - control buffer structure used to store private data relevant
- * to batman-adv in the skb->cb buffer in skbs.
+ * struct batadv_skb_cb - control buffer structure used to store private data
+ * relevant to batman-adv in the skb->cb buffer in skbs.
* @decoded: Marks a skb as decoded, which is checked when searching for coding
* opportunities in network-coding.c
*/
@@ -1116,6 +1176,16 @@
};
/**
+ * struct batadv_hw_addr - a list entry for a MAC address
+ * @list: list node for the linking of entries
+ * @addr: the MAC address of this list entry
+ */
+struct batadv_hw_addr {
+ struct hlist_node list;
+ unsigned char addr[ETH_ALEN];
+};
+
+/**
* struct batadv_dat_candidate - candidate destination for DAT operations
* @type: the type of the selected candidate. It can one of the following:
* - BATADV_DAT_CANDIDATE_NOT_FOUND
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index adb3ea0..73492b9 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -27,7 +27,7 @@
#include "6lowpan.h"
-#include "../ieee802154/6lowpan.h" /* for the compression support */
+#include <net/6lowpan.h> /* for the compression support */
#define IFACE_NAME_TEMPLATE "bt%d"
#define EUI64_ADDR_LEN 8
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 292e619..d9fb934 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -430,6 +430,16 @@
del_timer(&session->timer);
}
+static void hidp_process_report(struct hidp_session *session,
+ int type, const u8 *data, int len, int intr)
+{
+ if (len > HID_MAX_BUFFER_SIZE)
+ len = HID_MAX_BUFFER_SIZE;
+
+ memcpy(session->input_buf, data, len);
+ hid_input_report(session->hid, type, session->input_buf, len, intr);
+}
+
static void hidp_process_handshake(struct hidp_session *session,
unsigned char param)
{
@@ -502,7 +512,8 @@
hidp_input_report(session, skb);
if (session->hid)
- hid_input_report(session->hid, HID_INPUT_REPORT, skb->data, skb->len, 0);
+ hidp_process_report(session, HID_INPUT_REPORT,
+ skb->data, skb->len, 0);
break;
case HIDP_DATA_RTYPE_OTHER:
@@ -584,7 +595,8 @@
hidp_input_report(session, skb);
if (session->hid) {
- hid_input_report(session->hid, HID_INPUT_REPORT, skb->data, skb->len, 1);
+ hidp_process_report(session, HID_INPUT_REPORT,
+ skb->data, skb->len, 1);
BT_DBG("report len %d", skb->len);
}
} else {
diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h
index ab52414..8798492 100644
--- a/net/bluetooth/hidp/hidp.h
+++ b/net/bluetooth/hidp/hidp.h
@@ -24,6 +24,7 @@
#define __HIDP_H
#include <linux/types.h>
+#include <linux/hid.h>
#include <linux/kref.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/l2cap.h>
@@ -179,6 +180,9 @@
/* Used in hidp_output_raw_report() */
int output_report_success; /* boolean */
+
+ /* temporary input buffer */
+ u8 input_buf[HID_MAX_BUFFER_SIZE];
};
/* HIDP init defines */
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index e4401a5..3e2da2c 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -49,14 +49,14 @@
brstats->tx_bytes += skb->len;
u64_stats_update_end(&brstats->syncp);
- if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
- goto out;
-
BR_INPUT_SKB_CB(skb)->brdev = dev;
skb_reset_mac_header(skb);
skb_pull(skb, ETH_HLEN);
+ if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
+ goto out;
+
if (is_broadcast_ether_addr(dest))
br_flood_deliver(br, skb, false);
else if (is_multicast_ether_addr(dest)) {
@@ -88,18 +88,11 @@
static int br_dev_init(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
- int i;
- br->stats = alloc_percpu(struct pcpu_sw_netstats);
+ br->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!br->stats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct pcpu_sw_netstats *br_dev_stats;
- br_dev_stats = per_cpu_ptr(br->stats, i);
- u64_stats_init(&br_dev_stats->syncp);
- }
-
return 0;
}
@@ -143,9 +136,9 @@
const struct pcpu_sw_netstats *bstats
= per_cpu_ptr(br->stats, cpu);
do {
- start = u64_stats_fetch_begin_bh(&bstats->syncp);
+ start = u64_stats_fetch_begin_irq(&bstats->syncp);
memcpy(&tmp, bstats, sizeof(tmp));
- } while (u64_stats_fetch_retry_bh(&bstats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&bstats->syncp, start));
sum.tx_bytes += tmp.tx_bytes;
sum.tx_packets += tmp.tx_packets;
sum.rx_bytes += tmp.rx_bytes;
@@ -187,8 +180,7 @@
spin_lock_bh(&br->lock);
if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) {
- memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
- br_fdb_change_mac_address(br, addr->sa_data);
+ /* Mac address will be changed in br_stp_change_bridge_id(). */
br_stp_change_bridge_id(br, addr->sa_data);
}
spin_unlock_bh(&br->lock);
@@ -226,8 +218,34 @@
br_netpoll_disable(p);
}
-static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni,
- gfp_t gfp)
+static int __br_netpoll_enable(struct net_bridge_port *p)
+{
+ struct netpoll *np;
+ int err;
+
+ np = kzalloc(sizeof(*p->np), GFP_KERNEL);
+ if (!np)
+ return -ENOMEM;
+
+ err = __netpoll_setup(np, p->dev);
+ if (err) {
+ kfree(np);
+ return err;
+ }
+
+ p->np = np;
+ return err;
+}
+
+int br_netpoll_enable(struct net_bridge_port *p)
+{
+ if (!p->br->dev->npinfo)
+ return 0;
+
+ return __br_netpoll_enable(p);
+}
+
+static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
{
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *p;
@@ -236,7 +254,7 @@
list_for_each_entry(p, &br->port_list, list) {
if (!p->dev)
continue;
- err = br_netpoll_enable(p, gfp);
+ err = __br_netpoll_enable(p);
if (err)
goto fail;
}
@@ -249,28 +267,6 @@
goto out;
}
-int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
-{
- struct netpoll *np;
- int err;
-
- if (!p->br->dev->npinfo)
- return 0;
-
- np = kzalloc(sizeof(*p->np), gfp);
- if (!np)
- return -ENOMEM;
-
- err = __netpoll_setup(np, p->dev, gfp);
- if (err) {
- kfree(np);
- return err;
- }
-
- p->np = np;
- return err;
-}
-
void br_netpoll_disable(struct net_bridge_port *p)
{
struct netpoll *np = p->np;
@@ -370,7 +366,7 @@
br->bridge_id.prio[0] = 0x80;
br->bridge_id.prio[1] = 0x00;
- memcpy(br->group_addr, eth_reserved_addr_base, ETH_ALEN);
+ ether_addr_copy(br->group_addr, eth_reserved_addr_base);
br->stp_enabled = BR_NO_STP;
br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index c5f5a4a..9203d5a 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -27,6 +27,9 @@
#include "br_private.h"
static struct kmem_cache *br_fdb_cache __read_mostly;
+static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head,
+ const unsigned char *addr,
+ __u16 vid);
static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr, u16 vid);
static void fdb_notify(struct net_bridge *br,
@@ -89,11 +92,57 @@
call_rcu(&f->rcu, fdb_rcu_free);
}
+/* Delete a local entry if no other port had the same address. */
+static void fdb_delete_local(struct net_bridge *br,
+ const struct net_bridge_port *p,
+ struct net_bridge_fdb_entry *f)
+{
+ const unsigned char *addr = f->addr.addr;
+ u16 vid = f->vlan_id;
+ struct net_bridge_port *op;
+
+ /* Maybe another port has same hw addr? */
+ list_for_each_entry(op, &br->port_list, list) {
+ if (op != p && ether_addr_equal(op->dev->dev_addr, addr) &&
+ (!vid || nbp_vlan_find(op, vid))) {
+ f->dst = op;
+ f->added_by_user = 0;
+ return;
+ }
+ }
+
+ /* Maybe bridge device has same hw addr? */
+ if (p && ether_addr_equal(br->dev->dev_addr, addr) &&
+ (!vid || br_vlan_find(br, vid))) {
+ f->dst = NULL;
+ f->added_by_user = 0;
+ return;
+ }
+
+ fdb_delete(br, f);
+}
+
+void br_fdb_find_delete_local(struct net_bridge *br,
+ const struct net_bridge_port *p,
+ const unsigned char *addr, u16 vid)
+{
+ struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
+ struct net_bridge_fdb_entry *f;
+
+ spin_lock_bh(&br->hash_lock);
+ f = fdb_find(head, addr, vid);
+ if (f && f->is_local && !f->added_by_user && f->dst == p)
+ fdb_delete_local(br, p, f);
+ spin_unlock_bh(&br->hash_lock);
+}
+
void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
{
struct net_bridge *br = p->br;
- bool no_vlan = (nbp_get_vlan_info(p) == NULL) ? true : false;
+ struct net_port_vlans *pv = nbp_get_vlan_info(p);
+ bool no_vlan = !pv;
int i;
+ u16 vid;
spin_lock_bh(&br->hash_lock);
@@ -104,38 +153,34 @@
struct net_bridge_fdb_entry *f;
f = hlist_entry(h, struct net_bridge_fdb_entry, hlist);
- if (f->dst == p && f->is_local) {
- /* maybe another port has same hw addr? */
- struct net_bridge_port *op;
- u16 vid = f->vlan_id;
- list_for_each_entry(op, &br->port_list, list) {
- if (op != p &&
- ether_addr_equal(op->dev->dev_addr,
- f->addr.addr) &&
- nbp_vlan_find(op, vid)) {
- f->dst = op;
- goto insert;
- }
- }
-
+ if (f->dst == p && f->is_local && !f->added_by_user) {
/* delete old one */
- fdb_delete(br, f);
-insert:
- /* insert new address, may fail if invalid
- * address or dup.
- */
- fdb_insert(br, p, newaddr, vid);
+ fdb_delete_local(br, p, f);
/* if this port has no vlan information
* configured, we can safely be done at
* this point.
*/
if (no_vlan)
- goto done;
+ goto insert;
}
}
}
+insert:
+ /* insert new address, may fail if invalid address or dup. */
+ fdb_insert(br, p, newaddr, 0);
+
+ if (no_vlan)
+ goto done;
+
+ /* Now add entries for every VLAN configured on the port.
+ * This function runs under RTNL so the bitmap will not change
+ * from under us.
+ */
+ for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
+ fdb_insert(br, p, newaddr, vid);
+
done:
spin_unlock_bh(&br->hash_lock);
}
@@ -146,10 +191,12 @@
struct net_port_vlans *pv;
u16 vid = 0;
+ spin_lock_bh(&br->hash_lock);
+
/* If old entry was unassociated with any port, then delete it. */
f = __br_fdb_get(br, br->dev->dev_addr, 0);
if (f && f->is_local && !f->dst)
- fdb_delete(br, f);
+ fdb_delete_local(br, NULL, f);
fdb_insert(br, NULL, newaddr, 0);
@@ -159,14 +206,16 @@
*/
pv = br_get_vlan_info(br);
if (!pv)
- return;
+ goto out;
for_each_set_bit_from(vid, pv->vlan_bitmap, VLAN_N_VID) {
f = __br_fdb_get(br, br->dev->dev_addr, vid);
if (f && f->is_local && !f->dst)
- fdb_delete(br, f);
+ fdb_delete_local(br, NULL, f);
fdb_insert(br, NULL, newaddr, vid);
}
+out:
+ spin_unlock_bh(&br->hash_lock);
}
void br_fdb_cleanup(unsigned long _data)
@@ -235,25 +284,11 @@
if (f->is_static && !do_all)
continue;
- /*
- * if multiple ports all have the same device address
- * then when one port is deleted, assign
- * the local entry to other port
- */
- if (f->is_local) {
- struct net_bridge_port *op;
- list_for_each_entry(op, &br->port_list, list) {
- if (op != p &&
- ether_addr_equal(op->dev->dev_addr,
- f->addr.addr)) {
- f->dst = op;
- goto skip_delete;
- }
- }
- }
- fdb_delete(br, f);
- skip_delete: ;
+ if (f->is_local)
+ fdb_delete_local(br, p, f);
+ else
+ fdb_delete(br, f);
}
}
spin_unlock_bh(&br->hash_lock);
@@ -397,6 +432,7 @@
fdb->vlan_id = vid;
fdb->is_local = 0;
fdb->is_static = 0;
+ fdb->added_by_user = 0;
fdb->updated = fdb->used = jiffies;
hlist_add_head_rcu(&fdb->hlist, head);
}
@@ -447,7 +483,7 @@
}
void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
- const unsigned char *addr, u16 vid)
+ const unsigned char *addr, u16 vid, bool added_by_user)
{
struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
struct net_bridge_fdb_entry *fdb;
@@ -473,13 +509,18 @@
/* fastpath: update of existing entry */
fdb->dst = source;
fdb->updated = jiffies;
+ if (unlikely(added_by_user))
+ fdb->added_by_user = 1;
}
} else {
spin_lock(&br->hash_lock);
if (likely(!fdb_find(head, addr, vid))) {
fdb = fdb_create(head, source, addr, vid);
- if (fdb)
+ if (fdb) {
+ if (unlikely(added_by_user))
+ fdb->added_by_user = 1;
fdb_notify(br, fdb, RTM_NEWNEIGH);
+ }
}
/* else we lose race and someone else inserts
* it first, don't bother updating
@@ -647,6 +688,7 @@
modified = true;
}
+ fdb->added_by_user = 1;
fdb->used = jiffies;
if (modified) {
@@ -664,7 +706,7 @@
if (ndm->ndm_flags & NTF_USE) {
rcu_read_lock();
- br_fdb_update(p->br, p, addr, vid);
+ br_fdb_update(p->br, p, addr, vid, true);
rcu_read_unlock();
} else {
spin_lock_bh(&p->br->hash_lock);
@@ -749,8 +791,7 @@
return err;
}
-int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr,
- u16 vlan)
+static int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vlan)
{
struct hlist_head *head = &br->hash[br_mac_hash(addr, vlan)];
struct net_bridge_fdb_entry *fdb;
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index cffe1d6..5262b86 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -366,7 +366,7 @@
if (err)
goto err2;
- err = br_netpoll_enable(p, GFP_KERNEL);
+ err = br_netpoll_enable(p);
if (err)
goto err3;
@@ -389,6 +389,9 @@
if (br->dev->needed_headroom < dev->needed_headroom)
br->dev->needed_headroom = dev->needed_headroom;
+ if (br_fdb_insert(br, p, dev->dev_addr, 0))
+ netdev_err(dev, "failed insert local address bridge forwarding table\n");
+
spin_lock_bh(&br->lock);
changed_addr = br_stp_recalculate_bridge_id(br);
@@ -404,9 +407,6 @@
dev_set_mtu(br->dev, br_min_mtu(br));
- if (br_fdb_insert(br, p, dev->dev_addr, 0))
- netdev_err(dev, "failed insert local address bridge forwarding table\n");
-
kobject_uevent(&p->kobj, KOBJ_ADD);
return 0;
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index bf8dc7d..d0cca3c 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -29,6 +29,7 @@
struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
struct net_bridge *br = netdev_priv(brdev);
struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
+ struct net_port_vlans *pv;
u64_stats_update_begin(&brstats->syncp);
brstats->rx_packets++;
@@ -39,18 +40,18 @@
* packet is allowed except in promisc modue when someone
* may be running packet capture.
*/
+ pv = br_get_vlan_info(br);
if (!(brdev->flags & IFF_PROMISC) &&
- !br_allowed_egress(br, br_get_vlan_info(br), skb)) {
+ !br_allowed_egress(br, pv, skb)) {
kfree_skb(skb);
return NET_RX_DROP;
}
- skb = br_handle_vlan(br, br_get_vlan_info(br), skb);
- if (!skb)
- return NET_RX_DROP;
-
indev = skb->dev;
skb->dev = brdev;
+ skb = br_handle_vlan(br, pv, skb);
+ if (!skb)
+ return NET_RX_DROP;
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL,
netif_receive_skb);
@@ -77,7 +78,7 @@
/* insert into forwarding database after filtering to avoid spoofing */
br = p->br;
if (p->flags & BR_LEARNING)
- br_fdb_update(br, p, eth_hdr(skb)->h_source, vid);
+ br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false);
if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) &&
br_multicast_rcv(br, p, skb, vid))
@@ -148,7 +149,7 @@
br_vlan_get_tag(skb, &vid);
if (p->flags & BR_LEARNING)
- br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid);
+ br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
return 0; /* process further */
}
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index ef66365..7b757b5 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -363,7 +363,7 @@
skb_reset_mac_header(skb);
eth = eth_hdr(skb);
- memcpy(eth->h_source, br->dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(eth->h_source, br->dev->dev_addr);
eth->h_dest[0] = 1;
eth->h_dest[1] = 0;
eth->h_dest[2] = 0x5e;
@@ -433,7 +433,7 @@
skb_reset_mac_header(skb);
eth = eth_hdr(skb);
- memcpy(eth->h_source, br->dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(eth->h_source, br->dev->dev_addr);
eth->h_proto = htons(ETH_P_IPV6);
skb_put(skb, sizeof(*eth));
@@ -1127,9 +1127,10 @@
struct net_bridge_port *port,
struct bridge_mcast_querier *querier,
int saddr,
+ bool is_general_query,
unsigned long max_delay)
{
- if (saddr)
+ if (saddr && is_general_query)
br_multicast_update_querier_timer(br, querier, max_delay);
else if (timer_pending(&querier->timer))
return;
@@ -1181,8 +1182,16 @@
IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1;
}
+ /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer
+ * all-systems destination addresses (224.0.0.1) for general queries
+ */
+ if (!group && iph->daddr != htonl(INADDR_ALLHOSTS_GROUP)) {
+ err = -EINVAL;
+ goto out;
+ }
+
br_multicast_query_received(br, port, &br->ip4_querier, !!iph->saddr,
- max_delay);
+ !group, max_delay);
if (!group)
goto out;
@@ -1228,6 +1237,7 @@
unsigned long max_delay;
unsigned long now = jiffies;
const struct in6_addr *group = NULL;
+ bool is_general_query;
int err = 0;
spin_lock(&br->multicast_lock);
@@ -1235,6 +1245,12 @@
(port && port->state == BR_STATE_DISABLED))
goto out;
+ /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
+ if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) {
+ err = -EINVAL;
+ goto out;
+ }
+
if (skb->len == sizeof(*mld)) {
if (!pskb_may_pull(skb, sizeof(*mld))) {
err = -EINVAL;
@@ -1256,8 +1272,19 @@
max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL);
}
+ is_general_query = group && ipv6_addr_any(group);
+
+ /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer
+ * all-nodes destination address (ff02::1) for general queries
+ */
+ if (is_general_query && !ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) {
+ err = -EINVAL;
+ goto out;
+ }
+
br_multicast_query_received(br, port, &br->ip6_querier,
- !ipv6_addr_any(&ip6h->saddr), max_delay);
+ !ipv6_addr_any(&ip6h->saddr),
+ is_general_query, max_delay);
if (!group)
goto out;
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index b008c59..80e1b0f 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -167,7 +167,7 @@
rt->dst.dev = br->dev;
rt->dst.path = &rt->dst;
dst_init_metrics(&rt->dst, br_dst_default_metrics, true);
- rt->dst.flags = DST_NOXFRM | DST_NOPEER | DST_FAKE_RTABLE;
+ rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE;
rt->dst.ops = &fake_dst_ops;
}
@@ -506,7 +506,7 @@
1);
return 0;
}
- memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
skb->pkt_type = PACKET_HOST;
}
} else {
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index fcd1233..06811d7 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -46,12 +46,12 @@
struct bridge_id
{
unsigned char prio[2];
- unsigned char addr[6];
+ unsigned char addr[ETH_ALEN];
};
struct mac_addr
{
- unsigned char addr[6];
+ unsigned char addr[ETH_ALEN];
};
struct br_ip
@@ -104,6 +104,7 @@
mac_addr addr;
unsigned char is_local;
unsigned char is_static;
+ unsigned char added_by_user;
__u16 vlan_id;
};
@@ -348,7 +349,7 @@
netpoll_send_skb(np, skb);
}
-int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp);
+int br_netpoll_enable(struct net_bridge_port *p);
void br_netpoll_disable(struct net_bridge_port *p);
#else
static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
@@ -356,7 +357,7 @@
{
}
-static inline int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
+static inline int br_netpoll_enable(struct net_bridge_port *p)
{
return 0;
}
@@ -370,6 +371,9 @@
int br_fdb_init(void);
void br_fdb_fini(void);
void br_fdb_flush(struct net_bridge *br);
+void br_fdb_find_delete_local(struct net_bridge *br,
+ const struct net_bridge_port *p,
+ const unsigned char *addr, u16 vid);
void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr);
void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr);
void br_fdb_cleanup(unsigned long arg);
@@ -383,8 +387,7 @@
int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr, u16 vid);
void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
- const unsigned char *addr, u16 vid);
-int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vid);
+ const unsigned char *addr, u16 vid, bool added_by_user);
int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev, const unsigned char *addr);
@@ -584,6 +587,7 @@
int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags);
int br_vlan_delete(struct net_bridge *br, u16 vid);
void br_vlan_flush(struct net_bridge *br);
+bool br_vlan_find(struct net_bridge *br, u16 vid);
int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val);
int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags);
int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
@@ -665,6 +669,11 @@
{
}
+static inline bool br_vlan_find(struct net_bridge *br, u16 vid)
+{
+ return false;
+}
+
static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
{
return -EOPNOTSUPP;
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 656a6f3..189ba1e 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -194,6 +194,8 @@
wasroot = br_is_root_bridge(br);
+ br_fdb_change_mac_address(br, addr);
+
memcpy(oldaddr, br->bridge_id.addr, ETH_ALEN);
memcpy(br->bridge_id.addr, addr, ETH_ALEN);
memcpy(br->dev->dev_addr, addr, ETH_ALEN);
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 4ca4d0a..9151071 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -99,9 +99,9 @@
v->num_vlans--;
if (bitmap_empty(v->vlan_bitmap, VLAN_N_VID)) {
if (v->port_idx)
- rcu_assign_pointer(v->parent.port->vlan_info, NULL);
+ RCU_INIT_POINTER(v->parent.port->vlan_info, NULL);
else
- rcu_assign_pointer(v->parent.br->vlan_info, NULL);
+ RCU_INIT_POINTER(v->parent.br->vlan_info, NULL);
kfree_rcu(v, rcu);
}
return 0;
@@ -113,28 +113,12 @@
v->pvid = 0;
bitmap_zero(v->vlan_bitmap, VLAN_N_VID);
if (v->port_idx)
- rcu_assign_pointer(v->parent.port->vlan_info, NULL);
+ RCU_INIT_POINTER(v->parent.port->vlan_info, NULL);
else
- rcu_assign_pointer(v->parent.br->vlan_info, NULL);
+ RCU_INIT_POINTER(v->parent.br->vlan_info, NULL);
kfree_rcu(v, rcu);
}
-/* Strip the tag from the packet. Will return skb with tci set 0. */
-static struct sk_buff *br_vlan_untag(struct sk_buff *skb)
-{
- if (skb->protocol != htons(ETH_P_8021Q)) {
- skb->vlan_tci = 0;
- return skb;
- }
-
- skb->vlan_tci = 0;
- skb = vlan_untag(skb);
- if (skb)
- skb->vlan_tci = 0;
-
- return skb;
-}
-
struct sk_buff *br_handle_vlan(struct net_bridge *br,
const struct net_port_vlans *pv,
struct sk_buff *skb)
@@ -144,13 +128,27 @@
if (!br->vlan_enabled)
goto out;
+ /* Vlan filter table must be configured at this point. The
+ * only exception is the bridge is set in promisc mode and the
+ * packet is destined for the bridge device. In this case
+ * pass the packet as is.
+ */
+ if (!pv) {
+ if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) {
+ goto out;
+ } else {
+ kfree_skb(skb);
+ return NULL;
+ }
+ }
+
/* At this point, we know that the frame was filtered and contains
* a valid vlan id. If the vlan id is set in the untagged bitmap,
* send untagged; otherwise, send tagged.
*/
br_vlan_get_tag(skb, &vid);
if (test_bit(vid, pv->untagged_bitmap))
- skb = br_vlan_untag(skb);
+ skb->vlan_tci = 0;
out:
return skb;
@@ -174,6 +172,18 @@
if (!v)
return false;
+ /* If vlan tx offload is disabled on bridge device and frame was
+ * sent from vlan device on the bridge device, it does not have
+ * HW accelerated vlan tag.
+ */
+ if (unlikely(!vlan_tx_tag_present(skb) &&
+ (skb->protocol == htons(ETH_P_8021Q) ||
+ skb->protocol == htons(ETH_P_8021AD)))) {
+ skb = vlan_untag(skb);
+ if (unlikely(!skb))
+ return false;
+ }
+
err = br_vlan_get_tag(skb, vid);
if (!*vid) {
u16 pvid = br_get_pvid(v);
@@ -275,9 +285,7 @@
if (!pv)
return -EINVAL;
- spin_lock_bh(&br->hash_lock);
- fdb_delete_by_addr(br, br->dev->dev_addr, vid);
- spin_unlock_bh(&br->hash_lock);
+ br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid);
__vlan_del(pv, vid);
return 0;
@@ -295,6 +303,25 @@
__vlan_flush(pv);
}
+bool br_vlan_find(struct net_bridge *br, u16 vid)
+{
+ struct net_port_vlans *pv;
+ bool found = false;
+
+ rcu_read_lock();
+ pv = rcu_dereference(br->vlan_info);
+
+ if (!pv)
+ goto out;
+
+ if (test_bit(vid, pv->vlan_bitmap))
+ found = true;
+
+out:
+ rcu_read_unlock();
+ return found;
+}
+
int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val)
{
if (!rtnl_trylock())
@@ -359,9 +386,7 @@
if (!pv)
return -EINVAL;
- spin_lock_bh(&port->br->hash_lock);
- fdb_delete_by_addr(port->br, port->dev->dev_addr, vid);
- spin_unlock_bh(&port->br->hash_lock);
+ br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid);
return __vlan_del(pv, vid);
}
diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c
index 3fb3c84..9024283 100644
--- a/net/bridge/netfilter/ebt_among.c
+++ b/net/bridge/netfilter/ebt_among.c
@@ -28,7 +28,7 @@
uint32_t cmp[2] = { 0, 0 };
int key = ((const unsigned char *)mac)[5];
- memcpy(((char *) cmp) + 2, mac, ETH_ALEN);
+ ether_addr_copy(((char *) cmp) + 2, mac);
start = wh->table[key];
limit = wh->table[key + 1];
if (ip) {
diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c
index c59f7bf..4e0b0c3 100644
--- a/net/bridge/netfilter/ebt_dnat.c
+++ b/net/bridge/netfilter/ebt_dnat.c
@@ -22,7 +22,7 @@
if (!skb_make_writable(skb, 0))
return EBT_DROP;
- memcpy(eth_hdr(skb)->h_dest, info->mac, ETH_ALEN);
+ ether_addr_copy(eth_hdr(skb)->h_dest, info->mac);
return info->target;
}
diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c
index 46624bb..20396499 100644
--- a/net/bridge/netfilter/ebt_redirect.c
+++ b/net/bridge/netfilter/ebt_redirect.c
@@ -25,10 +25,10 @@
if (par->hooknum != NF_BR_BROUTING)
/* rcu_read_lock()ed by nf_hook_slow */
- memcpy(eth_hdr(skb)->h_dest,
- br_port_get_rcu(par->in)->br->dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(eth_hdr(skb)->h_dest,
+ br_port_get_rcu(par->in)->br->dev->dev_addr);
else
- memcpy(eth_hdr(skb)->h_dest, par->in->dev_addr, ETH_ALEN);
+ ether_addr_copy(eth_hdr(skb)->h_dest, par->in->dev_addr);
skb->pkt_type = PACKET_HOST;
return info->target;
}
diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c
index 0f6b118..e56ccd0 100644
--- a/net/bridge/netfilter/ebt_snat.c
+++ b/net/bridge/netfilter/ebt_snat.c
@@ -24,7 +24,7 @@
if (!skb_make_writable(skb, 0))
return EBT_DROP;
- memcpy(eth_hdr(skb)->h_source, info->mac, ETH_ALEN);
+ ether_addr_copy(eth_hdr(skb)->h_source, info->mac);
if (!(info->target & NAT_ARP_BIT) &&
eth_hdr(skb)->h_proto == htons(ETH_P_ARP)) {
const struct arphdr *ap;
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index 4dca159..edbca46 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -22,6 +22,7 @@
#include <net/pkt_sched.h>
#include <net/caif/caif_device.h>
#include <net/caif/caif_layer.h>
+#include <net/caif/caif_dev.h>
#include <net/caif/cfpkt.h>
#include <net/caif/cfcnfg.h>
#include <net/caif/cfserl.h>
diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c
index 353f793..a6e1154 100644
--- a/net/caif/cfsrvl.c
+++ b/net/caif/cfsrvl.c
@@ -15,6 +15,7 @@
#include <net/caif/caif_layer.h>
#include <net/caif/cfsrvl.h>
#include <net/caif/cfpkt.h>
+#include <net/caif/caif_dev.h>
#define SRVL_CTRL_PKT_SIZE 1
#define SRVL_FLOW_OFF 0x81
diff --git a/net/can/af_can.c b/net/can/af_can.c
index d249874..a27f8aa 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -57,6 +57,7 @@
#include <linux/skbuff.h>
#include <linux/can.h>
#include <linux/can/core.h>
+#include <linux/can/skb.h>
#include <linux/ratelimit.h>
#include <net/net_namespace.h>
#include <net/sock.h>
@@ -290,7 +291,7 @@
return -ENOMEM;
}
- newskb->sk = skb->sk;
+ can_skb_set_owner(newskb, skb->sk);
newskb->ip_summed = CHECKSUM_UNNECESSARY;
newskb->pkt_type = PACKET_BROADCAST;
}
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 3fc737b..dcb75c0 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -268,7 +268,7 @@
/* send with loopback */
skb->dev = dev;
- skb->sk = op->sk;
+ can_skb_set_owner(skb, op->sk);
can_send(skb, 1);
/* update statistics */
@@ -1223,7 +1223,7 @@
can_skb_prv(skb)->ifindex = dev->ifindex;
skb->dev = dev;
- skb->sk = sk;
+ can_skb_set_owner(skb, sk);
err = can_send(skb, 1); /* send with loopback */
dev_put(dev);
diff --git a/net/can/raw.c b/net/can/raw.c
index 07d72d8..081e81f 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -121,13 +121,9 @@
if (!ro->recv_own_msgs && oskb->sk == sk)
return;
- /* do not pass frames with DLC > 8 to a legacy socket */
- if (!ro->fd_frames) {
- struct canfd_frame *cfd = (struct canfd_frame *)oskb->data;
-
- if (unlikely(cfd->len > CAN_MAX_DLEN))
- return;
- }
+ /* do not pass non-CAN2.0 frames to a legacy socket */
+ if (!ro->fd_frames && oskb->len != CAN_MTU)
+ return;
/* clone the given skb to be able to enqueue it into the rcv queue */
skb = skb_clone(oskb, GFP_ATOMIC);
@@ -715,6 +711,7 @@
skb->dev = dev;
skb->sk = sk;
+ skb->priority = sk->sk_priority;
err = can_send(skb, ro->loopback);
@@ -737,9 +734,7 @@
struct msghdr *msg, size_t size, int flags)
{
struct sock *sk = sock->sk;
- struct raw_sock *ro = raw_sk(sk);
struct sk_buff *skb;
- int rxmtu;
int err = 0;
int noblock;
@@ -750,20 +745,10 @@
if (!skb)
return err;
- /*
- * when serving a legacy socket the DLC <= 8 is already checked inside
- * raw_rcv(). Now check if we need to pass a canfd_frame to a legacy
- * socket and cut the possible CANFD_MTU/CAN_MTU length to CAN_MTU
- */
- if (!ro->fd_frames)
- rxmtu = CAN_MTU;
- else
- rxmtu = skb->len;
-
- if (size < rxmtu)
+ if (size < skb->len)
msg->msg_flags |= MSG_TRUNC;
else
- size = rxmtu;
+ size = skb->len;
err = memcpy_toiovec(msg->msg_iov, skb->data, size);
if (err < 0) {
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 0676f2b..82750f9 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -2082,7 +2082,6 @@
pr_err("osdc handle_map corrupt msg\n");
ceph_msg_dump(msg);
up_write(&osdc->map_sem);
- return;
}
/*
@@ -2281,7 +2280,6 @@
bad:
pr_err("osdc handle_watch_notify corrupt msg\n");
- return;
}
/*
diff --git a/net/core/dev.c b/net/core/dev.c
index 3721db7..cf92139 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1245,7 +1245,7 @@
* If we don't do this there is a chance ndo_poll_controller
* or ndo_poll may be running while we open the device
*/
- netpoll_rx_disable(dev);
+ netpoll_poll_disable(dev);
ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
ret = notifier_to_errno(ret);
@@ -1260,7 +1260,7 @@
if (!ret && ops->ndo_open)
ret = ops->ndo_open(dev);
- netpoll_rx_enable(dev);
+ netpoll_poll_enable(dev);
if (ret)
clear_bit(__LINK_STATE_START, &dev->state);
@@ -1313,6 +1313,9 @@
might_sleep();
list_for_each_entry(dev, head, close_list) {
+ /* Temporarily disable netpoll until the interface is down */
+ netpoll_poll_disable(dev);
+
call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
clear_bit(__LINK_STATE_START, &dev->state);
@@ -1343,6 +1346,7 @@
dev->flags &= ~IFF_UP;
net_dmaengine_put();
+ netpoll_poll_enable(dev);
}
return 0;
@@ -1353,14 +1357,10 @@
int retval;
LIST_HEAD(single);
- /* Temporarily disable netpoll until the interface is down */
- netpoll_rx_disable(dev);
-
list_add(&dev->close_list, &single);
retval = __dev_close_many(&single);
list_del(&single);
- netpoll_rx_enable(dev);
return retval;
}
@@ -1398,14 +1398,9 @@
if (dev->flags & IFF_UP) {
LIST_HEAD(single);
- /* Block netpoll rx while the interface is going down */
- netpoll_rx_disable(dev);
-
list_add(&dev->close_list, &single);
dev_close_many(&single);
list_del(&single);
-
- netpoll_rx_enable(dev);
}
return 0;
}
@@ -2286,7 +2281,7 @@
}
EXPORT_SYMBOL(skb_checksum_help);
-__be16 skb_network_protocol(struct sk_buff *skb)
+__be16 skb_network_protocol(struct sk_buff *skb, int *depth)
{
__be16 type = skb->protocol;
int vlan_depth = ETH_HLEN;
@@ -2313,6 +2308,8 @@
vlan_depth += VLAN_HLEN;
}
+ *depth = vlan_depth;
+
return type;
}
@@ -2326,12 +2323,13 @@
{
struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
struct packet_offload *ptype;
- __be16 type = skb_network_protocol(skb);
+ int vlan_depth = skb->mac_len;
+ __be16 type = skb_network_protocol(skb, &vlan_depth);
if (unlikely(!type))
return ERR_PTR(-EINVAL);
- __skb_pull(skb, skb->mac_len);
+ __skb_pull(skb, vlan_depth);
rcu_read_lock();
list_for_each_entry_rcu(ptype, &offload_base, list) {
@@ -2420,7 +2418,7 @@
* 2. No high memory really exists on this machine.
*/
-static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
+static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_HIGHMEM
int i;
@@ -2495,34 +2493,38 @@
}
static netdev_features_t harmonize_features(struct sk_buff *skb,
- netdev_features_t features)
+ const struct net_device *dev,
+ netdev_features_t features)
{
+ int tmp;
+
if (skb->ip_summed != CHECKSUM_NONE &&
- !can_checksum_protocol(features, skb_network_protocol(skb))) {
+ !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) {
features &= ~NETIF_F_ALL_CSUM;
- } else if (illegal_highdma(skb->dev, skb)) {
+ } else if (illegal_highdma(dev, skb)) {
features &= ~NETIF_F_SG;
}
return features;
}
-netdev_features_t netif_skb_features(struct sk_buff *skb)
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+ const struct net_device *dev)
{
__be16 protocol = skb->protocol;
- netdev_features_t features = skb->dev->features;
+ netdev_features_t features = dev->features;
- if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+ if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs)
features &= ~NETIF_F_GSO_MASK;
if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
} else if (!vlan_tx_tag_present(skb)) {
- return harmonize_features(skb, features);
+ return harmonize_features(skb, dev, features);
}
- features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+ features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX);
if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))
@@ -2530,9 +2532,9 @@
NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
- return harmonize_features(skb, features);
+ return harmonize_features(skb, dev, features);
}
-EXPORT_SYMBOL(netif_skb_features);
+EXPORT_SYMBOL(netif_skb_dev_features);
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
@@ -2803,7 +2805,7 @@
* the BH enable code must have IRQs enabled so that it will not deadlock.
* --BLG
*/
-int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
+static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
{
struct net_device *dev = skb->dev;
struct netdev_queue *txq;
@@ -2878,6 +2880,7 @@
rc = -ENETDOWN;
rcu_read_unlock_bh();
+ atomic_long_inc(&dev->tx_dropped);
kfree_skb(skb);
return rc;
out:
@@ -2950,7 +2953,7 @@
flow_table = rcu_dereference(rxqueue->rps_flow_table);
if (!flow_table)
goto out;
- flow_id = skb->rxhash & flow_table->mask;
+ flow_id = skb_get_hash(skb) & flow_table->mask;
rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb,
rxq_index, flow_id);
if (rc < 0)
@@ -2984,6 +2987,7 @@
struct rps_sock_flow_table *sock_flow_table;
int cpu = -1;
u16 tcpu;
+ u32 hash;
if (skb_rx_queue_recorded(skb)) {
u16 index = skb_get_rx_queue(skb);
@@ -3012,7 +3016,8 @@
}
skb_reset_network_header(skb);
- if (!skb_get_hash(skb))
+ hash = skb_get_hash(skb);
+ if (!hash)
goto done;
flow_table = rcu_dereference(rxqueue->rps_flow_table);
@@ -3021,11 +3026,10 @@
u16 next_cpu;
struct rps_dev_flow *rflow;
- rflow = &flow_table->flows[skb->rxhash & flow_table->mask];
+ rflow = &flow_table->flows[hash & flow_table->mask];
tcpu = rflow->cpu;
- next_cpu = sock_flow_table->ents[skb->rxhash &
- sock_flow_table->mask];
+ next_cpu = sock_flow_table->ents[hash & sock_flow_table->mask];
/*
* If the desired CPU (where last recvmsg was done) is
@@ -3054,7 +3058,7 @@
}
if (map) {
- tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
+ tcpu = map->cpus[((u64) hash * map->len) >> 32];
if (cpu_online(tcpu)) {
cpu = tcpu;
@@ -3229,10 +3233,6 @@
{
int ret;
- /* if netpoll wants it, pretend we never saw it */
- if (netpoll_rx(skb))
- return NET_RX_DROP;
-
net_timestamp_check(netdev_tstamp_prequeue, skb);
trace_netif_rx(skb);
@@ -3493,11 +3493,11 @@
static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
{
switch (skb->protocol) {
- case __constant_htons(ETH_P_ARP):
- case __constant_htons(ETH_P_IP):
- case __constant_htons(ETH_P_IPV6):
- case __constant_htons(ETH_P_8021Q):
- case __constant_htons(ETH_P_8021AD):
+ case htons(ETH_P_ARP):
+ case htons(ETH_P_IP):
+ case htons(ETH_P_IPV6):
+ case htons(ETH_P_8021Q):
+ case htons(ETH_P_8021AD):
return true;
default:
return false;
@@ -3518,10 +3518,6 @@
trace_netif_receive_skb(skb);
- /* if we've gotten here through NAPI, check netpoll */
- if (netpoll_receive_skb(skb))
- goto out;
-
orig_dev = skb->dev;
skb_reset_network_header(skb);
@@ -3648,7 +3644,6 @@
unlock:
rcu_read_unlock();
-out:
return ret;
}
@@ -3873,7 +3868,7 @@
int same_flow;
enum gro_result ret;
- if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb))
+ if (!(skb->dev->features & NETIF_F_GRO))
goto normal;
if (skb_is_gso(skb) || skb_has_frag_list(skb))
@@ -4637,7 +4632,7 @@
}
EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu);
-int netdev_adjacent_sysfs_add(struct net_device *dev,
+static int netdev_adjacent_sysfs_add(struct net_device *dev,
struct net_device *adj_dev,
struct list_head *dev_list)
{
@@ -4647,7 +4642,7 @@
return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj),
linkname);
}
-void netdev_adjacent_sysfs_del(struct net_device *dev,
+static void netdev_adjacent_sysfs_del(struct net_device *dev,
char *name,
struct list_head *dev_list)
{
@@ -6244,6 +6239,7 @@
netdev_stats_to_stats64(storage, &dev->stats);
}
storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
+ storage->tx_dropped += atomic_long_read(&dev->tx_dropped);
return storage;
}
EXPORT_SYMBOL(dev_get_stats);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index f409e0b..185c341 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -745,6 +745,13 @@
attach_rules(&ops->rules_list, dev);
break;
+ case NETDEV_CHANGENAME:
+ list_for_each_entry(ops, &net->rules_ops, list) {
+ detach_rules(&ops->rules_list, dev);
+ attach_rules(&ops->rules_list, dev);
+ }
+ break;
+
case NETDEV_UNREGISTER:
list_for_each_entry(ops, &net->rules_ops, list)
detach_rules(&ops->rules_list, dev);
diff --git a/net/core/filter.c b/net/core/filter.c
index ad30d62..3733381 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1,11 +1,16 @@
/*
* Linux Socket Filter - Kernel level socket filtering
*
- * Author:
- * Jay Schulist <jschlst@samba.org>
+ * Based on the design of the Berkeley Packet Filter. The new
+ * internal format has been designed by PLUMgrid:
*
- * Based on the design of:
- * - The Berkeley Packet Filter
+ * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
+ *
+ * Authors:
+ *
+ * Jay Schulist <jschlst@samba.org>
+ * Alexei Starovoitov <ast@plumgrid.com>
+ * Daniel Borkmann <dborkman@redhat.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -108,304 +113,1045 @@
}
EXPORT_SYMBOL(sk_filter);
+/* Base function for offset calculation. Needs to go into .text section,
+ * therefore keeping it non-static as well; will also be used by JITs
+ * anyway later on, so do not let the compiler omit it.
+ */
+noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ return 0;
+}
+
/**
- * sk_run_filter - run a filter on a socket
- * @skb: buffer to run the filter on
+ * __sk_run_filter - run a filter on a given context
+ * @ctx: buffer to run the filter on
* @fentry: filter to apply
*
- * Decode and apply filter instructions to the skb->data.
- * Return length to keep, 0 for none. @skb is the data we are
- * filtering, @filter is the array of filter instructions.
- * Because all jumps are guaranteed to be before last instruction,
- * and last instruction guaranteed to be a RET, we dont need to check
- * flen. (We used to pass to this function the length of filter)
+ * Decode and apply filter instructions to the skb->data. Return length to
+ * keep, 0 for none. @ctx is the data we are operating on, @filter is the
+ * array of filter instructions.
*/
-unsigned int sk_run_filter(const struct sk_buff *skb,
- const struct sock_filter *fentry)
+unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn)
{
+ u64 stack[MAX_BPF_STACK / sizeof(u64)];
+ u64 regs[MAX_BPF_REG], tmp;
void *ptr;
- u32 A = 0; /* Accumulator */
- u32 X = 0; /* Index Register */
- u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */
- u32 tmp;
- int k;
+ int off;
- /*
- * Process array of filter instructions.
- */
- for (;; fentry++) {
-#if defined(CONFIG_X86_32)
-#define K (fentry->k)
-#else
- const u32 K = fentry->k;
-#endif
+#define K insn->imm
+#define A regs[insn->a_reg]
+#define X regs[insn->x_reg]
+#define R0 regs[0]
- switch (fentry->code) {
- case BPF_S_ALU_ADD_X:
- A += X;
- continue;
- case BPF_S_ALU_ADD_K:
- A += K;
- continue;
- case BPF_S_ALU_SUB_X:
- A -= X;
- continue;
- case BPF_S_ALU_SUB_K:
- A -= K;
- continue;
- case BPF_S_ALU_MUL_X:
- A *= X;
- continue;
- case BPF_S_ALU_MUL_K:
- A *= K;
- continue;
- case BPF_S_ALU_DIV_X:
- if (X == 0)
- return 0;
- A /= X;
- continue;
- case BPF_S_ALU_DIV_K:
- A /= K;
- continue;
- case BPF_S_ALU_MOD_X:
- if (X == 0)
- return 0;
- A %= X;
- continue;
- case BPF_S_ALU_MOD_K:
- A %= K;
- continue;
- case BPF_S_ALU_AND_X:
- A &= X;
- continue;
- case BPF_S_ALU_AND_K:
- A &= K;
- continue;
- case BPF_S_ALU_OR_X:
- A |= X;
- continue;
- case BPF_S_ALU_OR_K:
- A |= K;
- continue;
- case BPF_S_ANC_ALU_XOR_X:
- case BPF_S_ALU_XOR_X:
- A ^= X;
- continue;
- case BPF_S_ALU_XOR_K:
- A ^= K;
- continue;
- case BPF_S_ALU_LSH_X:
- A <<= X;
- continue;
- case BPF_S_ALU_LSH_K:
- A <<= K;
- continue;
- case BPF_S_ALU_RSH_X:
- A >>= X;
- continue;
- case BPF_S_ALU_RSH_K:
- A >>= K;
- continue;
- case BPF_S_ALU_NEG:
- A = -A;
- continue;
- case BPF_S_JMP_JA:
- fentry += K;
- continue;
- case BPF_S_JMP_JGT_K:
- fentry += (A > K) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JGE_K:
- fentry += (A >= K) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JEQ_K:
- fentry += (A == K) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JSET_K:
- fentry += (A & K) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JGT_X:
- fentry += (A > X) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JGE_X:
- fentry += (A >= X) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JEQ_X:
- fentry += (A == X) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JSET_X:
- fentry += (A & X) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_LD_W_ABS:
- k = K;
-load_w:
- ptr = load_pointer(skb, k, 4, &tmp);
- if (ptr != NULL) {
- A = get_unaligned_be32(ptr);
- continue;
- }
- return 0;
- case BPF_S_LD_H_ABS:
- k = K;
-load_h:
- ptr = load_pointer(skb, k, 2, &tmp);
- if (ptr != NULL) {
- A = get_unaligned_be16(ptr);
- continue;
- }
- return 0;
- case BPF_S_LD_B_ABS:
- k = K;
-load_b:
- ptr = load_pointer(skb, k, 1, &tmp);
- if (ptr != NULL) {
- A = *(u8 *)ptr;
- continue;
- }
- return 0;
- case BPF_S_LD_W_LEN:
- A = skb->len;
- continue;
- case BPF_S_LDX_W_LEN:
- X = skb->len;
- continue;
- case BPF_S_LD_W_IND:
- k = X + K;
- goto load_w;
- case BPF_S_LD_H_IND:
- k = X + K;
- goto load_h;
- case BPF_S_LD_B_IND:
- k = X + K;
- goto load_b;
- case BPF_S_LDX_B_MSH:
- ptr = load_pointer(skb, K, 1, &tmp);
- if (ptr != NULL) {
- X = (*(u8 *)ptr & 0xf) << 2;
- continue;
- }
- return 0;
- case BPF_S_LD_IMM:
- A = K;
- continue;
- case BPF_S_LDX_IMM:
- X = K;
- continue;
- case BPF_S_LD_MEM:
- A = mem[K];
- continue;
- case BPF_S_LDX_MEM:
- X = mem[K];
- continue;
- case BPF_S_MISC_TAX:
- X = A;
- continue;
- case BPF_S_MISC_TXA:
- A = X;
- continue;
- case BPF_S_RET_K:
- return K;
- case BPF_S_RET_A:
- return A;
- case BPF_S_ST:
- mem[K] = A;
- continue;
- case BPF_S_STX:
- mem[K] = X;
- continue;
- case BPF_S_ANC_PROTOCOL:
- A = ntohs(skb->protocol);
- continue;
- case BPF_S_ANC_PKTTYPE:
- A = skb->pkt_type;
- continue;
- case BPF_S_ANC_IFINDEX:
- if (!skb->dev)
- return 0;
- A = skb->dev->ifindex;
- continue;
- case BPF_S_ANC_MARK:
- A = skb->mark;
- continue;
- case BPF_S_ANC_QUEUE:
- A = skb->queue_mapping;
- continue;
- case BPF_S_ANC_HATYPE:
- if (!skb->dev)
- return 0;
- A = skb->dev->type;
- continue;
- case BPF_S_ANC_RXHASH:
- A = skb->rxhash;
- continue;
- case BPF_S_ANC_CPU:
- A = raw_smp_processor_id();
- continue;
- case BPF_S_ANC_VLAN_TAG:
- A = vlan_tx_tag_get(skb);
- continue;
- case BPF_S_ANC_VLAN_TAG_PRESENT:
- A = !!vlan_tx_tag_present(skb);
- continue;
- case BPF_S_ANC_PAY_OFFSET:
- A = __skb_get_poff(skb);
- continue;
- case BPF_S_ANC_NLATTR: {
- struct nlattr *nla;
+#define CONT ({insn++; goto select_insn; })
+#define CONT_JMP ({insn++; goto select_insn; })
- if (skb_is_nonlinear(skb))
- return 0;
- if (A > skb->len - sizeof(struct nlattr))
- return 0;
+ static const void *jumptable[256] = {
+ [0 ... 255] = &&default_label,
+ /* Now overwrite non-defaults ... */
+#define DL(A, B, C) [A|B|C] = &&A##_##B##_##C
+ DL(BPF_ALU, BPF_ADD, BPF_X),
+ DL(BPF_ALU, BPF_ADD, BPF_K),
+ DL(BPF_ALU, BPF_SUB, BPF_X),
+ DL(BPF_ALU, BPF_SUB, BPF_K),
+ DL(BPF_ALU, BPF_AND, BPF_X),
+ DL(BPF_ALU, BPF_AND, BPF_K),
+ DL(BPF_ALU, BPF_OR, BPF_X),
+ DL(BPF_ALU, BPF_OR, BPF_K),
+ DL(BPF_ALU, BPF_LSH, BPF_X),
+ DL(BPF_ALU, BPF_LSH, BPF_K),
+ DL(BPF_ALU, BPF_RSH, BPF_X),
+ DL(BPF_ALU, BPF_RSH, BPF_K),
+ DL(BPF_ALU, BPF_XOR, BPF_X),
+ DL(BPF_ALU, BPF_XOR, BPF_K),
+ DL(BPF_ALU, BPF_MUL, BPF_X),
+ DL(BPF_ALU, BPF_MUL, BPF_K),
+ DL(BPF_ALU, BPF_MOV, BPF_X),
+ DL(BPF_ALU, BPF_MOV, BPF_K),
+ DL(BPF_ALU, BPF_DIV, BPF_X),
+ DL(BPF_ALU, BPF_DIV, BPF_K),
+ DL(BPF_ALU, BPF_MOD, BPF_X),
+ DL(BPF_ALU, BPF_MOD, BPF_K),
+ DL(BPF_ALU, BPF_NEG, 0),
+ DL(BPF_ALU, BPF_END, BPF_TO_BE),
+ DL(BPF_ALU, BPF_END, BPF_TO_LE),
+ DL(BPF_ALU64, BPF_ADD, BPF_X),
+ DL(BPF_ALU64, BPF_ADD, BPF_K),
+ DL(BPF_ALU64, BPF_SUB, BPF_X),
+ DL(BPF_ALU64, BPF_SUB, BPF_K),
+ DL(BPF_ALU64, BPF_AND, BPF_X),
+ DL(BPF_ALU64, BPF_AND, BPF_K),
+ DL(BPF_ALU64, BPF_OR, BPF_X),
+ DL(BPF_ALU64, BPF_OR, BPF_K),
+ DL(BPF_ALU64, BPF_LSH, BPF_X),
+ DL(BPF_ALU64, BPF_LSH, BPF_K),
+ DL(BPF_ALU64, BPF_RSH, BPF_X),
+ DL(BPF_ALU64, BPF_RSH, BPF_K),
+ DL(BPF_ALU64, BPF_XOR, BPF_X),
+ DL(BPF_ALU64, BPF_XOR, BPF_K),
+ DL(BPF_ALU64, BPF_MUL, BPF_X),
+ DL(BPF_ALU64, BPF_MUL, BPF_K),
+ DL(BPF_ALU64, BPF_MOV, BPF_X),
+ DL(BPF_ALU64, BPF_MOV, BPF_K),
+ DL(BPF_ALU64, BPF_ARSH, BPF_X),
+ DL(BPF_ALU64, BPF_ARSH, BPF_K),
+ DL(BPF_ALU64, BPF_DIV, BPF_X),
+ DL(BPF_ALU64, BPF_DIV, BPF_K),
+ DL(BPF_ALU64, BPF_MOD, BPF_X),
+ DL(BPF_ALU64, BPF_MOD, BPF_K),
+ DL(BPF_ALU64, BPF_NEG, 0),
+ DL(BPF_JMP, BPF_CALL, 0),
+ DL(BPF_JMP, BPF_JA, 0),
+ DL(BPF_JMP, BPF_JEQ, BPF_X),
+ DL(BPF_JMP, BPF_JEQ, BPF_K),
+ DL(BPF_JMP, BPF_JNE, BPF_X),
+ DL(BPF_JMP, BPF_JNE, BPF_K),
+ DL(BPF_JMP, BPF_JGT, BPF_X),
+ DL(BPF_JMP, BPF_JGT, BPF_K),
+ DL(BPF_JMP, BPF_JGE, BPF_X),
+ DL(BPF_JMP, BPF_JGE, BPF_K),
+ DL(BPF_JMP, BPF_JSGT, BPF_X),
+ DL(BPF_JMP, BPF_JSGT, BPF_K),
+ DL(BPF_JMP, BPF_JSGE, BPF_X),
+ DL(BPF_JMP, BPF_JSGE, BPF_K),
+ DL(BPF_JMP, BPF_JSET, BPF_X),
+ DL(BPF_JMP, BPF_JSET, BPF_K),
+ DL(BPF_JMP, BPF_EXIT, 0),
+ DL(BPF_STX, BPF_MEM, BPF_B),
+ DL(BPF_STX, BPF_MEM, BPF_H),
+ DL(BPF_STX, BPF_MEM, BPF_W),
+ DL(BPF_STX, BPF_MEM, BPF_DW),
+ DL(BPF_STX, BPF_XADD, BPF_W),
+ DL(BPF_STX, BPF_XADD, BPF_DW),
+ DL(BPF_ST, BPF_MEM, BPF_B),
+ DL(BPF_ST, BPF_MEM, BPF_H),
+ DL(BPF_ST, BPF_MEM, BPF_W),
+ DL(BPF_ST, BPF_MEM, BPF_DW),
+ DL(BPF_LDX, BPF_MEM, BPF_B),
+ DL(BPF_LDX, BPF_MEM, BPF_H),
+ DL(BPF_LDX, BPF_MEM, BPF_W),
+ DL(BPF_LDX, BPF_MEM, BPF_DW),
+ DL(BPF_LD, BPF_ABS, BPF_W),
+ DL(BPF_LD, BPF_ABS, BPF_H),
+ DL(BPF_LD, BPF_ABS, BPF_B),
+ DL(BPF_LD, BPF_IND, BPF_W),
+ DL(BPF_LD, BPF_IND, BPF_H),
+ DL(BPF_LD, BPF_IND, BPF_B),
+#undef DL
+ };
- nla = nla_find((struct nlattr *)&skb->data[A],
- skb->len - A, X);
- if (nla)
- A = (void *)nla - (void *)skb->data;
- else
- A = 0;
- continue;
+ regs[FP_REG] = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
+ regs[ARG1_REG] = (u64) (unsigned long) ctx;
+
+select_insn:
+ goto *jumptable[insn->code];
+
+ /* ALU */
+#define ALU(OPCODE, OP) \
+ BPF_ALU64_##OPCODE##_BPF_X: \
+ A = A OP X; \
+ CONT; \
+ BPF_ALU_##OPCODE##_BPF_X: \
+ A = (u32) A OP (u32) X; \
+ CONT; \
+ BPF_ALU64_##OPCODE##_BPF_K: \
+ A = A OP K; \
+ CONT; \
+ BPF_ALU_##OPCODE##_BPF_K: \
+ A = (u32) A OP (u32) K; \
+ CONT;
+
+ ALU(BPF_ADD, +)
+ ALU(BPF_SUB, -)
+ ALU(BPF_AND, &)
+ ALU(BPF_OR, |)
+ ALU(BPF_LSH, <<)
+ ALU(BPF_RSH, >>)
+ ALU(BPF_XOR, ^)
+ ALU(BPF_MUL, *)
+#undef ALU
+ BPF_ALU_BPF_NEG_0:
+ A = (u32) -A;
+ CONT;
+ BPF_ALU64_BPF_NEG_0:
+ A = -A;
+ CONT;
+ BPF_ALU_BPF_MOV_BPF_X:
+ A = (u32) X;
+ CONT;
+ BPF_ALU_BPF_MOV_BPF_K:
+ A = (u32) K;
+ CONT;
+ BPF_ALU64_BPF_MOV_BPF_X:
+ A = X;
+ CONT;
+ BPF_ALU64_BPF_MOV_BPF_K:
+ A = K;
+ CONT;
+ BPF_ALU64_BPF_ARSH_BPF_X:
+ (*(s64 *) &A) >>= X;
+ CONT;
+ BPF_ALU64_BPF_ARSH_BPF_K:
+ (*(s64 *) &A) >>= K;
+ CONT;
+ BPF_ALU64_BPF_MOD_BPF_X:
+ tmp = A;
+ if (X)
+ A = do_div(tmp, X);
+ CONT;
+ BPF_ALU_BPF_MOD_BPF_X:
+ tmp = (u32) A;
+ if (X)
+ A = do_div(tmp, (u32) X);
+ CONT;
+ BPF_ALU64_BPF_MOD_BPF_K:
+ tmp = A;
+ if (K)
+ A = do_div(tmp, K);
+ CONT;
+ BPF_ALU_BPF_MOD_BPF_K:
+ tmp = (u32) A;
+ if (K)
+ A = do_div(tmp, (u32) K);
+ CONT;
+ BPF_ALU64_BPF_DIV_BPF_X:
+ if (X)
+ do_div(A, X);
+ CONT;
+ BPF_ALU_BPF_DIV_BPF_X:
+ tmp = (u32) A;
+ if (X)
+ do_div(tmp, (u32) X);
+ A = (u32) tmp;
+ CONT;
+ BPF_ALU64_BPF_DIV_BPF_K:
+ if (K)
+ do_div(A, K);
+ CONT;
+ BPF_ALU_BPF_DIV_BPF_K:
+ tmp = (u32) A;
+ if (K)
+ do_div(tmp, (u32) K);
+ A = (u32) tmp;
+ CONT;
+ BPF_ALU_BPF_END_BPF_TO_BE:
+ switch (K) {
+ case 16:
+ A = (__force u16) cpu_to_be16(A);
+ break;
+ case 32:
+ A = (__force u32) cpu_to_be32(A);
+ break;
+ case 64:
+ A = (__force u64) cpu_to_be64(A);
+ break;
}
- case BPF_S_ANC_NLATTR_NEST: {
- struct nlattr *nla;
-
- if (skb_is_nonlinear(skb))
- return 0;
- if (A > skb->len - sizeof(struct nlattr))
- return 0;
-
- nla = (struct nlattr *)&skb->data[A];
- if (nla->nla_len > A - skb->len)
- return 0;
-
- nla = nla_find_nested(nla, X);
- if (nla)
- A = (void *)nla - (void *)skb->data;
- else
- A = 0;
- continue;
+ CONT;
+ BPF_ALU_BPF_END_BPF_TO_LE:
+ switch (K) {
+ case 16:
+ A = (__force u16) cpu_to_le16(A);
+ break;
+ case 32:
+ A = (__force u32) cpu_to_le32(A);
+ break;
+ case 64:
+ A = (__force u64) cpu_to_le64(A);
+ break;
}
-#ifdef CONFIG_SECCOMP_FILTER
- case BPF_S_ANC_SECCOMP_LD_W:
- A = seccomp_bpf_load(fentry->k);
- continue;
-#endif
- default:
- WARN_RATELIMIT(1, "Unknown code:%u jt:%u tf:%u k:%u\n",
- fentry->code, fentry->jt,
- fentry->jf, fentry->k);
- return 0;
+ CONT;
+
+ /* CALL */
+ BPF_JMP_BPF_CALL_0:
+ /* Function call scratches R1-R5 registers, preserves R6-R9,
+ * and stores return value into R0.
+ */
+ R0 = (__bpf_call_base + insn->imm)(regs[1], regs[2], regs[3],
+ regs[4], regs[5]);
+ CONT;
+
+ /* JMP */
+ BPF_JMP_BPF_JA_0:
+ insn += insn->off;
+ CONT;
+ BPF_JMP_BPF_JEQ_BPF_X:
+ if (A == X) {
+ insn += insn->off;
+ CONT_JMP;
}
+ CONT;
+ BPF_JMP_BPF_JEQ_BPF_K:
+ if (A == K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JNE_BPF_X:
+ if (A != X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JNE_BPF_K:
+ if (A != K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JGT_BPF_X:
+ if (A > X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JGT_BPF_K:
+ if (A > K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JGE_BPF_X:
+ if (A >= X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JGE_BPF_K:
+ if (A >= K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JSGT_BPF_X:
+ if (((s64)A) > ((s64)X)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JSGT_BPF_K:
+ if (((s64)A) > ((s64)K)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JSGE_BPF_X:
+ if (((s64)A) >= ((s64)X)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JSGE_BPF_K:
+ if (((s64)A) >= ((s64)K)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JSET_BPF_X:
+ if (A & X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JSET_BPF_K:
+ if (A & K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_EXIT_0:
+ return R0;
+
+ /* STX and ST and LDX*/
+#define LDST(SIZEOP, SIZE) \
+ BPF_STX_BPF_MEM_##SIZEOP: \
+ *(SIZE *)(unsigned long) (A + insn->off) = X; \
+ CONT; \
+ BPF_ST_BPF_MEM_##SIZEOP: \
+ *(SIZE *)(unsigned long) (A + insn->off) = K; \
+ CONT; \
+ BPF_LDX_BPF_MEM_##SIZEOP: \
+ A = *(SIZE *)(unsigned long) (X + insn->off); \
+ CONT;
+
+ LDST(BPF_B, u8)
+ LDST(BPF_H, u16)
+ LDST(BPF_W, u32)
+ LDST(BPF_DW, u64)
+#undef LDST
+ BPF_STX_BPF_XADD_BPF_W: /* lock xadd *(u32 *)(A + insn->off) += X */
+ atomic_add((u32) X, (atomic_t *)(unsigned long)
+ (A + insn->off));
+ CONT;
+ BPF_STX_BPF_XADD_BPF_DW: /* lock xadd *(u64 *)(A + insn->off) += X */
+ atomic64_add((u64) X, (atomic64_t *)(unsigned long)
+ (A + insn->off));
+ CONT;
+ BPF_LD_BPF_ABS_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + K)) */
+ off = K;
+load_word:
+ /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only
+ * appearing in the programs where ctx == skb. All programs
+ * keep 'ctx' in regs[CTX_REG] == R6, sk_convert_filter()
+ * saves it in R6, internal BPF verifier will check that
+ * R6 == ctx.
+ *
+ * BPF_ABS and BPF_IND are wrappers of function calls, so
+ * they scratch R1-R5 registers, preserve R6-R9, and store
+ * return value into R0.
+ *
+ * Implicit input:
+ * ctx
+ *
+ * Explicit input:
+ * X == any register
+ * K == 32-bit immediate
+ *
+ * Output:
+ * R0 - 8/16/32-bit skb data converted to cpu endianness
+ */
+ ptr = load_pointer((struct sk_buff *) ctx, off, 4, &tmp);
+ if (likely(ptr != NULL)) {
+ R0 = get_unaligned_be32(ptr);
+ CONT;
+ }
+ return 0;
+ BPF_LD_BPF_ABS_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + K)) */
+ off = K;
+load_half:
+ ptr = load_pointer((struct sk_buff *) ctx, off, 2, &tmp);
+ if (likely(ptr != NULL)) {
+ R0 = get_unaligned_be16(ptr);
+ CONT;
+ }
+ return 0;
+ BPF_LD_BPF_ABS_BPF_B: /* R0 = *(u8 *) (ctx + K) */
+ off = K;
+load_byte:
+ ptr = load_pointer((struct sk_buff *) ctx, off, 1, &tmp);
+ if (likely(ptr != NULL)) {
+ R0 = *(u8 *)ptr;
+ CONT;
+ }
+ return 0;
+ BPF_LD_BPF_IND_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + X + K)) */
+ off = K + X;
+ goto load_word;
+ BPF_LD_BPF_IND_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + X + K)) */
+ off = K + X;
+ goto load_half;
+ BPF_LD_BPF_IND_BPF_B: /* R0 = *(u8 *) (skb->data + X + K) */
+ off = K + X;
+ goto load_byte;
+
+ default_label:
+ /* If we ever reach this, we have a bug somewhere. */
+ WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
+ return 0;
+#undef CONT_JMP
+#undef CONT
+
+#undef R0
+#undef X
+#undef A
+#undef K
+}
+
+u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx,
+ const struct sock_filter_int *insni)
+ __attribute__ ((alias ("__sk_run_filter")));
+
+u32 sk_run_filter_int_skb(const struct sk_buff *ctx,
+ const struct sock_filter_int *insni)
+ __attribute__ ((alias ("__sk_run_filter")));
+EXPORT_SYMBOL_GPL(sk_run_filter_int_skb);
+
+/* Helper to find the offset of pkt_type in sk_buff structure. We want
+ * to make sure its still a 3bit field starting at a byte boundary;
+ * taken from arch/x86/net/bpf_jit_comp.c.
+ */
+#define PKT_TYPE_MAX 7
+static unsigned int pkt_type_offset(void)
+{
+ struct sk_buff skb_probe = { .pkt_type = ~0, };
+ u8 *ct = (u8 *) &skb_probe;
+ unsigned int off;
+
+ for (off = 0; off < sizeof(struct sk_buff); off++) {
+ if (ct[off] == PKT_TYPE_MAX)
+ return off;
}
+ pr_err_once("Please fix %s, as pkt_type couldn't be found!\n", __func__);
+ return -1;
+}
+
+static u64 __skb_get_pay_offset(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *)(long) ctx;
+
+ return __skb_get_poff(skb);
+}
+
+static u64 __skb_get_nlattr(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *)(long) ctx;
+ struct nlattr *nla;
+
+ if (skb_is_nonlinear(skb))
+ return 0;
+
+ if (A > skb->len - sizeof(struct nlattr))
+ return 0;
+
+ nla = nla_find((struct nlattr *) &skb->data[A], skb->len - A, X);
+ if (nla)
+ return (void *) nla - (void *) skb->data;
+
return 0;
}
-EXPORT_SYMBOL(sk_run_filter);
-/*
- * Security :
+static u64 __skb_get_nlattr_nest(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *)(long) ctx;
+ struct nlattr *nla;
+
+ if (skb_is_nonlinear(skb))
+ return 0;
+
+ if (A > skb->len - sizeof(struct nlattr))
+ return 0;
+
+ nla = (struct nlattr *) &skb->data[A];
+ if (nla->nla_len > A - skb->len)
+ return 0;
+
+ nla = nla_find_nested(nla, X);
+ if (nla)
+ return (void *) nla - (void *) skb->data;
+
+ return 0;
+}
+
+static u64 __get_raw_cpu_id(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+{
+ return raw_smp_processor_id();
+}
+
+/* Register mappings for user programs. */
+#define A_REG 0
+#define X_REG 7
+#define TMP_REG 8
+#define ARG2_REG 2
+#define ARG3_REG 3
+
+static bool convert_bpf_extensions(struct sock_filter *fp,
+ struct sock_filter_int **insnp)
+{
+ struct sock_filter_int *insn = *insnp;
+
+ switch (fp->k) {
+ case SKF_AD_OFF + SKF_AD_PROTOCOL:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
+
+ insn->code = BPF_LDX | BPF_MEM | BPF_H;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, protocol);
+ insn++;
+
+ /* A = ntohs(A) [emitting a nop or swap16] */
+ insn->code = BPF_ALU | BPF_END | BPF_FROM_BE;
+ insn->a_reg = A_REG;
+ insn->imm = 16;
+ break;
+
+ case SKF_AD_OFF + SKF_AD_PKTTYPE:
+ insn->code = BPF_LDX | BPF_MEM | BPF_B;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = pkt_type_offset();
+ if (insn->off < 0)
+ return false;
+ insn++;
+
+ insn->code = BPF_ALU | BPF_AND | BPF_K;
+ insn->a_reg = A_REG;
+ insn->imm = PKT_TYPE_MAX;
+ break;
+
+ case SKF_AD_OFF + SKF_AD_IFINDEX:
+ case SKF_AD_OFF + SKF_AD_HATYPE:
+ if (FIELD_SIZEOF(struct sk_buff, dev) == 8)
+ insn->code = BPF_LDX | BPF_MEM | BPF_DW;
+ else
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = TMP_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, dev);
+ insn++;
+
+ insn->code = BPF_JMP | BPF_JNE | BPF_K;
+ insn->a_reg = TMP_REG;
+ insn->imm = 0;
+ insn->off = 1;
+ insn++;
+
+ insn->code = BPF_JMP | BPF_EXIT;
+ insn++;
+
+ BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
+ BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2);
+
+ insn->a_reg = A_REG;
+ insn->x_reg = TMP_REG;
+
+ if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) {
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->off = offsetof(struct net_device, ifindex);
+ } else {
+ insn->code = BPF_LDX | BPF_MEM | BPF_H;
+ insn->off = offsetof(struct net_device, type);
+ }
+ break;
+
+ case SKF_AD_OFF + SKF_AD_MARK:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, mark);
+ break;
+
+ case SKF_AD_OFF + SKF_AD_RXHASH:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, hash);
+ break;
+
+ case SKF_AD_OFF + SKF_AD_QUEUE:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
+
+ insn->code = BPF_LDX | BPF_MEM | BPF_H;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, queue_mapping);
+ break;
+
+ case SKF_AD_OFF + SKF_AD_VLAN_TAG:
+ case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
+
+ insn->code = BPF_LDX | BPF_MEM | BPF_H;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, vlan_tci);
+ insn++;
+
+ BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+
+ if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) {
+ insn->code = BPF_ALU | BPF_AND | BPF_K;
+ insn->a_reg = A_REG;
+ insn->imm = ~VLAN_TAG_PRESENT;
+ } else {
+ insn->code = BPF_ALU | BPF_RSH | BPF_K;
+ insn->a_reg = A_REG;
+ insn->imm = 12;
+ insn++;
+
+ insn->code = BPF_ALU | BPF_AND | BPF_K;
+ insn->a_reg = A_REG;
+ insn->imm = 1;
+ }
+ break;
+
+ case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
+ case SKF_AD_OFF + SKF_AD_NLATTR:
+ case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
+ case SKF_AD_OFF + SKF_AD_CPU:
+ /* arg1 = ctx */
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = ARG1_REG;
+ insn->x_reg = CTX_REG;
+ insn++;
+
+ /* arg2 = A */
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = ARG2_REG;
+ insn->x_reg = A_REG;
+ insn++;
+
+ /* arg3 = X */
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = ARG3_REG;
+ insn->x_reg = X_REG;
+ insn++;
+
+ /* Emit call(ctx, arg2=A, arg3=X) */
+ insn->code = BPF_JMP | BPF_CALL;
+ switch (fp->k) {
+ case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
+ insn->imm = __skb_get_pay_offset - __bpf_call_base;
+ break;
+ case SKF_AD_OFF + SKF_AD_NLATTR:
+ insn->imm = __skb_get_nlattr - __bpf_call_base;
+ break;
+ case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
+ insn->imm = __skb_get_nlattr_nest - __bpf_call_base;
+ break;
+ case SKF_AD_OFF + SKF_AD_CPU:
+ insn->imm = __get_raw_cpu_id - __bpf_call_base;
+ break;
+ }
+ break;
+
+ case SKF_AD_OFF + SKF_AD_ALU_XOR_X:
+ insn->code = BPF_ALU | BPF_XOR | BPF_X;
+ insn->a_reg = A_REG;
+ insn->x_reg = X_REG;
+ break;
+
+ default:
+ /* This is just a dummy call to avoid letting the compiler
+ * evict __bpf_call_base() as an optimization. Placed here
+ * where no-one bothers.
+ */
+ BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0);
+ return false;
+ }
+
+ *insnp = insn;
+ return true;
+}
+
+/**
+ * sk_convert_filter - convert filter program
+ * @prog: the user passed filter program
+ * @len: the length of the user passed filter program
+ * @new_prog: buffer where converted program will be stored
+ * @new_len: pointer to store length of converted program
+ *
+ * Remap 'sock_filter' style BPF instruction set to 'sock_filter_ext' style.
+ * Conversion workflow:
+ *
+ * 1) First pass for calculating the new program length:
+ * sk_convert_filter(old_prog, old_len, NULL, &new_len)
+ *
+ * 2) 2nd pass to remap in two passes: 1st pass finds new
+ * jump offsets, 2nd pass remapping:
+ * new_prog = kmalloc(sizeof(struct sock_filter_int) * new_len);
+ * sk_convert_filter(old_prog, old_len, new_prog, &new_len);
+ *
+ * User BPF's register A is mapped to our BPF register 6, user BPF
+ * register X is mapped to BPF register 7; frame pointer is always
+ * register 10; Context 'void *ctx' is stored in register 1, that is,
+ * for socket filters: ctx == 'struct sk_buff *', for seccomp:
+ * ctx == 'struct seccomp_data *'.
+ */
+int sk_convert_filter(struct sock_filter *prog, int len,
+ struct sock_filter_int *new_prog, int *new_len)
+{
+ int new_flen = 0, pass = 0, target, i;
+ struct sock_filter_int *new_insn;
+ struct sock_filter *fp;
+ int *addrs = NULL;
+ u8 bpf_src;
+
+ BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK);
+ BUILD_BUG_ON(FP_REG + 1 != MAX_BPF_REG);
+
+ if (len <= 0 || len >= BPF_MAXINSNS)
+ return -EINVAL;
+
+ if (new_prog) {
+ addrs = kzalloc(len * sizeof(*addrs), GFP_KERNEL);
+ if (!addrs)
+ return -ENOMEM;
+ }
+
+do_pass:
+ new_insn = new_prog;
+ fp = prog;
+
+ if (new_insn) {
+ new_insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ new_insn->a_reg = CTX_REG;
+ new_insn->x_reg = ARG1_REG;
+ }
+ new_insn++;
+
+ for (i = 0; i < len; fp++, i++) {
+ struct sock_filter_int tmp_insns[6] = { };
+ struct sock_filter_int *insn = tmp_insns;
+
+ if (addrs)
+ addrs[i] = new_insn - new_prog;
+
+ switch (fp->code) {
+ /* All arithmetic insns and skb loads map as-is. */
+ case BPF_ALU | BPF_ADD | BPF_X:
+ case BPF_ALU | BPF_ADD | BPF_K:
+ case BPF_ALU | BPF_SUB | BPF_X:
+ case BPF_ALU | BPF_SUB | BPF_K:
+ case BPF_ALU | BPF_AND | BPF_X:
+ case BPF_ALU | BPF_AND | BPF_K:
+ case BPF_ALU | BPF_OR | BPF_X:
+ case BPF_ALU | BPF_OR | BPF_K:
+ case BPF_ALU | BPF_LSH | BPF_X:
+ case BPF_ALU | BPF_LSH | BPF_K:
+ case BPF_ALU | BPF_RSH | BPF_X:
+ case BPF_ALU | BPF_RSH | BPF_K:
+ case BPF_ALU | BPF_XOR | BPF_X:
+ case BPF_ALU | BPF_XOR | BPF_K:
+ case BPF_ALU | BPF_MUL | BPF_X:
+ case BPF_ALU | BPF_MUL | BPF_K:
+ case BPF_ALU | BPF_DIV | BPF_X:
+ case BPF_ALU | BPF_DIV | BPF_K:
+ case BPF_ALU | BPF_MOD | BPF_X:
+ case BPF_ALU | BPF_MOD | BPF_K:
+ case BPF_ALU | BPF_NEG:
+ case BPF_LD | BPF_ABS | BPF_W:
+ case BPF_LD | BPF_ABS | BPF_H:
+ case BPF_LD | BPF_ABS | BPF_B:
+ case BPF_LD | BPF_IND | BPF_W:
+ case BPF_LD | BPF_IND | BPF_H:
+ case BPF_LD | BPF_IND | BPF_B:
+ /* Check for overloaded BPF extension and
+ * directly convert it if found, otherwise
+ * just move on with mapping.
+ */
+ if (BPF_CLASS(fp->code) == BPF_LD &&
+ BPF_MODE(fp->code) == BPF_ABS &&
+ convert_bpf_extensions(fp, &insn))
+ break;
+
+ insn->code = fp->code;
+ insn->a_reg = A_REG;
+ insn->x_reg = X_REG;
+ insn->imm = fp->k;
+ break;
+
+ /* Jump opcodes map as-is, but offsets need adjustment. */
+ case BPF_JMP | BPF_JA:
+ target = i + fp->k + 1;
+ insn->code = fp->code;
+#define EMIT_JMP \
+ do { \
+ if (target >= len || target < 0) \
+ goto err; \
+ insn->off = addrs ? addrs[target] - addrs[i] - 1 : 0; \
+ /* Adjust pc relative offset for 2nd or 3rd insn. */ \
+ insn->off -= insn - tmp_insns; \
+ } while (0)
+
+ EMIT_JMP;
+ break;
+
+ case BPF_JMP | BPF_JEQ | BPF_K:
+ case BPF_JMP | BPF_JEQ | BPF_X:
+ case BPF_JMP | BPF_JSET | BPF_K:
+ case BPF_JMP | BPF_JSET | BPF_X:
+ case BPF_JMP | BPF_JGT | BPF_K:
+ case BPF_JMP | BPF_JGT | BPF_X:
+ case BPF_JMP | BPF_JGE | BPF_K:
+ case BPF_JMP | BPF_JGE | BPF_X:
+ if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) {
+ /* BPF immediates are signed, zero extend
+ * immediate into tmp register and use it
+ * in compare insn.
+ */
+ insn->code = BPF_ALU | BPF_MOV | BPF_K;
+ insn->a_reg = TMP_REG;
+ insn->imm = fp->k;
+ insn++;
+
+ insn->a_reg = A_REG;
+ insn->x_reg = TMP_REG;
+ bpf_src = BPF_X;
+ } else {
+ insn->a_reg = A_REG;
+ insn->x_reg = X_REG;
+ insn->imm = fp->k;
+ bpf_src = BPF_SRC(fp->code);
+ }
+
+ /* Common case where 'jump_false' is next insn. */
+ if (fp->jf == 0) {
+ insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
+ target = i + fp->jt + 1;
+ EMIT_JMP;
+ break;
+ }
+
+ /* Convert JEQ into JNE when 'jump_true' is next insn. */
+ if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) {
+ insn->code = BPF_JMP | BPF_JNE | bpf_src;
+ target = i + fp->jf + 1;
+ EMIT_JMP;
+ break;
+ }
+
+ /* Other jumps are mapped into two insns: Jxx and JA. */
+ target = i + fp->jt + 1;
+ insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
+ EMIT_JMP;
+ insn++;
+
+ insn->code = BPF_JMP | BPF_JA;
+ target = i + fp->jf + 1;
+ EMIT_JMP;
+ break;
+
+ /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */
+ case BPF_LDX | BPF_MSH | BPF_B:
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = TMP_REG;
+ insn->x_reg = A_REG;
+ insn++;
+
+ insn->code = BPF_LD | BPF_ABS | BPF_B;
+ insn->a_reg = A_REG;
+ insn->imm = fp->k;
+ insn++;
+
+ insn->code = BPF_ALU | BPF_AND | BPF_K;
+ insn->a_reg = A_REG;
+ insn->imm = 0xf;
+ insn++;
+
+ insn->code = BPF_ALU | BPF_LSH | BPF_K;
+ insn->a_reg = A_REG;
+ insn->imm = 2;
+ insn++;
+
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = X_REG;
+ insn->x_reg = A_REG;
+ insn++;
+
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = A_REG;
+ insn->x_reg = TMP_REG;
+ break;
+
+ /* RET_K, RET_A are remaped into 2 insns. */
+ case BPF_RET | BPF_A:
+ case BPF_RET | BPF_K:
+ insn->code = BPF_ALU | BPF_MOV |
+ (BPF_RVAL(fp->code) == BPF_K ?
+ BPF_K : BPF_X);
+ insn->a_reg = 0;
+ insn->x_reg = A_REG;
+ insn->imm = fp->k;
+ insn++;
+
+ insn->code = BPF_JMP | BPF_EXIT;
+ break;
+
+ /* Store to stack. */
+ case BPF_ST:
+ case BPF_STX:
+ insn->code = BPF_STX | BPF_MEM | BPF_W;
+ insn->a_reg = FP_REG;
+ insn->x_reg = fp->code == BPF_ST ? A_REG : X_REG;
+ insn->off = -(BPF_MEMWORDS - fp->k) * 4;
+ break;
+
+ /* Load from stack. */
+ case BPF_LD | BPF_MEM:
+ case BPF_LDX | BPF_MEM:
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
+ A_REG : X_REG;
+ insn->x_reg = FP_REG;
+ insn->off = -(BPF_MEMWORDS - fp->k) * 4;
+ break;
+
+ /* A = K or X = K */
+ case BPF_LD | BPF_IMM:
+ case BPF_LDX | BPF_IMM:
+ insn->code = BPF_ALU | BPF_MOV | BPF_K;
+ insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
+ A_REG : X_REG;
+ insn->imm = fp->k;
+ break;
+
+ /* X = A */
+ case BPF_MISC | BPF_TAX:
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = X_REG;
+ insn->x_reg = A_REG;
+ break;
+
+ /* A = X */
+ case BPF_MISC | BPF_TXA:
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = A_REG;
+ insn->x_reg = X_REG;
+ break;
+
+ /* A = skb->len or X = skb->len */
+ case BPF_LD | BPF_W | BPF_LEN:
+ case BPF_LDX | BPF_W | BPF_LEN:
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
+ A_REG : X_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, len);
+ break;
+
+ /* access seccomp_data fields */
+ case BPF_LDX | BPF_ABS | BPF_W:
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = fp->k;
+ break;
+
+ default:
+ goto err;
+ }
+
+ insn++;
+ if (new_prog)
+ memcpy(new_insn, tmp_insns,
+ sizeof(*insn) * (insn - tmp_insns));
+
+ new_insn += insn - tmp_insns;
+ }
+
+ if (!new_prog) {
+ /* Only calculating new length. */
+ *new_len = new_insn - new_prog;
+ return 0;
+ }
+
+ pass++;
+ if (new_flen != new_insn - new_prog) {
+ new_flen = new_insn - new_prog;
+ if (pass > 2)
+ goto err;
+
+ goto do_pass;
+ }
+
+ kfree(addrs);
+ BUG_ON(*new_len != new_flen);
+ return 0;
+err:
+ kfree(addrs);
+ return -EINVAL;
+}
+
+/* Security:
+ *
* A BPF program is able to use 16 cells of memory to store intermediate
- * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter())
+ * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter()).
+ *
* As we dont want to clear mem[] array for each packet going through
* sk_run_filter(), we check that filter loaded by user never try to read
* a cell if not previously written, and we check all branches to be sure
@@ -629,30 +1375,197 @@
}
EXPORT_SYMBOL(sk_chk_filter);
+static int sk_store_orig_filter(struct sk_filter *fp,
+ const struct sock_fprog *fprog)
+{
+ unsigned int fsize = sk_filter_proglen(fprog);
+ struct sock_fprog_kern *fkprog;
+
+ fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL);
+ if (!fp->orig_prog)
+ return -ENOMEM;
+
+ fkprog = fp->orig_prog;
+ fkprog->len = fprog->len;
+ fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL);
+ if (!fkprog->filter) {
+ kfree(fp->orig_prog);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void sk_release_orig_filter(struct sk_filter *fp)
+{
+ struct sock_fprog_kern *fprog = fp->orig_prog;
+
+ if (fprog) {
+ kfree(fprog->filter);
+ kfree(fprog);
+ }
+}
+
/**
* sk_filter_release_rcu - Release a socket filter by rcu_head
* @rcu: rcu_head that contains the sk_filter to free
*/
-void sk_filter_release_rcu(struct rcu_head *rcu)
+static void sk_filter_release_rcu(struct rcu_head *rcu)
{
struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
+ sk_release_orig_filter(fp);
bpf_jit_free(fp);
}
-EXPORT_SYMBOL(sk_filter_release_rcu);
-static int __sk_prepare_filter(struct sk_filter *fp)
+/**
+ * sk_filter_release - release a socket filter
+ * @fp: filter to remove
+ *
+ * Remove a filter from a socket and release its resources.
+ */
+static void sk_filter_release(struct sk_filter *fp)
+{
+ if (atomic_dec_and_test(&fp->refcnt))
+ call_rcu(&fp->rcu, sk_filter_release_rcu);
+}
+
+void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
+{
+ atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc);
+ sk_filter_release(fp);
+}
+
+void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+{
+ atomic_inc(&fp->refcnt);
+ atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc);
+}
+
+static struct sk_filter *__sk_migrate_realloc(struct sk_filter *fp,
+ struct sock *sk,
+ unsigned int len)
+{
+ struct sk_filter *fp_new;
+
+ if (sk == NULL)
+ return krealloc(fp, len, GFP_KERNEL);
+
+ fp_new = sock_kmalloc(sk, len, GFP_KERNEL);
+ if (fp_new) {
+ memcpy(fp_new, fp, sizeof(struct sk_filter));
+ /* As we're kepping orig_prog in fp_new along,
+ * we need to make sure we're not evicting it
+ * from the old fp.
+ */
+ fp->orig_prog = NULL;
+ sk_filter_uncharge(sk, fp);
+ }
+
+ return fp_new;
+}
+
+static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp,
+ struct sock *sk)
+{
+ struct sock_filter *old_prog;
+ struct sk_filter *old_fp;
+ int i, err, new_len, old_len = fp->len;
+
+ /* We are free to overwrite insns et al right here as it
+ * won't be used at this point in time anymore internally
+ * after the migration to the internal BPF instruction
+ * representation.
+ */
+ BUILD_BUG_ON(sizeof(struct sock_filter) !=
+ sizeof(struct sock_filter_int));
+
+ /* For now, we need to unfiddle BPF_S_* identifiers in place.
+ * This can sooner or later on be subject to removal, e.g. when
+ * JITs have been converted.
+ */
+ for (i = 0; i < fp->len; i++)
+ sk_decode_filter(&fp->insns[i], &fp->insns[i]);
+
+ /* Conversion cannot happen on overlapping memory areas,
+ * so we need to keep the user BPF around until the 2nd
+ * pass. At this time, the user BPF is stored in fp->insns.
+ */
+ old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter),
+ GFP_KERNEL);
+ if (!old_prog) {
+ err = -ENOMEM;
+ goto out_err;
+ }
+
+ /* 1st pass: calculate the new program length. */
+ err = sk_convert_filter(old_prog, old_len, NULL, &new_len);
+ if (err)
+ goto out_err_free;
+
+ /* Expand fp for appending the new filter representation. */
+ old_fp = fp;
+ fp = __sk_migrate_realloc(old_fp, sk, sk_filter_size(new_len));
+ if (!fp) {
+ /* The old_fp is still around in case we couldn't
+ * allocate new memory, so uncharge on that one.
+ */
+ fp = old_fp;
+ err = -ENOMEM;
+ goto out_err_free;
+ }
+
+ fp->bpf_func = sk_run_filter_int_skb;
+ fp->len = new_len;
+
+ /* 2nd pass: remap sock_filter insns into sock_filter_int insns. */
+ err = sk_convert_filter(old_prog, old_len, fp->insnsi, &new_len);
+ if (err)
+ /* 2nd sk_convert_filter() can fail only if it fails
+ * to allocate memory, remapping must succeed. Note,
+ * that at this time old_fp has already been released
+ * by __sk_migrate_realloc().
+ */
+ goto out_err_free;
+
+ kfree(old_prog);
+ return fp;
+
+out_err_free:
+ kfree(old_prog);
+out_err:
+ /* Rollback filter setup. */
+ if (sk != NULL)
+ sk_filter_uncharge(sk, fp);
+ else
+ kfree(fp);
+ return ERR_PTR(err);
+}
+
+static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
+ struct sock *sk)
{
int err;
- fp->bpf_func = sk_run_filter;
+ fp->bpf_func = NULL;
+ fp->jited = 0;
err = sk_chk_filter(fp->insns, fp->len);
if (err)
- return err;
+ return ERR_PTR(err);
+ /* Probe if we can JIT compile the filter and if so, do
+ * the compilation of the filter.
+ */
bpf_jit_compile(fp);
- return 0;
+
+ /* JIT compiler couldn't process this filter, so do the
+ * internal BPF translation for the optimized interpreter.
+ */
+ if (!fp->jited)
+ fp = __sk_migrate_filter(fp, sk);
+
+ return fp;
}
/**
@@ -668,9 +1581,8 @@
int sk_unattached_filter_create(struct sk_filter **pfp,
struct sock_fprog *fprog)
{
+ unsigned int fsize = sk_filter_proglen(fprog);
struct sk_filter *fp;
- unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
- int err;
/* Make sure new filter is there and in the right amounts. */
if (fprog->filter == NULL)
@@ -679,20 +1591,26 @@
fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL);
if (!fp)
return -ENOMEM;
+
memcpy(fp->insns, fprog->filter, fsize);
atomic_set(&fp->refcnt, 1);
fp->len = fprog->len;
+ /* Since unattached filters are not copied back to user
+ * space through sk_get_filter(), we do not need to hold
+ * a copy here, and can spare us the work.
+ */
+ fp->orig_prog = NULL;
- err = __sk_prepare_filter(fp);
- if (err)
- goto free_mem;
+ /* __sk_prepare_filter() already takes care of uncharging
+ * memory in case something goes wrong.
+ */
+ fp = __sk_prepare_filter(fp, NULL);
+ if (IS_ERR(fp))
+ return PTR_ERR(fp);
*pfp = fp;
return 0;
-free_mem:
- kfree(fp);
- return err;
}
EXPORT_SYMBOL_GPL(sk_unattached_filter_create);
@@ -715,7 +1633,7 @@
int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
{
struct sk_filter *fp, *old_fp;
- unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
+ unsigned int fsize = sk_filter_proglen(fprog);
unsigned int sk_fsize = sk_filter_size(fprog->len);
int err;
@@ -729,6 +1647,7 @@
fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL);
if (!fp)
return -ENOMEM;
+
if (copy_from_user(fp->insns, fprog->filter, fsize)) {
sock_kfree_s(sk, fp, sk_fsize);
return -EFAULT;
@@ -737,18 +1656,26 @@
atomic_set(&fp->refcnt, 1);
fp->len = fprog->len;
- err = __sk_prepare_filter(fp);
+ err = sk_store_orig_filter(fp, fprog);
if (err) {
sk_filter_uncharge(sk, fp);
- return err;
+ return -ENOMEM;
}
+ /* __sk_prepare_filter() already takes care of uncharging
+ * memory in case something goes wrong.
+ */
+ fp = __sk_prepare_filter(fp, sk);
+ if (IS_ERR(fp))
+ return PTR_ERR(fp);
+
old_fp = rcu_dereference_protected(sk->sk_filter,
sock_owned_by_user(sk));
rcu_assign_pointer(sk->sk_filter, fp);
if (old_fp)
sk_filter_uncharge(sk, old_fp);
+
return 0;
}
EXPORT_SYMBOL_GPL(sk_attach_filter);
@@ -768,6 +1695,7 @@
sk_filter_uncharge(sk, filter);
ret = 0;
}
+
return ret;
}
EXPORT_SYMBOL_GPL(sk_detach_filter);
@@ -850,34 +1778,41 @@
to->k = filt->k;
}
-int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len)
+int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
+ unsigned int len)
{
+ struct sock_fprog_kern *fprog;
struct sk_filter *filter;
- int i, ret;
+ int ret = 0;
lock_sock(sk);
filter = rcu_dereference_protected(sk->sk_filter,
- sock_owned_by_user(sk));
- ret = 0;
+ sock_owned_by_user(sk));
if (!filter)
goto out;
- ret = filter->len;
+
+ /* We're copying the filter that has been originally attached,
+ * so no conversion/decode needed anymore.
+ */
+ fprog = filter->orig_prog;
+
+ ret = fprog->len;
if (!len)
+ /* User space only enquires number of filter blocks. */
goto out;
+
ret = -EINVAL;
- if (len < filter->len)
+ if (len < fprog->len)
goto out;
ret = -EFAULT;
- for (i = 0; i < filter->len; i++) {
- struct sock_filter fb;
+ if (copy_to_user(ubuf, fprog->filter, sk_filter_proglen(fprog)))
+ goto out;
- sk_decode_filter(&filter->insns[i], &fb);
- if (copy_to_user(&ubuf[i], &fb, sizeof(fb)))
- goto out;
- }
-
- ret = filter->len;
+ /* Instead of bytes, the API requests to return the number
+ * of filter blocks.
+ */
+ ret = fprog->len;
out:
release_sock(sk);
return ret;
diff --git a/net/core/flow.c b/net/core/flow.c
index dfa602c..31cfb36 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -24,6 +24,7 @@
#include <net/flow.h>
#include <linux/atomic.h>
#include <linux/security.h>
+#include <net/net_namespace.h>
struct flow_cache_entry {
union {
@@ -38,37 +39,14 @@
struct flow_cache_object *object;
};
-struct flow_cache_percpu {
- struct hlist_head *hash_table;
- int hash_count;
- u32 hash_rnd;
- int hash_rnd_recalc;
- struct tasklet_struct flush_tasklet;
-};
-
struct flow_flush_info {
struct flow_cache *cache;
atomic_t cpuleft;
struct completion completion;
};
-struct flow_cache {
- u32 hash_shift;
- struct flow_cache_percpu __percpu *percpu;
- struct notifier_block hotcpu_notifier;
- int low_watermark;
- int high_watermark;
- struct timer_list rnd_timer;
-};
-
-atomic_t flow_cache_genid = ATOMIC_INIT(0);
-EXPORT_SYMBOL(flow_cache_genid);
-static struct flow_cache flow_cache_global;
static struct kmem_cache *flow_cachep __read_mostly;
-static DEFINE_SPINLOCK(flow_cache_gc_lock);
-static LIST_HEAD(flow_cache_gc_list);
-
#define flow_cache_hash_size(cache) (1 << (cache)->hash_shift)
#define FLOW_HASH_RND_PERIOD (10 * 60 * HZ)
@@ -84,16 +62,18 @@
add_timer(&fc->rnd_timer);
}
-static int flow_entry_valid(struct flow_cache_entry *fle)
+static int flow_entry_valid(struct flow_cache_entry *fle,
+ struct netns_xfrm *xfrm)
{
- if (atomic_read(&flow_cache_genid) != fle->genid)
+ if (atomic_read(&xfrm->flow_cache_genid) != fle->genid)
return 0;
if (fle->object && !fle->object->ops->check(fle->object))
return 0;
return 1;
}
-static void flow_entry_kill(struct flow_cache_entry *fle)
+static void flow_entry_kill(struct flow_cache_entry *fle,
+ struct netns_xfrm *xfrm)
{
if (fle->object)
fle->object->ops->delete(fle->object);
@@ -104,26 +84,28 @@
{
struct list_head gc_list;
struct flow_cache_entry *fce, *n;
+ struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
+ flow_cache_gc_work);
INIT_LIST_HEAD(&gc_list);
- spin_lock_bh(&flow_cache_gc_lock);
- list_splice_tail_init(&flow_cache_gc_list, &gc_list);
- spin_unlock_bh(&flow_cache_gc_lock);
+ spin_lock_bh(&xfrm->flow_cache_gc_lock);
+ list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list);
+ spin_unlock_bh(&xfrm->flow_cache_gc_lock);
list_for_each_entry_safe(fce, n, &gc_list, u.gc_list)
- flow_entry_kill(fce);
+ flow_entry_kill(fce, xfrm);
}
-static DECLARE_WORK(flow_cache_gc_work, flow_cache_gc_task);
static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
- int deleted, struct list_head *gc_list)
+ int deleted, struct list_head *gc_list,
+ struct netns_xfrm *xfrm)
{
if (deleted) {
fcp->hash_count -= deleted;
- spin_lock_bh(&flow_cache_gc_lock);
- list_splice_tail(gc_list, &flow_cache_gc_list);
- spin_unlock_bh(&flow_cache_gc_lock);
- schedule_work(&flow_cache_gc_work);
+ spin_lock_bh(&xfrm->flow_cache_gc_lock);
+ list_splice_tail(gc_list, &xfrm->flow_cache_gc_list);
+ spin_unlock_bh(&xfrm->flow_cache_gc_lock);
+ schedule_work(&xfrm->flow_cache_gc_work);
}
}
@@ -135,6 +117,8 @@
struct hlist_node *tmp;
LIST_HEAD(gc_list);
int i, deleted = 0;
+ struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
+ flow_cache_global);
for (i = 0; i < flow_cache_hash_size(fc); i++) {
int saved = 0;
@@ -142,7 +126,7 @@
hlist_for_each_entry_safe(fle, tmp,
&fcp->hash_table[i], u.hlist) {
if (saved < shrink_to &&
- flow_entry_valid(fle)) {
+ flow_entry_valid(fle, xfrm)) {
saved++;
} else {
deleted++;
@@ -152,7 +136,7 @@
}
}
- flow_cache_queue_garbage(fcp, deleted, &gc_list);
+ flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
}
static void flow_cache_shrink(struct flow_cache *fc,
@@ -208,7 +192,7 @@
flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
flow_resolve_t resolver, void *ctx)
{
- struct flow_cache *fc = &flow_cache_global;
+ struct flow_cache *fc = &net->xfrm.flow_cache_global;
struct flow_cache_percpu *fcp;
struct flow_cache_entry *fle, *tfle;
struct flow_cache_object *flo;
@@ -258,7 +242,7 @@
hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]);
fcp->hash_count++;
}
- } else if (likely(fle->genid == atomic_read(&flow_cache_genid))) {
+ } else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) {
flo = fle->object;
if (!flo)
goto ret_object;
@@ -279,7 +263,7 @@
}
flo = resolver(net, key, family, dir, flo, ctx);
if (fle) {
- fle->genid = atomic_read(&flow_cache_genid);
+ fle->genid = atomic_read(&net->xfrm.flow_cache_genid);
if (!IS_ERR(flo))
fle->object = flo;
else
@@ -303,12 +287,14 @@
struct hlist_node *tmp;
LIST_HEAD(gc_list);
int i, deleted = 0;
+ struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
+ flow_cache_global);
fcp = this_cpu_ptr(fc->percpu);
for (i = 0; i < flow_cache_hash_size(fc); i++) {
hlist_for_each_entry_safe(fle, tmp,
&fcp->hash_table[i], u.hlist) {
- if (flow_entry_valid(fle))
+ if (flow_entry_valid(fle, xfrm))
continue;
deleted++;
@@ -317,7 +303,7 @@
}
}
- flow_cache_queue_garbage(fcp, deleted, &gc_list);
+ flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
if (atomic_dec_and_test(&info->cpuleft))
complete(&info->completion);
@@ -351,10 +337,9 @@
tasklet_schedule(tasklet);
}
-void flow_cache_flush(void)
+void flow_cache_flush(struct net *net)
{
struct flow_flush_info info;
- static DEFINE_MUTEX(flow_flush_sem);
cpumask_var_t mask;
int i, self;
@@ -365,8 +350,8 @@
/* Don't want cpus going down or up during this. */
get_online_cpus();
- mutex_lock(&flow_flush_sem);
- info.cache = &flow_cache_global;
+ mutex_lock(&net->xfrm.flow_flush_sem);
+ info.cache = &net->xfrm.flow_cache_global;
for_each_online_cpu(i)
if (!flow_cache_percpu_empty(info.cache, i))
cpumask_set_cpu(i, mask);
@@ -386,21 +371,23 @@
wait_for_completion(&info.completion);
done:
- mutex_unlock(&flow_flush_sem);
+ mutex_unlock(&net->xfrm.flow_flush_sem);
put_online_cpus();
free_cpumask_var(mask);
}
static void flow_cache_flush_task(struct work_struct *work)
{
- flow_cache_flush();
+ struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
+ flow_cache_gc_work);
+ struct net *net = container_of(xfrm, struct net, xfrm);
+
+ flow_cache_flush(net);
}
-static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task);
-
-void flow_cache_flush_deferred(void)
+void flow_cache_flush_deferred(struct net *net)
{
- schedule_work(&flow_cache_flush_work);
+ schedule_work(&net->xfrm.flow_cache_flush_work);
}
static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
@@ -425,7 +412,8 @@
unsigned long action,
void *hcpu)
{
- struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier);
+ struct flow_cache *fc = container_of(nfb, struct flow_cache,
+ hotcpu_notifier);
int res, cpu = (unsigned long) hcpu;
struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
@@ -444,9 +432,20 @@
return NOTIFY_OK;
}
-static int __init flow_cache_init(struct flow_cache *fc)
+int flow_cache_init(struct net *net)
{
int i;
+ struct flow_cache *fc = &net->xfrm.flow_cache_global;
+
+ if (!flow_cachep)
+ flow_cachep = kmem_cache_create("flow_cache",
+ sizeof(struct flow_cache_entry),
+ 0, SLAB_PANIC, NULL);
+ spin_lock_init(&net->xfrm.flow_cache_gc_lock);
+ INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list);
+ INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task);
+ INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task);
+ mutex_init(&net->xfrm.flow_flush_sem);
fc->hash_shift = 10;
fc->low_watermark = 2 * flow_cache_hash_size(fc);
@@ -484,14 +483,23 @@
return -ENOMEM;
}
+EXPORT_SYMBOL(flow_cache_init);
-static int __init flow_cache_init_global(void)
+void flow_cache_fini(struct net *net)
{
- flow_cachep = kmem_cache_create("flow_cache",
- sizeof(struct flow_cache_entry),
- 0, SLAB_PANIC, NULL);
+ int i;
+ struct flow_cache *fc = &net->xfrm.flow_cache_global;
- return flow_cache_init(&flow_cache_global);
+ del_timer_sync(&fc->rnd_timer);
+ unregister_hotcpu_notifier(&fc->hotcpu_notifier);
+
+ for_each_possible_cpu(i) {
+ struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i);
+ kfree(fcp->hash_table);
+ fcp->hash_table = NULL;
+ }
+
+ free_percpu(fc->percpu);
+ fc->percpu = NULL;
}
-
-module_init(flow_cache_init_global);
+EXPORT_SYMBOL(flow_cache_fini);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 87577d4..107ed12 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -61,7 +61,7 @@
again:
switch (proto) {
- case __constant_htons(ETH_P_IP): {
+ case htons(ETH_P_IP): {
const struct iphdr *iph;
struct iphdr _iph;
ip:
@@ -77,7 +77,7 @@
iph_to_flow_copy_addrs(flow, iph);
break;
}
- case __constant_htons(ETH_P_IPV6): {
+ case htons(ETH_P_IPV6): {
const struct ipv6hdr *iph;
struct ipv6hdr _iph;
ipv6:
@@ -91,8 +91,8 @@
nhoff += sizeof(struct ipv6hdr);
break;
}
- case __constant_htons(ETH_P_8021AD):
- case __constant_htons(ETH_P_8021Q): {
+ case htons(ETH_P_8021AD):
+ case htons(ETH_P_8021Q): {
const struct vlan_hdr *vlan;
struct vlan_hdr _vlan;
@@ -104,7 +104,7 @@
nhoff += sizeof(*vlan);
goto again;
}
- case __constant_htons(ETH_P_PPP_SES): {
+ case htons(ETH_P_PPP_SES): {
struct {
struct pppoe_hdr hdr;
__be16 proto;
@@ -115,9 +115,9 @@
proto = hdr->proto;
nhoff += PPPOE_SES_HLEN;
switch (proto) {
- case __constant_htons(PPP_IP):
+ case htons(PPP_IP):
goto ip;
- case __constant_htons(PPP_IPV6):
+ case htons(PPP_IPV6):
goto ipv6;
default:
return false;
@@ -203,8 +203,8 @@
/*
* __skb_get_hash: calculate a flow hash based on src/dst addresses
- * and src/dst port numbers. Sets rxhash in skb to non-zero hash value
- * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb
+ * and src/dst port numbers. Sets hash in skb to non-zero hash value
+ * on success, zero indicates no valid hash. Also, sets l4_hash in skb
* if hash is a canonical 4-tuple hash over transport ports.
*/
void __skb_get_hash(struct sk_buff *skb)
@@ -216,7 +216,7 @@
return;
if (keys.ports)
- skb->l4_rxhash = 1;
+ skb->l4_hash = 1;
/* get a consistent hash (same value on both flow directions) */
if (((__force u32)keys.dst < (__force u32)keys.src) ||
@@ -232,7 +232,7 @@
if (!hash)
hash = 1;
- skb->rxhash = hash;
+ skb->hash = hash;
}
EXPORT_SYMBOL(__skb_get_hash);
@@ -323,17 +323,6 @@
return poff;
}
-static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
-{
- if (unlikely(queue_index >= dev->real_num_tx_queues)) {
- net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
- dev->name, queue_index,
- dev->real_num_tx_queues);
- return 0;
- }
- return queue_index;
-}
-
static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_XPS
@@ -355,7 +344,7 @@
hash = skb->sk->sk_hash;
else
hash = (__force u16) skb->protocol ^
- skb->rxhash;
+ skb->hash;
hash = __flow_hash_1word(hash);
queue_index = map->queues[
((u64)hash * map->len) >> 32];
@@ -372,7 +361,7 @@
#endif
}
-u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
{
struct sock *sk = skb->sk;
int queue_index = sk_tx_queue_get(sk);
@@ -392,7 +381,6 @@
return queue_index;
}
-EXPORT_SYMBOL(__netdev_pick_tx);
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
struct sk_buff *skb,
@@ -403,13 +391,13 @@
if (dev->real_num_tx_queues != 1) {
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_select_queue)
- queue_index = ops->ndo_select_queue(dev, skb,
- accel_priv);
+ queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+ __netdev_pick_tx);
else
queue_index = __netdev_pick_tx(dev, skb);
if (!accel_priv)
- queue_index = dev_cap_txqueue(dev, queue_index);
+ queue_index = netdev_cap_txqueue(dev, queue_index);
}
skb_set_queue_mapping(skb, queue_index);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index b9e9e0d..8f8a96e 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -766,9 +766,6 @@
nht = rcu_dereference_protected(tbl->nht,
lockdep_is_held(&tbl->lock));
- if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
- goto out;
-
/*
* periodically recompute ReachableTime from random function
*/
@@ -781,6 +778,9 @@
neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
}
+ if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
+ goto out;
+
for (i = 0 ; i < (1 << nht->hash_shift); i++) {
np = &nht->hash_buckets[i];
@@ -836,10 +836,10 @@
static __inline__ int neigh_max_probes(struct neighbour *n)
{
struct neigh_parms *p = n->parms;
- return (n->nud_state & NUD_PROBE) ?
- NEIGH_VAR(p, UCAST_PROBES) :
- NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) +
- NEIGH_VAR(p, MCAST_PROBES);
+ int max_probes = NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES);
+ if (!(n->nud_state & NUD_PROBE))
+ max_probes += NEIGH_VAR(p, MCAST_PROBES);
+ return max_probes;
}
static void neigh_invalidate(struct neighbour *neigh)
@@ -945,6 +945,7 @@
neigh->nud_state = NUD_FAILED;
notify = 1;
neigh_invalidate(neigh);
+ goto out;
}
if (neigh->nud_state & NUD_IN_TIMER) {
@@ -3046,7 +3047,7 @@
if (!t)
goto err;
- for (i = 0; i < ARRAY_SIZE(t->neigh_vars); i++) {
+ for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) {
t->neigh_vars[i].data += (long) p;
t->neigh_vars[i].extra1 = dev;
t->neigh_vars[i].extra2 = p;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 9388624..daed9a6 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -104,6 +104,7 @@
}
NETDEVICE_SHOW_RO(dev_id, fmt_hex);
+NETDEVICE_SHOW_RO(dev_port, fmt_dec);
NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec);
NETDEVICE_SHOW_RO(addr_len, fmt_dec);
NETDEVICE_SHOW_RO(iflink, fmt_dec);
@@ -373,6 +374,7 @@
&dev_attr_netdev_group.attr,
&dev_attr_type.attr,
&dev_attr_dev_id.attr,
+ &dev_attr_dev_port.attr,
&dev_attr_iflink.attr,
&dev_attr_ifindex.attr,
&dev_attr_addr_assign_type.attr,
@@ -996,15 +998,12 @@
#endif /* CONFIG_BQL */
#ifdef CONFIG_XPS
-static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue)
+static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
{
struct net_device *dev = queue->dev;
- int i;
+ unsigned int i;
- for (i = 0; i < dev->num_tx_queues; i++)
- if (queue == &dev->_tx[i])
- break;
-
+ i = queue - dev->_tx;
BUG_ON(i >= dev->num_tx_queues);
return i;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index c03f3de..ed7740f 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -46,13 +46,9 @@
static struct sk_buff_head skb_pool;
-static atomic_t trapped;
-
DEFINE_STATIC_SRCU(netpoll_srcu);
#define USEC_PER_POLL 50
-#define NETPOLL_RX_ENABLED 1
-#define NETPOLL_RX_DROP 2
#define MAX_SKB_SIZE \
(sizeof(struct ethhdr) + \
@@ -61,7 +57,6 @@
MAX_UDP_CHUNK)
static void zap_completion_queue(void);
-static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
static void netpoll_async_cleanup(struct work_struct *work);
static unsigned int carrier_timeout = 4;
@@ -74,6 +69,37 @@
#define np_notice(np, fmt, ...) \
pr_notice("%s: " fmt, np->name, ##__VA_ARGS__)
+static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
+ struct netdev_queue *txq)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ int status = NETDEV_TX_OK;
+ netdev_features_t features;
+
+ features = netif_skb_features(skb);
+
+ if (vlan_tx_tag_present(skb) &&
+ !vlan_hw_offload_capable(features, skb->vlan_proto)) {
+ skb = __vlan_put_tag(skb, skb->vlan_proto,
+ vlan_tx_tag_get(skb));
+ if (unlikely(!skb)) {
+ /* This is actually a packet drop, but we
+ * don't want the code that calls this
+ * function to try and operate on a NULL skb.
+ */
+ goto out;
+ }
+ skb->vlan_tci = 0;
+ }
+
+ status = ops->ndo_start_xmit(skb, dev);
+ if (status == NETDEV_TX_OK)
+ txq_trans_update(txq);
+
+out:
+ return status;
+}
+
static void queue_process(struct work_struct *work)
{
struct netpoll_info *npinfo =
@@ -83,51 +109,31 @@
while ((skb = skb_dequeue(&npinfo->txq))) {
struct net_device *dev = skb->dev;
- const struct net_device_ops *ops = dev->netdev_ops;
struct netdev_queue *txq;
if (!netif_device_present(dev) || !netif_running(dev)) {
- __kfree_skb(skb);
+ kfree_skb(skb);
continue;
}
txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
local_irq_save(flags);
- __netif_tx_lock(txq, smp_processor_id());
+ HARD_TX_LOCK(dev, txq, smp_processor_id());
if (netif_xmit_frozen_or_stopped(txq) ||
- ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) {
+ netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
skb_queue_head(&npinfo->txq, skb);
- __netif_tx_unlock(txq);
+ HARD_TX_UNLOCK(dev, txq);
local_irq_restore(flags);
schedule_delayed_work(&npinfo->tx_work, HZ/10);
return;
}
- __netif_tx_unlock(txq);
+ HARD_TX_UNLOCK(dev, txq);
local_irq_restore(flags);
}
}
-static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
- unsigned short ulen, __be32 saddr, __be32 daddr)
-{
- __wsum psum;
-
- if (uh->check == 0 || skb_csum_unnecessary(skb))
- return 0;
-
- psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
-
- if (skb->ip_summed == CHECKSUM_COMPLETE &&
- !csum_fold(csum_add(psum, skb->csum)))
- return 0;
-
- skb->csum = psum;
-
- return __skb_checksum_complete(skb);
-}
-
/*
* Check whether delayed processing was scheduled for our NIC. If so,
* we attempt to grab the poll lock and use ->poll() to pump the card.
@@ -138,14 +144,8 @@
* trylock here and interrupts are already disabled in the softirq
* case. Further, we test the poll_owner to avoid recursion on UP
* systems where the lock doesn't exist.
- *
- * In cases where there is bi-directional communications, reading only
- * one message at a time can lead to packets being dropped by the
- * network adapter, forcing superfluous retries and possibly timeouts.
- * Thus, we set our budget to greater than 1.
*/
-static int poll_one_napi(struct netpoll_info *npinfo,
- struct napi_struct *napi, int budget)
+static int poll_one_napi(struct napi_struct *napi, int budget)
{
int work;
@@ -156,52 +156,35 @@
if (!test_bit(NAPI_STATE_SCHED, &napi->state))
return budget;
- npinfo->rx_flags |= NETPOLL_RX_DROP;
- atomic_inc(&trapped);
set_bit(NAPI_STATE_NPSVC, &napi->state);
work = napi->poll(napi, budget);
+ WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll);
trace_napi_poll(napi);
clear_bit(NAPI_STATE_NPSVC, &napi->state);
- atomic_dec(&trapped);
- npinfo->rx_flags &= ~NETPOLL_RX_DROP;
return budget - work;
}
-static void poll_napi(struct net_device *dev)
+static void poll_napi(struct net_device *dev, int budget)
{
struct napi_struct *napi;
- int budget = 16;
list_for_each_entry(napi, &dev->napi_list, dev_list) {
if (napi->poll_owner != smp_processor_id() &&
spin_trylock(&napi->poll_lock)) {
- budget = poll_one_napi(rcu_dereference_bh(dev->npinfo),
- napi, budget);
+ budget = poll_one_napi(napi, budget);
spin_unlock(&napi->poll_lock);
-
- if (!budget)
- break;
}
}
}
-static void service_neigh_queue(struct netpoll_info *npi)
-{
- if (npi) {
- struct sk_buff *skb;
-
- while ((skb = skb_dequeue(&npi->neigh_tx)))
- netpoll_neigh_reply(skb, npi);
- }
-}
-
static void netpoll_poll_dev(struct net_device *dev)
{
const struct net_device_ops *ops;
struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
+ int budget = 0;
/* Don't do any rx activity if the dev_lock mutex is held
* the dev_open/close paths use this to block netpoll activity
@@ -224,31 +207,14 @@
/* Process pending work on NIC */
ops->ndo_poll_controller(dev);
- poll_napi(dev);
+ poll_napi(dev, budget);
up(&ni->dev_lock);
- if (dev->flags & IFF_SLAVE) {
- if (ni) {
- struct net_device *bond_dev;
- struct sk_buff *skb;
- struct netpoll_info *bond_ni;
-
- bond_dev = netdev_master_upper_dev_get_rcu(dev);
- bond_ni = rcu_dereference_bh(bond_dev->npinfo);
- while ((skb = skb_dequeue(&ni->neigh_tx))) {
- skb->dev = bond_dev;
- skb_queue_tail(&bond_ni->neigh_tx, skb);
- }
- }
- }
-
- service_neigh_queue(ni);
-
zap_completion_queue();
}
-void netpoll_rx_disable(struct net_device *dev)
+void netpoll_poll_disable(struct net_device *dev)
{
struct netpoll_info *ni;
int idx;
@@ -259,9 +225,9 @@
down(&ni->dev_lock);
srcu_read_unlock(&netpoll_srcu, idx);
}
-EXPORT_SYMBOL(netpoll_rx_disable);
+EXPORT_SYMBOL(netpoll_poll_disable);
-void netpoll_rx_enable(struct net_device *dev)
+void netpoll_poll_enable(struct net_device *dev)
{
struct netpoll_info *ni;
rcu_read_lock();
@@ -270,7 +236,7 @@
up(&ni->dev_lock);
rcu_read_unlock();
}
-EXPORT_SYMBOL(netpoll_rx_enable);
+EXPORT_SYMBOL(netpoll_poll_enable);
static void refill_skbs(void)
{
@@ -359,7 +325,6 @@
{
int status = NETDEV_TX_BUSY;
unsigned long tries;
- const struct net_device_ops *ops = dev->netdev_ops;
/* It is up to the caller to keep npinfo alive. */
struct netpoll_info *npinfo;
@@ -367,7 +332,7 @@
npinfo = rcu_dereference_bh(np->dev->npinfo);
if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
- __kfree_skb(skb);
+ dev_kfree_skb_irq(skb);
return;
}
@@ -380,29 +345,11 @@
/* try until next clock tick */
for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
tries > 0; --tries) {
- if (__netif_tx_trylock(txq)) {
- if (!netif_xmit_stopped(txq)) {
- if (vlan_tx_tag_present(skb) &&
- !vlan_hw_offload_capable(netif_skb_features(skb),
- skb->vlan_proto)) {
- skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb));
- if (unlikely(!skb)) {
- /* This is actually a packet drop, but we
- * don't want the code at the end of this
- * function to try and re-queue a NULL skb.
- */
- status = NETDEV_TX_OK;
- goto unlock_txq;
- }
- skb->vlan_tci = 0;
- }
+ if (HARD_TX_TRYLOCK(dev, txq)) {
+ if (!netif_xmit_stopped(txq))
+ status = netpoll_start_xmit(skb, dev, txq);
- status = ops->ndo_start_xmit(skb, dev);
- if (status == NETDEV_TX_OK)
- txq_trans_update(txq);
- }
- unlock_txq:
- __netif_tx_unlock(txq);
+ HARD_TX_UNLOCK(dev, txq);
if (status == NETDEV_TX_OK)
break;
@@ -417,7 +364,7 @@
WARN_ONCE(!irqs_disabled(),
"netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",
- dev->name, ops->ndo_start_xmit);
+ dev->name, dev->netdev_ops->ndo_start_xmit);
}
@@ -529,384 +476,6 @@
}
EXPORT_SYMBOL(netpoll_send_udp);
-static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
-{
- int size, type = ARPOP_REPLY;
- __be32 sip, tip;
- unsigned char *sha;
- struct sk_buff *send_skb;
- struct netpoll *np, *tmp;
- unsigned long flags;
- int hlen, tlen;
- int hits = 0, proto;
-
- if (list_empty(&npinfo->rx_np))
- return;
-
- /* Before checking the packet, we do some early
- inspection whether this is interesting at all */
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (np->dev == skb->dev)
- hits++;
- }
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-
- /* No netpoll struct is using this dev */
- if (!hits)
- return;
-
- proto = ntohs(eth_hdr(skb)->h_proto);
- if (proto == ETH_P_ARP) {
- struct arphdr *arp;
- unsigned char *arp_ptr;
- /* No arp on this interface */
- if (skb->dev->flags & IFF_NOARP)
- return;
-
- if (!pskb_may_pull(skb, arp_hdr_len(skb->dev)))
- return;
-
- skb_reset_network_header(skb);
- skb_reset_transport_header(skb);
- arp = arp_hdr(skb);
-
- if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
- arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
- arp->ar_pro != htons(ETH_P_IP) ||
- arp->ar_op != htons(ARPOP_REQUEST))
- return;
-
- arp_ptr = (unsigned char *)(arp+1);
- /* save the location of the src hw addr */
- sha = arp_ptr;
- arp_ptr += skb->dev->addr_len;
- memcpy(&sip, arp_ptr, 4);
- arp_ptr += 4;
- /* If we actually cared about dst hw addr,
- it would get copied here */
- arp_ptr += skb->dev->addr_len;
- memcpy(&tip, arp_ptr, 4);
-
- /* Should we ignore arp? */
- if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
- return;
-
- size = arp_hdr_len(skb->dev);
-
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (tip != np->local_ip.ip)
- continue;
-
- hlen = LL_RESERVED_SPACE(np->dev);
- tlen = np->dev->needed_tailroom;
- send_skb = find_skb(np, size + hlen + tlen, hlen);
- if (!send_skb)
- continue;
-
- skb_reset_network_header(send_skb);
- arp = (struct arphdr *) skb_put(send_skb, size);
- send_skb->dev = skb->dev;
- send_skb->protocol = htons(ETH_P_ARP);
-
- /* Fill the device header for the ARP frame */
- if (dev_hard_header(send_skb, skb->dev, ETH_P_ARP,
- sha, np->dev->dev_addr,
- send_skb->len) < 0) {
- kfree_skb(send_skb);
- continue;
- }
-
- /*
- * Fill out the arp protocol part.
- *
- * we only support ethernet device type,
- * which (according to RFC 1390) should
- * always equal 1 (Ethernet).
- */
-
- arp->ar_hrd = htons(np->dev->type);
- arp->ar_pro = htons(ETH_P_IP);
- arp->ar_hln = np->dev->addr_len;
- arp->ar_pln = 4;
- arp->ar_op = htons(type);
-
- arp_ptr = (unsigned char *)(arp + 1);
- memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
- arp_ptr += np->dev->addr_len;
- memcpy(arp_ptr, &tip, 4);
- arp_ptr += 4;
- memcpy(arp_ptr, sha, np->dev->addr_len);
- arp_ptr += np->dev->addr_len;
- memcpy(arp_ptr, &sip, 4);
-
- netpoll_send_skb(np, send_skb);
-
- /* If there are several rx_skb_hooks for the same
- * address we're fine by sending a single reply
- */
- break;
- }
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
- } else if( proto == ETH_P_IPV6) {
-#if IS_ENABLED(CONFIG_IPV6)
- struct nd_msg *msg;
- u8 *lladdr = NULL;
- struct ipv6hdr *hdr;
- struct icmp6hdr *icmp6h;
- const struct in6_addr *saddr;
- const struct in6_addr *daddr;
- struct inet6_dev *in6_dev = NULL;
- struct in6_addr *target;
-
- in6_dev = in6_dev_get(skb->dev);
- if (!in6_dev || !in6_dev->cnf.accept_ra)
- return;
-
- if (!pskb_may_pull(skb, skb->len))
- return;
-
- msg = (struct nd_msg *)skb_transport_header(skb);
-
- __skb_push(skb, skb->data - skb_transport_header(skb));
-
- if (ipv6_hdr(skb)->hop_limit != 255)
- return;
- if (msg->icmph.icmp6_code != 0)
- return;
- if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
- return;
-
- saddr = &ipv6_hdr(skb)->saddr;
- daddr = &ipv6_hdr(skb)->daddr;
-
- size = sizeof(struct icmp6hdr) + sizeof(struct in6_addr);
-
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (!ipv6_addr_equal(daddr, &np->local_ip.in6))
- continue;
-
- hlen = LL_RESERVED_SPACE(np->dev);
- tlen = np->dev->needed_tailroom;
- send_skb = find_skb(np, size + hlen + tlen, hlen);
- if (!send_skb)
- continue;
-
- send_skb->protocol = htons(ETH_P_IPV6);
- send_skb->dev = skb->dev;
-
- skb_reset_network_header(send_skb);
- hdr = (struct ipv6hdr *) skb_put(send_skb, sizeof(struct ipv6hdr));
- *(__be32*)hdr = htonl(0x60000000);
- hdr->payload_len = htons(size);
- hdr->nexthdr = IPPROTO_ICMPV6;
- hdr->hop_limit = 255;
- hdr->saddr = *saddr;
- hdr->daddr = *daddr;
-
- icmp6h = (struct icmp6hdr *) skb_put(send_skb, sizeof(struct icmp6hdr));
- icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
- icmp6h->icmp6_router = 0;
- icmp6h->icmp6_solicited = 1;
-
- target = (struct in6_addr *) skb_put(send_skb, sizeof(struct in6_addr));
- *target = msg->target;
- icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size,
- IPPROTO_ICMPV6,
- csum_partial(icmp6h,
- size, 0));
-
- if (dev_hard_header(send_skb, skb->dev, ETH_P_IPV6,
- lladdr, np->dev->dev_addr,
- send_skb->len) < 0) {
- kfree_skb(send_skb);
- continue;
- }
-
- netpoll_send_skb(np, send_skb);
-
- /* If there are several rx_skb_hooks for the same
- * address, we're fine by sending a single reply
- */
- break;
- }
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-#endif
- }
-}
-
-static bool pkt_is_ns(struct sk_buff *skb)
-{
- struct nd_msg *msg;
- struct ipv6hdr *hdr;
-
- if (skb->protocol != htons(ETH_P_ARP))
- return false;
- if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
- return false;
-
- msg = (struct nd_msg *)skb_transport_header(skb);
- __skb_push(skb, skb->data - skb_transport_header(skb));
- hdr = ipv6_hdr(skb);
-
- if (hdr->nexthdr != IPPROTO_ICMPV6)
- return false;
- if (hdr->hop_limit != 255)
- return false;
- if (msg->icmph.icmp6_code != 0)
- return false;
- if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
- return false;
-
- return true;
-}
-
-int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
-{
- int proto, len, ulen, data_len;
- int hits = 0, offset;
- const struct iphdr *iph;
- struct udphdr *uh;
- struct netpoll *np, *tmp;
- uint16_t source;
-
- if (list_empty(&npinfo->rx_np))
- goto out;
-
- if (skb->dev->type != ARPHRD_ETHER)
- goto out;
-
- /* check if netpoll clients need ARP */
- if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) {
- skb_queue_tail(&npinfo->neigh_tx, skb);
- return 1;
- } else if (pkt_is_ns(skb) && atomic_read(&trapped)) {
- skb_queue_tail(&npinfo->neigh_tx, skb);
- return 1;
- }
-
- if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
- skb = vlan_untag(skb);
- if (unlikely(!skb))
- goto out;
- }
-
- proto = ntohs(eth_hdr(skb)->h_proto);
- if (proto != ETH_P_IP && proto != ETH_P_IPV6)
- goto out;
- if (skb->pkt_type == PACKET_OTHERHOST)
- goto out;
- if (skb_shared(skb))
- goto out;
-
- if (proto == ETH_P_IP) {
- if (!pskb_may_pull(skb, sizeof(struct iphdr)))
- goto out;
- iph = (struct iphdr *)skb->data;
- if (iph->ihl < 5 || iph->version != 4)
- goto out;
- if (!pskb_may_pull(skb, iph->ihl*4))
- goto out;
- iph = (struct iphdr *)skb->data;
- if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
- goto out;
-
- len = ntohs(iph->tot_len);
- if (skb->len < len || len < iph->ihl*4)
- goto out;
-
- /*
- * Our transport medium may have padded the buffer out.
- * Now We trim to the true length of the frame.
- */
- if (pskb_trim_rcsum(skb, len))
- goto out;
-
- iph = (struct iphdr *)skb->data;
- if (iph->protocol != IPPROTO_UDP)
- goto out;
-
- len -= iph->ihl*4;
- uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
- offset = (unsigned char *)(uh + 1) - skb->data;
- ulen = ntohs(uh->len);
- data_len = skb->len - offset;
- source = ntohs(uh->source);
-
- if (ulen != len)
- goto out;
- if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr))
- goto out;
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (np->local_ip.ip && np->local_ip.ip != iph->daddr)
- continue;
- if (np->remote_ip.ip && np->remote_ip.ip != iph->saddr)
- continue;
- if (np->local_port && np->local_port != ntohs(uh->dest))
- continue;
-
- np->rx_skb_hook(np, source, skb, offset, data_len);
- hits++;
- }
- } else {
-#if IS_ENABLED(CONFIG_IPV6)
- const struct ipv6hdr *ip6h;
-
- if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
- goto out;
- ip6h = (struct ipv6hdr *)skb->data;
- if (ip6h->version != 6)
- goto out;
- len = ntohs(ip6h->payload_len);
- if (!len)
- goto out;
- if (len + sizeof(struct ipv6hdr) > skb->len)
- goto out;
- if (pskb_trim_rcsum(skb, len + sizeof(struct ipv6hdr)))
- goto out;
- ip6h = ipv6_hdr(skb);
- if (!pskb_may_pull(skb, sizeof(struct udphdr)))
- goto out;
- uh = udp_hdr(skb);
- offset = (unsigned char *)(uh + 1) - skb->data;
- ulen = ntohs(uh->len);
- data_len = skb->len - offset;
- source = ntohs(uh->source);
- if (ulen != skb->len)
- goto out;
- if (udp6_csum_init(skb, uh, IPPROTO_UDP))
- goto out;
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (!ipv6_addr_equal(&np->local_ip.in6, &ip6h->daddr))
- continue;
- if (!ipv6_addr_equal(&np->remote_ip.in6, &ip6h->saddr))
- continue;
- if (np->local_port && np->local_port != ntohs(uh->dest))
- continue;
-
- np->rx_skb_hook(np, source, skb, offset, data_len);
- hits++;
- }
-#endif
- }
-
- if (!hits)
- goto out;
-
- kfree_skb(skb);
- return 1;
-
-out:
- if (atomic_read(&trapped)) {
- kfree_skb(skb);
- return 1;
- }
-
- return 0;
-}
-
void netpoll_print_options(struct netpoll *np)
{
np_info(np, "local port %d\n", np->local_port);
@@ -948,6 +517,7 @@
{
char *cur=opt, *delim;
int ipv6;
+ bool ipversion_set = false;
if (*cur != '@') {
if ((delim = strchr(cur, '@')) == NULL)
@@ -960,6 +530,7 @@
cur++;
if (*cur != '/') {
+ ipversion_set = true;
if ((delim = strchr(cur, '/')) == NULL)
goto parse_failed;
*delim = 0;
@@ -1002,7 +573,7 @@
ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip);
if (ipv6 < 0)
goto parse_failed;
- else if (np->ipv6 != (bool)ipv6)
+ else if (ipversion_set && np->ipv6 != (bool)ipv6)
goto parse_failed;
else
np->ipv6 = (bool)ipv6;
@@ -1024,11 +595,10 @@
}
EXPORT_SYMBOL(netpoll_parse_options);
-int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
{
struct netpoll_info *npinfo;
const struct net_device_ops *ops;
- unsigned long flags;
int err;
np->dev = ndev;
@@ -1044,18 +614,13 @@
}
if (!ndev->npinfo) {
- npinfo = kmalloc(sizeof(*npinfo), gfp);
+ npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
if (!npinfo) {
err = -ENOMEM;
goto out;
}
- npinfo->rx_flags = 0;
- INIT_LIST_HEAD(&npinfo->rx_np);
-
- spin_lock_init(&npinfo->rx_lock);
sema_init(&npinfo->dev_lock, 1);
- skb_queue_head_init(&npinfo->neigh_tx);
skb_queue_head_init(&npinfo->txq);
INIT_DELAYED_WORK(&npinfo->tx_work, queue_process);
@@ -1063,7 +628,7 @@
ops = np->dev->netdev_ops;
if (ops->ndo_netpoll_setup) {
- err = ops->ndo_netpoll_setup(ndev, npinfo, gfp);
+ err = ops->ndo_netpoll_setup(ndev, npinfo);
if (err)
goto free_npinfo;
}
@@ -1074,13 +639,6 @@
npinfo->netpoll = np;
- if (np->rx_skb_hook) {
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- npinfo->rx_flags |= NETPOLL_RX_ENABLED;
- list_add_tail(&np->rx, &npinfo->rx_np);
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
- }
-
/* last thing to do is link it to the net device structure */
rcu_assign_pointer(ndev->npinfo, npinfo);
@@ -1202,7 +760,7 @@
/* fill up the skb queue */
refill_skbs();
- err = __netpoll_setup(np, ndev, GFP_KERNEL);
+ err = __netpoll_setup(np, ndev);
if (err)
goto put;
@@ -1229,7 +787,6 @@
struct netpoll_info *npinfo =
container_of(rcu_head, struct netpoll_info, rcu);
- skb_queue_purge(&npinfo->neigh_tx);
skb_queue_purge(&npinfo->txq);
/* we can't call cancel_delayed_work_sync here, as we are in softirq */
@@ -1245,7 +802,6 @@
void __netpoll_cleanup(struct netpoll *np)
{
struct netpoll_info *npinfo;
- unsigned long flags;
/* rtnl_dereference would be preferable here but
* rcu_cleanup_netpoll path can put us in here safely without
@@ -1255,14 +811,6 @@
if (!npinfo)
return;
- if (!list_empty(&npinfo->rx_np)) {
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_del(&np->rx);
- if (list_empty(&npinfo->rx_np))
- npinfo->rx_flags &= ~NETPOLL_RX_ENABLED;
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
- }
-
synchronize_srcu(&netpoll_srcu);
if (atomic_dec_and_test(&npinfo->refcnt)) {
@@ -1272,7 +820,7 @@
if (ops->ndo_netpoll_cleanup)
ops->ndo_netpoll_cleanup(np->dev);
- rcu_assign_pointer(np->dev->npinfo, NULL);
+ RCU_INIT_POINTER(np->dev->npinfo, NULL);
call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info);
}
}
@@ -1306,18 +854,3 @@
rtnl_unlock();
}
EXPORT_SYMBOL(netpoll_cleanup);
-
-int netpoll_trap(void)
-{
- return atomic_read(&trapped);
-}
-EXPORT_SYMBOL(netpoll_trap);
-
-void netpoll_set_trap(int trap)
-{
- if (trap)
- atomic_inc(&trapped);
- else
- atomic_dec(&trapped);
-}
-EXPORT_SYMBOL(netpoll_set_trap);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index fdac61c..d0dac57 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -476,23 +476,22 @@
static ssize_t pgctrl_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
- int err = 0;
char data[128];
struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id);
- if (!capable(CAP_NET_ADMIN)) {
- err = -EPERM;
- goto out;
- }
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (count == 0)
+ return -EINVAL;
if (count > sizeof(data))
count = sizeof(data);
- if (copy_from_user(data, buf, count)) {
- err = -EFAULT;
- goto out;
- }
- data[count - 1] = 0; /* Make string */
+ if (copy_from_user(data, buf, count))
+ return -EFAULT;
+
+ data[count - 1] = 0; /* Strip trailing '\n' and terminate string */
if (!strcmp(data, "stop"))
pktgen_stop_all_threads_ifs(pn);
@@ -506,10 +505,7 @@
else
pr_warning("Unknown command: %s\n", data);
- err = count;
-
-out:
- return err;
+ return count;
}
static int pgctrl_open(struct inode *inode, struct file *file)
@@ -1251,7 +1247,13 @@
"Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s",
f,
"IPSRC_RND, IPDST_RND, UDPSRC_RND, UDPDST_RND, "
- "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, IPSEC, NODE_ALLOC\n");
+ "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, "
+ "MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, "
+ "QUEUE_MAP_RND, QUEUE_MAP_CPU, UDPCSUM, "
+#ifdef CONFIG_XFRM
+ "IPSEC, "
+#endif
+ "NODE_ALLOC\n");
return count;
}
sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags);
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index 4425148..467f326 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -221,5 +221,4 @@
out:
spin_unlock_bh(&fastopenq->lock);
sock_put(lsk);
- return;
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 393b1bc..e7c6006 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -374,7 +374,7 @@
if (!master_dev)
return 0;
ops = master_dev->rtnl_link_ops;
- if (!ops->get_slave_size)
+ if (!ops || !ops->get_slave_size)
return 0;
/* IFLA_INFO_SLAVE_DATA + nested data */
return nla_total_size(sizeof(struct nlattr)) +
@@ -1121,6 +1121,70 @@
return -EMSGSIZE;
}
+static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
+ [IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 },
+ [IFLA_ADDRESS] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
+ [IFLA_BROADCAST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
+ [IFLA_MAP] = { .len = sizeof(struct rtnl_link_ifmap) },
+ [IFLA_MTU] = { .type = NLA_U32 },
+ [IFLA_LINK] = { .type = NLA_U32 },
+ [IFLA_MASTER] = { .type = NLA_U32 },
+ [IFLA_CARRIER] = { .type = NLA_U8 },
+ [IFLA_TXQLEN] = { .type = NLA_U32 },
+ [IFLA_WEIGHT] = { .type = NLA_U32 },
+ [IFLA_OPERSTATE] = { .type = NLA_U8 },
+ [IFLA_LINKMODE] = { .type = NLA_U8 },
+ [IFLA_LINKINFO] = { .type = NLA_NESTED },
+ [IFLA_NET_NS_PID] = { .type = NLA_U32 },
+ [IFLA_NET_NS_FD] = { .type = NLA_U32 },
+ [IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 },
+ [IFLA_VFINFO_LIST] = {. type = NLA_NESTED },
+ [IFLA_VF_PORTS] = { .type = NLA_NESTED },
+ [IFLA_PORT_SELF] = { .type = NLA_NESTED },
+ [IFLA_AF_SPEC] = { .type = NLA_NESTED },
+ [IFLA_EXT_MASK] = { .type = NLA_U32 },
+ [IFLA_PROMISCUITY] = { .type = NLA_U32 },
+ [IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 },
+ [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 },
+ [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN },
+};
+
+static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
+ [IFLA_INFO_KIND] = { .type = NLA_STRING },
+ [IFLA_INFO_DATA] = { .type = NLA_NESTED },
+ [IFLA_INFO_SLAVE_KIND] = { .type = NLA_STRING },
+ [IFLA_INFO_SLAVE_DATA] = { .type = NLA_NESTED },
+};
+
+static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
+ [IFLA_VF_INFO] = { .type = NLA_NESTED },
+};
+
+static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
+ [IFLA_VF_MAC] = { .type = NLA_BINARY,
+ .len = sizeof(struct ifla_vf_mac) },
+ [IFLA_VF_VLAN] = { .type = NLA_BINARY,
+ .len = sizeof(struct ifla_vf_vlan) },
+ [IFLA_VF_TX_RATE] = { .type = NLA_BINARY,
+ .len = sizeof(struct ifla_vf_tx_rate) },
+ [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY,
+ .len = sizeof(struct ifla_vf_spoofchk) },
+};
+
+static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
+ [IFLA_PORT_VF] = { .type = NLA_U32 },
+ [IFLA_PORT_PROFILE] = { .type = NLA_STRING,
+ .len = PORT_PROFILE_MAX },
+ [IFLA_PORT_VSI_TYPE] = { .type = NLA_BINARY,
+ .len = sizeof(struct ifla_port_vsi)},
+ [IFLA_PORT_INSTANCE_UUID] = { .type = NLA_BINARY,
+ .len = PORT_UUID_MAX },
+ [IFLA_PORT_HOST_UUID] = { .type = NLA_STRING,
+ .len = PORT_UUID_MAX },
+ [IFLA_PORT_REQUEST] = { .type = NLA_U8, },
+ [IFLA_PORT_RESPONSE] = { .type = NLA_U16, },
+};
+
static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
@@ -1170,70 +1234,11 @@
return skb->len;
}
-const struct nla_policy ifla_policy[IFLA_MAX+1] = {
- [IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 },
- [IFLA_ADDRESS] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
- [IFLA_BROADCAST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
- [IFLA_MAP] = { .len = sizeof(struct rtnl_link_ifmap) },
- [IFLA_MTU] = { .type = NLA_U32 },
- [IFLA_LINK] = { .type = NLA_U32 },
- [IFLA_MASTER] = { .type = NLA_U32 },
- [IFLA_CARRIER] = { .type = NLA_U8 },
- [IFLA_TXQLEN] = { .type = NLA_U32 },
- [IFLA_WEIGHT] = { .type = NLA_U32 },
- [IFLA_OPERSTATE] = { .type = NLA_U8 },
- [IFLA_LINKMODE] = { .type = NLA_U8 },
- [IFLA_LINKINFO] = { .type = NLA_NESTED },
- [IFLA_NET_NS_PID] = { .type = NLA_U32 },
- [IFLA_NET_NS_FD] = { .type = NLA_U32 },
- [IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 },
- [IFLA_VFINFO_LIST] = {. type = NLA_NESTED },
- [IFLA_VF_PORTS] = { .type = NLA_NESTED },
- [IFLA_PORT_SELF] = { .type = NLA_NESTED },
- [IFLA_AF_SPEC] = { .type = NLA_NESTED },
- [IFLA_EXT_MASK] = { .type = NLA_U32 },
- [IFLA_PROMISCUITY] = { .type = NLA_U32 },
- [IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 },
- [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 },
- [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN },
-};
-EXPORT_SYMBOL(ifla_policy);
-
-static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
- [IFLA_INFO_KIND] = { .type = NLA_STRING },
- [IFLA_INFO_DATA] = { .type = NLA_NESTED },
- [IFLA_INFO_SLAVE_KIND] = { .type = NLA_STRING },
- [IFLA_INFO_SLAVE_DATA] = { .type = NLA_NESTED },
-};
-
-static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
- [IFLA_VF_INFO] = { .type = NLA_NESTED },
-};
-
-static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
- [IFLA_VF_MAC] = { .type = NLA_BINARY,
- .len = sizeof(struct ifla_vf_mac) },
- [IFLA_VF_VLAN] = { .type = NLA_BINARY,
- .len = sizeof(struct ifla_vf_vlan) },
- [IFLA_VF_TX_RATE] = { .type = NLA_BINARY,
- .len = sizeof(struct ifla_vf_tx_rate) },
- [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY,
- .len = sizeof(struct ifla_vf_spoofchk) },
-};
-
-static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
- [IFLA_PORT_VF] = { .type = NLA_U32 },
- [IFLA_PORT_PROFILE] = { .type = NLA_STRING,
- .len = PORT_PROFILE_MAX },
- [IFLA_PORT_VSI_TYPE] = { .type = NLA_BINARY,
- .len = sizeof(struct ifla_port_vsi)},
- [IFLA_PORT_INSTANCE_UUID] = { .type = NLA_BINARY,
- .len = PORT_UUID_MAX },
- [IFLA_PORT_HOST_UUID] = { .type = NLA_STRING,
- .len = PORT_UUID_MAX },
- [IFLA_PORT_REQUEST] = { .type = NLA_U8, },
- [IFLA_PORT_RESPONSE] = { .type = NLA_U16, },
-};
+int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len)
+{
+ return nla_parse(tb, IFLA_MAX, head, len, ifla_policy);
+}
+EXPORT_SYMBOL(rtnl_nla_parse_ifla);
struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[])
{
@@ -1963,16 +1968,21 @@
dev->ifindex = ifm->ifi_index;
- if (ops->newlink)
+ if (ops->newlink) {
err = ops->newlink(net, dev, tb, data);
- else
+ /* Drivers should call free_netdev() in ->destructor
+ * and unregister it on failure so that device could be
+ * finally freed in rtnl_unlock.
+ */
+ if (err < 0)
+ goto out;
+ } else {
err = register_netdevice(dev);
-
- if (err < 0) {
- free_netdev(dev);
- goto out;
+ if (err < 0) {
+ free_netdev(dev);
+ goto out;
+ }
}
-
err = rtnl_configure_link(dev, ifm);
if (err < 0)
unregister_netdevice(dev);
@@ -2116,12 +2126,13 @@
static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
struct net_device *dev,
u8 *addr, u32 pid, u32 seq,
- int type, unsigned int flags)
+ int type, unsigned int flags,
+ int nlflags)
{
struct nlmsghdr *nlh;
struct ndmsg *ndm;
- nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), NLM_F_MULTI);
+ nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), nlflags);
if (!nlh)
return -EMSGSIZE;
@@ -2159,7 +2170,7 @@
if (!skb)
goto errout;
- err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF);
+ err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF, 0);
if (err < 0) {
kfree_skb(skb);
goto errout;
@@ -2384,7 +2395,8 @@
err = nlmsg_populate_fdb_fill(skb, dev, ha->addr,
portid, seq,
- RTM_NEWNEIGH, NTF_SELF);
+ RTM_NEWNEIGH, NTF_SELF,
+ NLM_F_MULTI);
if (err < 0)
return err;
skip:
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5976ef0..30c7d35 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -707,9 +707,6 @@
new->mark = old->mark;
new->skb_iif = old->skb_iif;
__nf_copy(new, old);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
- new->nf_trace = old->nf_trace;
-#endif
#ifdef CONFIG_NET_SCHED
new->tc_index = old->tc_index;
#ifdef CONFIG_NET_CLS_ACT
@@ -2130,25 +2127,31 @@
*
* The `hlen` as calculated by skb_zerocopy_headlen() specifies the
* headroom in the `to` buffer.
+ *
+ * Return value:
+ * 0: everything is OK
+ * -ENOMEM: couldn't orphan frags of @from due to lack of memory
+ * -EFAULT: skb_copy_bits() found some problem with skb geometry
*/
-void
-skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
+int
+skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen)
{
int i, j = 0;
int plen = 0; /* length of skb->head fragment */
+ int ret;
struct page *page;
unsigned int offset;
BUG_ON(!from->head_frag && !hlen);
/* dont bother with small payloads */
- if (len <= skb_tailroom(to)) {
- skb_copy_bits(from, 0, skb_put(to, len), len);
- return;
- }
+ if (len <= skb_tailroom(to))
+ return skb_copy_bits(from, 0, skb_put(to, len), len);
if (hlen) {
- skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+ ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+ if (unlikely(ret))
+ return ret;
len -= hlen;
} else {
plen = min_t(int, skb_headlen(from), len);
@@ -2166,6 +2169,11 @@
to->len += len + plen;
to->data_len += len + plen;
+ if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) {
+ skb_tx_error(from);
+ return -ENOMEM;
+ }
+
for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
if (!len)
break;
@@ -2176,6 +2184,8 @@
j++;
}
skb_shinfo(to)->nr_frags = j;
+
+ return 0;
}
EXPORT_SYMBOL_GPL(skb_zerocopy);
@@ -2841,81 +2851,85 @@
/**
* skb_segment - Perform protocol segmentation on skb.
- * @skb: buffer to segment
+ * @head_skb: buffer to segment
* @features: features for the output path (see dev->features)
*
* This function performs segmentation on the given skb. It returns
* a pointer to the first in a list of new skbs for the segments.
* In case of error it returns ERR_PTR(err).
*/
-struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
+struct sk_buff *skb_segment(struct sk_buff *head_skb,
+ netdev_features_t features)
{
struct sk_buff *segs = NULL;
struct sk_buff *tail = NULL;
- struct sk_buff *fskb = skb_shinfo(skb)->frag_list;
- skb_frag_t *skb_frag = skb_shinfo(skb)->frags;
- unsigned int mss = skb_shinfo(skb)->gso_size;
- unsigned int doffset = skb->data - skb_mac_header(skb);
+ struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list;
+ skb_frag_t *frag = skb_shinfo(head_skb)->frags;
+ unsigned int mss = skb_shinfo(head_skb)->gso_size;
+ unsigned int doffset = head_skb->data - skb_mac_header(head_skb);
+ struct sk_buff *frag_skb = head_skb;
unsigned int offset = doffset;
- unsigned int tnl_hlen = skb_tnl_header_len(skb);
+ unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
unsigned int headroom;
unsigned int len;
__be16 proto;
bool csum;
int sg = !!(features & NETIF_F_SG);
- int nfrags = skb_shinfo(skb)->nr_frags;
+ int nfrags = skb_shinfo(head_skb)->nr_frags;
int err = -ENOMEM;
int i = 0;
int pos;
+ int dummy;
- proto = skb_network_protocol(skb);
+ proto = skb_network_protocol(head_skb, &dummy);
if (unlikely(!proto))
return ERR_PTR(-EINVAL);
csum = !!can_checksum_protocol(features, proto);
- __skb_push(skb, doffset);
- headroom = skb_headroom(skb);
- pos = skb_headlen(skb);
+ __skb_push(head_skb, doffset);
+ headroom = skb_headroom(head_skb);
+ pos = skb_headlen(head_skb);
do {
struct sk_buff *nskb;
- skb_frag_t *frag;
+ skb_frag_t *nskb_frag;
int hsize;
int size;
- len = skb->len - offset;
+ len = head_skb->len - offset;
if (len > mss)
len = mss;
- hsize = skb_headlen(skb) - offset;
+ hsize = skb_headlen(head_skb) - offset;
if (hsize < 0)
hsize = 0;
if (hsize > len || !sg)
hsize = len;
- if (!hsize && i >= nfrags && skb_headlen(fskb) &&
- (skb_headlen(fskb) == len || sg)) {
- BUG_ON(skb_headlen(fskb) > len);
+ if (!hsize && i >= nfrags && skb_headlen(list_skb) &&
+ (skb_headlen(list_skb) == len || sg)) {
+ BUG_ON(skb_headlen(list_skb) > len);
i = 0;
- nfrags = skb_shinfo(fskb)->nr_frags;
- skb_frag = skb_shinfo(fskb)->frags;
- pos += skb_headlen(fskb);
+ nfrags = skb_shinfo(list_skb)->nr_frags;
+ frag = skb_shinfo(list_skb)->frags;
+ frag_skb = list_skb;
+ pos += skb_headlen(list_skb);
while (pos < offset + len) {
BUG_ON(i >= nfrags);
- size = skb_frag_size(skb_frag);
+ size = skb_frag_size(frag);
if (pos + size > offset + len)
break;
i++;
pos += size;
- skb_frag++;
+ frag++;
}
- nskb = skb_clone(fskb, GFP_ATOMIC);
- fskb = fskb->next;
+ nskb = skb_clone(list_skb, GFP_ATOMIC);
+ list_skb = list_skb->next;
if (unlikely(!nskb))
goto err;
@@ -2936,7 +2950,7 @@
__skb_push(nskb, doffset);
} else {
nskb = __alloc_skb(hsize + doffset + headroom,
- GFP_ATOMIC, skb_alloc_rx_flag(skb),
+ GFP_ATOMIC, skb_alloc_rx_flag(head_skb),
NUMA_NO_NODE);
if (unlikely(!nskb))
@@ -2952,12 +2966,12 @@
segs = nskb;
tail = nskb;
- __copy_skb_header(nskb, skb);
- nskb->mac_len = skb->mac_len;
+ __copy_skb_header(nskb, head_skb);
+ nskb->mac_len = head_skb->mac_len;
skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom);
- skb_copy_from_linear_data_offset(skb, -tnl_hlen,
+ skb_copy_from_linear_data_offset(head_skb, -tnl_hlen,
nskb->data - tnl_hlen,
doffset + tnl_hlen);
@@ -2966,30 +2980,32 @@
if (!sg) {
nskb->ip_summed = CHECKSUM_NONE;
- nskb->csum = skb_copy_and_csum_bits(skb, offset,
+ nskb->csum = skb_copy_and_csum_bits(head_skb, offset,
skb_put(nskb, len),
len, 0);
continue;
}
- frag = skb_shinfo(nskb)->frags;
+ nskb_frag = skb_shinfo(nskb)->frags;
- skb_copy_from_linear_data_offset(skb, offset,
+ skb_copy_from_linear_data_offset(head_skb, offset,
skb_put(nskb, hsize), hsize);
- skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG;
+ skb_shinfo(nskb)->tx_flags = skb_shinfo(head_skb)->tx_flags &
+ SKBTX_SHARED_FRAG;
while (pos < offset + len) {
if (i >= nfrags) {
- BUG_ON(skb_headlen(fskb));
+ BUG_ON(skb_headlen(list_skb));
i = 0;
- nfrags = skb_shinfo(fskb)->nr_frags;
- skb_frag = skb_shinfo(fskb)->frags;
+ nfrags = skb_shinfo(list_skb)->nr_frags;
+ frag = skb_shinfo(list_skb)->frags;
+ frag_skb = list_skb;
BUG_ON(!nfrags);
- fskb = fskb->next;
+ list_skb = list_skb->next;
}
if (unlikely(skb_shinfo(nskb)->nr_frags >=
@@ -3000,27 +3016,30 @@
goto err;
}
- *frag = *skb_frag;
- __skb_frag_ref(frag);
- size = skb_frag_size(frag);
+ if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC)))
+ goto err;
+
+ *nskb_frag = *frag;
+ __skb_frag_ref(nskb_frag);
+ size = skb_frag_size(nskb_frag);
if (pos < offset) {
- frag->page_offset += offset - pos;
- skb_frag_size_sub(frag, offset - pos);
+ nskb_frag->page_offset += offset - pos;
+ skb_frag_size_sub(nskb_frag, offset - pos);
}
skb_shinfo(nskb)->nr_frags++;
if (pos + size <= offset + len) {
i++;
- skb_frag++;
+ frag++;
pos += size;
} else {
- skb_frag_size_sub(frag, pos + size - (offset + len));
+ skb_frag_size_sub(nskb_frag, pos + size - (offset + len));
goto skip_fraglist;
}
- frag++;
+ nskb_frag++;
}
skip_fraglist:
@@ -3034,7 +3053,7 @@
nskb->len - doffset, 0);
nskb->ip_summed = CHECKSUM_NONE;
}
- } while ((offset += len) < skb->len);
+ } while ((offset += len) < head_skb->len);
return segs;
@@ -3281,6 +3300,32 @@
return elt;
}
+/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given
+ * sglist without mark the sg which contain last skb data as the end.
+ * So the caller can mannipulate sg list as will when padding new data after
+ * the first call without calling sg_unmark_end to expend sg list.
+ *
+ * Scenario to use skb_to_sgvec_nomark:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec_nomark(payload1)
+ * 3. skb_to_sgvec_nomark(payload2)
+ *
+ * This is equivalent to:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec(payload1)
+ * 3. sg_unmark_end
+ * 4. skb_to_sgvec(payload2)
+ *
+ * When mapping mutilple payload conditionally, skb_to_sgvec_nomark
+ * is more preferable.
+ */
+int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
+ int offset, int len)
+{
+ return __skb_to_sgvec(skb, sg, offset, len);
+}
+EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark);
+
int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
{
int nsg = __skb_to_sgvec(skb, sg, offset, len);
@@ -3543,15 +3588,47 @@
return 0;
}
+#define MAX_TCP_HDR_LEN (15 * 4)
+
+static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb,
+ typeof(IPPROTO_IP) proto,
+ unsigned int off)
+{
+ switch (proto) {
+ int err;
+
+ case IPPROTO_TCP:
+ err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr),
+ off + MAX_TCP_HDR_LEN);
+ if (!err && !skb_partial_csum_set(skb, off,
+ offsetof(struct tcphdr,
+ check)))
+ err = -EPROTO;
+ return err ? ERR_PTR(err) : &tcp_hdr(skb)->check;
+
+ case IPPROTO_UDP:
+ err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr),
+ off + sizeof(struct udphdr));
+ if (!err && !skb_partial_csum_set(skb, off,
+ offsetof(struct udphdr,
+ check)))
+ err = -EPROTO;
+ return err ? ERR_PTR(err) : &udp_hdr(skb)->check;
+ }
+
+ return ERR_PTR(-EPROTO);
+}
+
/* This value should be large enough to cover a tagged ethernet header plus
* maximally sized IP and TCP or UDP headers.
*/
#define MAX_IP_HDR_LEN 128
-static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate)
+static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate)
{
unsigned int off;
bool fragment;
+ __sum16 *csum;
int err;
fragment = false;
@@ -3572,51 +3649,15 @@
if (fragment)
goto out;
- switch (ip_hdr(skb)->protocol) {
- case IPPROTO_TCP:
- err = skb_maybe_pull_tail(skb,
- off + sizeof(struct tcphdr),
- MAX_IP_HDR_LEN);
- if (err < 0)
- goto out;
+ csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off);
+ if (IS_ERR(csum))
+ return PTR_ERR(csum);
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct tcphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate)
- tcp_hdr(skb)->check =
- ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
- ip_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_TCP, 0);
- break;
- case IPPROTO_UDP:
- err = skb_maybe_pull_tail(skb,
- off + sizeof(struct udphdr),
- MAX_IP_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct udphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate)
- udp_hdr(skb)->check =
- ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
- ip_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_UDP, 0);
- break;
- default:
- goto out;
- }
-
+ if (recalculate)
+ *csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr,
+ skb->len - off,
+ ip_hdr(skb)->protocol, 0);
err = 0;
out:
@@ -3639,6 +3680,7 @@
unsigned int len;
bool fragment;
bool done;
+ __sum16 *csum;
fragment = false;
done = false;
@@ -3716,51 +3758,14 @@
if (!done || fragment)
goto out;
- switch (nexthdr) {
- case IPPROTO_TCP:
- err = skb_maybe_pull_tail(skb,
- off + sizeof(struct tcphdr),
- MAX_IPV6_HDR_LEN);
- if (err < 0)
- goto out;
+ csum = skb_checksum_setup_ip(skb, nexthdr, off);
+ if (IS_ERR(csum))
+ return PTR_ERR(csum);
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct tcphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate)
- tcp_hdr(skb)->check =
- ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
- &ipv6_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_TCP, 0);
- break;
- case IPPROTO_UDP:
- err = skb_maybe_pull_tail(skb,
- off + sizeof(struct udphdr),
- MAX_IPV6_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct udphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate)
- udp_hdr(skb)->check =
- ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
- &ipv6_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_UDP, 0);
- break;
- default:
- goto out;
- }
-
+ if (recalculate)
+ *csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr,
+ skb->len - off, nexthdr, 0);
err = 0;
out:
@@ -3778,7 +3783,7 @@
switch (skb->protocol) {
case htons(ETH_P_IP):
- err = skb_checksum_setup_ip(skb, recalculate);
+ err = skb_checksum_setup_ipv4(skb, recalculate);
break;
case htons(ETH_P_IPV6):
diff --git a/net/core/sock.c b/net/core/sock.c
index 0c127dc..c0fc6bd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1775,7 +1775,9 @@
while (order) {
if (npages >= 1 << order) {
page = alloc_pages(sk->sk_allocation |
- __GFP_COMP | __GFP_NOWARN,
+ __GFP_COMP |
+ __GFP_NOWARN |
+ __GFP_NORETRY,
order);
if (page)
goto fill_page;
@@ -1845,7 +1847,7 @@
gfp_t gfp = prio;
if (order)
- gfp |= __GFP_COMP | __GFP_NOWARN;
+ gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
pfrag->page = alloc_pages(gfp, order);
if (likely(pfrag->page)) {
pfrag->offset = 0;
@@ -2355,10 +2357,13 @@
if (sk->sk_backlog.tail)
__release_sock(sk);
+ /* Warning : release_cb() might need to release sk ownership,
+ * ie call sock_release_ownership(sk) before us.
+ */
if (sk->sk_prot->release_cb)
sk->sk_prot->release_cb(sk);
- sk->sk_lock.owned = 0;
+ sock_release_ownership(sk);
if (waitqueue_active(&sk->sk_lock.wq))
wake_up(&sk->sk_lock.wq);
spin_unlock_bh(&sk->sk_lock.slock);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index a0e9cf6..d7af188 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -52,9 +52,10 @@
int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
struct sk_buff *skb, int attrtype)
{
- struct nlattr *attr;
+ struct sock_fprog_kern *fprog;
struct sk_filter *filter;
- unsigned int len;
+ struct nlattr *attr;
+ unsigned int flen;
int err = 0;
if (!ns_capable(user_ns, CAP_NET_ADMIN)) {
@@ -63,24 +64,20 @@
}
rcu_read_lock();
-
filter = rcu_dereference(sk->sk_filter);
- len = filter ? filter->len * sizeof(struct sock_filter) : 0;
+ if (!filter)
+ goto out;
- attr = nla_reserve(skb, attrtype, len);
+ fprog = filter->orig_prog;
+ flen = sk_filter_proglen(fprog);
+
+ attr = nla_reserve(skb, attrtype, flen);
if (attr == NULL) {
err = -EMSGSIZE;
goto out;
}
- if (filter) {
- struct sock_filter *fb = (struct sock_filter *)nla_data(attr);
- int i;
-
- for (i = 0; i < filter->len; i++, fb++)
- sk_decode_filter(&filter->insns[i], fb);
- }
-
+ memcpy(nla_data(attr), fprog->filter, flen);
out:
rcu_read_unlock();
return err;
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index 661b5a4..9ff26b3 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -23,16 +23,19 @@
#include <linux/skbuff.h>
#include <linux/export.h>
-static struct sock_filter ptp_filter[] = {
- PTP_FILTER
-};
+static struct sk_filter *ptp_insns __read_mostly;
+
+unsigned int ptp_classify_raw(const struct sk_buff *skb)
+{
+ return SK_RUN_FILTER(ptp_insns, skb);
+}
+EXPORT_SYMBOL_GPL(ptp_classify_raw);
static unsigned int classify(const struct sk_buff *skb)
{
- if (likely(skb->dev &&
- skb->dev->phydev &&
+ if (likely(skb->dev && skb->dev->phydev &&
skb->dev->phydev->drv))
- return sk_run_filter(skb, ptp_filter);
+ return ptp_classify_raw(skb);
else
return PTP_CLASS_NONE;
}
@@ -60,11 +63,13 @@
if (likely(phydev->drv->txtstamp)) {
if (!atomic_inc_not_zero(&sk->sk_refcnt))
return;
+
clone = skb_clone(skb, GFP_ATOMIC);
if (!clone) {
sock_put(sk);
return;
}
+
clone->sk = sk;
phydev->drv->txtstamp(phydev, clone, type);
}
@@ -89,12 +94,15 @@
}
*skb_hwtstamps(skb) = *hwtstamps;
+
serr = SKB_EXT_ERR(skb);
memset(serr, 0, sizeof(*serr));
serr->ee.ee_errno = ENOMSG;
serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
skb->sk = NULL;
+
err = sock_queue_err_skb(sk, skb);
+
sock_put(sk);
if (err)
kfree_skb(skb);
@@ -135,5 +143,10 @@
void __init skb_timestamping_init(void)
{
- BUG_ON(sk_chk_filter(ptp_filter, ARRAY_SIZE(ptp_filter)));
+ static struct sock_filter ptp_filter[] = { PTP_FILTER };
+ struct sock_fprog ptp_prog = {
+ .len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
+ };
+
+ BUG_ON(sk_unattached_filter_create(&ptp_insns, &ptp_prog));
}
diff --git a/net/dccp/ccids/lib/tfrc.c b/net/dccp/ccids/lib/tfrc.c
index c073b81..62b5828 100644
--- a/net/dccp/ccids/lib/tfrc.c
+++ b/net/dccp/ccids/lib/tfrc.c
@@ -8,7 +8,7 @@
#include "tfrc.h"
#ifdef CONFIG_IP_DCCP_TFRC_DEBUG
-static bool tfrc_debug;
+bool tfrc_debug;
module_param(tfrc_debug, bool, 0644);
MODULE_PARM_DESC(tfrc_debug, "Enable TFRC debug messages");
#endif
diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h
index a3d8f7c..40ee7d6 100644
--- a/net/dccp/ccids/lib/tfrc.h
+++ b/net/dccp/ccids/lib/tfrc.h
@@ -21,6 +21,7 @@
#include "packet_history.h"
#ifdef CONFIG_IP_DCCP_TFRC_DEBUG
+extern bool tfrc_debug;
#define tfrc_pr_debug(format, a...) DCCP_PR_DEBUG(tfrc_debug, format, ##a)
#else
#define tfrc_pr_debug(format, a...)
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 2954dcb..4c04848 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -2104,8 +2104,6 @@
.notifier_call = dn_device_event,
};
-extern int dn_route_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *);
-
static struct packet_type dn_dix_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_DNA_RT),
.func = dn_route_rcv,
@@ -2353,9 +2351,6 @@
.sendpage = sock_no_sendpage,
};
-void dn_register_sysctl(void);
-void dn_unregister_sysctl(void);
-
MODULE_DESCRIPTION("The Linux DECnet Network Protocol");
MODULE_AUTHOR("Linux DECnet Project Team");
MODULE_LICENSE("GPL");
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index cac505f..e5302b7 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -209,7 +209,7 @@
/* Address substitution (IEC62439-3 pp 26, 50): replace mac
* address of outgoing frame with that of the outgoing slave's.
*/
- memcpy(hsr_ethhdr->ethhdr.h_source, skb->dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(hsr_ethhdr->ethhdr.h_source, skb->dev->dev_addr);
return dev_queue_xmit(skb);
}
@@ -346,7 +346,7 @@
/* Payload: MacAddressA */
hsr_sp = (typeof(hsr_sp)) skb_put(skb, sizeof(*hsr_sp));
- memcpy(hsr_sp->MacAddressA, hsr_dev->dev_addr, ETH_ALEN);
+ ether_addr_copy(hsr_sp->MacAddressA, hsr_dev->dev_addr);
dev_queue_xmit(skb);
return;
@@ -493,7 +493,7 @@
/* Default multicast address for HSR Supervision frames */
-static const unsigned char def_multicast_addr[ETH_ALEN] = {
+static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = {
0x01, 0x15, 0x4e, 0x00, 0x01, 0x00
};
@@ -519,7 +519,7 @@
hsr_priv->announce_timer.function = hsr_announce;
hsr_priv->announce_timer.data = (unsigned long) hsr_priv;
- memcpy(hsr_priv->sup_multicast_addr, def_multicast_addr, ETH_ALEN);
+ ether_addr_copy(hsr_priv->sup_multicast_addr, def_multicast_addr);
hsr_priv->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec;
/* FIXME: should I modify the value of these?
@@ -547,7 +547,7 @@
hsr_dev->features |= NETIF_F_VLAN_CHALLENGED;
/* Set hsr_dev's MAC address to that of mac_slave1 */
- memcpy(hsr_dev->dev_addr, hsr_priv->slave[0]->dev_addr, ETH_ALEN);
+ ether_addr_copy(hsr_dev->dev_addr, hsr_priv->slave[0]->dev_addr);
/* Set required header length */
for (i = 0; i < HSR_MAX_SLAVE; i++) {
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 327060c..83e5844 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -108,8 +108,8 @@
if (!node)
return -ENOMEM;
- memcpy(node->MacAddressA, addr_a, ETH_ALEN);
- memcpy(node->MacAddressB, addr_b, ETH_ALEN);
+ ether_addr_copy(node->MacAddressA, addr_a);
+ ether_addr_copy(node->MacAddressB, addr_b);
rcu_read_lock();
oldnode = list_first_or_null_rcu(self_node_db,
@@ -199,7 +199,7 @@
/* Node is known, but frame was received from an unknown
* address. Node is PICS_SUBS capable; merge its AddrB.
*/
- memcpy(node->MacAddressB, hsr_ethsup->ethhdr.h_source, ETH_ALEN);
+ ether_addr_copy(node->MacAddressB, hsr_ethsup->ethhdr.h_source);
node->AddrB_if = dev_idx;
return node;
}
@@ -208,8 +208,8 @@
if (!node)
return NULL;
- memcpy(node->MacAddressA, hsr_sp->MacAddressA, ETH_ALEN);
- memcpy(node->MacAddressB, hsr_ethsup->ethhdr.h_source, ETH_ALEN);
+ ether_addr_copy(node->MacAddressA, hsr_sp->MacAddressA);
+ ether_addr_copy(node->MacAddressB, hsr_ethsup->ethhdr.h_source);
if (!ether_addr_equal(hsr_sp->MacAddressA, hsr_ethsup->ethhdr.h_source))
node->AddrB_if = dev_idx;
else
@@ -250,7 +250,7 @@
rcu_read_lock();
node = find_node_by_AddrB(&hsr_priv->node_db, ethhdr->h_source);
if (node)
- memcpy(ethhdr->h_source, node->MacAddressA, ETH_ALEN);
+ ether_addr_copy(ethhdr->h_source, node->MacAddressA);
rcu_read_unlock();
}
@@ -272,7 +272,7 @@
rcu_read_lock();
node = find_node_by_AddrA(&hsr_priv->node_db, ethhdr->h_dest);
if (node && (node->AddrB_if == dev_idx))
- memcpy(ethhdr->h_dest, node->MacAddressB, ETH_ALEN);
+ ether_addr_copy(ethhdr->h_dest, node->MacAddressB);
rcu_read_unlock();
}
@@ -297,7 +297,7 @@
void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx)
{
- if ((dev_idx < 0) || (dev_idx >= HSR_MAX_DEV)) {
+ if ((dev_idx < 0) || (dev_idx >= HSR_MAX_SLAVE)) {
WARN_ONCE(1, "%s: Invalid dev_idx (%d)\n", __func__, dev_idx);
return;
}
@@ -428,13 +428,13 @@
node = list_first_or_null_rcu(&hsr_priv->node_db,
struct node_entry, mac_list);
if (node)
- memcpy(addr, node->MacAddressA, ETH_ALEN);
+ ether_addr_copy(addr, node->MacAddressA);
return node;
}
node = _pos;
list_for_each_entry_continue_rcu(node, &hsr_priv->node_db, mac_list) {
- memcpy(addr, node->MacAddressA, ETH_ALEN);
+ ether_addr_copy(addr, node->MacAddressA);
return node;
}
@@ -462,7 +462,7 @@
return -ENOENT; /* No such entry */
}
- memcpy(addr_b, node->MacAddressB, ETH_ALEN);
+ ether_addr_copy(addr_b, node->MacAddressB);
tdiff = jiffies - node->time_in[HSR_DEV_SLAVE_A];
if (node->time_in_stale[HSR_DEV_SLAVE_A])
diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
index af68dd8..3fee521 100644
--- a/net/hsr/hsr_main.c
+++ b/net/hsr/hsr_main.c
@@ -138,8 +138,8 @@
break;
if (dev == hsr_priv->slave[0])
- memcpy(hsr_priv->dev->dev_addr,
- hsr_priv->slave[0]->dev_addr, ETH_ALEN);
+ ether_addr_copy(hsr_priv->dev->dev_addr,
+ hsr_priv->slave[0]->dev_addr);
/* Make sure we recognize frames from ourselves in hsr_rcv() */
res = hsr_create_self_node(&hsr_priv->self_node_db,
@@ -459,7 +459,7 @@
static void __exit hsr_exit(void)
{
unregister_netdevice_notifier(&hsr_nb);
- del_timer(&prune_timer);
+ del_timer_sync(&prune_timer);
hsr_netlink_exit();
dev_remove_pack(&hsr_pt);
}
diff --git a/net/ieee802154/6lowpan_iphc.c b/net/ieee802154/6lowpan_iphc.c
index 860aa2d..211b568 100644
--- a/net/ieee802154/6lowpan_iphc.c
+++ b/net/ieee802154/6lowpan_iphc.c
@@ -54,11 +54,10 @@
#include <linux/if_arp.h>
#include <linux/module.h>
#include <linux/netdevice.h>
+#include <net/6lowpan.h>
#include <net/ipv6.h>
#include <net/af_ieee802154.h>
-#include "6lowpan.h"
-
/*
* Uncompress address function for source and
* destination address(non-multicast).
diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan_rtnl.c
similarity index 64%
rename from net/ieee802154/6lowpan.c
rename to net/ieee802154/6lowpan_rtnl.c
index 48b25c0..0f5a69e 100644
--- a/net/ieee802154/6lowpan.c
+++ b/net/ieee802154/6lowpan_rtnl.c
@@ -1,10 +1,8 @@
-/*
- * Copyright 2011, Siemens AG
+/* Copyright 2011, Siemens AG
* written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
*/
-/*
- * Based on patches from Jon Smirl <jonsmirl@gmail.com>
+/* Based on patches from Jon Smirl <jonsmirl@gmail.com>
* Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com>
*
* This program is free software; you can redistribute it and/or modify
@@ -15,10 +13,6 @@
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
*/
/* Jon's code is based on 6lowpan implementation for Contiki which is:
@@ -58,9 +52,10 @@
#include <net/af_ieee802154.h>
#include <net/ieee802154.h>
#include <net/ieee802154_netdev.h>
+#include <net/6lowpan.h>
#include <net/ipv6.h>
-#include "6lowpan.h"
+#include "reassembly.h"
static LIST_HEAD(lowpan_devices);
@@ -68,7 +63,7 @@
struct lowpan_dev_info {
struct net_device *real_dev; /* real WPAN device ptr */
struct mutex dev_list_mtx; /* mutex for list ops */
- unsigned short fragment_tag;
+ __be16 fragment_tag;
};
struct lowpan_dev_record {
@@ -76,18 +71,6 @@
struct list_head list;
};
-struct lowpan_fragment {
- struct sk_buff *skb; /* skb to be assembled */
- u16 length; /* length to be assemled */
- u32 bytes_rcv; /* bytes received */
- u16 tag; /* current fragment tag */
- struct timer_list timer; /* assembling timer */
- struct list_head list; /* fragments list */
-};
-
-static LIST_HEAD(lowpan_fragments);
-static DEFINE_SPINLOCK(flist_lock);
-
static inline struct
lowpan_dev_info *lowpan_dev_info(const struct net_device *dev)
{
@@ -106,7 +89,6 @@
unsigned short type, const void *_daddr,
const void *_saddr, unsigned int len)
{
- struct ipv6hdr *hdr;
const u8 *saddr = _saddr;
const u8 *daddr = _daddr;
struct ieee802154_addr sa, da;
@@ -117,8 +99,6 @@
if (type != ETH_P_IPV6)
return 0;
- hdr = ipv6_hdr(skb);
-
if (!saddr)
saddr = dev->dev_addr;
@@ -127,13 +107,11 @@
lowpan_header_compress(skb, dev, type, daddr, saddr, len);
- /*
- * NOTE1: I'm still unsure about the fact that compression and WPAN
+ /* NOTE1: I'm still unsure about the fact that compression and WPAN
* header are created here and not later in the xmit. So wait for
* an opinion of net maintainers.
*/
- /*
- * NOTE2: to be absolutely correct, we must derive PANid information
+ /* NOTE2: to be absolutely correct, we must derive PANid information
* from MAC subif of the 'dev' and 'real_dev' network devices, but
* this isn't implemented in mainline yet, so currently we assign 0xff
*/
@@ -141,30 +119,29 @@
mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev);
/* prepare wpan address data */
- sa.addr_type = IEEE802154_ADDR_LONG;
+ sa.mode = IEEE802154_ADDR_LONG;
sa.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
+ sa.extended_addr = ieee802154_devaddr_from_raw(saddr);
- memcpy(&(sa.hwaddr), saddr, 8);
/* intra-PAN communications */
- da.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
+ da.pan_id = sa.pan_id;
- /*
- * if the destination address is the broadcast address, use the
+ /* if the destination address is the broadcast address, use the
* corresponding short address
*/
if (lowpan_is_addr_broadcast(daddr)) {
- da.addr_type = IEEE802154_ADDR_SHORT;
- da.short_addr = IEEE802154_ADDR_BROADCAST;
+ da.mode = IEEE802154_ADDR_SHORT;
+ da.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
} else {
- da.addr_type = IEEE802154_ADDR_LONG;
- memcpy(&(da.hwaddr), daddr, IEEE802154_ADDR_LEN);
+ da.mode = IEEE802154_ADDR_LONG;
+ da.extended_addr = ieee802154_devaddr_from_raw(daddr);
/* request acknowledgment */
mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ;
}
return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev,
- type, (void *)&da, (void *)&sa, skb->len);
+ type, (void *)&da, (void *)&sa, 0);
}
static int lowpan_give_skb_to_devices(struct sk_buff *skb,
@@ -191,73 +168,11 @@
return stat;
}
-static void lowpan_fragment_timer_expired(unsigned long entry_addr)
-{
- struct lowpan_fragment *entry = (struct lowpan_fragment *)entry_addr;
-
- pr_debug("timer expired for frame with tag %d\n", entry->tag);
-
- list_del(&entry->list);
- dev_kfree_skb(entry->skb);
- kfree(entry);
-}
-
-static struct lowpan_fragment *
-lowpan_alloc_new_frame(struct sk_buff *skb, u16 len, u16 tag)
-{
- struct lowpan_fragment *frame;
-
- frame = kzalloc(sizeof(struct lowpan_fragment),
- GFP_ATOMIC);
- if (!frame)
- goto frame_err;
-
- INIT_LIST_HEAD(&frame->list);
-
- frame->length = len;
- frame->tag = tag;
-
- /* allocate buffer for frame assembling */
- frame->skb = netdev_alloc_skb_ip_align(skb->dev, frame->length +
- sizeof(struct ipv6hdr));
-
- if (!frame->skb)
- goto skb_err;
-
- frame->skb->priority = skb->priority;
-
- /* reserve headroom for uncompressed ipv6 header */
- skb_reserve(frame->skb, sizeof(struct ipv6hdr));
- skb_put(frame->skb, frame->length);
-
- /* copy the first control block to keep a
- * trace of the link-layer addresses in case
- * of a link-local compressed address
- */
- memcpy(frame->skb->cb, skb->cb, sizeof(skb->cb));
-
- init_timer(&frame->timer);
- /* time out is the same as for ipv6 - 60 sec */
- frame->timer.expires = jiffies + LOWPAN_FRAG_TIMEOUT;
- frame->timer.data = (unsigned long)frame;
- frame->timer.function = lowpan_fragment_timer_expired;
-
- add_timer(&frame->timer);
-
- list_add_tail(&frame->list, &lowpan_fragments);
-
- return frame;
-
-skb_err:
- kfree(frame);
-frame_err:
- return NULL;
-}
-
-static int process_data(struct sk_buff *skb)
+static int process_data(struct sk_buff *skb, const struct ieee802154_hdr *hdr)
{
u8 iphc0, iphc1;
- const struct ieee802154_addr *_saddr, *_daddr;
+ struct ieee802154_addr_sa sa, da;
+ void *sap, *dap;
raw_dump_table(__func__, "raw skb data dump", skb->data, skb->len);
/* at least two bytes will be used for the encoding */
@@ -267,108 +182,27 @@
if (lowpan_fetch_skb_u8(skb, &iphc0))
goto drop;
- /* fragments assembling */
- switch (iphc0 & LOWPAN_DISPATCH_MASK) {
- case LOWPAN_DISPATCH_FRAG1:
- case LOWPAN_DISPATCH_FRAGN:
- {
- struct lowpan_fragment *frame;
- /* slen stores the rightmost 8 bits of the 11 bits length */
- u8 slen, offset = 0;
- u16 len, tag;
- bool found = false;
-
- if (lowpan_fetch_skb_u8(skb, &slen) || /* frame length */
- lowpan_fetch_skb_u16(skb, &tag)) /* fragment tag */
- goto drop;
-
- /* adds the 3 MSB to the 8 LSB to retrieve the 11 bits length */
- len = ((iphc0 & 7) << 8) | slen;
-
- if ((iphc0 & LOWPAN_DISPATCH_MASK) == LOWPAN_DISPATCH_FRAG1) {
- pr_debug("%s received a FRAG1 packet (tag: %d, "
- "size of the entire IP packet: %d)",
- __func__, tag, len);
- } else { /* FRAGN */
- if (lowpan_fetch_skb_u8(skb, &offset))
- goto unlock_and_drop;
- pr_debug("%s received a FRAGN packet (tag: %d, "
- "size of the entire IP packet: %d, "
- "offset: %d)", __func__, tag, len, offset * 8);
- }
-
- /*
- * check if frame assembling with the same tag is
- * already in progress
- */
- spin_lock_bh(&flist_lock);
-
- list_for_each_entry(frame, &lowpan_fragments, list)
- if (frame->tag == tag) {
- found = true;
- break;
- }
-
- /* alloc new frame structure */
- if (!found) {
- pr_debug("%s first fragment received for tag %d, "
- "begin packet reassembly", __func__, tag);
- frame = lowpan_alloc_new_frame(skb, len, tag);
- if (!frame)
- goto unlock_and_drop;
- }
-
- /* if payload fits buffer, copy it */
- if (likely((offset * 8 + skb->len) <= frame->length))
- skb_copy_to_linear_data_offset(frame->skb, offset * 8,
- skb->data, skb->len);
- else
- goto unlock_and_drop;
-
- frame->bytes_rcv += skb->len;
-
- /* frame assembling complete */
- if ((frame->bytes_rcv == frame->length) &&
- frame->timer.expires > jiffies) {
- /* if timer haven't expired - first of all delete it */
- del_timer_sync(&frame->timer);
- list_del(&frame->list);
- spin_unlock_bh(&flist_lock);
-
- pr_debug("%s successfully reassembled fragment "
- "(tag %d)", __func__, tag);
-
- dev_kfree_skb(skb);
- skb = frame->skb;
- kfree(frame);
-
- if (lowpan_fetch_skb_u8(skb, &iphc0))
- goto drop;
-
- break;
- }
- spin_unlock_bh(&flist_lock);
-
- return kfree_skb(skb), 0;
- }
- default:
- break;
- }
-
if (lowpan_fetch_skb_u8(skb, &iphc1))
goto drop;
- _saddr = &mac_cb(skb)->sa;
- _daddr = &mac_cb(skb)->da;
+ ieee802154_addr_to_sa(&sa, &hdr->source);
+ ieee802154_addr_to_sa(&da, &hdr->dest);
- return lowpan_process_data(skb, skb->dev, (u8 *)_saddr->hwaddr,
- _saddr->addr_type, IEEE802154_ADDR_LEN,
- (u8 *)_daddr->hwaddr, _daddr->addr_type,
- IEEE802154_ADDR_LEN, iphc0, iphc1,
- lowpan_give_skb_to_devices);
+ if (sa.addr_type == IEEE802154_ADDR_SHORT)
+ sap = &sa.short_addr;
+ else
+ sap = &sa.hwaddr;
-unlock_and_drop:
- spin_unlock_bh(&flist_lock);
+ if (da.addr_type == IEEE802154_ADDR_SHORT)
+ dap = &da.short_addr;
+ else
+ dap = &da.hwaddr;
+
+ return lowpan_process_data(skb, skb->dev, sap, sa.addr_type,
+ IEEE802154_ADDR_LEN, dap, da.addr_type,
+ IEEE802154_ADDR_LEN, iphc0, iphc1,
+ lowpan_give_skb_to_devices);
+
drop:
kfree_skb(skb);
return -EINVAL;
@@ -389,7 +223,7 @@
static int
lowpan_fragment_xmit(struct sk_buff *skb, u8 *head,
- int mlen, int plen, int offset, int type)
+ int mlen, int plen, int offset, int type)
{
struct sk_buff *frag;
int hlen;
@@ -425,51 +259,68 @@
static int
lowpan_skb_fragmentation(struct sk_buff *skb, struct net_device *dev)
{
- int err, header_length, payload_length, tag, offset = 0;
+ int err;
+ u16 dgram_offset, dgram_size, payload_length, header_length,
+ lowpan_size, frag_plen, offset;
+ __be16 tag;
u8 head[5];
header_length = skb->mac_len;
payload_length = skb->len - header_length;
tag = lowpan_dev_info(dev)->fragment_tag++;
+ lowpan_size = skb_network_header_len(skb);
+ dgram_size = lowpan_uncompress_size(skb, &dgram_offset) -
+ header_length;
/* first fragment header */
- head[0] = LOWPAN_DISPATCH_FRAG1 | ((payload_length >> 8) & 0x7);
- head[1] = payload_length & 0xff;
- head[2] = tag >> 8;
- head[3] = tag & 0xff;
+ head[0] = LOWPAN_DISPATCH_FRAG1 | ((dgram_size >> 8) & 0x7);
+ head[1] = dgram_size & 0xff;
+ memcpy(head + 2, &tag, sizeof(tag));
- err = lowpan_fragment_xmit(skb, head, header_length, LOWPAN_FRAG_SIZE,
- 0, LOWPAN_DISPATCH_FRAG1);
+ /* calc the nearest payload length(divided to 8) for first fragment
+ * which fits into a IEEE802154_MTU
+ */
+ frag_plen = round_down(IEEE802154_MTU - header_length -
+ LOWPAN_FRAG1_HEAD_SIZE - lowpan_size -
+ IEEE802154_MFR_SIZE, 8);
+ err = lowpan_fragment_xmit(skb, head, header_length,
+ frag_plen + lowpan_size, 0,
+ LOWPAN_DISPATCH_FRAG1);
if (err) {
pr_debug("%s unable to send FRAG1 packet (tag: %d)",
__func__, tag);
goto exit;
}
- offset = LOWPAN_FRAG_SIZE;
+ offset = lowpan_size + frag_plen;
+ dgram_offset += frag_plen;
/* next fragment header */
head[0] &= ~LOWPAN_DISPATCH_FRAG1;
head[0] |= LOWPAN_DISPATCH_FRAGN;
- while (payload_length - offset > 0) {
- int len = LOWPAN_FRAG_SIZE;
+ frag_plen = round_down(IEEE802154_MTU - header_length -
+ LOWPAN_FRAGN_HEAD_SIZE - IEEE802154_MFR_SIZE, 8);
- head[4] = offset / 8;
+ while (payload_length - offset > 0) {
+ int len = frag_plen;
+
+ head[4] = dgram_offset >> 3;
if (payload_length - offset < len)
len = payload_length - offset;
- err = lowpan_fragment_xmit(skb, head, header_length,
- len, offset, LOWPAN_DISPATCH_FRAGN);
+ err = lowpan_fragment_xmit(skb, head, header_length, len,
+ offset, LOWPAN_DISPATCH_FRAGN);
if (err) {
- pr_debug("%s unable to send a subsequent FRAGN packet "
- "(tag: %d, offset: %d", __func__, tag, offset);
+ pr_debug("%s unable to send a FRAGN packet. (tag: %d, offset: %d)\n",
+ __func__, tag, offset);
goto exit;
}
offset += len;
+ dgram_offset += len;
}
exit:
@@ -511,13 +362,13 @@
return ieee802154_mlme_ops(real_dev)->get_phy(real_dev);
}
-static u16 lowpan_get_pan_id(const struct net_device *dev)
+static __le16 lowpan_get_pan_id(const struct net_device *dev)
{
struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
return ieee802154_mlme_ops(real_dev)->get_pan_id(real_dev);
}
-static u16 lowpan_get_short_addr(const struct net_device *dev)
+static __le16 lowpan_get_short_addr(const struct net_device *dev)
{
struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
return ieee802154_mlme_ops(real_dev)->get_short_addr(real_dev);
@@ -533,7 +384,27 @@
.create = lowpan_header_create,
};
+static struct lock_class_key lowpan_tx_busylock;
+static struct lock_class_key lowpan_netdev_xmit_lock_key;
+
+static void lowpan_set_lockdep_class_one(struct net_device *dev,
+ struct netdev_queue *txq,
+ void *_unused)
+{
+ lockdep_set_class(&txq->_xmit_lock,
+ &lowpan_netdev_xmit_lock_key);
+}
+
+
+static int lowpan_dev_init(struct net_device *dev)
+{
+ netdev_for_each_tx_queue(dev, lowpan_set_lockdep_class_one, NULL);
+ dev->qdisc_tx_busylock = &lowpan_tx_busylock;
+ return 0;
+}
+
static const struct net_device_ops lowpan_netdev_ops = {
+ .ndo_init = lowpan_dev_init,
.ndo_start_xmit = lowpan_xmit,
.ndo_set_mac_address = lowpan_set_address,
};
@@ -576,45 +447,55 @@
static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
- struct sk_buff *local_skb;
+ struct ieee802154_hdr hdr;
+ int ret;
+
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (!skb)
+ goto drop;
if (!netif_running(dev))
- goto drop;
+ goto drop_skb;
if (dev->type != ARPHRD_IEEE802154)
- goto drop;
+ goto drop_skb;
+
+ if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0)
+ goto drop_skb;
/* check that it's our buffer */
if (skb->data[0] == LOWPAN_DISPATCH_IPV6) {
- /* Copy the packet so that the IPv6 header is
- * properly aligned.
- */
- local_skb = skb_copy_expand(skb, NET_SKB_PAD - 1,
- skb_tailroom(skb), GFP_ATOMIC);
- if (!local_skb)
- goto drop;
-
- local_skb->protocol = htons(ETH_P_IPV6);
- local_skb->pkt_type = PACKET_HOST;
+ skb->protocol = htons(ETH_P_IPV6);
+ skb->pkt_type = PACKET_HOST;
/* Pull off the 1-byte of 6lowpan header. */
- skb_pull(local_skb, 1);
+ skb_pull(skb, 1);
- lowpan_give_skb_to_devices(local_skb, NULL);
-
- kfree_skb(local_skb);
- kfree_skb(skb);
+ ret = lowpan_give_skb_to_devices(skb, NULL);
+ if (ret == NET_RX_DROP)
+ goto drop;
} else {
switch (skb->data[0] & 0xe0) {
case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */
- case LOWPAN_DISPATCH_FRAG1: /* first fragment header */
- case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */
- local_skb = skb_clone(skb, GFP_ATOMIC);
- if (!local_skb)
+ ret = process_data(skb, &hdr);
+ if (ret == NET_RX_DROP)
goto drop;
- process_data(local_skb);
-
- kfree_skb(skb);
+ break;
+ case LOWPAN_DISPATCH_FRAG1: /* first fragment header */
+ ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAG1);
+ if (ret == 1) {
+ ret = process_data(skb, &hdr);
+ if (ret == NET_RX_DROP)
+ goto drop;
+ }
+ break;
+ case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */
+ ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAGN);
+ if (ret == 1) {
+ ret = process_data(skb, &hdr);
+ if (ret == NET_RX_DROP)
+ goto drop;
+ }
break;
default:
break;
@@ -622,9 +503,9 @@
}
return NET_RX_SUCCESS;
-
-drop:
+drop_skb:
kfree_skb(skb);
+drop:
return NET_RX_DROP;
}
@@ -648,10 +529,9 @@
}
lowpan_dev_info(dev)->real_dev = real_dev;
- lowpan_dev_info(dev)->fragment_tag = 0;
mutex_init(&lowpan_dev_info(dev)->dev_list_mtx);
- entry = kzalloc(sizeof(struct lowpan_dev_record), GFP_KERNEL);
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
if (!entry) {
dev_put(real_dev);
lowpan_dev_info(dev)->real_dev = NULL;
@@ -744,7 +624,7 @@
};
static struct packet_type lowpan_packet_type = {
- .type = __constant_htons(ETH_P_IEEE802154),
+ .type = htons(ETH_P_IEEE802154),
.func = lowpan_rcv,
};
@@ -752,43 +632,40 @@
{
int err = 0;
- err = lowpan_netlink_init();
+ err = lowpan_net_frag_init();
if (err < 0)
goto out;
+ err = lowpan_netlink_init();
+ if (err < 0)
+ goto out_frag;
+
dev_add_pack(&lowpan_packet_type);
err = register_netdevice_notifier(&lowpan_dev_notifier);
- if (err < 0) {
- dev_remove_pack(&lowpan_packet_type);
- lowpan_netlink_fini();
- }
+ if (err < 0)
+ goto out_pack;
+
+ return 0;
+
+out_pack:
+ dev_remove_pack(&lowpan_packet_type);
+ lowpan_netlink_fini();
+out_frag:
+ lowpan_net_frag_exit();
out:
return err;
}
static void __exit lowpan_cleanup_module(void)
{
- struct lowpan_fragment *frame, *tframe;
-
lowpan_netlink_fini();
dev_remove_pack(&lowpan_packet_type);
- unregister_netdevice_notifier(&lowpan_dev_notifier);
+ lowpan_net_frag_exit();
- /* Now 6lowpan packet_type is removed, so no new fragments are
- * expected on RX, therefore that's the time to clean incomplete
- * fragments.
- */
- spin_lock_bh(&flist_lock);
- list_for_each_entry_safe(frame, tframe, &lowpan_fragments, list) {
- del_timer_sync(&frame->timer);
- list_del(&frame->list);
- dev_kfree_skb(frame->skb);
- kfree(frame);
- }
- spin_unlock_bh(&flist_lock);
+ unregister_netdevice_notifier(&lowpan_dev_notifier);
}
module_init(lowpan_init_module);
diff --git a/net/ieee802154/Kconfig b/net/ieee802154/Kconfig
index 9c9879d..8af1330 100644
--- a/net/ieee802154/Kconfig
+++ b/net/ieee802154/Kconfig
@@ -15,7 +15,7 @@
depends on IEEE802154 && IPV6
select 6LOWPAN_IPHC
---help---
- IPv6 compression over IEEE 802.15.4.
+ IPv6 compression over IEEE 802.15.4.
config 6LOWPAN_IPHC
tristate
diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile
index e8f0588..bf1b514 100644
--- a/net/ieee802154/Makefile
+++ b/net/ieee802154/Makefile
@@ -2,5 +2,9 @@
obj-$(CONFIG_IEEE802154_6LOWPAN) += 6lowpan.o
obj-$(CONFIG_6LOWPAN_IPHC) += 6lowpan_iphc.o
-ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o
+6lowpan-y := 6lowpan_rtnl.o reassembly.o
+ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o \
+ header_ops.o
af_802154-y := af_ieee802154.o raw.o dgram.o
+
+ccflags-y += -D__CHECK_ENDIAN__
diff --git a/net/ieee802154/af802154.h b/net/ieee802154/af802154.h
index b1ec525..8330a09 100644
--- a/net/ieee802154/af802154.h
+++ b/net/ieee802154/af802154.h
@@ -25,12 +25,13 @@
#define AF802154_H
struct sk_buff;
-struct net_devce;
+struct net_device;
+struct ieee802154_addr;
extern struct proto ieee802154_raw_prot;
extern struct proto ieee802154_dgram_prot;
void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb);
int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb);
struct net_device *ieee802154_get_dev(struct net *net,
- struct ieee802154_addr *addr);
+ const struct ieee802154_addr *addr);
#endif
diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c
index 40e606f..351d9a9 100644
--- a/net/ieee802154/af_ieee802154.c
+++ b/net/ieee802154/af_ieee802154.c
@@ -43,25 +43,27 @@
/*
* Utility function for families
*/
-struct net_device *ieee802154_get_dev(struct net *net,
- struct ieee802154_addr *addr)
+struct net_device*
+ieee802154_get_dev(struct net *net, const struct ieee802154_addr *addr)
{
struct net_device *dev = NULL;
struct net_device *tmp;
- u16 pan_id, short_addr;
+ __le16 pan_id, short_addr;
+ u8 hwaddr[IEEE802154_ADDR_LEN];
- switch (addr->addr_type) {
+ switch (addr->mode) {
case IEEE802154_ADDR_LONG:
+ ieee802154_devaddr_to_raw(hwaddr, addr->extended_addr);
rcu_read_lock();
- dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, addr->hwaddr);
+ dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, hwaddr);
if (dev)
dev_hold(dev);
rcu_read_unlock();
break;
case IEEE802154_ADDR_SHORT:
- if (addr->pan_id == 0xffff ||
- addr->short_addr == IEEE802154_ADDR_UNDEF ||
- addr->short_addr == 0xffff)
+ if (addr->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST) ||
+ addr->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) ||
+ addr->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST))
break;
rtnl_lock();
@@ -86,7 +88,7 @@
break;
default:
pr_warning("Unsupported ieee802154 address type: %d\n",
- addr->addr_type);
+ addr->mode);
break;
}
@@ -326,7 +328,7 @@
static struct packet_type ieee802154_packet_type = {
- .type = __constant_htons(ETH_P_IEEE802154),
+ .type = htons(ETH_P_IEEE802154),
.func = ieee802154_rcv,
};
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index 1846c1f..786437b 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -73,10 +73,10 @@
{
struct dgram_sock *ro = dgram_sk(sk);
- ro->dst_addr.addr_type = IEEE802154_ADDR_LONG;
- ro->dst_addr.pan_id = 0xffff;
+ ro->dst_addr.mode = IEEE802154_ADDR_LONG;
+ ro->dst_addr.pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
ro->want_ack = 1;
- memset(&ro->dst_addr.hwaddr, 0xff, sizeof(ro->dst_addr.hwaddr));
+ memset(&ro->dst_addr.extended_addr, 0xff, IEEE802154_ADDR_LEN);
return 0;
}
@@ -88,6 +88,7 @@
static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len)
{
struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr;
+ struct ieee802154_addr haddr;
struct dgram_sock *ro = dgram_sk(sk);
int err = -EINVAL;
struct net_device *dev;
@@ -102,7 +103,8 @@
if (addr->family != AF_IEEE802154)
goto out;
- dev = ieee802154_get_dev(sock_net(sk), &addr->addr);
+ ieee802154_addr_from_sa(&haddr, &addr->addr);
+ dev = ieee802154_get_dev(sock_net(sk), &haddr);
if (!dev) {
err = -ENODEV;
goto out;
@@ -113,7 +115,7 @@
goto out_put;
}
- memcpy(&ro->src_addr, &addr->addr, sizeof(struct ieee802154_addr));
+ ro->src_addr = haddr;
ro->bound = 1;
err = 0;
@@ -149,8 +151,7 @@
* of this packet since that is all
* that will be read.
*/
- /* FIXME: parse the header for more correct value */
- amount = skb->len - (3+8+8);
+ amount = skb->len - ieee802154_hdr_length(skb);
}
spin_unlock_bh(&sk->sk_receive_queue.lock);
return put_user(amount, (int __user *)arg);
@@ -181,7 +182,7 @@
goto out;
}
- memcpy(&ro->dst_addr, &addr->addr, sizeof(struct ieee802154_addr));
+ ieee802154_addr_from_sa(&ro->dst_addr, &addr->addr);
out:
release_sock(sk);
@@ -194,8 +195,8 @@
lock_sock(sk);
- ro->dst_addr.addr_type = IEEE802154_ADDR_LONG;
- memset(&ro->dst_addr.hwaddr, 0xff, sizeof(ro->dst_addr.hwaddr));
+ ro->dst_addr.mode = IEEE802154_ADDR_LONG;
+ memset(&ro->dst_addr.extended_addr, 0xff, IEEE802154_ADDR_LEN);
release_sock(sk);
@@ -232,7 +233,7 @@
if (size > mtu) {
pr_debug("size = %Zu, mtu = %u\n", size, mtu);
- err = -EINVAL;
+ err = -EMSGSIZE;
goto out_dev;
}
@@ -312,7 +313,7 @@
if (saddr) {
saddr->family = AF_IEEE802154;
- saddr->addr = mac_cb(skb)->sa;
+ ieee802154_addr_to_sa(&saddr->addr, &mac_cb(skb)->source);
*addr_len = sizeof(*saddr);
}
@@ -328,6 +329,10 @@
static int dgram_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (!skb)
+ return NET_RX_DROP;
+
if (sock_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
@@ -336,40 +341,43 @@
return NET_RX_SUCCESS;
}
-static inline int ieee802154_match_sock(u8 *hw_addr, u16 pan_id,
- u16 short_addr, struct dgram_sock *ro)
+static inline bool
+ieee802154_match_sock(__le64 hw_addr, __le16 pan_id, __le16 short_addr,
+ struct dgram_sock *ro)
{
if (!ro->bound)
- return 1;
+ return true;
- if (ro->src_addr.addr_type == IEEE802154_ADDR_LONG &&
- !memcmp(ro->src_addr.hwaddr, hw_addr, IEEE802154_ADDR_LEN))
- return 1;
+ if (ro->src_addr.mode == IEEE802154_ADDR_LONG &&
+ hw_addr == ro->src_addr.extended_addr)
+ return true;
- if (ro->src_addr.addr_type == IEEE802154_ADDR_SHORT &&
- pan_id == ro->src_addr.pan_id &&
- short_addr == ro->src_addr.short_addr)
- return 1;
+ if (ro->src_addr.mode == IEEE802154_ADDR_SHORT &&
+ pan_id == ro->src_addr.pan_id &&
+ short_addr == ro->src_addr.short_addr)
+ return true;
- return 0;
+ return false;
}
int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb)
{
struct sock *sk, *prev = NULL;
int ret = NET_RX_SUCCESS;
- u16 pan_id, short_addr;
+ __le16 pan_id, short_addr;
+ __le64 hw_addr;
/* Data frame processing */
BUG_ON(dev->type != ARPHRD_IEEE802154);
pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev);
+ hw_addr = ieee802154_devaddr_from_raw(dev->dev_addr);
read_lock(&dgram_lock);
sk_for_each(sk, &dgram_head) {
- if (ieee802154_match_sock(dev->dev_addr, pan_id, short_addr,
- dgram_sk(sk))) {
+ if (ieee802154_match_sock(hw_addr, pan_id, short_addr,
+ dgram_sk(sk))) {
if (prev) {
struct sk_buff *clone;
clone = skb_clone(skb, GFP_ATOMIC);
diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c
new file mode 100644
index 0000000..bed42a4
--- /dev/null
+++ b/net/ieee802154/header_ops.c
@@ -0,0 +1,287 @@
+/*
+ * Copyright (C) 2014 Fraunhofer ITWM
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Written by:
+ * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
+ */
+
+#include <net/mac802154.h>
+#include <net/ieee802154.h>
+#include <net/ieee802154_netdev.h>
+
+static int
+ieee802154_hdr_push_addr(u8 *buf, const struct ieee802154_addr *addr,
+ bool omit_pan)
+{
+ int pos = 0;
+
+ if (addr->mode == IEEE802154_ADDR_NONE)
+ return 0;
+
+ if (!omit_pan) {
+ memcpy(buf + pos, &addr->pan_id, 2);
+ pos += 2;
+ }
+
+ switch (addr->mode) {
+ case IEEE802154_ADDR_SHORT:
+ memcpy(buf + pos, &addr->short_addr, 2);
+ pos += 2;
+ break;
+
+ case IEEE802154_ADDR_LONG:
+ memcpy(buf + pos, &addr->extended_addr, IEEE802154_ADDR_LEN);
+ pos += IEEE802154_ADDR_LEN;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ return pos;
+}
+
+static int
+ieee802154_hdr_push_sechdr(u8 *buf, const struct ieee802154_sechdr *hdr)
+{
+ int pos = 5;
+
+ memcpy(buf, hdr, 1);
+ memcpy(buf + 1, &hdr->frame_counter, 4);
+
+ switch (hdr->key_id_mode) {
+ case IEEE802154_SCF_KEY_IMPLICIT:
+ return pos;
+
+ case IEEE802154_SCF_KEY_INDEX:
+ break;
+
+ case IEEE802154_SCF_KEY_SHORT_INDEX:
+ memcpy(buf + pos, &hdr->short_src, 4);
+ pos += 4;
+ break;
+
+ case IEEE802154_SCF_KEY_HW_INDEX:
+ memcpy(buf + pos, &hdr->extended_src, IEEE802154_ADDR_LEN);
+ pos += IEEE802154_ADDR_LEN;
+ break;
+ }
+
+ buf[pos++] = hdr->key_id;
+
+ return pos;
+}
+
+int
+ieee802154_hdr_push(struct sk_buff *skb, const struct ieee802154_hdr *hdr)
+{
+ u8 buf[MAC802154_FRAME_HARD_HEADER_LEN];
+ int pos = 2;
+ int rc;
+ struct ieee802154_hdr_fc fc = hdr->fc;
+
+ buf[pos++] = hdr->seq;
+
+ fc.dest_addr_mode = hdr->dest.mode;
+
+ rc = ieee802154_hdr_push_addr(buf + pos, &hdr->dest, false);
+ if (rc < 0)
+ return -EINVAL;
+ pos += rc;
+
+ fc.source_addr_mode = hdr->source.mode;
+
+ if (hdr->source.pan_id == hdr->dest.pan_id &&
+ hdr->dest.mode != IEEE802154_ADDR_NONE)
+ fc.intra_pan = true;
+
+ rc = ieee802154_hdr_push_addr(buf + pos, &hdr->source, fc.intra_pan);
+ if (rc < 0)
+ return -EINVAL;
+ pos += rc;
+
+ if (fc.security_enabled) {
+ fc.version = 1;
+
+ rc = ieee802154_hdr_push_sechdr(buf + pos, &hdr->sec);
+ if (rc < 0)
+ return -EINVAL;
+
+ pos += rc;
+ }
+
+ memcpy(buf, &fc, 2);
+
+ memcpy(skb_push(skb, pos), buf, pos);
+
+ return pos;
+}
+EXPORT_SYMBOL_GPL(ieee802154_hdr_push);
+
+static int
+ieee802154_hdr_get_addr(const u8 *buf, int mode, bool omit_pan,
+ struct ieee802154_addr *addr)
+{
+ int pos = 0;
+
+ addr->mode = mode;
+
+ if (mode == IEEE802154_ADDR_NONE)
+ return 0;
+
+ if (!omit_pan) {
+ memcpy(&addr->pan_id, buf + pos, 2);
+ pos += 2;
+ }
+
+ if (mode == IEEE802154_ADDR_SHORT) {
+ memcpy(&addr->short_addr, buf + pos, 2);
+ return pos + 2;
+ } else {
+ memcpy(&addr->extended_addr, buf + pos, IEEE802154_ADDR_LEN);
+ return pos + IEEE802154_ADDR_LEN;
+ }
+}
+
+static int ieee802154_hdr_addr_len(int mode, bool omit_pan)
+{
+ int pan_len = omit_pan ? 0 : 2;
+
+ switch (mode) {
+ case IEEE802154_ADDR_NONE: return 0;
+ case IEEE802154_ADDR_SHORT: return 2 + pan_len;
+ case IEEE802154_ADDR_LONG: return IEEE802154_ADDR_LEN + pan_len;
+ default: return -EINVAL;
+ }
+}
+
+static int
+ieee802154_hdr_get_sechdr(const u8 *buf, struct ieee802154_sechdr *hdr)
+{
+ int pos = 5;
+
+ memcpy(hdr, buf, 1);
+ memcpy(&hdr->frame_counter, buf + 1, 4);
+
+ switch (hdr->key_id_mode) {
+ case IEEE802154_SCF_KEY_IMPLICIT:
+ return pos;
+
+ case IEEE802154_SCF_KEY_INDEX:
+ break;
+
+ case IEEE802154_SCF_KEY_SHORT_INDEX:
+ memcpy(&hdr->short_src, buf + pos, 4);
+ pos += 4;
+ break;
+
+ case IEEE802154_SCF_KEY_HW_INDEX:
+ memcpy(&hdr->extended_src, buf + pos, IEEE802154_ADDR_LEN);
+ pos += IEEE802154_ADDR_LEN;
+ break;
+ }
+
+ hdr->key_id = buf[pos++];
+
+ return pos;
+}
+
+static int ieee802154_hdr_sechdr_len(u8 sc)
+{
+ switch (IEEE802154_SCF_KEY_ID_MODE(sc)) {
+ case IEEE802154_SCF_KEY_IMPLICIT: return 5;
+ case IEEE802154_SCF_KEY_INDEX: return 6;
+ case IEEE802154_SCF_KEY_SHORT_INDEX: return 10;
+ case IEEE802154_SCF_KEY_HW_INDEX: return 14;
+ default: return -EINVAL;
+ }
+}
+
+static int ieee802154_hdr_minlen(const struct ieee802154_hdr *hdr)
+{
+ int dlen, slen;
+
+ dlen = ieee802154_hdr_addr_len(hdr->fc.dest_addr_mode, false);
+ slen = ieee802154_hdr_addr_len(hdr->fc.source_addr_mode,
+ hdr->fc.intra_pan);
+
+ if (slen < 0 || dlen < 0)
+ return -EINVAL;
+
+ return 3 + dlen + slen + hdr->fc.security_enabled;
+}
+
+static int
+ieee802154_hdr_get_addrs(const u8 *buf, struct ieee802154_hdr *hdr)
+{
+ int pos = 0;
+
+ pos += ieee802154_hdr_get_addr(buf + pos, hdr->fc.dest_addr_mode,
+ false, &hdr->dest);
+ pos += ieee802154_hdr_get_addr(buf + pos, hdr->fc.source_addr_mode,
+ hdr->fc.intra_pan, &hdr->source);
+
+ if (hdr->fc.intra_pan)
+ hdr->source.pan_id = hdr->dest.pan_id;
+
+ return pos;
+}
+
+int
+ieee802154_hdr_pull(struct sk_buff *skb, struct ieee802154_hdr *hdr)
+{
+ int pos = 3, rc;
+
+ if (!pskb_may_pull(skb, 3))
+ return -EINVAL;
+
+ memcpy(hdr, skb->data, 3);
+
+ rc = ieee802154_hdr_minlen(hdr);
+ if (rc < 0 || !pskb_may_pull(skb, rc))
+ return -EINVAL;
+
+ pos += ieee802154_hdr_get_addrs(skb->data + pos, hdr);
+
+ if (hdr->fc.security_enabled) {
+ int want = pos + ieee802154_hdr_sechdr_len(skb->data[pos]);
+
+ if (!pskb_may_pull(skb, want))
+ return -EINVAL;
+
+ pos += ieee802154_hdr_get_sechdr(skb->data + pos, &hdr->sec);
+ }
+
+ skb_pull(skb, pos);
+ return pos;
+}
+EXPORT_SYMBOL_GPL(ieee802154_hdr_pull);
+
+int
+ieee802154_hdr_peek_addrs(const struct sk_buff *skb, struct ieee802154_hdr *hdr)
+{
+ const u8 *buf = skb_mac_header(skb);
+ int pos = 3, rc;
+
+ if (buf + 3 > skb_tail_pointer(skb))
+ return -EINVAL;
+
+ memcpy(hdr, buf, 3);
+
+ rc = ieee802154_hdr_minlen(hdr);
+ if (rc < 0 || buf + rc > skb_tail_pointer(skb))
+ return -EINVAL;
+
+ pos += ieee802154_hdr_get_addrs(buf + pos, hdr);
+ return pos;
+}
+EXPORT_SYMBOL_GPL(ieee802154_hdr_peek_addrs);
diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h
index cee4425..6cbc896 100644
--- a/net/ieee802154/ieee802154.h
+++ b/net/ieee802154/ieee802154.h
@@ -53,6 +53,7 @@
int ieee802154_dump_phy(struct sk_buff *skb, struct netlink_callback *cb);
int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info);
int ieee802154_del_iface(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info);
enum ieee802154_mcgrp_ids {
IEEE802154_COORD_MCGRP,
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 43f1b2b..67c151b 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -115,6 +115,7 @@
ieee802154_dump_phy),
IEEE802154_OP(IEEE802154_ADD_IFACE, ieee802154_add_iface),
IEEE802154_OP(IEEE802154_DEL_IFACE, ieee802154_del_iface),
+ IEEE802154_OP(IEEE802154_SET_PHYPARAMS, ieee802154_set_phyparams),
/* see nl-mac.c */
IEEE802154_OP(IEEE802154_ASSOCIATE_REQ, ieee802154_associate_req),
IEEE802154_OP(IEEE802154_ASSOCIATE_RESP, ieee802154_associate_resp),
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index ba5c1e0..bda8dba 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -39,6 +39,26 @@
#include "ieee802154.h"
+static int nla_put_hwaddr(struct sk_buff *msg, int type, __le64 hwaddr)
+{
+ return nla_put_u64(msg, type, swab64((__force u64)hwaddr));
+}
+
+static __le64 nla_get_hwaddr(const struct nlattr *nla)
+{
+ return ieee802154_devaddr_from_raw(nla_data(nla));
+}
+
+static int nla_put_shortaddr(struct sk_buff *msg, int type, __le16 addr)
+{
+ return nla_put_u16(msg, type, le16_to_cpu(addr));
+}
+
+static __le16 nla_get_shortaddr(const struct nlattr *nla)
+{
+ return cpu_to_le16(nla_get_u16(nla));
+}
+
int ieee802154_nl_assoc_indic(struct net_device *dev,
struct ieee802154_addr *addr, u8 cap)
{
@@ -46,7 +66,7 @@
pr_debug("%s\n", __func__);
- if (addr->addr_type != IEEE802154_ADDR_LONG) {
+ if (addr->mode != IEEE802154_ADDR_LONG) {
pr_err("%s: received non-long source address!\n", __func__);
return -EINVAL;
}
@@ -59,8 +79,8 @@
nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
dev->dev_addr) ||
- nla_put(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN,
- addr->hwaddr) ||
+ nla_put_hwaddr(msg, IEEE802154_ATTR_SRC_HW_ADDR,
+ addr->extended_addr) ||
nla_put_u8(msg, IEEE802154_ATTR_CAPABILITY, cap))
goto nla_put_failure;
@@ -72,7 +92,7 @@
}
EXPORT_SYMBOL(ieee802154_nl_assoc_indic);
-int ieee802154_nl_assoc_confirm(struct net_device *dev, u16 short_addr,
+int ieee802154_nl_assoc_confirm(struct net_device *dev, __le16 short_addr,
u8 status)
{
struct sk_buff *msg;
@@ -87,7 +107,7 @@
nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
dev->dev_addr) ||
- nla_put_u16(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) ||
+ nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) ||
nla_put_u8(msg, IEEE802154_ATTR_STATUS, status))
goto nla_put_failure;
return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
@@ -114,13 +134,13 @@
nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
dev->dev_addr))
goto nla_put_failure;
- if (addr->addr_type == IEEE802154_ADDR_LONG) {
- if (nla_put(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN,
- addr->hwaddr))
+ if (addr->mode == IEEE802154_ADDR_LONG) {
+ if (nla_put_hwaddr(msg, IEEE802154_ATTR_SRC_HW_ADDR,
+ addr->extended_addr))
goto nla_put_failure;
} else {
- if (nla_put_u16(msg, IEEE802154_ATTR_SRC_SHORT_ADDR,
- addr->short_addr))
+ if (nla_put_shortaddr(msg, IEEE802154_ATTR_SRC_SHORT_ADDR,
+ addr->short_addr))
goto nla_put_failure;
}
if (nla_put_u8(msg, IEEE802154_ATTR_REASON, reason))
@@ -157,8 +177,8 @@
}
EXPORT_SYMBOL(ieee802154_nl_disassoc_confirm);
-int ieee802154_nl_beacon_indic(struct net_device *dev,
- u16 panid, u16 coord_addr)
+int ieee802154_nl_beacon_indic(struct net_device *dev, __le16 panid,
+ __le16 coord_addr)
{
struct sk_buff *msg;
@@ -172,8 +192,9 @@
nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
dev->dev_addr) ||
- nla_put_u16(msg, IEEE802154_ATTR_COORD_SHORT_ADDR, coord_addr) ||
- nla_put_u16(msg, IEEE802154_ATTR_COORD_PAN_ID, panid))
+ nla_put_shortaddr(msg, IEEE802154_ATTR_COORD_SHORT_ADDR,
+ coord_addr) ||
+ nla_put_shortaddr(msg, IEEE802154_ATTR_COORD_PAN_ID, panid))
goto nla_put_failure;
return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
@@ -243,6 +264,7 @@
{
void *hdr;
struct wpan_phy *phy;
+ __le16 short_addr, pan_id;
pr_debug("%s\n", __func__);
@@ -254,15 +276,16 @@
phy = ieee802154_mlme_ops(dev)->get_phy(dev);
BUG_ON(!phy);
+ short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev);
+ pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
+
if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) ||
nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
dev->dev_addr) ||
- nla_put_u16(msg, IEEE802154_ATTR_SHORT_ADDR,
- ieee802154_mlme_ops(dev)->get_short_addr(dev)) ||
- nla_put_u16(msg, IEEE802154_ATTR_PAN_ID,
- ieee802154_mlme_ops(dev)->get_pan_id(dev)))
+ nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) ||
+ nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID, pan_id))
goto nla_put_failure;
wpan_phy_put(phy);
return genlmsg_end(msg, hdr);
@@ -322,16 +345,16 @@
goto out;
if (info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]) {
- addr.addr_type = IEEE802154_ADDR_LONG;
- nla_memcpy(addr.hwaddr,
- info->attrs[IEEE802154_ATTR_COORD_HW_ADDR],
- IEEE802154_ADDR_LEN);
+ addr.mode = IEEE802154_ADDR_LONG;
+ addr.extended_addr = nla_get_hwaddr(
+ info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]);
} else {
- addr.addr_type = IEEE802154_ADDR_SHORT;
- addr.short_addr = nla_get_u16(
+ addr.mode = IEEE802154_ADDR_SHORT;
+ addr.short_addr = nla_get_shortaddr(
info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]);
}
- addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]);
+ addr.pan_id = nla_get_shortaddr(
+ info->attrs[IEEE802154_ATTR_COORD_PAN_ID]);
if (info->attrs[IEEE802154_ATTR_PAGE])
page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]);
@@ -365,14 +388,13 @@
if (!ieee802154_mlme_ops(dev)->assoc_resp)
goto out;
- addr.addr_type = IEEE802154_ADDR_LONG;
- nla_memcpy(addr.hwaddr, info->attrs[IEEE802154_ATTR_DEST_HW_ADDR],
- IEEE802154_ADDR_LEN);
+ addr.mode = IEEE802154_ADDR_LONG;
+ addr.extended_addr = nla_get_hwaddr(
+ info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]);
addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
-
ret = ieee802154_mlme_ops(dev)->assoc_resp(dev, &addr,
- nla_get_u16(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]),
+ nla_get_shortaddr(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]),
nla_get_u8(info->attrs[IEEE802154_ATTR_STATUS]));
out:
@@ -398,13 +420,12 @@
goto out;
if (info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]) {
- addr.addr_type = IEEE802154_ADDR_LONG;
- nla_memcpy(addr.hwaddr,
- info->attrs[IEEE802154_ATTR_DEST_HW_ADDR],
- IEEE802154_ADDR_LEN);
+ addr.mode = IEEE802154_ADDR_LONG;
+ addr.extended_addr = nla_get_hwaddr(
+ info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]);
} else {
- addr.addr_type = IEEE802154_ADDR_SHORT;
- addr.short_addr = nla_get_u16(
+ addr.mode = IEEE802154_ADDR_SHORT;
+ addr.short_addr = nla_get_shortaddr(
info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]);
}
addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
@@ -449,10 +470,11 @@
if (!ieee802154_mlme_ops(dev)->start_req)
goto out;
- addr.addr_type = IEEE802154_ADDR_SHORT;
- addr.short_addr = nla_get_u16(
+ addr.mode = IEEE802154_ADDR_SHORT;
+ addr.short_addr = nla_get_shortaddr(
info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]);
- addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]);
+ addr.pan_id = nla_get_shortaddr(
+ info->attrs[IEEE802154_ATTR_COORD_PAN_ID]);
channel = nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]);
bcn_ord = nla_get_u8(info->attrs[IEEE802154_ATTR_BCN_ORD]);
@@ -467,7 +489,7 @@
page = 0;
- if (addr.short_addr == IEEE802154_ADDR_BROADCAST) {
+ if (addr.short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) {
ieee802154_nl_start_confirm(dev, IEEE802154_NO_SHORT_ADDRESS);
dev_put(dev);
return -EINVAL;
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 89b265a..222310a 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -55,7 +55,15 @@
mutex_lock(&phy->pib_lock);
if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) ||
nla_put_u8(msg, IEEE802154_ATTR_PAGE, phy->current_page) ||
- nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel))
+ nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel) ||
+ nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, phy->transmit_power) ||
+ nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, phy->lbt) ||
+ nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE, phy->cca_mode) ||
+ nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL, phy->cca_ed_level) ||
+ nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES, phy->csma_retries) ||
+ nla_put_u8(msg, IEEE802154_ATTR_CSMA_MIN_BE, phy->min_be) ||
+ nla_put_u8(msg, IEEE802154_ATTR_CSMA_MAX_BE, phy->max_be) ||
+ nla_put_s8(msg, IEEE802154_ATTR_FRAME_RETRIES, phy->frame_retries))
goto nla_put_failure;
for (i = 0; i < 32; i++) {
if (phy->channels_supported[i])
@@ -354,3 +362,193 @@
return rc;
}
+
+static int phy_set_txpower(struct wpan_phy *phy, struct genl_info *info)
+{
+ int txpower = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]);
+ int rc;
+
+ rc = phy->set_txpower(phy, txpower);
+ if (rc < 0)
+ return rc;
+
+ phy->transmit_power = txpower;
+
+ return 0;
+}
+
+static int phy_set_lbt(struct wpan_phy *phy, struct genl_info *info)
+{
+ u8 on = !!nla_get_u8(info->attrs[IEEE802154_ATTR_LBT_ENABLED]);
+ int rc;
+
+ rc = phy->set_lbt(phy, on);
+ if (rc < 0)
+ return rc;
+
+ phy->lbt = on;
+
+ return 0;
+}
+
+static int phy_set_cca_mode(struct wpan_phy *phy, struct genl_info *info)
+{
+ u8 mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]);
+ int rc;
+
+ if (mode > 3)
+ return -EINVAL;
+
+ rc = phy->set_cca_mode(phy, mode);
+ if (rc < 0)
+ return rc;
+
+ phy->cca_mode = mode;
+
+ return 0;
+}
+
+static int phy_set_cca_ed_level(struct wpan_phy *phy, struct genl_info *info)
+{
+ s32 level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]);
+ int rc;
+
+ rc = phy->set_cca_ed_level(phy, level);
+ if (rc < 0)
+ return rc;
+
+ phy->cca_ed_level = level;
+
+ return 0;
+}
+
+static int phy_set_csma_params(struct wpan_phy *phy, struct genl_info *info)
+{
+ int rc;
+ u8 min_be = phy->min_be;
+ u8 max_be = phy->max_be;
+ u8 retries = phy->csma_retries;
+
+ if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES])
+ retries = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_RETRIES]);
+ if (info->attrs[IEEE802154_ATTR_CSMA_MIN_BE])
+ min_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MIN_BE]);
+ if (info->attrs[IEEE802154_ATTR_CSMA_MAX_BE])
+ max_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]);
+
+ if (retries > 5 || max_be < 3 || max_be > 8 || min_be > max_be)
+ return -EINVAL;
+
+ rc = phy->set_csma_params(phy, min_be, max_be, retries);
+ if (rc < 0)
+ return rc;
+
+ phy->min_be = min_be;
+ phy->max_be = max_be;
+ phy->csma_retries = retries;
+
+ return 0;
+}
+
+static int phy_set_frame_retries(struct wpan_phy *phy, struct genl_info *info)
+{
+ s8 retries = nla_get_s8(info->attrs[IEEE802154_ATTR_FRAME_RETRIES]);
+ int rc;
+
+ if (retries < -1 || retries > 7)
+ return -EINVAL;
+
+ rc = phy->set_frame_retries(phy, retries);
+ if (rc < 0)
+ return rc;
+
+ phy->frame_retries = retries;
+
+ return 0;
+}
+
+int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
+{
+ struct wpan_phy *phy;
+ const char *name;
+ int rc = -ENOTSUPP;
+
+ pr_debug("%s\n", __func__);
+
+ if (!info->attrs[IEEE802154_ATTR_PHY_NAME] &&
+ !info->attrs[IEEE802154_ATTR_LBT_ENABLED] &&
+ !info->attrs[IEEE802154_ATTR_CCA_MODE] &&
+ !info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL] &&
+ !info->attrs[IEEE802154_ATTR_CSMA_RETRIES] &&
+ !info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] &&
+ !info->attrs[IEEE802154_ATTR_CSMA_MAX_BE] &&
+ !info->attrs[IEEE802154_ATTR_FRAME_RETRIES])
+ return -EINVAL;
+
+ name = nla_data(info->attrs[IEEE802154_ATTR_PHY_NAME]);
+ if (name[nla_len(info->attrs[IEEE802154_ATTR_PHY_NAME]) - 1] != '\0')
+ return -EINVAL; /* phy name should be null-terminated */
+
+ phy = wpan_phy_find(name);
+ if (!phy)
+ return -ENODEV;
+
+ if ((!phy->set_txpower && info->attrs[IEEE802154_ATTR_TXPOWER]) ||
+ (!phy->set_lbt && info->attrs[IEEE802154_ATTR_LBT_ENABLED]) ||
+ (!phy->set_cca_mode && info->attrs[IEEE802154_ATTR_CCA_MODE]) ||
+ (!phy->set_cca_ed_level &&
+ info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]))
+ goto out;
+
+ mutex_lock(&phy->pib_lock);
+
+ if (info->attrs[IEEE802154_ATTR_TXPOWER]) {
+ rc = phy_set_txpower(phy, info);
+ if (rc < 0)
+ goto error;
+ }
+
+ if (info->attrs[IEEE802154_ATTR_LBT_ENABLED]) {
+ rc = phy_set_lbt(phy, info);
+ if (rc < 0)
+ goto error;
+ }
+
+ if (info->attrs[IEEE802154_ATTR_CCA_MODE]) {
+ rc = phy_set_cca_mode(phy, info);
+ if (rc < 0)
+ goto error;
+ }
+
+ if (info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) {
+ rc = phy_set_cca_ed_level(phy, info);
+ if (rc < 0)
+ goto error;
+ }
+
+ if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES] ||
+ info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] ||
+ info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]) {
+ rc = phy_set_csma_params(phy, info);
+ if (rc < 0)
+ goto error;
+ }
+
+ if (info->attrs[IEEE802154_ATTR_FRAME_RETRIES]) {
+ rc = phy_set_frame_retries(phy, info);
+ if (rc < 0)
+ goto error;
+ }
+
+ mutex_unlock(&phy->pib_lock);
+
+ wpan_phy_put(phy);
+
+ return 0;
+
+error:
+ mutex_unlock(&phy->pib_lock);
+out:
+ wpan_phy_put(phy);
+ return rc;
+}
diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 6adda4d..fd7be5e 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -52,5 +52,15 @@
[IEEE802154_ATTR_DURATION] = { .type = NLA_U8, },
[IEEE802154_ATTR_ED_LIST] = { .len = 27 },
[IEEE802154_ATTR_CHANNEL_PAGE_LIST] = { .len = 32 * 4, },
+
+ [IEEE802154_ATTR_TXPOWER] = { .type = NLA_S8, },
+ [IEEE802154_ATTR_LBT_ENABLED] = { .type = NLA_U8, },
+ [IEEE802154_ATTR_CCA_MODE] = { .type = NLA_U8, },
+ [IEEE802154_ATTR_CCA_ED_LEVEL] = { .type = NLA_S32, },
+ [IEEE802154_ATTR_CSMA_RETRIES] = { .type = NLA_U8, },
+ [IEEE802154_ATTR_CSMA_MIN_BE] = { .type = NLA_U8, },
+ [IEEE802154_ATTR_CSMA_MAX_BE] = { .type = NLA_U8, },
+
+ [IEEE802154_ATTR_FRAME_RETRIES] = { .type = NLA_S8, },
};
diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c
index 41f538b..74d54fa 100644
--- a/net/ieee802154/raw.c
+++ b/net/ieee802154/raw.c
@@ -28,6 +28,7 @@
#include <linux/slab.h>
#include <net/sock.h>
#include <net/af_ieee802154.h>
+#include <net/ieee802154_netdev.h>
#include "af802154.h"
@@ -55,21 +56,24 @@
sk_common_release(sk);
}
-static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int len)
+static int raw_bind(struct sock *sk, struct sockaddr *_uaddr, int len)
{
- struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr;
+ struct ieee802154_addr addr;
+ struct sockaddr_ieee802154 *uaddr = (struct sockaddr_ieee802154 *)_uaddr;
int err = 0;
struct net_device *dev = NULL;
- if (len < sizeof(*addr))
+ if (len < sizeof(*uaddr))
return -EINVAL;
- if (addr->family != AF_IEEE802154)
+ uaddr = (struct sockaddr_ieee802154 *)_uaddr;
+ if (uaddr->family != AF_IEEE802154)
return -EINVAL;
lock_sock(sk);
- dev = ieee802154_get_dev(sock_net(sk), &addr->addr);
+ ieee802154_addr_from_sa(&addr, &uaddr->addr);
+ dev = ieee802154_get_dev(sock_net(sk), &addr);
if (!dev) {
err = -ENODEV;
goto out;
@@ -209,6 +213,10 @@
static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (!skb)
+ return NET_RX_DROP;
+
if (sock_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
diff --git a/net/ieee802154/reassembly.c b/net/ieee802154/reassembly.c
new file mode 100644
index 0000000..ef2d543
--- /dev/null
+++ b/net/ieee802154/reassembly.c
@@ -0,0 +1,571 @@
+/* 6LoWPAN fragment reassembly
+ *
+ *
+ * Authors:
+ * Alexander Aring <aar@pengutronix.de>
+ *
+ * Based on: net/ipv6/reassembly.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "6LoWPAN: " fmt
+
+#include <linux/net.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/random.h>
+#include <linux/jhash.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+
+#include <net/ieee802154_netdev.h>
+#include <net/6lowpan.h>
+#include <net/ipv6.h>
+#include <net/inet_frag.h>
+
+#include "reassembly.h"
+
+struct lowpan_frag_info {
+ __be16 d_tag;
+ u16 d_size;
+ u8 d_offset;
+};
+
+struct lowpan_frag_info *lowpan_cb(struct sk_buff *skb)
+{
+ return (struct lowpan_frag_info *)skb->cb;
+}
+
+static struct inet_frags lowpan_frags;
+
+static int lowpan_frag_reasm(struct lowpan_frag_queue *fq,
+ struct sk_buff *prev, struct net_device *dev);
+
+static unsigned int lowpan_hash_frag(__be16 tag, u16 d_size,
+ const struct ieee802154_addr *saddr,
+ const struct ieee802154_addr *daddr)
+{
+ u32 c;
+
+ net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd));
+ c = jhash_3words(ieee802154_addr_hash(saddr),
+ ieee802154_addr_hash(daddr),
+ (__force u32)(tag + (d_size << 16)),
+ lowpan_frags.rnd);
+
+ return c & (INETFRAGS_HASHSZ - 1);
+}
+
+static unsigned int lowpan_hashfn(struct inet_frag_queue *q)
+{
+ struct lowpan_frag_queue *fq;
+
+ fq = container_of(q, struct lowpan_frag_queue, q);
+ return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr);
+}
+
+static bool lowpan_frag_match(struct inet_frag_queue *q, void *a)
+{
+ struct lowpan_frag_queue *fq;
+ struct lowpan_create_arg *arg = a;
+
+ fq = container_of(q, struct lowpan_frag_queue, q);
+ return fq->tag == arg->tag && fq->d_size == arg->d_size &&
+ ieee802154_addr_equal(&fq->saddr, arg->src) &&
+ ieee802154_addr_equal(&fq->daddr, arg->dst);
+}
+
+static void lowpan_frag_init(struct inet_frag_queue *q, void *a)
+{
+ struct lowpan_frag_queue *fq;
+ struct lowpan_create_arg *arg = a;
+
+ fq = container_of(q, struct lowpan_frag_queue, q);
+
+ fq->tag = arg->tag;
+ fq->d_size = arg->d_size;
+ fq->saddr = *arg->src;
+ fq->daddr = *arg->dst;
+}
+
+static void lowpan_frag_expire(unsigned long data)
+{
+ struct frag_queue *fq;
+ struct net *net;
+
+ fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+ net = container_of(fq->q.net, struct net, ieee802154_lowpan.frags);
+
+ spin_lock(&fq->q.lock);
+
+ if (fq->q.last_in & INET_FRAG_COMPLETE)
+ goto out;
+
+ inet_frag_kill(&fq->q, &lowpan_frags);
+out:
+ spin_unlock(&fq->q.lock);
+ inet_frag_put(&fq->q, &lowpan_frags);
+}
+
+static inline struct lowpan_frag_queue *
+fq_find(struct net *net, const struct lowpan_frag_info *frag_info,
+ const struct ieee802154_addr *src,
+ const struct ieee802154_addr *dst)
+{
+ struct inet_frag_queue *q;
+ struct lowpan_create_arg arg;
+ unsigned int hash;
+
+ arg.tag = frag_info->d_tag;
+ arg.d_size = frag_info->d_size;
+ arg.src = src;
+ arg.dst = dst;
+
+ read_lock(&lowpan_frags.lock);
+ hash = lowpan_hash_frag(frag_info->d_tag, frag_info->d_size, src, dst);
+
+ q = inet_frag_find(&net->ieee802154_lowpan.frags,
+ &lowpan_frags, &arg, hash);
+ if (IS_ERR_OR_NULL(q)) {
+ inet_frag_maybe_warn_overflow(q, pr_fmt());
+ return NULL;
+ }
+ return container_of(q, struct lowpan_frag_queue, q);
+}
+
+static int lowpan_frag_queue(struct lowpan_frag_queue *fq,
+ struct sk_buff *skb, const u8 frag_type)
+{
+ struct sk_buff *prev, *next;
+ struct net_device *dev;
+ int end, offset;
+
+ if (fq->q.last_in & INET_FRAG_COMPLETE)
+ goto err;
+
+ offset = lowpan_cb(skb)->d_offset << 3;
+ end = lowpan_cb(skb)->d_size;
+
+ /* Is this the final fragment? */
+ if (offset + skb->len == end) {
+ /* If we already have some bits beyond end
+ * or have different end, the segment is corrupted.
+ */
+ if (end < fq->q.len ||
+ ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))
+ goto err;
+ fq->q.last_in |= INET_FRAG_LAST_IN;
+ fq->q.len = end;
+ } else {
+ if (end > fq->q.len) {
+ /* Some bits beyond end -> corruption. */
+ if (fq->q.last_in & INET_FRAG_LAST_IN)
+ goto err;
+ fq->q.len = end;
+ }
+ }
+
+ /* Find out which fragments are in front and at the back of us
+ * in the chain of fragments so far. We must know where to put
+ * this fragment, right?
+ */
+ prev = fq->q.fragments_tail;
+ if (!prev || lowpan_cb(prev)->d_offset < lowpan_cb(skb)->d_offset) {
+ next = NULL;
+ goto found;
+ }
+ prev = NULL;
+ for (next = fq->q.fragments; next != NULL; next = next->next) {
+ if (lowpan_cb(next)->d_offset >= lowpan_cb(skb)->d_offset)
+ break; /* bingo! */
+ prev = next;
+ }
+
+found:
+ /* Insert this fragment in the chain of fragments. */
+ skb->next = next;
+ if (!next)
+ fq->q.fragments_tail = skb;
+ if (prev)
+ prev->next = skb;
+ else
+ fq->q.fragments = skb;
+
+ dev = skb->dev;
+ if (dev)
+ skb->dev = NULL;
+
+ fq->q.stamp = skb->tstamp;
+ if (frag_type == LOWPAN_DISPATCH_FRAG1) {
+ /* Calculate uncomp. 6lowpan header to estimate full size */
+ fq->q.meat += lowpan_uncompress_size(skb, NULL);
+ fq->q.last_in |= INET_FRAG_FIRST_IN;
+ } else {
+ fq->q.meat += skb->len;
+ }
+ add_frag_mem_limit(&fq->q, skb->truesize);
+
+ if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
+ fq->q.meat == fq->q.len) {
+ int res;
+ unsigned long orefdst = skb->_skb_refdst;
+
+ skb->_skb_refdst = 0UL;
+ res = lowpan_frag_reasm(fq, prev, dev);
+ skb->_skb_refdst = orefdst;
+ return res;
+ }
+
+ inet_frag_lru_move(&fq->q);
+ return -1;
+err:
+ kfree_skb(skb);
+ return -1;
+}
+
+/* Check if this packet is complete.
+ * Returns NULL on failure by any reason, and pointer
+ * to current nexthdr field in reassembled frame.
+ *
+ * It is called with locked fq, and caller must check that
+ * queue is eligible for reassembly i.e. it is not COMPLETE,
+ * the last and the first frames arrived and all the bits are here.
+ */
+static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev,
+ struct net_device *dev)
+{
+ struct sk_buff *fp, *head = fq->q.fragments;
+ int sum_truesize;
+
+ inet_frag_kill(&fq->q, &lowpan_frags);
+
+ /* Make the one we just received the head. */
+ if (prev) {
+ head = prev->next;
+ fp = skb_clone(head, GFP_ATOMIC);
+
+ if (!fp)
+ goto out_oom;
+
+ fp->next = head->next;
+ if (!fp->next)
+ fq->q.fragments_tail = fp;
+ prev->next = fp;
+
+ skb_morph(head, fq->q.fragments);
+ head->next = fq->q.fragments->next;
+
+ consume_skb(fq->q.fragments);
+ fq->q.fragments = head;
+ }
+
+ /* Head of list must not be cloned. */
+ if (skb_unclone(head, GFP_ATOMIC))
+ goto out_oom;
+
+ /* If the first fragment is fragmented itself, we split
+ * it to two chunks: the first with data and paged part
+ * and the second, holding only fragments.
+ */
+ if (skb_has_frag_list(head)) {
+ struct sk_buff *clone;
+ int i, plen = 0;
+
+ clone = alloc_skb(0, GFP_ATOMIC);
+ if (!clone)
+ goto out_oom;
+ clone->next = head->next;
+ head->next = clone;
+ skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
+ skb_frag_list_init(head);
+ for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
+ plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
+ clone->len = head->data_len - plen;
+ clone->data_len = clone->len;
+ head->data_len -= clone->len;
+ head->len -= clone->len;
+ add_frag_mem_limit(&fq->q, clone->truesize);
+ }
+
+ WARN_ON(head == NULL);
+
+ sum_truesize = head->truesize;
+ for (fp = head->next; fp;) {
+ bool headstolen;
+ int delta;
+ struct sk_buff *next = fp->next;
+
+ sum_truesize += fp->truesize;
+ if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
+ kfree_skb_partial(fp, headstolen);
+ } else {
+ if (!skb_shinfo(head)->frag_list)
+ skb_shinfo(head)->frag_list = fp;
+ head->data_len += fp->len;
+ head->len += fp->len;
+ head->truesize += fp->truesize;
+ }
+ fp = next;
+ }
+ sub_frag_mem_limit(&fq->q, sum_truesize);
+
+ head->next = NULL;
+ head->dev = dev;
+ head->tstamp = fq->q.stamp;
+
+ fq->q.fragments = NULL;
+ fq->q.fragments_tail = NULL;
+
+ return 1;
+out_oom:
+ net_dbg_ratelimited("lowpan_frag_reasm: no memory for reassembly\n");
+ return -1;
+}
+
+static int lowpan_get_frag_info(struct sk_buff *skb, const u8 frag_type,
+ struct lowpan_frag_info *frag_info)
+{
+ bool fail;
+ u8 pattern = 0, low = 0;
+
+ fail = lowpan_fetch_skb(skb, &pattern, 1);
+ fail |= lowpan_fetch_skb(skb, &low, 1);
+ frag_info->d_size = (pattern & 7) << 8 | low;
+ fail |= lowpan_fetch_skb(skb, &frag_info->d_tag, 2);
+
+ if (frag_type == LOWPAN_DISPATCH_FRAGN) {
+ fail |= lowpan_fetch_skb(skb, &frag_info->d_offset, 1);
+ } else {
+ skb_reset_network_header(skb);
+ frag_info->d_offset = 0;
+ }
+
+ if (unlikely(fail))
+ return -EIO;
+
+ return 0;
+}
+
+int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type)
+{
+ struct lowpan_frag_queue *fq;
+ struct net *net = dev_net(skb->dev);
+ struct lowpan_frag_info *frag_info = lowpan_cb(skb);
+ struct ieee802154_addr source, dest;
+ int err;
+
+ source = mac_cb(skb)->source;
+ dest = mac_cb(skb)->dest;
+
+ err = lowpan_get_frag_info(skb, frag_type, frag_info);
+ if (err < 0)
+ goto err;
+
+ if (frag_info->d_size > net->ieee802154_lowpan.max_dsize)
+ goto err;
+
+ inet_frag_evictor(&net->ieee802154_lowpan.frags, &lowpan_frags, false);
+
+ fq = fq_find(net, frag_info, &source, &dest);
+ if (fq != NULL) {
+ int ret;
+ spin_lock(&fq->q.lock);
+ ret = lowpan_frag_queue(fq, skb, frag_type);
+ spin_unlock(&fq->q.lock);
+
+ inet_frag_put(&fq->q, &lowpan_frags);
+ return ret;
+ }
+
+err:
+ kfree_skb(skb);
+ return -1;
+}
+EXPORT_SYMBOL(lowpan_frag_rcv);
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table lowpan_frags_ns_ctl_table[] = {
+ {
+ .procname = "6lowpanfrag_high_thresh",
+ .data = &init_net.ieee802154_lowpan.frags.high_thresh,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "6lowpanfrag_low_thresh",
+ .data = &init_net.ieee802154_lowpan.frags.low_thresh,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "6lowpanfrag_time",
+ .data = &init_net.ieee802154_lowpan.frags.timeout,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ {
+ .procname = "6lowpanfrag_max_datagram_size",
+ .data = &init_net.ieee802154_lowpan.max_dsize,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ { }
+};
+
+static struct ctl_table lowpan_frags_ctl_table[] = {
+ {
+ .procname = "6lowpanfrag_secret_interval",
+ .data = &lowpan_frags.secret_interval,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ { }
+};
+
+static int __net_init lowpan_frags_ns_sysctl_register(struct net *net)
+{
+ struct ctl_table *table;
+ struct ctl_table_header *hdr;
+
+ table = lowpan_frags_ns_ctl_table;
+ if (!net_eq(net, &init_net)) {
+ table = kmemdup(table, sizeof(lowpan_frags_ns_ctl_table),
+ GFP_KERNEL);
+ if (table == NULL)
+ goto err_alloc;
+
+ table[0].data = &net->ieee802154_lowpan.frags.high_thresh;
+ table[1].data = &net->ieee802154_lowpan.frags.low_thresh;
+ table[2].data = &net->ieee802154_lowpan.frags.timeout;
+ table[3].data = &net->ieee802154_lowpan.max_dsize;
+
+ /* Don't export sysctls to unprivileged users */
+ if (net->user_ns != &init_user_ns)
+ table[0].procname = NULL;
+ }
+
+ hdr = register_net_sysctl(net, "net/ieee802154/6lowpan", table);
+ if (hdr == NULL)
+ goto err_reg;
+
+ net->ieee802154_lowpan.sysctl.frags_hdr = hdr;
+ return 0;
+
+err_reg:
+ if (!net_eq(net, &init_net))
+ kfree(table);
+err_alloc:
+ return -ENOMEM;
+}
+
+static void __net_exit lowpan_frags_ns_sysctl_unregister(struct net *net)
+{
+ struct ctl_table *table;
+
+ table = net->ieee802154_lowpan.sysctl.frags_hdr->ctl_table_arg;
+ unregister_net_sysctl_table(net->ieee802154_lowpan.sysctl.frags_hdr);
+ if (!net_eq(net, &init_net))
+ kfree(table);
+}
+
+static struct ctl_table_header *lowpan_ctl_header;
+
+static int lowpan_frags_sysctl_register(void)
+{
+ lowpan_ctl_header = register_net_sysctl(&init_net,
+ "net/ieee802154/6lowpan",
+ lowpan_frags_ctl_table);
+ return lowpan_ctl_header == NULL ? -ENOMEM : 0;
+}
+
+static void lowpan_frags_sysctl_unregister(void)
+{
+ unregister_net_sysctl_table(lowpan_ctl_header);
+}
+#else
+static inline int lowpan_frags_ns_sysctl_register(struct net *net)
+{
+ return 0;
+}
+
+static inline void lowpan_frags_ns_sysctl_unregister(struct net *net)
+{
+}
+
+static inline int lowpan_frags_sysctl_register(void)
+{
+ return 0;
+}
+
+static inline void lowpan_frags_sysctl_unregister(void)
+{
+}
+#endif
+
+static int __net_init lowpan_frags_init_net(struct net *net)
+{
+ net->ieee802154_lowpan.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
+ net->ieee802154_lowpan.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
+ net->ieee802154_lowpan.frags.timeout = IPV6_FRAG_TIMEOUT;
+ net->ieee802154_lowpan.max_dsize = 0xFFFF;
+
+ inet_frags_init_net(&net->ieee802154_lowpan.frags);
+
+ return lowpan_frags_ns_sysctl_register(net);
+}
+
+static void __net_exit lowpan_frags_exit_net(struct net *net)
+{
+ lowpan_frags_ns_sysctl_unregister(net);
+ inet_frags_exit_net(&net->ieee802154_lowpan.frags, &lowpan_frags);
+}
+
+static struct pernet_operations lowpan_frags_ops = {
+ .init = lowpan_frags_init_net,
+ .exit = lowpan_frags_exit_net,
+};
+
+int __init lowpan_net_frag_init(void)
+{
+ int ret;
+
+ ret = lowpan_frags_sysctl_register();
+ if (ret)
+ return ret;
+
+ ret = register_pernet_subsys(&lowpan_frags_ops);
+ if (ret)
+ goto err_pernet;
+
+ lowpan_frags.hashfn = lowpan_hashfn;
+ lowpan_frags.constructor = lowpan_frag_init;
+ lowpan_frags.destructor = NULL;
+ lowpan_frags.skb_free = NULL;
+ lowpan_frags.qsize = sizeof(struct frag_queue);
+ lowpan_frags.match = lowpan_frag_match;
+ lowpan_frags.frag_expire = lowpan_frag_expire;
+ lowpan_frags.secret_interval = 10 * 60 * HZ;
+ inet_frags_init(&lowpan_frags);
+
+ return ret;
+err_pernet:
+ lowpan_frags_sysctl_unregister();
+ return ret;
+}
+
+void lowpan_net_frag_exit(void)
+{
+ inet_frags_fini(&lowpan_frags);
+ lowpan_frags_sysctl_unregister();
+ unregister_pernet_subsys(&lowpan_frags_ops);
+}
diff --git a/net/ieee802154/reassembly.h b/net/ieee802154/reassembly.h
new file mode 100644
index 0000000..74e4a7c
--- /dev/null
+++ b/net/ieee802154/reassembly.h
@@ -0,0 +1,41 @@
+#ifndef __IEEE802154_6LOWPAN_REASSEMBLY_H__
+#define __IEEE802154_6LOWPAN_REASSEMBLY_H__
+
+#include <net/inet_frag.h>
+
+struct lowpan_create_arg {
+ __be16 tag;
+ u16 d_size;
+ const struct ieee802154_addr *src;
+ const struct ieee802154_addr *dst;
+};
+
+/* Equivalent of ipv4 struct ip
+ */
+struct lowpan_frag_queue {
+ struct inet_frag_queue q;
+
+ __be16 tag;
+ u16 d_size;
+ struct ieee802154_addr saddr;
+ struct ieee802154_addr daddr;
+};
+
+static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a)
+{
+ switch (a->mode) {
+ case IEEE802154_ADDR_LONG:
+ return (((__force u64)a->extended_addr) >> 32) ^
+ (((__force u64)a->extended_addr) & 0xffffffff);
+ case IEEE802154_ADDR_SHORT:
+ return (__force u32)(a->short_addr);
+ default:
+ return 0;
+ }
+}
+
+int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type);
+void lowpan_net_frag_exit(void);
+int lowpan_net_frag_init(void);
+
+#endif /* __IEEE802154_6LOWPAN_REASSEMBLY_H__ */
diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c
index 4dd3761..edd0962 100644
--- a/net/ieee802154/wpan-class.c
+++ b/net/ieee802154/wpan-class.c
@@ -44,9 +44,7 @@
MASTER_SHOW(current_channel, "%d");
MASTER_SHOW(current_page, "%d");
-MASTER_SHOW_COMPLEX(transmit_power, "%d +- %d dB",
- ((signed char) (phy->transmit_power << 2)) >> 2,
- (phy->transmit_power >> 6) ? (phy->transmit_power >> 6) * 3 : 1);
+MASTER_SHOW(transmit_power, "%d +- 1 dB");
MASTER_SHOW(cca_mode, "%d");
static ssize_t channels_supported_show(struct device *dev,
@@ -171,6 +169,12 @@
phy->current_channel = -1; /* not initialised */
phy->current_page = 0; /* for compatibility */
+ /* defaults per 802.15.4-2011 */
+ phy->min_be = 3;
+ phy->max_be = 5;
+ phy->csma_retries = 4;
+ phy->frame_retries = -1; /* for compatibility, actual default is 3 */
+
return phy;
out:
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index f8c49ce..f032688 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -55,4 +55,4 @@
obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
- xfrm4_output.o
+ xfrm4_output.o xfrm4_protocol.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ecd2c3f..8c54870 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1296,8 +1296,11 @@
segs = ERR_PTR(-EPROTONOSUPPORT);
- /* Note : following gso_segment() might change skb->encapsulation */
- udpfrag = !skb->encapsulation && proto == IPPROTO_UDP;
+ if (skb->encapsulation &&
+ skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+ udpfrag = proto == IPPROTO_UDP && encap;
+ else
+ udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
ops = rcu_dereference(inet_offloads[proto]);
if (likely(ops && ops->callbacks.gso_segment))
@@ -1502,9 +1505,9 @@
bhptr = per_cpu_ptr(mib[0], cpu);
syncp = (struct u64_stats_sync *)(bhptr + syncp_offset);
do {
- start = u64_stats_fetch_begin_bh(syncp);
+ start = u64_stats_fetch_begin_irq(syncp);
v = *(((u64 *) bhptr) + offt);
- } while (u64_stats_fetch_retry_bh(syncp, start));
+ } while (u64_stats_fetch_retry_irq(syncp, start));
res += v;
}
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 7179026..a2afa89 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -155,6 +155,10 @@
struct iphdr *iph, *top_iph;
struct ip_auth_hdr *ah;
struct ah_data *ahp;
+ int seqhi_len = 0;
+ __be32 *seqhi;
+ int sglists = 0;
+ struct scatterlist *seqhisg;
ahp = x->data;
ahash = ahp->ahash;
@@ -167,14 +171,19 @@
ah = ip_auth_hdr(skb);
ihl = ip_hdrlen(skb);
+ if (x->props.flags & XFRM_STATE_ESN) {
+ sglists = 1;
+ seqhi_len = sizeof(*seqhi);
+ }
err = -ENOMEM;
- iph = ah_alloc_tmp(ahash, nfrags, ihl);
+ iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + seqhi_len);
if (!iph)
goto out;
-
- icv = ah_tmp_icv(ahash, iph, ihl);
+ seqhi = (__be32 *)((char *)iph + ihl);
+ icv = ah_tmp_icv(ahash, seqhi, seqhi_len);
req = ah_tmp_req(ahash, icv);
sg = ah_req_sg(ahash, req);
+ seqhisg = sg + nfrags;
memset(ah->auth_data, 0, ahp->icv_trunc_len);
@@ -210,10 +219,15 @@
ah->spi = x->id.spi;
ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
- sg_init_table(sg, nfrags);
- skb_to_sgvec(skb, sg, 0, skb->len);
+ sg_init_table(sg, nfrags + sglists);
+ skb_to_sgvec_nomark(skb, sg, 0, skb->len);
- ahash_request_set_crypt(req, sg, icv, skb->len);
+ if (x->props.flags & XFRM_STATE_ESN) {
+ /* Attach seqhi sg right after packet payload */
+ *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+ sg_set_buf(seqhisg, seqhi, seqhi_len);
+ }
+ ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
ahash_request_set_callback(req, 0, ah_output_done, skb);
AH_SKB_CB(skb)->tmp = iph;
@@ -295,6 +309,10 @@
struct ip_auth_hdr *ah;
struct ah_data *ahp;
int err = -ENOMEM;
+ int seqhi_len = 0;
+ __be32 *seqhi;
+ int sglists = 0;
+ struct scatterlist *seqhisg;
if (!pskb_may_pull(skb, sizeof(*ah)))
goto out;
@@ -335,14 +353,22 @@
iph = ip_hdr(skb);
ihl = ip_hdrlen(skb);
- work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len);
+ if (x->props.flags & XFRM_STATE_ESN) {
+ sglists = 1;
+ seqhi_len = sizeof(*seqhi);
+ }
+
+ work_iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl +
+ ahp->icv_trunc_len + seqhi_len);
if (!work_iph)
goto out;
- auth_data = ah_tmp_auth(work_iph, ihl);
+ seqhi = (__be32 *)((char *)work_iph + ihl);
+ auth_data = ah_tmp_auth(seqhi, seqhi_len);
icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len);
req = ah_tmp_req(ahash, icv);
sg = ah_req_sg(ahash, req);
+ seqhisg = sg + nfrags;
memcpy(work_iph, iph, ihl);
memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
@@ -361,10 +387,15 @@
skb_push(skb, ihl);
- sg_init_table(sg, nfrags);
- skb_to_sgvec(skb, sg, 0, skb->len);
+ sg_init_table(sg, nfrags + sglists);
+ skb_to_sgvec_nomark(skb, sg, 0, skb->len);
- ahash_request_set_crypt(req, sg, icv, skb->len);
+ if (x->props.flags & XFRM_STATE_ESN) {
+ /* Attach seqhi sg right after packet payload */
+ *seqhi = XFRM_SKB_CB(skb)->seq.input.hi;
+ sg_set_buf(seqhisg, seqhi, seqhi_len);
+ }
+ ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
ahash_request_set_callback(req, 0, ah_input_done, skb);
AH_SKB_CB(skb)->tmp = work_iph;
@@ -397,7 +428,7 @@
return err;
}
-static void ah4_err(struct sk_buff *skb, u32 info)
+static int ah4_err(struct sk_buff *skb, u32 info)
{
struct net *net = dev_net(skb->dev);
const struct iphdr *iph = (const struct iphdr *)skb->data;
@@ -407,23 +438,25 @@
switch (icmp_hdr(skb)->type) {
case ICMP_DEST_UNREACH:
if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
- return;
+ return 0;
case ICMP_REDIRECT:
break;
default:
- return;
+ return 0;
}
x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
ah->spi, IPPROTO_AH, AF_INET);
if (!x)
- return;
+ return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
else
ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0);
xfrm_state_put(x);
+
+ return 0;
}
static int ah_init_state(struct xfrm_state *x)
@@ -505,6 +538,10 @@
kfree(ahp);
}
+static int ah4_rcv_cb(struct sk_buff *skb, int err)
+{
+ return 0;
+}
static const struct xfrm_type ah_type =
{
@@ -518,11 +555,12 @@
.output = ah_output
};
-static const struct net_protocol ah4_protocol = {
+static struct xfrm4_protocol ah4_protocol = {
.handler = xfrm4_rcv,
+ .input_handler = xfrm_input,
+ .cb_handler = ah4_rcv_cb,
.err_handler = ah4_err,
- .no_policy = 1,
- .netns_ok = 1,
+ .priority = 0,
};
static int __init ah4_init(void)
@@ -531,7 +569,7 @@
pr_info("%s: can't add xfrm type\n", __func__);
return -EAGAIN;
}
- if (inet_add_protocol(&ah4_protocol, IPPROTO_AH) < 0) {
+ if (xfrm4_protocol_register(&ah4_protocol, IPPROTO_AH) < 0) {
pr_info("%s: can't add protocol\n", __func__);
xfrm_unregister_type(&ah_type, AF_INET);
return -EAGAIN;
@@ -541,7 +579,7 @@
static void __exit ah4_fini(void)
{
- if (inet_del_protocol(&ah4_protocol, IPPROTO_AH) < 0)
+ if (xfrm4_protocol_deregister(&ah4_protocol, IPPROTO_AH) < 0)
pr_info("%s: can't remove protocol\n", __func__);
if (xfrm_unregister_type(&ah_type, AF_INET) < 0)
pr_info("%s: can't remove xfrm type\n", __func__);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index ac2dff3..bdbf68b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1443,7 +1443,8 @@
+ nla_total_size(4) /* IFA_LOCAL */
+ nla_total_size(4) /* IFA_BROADCAST */
+ nla_total_size(IFNAMSIZ) /* IFA_LABEL */
- + nla_total_size(4); /* IFA_FLAGS */
+ + nla_total_size(4) /* IFA_FLAGS */
+ + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */
}
static inline u32 cstamp_delta(unsigned long cstamp)
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 7785b28..360b565 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -473,7 +473,7 @@
net_adj) & ~(blksize - 1)) + net_adj - 2;
}
-static void esp4_err(struct sk_buff *skb, u32 info)
+static int esp4_err(struct sk_buff *skb, u32 info)
{
struct net *net = dev_net(skb->dev);
const struct iphdr *iph = (const struct iphdr *)skb->data;
@@ -483,23 +483,25 @@
switch (icmp_hdr(skb)->type) {
case ICMP_DEST_UNREACH:
if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
- return;
+ return 0;
case ICMP_REDIRECT:
break;
default:
- return;
+ return 0;
}
x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
esph->spi, IPPROTO_ESP, AF_INET);
if (!x)
- return;
+ return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
else
ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0);
xfrm_state_put(x);
+
+ return 0;
}
static void esp_destroy(struct xfrm_state *x)
@@ -672,6 +674,11 @@
return err;
}
+static int esp4_rcv_cb(struct sk_buff *skb, int err)
+{
+ return 0;
+}
+
static const struct xfrm_type esp_type =
{
.description = "ESP4",
@@ -685,11 +692,12 @@
.output = esp_output
};
-static const struct net_protocol esp4_protocol = {
+static struct xfrm4_protocol esp4_protocol = {
.handler = xfrm4_rcv,
+ .input_handler = xfrm_input,
+ .cb_handler = esp4_rcv_cb,
.err_handler = esp4_err,
- .no_policy = 1,
- .netns_ok = 1,
+ .priority = 0,
};
static int __init esp4_init(void)
@@ -698,7 +706,7 @@
pr_info("%s: can't add xfrm type\n", __func__);
return -EAGAIN;
}
- if (inet_add_protocol(&esp4_protocol, IPPROTO_ESP) < 0) {
+ if (xfrm4_protocol_register(&esp4_protocol, IPPROTO_ESP) < 0) {
pr_info("%s: can't add protocol\n", __func__);
xfrm_unregister_type(&esp_type, AF_INET);
return -EAGAIN;
@@ -708,7 +716,7 @@
static void __exit esp4_fini(void)
{
- if (inet_del_protocol(&esp4_protocol, IPPROTO_ESP) < 0)
+ if (xfrm4_protocol_deregister(&esp4_protocol, IPPROTO_ESP) < 0)
pr_info("%s: can't remove protocol\n", __func__);
if (xfrm_unregister_type(&esp_type, AF_INET) < 0)
pr_info("%s: can't remove xfrm type\n", __func__);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c7539e2..1a629f8 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -659,7 +659,7 @@
if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
- return ip_rt_dump(skb, cb);
+ return skb->len;
s_h = cb->args[0];
s_e = cb->args[1];
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 1863422f..250be74 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -182,6 +182,14 @@
int i;
bool csum_err = false;
+#ifdef CONFIG_NET_IPGRE_BROADCAST
+ if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
+ /* Looped back packet, drop it! */
+ if (rt_is_output_route(skb_rtable(skb)))
+ goto drop;
+ }
+#endif
+
if (parse_gre_header(skb, &tpi, &csum_err) < 0)
goto drop;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index bb075fc..3b01959 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -208,7 +208,7 @@
}
work = frag_mem_limit(nf) - nf->low_thresh;
- while (work > 0) {
+ while (work > 0 || force) {
spin_lock(&nf->lru_lock);
if (list_empty(&nf->lru_list)) {
@@ -278,9 +278,10 @@
atomic_inc(&qp->refcnt);
hlist_add_head(&qp->list, &hb->chain);
+ inet_frag_lru_add(nf, qp);
spin_unlock(&hb->chain_lock);
read_unlock(&f->lock);
- inet_frag_lru_add(nf, qp);
+
return qp;
}
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index e9f1217..be8abe7 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,6 +39,71 @@
#include <net/route.h>
#include <net/xfrm.h>
+static bool ip_may_fragment(const struct sk_buff *skb)
+{
+ return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
+ !skb->local_df;
+}
+
+static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu || skb->local_df)
+ return false;
+
+ if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ return false;
+
+ return true;
+}
+
+static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
+{
+ unsigned int mtu;
+
+ if (skb->local_df || !skb_is_gso(skb))
+ return false;
+
+ mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true);
+
+ /* if seglen > mtu, do software segmentation for IP fragmentation on
+ * output. DF bit cannot be set since ip_forward would have sent
+ * icmp error.
+ */
+ return skb_gso_network_seglen(skb) > mtu;
+}
+
+/* called if GSO skb needs to be fragmented on forward */
+static int ip_forward_finish_gso(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ netdev_features_t features;
+ struct sk_buff *segs;
+ int ret = 0;
+
+ features = netif_skb_dev_features(skb, dst->dev);
+ segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+ if (IS_ERR(segs)) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+
+ consume_skb(skb);
+
+ do {
+ struct sk_buff *nskb = segs->next;
+ int err;
+
+ segs->next = NULL;
+ err = dst_output(segs);
+
+ if (err && ret == 0)
+ ret = err;
+ segs = nskb;
+ } while (segs);
+
+ return ret;
+}
+
static int ip_forward_finish(struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
@@ -49,6 +114,9 @@
if (unlikely(opt->optlen))
ip_forward_options(skb);
+ if (ip_gso_exceeds_dst_mtu(skb))
+ return ip_forward_finish_gso(skb);
+
return dst_output(skb);
}
@@ -59,6 +127,10 @@
struct rtable *rt; /* Route we use */
struct ip_options *opt = &(IPCB(skb)->opt);
+ /* that should never happen */
+ if (skb->pkt_type != PACKET_HOST)
+ goto drop;
+
if (skb_warn_if_lro(skb))
goto drop;
@@ -68,9 +140,6 @@
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
return NET_RX_SUCCESS;
- if (skb->pkt_type != PACKET_HOST)
- goto drop;
-
skb_forward_csum(skb);
/*
@@ -91,8 +160,7 @@
IPCB(skb)->flags |= IPSKB_FORWARDED;
mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
- if (unlikely(skb->len > mtu && !skb_is_gso(skb) &&
- (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
+ if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) {
IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8971780..1a0755f 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -422,9 +422,6 @@
to->tc_index = from->tc_index;
#endif
nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
- to->nf_trace = from->nf_trace;
-#endif
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
to->ipvs_property = from->ipvs_property;
#endif
@@ -449,7 +446,6 @@
__be16 not_last_frag;
struct rtable *rt = skb_rtable(skb);
int err = 0;
- bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
dev = rt->dst.dev;
@@ -459,7 +455,7 @@
iph = ip_hdr(skb);
- mtu = ip_dst_mtu_maybe_forward(&rt->dst, forwarding);
+ mtu = ip_skb_dst_mtu(skb);
if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) ||
(IPCB(skb)->frag_max_size &&
IPCB(skb)->frag_max_size > mtu))) {
@@ -825,8 +821,7 @@
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
- maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
- mtu : 0xFFFF;
+ maxnonfragsize = ip_sk_local_df(sk) ? 0xFFFF : mtu;
if (cork->length + length > maxnonfragsize - fragheaderlen) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
@@ -1149,8 +1144,7 @@
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
- maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
- mtu : 0xFFFF;
+ maxnonfragsize = ip_sk_local_df(sk) ? 0xFFFF : mtu;
if (cork->length + size > maxnonfragsize - fragheaderlen) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
@@ -1311,8 +1305,7 @@
* to fragment the frame generated here. No matter, what transforms
* how transforms change size of the packet, it will come out.
*/
- if (inet->pmtudisc < IP_PMTUDISC_DO)
- skb->local_df = 1;
+ skb->local_df = ip_sk_local_df(sk);
/* DF bit is set when we want to see DF on outgoing frames.
* If local_df is set too, we still allow to fragment this frame
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 580dd96..64741b9 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -186,7 +186,8 @@
}
EXPORT_SYMBOL(ip_cmsg_recv);
-int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
+int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
+ bool allow_ipv6)
{
int err, val;
struct cmsghdr *cmsg;
@@ -194,6 +195,22 @@
for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
if (!CMSG_OK(msg, cmsg))
return -EINVAL;
+#if defined(CONFIG_IPV6)
+ if (allow_ipv6 &&
+ cmsg->cmsg_level == SOL_IPV6 &&
+ cmsg->cmsg_type == IPV6_PKTINFO) {
+ struct in6_pktinfo *src_info;
+
+ if (cmsg->cmsg_len < CMSG_LEN(sizeof(*src_info)))
+ return -EINVAL;
+ src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
+ if (!ipv6_addr_v4mapped(&src_info->ipi6_addr))
+ return -EINVAL;
+ ipc->oif = src_info->ipi6_ifindex;
+ ipc->addr = src_info->ipi6_addr.s6_addr32[3];
+ continue;
+ }
+#endif
if (cmsg->cmsg_level != SOL_IP)
continue;
switch (cmsg->cmsg_type) {
@@ -626,7 +643,7 @@
inet->nodefrag = val ? 1 : 0;
break;
case IP_MTU_DISCOVER:
- if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_INTERFACE)
+ if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT)
goto e_inval;
inet->pmtudisc = val;
break;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index bd28f38..e77381d 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -93,84 +93,33 @@
tunnel_dst_set(t, NULL);
}
-static void tunnel_dst_reset_all(struct ip_tunnel *t)
+void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
{
int i;
for_each_possible_cpu(i)
__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
}
+EXPORT_SYMBOL(ip_tunnel_dst_reset_all);
-static struct dst_entry *tunnel_dst_get(struct ip_tunnel *t)
+static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
{
struct dst_entry *dst;
rcu_read_lock();
dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst);
- if (dst)
+ if (dst) {
+ if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
+ rcu_read_unlock();
+ tunnel_dst_reset(t);
+ return NULL;
+ }
dst_hold(dst);
+ }
rcu_read_unlock();
- return dst;
+ return (struct rtable *)dst;
}
-static struct dst_entry *tunnel_dst_check(struct ip_tunnel *t, u32 cookie)
-{
- struct dst_entry *dst = tunnel_dst_get(t);
-
- if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
- tunnel_dst_reset(t);
- return NULL;
- }
-
- return dst;
-}
-
-/* Often modified stats are per cpu, other are shared (netdev->stats) */
-struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_sw_netstats *tstats =
- per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
- }
-
- tot->multicast = dev->stats.multicast;
-
- tot->rx_crc_errors = dev->stats.rx_crc_errors;
- tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
- tot->rx_length_errors = dev->stats.rx_length_errors;
- tot->rx_frame_errors = dev->stats.rx_frame_errors;
- tot->rx_errors = dev->stats.rx_errors;
-
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
-
- tot->collisions = dev->stats.collisions;
-
- return tot;
-}
-EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
-
static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p,
__be16 flags, __be32 key)
{
@@ -286,13 +235,17 @@
{
unsigned int h;
__be32 remote;
+ __be32 i_key = parms->i_key;
if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr))
remote = parms->iph.daddr;
else
remote = 0;
- h = ip_tunnel_hash(parms->i_key, remote);
+ if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI))
+ i_key = 0;
+
+ h = ip_tunnel_hash(i_key, remote);
return &itn->tunnels[h];
}
@@ -449,7 +402,7 @@
fbt = netdev_priv(itn->fb_tunnel_dev);
dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
if (IS_ERR(dev))
- return NULL;
+ return ERR_CAST(dev);
dev->mtu = ip_tunnel_bind_dev(dev);
@@ -467,9 +420,6 @@
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
- /* Looped back packet, drop it! */
- if (rt_is_output_route(skb_rtable(skb)))
- goto drop;
tunnel->dev->stats.multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
@@ -584,7 +534,7 @@
struct flowi4 fl4;
u8 tos, ttl;
__be16 df;
- struct rtable *rt = NULL; /* Route to the other host */
+ struct rtable *rt; /* Route to the other host */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst;
int err;
@@ -657,8 +607,7 @@
init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link);
- if (connected)
- rt = (struct rtable *)tunnel_dst_check(tunnel, 0);
+ rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL;
if (!rt) {
rt = ip_route_output_key(tunnel->net, &fl4);
@@ -766,7 +715,7 @@
if (set_mtu)
dev->mtu = mtu;
}
- tunnel_dst_reset_all(t);
+ ip_tunnel_dst_reset_all(t);
netdev_state_change(dev);
}
@@ -803,9 +752,13 @@
t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
- if (!t && (cmd == SIOCADDTUNNEL))
+ if (!t && (cmd == SIOCADDTUNNEL)) {
t = ip_tunnel_create(net, itn, p);
-
+ if (IS_ERR(t)) {
+ err = PTR_ERR(t);
+ break;
+ }
+ }
if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
if (t != NULL) {
if (t->dev != dev) {
@@ -832,8 +785,9 @@
if (t) {
err = 0;
ip_tunnel_update(itn, t, dev, p, true);
- } else
- err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
+ } else {
+ err = -ENOENT;
+ }
break;
case SIOCDELTUNNEL:
@@ -1048,19 +1002,13 @@
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
- int i, err;
+ int err;
dev->destructor = ip_tunnel_dev_free;
- dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct pcpu_sw_netstats *ipt_stats;
- ipt_stats = per_cpu_ptr(dev->tstats, i);
- u64_stats_init(&ipt_stats->syncp);
- }
-
tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
if (!tunnel->dst_cache) {
free_percpu(dev->tstats);
@@ -1095,7 +1043,7 @@
if (itn->fb_tunnel_dev != dev)
ip_tunnel_del(netdev_priv(dev));
- tunnel_dst_reset_all(tunnel);
+ ip_tunnel_dst_reset_all(tunnel);
}
EXPORT_SYMBOL_GPL(ip_tunnel_uninit);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 6156f4e..e0c2b1d 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -148,3 +148,49 @@
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);
+
+/* Often modified stats are per cpu, other are shared (netdev->stats) */
+struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *tot)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ const struct pcpu_sw_netstats *tstats =
+ per_cpu_ptr(dev->tstats, i);
+ u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin_irq(&tstats->syncp);
+ rx_packets = tstats->rx_packets;
+ tx_packets = tstats->tx_packets;
+ rx_bytes = tstats->rx_bytes;
+ tx_bytes = tstats->tx_bytes;
+ } while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
+
+ tot->rx_packets += rx_packets;
+ tot->tx_packets += tx_packets;
+ tot->rx_bytes += rx_bytes;
+ tot->tx_bytes += tx_bytes;
+ }
+
+ tot->multicast = dev->stats.multicast;
+
+ tot->rx_crc_errors = dev->stats.rx_crc_errors;
+ tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
+ tot->rx_length_errors = dev->stats.rx_length_errors;
+ tot->rx_frame_errors = dev->stats.rx_frame_errors;
+ tot->rx_errors = dev->stats.rx_errors;
+
+ tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
+ tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
+ tot->tx_dropped = dev->stats.tx_dropped;
+ tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
+ tot->tx_errors = dev->stats.tx_errors;
+
+ tot->collisions = dev->stats.collisions;
+
+ return tot;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 48eafae..687ddef 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -34,6 +34,7 @@
#include <linux/init.h>
#include <linux/netfilter_ipv4.h>
#include <linux/if_ether.h>
+#include <linux/icmpv6.h>
#include <net/sock.h>
#include <net/ip.h>
@@ -49,8 +50,8 @@
static int vti_net_id __read_mostly;
static int vti_tunnel_init(struct net_device *dev);
-/* We dont digest the packet therefore let the packet pass */
-static int vti_rcv(struct sk_buff *skb)
+static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type)
{
struct ip_tunnel *tunnel;
const struct iphdr *iph = ip_hdr(skb);
@@ -60,79 +61,120 @@
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->saddr, iph->daddr, 0);
if (tunnel != NULL) {
- struct pcpu_sw_netstats *tstats;
- u32 oldmark = skb->mark;
- int ret;
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ goto drop;
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
+ skb->mark = be32_to_cpu(tunnel->parms.i_key);
- /* temporarily mark the skb with the tunnel o_key, to
- * only match policies with this mark.
- */
- skb->mark = be32_to_cpu(tunnel->parms.o_key);
- ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb);
- skb->mark = oldmark;
- if (!ret)
- return -1;
-
- tstats = this_cpu_ptr(tunnel->dev->tstats);
- u64_stats_update_begin(&tstats->syncp);
- tstats->rx_packets++;
- tstats->rx_bytes += skb->len;
- u64_stats_update_end(&tstats->syncp);
-
- secpath_reset(skb);
- skb->dev = tunnel->dev;
- return 1;
+ return xfrm_input(skb, nexthdr, spi, encap_type);
}
- return -1;
+ return -EINVAL;
+drop:
+ kfree_skb(skb);
+ return 0;
}
-/* This function assumes it is being called from dev_queue_xmit()
- * and that skb is filled properly by that function.
- */
-
-static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static int vti_rcv(struct sk_buff *skb)
{
- struct ip_tunnel *tunnel = netdev_priv(dev);
- struct iphdr *tiph = &tunnel->parms.iph;
- u8 tos;
- struct rtable *rt; /* Route to the other host */
- struct net_device *tdev; /* Device to other host */
- struct iphdr *old_iph = ip_hdr(skb);
- __be32 dst = tiph->daddr;
- struct flowi4 fl4;
- int err;
+ XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+ XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
- if (skb->protocol != htons(ETH_P_IP))
- goto tx_error;
+ return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
+}
- tos = old_iph->tos;
+static int vti_rcv_cb(struct sk_buff *skb, int err)
+{
+ unsigned short family;
+ struct net_device *dev;
+ struct pcpu_sw_netstats *tstats;
+ struct xfrm_state *x;
+ struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
- memset(&fl4, 0, sizeof(fl4));
- flowi4_init_output(&fl4, tunnel->parms.link,
- be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos),
- RT_SCOPE_UNIVERSE,
- IPPROTO_IPIP, 0,
- dst, tiph->saddr, 0, 0);
- rt = ip_route_output_key(dev_net(dev), &fl4);
- if (IS_ERR(rt)) {
- dev->stats.tx_carrier_errors++;
- goto tx_error_icmp;
+ if (!tunnel)
+ return 1;
+
+ dev = tunnel->dev;
+
+ if (err) {
+ dev->stats.rx_errors++;
+ dev->stats.rx_dropped++;
+
+ return 0;
}
+
+ x = xfrm_input_state(skb);
+ family = x->inner_mode->afinfo->family;
+
+ if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+ return -EPERM;
+
+ skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
+ skb->dev = dev;
+
+ tstats = this_cpu_ptr(dev->tstats);
+
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->rx_packets++;
+ tstats->rx_bytes += skb->len;
+ u64_stats_update_end(&tstats->syncp);
+
+ return 0;
+}
+
+static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src)
+{
+ xfrm_address_t *daddr = (xfrm_address_t *)&dst;
+ xfrm_address_t *saddr = (xfrm_address_t *)&src;
+
/* if there is no transform then this tunnel is not functional.
* Or if the xfrm is not mode tunnel.
*/
- if (!rt->dst.xfrm ||
- rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) {
+ if (!x || x->props.mode != XFRM_MODE_TUNNEL ||
+ x->props.family != AF_INET)
+ return false;
+
+ if (!dst)
+ return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET);
+
+ if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET))
+ return false;
+
+ return true;
+}
+
+static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
+ struct flowi *fl)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct ip_tunnel_parm *parms = &tunnel->parms;
+ struct dst_entry *dst = skb_dst(skb);
+ struct net_device *tdev; /* Device to other host */
+ int err;
+
+ if (!dst) {
dev->stats.tx_carrier_errors++;
- ip_rt_put(rt);
goto tx_error_icmp;
}
- tdev = rt->dst.dev;
+
+ dst_hold(dst);
+ dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0);
+ if (IS_ERR(dst)) {
+ dev->stats.tx_carrier_errors++;
+ goto tx_error_icmp;
+ }
+
+ if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) {
+ dev->stats.tx_carrier_errors++;
+ dst_release(dst);
+ goto tx_error_icmp;
+ }
+
+ tdev = dst->dev;
if (tdev == dev) {
- ip_rt_put(rt);
+ dst_release(dst);
dev->stats.collisions++;
goto tx_error;
}
@@ -146,10 +188,8 @@
tunnel->err_count = 0;
}
- memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
- nf_reset(skb);
+ skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
+ skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
err = dst_output(skb);
@@ -166,6 +206,95 @@
return NETDEV_TX_OK;
}
+/* This function assumes it is being called from dev_queue_xmit()
+ * and that skb is filled properly by that function.
+ */
+static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct flowi fl;
+
+ memset(&fl, 0, sizeof(fl));
+
+ skb->mark = be32_to_cpu(tunnel->parms.o_key);
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ xfrm_decode_session(skb, &fl, AF_INET);
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ break;
+ case htons(ETH_P_IPV6):
+ xfrm_decode_session(skb, &fl, AF_INET6);
+ memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ break;
+ default:
+ dev->stats.tx_errors++;
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
+ }
+
+ return vti_xmit(skb, dev, &fl);
+}
+
+static int vti4_err(struct sk_buff *skb, u32 info)
+{
+ __be32 spi;
+ struct xfrm_state *x;
+ struct ip_tunnel *tunnel;
+ struct ip_esp_hdr *esph;
+ struct ip_auth_hdr *ah ;
+ struct ip_comp_hdr *ipch;
+ struct net *net = dev_net(skb->dev);
+ const struct iphdr *iph = (const struct iphdr *)skb->data;
+ int protocol = iph->protocol;
+ struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
+
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->daddr, iph->saddr, 0);
+ if (!tunnel)
+ return -1;
+
+ switch (protocol) {
+ case IPPROTO_ESP:
+ esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
+ spi = esph->spi;
+ break;
+ case IPPROTO_AH:
+ ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
+ spi = ah->spi;
+ break;
+ case IPPROTO_COMP:
+ ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
+ spi = htonl(ntohs(ipch->cpi));
+ break;
+ default:
+ return 0;
+ }
+
+ switch (icmp_hdr(skb)->type) {
+ case ICMP_DEST_UNREACH:
+ if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+ return 0;
+ case ICMP_REDIRECT:
+ break;
+ default:
+ return 0;
+ }
+
+ x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+ spi, protocol, AF_INET);
+ if (!x)
+ return 0;
+
+ if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+ ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0);
+ else
+ ipv4_redirect(skb, net, 0, 0, protocol, 0);
+ xfrm_state_put(x);
+
+ return 0;
+}
+
static int
vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
@@ -181,12 +310,13 @@
return -EINVAL;
}
+ p.i_flags |= VTI_ISVTI;
err = ip_tunnel_ioctl(dev, &p, cmd);
if (err)
return err;
if (cmd != SIOCDELTUNNEL) {
- p.i_flags |= GRE_KEY | VTI_ISVTI;
+ p.i_flags |= GRE_KEY;
p.o_flags |= GRE_KEY;
}
@@ -224,7 +354,6 @@
dev->flags = IFF_NOARP;
dev->iflink = 0;
dev->addr_len = 4;
- dev->features |= NETIF_F_NETNS_LOCAL;
dev->features |= NETIF_F_LLTX;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
@@ -241,9 +370,28 @@
iph->ihl = 5;
}
-static struct xfrm_tunnel_notifier vti_handler __read_mostly = {
+static struct xfrm4_protocol vti_esp4_protocol __read_mostly = {
.handler = vti_rcv,
- .priority = 1,
+ .input_handler = vti_input,
+ .cb_handler = vti_rcv_cb,
+ .err_handler = vti4_err,
+ .priority = 100,
+};
+
+static struct xfrm4_protocol vti_ah4_protocol __read_mostly = {
+ .handler = vti_rcv,
+ .input_handler = vti_input,
+ .cb_handler = vti_rcv_cb,
+ .err_handler = vti4_err,
+ .priority = 100,
+};
+
+static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
+ .handler = vti_rcv,
+ .input_handler = vti_input,
+ .cb_handler = vti_rcv_cb,
+ .err_handler = vti4_err,
+ .priority = 100,
};
static int __net_init vti_init_net(struct net *net)
@@ -287,6 +435,8 @@
if (!data)
return;
+ parms->i_flags = VTI_ISVTI;
+
if (data[IFLA_VTI_LINK])
parms->link = nla_get_u32(data[IFLA_VTI_LINK]);
@@ -382,10 +532,31 @@
err = register_pernet_device(&vti_net_ops);
if (err < 0)
return err;
- err = xfrm4_mode_tunnel_input_register(&vti_handler);
+ err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP);
if (err < 0) {
unregister_pernet_device(&vti_net_ops);
pr_info("vti init: can't register tunnel\n");
+
+ return err;
+ }
+
+ err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH);
+ if (err < 0) {
+ xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
+ unregister_pernet_device(&vti_net_ops);
+ pr_info("vti init: can't register tunnel\n");
+
+ return err;
+ }
+
+ err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP);
+ if (err < 0) {
+ xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
+ xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
+ unregister_pernet_device(&vti_net_ops);
+ pr_info("vti init: can't register tunnel\n");
+
+ return err;
}
err = rtnl_link_register(&vti_link_ops);
@@ -395,7 +566,9 @@
return err;
rtnl_link_failed:
- xfrm4_mode_tunnel_input_deregister(&vti_handler);
+ xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
+ xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
+ xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
unregister_pernet_device(&vti_net_ops);
return err;
}
@@ -403,8 +576,13 @@
static void __exit vti_fini(void)
{
rtnl_link_unregister(&vti_link_ops);
- if (xfrm4_mode_tunnel_input_deregister(&vti_handler))
+ if (xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP))
pr_info("vti close: can't deregister tunnel\n");
+ if (xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH))
+ pr_info("vti close: can't deregister tunnel\n");
+ if (xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP))
+ pr_info("vti close: can't deregister tunnel\n");
+
unregister_pernet_device(&vti_net_ops);
}
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 826be4c..c0855d5 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -23,7 +23,7 @@
#include <net/protocol.h>
#include <net/sock.h>
-static void ipcomp4_err(struct sk_buff *skb, u32 info)
+static int ipcomp4_err(struct sk_buff *skb, u32 info)
{
struct net *net = dev_net(skb->dev);
__be32 spi;
@@ -34,24 +34,26 @@
switch (icmp_hdr(skb)->type) {
case ICMP_DEST_UNREACH:
if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
- return;
+ return 0;
case ICMP_REDIRECT:
break;
default:
- return;
+ return 0;
}
spi = htonl(ntohs(ipch->cpi));
x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
spi, IPPROTO_COMP, AF_INET);
if (!x)
- return;
+ return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0);
else
ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0);
xfrm_state_put(x);
+
+ return 0;
}
/* We always hold one tunnel user reference to indicate a tunnel */
@@ -147,6 +149,11 @@
return err;
}
+static int ipcomp4_rcv_cb(struct sk_buff *skb, int err)
+{
+ return 0;
+}
+
static const struct xfrm_type ipcomp_type = {
.description = "IPCOMP4",
.owner = THIS_MODULE,
@@ -157,11 +164,12 @@
.output = ipcomp_output
};
-static const struct net_protocol ipcomp4_protocol = {
+static struct xfrm4_protocol ipcomp4_protocol = {
.handler = xfrm4_rcv,
+ .input_handler = xfrm_input,
+ .cb_handler = ipcomp4_rcv_cb,
.err_handler = ipcomp4_err,
- .no_policy = 1,
- .netns_ok = 1,
+ .priority = 0,
};
static int __init ipcomp4_init(void)
@@ -170,7 +178,7 @@
pr_info("%s: can't add xfrm type\n", __func__);
return -EAGAIN;
}
- if (inet_add_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) {
+ if (xfrm4_protocol_register(&ipcomp4_protocol, IPPROTO_COMP) < 0) {
pr_info("%s: can't add protocol\n", __func__);
xfrm_unregister_type(&ipcomp_type, AF_INET);
return -EAGAIN;
@@ -180,7 +188,7 @@
static void __exit ipcomp4_fini(void)
{
- if (inet_del_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0)
+ if (xfrm4_protocol_deregister(&ipcomp4_protocol, IPPROTO_COMP) < 0)
pr_info("%s: can't remove protocol\n", __func__);
if (xfrm_unregister_type(&ipcomp_type, AF_INET) < 0)
pr_info("%s: can't remove xfrm type\n", __func__);
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index efa1138..b3e86ea 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -273,7 +273,7 @@
msleep(1);
- if time_before(jiffies, next_msg)
+ if (time_before(jiffies, next_msg))
continue;
elapsed = jiffies_to_msecs(jiffies - start);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index b9b3472..28863570 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2255,13 +2255,14 @@
}
static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
- u32 portid, u32 seq, struct mfc_cache *c, int cmd)
+ u32 portid, u32 seq, struct mfc_cache *c, int cmd,
+ int flags)
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
int err;
- nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
+ nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
if (nlh == NULL)
return -EMSGSIZE;
@@ -2329,7 +2330,7 @@
if (skb == NULL)
goto errout;
- err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+ err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
if (err < 0)
goto errout;
@@ -2368,7 +2369,8 @@
if (ipmr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc, RTM_NEWROUTE) < 0)
+ mfc, RTM_NEWROUTE,
+ NLM_F_MULTI) < 0)
goto done;
next_entry:
e++;
@@ -2382,7 +2384,8 @@
if (ipmr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc, RTM_NEWROUTE) < 0) {
+ mfc, RTM_NEWROUTE,
+ NLM_F_MULTI) < 0) {
spin_unlock_bh(&mfc_unres_lock);
goto done;
}
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index c3e0ade..7ebd6e3 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -61,7 +61,7 @@
skb_dst_set(skb, NULL);
dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
if (IS_ERR(dst))
- return PTR_ERR(dst);;
+ return PTR_ERR(dst);
skb_dst_set(skb, dst);
}
#endif
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 81c6910..a26ce03 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -61,6 +61,11 @@
packet transformations such as the source, destination address and
source and destination ports.
+config NFT_REJECT_IPV4
+ depends on NF_TABLES_IPV4
+ default NFT_REJECT
+ tristate
+
config NF_TABLES_ARP
depends on NF_TABLES
tristate "ARP nf_tables support"
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index c16be9d..90b8240 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -30,6 +30,7 @@
obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
+obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
# generic IP tables
diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c
index 9eea059d..574f7eb 100644
--- a/net/ipv4/netfilter/nf_nat_h323.c
+++ b/net/ipv4/netfilter/nf_nat_h323.c
@@ -229,7 +229,10 @@
ret = nf_ct_expect_related(rtcp_exp);
if (ret == 0)
break;
- else if (ret != -EBUSY) {
+ else if (ret == -EBUSY) {
+ nf_ct_unexpect_related(rtp_exp);
+ continue;
+ } else if (ret < 0) {
nf_ct_unexpect_related(rtp_exp);
nated_port = 0;
break;
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index d551e31..7c67667 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -1198,8 +1198,8 @@
map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip);
} else {
/* DNAT replies */
- map.from = NOCT1(&ct->tuplehash[dir].tuple.src.u3.ip);
- map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip);
+ map.from = NOCT1(&ct->tuplehash[!dir].tuple.src.u3.ip);
+ map.to = NOCT1(&ct->tuplehash[dir].tuple.dst.u3.ip);
}
if (map.from == map.to)
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
new file mode 100644
index 0000000..e79718a
--- /dev/null
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -0,0 +1,75 @@
+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2013 Eric Leblond <eric@regit.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/icmp.h>
+#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/nft_reject.h>
+
+void nft_reject_ipv4_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_reject *priv = nft_expr_priv(expr);
+
+ switch (priv->type) {
+ case NFT_REJECT_ICMP_UNREACH:
+ nf_send_unreach(pkt->skb, priv->icmp_code);
+ break;
+ case NFT_REJECT_TCP_RST:
+ nf_send_reset(pkt->skb, pkt->ops->hooknum);
+ break;
+ }
+
+ data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+EXPORT_SYMBOL_GPL(nft_reject_ipv4_eval);
+
+static struct nft_expr_type nft_reject_ipv4_type;
+static const struct nft_expr_ops nft_reject_ipv4_ops = {
+ .type = &nft_reject_ipv4_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+ .eval = nft_reject_ipv4_eval,
+ .init = nft_reject_init,
+ .dump = nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_ipv4_type __read_mostly = {
+ .family = NFPROTO_IPV4,
+ .name = "reject",
+ .ops = &nft_reject_ipv4_ops,
+ .policy = nft_reject_policy,
+ .maxattr = NFTA_REJECT_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_reject_ipv4_module_init(void)
+{
+ return nft_register_expr(&nft_reject_ipv4_type);
+}
+
+static void __exit nft_reject_ipv4_module_exit(void)
+{
+ nft_unregister_expr(&nft_reject_ipv4_type);
+}
+
+module_init(nft_reject_ipv4_module_init);
+module_exit(nft_reject_ipv4_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "reject");
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 2d11c09..f4b19e5 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -727,7 +727,7 @@
sock_tx_timestamp(sk, &ipc.tx_flags);
if (msg->msg_controllen) {
- err = ip_cmsg_send(sock_net(sk), msg, &ipc);
+ err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
if (err)
return err;
if (ipc.opt)
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index a6c8a80..ad737fa 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -273,6 +273,7 @@
SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK),
SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE),
SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE),
+ SNMP_MIB_ITEM("TCPFastOpenActiveFail", LINUX_MIB_TCPFASTOPENACTIVEFAIL),
SNMP_MIB_ITEM("TCPFastOpenPassive", LINUX_MIB_TCPFASTOPENPASSIVE),
SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL),
SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW),
@@ -280,6 +281,11 @@
SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES),
SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS),
SNMP_MIB_ITEM("TCPAutoCorking", LINUX_MIB_TCPAUTOCORKING),
+ SNMP_MIB_ITEM("TCPFromZeroWindowAdv", LINUX_MIB_TCPFROMZEROWINDOWADV),
+ SNMP_MIB_ITEM("TCPToZeroWindowAdv", LINUX_MIB_TCPTOZEROWINDOWADV),
+ SNMP_MIB_ITEM("TCPWantZeroWindowAdv", LINUX_MIB_TCPWANTZEROWINDOWADV),
+ SNMP_MIB_ITEM("TCPSynRetrans", LINUX_MIB_TCPSYNRETRANS),
+ SNMP_MIB_ITEM("TCPOrigDataSent", LINUX_MIB_TCPORIGDATASENT),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index c04518f..a9dbe58 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -524,7 +524,7 @@
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
- err = ip_cmsg_send(sock_net(sk), msg, &ipc);
+ err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
if (err)
goto out;
if (ipc.opt)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 25071b4..1be9e99 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -139,11 +139,6 @@
struct sk_buff *skb);
static void ipv4_dst_destroy(struct dst_entry *dst);
-static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
- int how)
-{
-}
-
static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old)
{
WARN_ON(1);
@@ -162,7 +157,6 @@
.mtu = ipv4_mtu,
.cow_metrics = ipv4_cow_metrics,
.destroy = ipv4_dst_destroy,
- .ifdown = ipv4_dst_ifdown,
.negative_advice = ipv4_negative_advice,
.link_failure = ipv4_link_failure,
.update_pmtu = ip_rt_update_pmtu,
@@ -697,7 +691,6 @@
out_unlock:
spin_unlock_bh(&fnhe_lock);
- return;
}
static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4,
@@ -1597,6 +1590,7 @@
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+ RT_CACHE_STAT_INC(in_slow_tot);
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
@@ -1695,10 +1689,11 @@
fl4.daddr = daddr;
fl4.saddr = saddr;
err = fib_lookup(net, &fl4, &res);
- if (err != 0)
+ if (err != 0) {
+ if (!IN_DEV_FORWARD(in_dev))
+ err = -EHOSTUNREACH;
goto no_route;
-
- RT_CACHE_STAT_INC(in_slow_tot);
+ }
if (res.type == RTN_BROADCAST)
goto brd_input;
@@ -1712,8 +1707,10 @@
goto local_input;
}
- if (!IN_DEV_FORWARD(in_dev))
+ if (!IN_DEV_FORWARD(in_dev)) {
+ err = -EHOSTUNREACH;
goto no_route;
+ }
if (res.type != RTN_UNICAST)
goto martian_destination;
@@ -1768,6 +1765,7 @@
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+ RT_CACHE_STAT_INC(in_slow_tot);
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;
@@ -2470,11 +2468,6 @@
goto errout;
}
-int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb)
-{
- return skb->len;
-}
-
void ip_rt_multicast_event(struct in_device *in_dev)
{
rt_cache_flush(dev_net(in_dev->dev));
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4475b3b..4bd6d52 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -387,7 +387,7 @@
INIT_LIST_HEAD(&tp->tsq_node);
icsk->icsk_rto = TCP_TIMEOUT_INIT;
- tp->mdev = TCP_TIMEOUT_INIT;
+ tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
/* So many TCP implementations out there (incorrectly) count the
* initial SYN frame in their delayed-ACK and congestion control
@@ -1044,7 +1044,8 @@
}
}
-static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
+static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
+ int *copied, size_t size)
{
struct tcp_sock *tp = tcp_sk(sk);
int err, flags;
@@ -1059,11 +1060,12 @@
if (unlikely(tp->fastopen_req == NULL))
return -ENOBUFS;
tp->fastopen_req->data = msg;
+ tp->fastopen_req->size = size;
flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
msg->msg_namelen, flags);
- *size = tp->fastopen_req->copied;
+ *copied = tp->fastopen_req->copied;
tcp_free_fastopen_req(tp);
return err;
}
@@ -1083,7 +1085,7 @@
flags = msg->msg_flags;
if (flags & MSG_FASTOPEN) {
- err = tcp_sendmsg_fastopen(sk, msg, &copied_syn);
+ err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
if (err == -EINPROGRESS && copied_syn > 0)
goto out;
else if (err)
@@ -2229,7 +2231,7 @@
/* This is a (useful) BSD violating of the RFC. There is a
* problem with TCP as specified in that the other end could
* keep a socket open forever with no application left this end.
- * We use a 3 minute timeout (about the same as BSD) then kill
+ * We use a 1 minute timeout (about the same as BSD) then kill
* our end. If they send after that then tough - BUT: long enough
* that we won't make the old 4*rto = almost no time - whoops
* reset mistake.
@@ -2339,7 +2341,7 @@
sk->sk_shutdown = 0;
sock_reset_flag(sk, SOCK_DONE);
- tp->srtt = 0;
+ tp->srtt_us = 0;
if ((tp->write_seq += tp->max_window + 2) == 0)
tp->write_seq = 1;
icsk->icsk_backoff = 0;
@@ -2783,8 +2785,8 @@
info->tcpi_pmtu = icsk->icsk_pmtu_cookie;
info->tcpi_rcv_ssthresh = tp->rcv_ssthresh;
- info->tcpi_rtt = jiffies_to_usecs(tp->srtt)>>3;
- info->tcpi_rttvar = jiffies_to_usecs(tp->mdev)>>2;
+ info->tcpi_rtt = tp->srtt_us >> 3;
+ info->tcpi_rttvar = tp->mdev_us >> 2;
info->tcpi_snd_ssthresh = tp->snd_ssthresh;
info->tcpi_snd_cwnd = tp->snd_cwnd;
info->tcpi_advmss = tp->advmss;
@@ -2794,6 +2796,11 @@
info->tcpi_rcv_space = tp->rcvq_space.space;
info->tcpi_total_retrans = tp->total_retrans;
+
+ info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ?
+ sk->sk_pacing_rate : ~0ULL;
+ info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ?
+ sk->sk_max_pacing_rate : ~0ULL;
}
EXPORT_SYMBOL_GPL(tcp_get_info);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index ad37bf1..2b9464c 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -290,8 +290,7 @@
left = tp->snd_cwnd - in_flight;
if (sk_can_gso(sk) &&
left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd &&
- left * tp->mss_cache < sk->sk_gso_max_size &&
- left < sk->sk_gso_max_segs)
+ left < tp->xmit_size_goal_segs)
return true;
return left <= tcp_max_tso_deferred_mss(tp);
}
@@ -362,21 +361,12 @@
}
EXPORT_SYMBOL_GPL(tcp_reno_ssthresh);
-/* Lower bound on congestion window with halving. */
-u32 tcp_reno_min_cwnd(const struct sock *sk)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
- return tp->snd_ssthresh/2;
-}
-EXPORT_SYMBOL_GPL(tcp_reno_min_cwnd);
-
struct tcp_congestion_ops tcp_reno = {
.flags = TCP_CONG_NON_RESTRICTED,
.name = "reno",
.owner = THIS_MODULE,
.ssthresh = tcp_reno_ssthresh,
.cong_avoid = tcp_reno_cong_avoid,
- .min_cwnd = tcp_reno_min_cwnd,
};
/* Initial congestion control used (until SYN)
@@ -388,6 +378,5 @@
.owner = THIS_MODULE,
.ssthresh = tcp_reno_ssthresh,
.cong_avoid = tcp_reno_cong_avoid,
- .min_cwnd = tcp_reno_min_cwnd,
};
EXPORT_SYMBOL_GPL(tcp_init_congestion_ops);
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 828e4c3..8bf2245 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -476,10 +476,6 @@
/* divide by bic_scale and by constant Srtt (100ms) */
do_div(cube_factor, bic_scale * 10);
- /* hystart needs ms clock resolution */
- if (hystart && HZ < 1000)
- cubictcp.flags |= TCP_CONG_RTT_STAMP;
-
return tcp_register_congestion_control(&cubictcp);
}
diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c
index 8ed9305..8b9e7ba 100644
--- a/net/ipv4/tcp_highspeed.c
+++ b/net/ipv4/tcp_highspeed.c
@@ -162,7 +162,6 @@
.init = hstcp_init,
.ssthresh = hstcp_ssthresh,
.cong_avoid = hstcp_cong_avoid,
- .min_cwnd = tcp_reno_min_cwnd,
.owner = THIS_MODULE,
.name = "highspeed"
diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c
index 478fe82..a15a799 100644
--- a/net/ipv4/tcp_hybla.c
+++ b/net/ipv4/tcp_hybla.c
@@ -21,7 +21,7 @@
u32 rho2; /* Rho * Rho, integer part */
u32 rho_3ls; /* Rho parameter, <<3 */
u32 rho2_7ls; /* Rho^2, <<7 */
- u32 minrtt; /* Minimum smoothed round trip time value seen */
+ u32 minrtt_us; /* Minimum smoothed round trip time value seen */
};
/* Hybla reference round trip time (default= 1/40 sec = 25 ms), in ms */
@@ -35,7 +35,9 @@
{
struct hybla *ca = inet_csk_ca(sk);
- ca->rho_3ls = max_t(u32, tcp_sk(sk)->srtt / msecs_to_jiffies(rtt0), 8);
+ ca->rho_3ls = max_t(u32,
+ tcp_sk(sk)->srtt_us / (rtt0 * USEC_PER_MSEC),
+ 8U);
ca->rho = ca->rho_3ls >> 3;
ca->rho2_7ls = (ca->rho_3ls * ca->rho_3ls) << 1;
ca->rho2 = ca->rho2_7ls >> 7;
@@ -59,7 +61,7 @@
hybla_recalc_param(sk);
/* set minimum rtt as this is the 1st ever seen */
- ca->minrtt = tp->srtt;
+ ca->minrtt_us = tp->srtt_us;
tp->snd_cwnd = ca->rho;
}
@@ -94,9 +96,9 @@
int is_slowstart = 0;
/* Recalculate rho only if this srtt is the lowest */
- if (tp->srtt < ca->minrtt){
+ if (tp->srtt_us < ca->minrtt_us) {
hybla_recalc_param(sk);
- ca->minrtt = tp->srtt;
+ ca->minrtt_us = tp->srtt_us;
}
if (!tcp_is_cwnd_limited(sk, in_flight))
@@ -166,7 +168,6 @@
static struct tcp_congestion_ops tcp_hybla __read_mostly = {
.init = hybla_init,
.ssthresh = tcp_reno_ssthresh,
- .min_cwnd = tcp_reno_min_cwnd,
.cong_avoid = hybla_cong_avoid,
.set_state = hybla_state,
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index e498a62..863d105 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -325,10 +325,8 @@
}
static struct tcp_congestion_ops tcp_illinois __read_mostly = {
- .flags = TCP_CONG_RTT_STAMP,
.init = tcp_illinois_init,
.ssthresh = tcp_illinois_ssthresh,
- .min_cwnd = tcp_reno_min_cwnd,
.cong_avoid = tcp_illinois_cong_avoid,
.set_state = tcp_illinois_state,
.get_info = tcp_illinois_info,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 65cf90e..e1661f4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -667,10 +667,11 @@
* To save cycles in the RFC 1323 implementation it was better to break
* it up into three procedures. -- erics
*/
-static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
+static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
{
struct tcp_sock *tp = tcp_sk(sk);
- long m = mrtt; /* RTT */
+ long m = mrtt_us; /* RTT */
+ u32 srtt = tp->srtt_us;
/* The following amusing code comes from Jacobson's
* article in SIGCOMM '88. Note that rtt and mdev
@@ -688,14 +689,12 @@
* does not matter how to _calculate_ it. Seems, it was trap
* that VJ failed to avoid. 8)
*/
- if (m == 0)
- m = 1;
- if (tp->srtt != 0) {
- m -= (tp->srtt >> 3); /* m is now error in rtt est */
- tp->srtt += m; /* rtt = 7/8 rtt + 1/8 new */
+ if (srtt != 0) {
+ m -= (srtt >> 3); /* m is now error in rtt est */
+ srtt += m; /* rtt = 7/8 rtt + 1/8 new */
if (m < 0) {
m = -m; /* m is now abs(error) */
- m -= (tp->mdev >> 2); /* similar update on mdev */
+ m -= (tp->mdev_us >> 2); /* similar update on mdev */
/* This is similar to one of Eifel findings.
* Eifel blocks mdev updates when rtt decreases.
* This solution is a bit different: we use finer gain
@@ -707,27 +706,29 @@
if (m > 0)
m >>= 3;
} else {
- m -= (tp->mdev >> 2); /* similar update on mdev */
+ m -= (tp->mdev_us >> 2); /* similar update on mdev */
}
- tp->mdev += m; /* mdev = 3/4 mdev + 1/4 new */
- if (tp->mdev > tp->mdev_max) {
- tp->mdev_max = tp->mdev;
- if (tp->mdev_max > tp->rttvar)
- tp->rttvar = tp->mdev_max;
+ tp->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */
+ if (tp->mdev_us > tp->mdev_max_us) {
+ tp->mdev_max_us = tp->mdev_us;
+ if (tp->mdev_max_us > tp->rttvar_us)
+ tp->rttvar_us = tp->mdev_max_us;
}
if (after(tp->snd_una, tp->rtt_seq)) {
- if (tp->mdev_max < tp->rttvar)
- tp->rttvar -= (tp->rttvar - tp->mdev_max) >> 2;
+ if (tp->mdev_max_us < tp->rttvar_us)
+ tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2;
tp->rtt_seq = tp->snd_nxt;
- tp->mdev_max = tcp_rto_min(sk);
+ tp->mdev_max_us = tcp_rto_min_us(sk);
}
} else {
/* no previous measure. */
- tp->srtt = m << 3; /* take the measured time to be rtt */
- tp->mdev = m << 1; /* make sure rto = 3*rtt */
- tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
+ srtt = m << 3; /* take the measured time to be rtt */
+ tp->mdev_us = m << 1; /* make sure rto = 3*rtt */
+ tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk));
+ tp->mdev_max_us = tp->rttvar_us;
tp->rtt_seq = tp->snd_nxt;
}
+ tp->srtt_us = max(1U, srtt);
}
/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
@@ -742,18 +743,12 @@
u64 rate;
/* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
- rate = (u64)tp->mss_cache * 2 * (HZ << 3);
+ rate = (u64)tp->mss_cache * 2 * (USEC_PER_SEC << 3);
rate *= max(tp->snd_cwnd, tp->packets_out);
- /* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3),
- * be conservative and assume srtt = 1 (125 us instead of 1.25 ms)
- * We probably need usec resolution in the future.
- * Note: This also takes care of possible srtt=0 case,
- * when tcp_rtt_estimator() was not yet called.
- */
- if (tp->srtt > 8 + 2)
- do_div(rate, tp->srtt);
+ if (likely(tp->srtt_us))
+ do_div(rate, tp->srtt_us);
/* ACCESS_ONCE() is needed because sch_fq fetches sk_pacing_rate
* without any lock. We want to make sure compiler wont store
@@ -1120,10 +1115,10 @@
}
struct tcp_sacktag_state {
- int reord;
- int fack_count;
- int flag;
- s32 rtt; /* RTT measured by SACKing never-retransmitted data */
+ int reord;
+ int fack_count;
+ long rtt_us; /* RTT measured by SACKing never-retransmitted data */
+ int flag;
};
/* Check if skb is fully within the SACK block. In presence of GSO skbs,
@@ -1184,7 +1179,8 @@
static u8 tcp_sacktag_one(struct sock *sk,
struct tcp_sacktag_state *state, u8 sacked,
u32 start_seq, u32 end_seq,
- int dup_sack, int pcount, u32 xmit_time)
+ int dup_sack, int pcount,
+ const struct skb_mstamp *xmit_time)
{
struct tcp_sock *tp = tcp_sk(sk);
int fack_count = state->fack_count;
@@ -1225,8 +1221,13 @@
if (!after(end_seq, tp->high_seq))
state->flag |= FLAG_ORIG_SACK_ACKED;
/* Pick the earliest sequence sacked for RTT */
- if (state->rtt < 0)
- state->rtt = tcp_time_stamp - xmit_time;
+ if (state->rtt_us < 0) {
+ struct skb_mstamp now;
+
+ skb_mstamp_get(&now);
+ state->rtt_us = skb_mstamp_us_delta(&now,
+ xmit_time);
+ }
}
if (sacked & TCPCB_LOST) {
@@ -1285,7 +1286,7 @@
*/
tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
start_seq, end_seq, dup_sack, pcount,
- TCP_SKB_CB(skb)->when);
+ &skb->skb_mstamp);
if (skb == tp->lost_skb_hint)
tp->lost_cnt_hint += pcount;
@@ -1563,7 +1564,7 @@
TCP_SKB_CB(skb)->end_seq,
dup_sack,
tcp_skb_pcount(skb),
- TCP_SKB_CB(skb)->when);
+ &skb->skb_mstamp);
if (!before(TCP_SKB_CB(skb)->seq,
tcp_highest_sack_seq(tp)))
@@ -1620,7 +1621,7 @@
static int
tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
- u32 prior_snd_una, s32 *sack_rtt)
+ u32 prior_snd_una, long *sack_rtt_us)
{
struct tcp_sock *tp = tcp_sk(sk);
const unsigned char *ptr = (skb_transport_header(ack_skb) +
@@ -1638,7 +1639,7 @@
state.flag = 0;
state.reord = tp->packets_out;
- state.rtt = -1;
+ state.rtt_us = -1L;
if (!tp->sacked_out) {
if (WARN_ON(tp->fackets_out))
@@ -1822,7 +1823,7 @@
WARN_ON((int)tp->retrans_out < 0);
WARN_ON((int)tcp_packets_in_flight(tp) < 0);
#endif
- *sack_rtt = state.rtt;
+ *sack_rtt_us = state.rtt_us;
return state.flag;
}
@@ -1943,8 +1944,9 @@
if (skb == tcp_send_head(sk))
break;
- if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
tp->undo_marker = 0;
+
TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
@@ -2032,10 +2034,12 @@
* available, or RTO is scheduled to fire first.
*/
if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 ||
- (flag & FLAG_ECE) || !tp->srtt)
+ (flag & FLAG_ECE) || !tp->srtt_us)
return false;
- delay = max_t(unsigned long, (tp->srtt >> 5), msecs_to_jiffies(2));
+ delay = max(usecs_to_jiffies(tp->srtt_us >> 5),
+ msecs_to_jiffies(2));
+
if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay)))
return false;
@@ -2882,7 +2886,7 @@
}
static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
- s32 seq_rtt, s32 sack_rtt)
+ long seq_rtt_us, long sack_rtt_us)
{
const struct tcp_sock *tp = tcp_sk(sk);
@@ -2892,10 +2896,10 @@
* is acked (RFC6298).
*/
if (flag & FLAG_RETRANS_DATA_ACKED)
- seq_rtt = -1;
+ seq_rtt_us = -1L;
- if (seq_rtt < 0)
- seq_rtt = sack_rtt;
+ if (seq_rtt_us < 0)
+ seq_rtt_us = sack_rtt_us;
/* RTTM Rule: A TSecr value received in a segment is used to
* update the averaged RTT measurement only if the segment
@@ -2903,14 +2907,14 @@
* left edge of the send window.
* See draft-ietf-tcplw-high-performance-00, section 3.3.
*/
- if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
+ if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
flag & FLAG_ACKED)
- seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
+ seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - tp->rx_opt.rcv_tsecr);
- if (seq_rtt < 0)
+ if (seq_rtt_us < 0)
return false;
- tcp_rtt_estimator(sk, seq_rtt);
+ tcp_rtt_estimator(sk, seq_rtt_us);
tcp_set_rto(sk);
/* RFC6298: only reset backoff on valid RTT measurement. */
@@ -2922,16 +2926,16 @@
static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp)
{
struct tcp_sock *tp = tcp_sk(sk);
- s32 seq_rtt = -1;
+ long seq_rtt_us = -1L;
if (synack_stamp && !tp->total_retrans)
- seq_rtt = tcp_time_stamp - synack_stamp;
+ seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - synack_stamp);
/* If the ACK acks both the SYNACK and the (Fast Open'd) data packets
* sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack()
*/
- if (!tp->srtt)
- tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1);
+ if (!tp->srtt_us)
+ tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt_us, -1L);
}
static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
@@ -3020,26 +3024,27 @@
* arrived at the other end.
*/
static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
- u32 prior_snd_una, s32 sack_rtt)
+ u32 prior_snd_una, long sack_rtt_us)
{
- struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
- struct sk_buff *skb;
- u32 now = tcp_time_stamp;
- bool fully_acked = true;
- int flag = 0;
- u32 pkts_acked = 0;
- u32 reord = tp->packets_out;
+ struct skb_mstamp first_ackt, last_ackt, now;
+ struct tcp_sock *tp = tcp_sk(sk);
u32 prior_sacked = tp->sacked_out;
- s32 seq_rtt = -1;
- s32 ca_seq_rtt = -1;
- ktime_t last_ackt = net_invalid_timestamp();
+ u32 reord = tp->packets_out;
+ bool fully_acked = true;
+ long ca_seq_rtt_us = -1L;
+ long seq_rtt_us = -1L;
+ struct sk_buff *skb;
+ u32 pkts_acked = 0;
bool rtt_update;
+ int flag = 0;
+
+ first_ackt.v64 = 0;
while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
- u32 acked_pcount;
u8 sacked = scb->sacked;
+ u32 acked_pcount;
/* Determine how many packets and what bytes were acked, tso and else */
if (after(scb->end_seq, tp->snd_una)) {
@@ -3061,11 +3066,11 @@
tp->retrans_out -= acked_pcount;
flag |= FLAG_RETRANS_DATA_ACKED;
} else {
- ca_seq_rtt = now - scb->when;
- last_ackt = skb->tstamp;
- if (seq_rtt < 0) {
- seq_rtt = ca_seq_rtt;
- }
+ last_ackt = skb->skb_mstamp;
+ WARN_ON_ONCE(last_ackt.v64 == 0);
+ if (!first_ackt.v64)
+ first_ackt = last_ackt;
+
if (!(sacked & TCPCB_SACKED_ACKED))
reord = min(pkts_acked, reord);
if (!after(scb->end_seq, tp->high_seq))
@@ -3111,7 +3116,13 @@
if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
flag |= FLAG_SACK_RENEGING;
- rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt);
+ skb_mstamp_get(&now);
+ if (first_ackt.v64) {
+ seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt);
+ ca_seq_rtt_us = skb_mstamp_us_delta(&now, &last_ackt);
+ }
+
+ rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us);
if (flag & FLAG_ACKED) {
const struct tcp_congestion_ops *ca_ops
@@ -3139,25 +3150,11 @@
tp->fackets_out -= min(pkts_acked, tp->fackets_out);
- if (ca_ops->pkts_acked) {
- s32 rtt_us = -1;
+ if (ca_ops->pkts_acked)
+ ca_ops->pkts_acked(sk, pkts_acked, ca_seq_rtt_us);
- /* Is the ACK triggering packet unambiguous? */
- if (!(flag & FLAG_RETRANS_DATA_ACKED)) {
- /* High resolution needed and available? */
- if (ca_ops->flags & TCP_CONG_RTT_STAMP &&
- !ktime_equal(last_ackt,
- net_invalid_timestamp()))
- rtt_us = ktime_us_delta(ktime_get_real(),
- last_ackt);
- else if (ca_seq_rtt >= 0)
- rtt_us = jiffies_to_usecs(ca_seq_rtt);
- }
-
- ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
- }
- } else if (skb && rtt_update && sack_rtt >= 0 &&
- sack_rtt > (s32)(now - TCP_SKB_CB(skb)->when)) {
+ } else if (skb && rtt_update && sack_rtt_us >= 0 &&
+ sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) {
/* Do not re-arm RTO if the sack RTT is measured from data sent
* after when the head was last (re)transmitted. Otherwise the
* timeout may continue to extend in loss recovery.
@@ -3367,12 +3364,12 @@
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
bool is_dupack = false;
- u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt;
+ u32 prior_in_flight;
u32 prior_fackets;
int prior_packets = tp->packets_out;
const int prior_unsacked = tp->packets_out - tp->sacked_out;
int acked = 0; /* Number of packets newly acked */
- s32 sack_rtt = -1;
+ long sack_rtt_us = -1L;
/* If the ack is older than previous acks
* then we can probably ignore it.
@@ -3430,7 +3427,7 @@
if (TCP_SKB_CB(skb)->sacked)
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
- &sack_rtt);
+ &sack_rtt_us);
if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
flag |= FLAG_ECE;
@@ -3449,7 +3446,8 @@
/* See if we can take anything off of the retransmit queue. */
acked = tp->packets_out;
- flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt);
+ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una,
+ sack_rtt_us);
acked -= tp->packets_out;
/* Advance cwnd if state allows */
@@ -3472,8 +3470,7 @@
if (icsk->icsk_pending == ICSK_TIME_RETRANS)
tcp_schedule_loss_probe(sk);
- if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd)
- tcp_update_pacing_rate(sk);
+ tcp_update_pacing_rate(sk);
return 1;
no_queue:
@@ -3502,7 +3499,7 @@
*/
if (TCP_SKB_CB(skb)->sacked) {
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
- &sack_rtt);
+ &sack_rtt_us);
tcp_fastretrans_alert(sk, acked, prior_unsacked,
is_dupack, flag);
}
@@ -5398,9 +5395,12 @@
break;
}
tcp_rearm_rto(sk);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL);
return true;
}
tp->syn_data_acked = tp->syn_data;
+ if (tp->syn_data_acked)
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
return false;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3cf97651..6379894 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -435,7 +435,7 @@
break;
icsk->icsk_backoff--;
- inet_csk(sk)->icsk_rto = (tp->srtt ? __tcp_set_rto(tp) :
+ inet_csk(sk)->icsk_rto = (tp->srtt_us ? __tcp_set_rto(tp) :
TCP_TIMEOUT_INIT) << icsk->icsk_backoff;
tcp_bound_rto(sk);
@@ -854,8 +854,10 @@
{
int res = tcp_v4_send_synack(sk, NULL, req, 0);
- if (!res)
+ if (!res) {
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+ }
return res;
}
@@ -878,8 +880,6 @@
bool want_cookie = false;
struct listen_sock *lopt;
-
-
#ifdef CONFIG_SYN_COOKIES
if (sysctl_tcp_syncookies) {
msg = "Sending cookies";
@@ -2628,7 +2628,7 @@
{
__be32 dest, src;
__u16 destp, srcp;
- long delta = tw->tw_ttd - jiffies;
+ s32 delta = tw->tw_ttd - inet_tw_time_stamp();
dest = tw->tw_daddr;
src = tw->tw_rcv_saddr;
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 991d62a..c9aecae 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -315,11 +315,9 @@
}
static struct tcp_congestion_ops tcp_lp __read_mostly = {
- .flags = TCP_CONG_RTT_STAMP,
.init = tcp_lp_init,
.ssthresh = tcp_reno_ssthresh,
.cong_avoid = tcp_lp_cong_avoid,
- .min_cwnd = tcp_reno_min_cwnd,
.pkts_acked = tcp_lp_pkts_acked,
.owner = THIS_MODULE,
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index d547075..dcaf72f 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -33,6 +33,11 @@
struct tcp_fastopen_cookie cookie;
};
+/* TCP_METRIC_MAX includes 2 extra fields for userspace compatibility
+ * Kernel only stores RTT and RTTVAR in usec resolution
+ */
+#define TCP_METRIC_MAX_KERNEL (TCP_METRIC_MAX - 2)
+
struct tcp_metrics_block {
struct tcp_metrics_block __rcu *tcpm_next;
struct inetpeer_addr tcpm_saddr;
@@ -41,7 +46,7 @@
u32 tcpm_ts;
u32 tcpm_ts_stamp;
u32 tcpm_lock;
- u32 tcpm_vals[TCP_METRIC_MAX + 1];
+ u32 tcpm_vals[TCP_METRIC_MAX_KERNEL + 1];
struct tcp_fastopen_metrics tcpm_fastopen;
struct rcu_head rcu_head;
@@ -59,12 +64,6 @@
return tm->tcpm_vals[idx];
}
-static u32 tcp_metric_get_jiffies(struct tcp_metrics_block *tm,
- enum tcp_metric_index idx)
-{
- return msecs_to_jiffies(tm->tcpm_vals[idx]);
-}
-
static void tcp_metric_set(struct tcp_metrics_block *tm,
enum tcp_metric_index idx,
u32 val)
@@ -72,13 +71,6 @@
tm->tcpm_vals[idx] = val;
}
-static void tcp_metric_set_msecs(struct tcp_metrics_block *tm,
- enum tcp_metric_index idx,
- u32 val)
-{
- tm->tcpm_vals[idx] = jiffies_to_msecs(val);
-}
-
static bool addr_same(const struct inetpeer_addr *a,
const struct inetpeer_addr *b)
{
@@ -101,9 +93,11 @@
static DEFINE_SPINLOCK(tcp_metrics_lock);
-static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst,
+static void tcpm_suck_dst(struct tcp_metrics_block *tm,
+ const struct dst_entry *dst,
bool fastopen_clear)
{
+ u32 msval;
u32 val;
tm->tcpm_stamp = jiffies;
@@ -121,8 +115,11 @@
val |= 1 << TCP_METRIC_REORDERING;
tm->tcpm_lock = val;
- tm->tcpm_vals[TCP_METRIC_RTT] = dst_metric_raw(dst, RTAX_RTT);
- tm->tcpm_vals[TCP_METRIC_RTTVAR] = dst_metric_raw(dst, RTAX_RTTVAR);
+ msval = dst_metric_raw(dst, RTAX_RTT);
+ tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC;
+
+ msval = dst_metric_raw(dst, RTAX_RTTVAR);
+ tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC;
tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH);
tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND);
tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING);
@@ -384,7 +381,7 @@
dst_confirm(dst);
rcu_read_lock();
- if (icsk->icsk_backoff || !tp->srtt) {
+ if (icsk->icsk_backoff || !tp->srtt_us) {
/* This session failed to estimate rtt. Why?
* Probably, no packets returned in time. Reset our
* results.
@@ -399,8 +396,8 @@
if (!tm)
goto out_unlock;
- rtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT);
- m = rtt - tp->srtt;
+ rtt = tcp_metric_get(tm, TCP_METRIC_RTT);
+ m = rtt - tp->srtt_us;
/* If newly calculated rtt larger than stored one, store new
* one. Otherwise, use EWMA. Remember, rtt overestimation is
@@ -408,10 +405,10 @@
*/
if (!tcp_metric_locked(tm, TCP_METRIC_RTT)) {
if (m <= 0)
- rtt = tp->srtt;
+ rtt = tp->srtt_us;
else
rtt -= (m >> 3);
- tcp_metric_set_msecs(tm, TCP_METRIC_RTT, rtt);
+ tcp_metric_set(tm, TCP_METRIC_RTT, rtt);
}
if (!tcp_metric_locked(tm, TCP_METRIC_RTTVAR)) {
@@ -422,16 +419,16 @@
/* Scale deviation to rttvar fixed point */
m >>= 1;
- if (m < tp->mdev)
- m = tp->mdev;
+ if (m < tp->mdev_us)
+ m = tp->mdev_us;
- var = tcp_metric_get_jiffies(tm, TCP_METRIC_RTTVAR);
+ var = tcp_metric_get(tm, TCP_METRIC_RTTVAR);
if (m >= var)
var = m;
else
var -= (var - m) >> 2;
- tcp_metric_set_msecs(tm, TCP_METRIC_RTTVAR, var);
+ tcp_metric_set(tm, TCP_METRIC_RTTVAR, var);
}
if (tcp_in_initial_slowstart(tp)) {
@@ -528,7 +525,7 @@
tp->reordering = val;
}
- crtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT);
+ crtt = tcp_metric_get(tm, TCP_METRIC_RTT);
rcu_read_unlock();
reset:
/* The initial RTT measurement from the SYN/SYN-ACK is not ideal
@@ -551,18 +548,20 @@
* to low value, and then abruptly stops to do it and starts to delay
* ACKs, wait for troubles.
*/
- if (crtt > tp->srtt) {
+ if (crtt > tp->srtt_us) {
/* Set RTO like tcp_rtt_estimator(), but from cached RTT. */
- crtt >>= 3;
+ crtt /= 8 * USEC_PER_MSEC;
inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk));
- } else if (tp->srtt == 0) {
+ } else if (tp->srtt_us == 0) {
/* RFC6298: 5.7 We've failed to get a valid RTT sample from
* 3WHS. This is most likely due to retransmission,
* including spurious one. Reset the RTO back to 3secs
* from the more aggressive 1sec to avoid more spurious
* retransmission.
*/
- tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK;
+ tp->rttvar_us = jiffies_to_usecs(TCP_TIMEOUT_FALLBACK);
+ tp->mdev_us = tp->mdev_max_us = tp->rttvar_us;
+
inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK;
}
/* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been
@@ -809,10 +808,26 @@
nest = nla_nest_start(msg, TCP_METRICS_ATTR_VALS);
if (!nest)
goto nla_put_failure;
- for (i = 0; i < TCP_METRIC_MAX + 1; i++) {
- if (!tm->tcpm_vals[i])
+ for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) {
+ u32 val = tm->tcpm_vals[i];
+
+ if (!val)
continue;
- if (nla_put_u32(msg, i + 1, tm->tcpm_vals[i]) < 0)
+ if (i == TCP_METRIC_RTT) {
+ if (nla_put_u32(msg, TCP_METRIC_RTT_US + 1,
+ val) < 0)
+ goto nla_put_failure;
+ n++;
+ val = max(val / 1000, 1U);
+ }
+ if (i == TCP_METRIC_RTTVAR) {
+ if (nla_put_u32(msg, TCP_METRIC_RTTVAR_US + 1,
+ val) < 0)
+ goto nla_put_failure;
+ n++;
+ val = max(val / 1000, 1U);
+ }
+ if (nla_put_u32(msg, i + 1, val) < 0)
goto nla_put_failure;
n++;
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7a436c5..ca788ad 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -398,8 +398,8 @@
tcp_init_wl(newtp, treq->rcv_isn);
- newtp->srtt = 0;
- newtp->mdev = TCP_TIMEOUT_INIT;
+ newtp->srtt_us = 0;
+ newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
newicsk->icsk_rto = TCP_TIMEOUT_INIT;
newtp->packets_out = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 03d26b8..699fb10 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -86,6 +86,9 @@
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
tcp_rearm_rto(sk);
}
+
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT,
+ tcp_skb_pcount(skb));
}
/* SND.NXT, if window was not shrunk.
@@ -269,6 +272,7 @@
static u16 tcp_select_window(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ u32 old_win = tp->rcv_wnd;
u32 cur_win = tcp_receive_window(tp);
u32 new_win = __tcp_select_window(sk);
@@ -281,6 +285,9 @@
*
* Relax Will Robinson.
*/
+ if (new_win == 0)
+ NET_INC_STATS(sock_net(sk),
+ LINUX_MIB_TCPWANTZEROWINDOWADV);
new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale);
}
tp->rcv_wnd = new_win;
@@ -298,8 +305,14 @@
new_win >>= tp->rx_opt.rcv_wscale;
/* If we advertise zero window, disable fast path. */
- if (new_win == 0)
+ if (new_win == 0) {
tp->pred_flags = 0;
+ if (old_win)
+ NET_INC_STATS(sock_net(sk),
+ LINUX_MIB_TCPTOZEROWINDOWADV);
+ } else if (old_win == 0) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV);
+ }
return new_win;
}
@@ -698,7 +711,8 @@
if ((1 << sk->sk_state) &
(TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
TCPF_CLOSE_WAIT | TCPF_LAST_ACK))
- tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC);
+ tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle,
+ 0, GFP_ATOMIC);
}
/*
* One tasklet per cpu tries to send more skbs.
@@ -766,6 +780,17 @@
if (flags & (1UL << TCP_TSQ_DEFERRED))
tcp_tsq_handler(sk);
+ /* Here begins the tricky part :
+ * We are called from release_sock() with :
+ * 1) BH disabled
+ * 2) sk_lock.slock spinlock held
+ * 3) socket owned by us (sk->sk_lock.owned == 1)
+ *
+ * But following code is meant to be called from BH handlers,
+ * so we should keep BH disabled, but early release socket ownership
+ */
+ sock_release_ownership(sk);
+
if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) {
tcp_write_timer_handler(sk);
__sock_put(sk);
@@ -855,16 +880,12 @@
if (clone_it) {
const struct sk_buff *fclone = skb + 1;
- /* If congestion control is doing timestamping, we must
- * take such a timestamp before we potentially clone/copy.
- */
- if (icsk->icsk_ca_ops->flags & TCP_CONG_RTT_STAMP)
- __net_timestamp(skb);
+ skb_mstamp_get(&skb->skb_mstamp);
if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
fclone->fclone == SKB_FCLONE_CLONE))
- NET_INC_STATS_BH(sock_net(sk),
- LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
+ NET_INC_STATS(sock_net(sk),
+ LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
if (unlikely(skb_cloned(skb)))
skb = pskb_copy(skb, gfp_mask);
@@ -872,6 +893,8 @@
skb = skb_clone(skb, gfp_mask);
if (unlikely(!skb))
return -ENOBUFS;
+ /* Our usage of tstamp should remain private */
+ skb->tstamp.tv64 = 0;
}
inet = inet_sk(sk);
@@ -1414,7 +1437,7 @@
* With Minshall's modification: all sent small packets are ACKed.
*/
static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
- unsigned int mss_now, int nonagle)
+ int nonagle)
{
return partial &&
((nonagle & TCP_NAGLE_CORK) ||
@@ -1446,7 +1469,7 @@
* to include this last segment in this skb.
* Otherwise, we'll split the skb at last MSS boundary
*/
- if (tcp_nagle_check(partial != 0, tp, mss_now, nonagle))
+ if (tcp_nagle_check(partial != 0, tp, nonagle))
return needed - partial;
return needed;
@@ -1509,7 +1532,7 @@
if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
return true;
- if (!tcp_nagle_check(skb->len < cur_mss, tp, cur_mss, nonagle))
+ if (!tcp_nagle_check(skb->len < cur_mss, tp, nonagle))
return true;
return false;
@@ -1904,7 +1927,15 @@
if (atomic_read(&sk->sk_wmem_alloc) > limit) {
set_bit(TSQ_THROTTLED, &tp->tsq_flags);
- break;
+ /* It is possible TX completion already happened
+ * before we set TSQ_THROTTLED, so we must
+ * test again the condition.
+ * We abuse smp_mb__after_clear_bit() because
+ * there is no smp_mb__after_set_bit() yet
+ */
+ smp_mb__after_clear_bit();
+ if (atomic_read(&sk->sk_wmem_alloc) > limit)
+ break;
}
limit = mss_now;
@@ -1955,7 +1986,7 @@
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
u32 timeout, tlp_time_stamp, rto_time_stamp;
- u32 rtt = tp->srtt >> 3;
+ u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3);
if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS))
return false;
@@ -1977,7 +2008,7 @@
/* Schedule a loss probe in 2*RTT for SACK capable connections
* in Open state, that are either limited by cwnd or application.
*/
- if (sysctl_tcp_early_retrans < 3 || !rtt || !tp->packets_out ||
+ if (sysctl_tcp_early_retrans < 3 || !tp->srtt_us || !tp->packets_out ||
!tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
return false;
@@ -2062,7 +2093,6 @@
if (likely(!err))
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPLOSSPROBES);
- return;
}
/* Push out any pending frames which were held back due to
@@ -2160,7 +2190,8 @@
*/
int mss = icsk->icsk_ack.rcv_mss;
int free_space = tcp_space(sk);
- int full_space = min_t(int, tp->window_clamp, tcp_full_space(sk));
+ int allowed_space = tcp_full_space(sk);
+ int full_space = min_t(int, tp->window_clamp, allowed_space);
int window;
if (mss > full_space)
@@ -2173,7 +2204,19 @@
tp->rcv_ssthresh = min(tp->rcv_ssthresh,
4U * tp->advmss);
- if (free_space < mss)
+ /* free_space might become our new window, make sure we don't
+ * increase it due to wscale.
+ */
+ free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale);
+
+ /* if free space is less than mss estimate, or is below 1/16th
+ * of the maximum allowed, try to move to zero-window, else
+ * tcp_clamp_window() will grow rcv buf up to tcp_rmem[2], and
+ * new incoming data is dropped due to memory limits.
+ * With large window, mss test triggers way too late in order
+ * to announce zero window in time before rmem limit kicks in.
+ */
+ if (free_space < (allowed_space >> 4) || free_space < mss)
return 0;
}
@@ -2328,6 +2371,7 @@
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
unsigned int cur_mss;
+ int err;
/* Inconslusive MTU probe */
if (icsk->icsk_mtup.probe_size) {
@@ -2391,11 +2435,15 @@
skb_headroom(skb) >= 0xFFFF)) {
struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
GFP_ATOMIC);
- return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
- -ENOBUFS;
+ err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+ -ENOBUFS;
} else {
- return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+ err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}
+
+ if (likely(!err))
+ TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
+ return err;
}
int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
@@ -2406,7 +2454,8 @@
if (err == 0) {
/* Update global TCP statistics. */
TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
-
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
tp->total_retrans++;
#if FASTRETRANS_DEBUG > 0
@@ -2692,7 +2741,7 @@
int tcp_header_size;
int mss;
- skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
+ skb = sock_wmalloc(sk, MAX_TCP_HEADER, 1, GFP_ATOMIC);
if (unlikely(!skb)) {
dst_release(dst);
return NULL;
@@ -2762,7 +2811,7 @@
th->window = htons(min(req->rcv_wnd, 65535U));
tcp_options_write((__be32 *)(th + 1), tp, &opts);
th->doff = (tcp_header_size >> 2);
- TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb));
+ TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS);
#ifdef CONFIG_TCP_MD5SIG
/* Okay, we have all we need - do the md5 hash if needed */
@@ -2899,7 +2948,12 @@
space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
MAX_TCP_OPTION_SPACE;
- syn_data = skb_copy_expand(syn, skb_headroom(syn), space,
+ space = min_t(size_t, space, fo->size);
+
+ /* limit to order-0 allocations */
+ space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
+
+ syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space,
sk->sk_allocation);
if (syn_data == NULL)
goto fallback;
@@ -2929,9 +2983,15 @@
tcp_connect_queue_skb(sk, data);
fo->copied = data->len;
+ /* syn_data is about to be sent, we need to take current time stamps
+ * for the packets that are in write queue : SYN packet and DATA
+ */
+ skb_mstamp_get(&syn->skb_mstamp);
+ data->skb_mstamp = syn->skb_mstamp;
+
if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) {
tp->syn_data = (fo->copied > 0);
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT);
goto done;
}
syn_data = NULL;
@@ -3019,8 +3079,9 @@
* Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements
* directly.
*/
- if (tp->srtt) {
- int rtt = max(tp->srtt >> 3, TCP_DELACK_MIN);
+ if (tp->srtt_us) {
+ int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3),
+ TCP_DELACK_MIN);
if (rtt < max_ato)
max_ato = rtt;
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 1f2d376..3b66610 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -154,7 +154,7 @@
p->snd_wnd = tp->snd_wnd;
p->rcv_wnd = tp->rcv_wnd;
p->ssthresh = tcp_current_ssthresh(sk);
- p->srtt = tp->srtt >> 3;
+ p->srtt = tp->srtt_us >> 3;
tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1);
}
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 19ea6c2..0ac5083 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -39,7 +39,6 @@
static struct tcp_congestion_ops tcp_scalable __read_mostly = {
.ssthresh = tcp_scalable_ssthresh,
.cong_avoid = tcp_scalable_cong_avoid,
- .min_cwnd = tcp_reno_min_cwnd,
.owner = THIS_MODULE,
.name = "scalable",
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 64f0354..286227a 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -165,6 +165,9 @@
dst_negative_advice(sk);
if (tp->syn_fastopen || tp->syn_data)
tcp_fastopen_cache_set(sk, 0, NULL, true);
+ if (tp->syn_data)
+ NET_INC_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPFASTOPENACTIVEFAIL);
}
retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
syn_set = true;
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 06cae62..48539ff 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -306,11 +306,9 @@
EXPORT_SYMBOL_GPL(tcp_vegas_get_info);
static struct tcp_congestion_ops tcp_vegas __read_mostly = {
- .flags = TCP_CONG_RTT_STAMP,
.init = tcp_vegas_init,
.ssthresh = tcp_reno_ssthresh,
.cong_avoid = tcp_vegas_cong_avoid,
- .min_cwnd = tcp_reno_min_cwnd,
.pkts_acked = tcp_vegas_pkts_acked,
.set_state = tcp_vegas_state,
.cwnd_event = tcp_vegas_cwnd_event,
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 326475a..1b8e28f 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -203,7 +203,6 @@
}
static struct tcp_congestion_ops tcp_veno __read_mostly = {
- .flags = TCP_CONG_RTT_STAMP,
.init = tcp_veno_init,
.ssthresh = tcp_veno_ssthresh,
.cong_avoid = tcp_veno_cong_avoid,
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index 76a1e23..b94a04a 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -276,7 +276,6 @@
.init = tcp_westwood_init,
.ssthresh = tcp_reno_ssthresh,
.cong_avoid = tcp_reno_cong_avoid,
- .min_cwnd = tcp_westwood_bw_rttmin,
.cwnd_event = tcp_westwood_event,
.get_info = tcp_westwood_info,
.pkts_acked = tcp_westwood_pkts_acked,
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 1a8d271..5ede0e7 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -227,11 +227,9 @@
}
static struct tcp_congestion_ops tcp_yeah __read_mostly = {
- .flags = TCP_CONG_RTT_STAMP,
.init = tcp_yeah_init,
.ssthresh = tcp_yeah_ssthresh,
.cong_avoid = tcp_yeah_cong_avoid,
- .min_cwnd = tcp_reno_min_cwnd,
.set_state = tcp_vegas_state,
.cwnd_event = tcp_vegas_cwnd_event,
.get_info = tcp_vegas_get_info,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 77bd16f..4468e1a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -931,7 +931,8 @@
sock_tx_timestamp(sk, &ipc.tx_flags);
if (msg->msg_controllen) {
- err = ip_cmsg_send(sock_net(sk), msg, &ipc);
+ err = ip_cmsg_send(sock_net(sk), msg, &ipc,
+ sk->sk_family == AF_INET6);
if (err)
return err;
if (ipc.opt)
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 25f5cee..88b4023 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -17,6 +17,8 @@
static DEFINE_SPINLOCK(udp_offload_lock);
static struct udp_offload_priv __rcu *udp_offload_base __read_mostly;
+#define udp_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&udp_offload_lock))
+
struct udp_offload_priv {
struct udp_offload *offload;
struct rcu_head rcu;
@@ -100,8 +102,7 @@
int udp_add_offload(struct udp_offload *uo)
{
- struct udp_offload_priv __rcu **head = &udp_offload_base;
- struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_KERNEL);
+ struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_ATOMIC);
if (!new_offload)
return -ENOMEM;
@@ -109,8 +110,8 @@
new_offload->offload = uo;
spin_lock(&udp_offload_lock);
- rcu_assign_pointer(new_offload->next, rcu_dereference(*head));
- rcu_assign_pointer(*head, new_offload);
+ new_offload->next = udp_offload_base;
+ rcu_assign_pointer(udp_offload_base, new_offload);
spin_unlock(&udp_offload_lock);
return 0;
@@ -130,12 +131,12 @@
spin_lock(&udp_offload_lock);
- uo_priv = rcu_dereference(*head);
+ uo_priv = udp_deref_protected(*head);
for (; uo_priv != NULL;
- uo_priv = rcu_dereference(*head)) {
-
+ uo_priv = udp_deref_protected(*head)) {
if (uo_priv->offload == uo) {
- rcu_assign_pointer(*head, rcu_dereference(uo_priv->next));
+ rcu_assign_pointer(*head,
+ udp_deref_protected(uo_priv->next));
goto unlock;
}
head = &uo_priv->next;
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 1f12c8b..aac6197 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -37,15 +37,6 @@
return NET_RX_DROP;
}
-int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
- int encap_type)
-{
- XFRM_SPI_SKB_CB(skb)->family = AF_INET;
- XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
- return xfrm_input(skb, nexthdr, spi, encap_type);
-}
-EXPORT_SYMBOL(xfrm4_rcv_encap);
-
int xfrm4_transport_finish(struct sk_buff *skb, int async)
{
struct iphdr *iph = ip_hdr(skb);
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 31b1815..05f2b48 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -15,65 +15,6 @@
#include <net/ip.h>
#include <net/xfrm.h>
-/* Informational hook. The decap is still done here. */
-static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly;
-static DEFINE_MUTEX(xfrm4_mode_tunnel_input_mutex);
-
-int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler)
-{
- struct xfrm_tunnel_notifier __rcu **pprev;
- struct xfrm_tunnel_notifier *t;
- int ret = -EEXIST;
- int priority = handler->priority;
-
- mutex_lock(&xfrm4_mode_tunnel_input_mutex);
-
- for (pprev = &rcv_notify_handlers;
- (t = rcu_dereference_protected(*pprev,
- lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL;
- pprev = &t->next) {
- if (t->priority > priority)
- break;
- if (t->priority == priority)
- goto err;
-
- }
-
- handler->next = *pprev;
- rcu_assign_pointer(*pprev, handler);
-
- ret = 0;
-
-err:
- mutex_unlock(&xfrm4_mode_tunnel_input_mutex);
- return ret;
-}
-EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_register);
-
-int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler)
-{
- struct xfrm_tunnel_notifier __rcu **pprev;
- struct xfrm_tunnel_notifier *t;
- int ret = -ENOENT;
-
- mutex_lock(&xfrm4_mode_tunnel_input_mutex);
- for (pprev = &rcv_notify_handlers;
- (t = rcu_dereference_protected(*pprev,
- lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL;
- pprev = &t->next) {
- if (t == handler) {
- *pprev = handler->next;
- ret = 0;
- break;
- }
- }
- mutex_unlock(&xfrm4_mode_tunnel_input_mutex);
- synchronize_net();
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_deregister);
-
static inline void ipip_ecn_decapsulate(struct sk_buff *skb)
{
struct iphdr *inner_iph = ipip_hdr(skb);
@@ -127,14 +68,8 @@
return 0;
}
-#define for_each_input_rcu(head, handler) \
- for (handler = rcu_dereference(head); \
- handler != NULL; \
- handler = rcu_dereference(handler->next))
-
static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
{
- struct xfrm_tunnel_notifier *handler;
int err = -EINVAL;
if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
@@ -143,9 +78,6 @@
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto out;
- for_each_input_rcu(rcv_notify_handlers, handler)
- handler->handler(skb);
-
err = skb_unclone(skb, GFP_ATOMIC);
if (err)
goto out;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index e1a6393..6156f68 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -325,6 +325,7 @@
xfrm4_state_init();
xfrm4_policy_init();
+ xfrm4_protocol_init();
#ifdef CONFIG_SYSCTL
register_pernet_subsys(&xfrm4_net_ops);
#endif
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
new file mode 100644
index 0000000..7f7b243
--- /dev/null
+++ b/net/ipv4/xfrm4_protocol.c
@@ -0,0 +1,286 @@
+/* xfrm4_protocol.c - Generic xfrm protocol multiplexer.
+ *
+ * Copyright (C) 2013 secunet Security Networks AG
+ *
+ * Author:
+ * Steffen Klassert <steffen.klassert@secunet.com>
+ *
+ * Based on:
+ * net/ipv4/tunnel4.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/skbuff.h>
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/protocol.h>
+#include <net/xfrm.h>
+
+static struct xfrm4_protocol __rcu *esp4_handlers __read_mostly;
+static struct xfrm4_protocol __rcu *ah4_handlers __read_mostly;
+static struct xfrm4_protocol __rcu *ipcomp4_handlers __read_mostly;
+static DEFINE_MUTEX(xfrm4_protocol_mutex);
+
+static inline struct xfrm4_protocol __rcu **proto_handlers(u8 protocol)
+{
+ switch (protocol) {
+ case IPPROTO_ESP:
+ return &esp4_handlers;
+ case IPPROTO_AH:
+ return &ah4_handlers;
+ case IPPROTO_COMP:
+ return &ipcomp4_handlers;
+ }
+
+ return NULL;
+}
+
+#define for_each_protocol_rcu(head, handler) \
+ for (handler = rcu_dereference(head); \
+ handler != NULL; \
+ handler = rcu_dereference(handler->next)) \
+
+int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
+{
+ int ret;
+ struct xfrm4_protocol *handler;
+
+ for_each_protocol_rcu(*proto_handlers(protocol), handler)
+ if ((ret = handler->cb_handler(skb, err)) <= 0)
+ return ret;
+
+ return 0;
+}
+EXPORT_SYMBOL(xfrm4_rcv_cb);
+
+int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type)
+{
+ int ret;
+ struct xfrm4_protocol *handler;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+ XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+ XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+ for_each_protocol_rcu(*proto_handlers(nexthdr), handler)
+ if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL)
+ return ret;
+
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+ kfree_skb(skb);
+ return 0;
+}
+EXPORT_SYMBOL(xfrm4_rcv_encap);
+
+static int xfrm4_esp_rcv(struct sk_buff *skb)
+{
+ int ret;
+ struct xfrm4_protocol *handler;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+
+ for_each_protocol_rcu(esp4_handlers, handler)
+ if ((ret = handler->handler(skb)) != -EINVAL)
+ return ret;
+
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+ kfree_skb(skb);
+ return 0;
+}
+
+static void xfrm4_esp_err(struct sk_buff *skb, u32 info)
+{
+ struct xfrm4_protocol *handler;
+
+ for_each_protocol_rcu(esp4_handlers, handler)
+ if (!handler->err_handler(skb, info))
+ break;
+}
+
+static int xfrm4_ah_rcv(struct sk_buff *skb)
+{
+ int ret;
+ struct xfrm4_protocol *handler;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+
+ for_each_protocol_rcu(ah4_handlers, handler)
+ if ((ret = handler->handler(skb)) != -EINVAL)
+ return ret;;
+
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+ kfree_skb(skb);
+ return 0;
+}
+
+static void xfrm4_ah_err(struct sk_buff *skb, u32 info)
+{
+ struct xfrm4_protocol *handler;
+
+ for_each_protocol_rcu(ah4_handlers, handler)
+ if (!handler->err_handler(skb, info))
+ break;
+}
+
+static int xfrm4_ipcomp_rcv(struct sk_buff *skb)
+{
+ int ret;
+ struct xfrm4_protocol *handler;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+
+ for_each_protocol_rcu(ipcomp4_handlers, handler)
+ if ((ret = handler->handler(skb)) != -EINVAL)
+ return ret;
+
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+ kfree_skb(skb);
+ return 0;
+}
+
+static void xfrm4_ipcomp_err(struct sk_buff *skb, u32 info)
+{
+ struct xfrm4_protocol *handler;
+
+ for_each_protocol_rcu(ipcomp4_handlers, handler)
+ if (!handler->err_handler(skb, info))
+ break;
+}
+
+static const struct net_protocol esp4_protocol = {
+ .handler = xfrm4_esp_rcv,
+ .err_handler = xfrm4_esp_err,
+ .no_policy = 1,
+ .netns_ok = 1,
+};
+
+static const struct net_protocol ah4_protocol = {
+ .handler = xfrm4_ah_rcv,
+ .err_handler = xfrm4_ah_err,
+ .no_policy = 1,
+ .netns_ok = 1,
+};
+
+static const struct net_protocol ipcomp4_protocol = {
+ .handler = xfrm4_ipcomp_rcv,
+ .err_handler = xfrm4_ipcomp_err,
+ .no_policy = 1,
+ .netns_ok = 1,
+};
+
+static struct xfrm_input_afinfo xfrm4_input_afinfo = {
+ .family = AF_INET,
+ .owner = THIS_MODULE,
+ .callback = xfrm4_rcv_cb,
+};
+
+static inline const struct net_protocol *netproto(unsigned char protocol)
+{
+ switch (protocol) {
+ case IPPROTO_ESP:
+ return &esp4_protocol;
+ case IPPROTO_AH:
+ return &ah4_protocol;
+ case IPPROTO_COMP:
+ return &ipcomp4_protocol;
+ }
+
+ return NULL;
+}
+
+int xfrm4_protocol_register(struct xfrm4_protocol *handler,
+ unsigned char protocol)
+{
+ struct xfrm4_protocol __rcu **pprev;
+ struct xfrm4_protocol *t;
+ bool add_netproto = false;
+ int ret = -EEXIST;
+ int priority = handler->priority;
+
+ mutex_lock(&xfrm4_protocol_mutex);
+
+ if (!rcu_dereference_protected(*proto_handlers(protocol),
+ lockdep_is_held(&xfrm4_protocol_mutex)))
+ add_netproto = true;
+
+ for (pprev = proto_handlers(protocol);
+ (t = rcu_dereference_protected(*pprev,
+ lockdep_is_held(&xfrm4_protocol_mutex))) != NULL;
+ pprev = &t->next) {
+ if (t->priority < priority)
+ break;
+ if (t->priority == priority)
+ goto err;
+ }
+
+ handler->next = *pprev;
+ rcu_assign_pointer(*pprev, handler);
+
+ ret = 0;
+
+err:
+ mutex_unlock(&xfrm4_protocol_mutex);
+
+ if (add_netproto) {
+ if (inet_add_protocol(netproto(protocol), protocol)) {
+ pr_err("%s: can't add protocol\n", __func__);
+ ret = -EAGAIN;
+ }
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(xfrm4_protocol_register);
+
+int xfrm4_protocol_deregister(struct xfrm4_protocol *handler,
+ unsigned char protocol)
+{
+ struct xfrm4_protocol __rcu **pprev;
+ struct xfrm4_protocol *t;
+ int ret = -ENOENT;
+
+ mutex_lock(&xfrm4_protocol_mutex);
+
+ for (pprev = proto_handlers(protocol);
+ (t = rcu_dereference_protected(*pprev,
+ lockdep_is_held(&xfrm4_protocol_mutex))) != NULL;
+ pprev = &t->next) {
+ if (t == handler) {
+ *pprev = handler->next;
+ ret = 0;
+ break;
+ }
+ }
+
+ if (!rcu_dereference_protected(*proto_handlers(protocol),
+ lockdep_is_held(&xfrm4_protocol_mutex))) {
+ if (inet_del_protocol(netproto(protocol), protocol) < 0) {
+ pr_err("%s: can't remove protocol\n", __func__);
+ ret = -EAGAIN;
+ }
+ }
+
+ mutex_unlock(&xfrm4_protocol_mutex);
+
+ synchronize_net();
+
+ return ret;
+}
+EXPORT_SYMBOL(xfrm4_protocol_deregister);
+
+void __init xfrm4_protocol_init(void)
+{
+ xfrm_input_register_afinfo(&xfrm4_input_afinfo);
+}
+EXPORT_SYMBOL(xfrm4_protocol_init);
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index d92e558..438a73a 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -138,6 +138,7 @@
config IPV6_VTI
tristate "Virtual (secure) IPv6: tunneling"
select IPV6_TUNNEL
+ select NET_IP_TUNNEL
depends on INET6_XFRM_MODE_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 17bb830..2fe6836 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -16,7 +16,7 @@
ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o
ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \
- xfrm6_output.o
+ xfrm6_output.o xfrm6_protocol.o
ipv6-$(CONFIG_NETFILTER) += netfilter.o
ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o
ipv6-$(CONFIG_PROC_FS) += proc.o
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ad23569..6c7fa08 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -133,10 +133,12 @@
static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE];
static DEFINE_SPINLOCK(addrconf_hash_lock);
-static void addrconf_verify(unsigned long);
+static void addrconf_verify(void);
+static void addrconf_verify_rtnl(void);
+static void addrconf_verify_work(struct work_struct *);
-static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0);
-static DEFINE_SPINLOCK(addrconf_verify_lock);
+static struct workqueue_struct *addrconf_wq;
+static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work);
static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
@@ -151,7 +153,7 @@
u32 flags, u32 noflags);
static void addrconf_dad_start(struct inet6_ifaddr *ifp);
-static void addrconf_dad_timer(unsigned long data);
+static void addrconf_dad_work(struct work_struct *w);
static void addrconf_dad_completed(struct inet6_ifaddr *ifp);
static void addrconf_dad_run(struct inet6_dev *idev);
static void addrconf_rs_timer(unsigned long data);
@@ -247,9 +249,9 @@
__in6_dev_put(idev);
}
-static void addrconf_del_dad_timer(struct inet6_ifaddr *ifp)
+static void addrconf_del_dad_work(struct inet6_ifaddr *ifp)
{
- if (del_timer(&ifp->dad_timer))
+ if (cancel_delayed_work(&ifp->dad_work))
__in6_ifa_put(ifp);
}
@@ -261,12 +263,12 @@
mod_timer(&idev->rs_timer, jiffies + when);
}
-static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp,
- unsigned long when)
+static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
+ unsigned long delay)
{
- if (!timer_pending(&ifp->dad_timer))
+ if (!delayed_work_pending(&ifp->dad_work))
in6_ifa_hold(ifp);
- mod_timer(&ifp->dad_timer, jiffies + when);
+ mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);
}
static int snmp6_alloc_dev(struct inet6_dev *idev)
@@ -751,8 +753,9 @@
in6_dev_put(ifp->idev);
- if (del_timer(&ifp->dad_timer))
- pr_notice("Timer is still running, when freeing ifa=%p\n", ifp);
+ if (cancel_delayed_work(&ifp->dad_work))
+ pr_notice("delayed DAD work was pending while freeing ifa=%p\n",
+ ifp);
if (ifp->state != INET6_IFADDR_STATE_DEAD) {
pr_warn("Freeing alive inet6 address %p\n", ifp);
@@ -849,8 +852,7 @@
spin_lock_init(&ifa->lock);
spin_lock_init(&ifa->state_lock);
- setup_timer(&ifa->dad_timer, addrconf_dad_timer,
- (unsigned long)ifa);
+ INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work);
INIT_HLIST_NODE(&ifa->addr_lst);
ifa->scope = scope;
ifa->prefix_len = pfxlen;
@@ -990,6 +992,8 @@
enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP;
unsigned long expires;
+ ASSERT_RTNL();
+
spin_lock_bh(&ifp->state_lock);
state = ifp->state;
ifp->state = INET6_IFADDR_STATE_DEAD;
@@ -1021,7 +1025,7 @@
write_unlock_bh(&ifp->idev->lock);
- addrconf_del_dad_timer(ifp);
+ addrconf_del_dad_work(ifp);
ipv6_ifa_notify(RTM_DELADDR, ifp);
@@ -1103,8 +1107,11 @@
* Lifetime is greater than REGEN_ADVANCE time units. In particular,
* an implementation must not create a temporary address with a zero
* Preferred Lifetime.
+ * Use age calculation as in addrconf_verify to avoid unnecessary
+ * temporary addresses being generated.
*/
- if (tmp_prefered_lft <= regen_advance) {
+ age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+ if (tmp_prefered_lft <= regen_advance + age) {
in6_ifa_put(ifp);
in6_dev_put(idev);
ret = -1;
@@ -1601,7 +1608,7 @@
{
if (ifp->flags&IFA_F_PERMANENT) {
spin_lock_bh(&ifp->lock);
- addrconf_del_dad_timer(ifp);
+ addrconf_del_dad_work(ifp);
ifp->flags |= IFA_F_TENTATIVE;
if (dad_failed)
ifp->flags |= IFA_F_DADFAILED;
@@ -1622,20 +1629,21 @@
spin_unlock_bh(&ifp->lock);
}
ipv6_del_addr(ifp);
- } else
+ } else {
ipv6_del_addr(ifp);
+ }
}
static int addrconf_dad_end(struct inet6_ifaddr *ifp)
{
int err = -ENOENT;
- spin_lock(&ifp->state_lock);
+ spin_lock_bh(&ifp->state_lock);
if (ifp->state == INET6_IFADDR_STATE_DAD) {
ifp->state = INET6_IFADDR_STATE_POSTDAD;
err = 0;
}
- spin_unlock(&ifp->state_lock);
+ spin_unlock_bh(&ifp->state_lock);
return err;
}
@@ -1668,7 +1676,12 @@
}
}
- addrconf_dad_stop(ifp, 1);
+ spin_lock_bh(&ifp->state_lock);
+ /* transition from _POSTDAD to _ERRDAD */
+ ifp->state = INET6_IFADDR_STATE_ERRDAD;
+ spin_unlock_bh(&ifp->state_lock);
+
+ addrconf_mod_dad_work(ifp, 0);
}
/* Join to solicited addr multicast group. */
@@ -1677,6 +1690,8 @@
{
struct in6_addr maddr;
+ ASSERT_RTNL();
+
if (dev->flags&(IFF_LOOPBACK|IFF_NOARP))
return;
@@ -1688,6 +1703,8 @@
{
struct in6_addr maddr;
+ ASSERT_RTNL();
+
if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP))
return;
@@ -1698,6 +1715,9 @@
static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
{
struct in6_addr addr;
+
+ ASSERT_RTNL();
+
if (ifp->prefix_len >= 127) /* RFC 6164 */
return;
ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -1709,6 +1729,9 @@
static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
{
struct in6_addr addr;
+
+ ASSERT_RTNL();
+
if (ifp->prefix_len >= 127) /* RFC 6164 */
return;
ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -2268,11 +2291,13 @@
return;
}
- ifp->flags |= IFA_F_MANAGETEMPADDR;
update_lft = 0;
create = 1;
+ spin_lock_bh(&ifp->lock);
+ ifp->flags |= IFA_F_MANAGETEMPADDR;
ifp->cstamp = jiffies;
ifp->tokenized = tokenized;
+ spin_unlock_bh(&ifp->lock);
addrconf_dad_start(ifp);
}
@@ -2323,7 +2348,7 @@
create, now);
in6_ifa_put(ifp);
- addrconf_verify(0);
+ addrconf_verify();
}
}
inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo);
@@ -2472,7 +2497,7 @@
manage_tempaddrs(idev, ifp, valid_lft, prefered_lft,
true, jiffies);
in6_ifa_put(ifp);
- addrconf_verify(0);
+ addrconf_verify_rtnl();
return 0;
}
@@ -2783,6 +2808,8 @@
ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0);
if (!ipv6_generate_eui64(addr.s6_addr + 8, dev))
addrconf_add_linklocal(idev, &addr);
+ else
+ addrconf_prefix_route(&addr, 64, dev, 0, 0);
}
#endif
@@ -3006,7 +3033,7 @@
hlist_for_each_entry_rcu(ifa, h, addr_lst) {
if (ifa->idev == idev) {
hlist_del_init_rcu(&ifa->addr_lst);
- addrconf_del_dad_timer(ifa);
+ addrconf_del_dad_work(ifa);
goto restart;
}
}
@@ -3044,7 +3071,7 @@
while (!list_empty(&idev->addr_list)) {
ifa = list_first_entry(&idev->addr_list,
struct inet6_ifaddr, if_list);
- addrconf_del_dad_timer(ifa);
+ addrconf_del_dad_work(ifa);
list_del(&ifa->if_list);
@@ -3143,10 +3170,10 @@
rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1);
ifp->dad_probes = idev->cnf.dad_transmits;
- addrconf_mod_dad_timer(ifp, rand_num);
+ addrconf_mod_dad_work(ifp, rand_num);
}
-static void addrconf_dad_start(struct inet6_ifaddr *ifp)
+static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
{
struct inet6_dev *idev = ifp->idev;
struct net_device *dev = idev->dev;
@@ -3198,25 +3225,68 @@
read_unlock_bh(&idev->lock);
}
-static void addrconf_dad_timer(unsigned long data)
+static void addrconf_dad_start(struct inet6_ifaddr *ifp)
{
- struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data;
+ bool begin_dad = false;
+
+ spin_lock_bh(&ifp->state_lock);
+ if (ifp->state != INET6_IFADDR_STATE_DEAD) {
+ ifp->state = INET6_IFADDR_STATE_PREDAD;
+ begin_dad = true;
+ }
+ spin_unlock_bh(&ifp->state_lock);
+
+ if (begin_dad)
+ addrconf_mod_dad_work(ifp, 0);
+}
+
+static void addrconf_dad_work(struct work_struct *w)
+{
+ struct inet6_ifaddr *ifp = container_of(to_delayed_work(w),
+ struct inet6_ifaddr,
+ dad_work);
struct inet6_dev *idev = ifp->idev;
struct in6_addr mcaddr;
+ enum {
+ DAD_PROCESS,
+ DAD_BEGIN,
+ DAD_ABORT,
+ } action = DAD_PROCESS;
+
+ rtnl_lock();
+
+ spin_lock_bh(&ifp->state_lock);
+ if (ifp->state == INET6_IFADDR_STATE_PREDAD) {
+ action = DAD_BEGIN;
+ ifp->state = INET6_IFADDR_STATE_DAD;
+ } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) {
+ action = DAD_ABORT;
+ ifp->state = INET6_IFADDR_STATE_POSTDAD;
+ }
+ spin_unlock_bh(&ifp->state_lock);
+
+ if (action == DAD_BEGIN) {
+ addrconf_dad_begin(ifp);
+ goto out;
+ } else if (action == DAD_ABORT) {
+ addrconf_dad_stop(ifp, 1);
+ goto out;
+ }
+
if (!ifp->dad_probes && addrconf_dad_end(ifp))
goto out;
- write_lock(&idev->lock);
+ write_lock_bh(&idev->lock);
if (idev->dead || !(idev->if_flags & IF_READY)) {
- write_unlock(&idev->lock);
+ write_unlock_bh(&idev->lock);
goto out;
}
spin_lock(&ifp->lock);
if (ifp->state == INET6_IFADDR_STATE_DEAD) {
spin_unlock(&ifp->lock);
- write_unlock(&idev->lock);
+ write_unlock_bh(&idev->lock);
goto out;
}
@@ -3227,7 +3297,7 @@
ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
spin_unlock(&ifp->lock);
- write_unlock(&idev->lock);
+ write_unlock_bh(&idev->lock);
addrconf_dad_completed(ifp);
@@ -3235,16 +3305,17 @@
}
ifp->dad_probes--;
- addrconf_mod_dad_timer(ifp,
- NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
+ addrconf_mod_dad_work(ifp,
+ NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
spin_unlock(&ifp->lock);
- write_unlock(&idev->lock);
+ write_unlock_bh(&idev->lock);
/* send a neighbour solicitation for our addr */
addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any);
out:
in6_ifa_put(ifp);
+ rtnl_unlock();
}
/* ifp->idev must be at least read locked */
@@ -3271,7 +3342,7 @@
struct in6_addr lladdr;
bool send_rs, send_mld;
- addrconf_del_dad_timer(ifp);
+ addrconf_del_dad_work(ifp);
/*
* Configure the address for reception. Now it is valid.
@@ -3512,23 +3583,23 @@
* Periodic address status verification
*/
-static void addrconf_verify(unsigned long foo)
+static void addrconf_verify_rtnl(void)
{
unsigned long now, next, next_sec, next_sched;
struct inet6_ifaddr *ifp;
int i;
+ ASSERT_RTNL();
+
rcu_read_lock_bh();
- spin_lock(&addrconf_verify_lock);
now = jiffies;
next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
- del_timer(&addr_chk_timer);
+ cancel_delayed_work(&addr_chk_work);
for (i = 0; i < IN6_ADDR_HSIZE; i++) {
restart:
- hlist_for_each_entry_rcu_bh(ifp,
- &inet6_addr_lst[i], addr_lst) {
+ hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) {
unsigned long age;
/* When setting preferred_lft to a value not zero or
@@ -3623,13 +3694,22 @@
ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n",
now, next, next_sec, next_sched);
-
- addr_chk_timer.expires = next_sched;
- add_timer(&addr_chk_timer);
- spin_unlock(&addrconf_verify_lock);
+ mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now);
rcu_read_unlock_bh();
}
+static void addrconf_verify_work(struct work_struct *w)
+{
+ rtnl_lock();
+ addrconf_verify_rtnl();
+ rtnl_unlock();
+}
+
+static void addrconf_verify(void)
+{
+ mod_delayed_work(addrconf_wq, &addr_chk_work, 0);
+}
+
static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local,
struct in6_addr **peer_pfx)
{
@@ -3686,6 +3766,8 @@
bool was_managetempaddr;
bool had_prefixroute;
+ ASSERT_RTNL();
+
if (!valid_lft || (prefered_lft > valid_lft))
return -EINVAL;
@@ -3751,7 +3833,7 @@
!was_managetempaddr, jiffies);
}
- addrconf_verify(0);
+ addrconf_verify_rtnl();
return 0;
}
@@ -4381,6 +4463,8 @@
bool update_rs = false;
struct in6_addr ll_addr;
+ ASSERT_RTNL();
+
if (token == NULL)
return -EINVAL;
if (ipv6_addr_any(token))
@@ -4429,7 +4513,7 @@
}
write_unlock_bh(&idev->lock);
- addrconf_verify(0);
+ addrconf_verify_rtnl();
return 0;
}
@@ -4631,6 +4715,9 @@
{
struct net *net = dev_net(ifp->idev->dev);
+ if (event)
+ ASSERT_RTNL();
+
inet6_ifa_notify(event ? : RTM_NEWADDR, ifp);
switch (event) {
@@ -5239,6 +5326,12 @@
if (err < 0)
goto out_addrlabel;
+ addrconf_wq = create_workqueue("ipv6_addrconf");
+ if (!addrconf_wq) {
+ err = -ENOMEM;
+ goto out_nowq;
+ }
+
/* The addrconf netdev notifier requires that loopback_dev
* has it's ipv6 private information allocated and setup
* before it can bring up and give link-local addresses
@@ -5269,7 +5362,7 @@
register_netdevice_notifier(&ipv6_dev_notf);
- addrconf_verify(0);
+ addrconf_verify();
rtnl_af_register(&inet6_ops);
@@ -5297,6 +5390,8 @@
rtnl_af_unregister(&inet6_ops);
unregister_netdevice_notifier(&ipv6_dev_notf);
errlo:
+ destroy_workqueue(addrconf_wq);
+out_nowq:
unregister_pernet_subsys(&addrconf_ops);
out_addrlabel:
ipv6_addr_label_cleanup();
@@ -5332,7 +5427,8 @@
for (i = 0; i < IN6_ADDR_HSIZE; i++)
WARN_ON(!hlist_empty(&inet6_addr_lst[i]));
spin_unlock_bh(&addrconf_hash_lock);
-
- del_timer(&addr_chk_timer);
+ cancel_delayed_work(&addr_chk_work);
rtnl_unlock();
+
+ destroy_workqueue(addrconf_wq);
}
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index b30ad37..731e1e1 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -6,7 +6,7 @@
*/
/*
* Author:
- * YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org>
+ * YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org>
*/
#include <linux/kernel.h>
@@ -22,14 +22,13 @@
#if 0
#define ADDRLABEL(x...) printk(x)
#else
-#define ADDRLABEL(x...) do { ; } while(0)
+#define ADDRLABEL(x...) do { ; } while (0)
#endif
/*
* Policy Table
*/
-struct ip6addrlbl_entry
-{
+struct ip6addrlbl_entry {
#ifdef CONFIG_NET_NS
struct net *lbl_net;
#endif
@@ -88,39 +87,39 @@
{ /* ::/0 */
.prefix = &in6addr_any,
.label = 1,
- },{ /* fc00::/7 */
- .prefix = &(struct in6_addr){{{ 0xfc }}},
+ }, { /* fc00::/7 */
+ .prefix = &(struct in6_addr){ { { 0xfc } } } ,
.prefixlen = 7,
.label = 5,
- },{ /* fec0::/10 */
- .prefix = &(struct in6_addr){{{ 0xfe, 0xc0 }}},
+ }, { /* fec0::/10 */
+ .prefix = &(struct in6_addr){ { { 0xfe, 0xc0 } } },
.prefixlen = 10,
.label = 11,
- },{ /* 2002::/16 */
- .prefix = &(struct in6_addr){{{ 0x20, 0x02 }}},
+ }, { /* 2002::/16 */
+ .prefix = &(struct in6_addr){ { { 0x20, 0x02 } } },
.prefixlen = 16,
.label = 2,
- },{ /* 3ffe::/16 */
- .prefix = &(struct in6_addr){{{ 0x3f, 0xfe }}},
+ }, { /* 3ffe::/16 */
+ .prefix = &(struct in6_addr){ { { 0x3f, 0xfe } } },
.prefixlen = 16,
.label = 12,
- },{ /* 2001::/32 */
- .prefix = &(struct in6_addr){{{ 0x20, 0x01 }}},
+ }, { /* 2001::/32 */
+ .prefix = &(struct in6_addr){ { { 0x20, 0x01 } } },
.prefixlen = 32,
.label = 6,
- },{ /* 2001:10::/28 */
- .prefix = &(struct in6_addr){{{ 0x20, 0x01, 0x00, 0x10 }}},
+ }, { /* 2001:10::/28 */
+ .prefix = &(struct in6_addr){ { { 0x20, 0x01, 0x00, 0x10 } } },
.prefixlen = 28,
.label = 7,
- },{ /* ::ffff:0:0 */
- .prefix = &(struct in6_addr){{{ [10] = 0xff, [11] = 0xff }}},
+ }, { /* ::ffff:0:0 */
+ .prefix = &(struct in6_addr){ { { [10] = 0xff, [11] = 0xff } } },
.prefixlen = 96,
.label = 4,
- },{ /* ::/96 */
+ }, { /* ::/96 */
.prefix = &in6addr_any,
.prefixlen = 96,
.label = 3,
- },{ /* ::1/128 */
+ }, { /* ::1/128 */
.prefix = &in6addr_loopback,
.prefixlen = 128,
.label = 0,
@@ -441,7 +440,7 @@
if (label == IPV6_ADDR_LABEL_DEFAULT)
return -EINVAL;
- switch(nlh->nlmsg_type) {
+ switch (nlh->nlmsg_type) {
case RTM_NEWADDRLABEL:
if (ifal->ifal_index &&
!__dev_get_by_index(net, ifal->ifal_index))
@@ -505,12 +504,13 @@
hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) {
if (idx >= s_idx &&
net_eq(ip6addrlbl_net(p), net)) {
- if ((err = ip6addrlbl_fill(skb, p,
- ip6addrlbl_table.seq,
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
- RTM_NEWADDRLABEL,
- NLM_F_MULTI)) <= 0)
+ err = ip6addrlbl_fill(skb, p,
+ ip6addrlbl_table.seq,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ RTM_NEWADDRLABEL,
+ NLM_F_MULTI);
+ if (err <= 0)
break;
}
idx++;
@@ -527,7 +527,7 @@
+ nla_total_size(4); /* IFAL_LABEL */
}
-static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh)
+static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(in_skb->sk);
struct ifaddrlblmsg *ifal;
@@ -568,7 +568,8 @@
goto out;
}
- if (!(skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL))) {
+ skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL);
+ if (!skb) {
ip6addrlbl_put(p);
return -ENOBUFS;
}
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 81e496a..72a4930 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -346,6 +346,10 @@
struct ip_auth_hdr *ah;
struct ah_data *ahp;
struct tmp_ext *iph_ext;
+ int seqhi_len = 0;
+ __be32 *seqhi;
+ int sglists = 0;
+ struct scatterlist *seqhisg;
ahp = x->data;
ahash = ahp->ahash;
@@ -359,15 +363,22 @@
if (extlen)
extlen += sizeof(*iph_ext);
+ if (x->props.flags & XFRM_STATE_ESN) {
+ sglists = 1;
+ seqhi_len = sizeof(*seqhi);
+ }
err = -ENOMEM;
- iph_base = ah_alloc_tmp(ahash, nfrags, IPV6HDR_BASELEN + extlen);
+ iph_base = ah_alloc_tmp(ahash, nfrags + sglists, IPV6HDR_BASELEN +
+ extlen + seqhi_len);
if (!iph_base)
goto out;
iph_ext = ah_tmp_ext(iph_base);
- icv = ah_tmp_icv(ahash, iph_ext, extlen);
+ seqhi = (__be32 *)((char *)iph_ext + extlen);
+ icv = ah_tmp_icv(ahash, seqhi, seqhi_len);
req = ah_tmp_req(ahash, icv);
sg = ah_req_sg(ahash, req);
+ seqhisg = sg + nfrags;
ah = ip_auth_hdr(skb);
memset(ah->auth_data, 0, ahp->icv_trunc_len);
@@ -411,10 +422,15 @@
ah->spi = x->id.spi;
ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
- sg_init_table(sg, nfrags);
- skb_to_sgvec(skb, sg, 0, skb->len);
+ sg_init_table(sg, nfrags + sglists);
+ skb_to_sgvec_nomark(skb, sg, 0, skb->len);
- ahash_request_set_crypt(req, sg, icv, skb->len);
+ if (x->props.flags & XFRM_STATE_ESN) {
+ /* Attach seqhi sg right after packet payload */
+ *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+ sg_set_buf(seqhisg, seqhi, seqhi_len);
+ }
+ ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
ahash_request_set_callback(req, 0, ah6_output_done, skb);
AH_SKB_CB(skb)->tmp = iph_base;
@@ -514,6 +530,10 @@
int nexthdr;
int nfrags;
int err = -ENOMEM;
+ int seqhi_len = 0;
+ __be32 *seqhi;
+ int sglists = 0;
+ struct scatterlist *seqhisg;
if (!pskb_may_pull(skb, sizeof(struct ip_auth_hdr)))
goto out;
@@ -550,14 +570,22 @@
skb_push(skb, hdr_len);
- work_iph = ah_alloc_tmp(ahash, nfrags, hdr_len + ahp->icv_trunc_len);
+ if (x->props.flags & XFRM_STATE_ESN) {
+ sglists = 1;
+ seqhi_len = sizeof(*seqhi);
+ }
+
+ work_iph = ah_alloc_tmp(ahash, nfrags + sglists, hdr_len +
+ ahp->icv_trunc_len + seqhi_len);
if (!work_iph)
goto out;
- auth_data = ah_tmp_auth(work_iph, hdr_len);
- icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len);
+ auth_data = ah_tmp_auth((u8 *)work_iph, hdr_len);
+ seqhi = (__be32 *)(auth_data + ahp->icv_trunc_len);
+ icv = ah_tmp_icv(ahash, seqhi, seqhi_len);
req = ah_tmp_req(ahash, icv);
sg = ah_req_sg(ahash, req);
+ seqhisg = sg + nfrags;
memcpy(work_iph, ip6h, hdr_len);
memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
@@ -572,10 +600,16 @@
ip6h->flow_lbl[2] = 0;
ip6h->hop_limit = 0;
- sg_init_table(sg, nfrags);
- skb_to_sgvec(skb, sg, 0, skb->len);
+ sg_init_table(sg, nfrags + sglists);
+ skb_to_sgvec_nomark(skb, sg, 0, skb->len);
- ahash_request_set_crypt(req, sg, icv, skb->len);
+ if (x->props.flags & XFRM_STATE_ESN) {
+ /* Attach seqhi sg right after packet payload */
+ *seqhi = XFRM_SKB_CB(skb)->seq.input.hi;
+ sg_set_buf(seqhisg, seqhi, seqhi_len);
+ }
+
+ ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
ahash_request_set_callback(req, 0, ah6_input_done, skb);
AH_SKB_CB(skb)->tmp = work_iph;
@@ -609,8 +643,8 @@
return err;
}
-static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
- u8 type, u8 code, int offset, __be32 info)
+static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info)
{
struct net *net = dev_net(skb->dev);
struct ipv6hdr *iph = (struct ipv6hdr*)skb->data;
@@ -619,17 +653,19 @@
if (type != ICMPV6_PKT_TOOBIG &&
type != NDISC_REDIRECT)
- return;
+ return 0;
x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6);
if (!x)
- return;
+ return 0;
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, skb->dev->ifindex, 0);
else
ip6_update_pmtu(skb, net, info, 0, 0);
xfrm_state_put(x);
+
+ return 0;
}
static int ah6_init_state(struct xfrm_state *x)
@@ -714,6 +750,11 @@
kfree(ahp);
}
+static int ah6_rcv_cb(struct sk_buff *skb, int err)
+{
+ return 0;
+}
+
static const struct xfrm_type ah6_type =
{
.description = "AH6",
@@ -727,10 +768,11 @@
.hdr_offset = xfrm6_find_1stfragopt,
};
-static const struct inet6_protocol ah6_protocol = {
+static struct xfrm6_protocol ah6_protocol = {
.handler = xfrm6_rcv,
+ .cb_handler = ah6_rcv_cb,
.err_handler = ah6_err,
- .flags = INET6_PROTO_NOPOLICY,
+ .priority = 0,
};
static int __init ah6_init(void)
@@ -740,7 +782,7 @@
return -EAGAIN;
}
- if (inet6_add_protocol(&ah6_protocol, IPPROTO_AH) < 0) {
+ if (xfrm6_protocol_register(&ah6_protocol, IPPROTO_AH) < 0) {
pr_info("%s: can't add protocol\n", __func__);
xfrm_unregister_type(&ah6_type, AF_INET6);
return -EAGAIN;
@@ -751,7 +793,7 @@
static void __exit ah6_fini(void)
{
- if (inet6_del_protocol(&ah6_protocol, IPPROTO_AH) < 0)
+ if (xfrm6_protocol_deregister(&ah6_protocol, IPPROTO_AH) < 0)
pr_info("%s: can't remove protocol\n", __func__);
if (xfrm_unregister_type(&ah6_type, AF_INET6) < 0)
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 6eef8a7..d15da13 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -421,8 +421,8 @@
net_adj) & ~(blksize - 1)) + net_adj - 2;
}
-static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
- u8 type, u8 code, int offset, __be32 info)
+static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info)
{
struct net *net = dev_net(skb->dev);
const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data;
@@ -431,18 +431,20 @@
if (type != ICMPV6_PKT_TOOBIG &&
type != NDISC_REDIRECT)
- return;
+ return 0;
x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
esph->spi, IPPROTO_ESP, AF_INET6);
if (!x)
- return;
+ return 0;
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, skb->dev->ifindex, 0);
else
ip6_update_pmtu(skb, net, info, 0, 0);
xfrm_state_put(x);
+
+ return 0;
}
static void esp6_destroy(struct xfrm_state *x)
@@ -614,6 +616,11 @@
return err;
}
+static int esp6_rcv_cb(struct sk_buff *skb, int err)
+{
+ return 0;
+}
+
static const struct xfrm_type esp6_type =
{
.description = "ESP6",
@@ -628,10 +635,11 @@
.hdr_offset = xfrm6_find_1stfragopt,
};
-static const struct inet6_protocol esp6_protocol = {
- .handler = xfrm6_rcv,
+static struct xfrm6_protocol esp6_protocol = {
+ .handler = xfrm6_rcv,
+ .cb_handler = esp6_rcv_cb,
.err_handler = esp6_err,
- .flags = INET6_PROTO_NOPOLICY,
+ .priority = 0,
};
static int __init esp6_init(void)
@@ -640,7 +648,7 @@
pr_info("%s: can't add xfrm type\n", __func__);
return -EAGAIN;
}
- if (inet6_add_protocol(&esp6_protocol, IPPROTO_ESP) < 0) {
+ if (xfrm6_protocol_register(&esp6_protocol, IPPROTO_ESP) < 0) {
pr_info("%s: can't add protocol\n", __func__);
xfrm_unregister_type(&esp6_type, AF_INET6);
return -EAGAIN;
@@ -651,7 +659,7 @@
static void __exit esp6_fini(void)
{
- if (inet6_del_protocol(&esp6_protocol, IPPROTO_ESP) < 0)
+ if (xfrm6_protocol_deregister(&esp6_protocol, IPPROTO_ESP) < 0)
pr_info("%s: can't remove protocol\n", __func__);
if (xfrm_unregister_type(&esp6_type, AF_INET6) < 0)
pr_info("%s: can't remove xfrm type\n", __func__);
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 140748d..8af3eb5 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -212,7 +212,7 @@
found = (nexthdr == target);
if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) {
- if (target < 0)
+ if (target < 0 || found)
break;
return -ENOENT;
}
diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index cf77f3a..447a7fb 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -25,11 +25,11 @@
int ret;
ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING);
- if (!ret)
+ if (ret)
goto out;
ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS);
- if (!ret)
+ if (ret)
goto out_rt;
out:
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index f81f596..f2610e1 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -414,7 +414,7 @@
addr_type = ipv6_addr_type(&hdr->daddr);
if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) ||
- ipv6_anycast_destination(skb))
+ ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr))
saddr = &hdr->daddr;
/*
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index 72d198b..ee7a97f 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -79,7 +79,9 @@
/* RFC 2460 section 8.1 says that we SHOULD log
this error. Well, it is reasonable.
*/
- LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n");
+ LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n",
+ &ipv6_hdr(skb)->saddr, ntohs(uh->source),
+ &ipv6_hdr(skb)->daddr, ntohs(uh->dest));
return 1;
}
if (skb->ip_summed == CHECKSUM_COMPLETE &&
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 075602f..34e0ded 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -9,14 +9,12 @@
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
- */
-
-/*
- * Changes:
- * Yuji SEKIYA @USAGI: Support default route on router node;
- * remove ip6_null_entry from the top of
- * routing table.
- * Ville Nuorvala: Fixed routing subtrees.
+ *
+ * Changes:
+ * Yuji SEKIYA @USAGI: Support default route on router node;
+ * remove ip6_null_entry from the top of
+ * routing table.
+ * Ville Nuorvala: Fixed routing subtrees.
*/
#define pr_fmt(fmt) "IPv6: " fmt
@@ -46,10 +44,9 @@
#define RT6_TRACE(x...) do { ; } while (0)
#endif
-static struct kmem_cache * fib6_node_kmem __read_mostly;
+static struct kmem_cache *fib6_node_kmem __read_mostly;
-enum fib_walk_state_t
-{
+enum fib_walk_state_t {
#ifdef CONFIG_IPV6_SUBTREES
FWS_S,
#endif
@@ -59,8 +56,7 @@
FWS_U
};
-struct fib6_cleaner_t
-{
+struct fib6_cleaner_t {
struct fib6_walker_t w;
struct net *net;
int (*func)(struct rt6_info *, void *arg);
@@ -138,7 +134,7 @@
const __be32 *addr = token;
/*
* Here,
- * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)
+ * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)
* is optimized version of
* htonl(1 << ((~fn_bit)&0x1F))
* See include/asm-generic/bitops/le.h.
@@ -147,7 +143,7 @@
addr[fn_bit >> 5];
}
-static __inline__ struct fib6_node * node_alloc(void)
+static __inline__ struct fib6_node *node_alloc(void)
{
struct fib6_node *fn;
@@ -156,7 +152,7 @@
return fn;
}
-static __inline__ void node_free(struct fib6_node * fn)
+static __inline__ void node_free(struct fib6_node *fn)
{
kmem_cache_free(fib6_node_kmem, fn);
}
@@ -292,7 +288,7 @@
static void fib6_dump_end(struct netlink_callback *cb)
{
- struct fib6_walker_t *w = (void*)cb->args[2];
+ struct fib6_walker_t *w = (void *)cb->args[2];
if (w) {
if (cb->args[4]) {
@@ -302,7 +298,7 @@
cb->args[2] = 0;
kfree(w);
}
- cb->done = (void*)cb->args[3];
+ cb->done = (void *)cb->args[3];
cb->args[1] = 3;
}
@@ -485,7 +481,7 @@
fn->fn_sernum = sernum;
dir = addr_bit_set(addr, fn->fn_bit);
pn = fn;
- fn = dir ? fn->right: fn->left;
+ fn = dir ? fn->right : fn->left;
} while (fn);
if (!allow_create) {
@@ -638,12 +634,41 @@
RTF_GATEWAY;
}
+static int fib6_commit_metrics(struct dst_entry *dst,
+ struct nlattr *mx, int mx_len)
+{
+ struct nlattr *nla;
+ int remaining;
+ u32 *mp;
+
+ if (dst->flags & DST_HOST) {
+ mp = dst_metrics_write_ptr(dst);
+ } else {
+ mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+ if (!mp)
+ return -ENOMEM;
+ dst_init_metrics(dst, mp, 0);
+ }
+
+ nla_for_each_attr(nla, mx, mx_len, remaining) {
+ int type = nla_type(nla);
+
+ if (type) {
+ if (type > RTAX_MAX)
+ return -EINVAL;
+
+ mp[type - 1] = nla_get_u32(nla);
+ }
+ }
+ return 0;
+}
+
/*
* Insert routing information in a node.
*/
static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
- struct nl_info *info)
+ struct nl_info *info, struct nlattr *mx, int mx_len)
{
struct rt6_info *iter = NULL;
struct rt6_info **ins;
@@ -653,6 +678,7 @@
(info->nlh->nlmsg_flags & NLM_F_CREATE));
int found = 0;
bool rt_can_ecmp = rt6_qualify_for_ecmp(rt);
+ int err;
ins = &fn->leaf;
@@ -751,6 +777,11 @@
pr_warn("NLM_F_CREATE should be set when creating new route\n");
add:
+ if (mx) {
+ err = fib6_commit_metrics(&rt->dst, mx, mx_len);
+ if (err)
+ return err;
+ }
rt->dst.rt6_next = iter;
*ins = rt;
rt->rt6i_node = fn;
@@ -770,6 +801,11 @@
pr_warn("NLM_F_REPLACE set, but no existing node found!\n");
return -ENOENT;
}
+ if (mx) {
+ err = fib6_commit_metrics(&rt->dst, mx, mx_len);
+ if (err)
+ return err;
+ }
*ins = rt;
rt->rt6i_node = fn;
rt->dst.rt6_next = iter->dst.rt6_next;
@@ -806,7 +842,8 @@
* with source addr info in sub-trees
*/
-int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
+int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
+ struct nlattr *mx, int mx_len)
{
struct fib6_node *fn, *pn = NULL;
int err = -ENOMEM;
@@ -900,7 +937,7 @@
}
#endif
- err = fib6_add_rt2node(fn, rt, info);
+ err = fib6_add_rt2node(fn, rt, info, mx, mx_len);
if (!err) {
fib6_start_gc(info->nl_net, rt);
if (!(rt->rt6i_flags & RTF_CACHE))
@@ -955,8 +992,8 @@
const struct in6_addr *addr; /* search key */
};
-static struct fib6_node * fib6_lookup_1(struct fib6_node *root,
- struct lookup_args *args)
+static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
+ struct lookup_args *args)
{
struct fib6_node *fn;
__be32 dir;
@@ -1018,8 +1055,8 @@
return NULL;
}
-struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
- const struct in6_addr *saddr)
+struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
{
struct fib6_node *fn;
struct lookup_args args[] = {
@@ -1051,9 +1088,9 @@
*/
-static struct fib6_node * fib6_locate_1(struct fib6_node *root,
- const struct in6_addr *addr,
- int plen, int offset)
+static struct fib6_node *fib6_locate_1(struct fib6_node *root,
+ const struct in6_addr *addr,
+ int plen, int offset)
{
struct fib6_node *fn;
@@ -1081,9 +1118,9 @@
return NULL;
}
-struct fib6_node * fib6_locate(struct fib6_node *root,
- const struct in6_addr *daddr, int dst_len,
- const struct in6_addr *saddr, int src_len)
+struct fib6_node *fib6_locate(struct fib6_node *root,
+ const struct in6_addr *daddr, int dst_len,
+ const struct in6_addr *saddr, int src_len)
{
struct fib6_node *fn;
@@ -1151,8 +1188,10 @@
children = 0;
child = NULL;
- if (fn->right) child = fn->right, children |= 1;
- if (fn->left) child = fn->left, children |= 2;
+ if (fn->right)
+ child = fn->right, children |= 1;
+ if (fn->left)
+ child = fn->left, children |= 2;
if (children == 3 || FIB6_SUBTREE(fn)
#ifdef CONFIG_IPV6_SUBTREES
@@ -1180,8 +1219,10 @@
} else {
WARN_ON(fn->fn_flags & RTN_ROOT);
#endif
- if (pn->right == fn) pn->right = child;
- else if (pn->left == fn) pn->left = child;
+ if (pn->right == fn)
+ pn->right = child;
+ else if (pn->left == fn)
+ pn->left = child;
#if RT6_DEBUG >= 2
else
WARN_ON(1);
@@ -1213,10 +1254,10 @@
w->node = child;
if (children&2) {
RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state);
- w->state = w->state>=FWS_R ? FWS_U : FWS_INIT;
+ w->state = w->state >= FWS_R ? FWS_U : FWS_INIT;
} else {
RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state);
- w->state = w->state>=FWS_C ? FWS_U : FWS_INIT;
+ w->state = w->state >= FWS_C ? FWS_U : FWS_INIT;
}
}
}
@@ -1314,7 +1355,7 @@
struct rt6_info **rtp;
#if RT6_DEBUG >= 2
- if (rt->dst.obsolete>0) {
+ if (rt->dst.obsolete > 0) {
WARN_ON(fn != NULL);
return -ENOENT;
}
@@ -1707,7 +1748,7 @@
kfree(net->ipv6.rt6_stats);
out_timer:
return -ENOMEM;
- }
+}
static void fib6_net_exit(struct net *net)
{
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index dfa41bb..0961b5e 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -15,9 +15,7 @@
#include <linux/socket.h>
#include <linux/net.h>
#include <linux/netdevice.h>
-#include <linux/if_arp.h>
#include <linux/in6.h>
-#include <linux/route.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
@@ -28,12 +26,8 @@
#include <net/sock.h>
#include <net/ipv6.h>
-#include <net/ndisc.h>
-#include <net/protocol.h>
-#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/rawv6.h>
-#include <net/icmp.h>
#include <net/transp_v6.h>
#include <asm/uaccess.h>
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index f3ffb43..c98338b 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1454,7 +1454,6 @@
static int ip6gre_tap_init(struct net_device *dev)
{
struct ip6_tnl *tunnel;
- int i;
tunnel = netdev_priv(dev);
@@ -1464,16 +1463,10 @@
ip6gre_tnl_link_config(tunnel, 1);
- dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct pcpu_sw_netstats *ip6gre_tap_stats;
- ip6gre_tap_stats = per_cpu_ptr(dev->tstats, i);
- u64_stats_init(&ip6gre_tap_stats->syncp);
- }
-
return 0;
}
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 1e8683b..59f95af 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -89,7 +89,7 @@
unsigned int unfrag_ip6hlen;
u8 *prevhdr;
int offset = 0;
- bool tunnel;
+ bool encap, udpfrag;
int nhoff;
if (unlikely(skb_shinfo(skb)->gso_type &
@@ -110,8 +110,8 @@
if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
goto out;
- tunnel = SKB_GSO_CB(skb)->encap_level > 0;
- if (tunnel)
+ encap = SKB_GSO_CB(skb)->encap_level > 0;
+ if (encap)
features = skb->dev->hw_enc_features & netif_skb_features(skb);
SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h);
@@ -121,6 +121,12 @@
proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
+ if (skb->encapsulation &&
+ skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+ udpfrag = proto == IPPROTO_UDP && encap;
+ else
+ udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+
ops = rcu_dereference(inet6_offloads[proto]);
if (likely(ops && ops->callbacks.gso_segment)) {
skb_reset_transport_header(skb);
@@ -133,13 +139,9 @@
for (skb = segs; skb; skb = skb->next) {
ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h));
- if (tunnel) {
- skb_reset_inner_headers(skb);
- skb->encapsulation = 1;
- }
skb->network_header = (u8 *)ipv6h - skb->head;
- if (!tunnel && proto == IPPROTO_UDP) {
+ if (udpfrag) {
unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
fptr->frag_off = htons(offset);
@@ -148,6 +150,8 @@
offset += (ntohs(ipv6h->payload_len) -
sizeof(struct frag_hdr));
}
+ if (encap)
+ skb_reset_inner_headers(skb);
}
out:
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ef02b26..6184dfa 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -342,6 +342,20 @@
return mtu;
}
+static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu || skb->local_df)
+ return false;
+
+ if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
+ return true;
+
+ if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ return false;
+
+ return true;
+}
+
int ip6_forward(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
@@ -353,6 +367,9 @@
if (net->ipv6.devconf_all->forwarding == 0)
goto error;
+ if (skb->pkt_type != PACKET_HOST)
+ goto drop;
+
if (skb_warn_if_lro(skb))
goto drop;
@@ -362,9 +379,6 @@
goto drop;
}
- if (skb->pkt_type != PACKET_HOST)
- goto drop;
-
skb_forward_csum(skb);
/*
@@ -466,8 +480,7 @@
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
- if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
- (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
+ if (ip6_pkt_too_big(skb, mtu)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
@@ -517,9 +530,6 @@
to->tc_index = from->tc_index;
#endif
nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
- to->nf_trace = from->nf_trace;
-#endif
skb_copy_secmark(to, from);
}
@@ -1091,21 +1101,19 @@
unsigned int fragheaderlen,
struct sk_buff *skb,
struct rt6_info *rt,
- bool pmtuprobe)
+ unsigned int orig_mtu)
{
if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
if (skb == NULL) {
/* first fragment, reserve header_len */
- *mtu = *mtu - rt->dst.header_len;
+ *mtu = orig_mtu - rt->dst.header_len;
} else {
/*
* this fragment is not first, the headers
* space is regarded as data space.
*/
- *mtu = min(*mtu, pmtuprobe ?
- rt->dst.dev->mtu :
- dst_mtu(rt->dst.path));
+ *mtu = orig_mtu;
}
*maxfraglen = ((*mtu - fragheaderlen) & ~7)
+ fragheaderlen - sizeof(struct frag_hdr);
@@ -1122,7 +1130,7 @@
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_cork *cork;
struct sk_buff *skb, *skb_prev = NULL;
- unsigned int maxfraglen, fragheaderlen, mtu;
+ unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
int exthdrlen;
int dst_exthdrlen;
int hh_len;
@@ -1204,6 +1212,7 @@
dst_exthdrlen = 0;
mtu = cork->fragsize;
}
+ orig_mtu = mtu;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
@@ -1221,8 +1230,10 @@
sizeof(struct frag_hdr) : 0) +
rt->rt6i_nfheader_len;
- maxnonfragsize = (np->pmtudisc >= IPV6_PMTUDISC_DO) ?
- mtu : sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
+ if (ip6_sk_local_df(sk))
+ maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
+ else
+ maxnonfragsize = mtu;
/* dontfrag active */
if ((cork->length + length > mtu - headersize) && dontfrag &&
@@ -1301,8 +1312,7 @@
if (skb == NULL || skb_prev == NULL)
ip6_append_data_mtu(&mtu, &maxfraglen,
fragheaderlen, skb, rt,
- np->pmtudisc >=
- IPV6_PMTUDISC_PROBE);
+ orig_mtu);
skb_prev = skb;
@@ -1530,8 +1540,7 @@
}
/* Allow local fragmentation. */
- if (np->pmtudisc < IPV6_PMTUDISC_DO)
- skb->local_df = 1;
+ skb->local_df = ip6_sk_local_df(sk);
*final_dst = fl6->daddr;
__skb_pull(skb, skb_network_header_len(skb));
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 5db8d31..e1df691 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -108,12 +108,12 @@
per_cpu_ptr(dev->tstats, i);
do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
+ start = u64_stats_fetch_begin_irq(&tstats->syncp);
tmp.rx_packets = tstats->rx_packets;
tmp.rx_bytes = tstats->rx_bytes;
tmp.tx_packets = tstats->tx_packets;
tmp.tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
sum.rx_packets += tmp.rx_packets;
sum.rx_bytes += tmp.rx_bytes;
@@ -1502,19 +1502,12 @@
ip6_tnl_dev_init_gen(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
- int i;
t->dev = dev;
t->net = dev_net(dev);
- dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
-
- for_each_possible_cpu(i) {
- struct pcpu_sw_netstats *ip6_tnl_stats;
- ip6_tnl_stats = per_cpu_ptr(dev->tstats, i);
- u64_stats_init(&ip6_tnl_stats->syncp);
- }
return 0;
}
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 2d19272..b7c0f82 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -278,7 +278,6 @@
RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL);
else
vti6_tnl_unlink(ip6n, t);
- ip6_tnl_dst_reset(t);
dev_put(dev);
}
@@ -288,11 +287,8 @@
const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
rcu_read_lock();
-
if ((t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr,
&ipv6h->daddr)) != NULL) {
- struct pcpu_sw_netstats *tstats;
-
if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) {
rcu_read_unlock();
goto discard;
@@ -309,27 +305,58 @@
goto discard;
}
- tstats = this_cpu_ptr(t->dev->tstats);
- u64_stats_update_begin(&tstats->syncp);
- tstats->rx_packets++;
- tstats->rx_bytes += skb->len;
- u64_stats_update_end(&tstats->syncp);
-
- skb->mark = 0;
- secpath_reset(skb);
- skb->dev = t->dev;
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
+ skb->mark = be32_to_cpu(t->parms.i_key);
rcu_read_unlock();
- return 0;
+
+ return xfrm6_rcv(skb);
}
rcu_read_unlock();
- return 1;
-
+ return -EINVAL;
discard:
kfree_skb(skb);
return 0;
}
+static int vti6_rcv_cb(struct sk_buff *skb, int err)
+{
+ unsigned short family;
+ struct net_device *dev;
+ struct pcpu_sw_netstats *tstats;
+ struct xfrm_state *x;
+ struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
+
+ if (!t)
+ return 1;
+
+ dev = t->dev;
+
+ if (err) {
+ dev->stats.rx_errors++;
+ dev->stats.rx_dropped++;
+
+ return 0;
+ }
+
+ x = xfrm_input_state(skb);
+ family = x->inner_mode->afinfo->family;
+
+ if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+ return -EPERM;
+
+ skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev)));
+ skb->dev = dev;
+
+ tstats = this_cpu_ptr(dev->tstats);
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->rx_packets++;
+ tstats->rx_bytes += skb->len;
+ u64_stats_update_end(&tstats->syncp);
+
+ return 0;
+}
+
/**
* vti6_addr_conflict - compare packet addresses to tunnel's own
* @t: the outgoing tunnel device
@@ -349,44 +376,56 @@
return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr);
}
+static bool vti6_state_check(const struct xfrm_state *x,
+ const struct in6_addr *dst,
+ const struct in6_addr *src)
+{
+ xfrm_address_t *daddr = (xfrm_address_t *)dst;
+ xfrm_address_t *saddr = (xfrm_address_t *)src;
+
+ /* if there is no transform then this tunnel is not functional.
+ * Or if the xfrm is not mode tunnel.
+ */
+ if (!x || x->props.mode != XFRM_MODE_TUNNEL ||
+ x->props.family != AF_INET6)
+ return false;
+
+ if (ipv6_addr_any(dst))
+ return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET6);
+
+ if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET6))
+ return false;
+
+ return true;
+}
+
/**
* vti6_xmit - send a packet
* @skb: the outgoing socket buffer
* @dev: the outgoing tunnel device
+ * @fl: the flow informations for the xfrm_lookup
**/
-static int vti6_xmit(struct sk_buff *skb, struct net_device *dev)
+static int
+vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
{
- struct net *net = dev_net(dev);
struct ip6_tnl *t = netdev_priv(dev);
struct net_device_stats *stats = &t->dev->stats;
- struct dst_entry *dst = NULL, *ndst = NULL;
- struct flowi6 fl6;
- struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ struct dst_entry *dst = skb_dst(skb);
struct net_device *tdev;
int err = -1;
- if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
- !ip6_tnl_xmit_ctl(t) || vti6_addr_conflict(t, ipv6h))
- return err;
+ if (!dst)
+ goto tx_err_link_failure;
- dst = ip6_tnl_dst_check(t);
- if (!dst) {
- memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-
- ndst = ip6_route_output(net, NULL, &fl6);
-
- if (ndst->error)
- goto tx_err_link_failure;
- ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(&fl6), NULL, 0);
- if (IS_ERR(ndst)) {
- err = PTR_ERR(ndst);
- ndst = NULL;
- goto tx_err_link_failure;
- }
- dst = ndst;
+ dst_hold(dst);
+ dst = xfrm_lookup(t->net, dst, fl, NULL, 0);
+ if (IS_ERR(dst)) {
+ err = PTR_ERR(dst);
+ dst = NULL;
+ goto tx_err_link_failure;
}
- if (!dst->xfrm || dst->xfrm->props.mode != XFRM_MODE_TUNNEL)
+ if (!vti6_state_check(dst->xfrm, &t->parms.raddr, &t->parms.laddr))
goto tx_err_link_failure;
tdev = dst->dev;
@@ -398,14 +437,21 @@
goto tx_err_dst_release;
}
+ skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
+ skb_dst_set(skb, dst);
+ skb->dev = skb_dst(skb)->dev;
- skb_dst_drop(skb);
- skb_dst_set_noref(skb, dst);
+ err = dst_output(skb);
+ if (net_xmit_eval(err) == 0) {
+ struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
- ip6tunnel_xmit(skb, dev);
- if (ndst) {
- dev->mtu = dst_mtu(ndst);
- ip6_tnl_dst_store(t, ndst);
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->tx_bytes += skb->len;
+ tstats->tx_packets++;
+ u64_stats_update_end(&tstats->syncp);
+ } else {
+ stats->tx_errors++;
+ stats->tx_aborted_errors++;
}
return 0;
@@ -413,7 +459,7 @@
stats->tx_carrier_errors++;
dst_link_failure(skb);
tx_err_dst_release:
- dst_release(ndst);
+ dst_release(dst);
return err;
}
@@ -422,16 +468,33 @@
{
struct ip6_tnl *t = netdev_priv(dev);
struct net_device_stats *stats = &t->dev->stats;
+ struct ipv6hdr *ipv6h;
+ struct flowi fl;
int ret;
+ memset(&fl, 0, sizeof(fl));
+ skb->mark = be32_to_cpu(t->parms.o_key);
+
switch (skb->protocol) {
case htons(ETH_P_IPV6):
- ret = vti6_xmit(skb, dev);
+ ipv6h = ipv6_hdr(skb);
+
+ if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
+ !ip6_tnl_xmit_ctl(t) || vti6_addr_conflict(t, ipv6h))
+ goto tx_err;
+
+ xfrm_decode_session(skb, &fl, AF_INET6);
+ memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ break;
+ case htons(ETH_P_IP):
+ xfrm_decode_session(skb, &fl, AF_INET);
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
break;
default:
goto tx_err;
}
+ ret = vti6_xmit(skb, dev, &fl);
if (ret < 0)
goto tx_err;
@@ -444,24 +507,66 @@
return NETDEV_TX_OK;
}
+static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info)
+{
+ __be32 spi;
+ struct xfrm_state *x;
+ struct ip6_tnl *t;
+ struct ip_esp_hdr *esph;
+ struct ip_auth_hdr *ah;
+ struct ip_comp_hdr *ipch;
+ struct net *net = dev_net(skb->dev);
+ const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data;
+ int protocol = iph->nexthdr;
+
+ t = vti6_tnl_lookup(dev_net(skb->dev), &iph->daddr, &iph->saddr);
+ if (!t)
+ return -1;
+
+ switch (protocol) {
+ case IPPROTO_ESP:
+ esph = (struct ip_esp_hdr *)(skb->data + offset);
+ spi = esph->spi;
+ break;
+ case IPPROTO_AH:
+ ah = (struct ip_auth_hdr *)(skb->data + offset);
+ spi = ah->spi;
+ break;
+ case IPPROTO_COMP:
+ ipch = (struct ip_comp_hdr *)(skb->data + offset);
+ spi = htonl(ntohs(ipch->cpi));
+ break;
+ default:
+ return 0;
+ }
+
+ if (type != ICMPV6_PKT_TOOBIG &&
+ type != NDISC_REDIRECT)
+ return 0;
+
+ x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+ spi, protocol, AF_INET6);
+ if (!x)
+ return 0;
+
+ if (type == NDISC_REDIRECT)
+ ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ else
+ ip6_update_pmtu(skb, net, info, 0, 0);
+ xfrm_state_put(x);
+
+ return 0;
+}
+
static void vti6_link_config(struct ip6_tnl *t)
{
- struct dst_entry *dst;
struct net_device *dev = t->dev;
struct __ip6_tnl_parm *p = &t->parms;
- struct flowi6 *fl6 = &t->fl.u.ip6;
memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
- /* Set up flowi template */
- fl6->saddr = p->laddr;
- fl6->daddr = p->raddr;
- fl6->flowi6_oif = p->link;
- fl6->flowi6_mark = be32_to_cpu(p->i_key);
- fl6->flowi6_proto = p->proto;
- fl6->flowlabel = 0;
-
p->flags &= ~(IP6_TNL_F_CAP_XMIT | IP6_TNL_F_CAP_RCV |
IP6_TNL_F_CAP_PER_PACKET);
p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr);
@@ -472,28 +577,6 @@
dev->flags &= ~IFF_POINTOPOINT;
dev->iflink = p->link;
-
- if (p->flags & IP6_TNL_F_CAP_XMIT) {
-
- dst = ip6_route_output(dev_net(dev), NULL, fl6);
- if (dst->error)
- return;
-
- dst = xfrm_lookup(dev_net(dev), dst, flowi6_to_flowi(fl6),
- NULL, 0);
- if (IS_ERR(dst))
- return;
-
- if (dst->dev) {
- dev->hard_header_len = dst->dev->hard_header_len;
-
- dev->mtu = dst_mtu(dst);
-
- if (dev->mtu < IPV6_MIN_MTU)
- dev->mtu = IPV6_MIN_MTU;
- }
- dst_release(dst);
- }
}
/**
@@ -720,7 +803,6 @@
t = netdev_priv(dev);
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
- dev->features |= NETIF_F_NETNS_LOCAL;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
}
@@ -731,18 +813,12 @@
static inline int vti6_dev_init_gen(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
- int i;
t->dev = dev;
t->net = dev_net(dev);
- dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct pcpu_sw_netstats *stats;
- stats = per_cpu_ptr(dev->tstats, i);
- u64_stats_init(&stats->syncp);
- }
return 0;
}
@@ -914,11 +990,6 @@
.fill_info = vti6_fill_info,
};
-static struct xfrm_tunnel_notifier vti6_handler __read_mostly = {
- .handler = vti6_rcv,
- .priority = 1,
-};
-
static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n)
{
int h;
@@ -990,6 +1061,27 @@
.size = sizeof(struct vti6_net),
};
+static struct xfrm6_protocol vti_esp6_protocol __read_mostly = {
+ .handler = vti6_rcv,
+ .cb_handler = vti6_rcv_cb,
+ .err_handler = vti6_err,
+ .priority = 100,
+};
+
+static struct xfrm6_protocol vti_ah6_protocol __read_mostly = {
+ .handler = vti6_rcv,
+ .cb_handler = vti6_rcv_cb,
+ .err_handler = vti6_err,
+ .priority = 100,
+};
+
+static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = {
+ .handler = vti6_rcv,
+ .cb_handler = vti6_rcv_cb,
+ .err_handler = vti6_err,
+ .priority = 100,
+};
+
/**
* vti6_tunnel_init - register protocol and reserve needed resources
*
@@ -1003,11 +1095,33 @@
if (err < 0)
goto out_pernet;
- err = xfrm6_mode_tunnel_input_register(&vti6_handler);
+ err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP);
if (err < 0) {
- pr_err("%s: can't register vti6\n", __func__);
+ unregister_pernet_device(&vti6_net_ops);
+ pr_err("%s: can't register vti6 protocol\n", __func__);
+
goto out;
}
+
+ err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH);
+ if (err < 0) {
+ xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
+ unregister_pernet_device(&vti6_net_ops);
+ pr_err("%s: can't register vti6 protocol\n", __func__);
+
+ goto out;
+ }
+
+ err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP);
+ if (err < 0) {
+ xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
+ xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
+ unregister_pernet_device(&vti6_net_ops);
+ pr_err("%s: can't register vti6 protocol\n", __func__);
+
+ goto out;
+ }
+
err = rtnl_link_register(&vti6_link_ops);
if (err < 0)
goto rtnl_link_failed;
@@ -1015,7 +1129,9 @@
return 0;
rtnl_link_failed:
- xfrm6_mode_tunnel_input_deregister(&vti6_handler);
+ xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP);
+ xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
+ xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
out:
unregister_pernet_device(&vti6_net_ops);
out_pernet:
@@ -1028,8 +1144,12 @@
static void __exit vti6_tunnel_cleanup(void)
{
rtnl_link_unregister(&vti6_link_ops);
- if (xfrm6_mode_tunnel_input_deregister(&vti6_handler))
- pr_info("%s: can't deregister vti6\n", __func__);
+ if (xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP))
+ pr_info("%s: can't deregister protocol\n", __func__);
+ if (xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH))
+ pr_info("%s: can't deregister protocol\n", __func__);
+ if (xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP))
+ pr_info("%s: can't deregister protocol\n", __func__);
unregister_pernet_device(&vti6_net_ops);
}
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 0eb4038..8737400 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2349,13 +2349,14 @@
}
static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
- u32 portid, u32 seq, struct mfc6_cache *c, int cmd)
+ u32 portid, u32 seq, struct mfc6_cache *c, int cmd,
+ int flags)
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
int err;
- nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
+ nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
if (nlh == NULL)
return -EMSGSIZE;
@@ -2423,7 +2424,7 @@
if (skb == NULL)
goto errout;
- err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+ err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
if (err < 0)
goto errout;
@@ -2462,7 +2463,8 @@
if (ip6mr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc, RTM_NEWROUTE) < 0)
+ mfc, RTM_NEWROUTE,
+ NLM_F_MULTI) < 0)
goto done;
next_entry:
e++;
@@ -2476,7 +2478,8 @@
if (ip6mr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc, RTM_NEWROUTE) < 0) {
+ mfc, RTM_NEWROUTE,
+ NLM_F_MULTI) < 0) {
spin_unlock_bh(&mfc_unres_lock);
goto done;
}
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index da9becb..d1c793c 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -53,7 +53,7 @@
#include <linux/icmpv6.h>
#include <linux/mutex.h>
-static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct net *net = dev_net(skb->dev);
@@ -65,19 +65,21 @@
if (type != ICMPV6_PKT_TOOBIG &&
type != NDISC_REDIRECT)
- return;
+ return 0;
spi = htonl(ntohs(ipcomph->cpi));
x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
spi, IPPROTO_COMP, AF_INET6);
if (!x)
- return;
+ return 0;
if (type == NDISC_REDIRECT)
ip6_redirect(skb, net, skb->dev->ifindex, 0);
else
ip6_update_pmtu(skb, net, info, 0, 0);
xfrm_state_put(x);
+
+ return 0;
}
static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x)
@@ -174,6 +176,11 @@
return err;
}
+static int ipcomp6_rcv_cb(struct sk_buff *skb, int err)
+{
+ return 0;
+}
+
static const struct xfrm_type ipcomp6_type =
{
.description = "IPCOMP6",
@@ -186,11 +193,12 @@
.hdr_offset = xfrm6_find_1stfragopt,
};
-static const struct inet6_protocol ipcomp6_protocol =
+static struct xfrm6_protocol ipcomp6_protocol =
{
.handler = xfrm6_rcv,
+ .cb_handler = ipcomp6_rcv_cb,
.err_handler = ipcomp6_err,
- .flags = INET6_PROTO_NOPOLICY,
+ .priority = 0,
};
static int __init ipcomp6_init(void)
@@ -199,7 +207,7 @@
pr_info("%s: can't add xfrm type\n", __func__);
return -EAGAIN;
}
- if (inet6_add_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0) {
+ if (xfrm6_protocol_register(&ipcomp6_protocol, IPPROTO_COMP) < 0) {
pr_info("%s: can't add protocol\n", __func__);
xfrm_unregister_type(&ipcomp6_type, AF_INET6);
return -EAGAIN;
@@ -209,7 +217,7 @@
static void __exit ipcomp6_fini(void)
{
- if (inet6_del_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0)
+ if (xfrm6_protocol_deregister(&ipcomp6_protocol, IPPROTO_COMP) < 0)
pr_info("%s: can't remove protocol\n", __func__);
if (xfrm_unregister_type(&ipcomp6_type, AF_INET6) < 0)
pr_info("%s: can't remove xfrm type\n", __func__);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 0a00f44..edb58af 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -722,7 +722,7 @@
case IPV6_MTU_DISCOVER:
if (optlen < sizeof(int))
goto e_inval;
- if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_INTERFACE)
+ if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_OMIT)
goto e_inval;
np->pmtudisc = val;
retv = 0;
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 35750df..4bff1f2 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -50,6 +50,11 @@
packet transformations such as the source, destination address and
source and destination ports.
+config NFT_REJECT_IPV6
+ depends on NF_TABLES_IPV6
+ default NFT_REJECT
+ tristate
+
config IP6_NF_IPTABLES
tristate "IP6 tables support (required for filtering)"
depends on INET && IPV6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index d1b4928..70d3dd6 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -27,6 +27,7 @@
obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
+obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
# matches
obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c
new file mode 100644
index 0000000..0bc19fa
--- /dev/null
+++ b/net/ipv6/netfilter/nft_reject_ipv6.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2013 Eric Leblond <eric@regit.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+#include <net/netfilter/ipv6/nf_reject.h>
+
+void nft_reject_ipv6_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_reject *priv = nft_expr_priv(expr);
+ struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out);
+
+ switch (priv->type) {
+ case NFT_REJECT_ICMP_UNREACH:
+ nf_send_unreach6(net, pkt->skb, priv->icmp_code,
+ pkt->ops->hooknum);
+ break;
+ case NFT_REJECT_TCP_RST:
+ nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
+ break;
+ }
+
+ data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+EXPORT_SYMBOL_GPL(nft_reject_ipv6_eval);
+
+static struct nft_expr_type nft_reject_ipv6_type;
+static const struct nft_expr_ops nft_reject_ipv6_ops = {
+ .type = &nft_reject_ipv6_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+ .eval = nft_reject_ipv6_eval,
+ .init = nft_reject_init,
+ .dump = nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_ipv6_type __read_mostly = {
+ .family = NFPROTO_IPV6,
+ .name = "reject",
+ .ops = &nft_reject_ipv6_ops,
+ .policy = nft_reject_policy,
+ .maxattr = NFTA_REJECT_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_reject_ipv6_module_init(void)
+{
+ return nft_register_expr(&nft_reject_ipv6_type);
+}
+
+static void __exit nft_reject_ipv6_module_exit(void)
+{
+ nft_unregister_expr(&nft_reject_ipv6_type);
+}
+
+module_init(nft_reject_ipv6_module_init);
+module_exit(nft_reject_ipv6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "reject");
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 827f795..d1b35d3 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -13,7 +13,7 @@
int old, new;
#if IS_ENABLED(CONFIG_IPV6)
- if (rt && !(rt->dst.flags & DST_NOPEER)) {
+ if (rt) {
struct inet_peer *peer;
struct net *net;
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index fb9beb7..587bbdc 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -135,6 +135,7 @@
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.saddr = np->saddr;
fl6.daddr = *daddr;
+ fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_icmp_type = user_icmph.icmp6_type;
fl6.fl6_icmp_code = user_icmph.icmp6_code;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 11dac21..b93ae6a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -149,7 +149,8 @@
unsigned long prev, new;
p = peer->metrics;
- if (inet_metrics_new(peer))
+ if (inet_metrics_new(peer) ||
+ (old & DST_METRICS_FORCE_OVERWRITE))
memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
new = (unsigned long) p;
@@ -857,14 +858,15 @@
be destroyed.
*/
-static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info)
+static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
+ struct nlattr *mx, int mx_len)
{
int err;
struct fib6_table *table;
table = rt->rt6i_table;
write_lock_bh(&table->tb6_lock);
- err = fib6_add(&table->tb6_root, rt, info);
+ err = fib6_add(&table->tb6_root, rt, info, mx, mx_len);
write_unlock_bh(&table->tb6_lock);
return err;
@@ -875,7 +877,7 @@
struct nl_info info = {
.nl_net = dev_net(rt->dst.dev),
};
- return __ip6_ins_rt(rt, &info);
+ return __ip6_ins_rt(rt, &info, NULL, 0);
}
static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
@@ -1513,7 +1515,7 @@
if (!table)
goto out;
- rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table);
+ rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table);
if (!rt) {
err = -ENOMEM;
@@ -1543,17 +1545,11 @@
ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
rt->rt6i_dst.plen = cfg->fc_dst_len;
- if (rt->rt6i_dst.plen == 128)
- rt->dst.flags |= DST_HOST;
-
- if (!(rt->dst.flags & DST_HOST) && cfg->fc_mx) {
- u32 *metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
- if (!metrics) {
- err = -ENOMEM;
- goto out;
- }
- dst_init_metrics(&rt->dst, metrics, 0);
+ if (rt->rt6i_dst.plen == 128) {
+ rt->dst.flags |= DST_HOST;
+ dst_metrics_set_force_overwrite(&rt->dst);
}
+
#ifdef CONFIG_IPV6_SUBTREES
ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
rt->rt6i_src.plen = cfg->fc_src_len;
@@ -1672,31 +1668,13 @@
rt->rt6i_flags = cfg->fc_flags;
install_route:
- if (cfg->fc_mx) {
- struct nlattr *nla;
- int remaining;
-
- nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
- int type = nla_type(nla);
-
- if (type) {
- if (type > RTAX_MAX) {
- err = -EINVAL;
- goto out;
- }
-
- dst_metric_set(&rt->dst, type, nla_get_u32(nla));
- }
- }
- }
-
rt->dst.dev = dev;
rt->rt6i_idev = idev;
rt->rt6i_table = table;
cfg->fc_nlinfo.nl_net = dev_net(dev);
- return __ip6_ins_rt(rt, &cfg->fc_nlinfo);
+ return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len);
out:
if (dev)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3dfbcf1..1693c8d 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -475,6 +475,7 @@
ipip6_tunnel_unlink(sitn, tunnel);
ipip6_tunnel_del_prl(tunnel, NULL);
}
+ ip_tunnel_dst_reset_all(tunnel);
dev_put(dev);
}
@@ -1082,6 +1083,7 @@
t->parms.link = p->link;
ipip6_tunnel_bind_dev(t->dev);
}
+ ip_tunnel_dst_reset_all(t);
netdev_state_change(t->dev);
}
@@ -1112,6 +1114,7 @@
t->ip6rd.relay_prefix = relay_prefix;
t->ip6rd.prefixlen = ip6rd->prefixlen;
t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen;
+ ip_tunnel_dst_reset_all(t);
netdev_state_change(t->dev);
return 0;
}
@@ -1271,6 +1274,7 @@
err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
break;
}
+ ip_tunnel_dst_reset_all(t);
netdev_state_change(dev);
break;
@@ -1326,6 +1330,9 @@
static void ipip6_dev_free(struct net_device *dev)
{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+
+ free_percpu(tunnel->dst_cache);
free_percpu(dev->tstats);
free_netdev(dev);
}
@@ -1356,7 +1363,6 @@
static int ipip6_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- int i;
tunnel->dev = dev;
tunnel->net = dev_net(dev);
@@ -1365,14 +1371,14 @@
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
ipip6_tunnel_bind_dev(dev);
- dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct pcpu_sw_netstats *ipip6_tunnel_stats;
- ipip6_tunnel_stats = per_cpu_ptr(dev->tstats, i);
- u64_stats_init(&ipip6_tunnel_stats->syncp);
+ tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+ if (!tunnel->dst_cache) {
+ free_percpu(dev->tstats);
+ return -ENOMEM;
}
return 0;
@@ -1384,7 +1390,6 @@
struct iphdr *iph = &tunnel->parms.iph;
struct net *net = dev_net(dev);
struct sit_net *sitn = net_generic(net, sit_net_id);
- int i;
tunnel->dev = dev;
tunnel->net = dev_net(dev);
@@ -1395,14 +1400,14 @@
iph->ihl = 5;
iph->ttl = 64;
- dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
- for_each_possible_cpu(i) {
- struct pcpu_sw_netstats *ipip6_fb_stats;
- ipip6_fb_stats = per_cpu_ptr(dev->tstats, i);
- u64_stats_init(&ipip6_fb_stats->syncp);
+ tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+ if (!tunnel->dst_cache) {
+ free_percpu(dev->tstats);
+ return -ENOMEM;
}
dev_hold(dev);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 889079b..3277680 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -501,8 +501,10 @@
int res;
res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0);
- if (!res)
+ if (!res) {
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+ }
return res;
}
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index e7359f9..b261ee8 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -113,7 +113,7 @@
fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
fptr->nexthdr = nexthdr;
fptr->reserved = 0;
- ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb));
+ fptr->identification = skb_shinfo(skb)->ip6_frag_id;
/* Fragment the skb. ipv6 header and the remaining fields of the
* fragment header are updated in ipv6_gso_segment()
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index cb04f7a..901ef6f 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -18,65 +18,6 @@
#include <net/ipv6.h>
#include <net/xfrm.h>
-/* Informational hook. The decap is still done here. */
-static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly;
-static DEFINE_MUTEX(xfrm6_mode_tunnel_input_mutex);
-
-int xfrm6_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler)
-{
- struct xfrm_tunnel_notifier __rcu **pprev;
- struct xfrm_tunnel_notifier *t;
- int ret = -EEXIST;
- int priority = handler->priority;
-
- mutex_lock(&xfrm6_mode_tunnel_input_mutex);
-
- for (pprev = &rcv_notify_handlers;
- (t = rcu_dereference_protected(*pprev,
- lockdep_is_held(&xfrm6_mode_tunnel_input_mutex))) != NULL;
- pprev = &t->next) {
- if (t->priority > priority)
- break;
- if (t->priority == priority)
- goto err;
-
- }
-
- handler->next = *pprev;
- rcu_assign_pointer(*pprev, handler);
-
- ret = 0;
-
-err:
- mutex_unlock(&xfrm6_mode_tunnel_input_mutex);
- return ret;
-}
-EXPORT_SYMBOL_GPL(xfrm6_mode_tunnel_input_register);
-
-int xfrm6_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler)
-{
- struct xfrm_tunnel_notifier __rcu **pprev;
- struct xfrm_tunnel_notifier *t;
- int ret = -ENOENT;
-
- mutex_lock(&xfrm6_mode_tunnel_input_mutex);
- for (pprev = &rcv_notify_handlers;
- (t = rcu_dereference_protected(*pprev,
- lockdep_is_held(&xfrm6_mode_tunnel_input_mutex))) != NULL;
- pprev = &t->next) {
- if (t == handler) {
- *pprev = handler->next;
- ret = 0;
- break;
- }
- }
- mutex_unlock(&xfrm6_mode_tunnel_input_mutex);
- synchronize_net();
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(xfrm6_mode_tunnel_input_deregister);
-
static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
{
const struct ipv6hdr *outer_iph = ipv6_hdr(skb);
@@ -130,7 +71,6 @@
static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
{
- struct xfrm_tunnel_notifier *handler;
int err = -EINVAL;
if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6)
@@ -138,9 +78,6 @@
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto out;
- for_each_input_rcu(rcv_notify_handlers, handler)
- handler->handler(skb);
-
err = skb_unclone(skb, GFP_ATOMIC);
if (err)
goto out;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 5f8e128..2a0bbda 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -389,11 +389,17 @@
if (ret)
goto out_policy;
+ ret = xfrm6_protocol_init();
+ if (ret)
+ goto out_state;
+
#ifdef CONFIG_SYSCTL
register_pernet_subsys(&xfrm6_net_ops);
#endif
out:
return ret;
+out_state:
+ xfrm6_state_fini();
out_policy:
xfrm6_policy_fini();
goto out;
@@ -404,6 +410,7 @@
#ifdef CONFIG_SYSCTL
unregister_pernet_subsys(&xfrm6_net_ops);
#endif
+ xfrm6_protocol_fini();
xfrm6_policy_fini();
xfrm6_state_fini();
dst_entries_destroy(&xfrm6_dst_ops);
diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c
new file mode 100644
index 0000000..6ab989c
--- /dev/null
+++ b/net/ipv6/xfrm6_protocol.c
@@ -0,0 +1,270 @@
+/* xfrm6_protocol.c - Generic xfrm protocol multiplexer for ipv6.
+ *
+ * Copyright (C) 2013 secunet Security Networks AG
+ *
+ * Author:
+ * Steffen Klassert <steffen.klassert@secunet.com>
+ *
+ * Based on:
+ * net/ipv4/xfrm4_protocol.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/skbuff.h>
+#include <linux/icmpv6.h>
+#include <net/ipv6.h>
+#include <net/protocol.h>
+#include <net/xfrm.h>
+
+static struct xfrm6_protocol __rcu *esp6_handlers __read_mostly;
+static struct xfrm6_protocol __rcu *ah6_handlers __read_mostly;
+static struct xfrm6_protocol __rcu *ipcomp6_handlers __read_mostly;
+static DEFINE_MUTEX(xfrm6_protocol_mutex);
+
+static inline struct xfrm6_protocol __rcu **proto_handlers(u8 protocol)
+{
+ switch (protocol) {
+ case IPPROTO_ESP:
+ return &esp6_handlers;
+ case IPPROTO_AH:
+ return &ah6_handlers;
+ case IPPROTO_COMP:
+ return &ipcomp6_handlers;
+ }
+
+ return NULL;
+}
+
+#define for_each_protocol_rcu(head, handler) \
+ for (handler = rcu_dereference(head); \
+ handler != NULL; \
+ handler = rcu_dereference(handler->next)) \
+
+int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
+{
+ int ret;
+ struct xfrm6_protocol *handler;
+
+ for_each_protocol_rcu(*proto_handlers(protocol), handler)
+ if ((ret = handler->cb_handler(skb, err)) <= 0)
+ return ret;
+
+ return 0;
+}
+EXPORT_SYMBOL(xfrm6_rcv_cb);
+
+static int xfrm6_esp_rcv(struct sk_buff *skb)
+{
+ int ret;
+ struct xfrm6_protocol *handler;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
+
+ for_each_protocol_rcu(esp6_handlers, handler)
+ if ((ret = handler->handler(skb)) != -EINVAL)
+ return ret;
+
+ icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
+
+ kfree_skb(skb);
+ return 0;
+}
+
+static void xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info)
+{
+ struct xfrm6_protocol *handler;
+
+ for_each_protocol_rcu(esp6_handlers, handler)
+ if (!handler->err_handler(skb, opt, type, code, offset, info))
+ break;
+}
+
+static int xfrm6_ah_rcv(struct sk_buff *skb)
+{
+ int ret;
+ struct xfrm6_protocol *handler;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
+
+ for_each_protocol_rcu(ah6_handlers, handler)
+ if ((ret = handler->handler(skb)) != -EINVAL)
+ return ret;
+
+ icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
+
+ kfree_skb(skb);
+ return 0;
+}
+
+static void xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info)
+{
+ struct xfrm6_protocol *handler;
+
+ for_each_protocol_rcu(ah6_handlers, handler)
+ if (!handler->err_handler(skb, opt, type, code, offset, info))
+ break;
+}
+
+static int xfrm6_ipcomp_rcv(struct sk_buff *skb)
+{
+ int ret;
+ struct xfrm6_protocol *handler;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
+
+ for_each_protocol_rcu(ipcomp6_handlers, handler)
+ if ((ret = handler->handler(skb)) != -EINVAL)
+ return ret;
+
+ icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
+
+ kfree_skb(skb);
+ return 0;
+}
+
+static void xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info)
+{
+ struct xfrm6_protocol *handler;
+
+ for_each_protocol_rcu(ipcomp6_handlers, handler)
+ if (!handler->err_handler(skb, opt, type, code, offset, info))
+ break;
+}
+
+static const struct inet6_protocol esp6_protocol = {
+ .handler = xfrm6_esp_rcv,
+ .err_handler = xfrm6_esp_err,
+ .flags = INET6_PROTO_NOPOLICY,
+};
+
+static const struct inet6_protocol ah6_protocol = {
+ .handler = xfrm6_ah_rcv,
+ .err_handler = xfrm6_ah_err,
+ .flags = INET6_PROTO_NOPOLICY,
+};
+
+static const struct inet6_protocol ipcomp6_protocol = {
+ .handler = xfrm6_ipcomp_rcv,
+ .err_handler = xfrm6_ipcomp_err,
+ .flags = INET6_PROTO_NOPOLICY,
+};
+
+static struct xfrm_input_afinfo xfrm6_input_afinfo = {
+ .family = AF_INET6,
+ .owner = THIS_MODULE,
+ .callback = xfrm6_rcv_cb,
+};
+
+static inline const struct inet6_protocol *netproto(unsigned char protocol)
+{
+ switch (protocol) {
+ case IPPROTO_ESP:
+ return &esp6_protocol;
+ case IPPROTO_AH:
+ return &ah6_protocol;
+ case IPPROTO_COMP:
+ return &ipcomp6_protocol;
+ }
+
+ return NULL;
+}
+
+int xfrm6_protocol_register(struct xfrm6_protocol *handler,
+ unsigned char protocol)
+{
+ struct xfrm6_protocol __rcu **pprev;
+ struct xfrm6_protocol *t;
+ bool add_netproto = false;
+
+ int ret = -EEXIST;
+ int priority = handler->priority;
+
+ mutex_lock(&xfrm6_protocol_mutex);
+
+ if (!rcu_dereference_protected(*proto_handlers(protocol),
+ lockdep_is_held(&xfrm6_protocol_mutex)))
+ add_netproto = true;
+
+ for (pprev = proto_handlers(protocol);
+ (t = rcu_dereference_protected(*pprev,
+ lockdep_is_held(&xfrm6_protocol_mutex))) != NULL;
+ pprev = &t->next) {
+ if (t->priority < priority)
+ break;
+ if (t->priority == priority)
+ goto err;
+ }
+
+ handler->next = *pprev;
+ rcu_assign_pointer(*pprev, handler);
+
+ ret = 0;
+
+err:
+ mutex_unlock(&xfrm6_protocol_mutex);
+
+ if (add_netproto) {
+ if (inet6_add_protocol(netproto(protocol), protocol)) {
+ pr_err("%s: can't add protocol\n", __func__);
+ ret = -EAGAIN;
+ }
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(xfrm6_protocol_register);
+
+int xfrm6_protocol_deregister(struct xfrm6_protocol *handler,
+ unsigned char protocol)
+{
+ struct xfrm6_protocol __rcu **pprev;
+ struct xfrm6_protocol *t;
+ int ret = -ENOENT;
+
+ mutex_lock(&xfrm6_protocol_mutex);
+
+ for (pprev = proto_handlers(protocol);
+ (t = rcu_dereference_protected(*pprev,
+ lockdep_is_held(&xfrm6_protocol_mutex))) != NULL;
+ pprev = &t->next) {
+ if (t == handler) {
+ *pprev = handler->next;
+ ret = 0;
+ break;
+ }
+ }
+
+ if (!rcu_dereference_protected(*proto_handlers(protocol),
+ lockdep_is_held(&xfrm6_protocol_mutex))) {
+ if (inet6_del_protocol(netproto(protocol), protocol) < 0) {
+ pr_err("%s: can't remove protocol\n", __func__);
+ ret = -EAGAIN;
+ }
+ }
+
+ mutex_unlock(&xfrm6_protocol_mutex);
+
+ synchronize_net();
+
+ return ret;
+}
+EXPORT_SYMBOL(xfrm6_protocol_deregister);
+
+int __init xfrm6_protocol_init(void)
+{
+ return xfrm_input_register_afinfo(&xfrm6_input_afinfo);
+}
+
+void xfrm6_protocol_fini(void)
+{
+ xfrm_input_unregister_afinfo(&xfrm6_input_afinfo);
+}
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 994e28b..41e4e93 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -52,18 +52,12 @@
#include <net/p8022.h>
#include <net/psnap.h>
#include <net/sock.h>
+#include <net/datalink.h>
#include <net/tcp_states.h>
+#include <net/net_namespace.h>
#include <asm/uaccess.h>
-#ifdef CONFIG_SYSCTL
-extern void ipx_register_sysctl(void);
-extern void ipx_unregister_sysctl(void);
-#else
-#define ipx_register_sysctl()
-#define ipx_unregister_sysctl()
-#endif
-
/* Configuration Variables */
static unsigned char ipxcfg_max_hops = 16;
static char ipxcfg_auto_select_primary;
@@ -84,15 +78,6 @@
struct ipx_interface *ipx_primary_net;
struct ipx_interface *ipx_internal_net;
-extern int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc,
- unsigned char *node);
-extern void ipxrtr_del_routes(struct ipx_interface *intrfc);
-extern int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx,
- struct iovec *iov, size_t len, int noblock);
-extern int ipxrtr_route_skb(struct sk_buff *skb);
-extern struct ipx_route *ipxrtr_lookup(__be32 net);
-extern int ipxrtr_ioctl(unsigned int cmd, void __user *arg);
-
struct ipx_interface *ipx_interfaces_head(void)
{
struct ipx_interface *rc = NULL;
@@ -1383,6 +1368,7 @@
goto out;
lock_sock(sk);
+ sk->sk_shutdown = SHUTDOWN_MASK;
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_state_change(sk);
@@ -1806,8 +1792,11 @@
skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
flags & MSG_DONTWAIT, &rc);
- if (!skb)
+ if (!skb) {
+ if (rc == -EAGAIN && (sk->sk_shutdown & RCV_SHUTDOWN))
+ rc = 0;
goto out;
+ }
ipx = ipx_hdr(skb);
copied = ntohs(ipx->ipx_pktsize) - sizeof(struct ipxhdr);
@@ -1937,6 +1926,26 @@
}
#endif
+static int ipx_shutdown(struct socket *sock, int mode)
+{
+ struct sock *sk = sock->sk;
+
+ if (mode < SHUT_RD || mode > SHUT_RDWR)
+ return -EINVAL;
+ /* This maps:
+ * SHUT_RD (0) -> RCV_SHUTDOWN (1)
+ * SHUT_WR (1) -> SEND_SHUTDOWN (2)
+ * SHUT_RDWR (2) -> SHUTDOWN_MASK (3)
+ */
+ ++mode;
+
+ lock_sock(sk);
+ sk->sk_shutdown |= mode;
+ release_sock(sk);
+ sk->sk_state_change(sk);
+
+ return 0;
+}
/*
* Socket family declarations
@@ -1963,7 +1972,7 @@
.compat_ioctl = ipx_compat_ioctl,
#endif
.listen = sock_no_listen,
- .shutdown = sock_no_shutdown, /* FIXME: support shutdown */
+ .shutdown = ipx_shutdown,
.setsockopt = ipx_setsockopt,
.getsockopt = ipx_getsockopt,
.sendmsg = ipx_sendmsg,
@@ -1986,9 +1995,6 @@
.notifier_call = ipxitf_device_event,
};
-extern struct datalink_proto *make_EII_client(void);
-extern void destroy_EII_client(struct datalink_proto *);
-
static const unsigned char ipx_8022_type = 0xE0;
static const unsigned char ipx_snap_id[5] = { 0x0, 0x0, 0x0, 0x81, 0x37 };
static const char ipx_EII_err_msg[] __initconst =
diff --git a/net/ipx/ipx_route.c b/net/ipx/ipx_route.c
index 30f4519..c1f0318 100644
--- a/net/ipx/ipx_route.c
+++ b/net/ipx/ipx_route.c
@@ -20,15 +20,11 @@
extern struct ipx_interface *ipx_internal_net;
-extern __be16 ipx_cksum(struct ipxhdr *packet, int length);
extern struct ipx_interface *ipxitf_find_using_net(__be32 net);
extern int ipxitf_demux_socket(struct ipx_interface *intrfc,
struct sk_buff *skb, int copy);
extern int ipxitf_demux_socket(struct ipx_interface *intrfc,
struct sk_buff *skb, int copy);
-extern int ipxitf_send(struct ipx_interface *intrfc, struct sk_buff *skb,
- char *node);
-extern struct ipx_interface *ipxitf_find_using_net(__be32 net);
struct ipx_route *ipxrtr_lookup(__be32 net)
{
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index c4b7218..a5e0311 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1382,6 +1382,7 @@
if (sk->sk_type == SOCK_STREAM) {
if (copied < rlen) {
IUCV_SKB_CB(skb)->offset = offset + copied;
+ skb_queue_head(&sk->sk_receive_queue, skb);
goto done;
}
}
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 1a04c13..e72589a 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -365,6 +365,7 @@
[SADB_X_EXT_NAT_T_OA] = (u8) sizeof(struct sadb_address),
[SADB_X_EXT_SEC_CTX] = (u8) sizeof(struct sadb_x_sec_ctx),
[SADB_X_EXT_KMADDRESS] = (u8) sizeof(struct sadb_x_kmaddress),
+ [SADB_X_EXT_FILTER] = (u8) sizeof(struct sadb_x_filter),
};
/* Verify sadb_address_{len,prefixlen} against sa_family. */
@@ -433,12 +434,13 @@
return 0;
}
-static inline struct xfrm_user_sec_ctx *pfkey_sadb2xfrm_user_sec_ctx(const struct sadb_x_sec_ctx *sec_ctx)
+static inline struct xfrm_user_sec_ctx *pfkey_sadb2xfrm_user_sec_ctx(const struct sadb_x_sec_ctx *sec_ctx,
+ gfp_t gfp)
{
struct xfrm_user_sec_ctx *uctx = NULL;
int ctx_size = sec_ctx->sadb_x_ctx_len;
- uctx = kmalloc((sizeof(*uctx)+ctx_size), GFP_KERNEL);
+ uctx = kmalloc((sizeof(*uctx)+ctx_size), gfp);
if (!uctx)
return NULL;
@@ -1124,7 +1126,7 @@
sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1];
if (sec_ctx != NULL) {
- struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx);
+ struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL);
if (!uctx)
goto out;
@@ -1798,6 +1800,7 @@
static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs)
{
u8 proto;
+ struct xfrm_address_filter *filter = NULL;
struct pfkey_sock *pfk = pfkey_sk(sk);
if (pfk->dump.dump != NULL)
@@ -1807,11 +1810,27 @@
if (proto == 0)
return -EINVAL;
+ if (ext_hdrs[SADB_X_EXT_FILTER - 1]) {
+ struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1];
+
+ filter = kmalloc(sizeof(*filter), GFP_KERNEL);
+ if (filter == NULL)
+ return -ENOMEM;
+
+ memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr,
+ sizeof(xfrm_address_t));
+ memcpy(&filter->daddr, &xfilter->sadb_x_filter_daddr,
+ sizeof(xfrm_address_t));
+ filter->family = xfilter->sadb_x_filter_family;
+ filter->splen = xfilter->sadb_x_filter_splen;
+ filter->dplen = xfilter->sadb_x_filter_dplen;
+ }
+
pfk->dump.msg_version = hdr->sadb_msg_version;
pfk->dump.msg_portid = hdr->sadb_msg_pid;
pfk->dump.dump = pfkey_dump_sa;
pfk->dump.done = pfkey_dump_sa_done;
- xfrm_state_walk_init(&pfk->dump.u.state, proto);
+ xfrm_state_walk_init(&pfk->dump.u.state, proto, filter);
return pfkey_do_dump(pfk);
}
@@ -2231,14 +2250,14 @@
sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1];
if (sec_ctx != NULL) {
- struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx);
+ struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL);
if (!uctx) {
err = -ENOBUFS;
goto out;
}
- err = security_xfrm_policy_alloc(&xp->security, uctx);
+ err = security_xfrm_policy_alloc(&xp->security, uctx, GFP_KERNEL);
kfree(uctx);
if (err)
@@ -2335,12 +2354,12 @@
sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1];
if (sec_ctx != NULL) {
- struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx);
+ struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL);
if (!uctx)
return -ENOMEM;
- err = security_xfrm_policy_alloc(&pol_ctx, uctx);
+ err = security_xfrm_policy_alloc(&pol_ctx, uctx, GFP_KERNEL);
kfree(uctx);
if (err)
return err;
@@ -3059,6 +3078,24 @@
return res;
}
+static bool pfkey_is_alive(const struct km_event *c)
+{
+ struct netns_pfkey *net_pfkey = net_generic(c->net, pfkey_net_id);
+ struct sock *sk;
+ bool is_alive = false;
+
+ rcu_read_lock();
+ sk_for_each_rcu(sk, &net_pfkey->table) {
+ if (pfkey_sk(sk)->registered) {
+ is_alive = true;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return is_alive;
+}
+
static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *xp)
{
struct sk_buff *skb;
@@ -3239,8 +3276,8 @@
}
if ((*dir = verify_sec_ctx_len(p)))
goto out;
- uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx);
- *dir = security_xfrm_policy_alloc(&xp->security, uctx);
+ uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_ATOMIC);
+ *dir = security_xfrm_policy_alloc(&xp->security, uctx, GFP_ATOMIC);
kfree(uctx);
if (*dir)
@@ -3784,6 +3821,7 @@
.new_mapping = pfkey_send_new_mapping,
.notify_policy = pfkey_send_policy_notify,
.migrate = pfkey_send_migrate,
+ .is_alive = pfkey_is_alive,
};
static int __net_init pfkey_net_init(struct net *net)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 735d0f6..ab48d41 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -112,7 +112,6 @@
spinlock_t l2tp_session_hlist_lock;
};
-static void l2tp_session_set_header_len(struct l2tp_session *session, int version);
static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk)
@@ -1131,7 +1130,7 @@
/* Queue the packet to IP for output */
skb->local_df = 1;
#if IS_ENABLED(CONFIG_IPV6)
- if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped)
+ if (tunnel->sock->sk_family == PF_INET6 && !tunnel->v4mapped)
error = inet6_csk_xmit(skb, NULL);
else
#endif
@@ -1151,23 +1150,6 @@
return 0;
}
-/* Automatically called when the skb is freed.
- */
-static void l2tp_sock_wfree(struct sk_buff *skb)
-{
- sock_put(skb->sk);
-}
-
-/* For data skbs that we transmit, we associate with the tunnel socket
- * but don't do accounting.
- */
-static inline void l2tp_skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
-{
- sock_hold(sk);
- skb->sk = sk;
- skb->destructor = l2tp_sock_wfree;
-}
-
#if IS_ENABLED(CONFIG_IPV6)
static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb,
int udp_len)
@@ -1221,7 +1203,6 @@
return NET_XMIT_DROP;
}
- skb_orphan(skb);
/* Setup L2TP header */
session->build_header(session, __skb_push(skb, hdr_len));
@@ -1287,8 +1268,6 @@
break;
}
- l2tp_skb_set_owner_w(skb, sk);
-
l2tp_xmit_core(session, skb, fl, data_len);
out_unlock:
bh_unlock_sock(sk);
@@ -1809,8 +1788,6 @@
}
kfree(session);
-
- return;
}
EXPORT_SYMBOL_GPL(l2tp_session_free);
@@ -1863,7 +1840,7 @@
/* We come here whenever a session's send_seq, cookie_len or
* l2specific_len parameters are set.
*/
-static void l2tp_session_set_header_len(struct l2tp_session *session, int version)
+void l2tp_session_set_header_len(struct l2tp_session *session, int version)
{
if (version == L2TP_HDR_VER_2) {
session->hdr_len = 6;
@@ -1876,6 +1853,7 @@
}
}
+EXPORT_SYMBOL_GPL(l2tp_session_set_header_len);
struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
{
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 1f01ba3..3f93ccd 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -263,6 +263,7 @@
int length, int (*payload_hook)(struct sk_buff *skb));
int l2tp_session_queue_purge(struct l2tp_session *session);
int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
+void l2tp_session_set_header_len(struct l2tp_session *session, int version);
int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb,
int hdr_len);
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 4cfd722..bd7387a 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -578,8 +578,10 @@
if (info->attrs[L2TP_ATTR_RECV_SEQ])
session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]);
- if (info->attrs[L2TP_ATTR_SEND_SEQ])
+ if (info->attrs[L2TP_ATTR_SEND_SEQ]) {
session->send_seq = nla_get_u8(info->attrs[L2TP_ATTR_SEND_SEQ]);
+ l2tp_session_set_header_len(session, session->tunnel->version);
+ }
if (info->attrs[L2TP_ATTR_LNS_MODE])
session->lns_mode = nla_get_u8(info->attrs[L2TP_ATTR_LNS_MODE]);
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index be5fadf..d276e2d 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -254,12 +254,14 @@
po = pppox_sk(sk);
ppp_input(&po->chan, skb);
} else {
- l2tp_info(session, PPPOL2TP_MSG_DATA, "%s: socket not bound\n",
- session->name);
+ l2tp_dbg(session, PPPOL2TP_MSG_DATA,
+ "%s: recv %d byte data frame, passing to L2TP socket\n",
+ session->name, data_len);
- /* Not bound. Nothing we can do, so discard. */
- atomic_long_inc(&session->stats.rx_errors);
- kfree_skb(skb);
+ if (sock_queue_rcv_skb(sk, skb) < 0) {
+ atomic_long_inc(&session->stats.rx_errors);
+ kfree_skb(skb);
+ }
}
return;
@@ -454,13 +456,11 @@
BUG_ON(session->magic != L2TP_SESSION_MAGIC);
-
if (sock) {
inet_shutdown(sock, 2);
/* Don't let the session go away before our socket does */
l2tp_session_inc_refcount(session);
}
- return;
}
/* Really kill the session socket. (Called from sock_put() if
@@ -474,7 +474,6 @@
BUG_ON(session->magic != L2TP_SESSION_MAGIC);
l2tp_session_dec_refcount(session);
}
- return;
}
/* Called when the PPPoX socket (session) is closed.
@@ -1312,6 +1311,7 @@
po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ :
PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
}
+ l2tp_session_set_header_len(session, session->tunnel->version);
l2tp_info(session, PPPOL2TP_MSG_CONTROL,
"%s: set send_seq=%d\n",
session->name, session->send_seq);
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 42c6592..bd1fd8e 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -100,6 +100,12 @@
}
max_bw = max(max_bw, width);
}
+
+ /* use the configured bandwidth in case of monitor interface */
+ sdata = rcu_dereference(local->monitor_sdata);
+ if (sdata && rcu_access_pointer(sdata->vif.chanctx_conf) == conf)
+ max_bw = max(max_bw, conf->def.width);
+
rcu_read_unlock();
return max_bw;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index be198f4..b8d331e 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1054,7 +1054,8 @@
static u16 ieee80211_netdev_select_queue(struct net_device *dev,
struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv,
+ select_queue_fallback_t fallback)
{
return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
}
@@ -1072,7 +1073,8 @@
static u16 ieee80211_monitor_select_queue(struct net_device *dev,
struct sk_buff *skb,
- void *accel_priv)
+ void *accel_priv,
+ select_queue_fallback_t fallback)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
struct ieee80211_local *local = sdata->local;
diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c
index 2802f9d..ad8b377 100644
--- a/net/mac80211/mesh_ps.c
+++ b/net/mac80211/mesh_ps.c
@@ -36,6 +36,7 @@
sdata->vif.addr);
nullfunc->frame_control = fc;
nullfunc->duration_id = 0;
+ nullfunc->seq_ctrl = 0;
/* no address resolution for this frame -> set addr 1 immediately */
memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN);
memset(skb_put(skb, 2), 0, 2); /* append QoS control field */
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index a023b43..137a192 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1206,6 +1206,7 @@
memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN);
memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN);
memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN);
+ nullfunc->seq_ctrl = 0;
skb->priority = tid;
skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]);
diff --git a/net/mac802154/Makefile b/net/mac802154/Makefile
index 57cf5d1..15d62df5 100644
--- a/net/mac802154/Makefile
+++ b/net/mac802154/Makefile
@@ -1,2 +1,4 @@
obj-$(CONFIG_MAC802154) += mac802154.o
mac802154-objs := ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o monitor.o wpan.o
+
+ccflags-y += -D__CHECK_ENDIAN__
diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c
index 52ae664..10cdb09 100644
--- a/net/mac802154/ieee802154_dev.c
+++ b/net/mac802154/ieee802154_dev.c
@@ -27,6 +27,7 @@
#include <net/netlink.h>
#include <linux/nl802154.h>
#include <net/mac802154.h>
+#include <net/ieee802154_netdev.h>
#include <net/route.h>
#include <net/wpan-phy.h>
@@ -46,7 +47,9 @@
}
if (ipriv->ops->ieee_addr) {
- res = ipriv->ops->ieee_addr(&ipriv->hw, dev->dev_addr);
+ __le64 addr = ieee802154_devaddr_from_raw(dev->dev_addr);
+
+ res = ipriv->ops->ieee_addr(&ipriv->hw, addr);
WARN_ON(res);
if (res)
goto err;
@@ -165,6 +168,67 @@
return ERR_PTR(err);
}
+static int mac802154_set_txpower(struct wpan_phy *phy, int db)
+{
+ struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+ if (!priv->ops->set_txpower)
+ return -ENOTSUPP;
+
+ return priv->ops->set_txpower(&priv->hw, db);
+}
+
+static int mac802154_set_lbt(struct wpan_phy *phy, bool on)
+{
+ struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+ if (!priv->ops->set_lbt)
+ return -ENOTSUPP;
+
+ return priv->ops->set_lbt(&priv->hw, on);
+}
+
+static int mac802154_set_cca_mode(struct wpan_phy *phy, u8 mode)
+{
+ struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+ if (!priv->ops->set_cca_mode)
+ return -ENOTSUPP;
+
+ return priv->ops->set_cca_mode(&priv->hw, mode);
+}
+
+static int mac802154_set_cca_ed_level(struct wpan_phy *phy, s32 level)
+{
+ struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+ if (!priv->ops->set_cca_ed_level)
+ return -ENOTSUPP;
+
+ return priv->ops->set_cca_ed_level(&priv->hw, level);
+}
+
+static int mac802154_set_csma_params(struct wpan_phy *phy, u8 min_be,
+ u8 max_be, u8 retries)
+{
+ struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+ if (!priv->ops->set_csma_params)
+ return -ENOTSUPP;
+
+ return priv->ops->set_csma_params(&priv->hw, min_be, max_be, retries);
+}
+
+static int mac802154_set_frame_retries(struct wpan_phy *phy, s8 retries)
+{
+ struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+ if (!priv->ops->set_frame_retries)
+ return -ENOTSUPP;
+
+ return priv->ops->set_frame_retries(&priv->hw, retries);
+}
+
struct ieee802154_dev *
ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops)
{
@@ -242,6 +306,12 @@
priv->phy->add_iface = mac802154_add_iface;
priv->phy->del_iface = mac802154_del_iface;
+ priv->phy->set_txpower = mac802154_set_txpower;
+ priv->phy->set_lbt = mac802154_set_lbt;
+ priv->phy->set_cca_mode = mac802154_set_cca_mode;
+ priv->phy->set_cca_ed_level = mac802154_set_cca_ed_level;
+ priv->phy->set_csma_params = mac802154_set_csma_params;
+ priv->phy->set_frame_retries = mac802154_set_frame_retries;
rc = wpan_phy_register(priv->phy);
if (rc < 0)
diff --git a/net/mac802154/mac802154.h b/net/mac802154/mac802154.h
index d48422e..4619486 100644
--- a/net/mac802154/mac802154.h
+++ b/net/mac802154/mac802154.h
@@ -76,6 +76,7 @@
__le16 pan_id;
__le16 short_addr;
+ __le64 extended_addr;
u8 chan;
u8 page;
@@ -106,11 +107,11 @@
u8 page, u8 chan);
/* MIB callbacks */
-void mac802154_dev_set_short_addr(struct net_device *dev, u16 val);
-u16 mac802154_dev_get_short_addr(const struct net_device *dev);
+void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val);
+__le16 mac802154_dev_get_short_addr(const struct net_device *dev);
void mac802154_dev_set_ieee_addr(struct net_device *dev);
-u16 mac802154_dev_get_pan_id(const struct net_device *dev);
-void mac802154_dev_set_pan_id(struct net_device *dev, u16 val);
+__le16 mac802154_dev_get_pan_id(const struct net_device *dev);
+void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val);
void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan);
u8 mac802154_dev_get_dsn(const struct net_device *dev);
diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c
index a99910d..15bac33 100644
--- a/net/mac802154/mac_cmd.c
+++ b/net/mac802154/mac_cmd.c
@@ -40,7 +40,7 @@
u8 pan_coord, u8 blx,
u8 coord_realign)
{
- BUG_ON(addr->addr_type != IEEE802154_ADDR_SHORT);
+ BUG_ON(addr->mode != IEEE802154_ADDR_SHORT);
mac802154_dev_set_pan_id(dev, addr->pan_id);
mac802154_dev_set_short_addr(dev, addr->short_addr);
diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c
index 8ded97c..153bd1d 100644
--- a/net/mac802154/mib.c
+++ b/net/mac802154/mib.c
@@ -24,7 +24,9 @@
#include <linux/if_arp.h>
#include <net/mac802154.h>
+#include <net/ieee802154_netdev.h>
#include <net/wpan-phy.h>
+#include <net/ieee802154_netdev.h>
#include "mac802154.h"
@@ -62,8 +64,6 @@
pr_debug("failed changed mask %lx\n", nw->changed);
kfree(nw);
-
- return;
}
static void set_hw_addr_filt(struct net_device *dev, unsigned long changed)
@@ -79,11 +79,9 @@
work->dev = dev;
work->changed = changed;
queue_work(priv->hw->dev_workqueue, &work->work);
-
- return;
}
-void mac802154_dev_set_short_addr(struct net_device *dev, u16 val)
+void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val)
{
struct mac802154_sub_if_data *priv = netdev_priv(dev);
@@ -100,10 +98,10 @@
}
}
-u16 mac802154_dev_get_short_addr(const struct net_device *dev)
+__le16 mac802154_dev_get_short_addr(const struct net_device *dev)
{
struct mac802154_sub_if_data *priv = netdev_priv(dev);
- u16 ret;
+ __le16 ret;
BUG_ON(dev->type != ARPHRD_IEEE802154);
@@ -119,19 +117,19 @@
struct mac802154_sub_if_data *priv = netdev_priv(dev);
struct mac802154_priv *mac = priv->hw;
+ priv->extended_addr = ieee802154_devaddr_from_raw(dev->dev_addr);
+
if (mac->ops->set_hw_addr_filt &&
- memcmp(mac->hw.hw_filt.ieee_addr,
- dev->dev_addr, IEEE802154_ADDR_LEN)) {
- memcpy(mac->hw.hw_filt.ieee_addr,
- dev->dev_addr, IEEE802154_ADDR_LEN);
+ mac->hw.hw_filt.ieee_addr != priv->extended_addr) {
+ mac->hw.hw_filt.ieee_addr = priv->extended_addr;
set_hw_addr_filt(dev, IEEE802515_AFILT_IEEEADDR_CHANGED);
}
}
-u16 mac802154_dev_get_pan_id(const struct net_device *dev)
+__le16 mac802154_dev_get_pan_id(const struct net_device *dev)
{
struct mac802154_sub_if_data *priv = netdev_priv(dev);
- u16 ret;
+ __le16 ret;
BUG_ON(dev->type != ARPHRD_IEEE802154);
@@ -142,7 +140,7 @@
return ret;
}
-void mac802154_dev_set_pan_id(struct net_device *dev, u16 val)
+void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val)
{
struct mac802154_sub_if_data *priv = netdev_priv(dev);
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index 38548ec..03855b0 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -80,7 +80,6 @@
mac802154_wpans_rx(priv, skb);
out:
dev_kfree_skb(skb);
- return;
}
static void mac802154_rx_worker(struct work_struct *work)
diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c
index 372d8a2..80cbee1 100644
--- a/net/mac802154/wpan.c
+++ b/net/mac802154/wpan.c
@@ -35,35 +35,6 @@
#include "mac802154.h"
-static inline int mac802154_fetch_skb_u8(struct sk_buff *skb, u8 *val)
-{
- if (unlikely(!pskb_may_pull(skb, 1)))
- return -EINVAL;
-
- *val = skb->data[0];
- skb_pull(skb, 1);
-
- return 0;
-}
-
-static inline int mac802154_fetch_skb_u16(struct sk_buff *skb, u16 *val)
-{
- if (unlikely(!pskb_may_pull(skb, 2)))
- return -EINVAL;
-
- *val = skb->data[0] | (skb->data[1] << 8);
- skb_pull(skb, 2);
-
- return 0;
-}
-
-static inline void mac802154_haddr_copy_swap(u8 *dest, const u8 *src)
-{
- int i;
- for (i = 0; i < IEEE802154_ADDR_LEN; i++)
- dest[IEEE802154_ADDR_LEN - i - 1] = src[i];
-}
-
static int
mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
@@ -76,19 +47,25 @@
switch (cmd) {
case SIOCGIFADDR:
- if (priv->pan_id == IEEE802154_PANID_BROADCAST ||
- priv->short_addr == IEEE802154_ADDR_BROADCAST) {
+ {
+ u16 pan_id, short_addr;
+
+ pan_id = le16_to_cpu(priv->pan_id);
+ short_addr = le16_to_cpu(priv->short_addr);
+ if (pan_id == IEEE802154_PANID_BROADCAST ||
+ short_addr == IEEE802154_ADDR_BROADCAST) {
err = -EADDRNOTAVAIL;
break;
}
sa->family = AF_IEEE802154;
sa->addr.addr_type = IEEE802154_ADDR_SHORT;
- sa->addr.pan_id = priv->pan_id;
- sa->addr.short_addr = priv->short_addr;
+ sa->addr.pan_id = pan_id;
+ sa->addr.short_addr = short_addr;
err = 0;
break;
+ }
case SIOCSIFADDR:
dev_warn(&dev->dev,
"Using DEBUGing ioctl SIOCSIFADDR isn't recommened!\n");
@@ -101,8 +78,8 @@
break;
}
- priv->pan_id = sa->addr.pan_id;
- priv->short_addr = sa->addr.short_addr;
+ priv->pan_id = cpu_to_le16(sa->addr.pan_id);
+ priv->short_addr = cpu_to_le16(sa->addr.short_addr);
err = 0;
break;
@@ -128,187 +105,70 @@
static int mac802154_header_create(struct sk_buff *skb,
struct net_device *dev,
unsigned short type,
- const void *_daddr,
- const void *_saddr,
+ const void *daddr,
+ const void *saddr,
unsigned len)
{
- const struct ieee802154_addr *saddr = _saddr;
- const struct ieee802154_addr *daddr = _daddr;
- struct ieee802154_addr dev_addr;
+ struct ieee802154_hdr hdr;
struct mac802154_sub_if_data *priv = netdev_priv(dev);
- int pos = 2;
- u8 head[MAC802154_FRAME_HARD_HEADER_LEN];
- u16 fc;
+ int hlen;
if (!daddr)
return -EINVAL;
- head[pos++] = mac_cb(skb)->seq; /* DSN/BSN */
- fc = mac_cb_type(skb);
- if (mac_cb_is_ackreq(skb))
- fc |= IEEE802154_FC_ACK_REQ;
+ memset(&hdr.fc, 0, sizeof(hdr.fc));
+ hdr.fc.type = mac_cb_type(skb);
+ hdr.fc.security_enabled = mac_cb_is_secen(skb);
+ hdr.fc.ack_request = mac_cb_is_ackreq(skb);
if (!saddr) {
spin_lock_bh(&priv->mib_lock);
- if (priv->short_addr == IEEE802154_ADDR_BROADCAST ||
- priv->short_addr == IEEE802154_ADDR_UNDEF ||
- priv->pan_id == IEEE802154_PANID_BROADCAST) {
- dev_addr.addr_type = IEEE802154_ADDR_LONG;
- memcpy(dev_addr.hwaddr, dev->dev_addr,
- IEEE802154_ADDR_LEN);
+ if (priv->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST) ||
+ priv->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) ||
+ priv->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) {
+ hdr.source.mode = IEEE802154_ADDR_LONG;
+ hdr.source.extended_addr = priv->extended_addr;
} else {
- dev_addr.addr_type = IEEE802154_ADDR_SHORT;
- dev_addr.short_addr = priv->short_addr;
+ hdr.source.mode = IEEE802154_ADDR_SHORT;
+ hdr.source.short_addr = priv->short_addr;
}
- dev_addr.pan_id = priv->pan_id;
- saddr = &dev_addr;
+ hdr.source.pan_id = priv->pan_id;
spin_unlock_bh(&priv->mib_lock);
+ } else {
+ hdr.source = *(const struct ieee802154_addr *)saddr;
}
- if (daddr->addr_type != IEEE802154_ADDR_NONE) {
- fc |= (daddr->addr_type << IEEE802154_FC_DAMODE_SHIFT);
+ hdr.dest = *(const struct ieee802154_addr *)daddr;
- head[pos++] = daddr->pan_id & 0xff;
- head[pos++] = daddr->pan_id >> 8;
+ hlen = ieee802154_hdr_push(skb, &hdr);
+ if (hlen < 0)
+ return -EINVAL;
- if (daddr->addr_type == IEEE802154_ADDR_SHORT) {
- head[pos++] = daddr->short_addr & 0xff;
- head[pos++] = daddr->short_addr >> 8;
- } else {
- mac802154_haddr_copy_swap(head + pos, daddr->hwaddr);
- pos += IEEE802154_ADDR_LEN;
- }
- }
-
- if (saddr->addr_type != IEEE802154_ADDR_NONE) {
- fc |= (saddr->addr_type << IEEE802154_FC_SAMODE_SHIFT);
-
- if ((saddr->pan_id == daddr->pan_id) &&
- (saddr->pan_id != IEEE802154_PANID_BROADCAST)) {
- /* PANID compression/intra PAN */
- fc |= IEEE802154_FC_INTRA_PAN;
- } else {
- head[pos++] = saddr->pan_id & 0xff;
- head[pos++] = saddr->pan_id >> 8;
- }
-
- if (saddr->addr_type == IEEE802154_ADDR_SHORT) {
- head[pos++] = saddr->short_addr & 0xff;
- head[pos++] = saddr->short_addr >> 8;
- } else {
- mac802154_haddr_copy_swap(head + pos, saddr->hwaddr);
- pos += IEEE802154_ADDR_LEN;
- }
- }
-
- head[0] = fc;
- head[1] = fc >> 8;
-
- memcpy(skb_push(skb, pos), head, pos);
skb_reset_mac_header(skb);
- skb->mac_len = pos;
+ skb->mac_len = hlen;
- return pos;
+ if (hlen + len + 2 > dev->mtu)
+ return -EMSGSIZE;
+
+ return hlen;
}
static int
mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr)
{
- const u8 *hdr = skb_mac_header(skb);
- const u8 *tail = skb_tail_pointer(skb);
+ struct ieee802154_hdr hdr;
struct ieee802154_addr *addr = (struct ieee802154_addr *)haddr;
- u16 fc;
- int da_type;
- if (hdr + 3 > tail)
- goto malformed;
-
- fc = hdr[0] | (hdr[1] << 8);
-
- hdr += 3;
-
- da_type = IEEE802154_FC_DAMODE(fc);
- addr->addr_type = IEEE802154_FC_SAMODE(fc);
-
- switch (da_type) {
- case IEEE802154_ADDR_NONE:
- if (fc & IEEE802154_FC_INTRA_PAN)
- goto malformed;
- break;
- case IEEE802154_ADDR_LONG:
- if (fc & IEEE802154_FC_INTRA_PAN) {
- if (hdr + 2 > tail)
- goto malformed;
- addr->pan_id = hdr[0] | (hdr[1] << 8);
- hdr += 2;
- }
-
- if (hdr + IEEE802154_ADDR_LEN > tail)
- goto malformed;
-
- hdr += IEEE802154_ADDR_LEN;
- break;
- case IEEE802154_ADDR_SHORT:
- if (fc & IEEE802154_FC_INTRA_PAN) {
- if (hdr + 2 > tail)
- goto malformed;
- addr->pan_id = hdr[0] | (hdr[1] << 8);
- hdr += 2;
- }
-
- if (hdr + 2 > tail)
- goto malformed;
-
- hdr += 2;
- break;
- default:
- goto malformed;
-
+ if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) {
+ pr_debug("malformed packet\n");
+ return 0;
}
- switch (addr->addr_type) {
- case IEEE802154_ADDR_NONE:
- break;
- case IEEE802154_ADDR_LONG:
- if (!(fc & IEEE802154_FC_INTRA_PAN)) {
- if (hdr + 2 > tail)
- goto malformed;
- addr->pan_id = hdr[0] | (hdr[1] << 8);
- hdr += 2;
- }
-
- if (hdr + IEEE802154_ADDR_LEN > tail)
- goto malformed;
-
- mac802154_haddr_copy_swap(addr->hwaddr, hdr);
- hdr += IEEE802154_ADDR_LEN;
- break;
- case IEEE802154_ADDR_SHORT:
- if (!(fc & IEEE802154_FC_INTRA_PAN)) {
- if (hdr + 2 > tail)
- goto malformed;
- addr->pan_id = hdr[0] | (hdr[1] << 8);
- hdr += 2;
- }
-
- if (hdr + 2 > tail)
- goto malformed;
-
- addr->short_addr = hdr[0] | (hdr[1] << 8);
- hdr += 2;
- break;
- default:
- goto malformed;
- }
-
- return sizeof(struct ieee802154_addr);
-
-malformed:
- pr_debug("malformed packet\n");
- return 0;
+ *addr = hdr.source;
+ return sizeof(*addr);
}
static netdev_tx_t
@@ -382,8 +242,8 @@
get_random_bytes(&priv->bsn, 1);
get_random_bytes(&priv->dsn, 1);
- priv->pan_id = IEEE802154_PANID_BROADCAST;
- priv->short_addr = IEEE802154_ADDR_BROADCAST;
+ priv->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
+ priv->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
}
static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb)
@@ -394,13 +254,18 @@
static int
mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb)
{
+ __le16 span, sshort;
+
pr_debug("getting packet via slave interface %s\n", sdata->dev->name);
spin_lock_bh(&sdata->mib_lock);
- switch (mac_cb(skb)->da.addr_type) {
+ span = sdata->pan_id;
+ sshort = sdata->short_addr;
+
+ switch (mac_cb(skb)->dest.mode) {
case IEEE802154_ADDR_NONE:
- if (mac_cb(skb)->sa.addr_type != IEEE802154_ADDR_NONE)
+ if (mac_cb(skb)->dest.mode != IEEE802154_ADDR_NONE)
/* FIXME: check if we are PAN coordinator */
skb->pkt_type = PACKET_OTHERHOST;
else
@@ -408,23 +273,22 @@
skb->pkt_type = PACKET_HOST;
break;
case IEEE802154_ADDR_LONG:
- if (mac_cb(skb)->da.pan_id != sdata->pan_id &&
- mac_cb(skb)->da.pan_id != IEEE802154_PANID_BROADCAST)
+ if (mac_cb(skb)->dest.pan_id != span &&
+ mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST))
skb->pkt_type = PACKET_OTHERHOST;
- else if (!memcmp(mac_cb(skb)->da.hwaddr, sdata->dev->dev_addr,
- IEEE802154_ADDR_LEN))
+ else if (mac_cb(skb)->dest.extended_addr == sdata->extended_addr)
skb->pkt_type = PACKET_HOST;
else
skb->pkt_type = PACKET_OTHERHOST;
break;
case IEEE802154_ADDR_SHORT:
- if (mac_cb(skb)->da.pan_id != sdata->pan_id &&
- mac_cb(skb)->da.pan_id != IEEE802154_PANID_BROADCAST)
+ if (mac_cb(skb)->dest.pan_id != span &&
+ mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST))
skb->pkt_type = PACKET_OTHERHOST;
- else if (mac_cb(skb)->da.short_addr == sdata->short_addr)
+ else if (mac_cb(skb)->dest.short_addr == sshort)
skb->pkt_type = PACKET_HOST;
- else if (mac_cb(skb)->da.short_addr ==
- IEEE802154_ADDR_BROADCAST)
+ else if (mac_cb(skb)->dest.short_addr ==
+ cpu_to_le16(IEEE802154_ADDR_BROADCAST))
skb->pkt_type = PACKET_BROADCAST;
else
skb->pkt_type = PACKET_OTHERHOST;
@@ -451,88 +315,82 @@
}
}
+static void mac802154_print_addr(const char *name,
+ const struct ieee802154_addr *addr)
+{
+ if (addr->mode == IEEE802154_ADDR_NONE)
+ pr_debug("%s not present\n", name);
+
+ pr_debug("%s PAN ID: %04x\n", name, le16_to_cpu(addr->pan_id));
+ if (addr->mode == IEEE802154_ADDR_SHORT) {
+ pr_debug("%s is short: %04x\n", name,
+ le16_to_cpu(addr->short_addr));
+ } else {
+ u64 hw = swab64((__force u64) addr->extended_addr);
+
+ pr_debug("%s is hardware: %8phC\n", name, &hw);
+ }
+}
+
static int mac802154_parse_frame_start(struct sk_buff *skb)
{
- u8 *head = skb->data;
- u16 fc;
+ int hlen;
+ struct ieee802154_hdr hdr;
- if (mac802154_fetch_skb_u16(skb, &fc) ||
- mac802154_fetch_skb_u8(skb, &(mac_cb(skb)->seq)))
- goto err;
+ hlen = ieee802154_hdr_pull(skb, &hdr);
+ if (hlen < 0)
+ return -EINVAL;
- pr_debug("fc: %04x dsn: %02x\n", fc, head[2]);
+ skb->mac_len = hlen;
- mac_cb(skb)->flags = IEEE802154_FC_TYPE(fc);
- mac_cb(skb)->sa.addr_type = IEEE802154_FC_SAMODE(fc);
- mac_cb(skb)->da.addr_type = IEEE802154_FC_DAMODE(fc);
+ pr_debug("fc: %04x dsn: %02x\n", le16_to_cpup((__le16 *)&hdr.fc),
+ hdr.seq);
- if (fc & IEEE802154_FC_INTRA_PAN)
- mac_cb(skb)->flags |= MAC_CB_FLAG_INTRAPAN;
+ mac_cb(skb)->flags = hdr.fc.type;
- if (mac_cb(skb)->da.addr_type != IEEE802154_ADDR_NONE) {
- if (mac802154_fetch_skb_u16(skb, &(mac_cb(skb)->da.pan_id)))
- goto err;
+ if (hdr.fc.ack_request)
+ mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ;
+ if (hdr.fc.security_enabled)
+ mac_cb(skb)->flags |= MAC_CB_FLAG_SECEN;
- /* source PAN id compression */
- if (mac_cb_is_intrapan(skb))
- mac_cb(skb)->sa.pan_id = mac_cb(skb)->da.pan_id;
+ mac802154_print_addr("destination", &hdr.dest);
+ mac802154_print_addr("source", &hdr.source);
- pr_debug("dest PAN addr: %04x\n", mac_cb(skb)->da.pan_id);
+ mac_cb(skb)->source = hdr.source;
+ mac_cb(skb)->dest = hdr.dest;
- if (mac_cb(skb)->da.addr_type == IEEE802154_ADDR_SHORT) {
- u16 *da = &(mac_cb(skb)->da.short_addr);
+ if (hdr.fc.security_enabled) {
+ u64 key;
- if (mac802154_fetch_skb_u16(skb, da))
- goto err;
+ pr_debug("seclevel %i\n", hdr.sec.level);
- pr_debug("destination address is short: %04x\n",
- mac_cb(skb)->da.short_addr);
- } else {
- if (!pskb_may_pull(skb, IEEE802154_ADDR_LEN))
- goto err;
+ switch (hdr.sec.key_id_mode) {
+ case IEEE802154_SCF_KEY_IMPLICIT:
+ pr_debug("implicit key\n");
+ break;
- mac802154_haddr_copy_swap(mac_cb(skb)->da.hwaddr,
- skb->data);
- skb_pull(skb, IEEE802154_ADDR_LEN);
+ case IEEE802154_SCF_KEY_INDEX:
+ pr_debug("key %02x\n", hdr.sec.key_id);
+ break;
- pr_debug("destination address is hardware\n");
- }
- }
+ case IEEE802154_SCF_KEY_SHORT_INDEX:
+ pr_debug("key %04x:%04x %02x\n",
+ le32_to_cpu(hdr.sec.short_src) >> 16,
+ le32_to_cpu(hdr.sec.short_src) & 0xffff,
+ hdr.sec.key_id);
+ break;
- if (mac_cb(skb)->sa.addr_type != IEEE802154_ADDR_NONE) {
- /* non PAN-compression, fetch source address id */
- if (!(mac_cb_is_intrapan(skb))) {
- u16 *sa_pan = &(mac_cb(skb)->sa.pan_id);
-
- if (mac802154_fetch_skb_u16(skb, sa_pan))
- goto err;
+ case IEEE802154_SCF_KEY_HW_INDEX:
+ key = swab64((__force u64) hdr.sec.extended_src);
+ pr_debug("key source %8phC %02x\n", &key,
+ hdr.sec.key_id);
+ break;
}
- pr_debug("source PAN addr: %04x\n", mac_cb(skb)->da.pan_id);
-
- if (mac_cb(skb)->sa.addr_type == IEEE802154_ADDR_SHORT) {
- u16 *sa = &(mac_cb(skb)->sa.short_addr);
-
- if (mac802154_fetch_skb_u16(skb, sa))
- goto err;
-
- pr_debug("source address is short: %04x\n",
- mac_cb(skb)->sa.short_addr);
- } else {
- if (!pskb_may_pull(skb, IEEE802154_ADDR_LEN))
- goto err;
-
- mac802154_haddr_copy_swap(mac_cb(skb)->sa.hwaddr,
- skb->data);
- skb_pull(skb, IEEE802154_ADDR_LEN);
-
- pr_debug("source address is hardware\n");
- }
+ return -EINVAL;
}
return 0;
-err:
- return -EINVAL;
}
void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb)
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index c374675..e9410d1 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -513,7 +513,6 @@
config NFT_REJECT
depends on NF_TABLES
- depends on NF_TABLES_IPV6 || !NF_TABLES_IPV6
default m if NETFILTER_ADVANCED=n
tristate "Netfilter nf_tables reject support"
help
@@ -521,6 +520,11 @@
explicitly deny and notify via TCP reset/ICMP informational errors
unallowed traffic.
+config NFT_REJECT_INET
+ depends on NF_TABLES_INET
+ default NFT_REJECT
+ tristate
+
config NFT_COMPAT
depends on NF_TABLES
depends on NETFILTER_XTABLES
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index ee9c4de..bffdad7 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -79,6 +79,7 @@
obj-$(CONFIG_NFT_NAT) += nft_nat.o
obj-$(CONFIG_NFT_QUEUE) += nft_queue.o
obj-$(CONFIG_NFT_REJECT) += nft_reject.o
+obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o
obj-$(CONFIG_NFT_RBTREE) += nft_rbtree.o
obj-$(CONFIG_NFT_HASH) += nft_hash.o
obj-$(CONFIG_NFT_COUNTER) += nft_counter.o
diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig
index 44cd4f5..2f7f5c3 100644
--- a/net/netfilter/ipset/Kconfig
+++ b/net/netfilter/ipset/Kconfig
@@ -61,6 +61,15 @@
To compile it as a module, choose M here. If unsure, say N.
+config IP_SET_HASH_IPMARK
+ tristate "hash:ip,mark set support"
+ depends on IP_SET
+ help
+ This option adds the hash:ip,mark set type support, by which one
+ can store IPv4/IPv6 address and mark pairs.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config IP_SET_HASH_IPPORT
tristate "hash:ip,port set support"
depends on IP_SET
diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile
index 44b2d38..231f101 100644
--- a/net/netfilter/ipset/Makefile
+++ b/net/netfilter/ipset/Makefile
@@ -14,6 +14,7 @@
# hash types
obj-$(CONFIG_IP_SET_HASH_IP) += ip_set_hash_ip.o
+obj-$(CONFIG_IP_SET_HASH_IPMARK) += ip_set_hash_ipmark.o
obj-$(CONFIG_IP_SET_HASH_IPPORT) += ip_set_hash_ipport.o
obj-$(CONFIG_IP_SET_HASH_IPPORTIP) += ip_set_hash_ipportip.o
obj-$(CONFIG_IP_SET_HASH_IPPORTNET) += ip_set_hash_ipportnet.o
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index de770ec..1172083 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -54,10 +54,10 @@
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
/* When the nfnl mutex is held: */
-#define nfnl_dereference(p) \
+#define ip_set_dereference(p) \
rcu_dereference_protected(p, 1)
-#define nfnl_set(inst, id) \
- nfnl_dereference((inst)->ip_set_list)[id]
+#define ip_set(inst, id) \
+ ip_set_dereference((inst)->ip_set_list)[id]
/*
* The set types are implemented in modules and registered set types
@@ -368,6 +368,8 @@
if (tb[IPSET_ATTR_CADT_FLAGS])
cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+ if (cadt_flags & IPSET_FLAG_WITH_FORCEADD)
+ set->flags |= IPSET_CREATE_FLAG_FORCEADD;
for (id = 0; id < IPSET_EXT_ID_MAX; id++) {
if (!add_extension(id, cadt_flags, tb))
continue;
@@ -510,7 +512,7 @@
if (opt->dim < set->type->dimension ||
!(opt->family == set->family || set->family == NFPROTO_UNSPEC))
- return 0;
+ return -IPSET_ERR_TYPE_MISMATCH;
write_lock_bh(&set->lock);
ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt);
@@ -533,7 +535,7 @@
if (opt->dim < set->type->dimension ||
!(opt->family == set->family || set->family == NFPROTO_UNSPEC))
- return 0;
+ return -IPSET_ERR_TYPE_MISMATCH;
write_lock_bh(&set->lock);
ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt);
@@ -640,7 +642,7 @@
return IPSET_INVALID_ID;
nfnl_lock(NFNL_SUBSYS_IPSET);
- set = nfnl_set(inst, index);
+ set = ip_set(inst, index);
if (set)
__ip_set_get(set);
else
@@ -666,7 +668,7 @@
nfnl_lock(NFNL_SUBSYS_IPSET);
if (!inst->is_deleted) { /* already deleted from ip_set_net_exit() */
- set = nfnl_set(inst, index);
+ set = ip_set(inst, index);
if (set != NULL)
__ip_set_put(set);
}
@@ -734,7 +736,7 @@
*id = IPSET_INVALID_ID;
for (i = 0; i < inst->ip_set_max; i++) {
- set = nfnl_set(inst, i);
+ set = ip_set(inst, i);
if (set != NULL && STREQ(set->name, name)) {
*id = i;
break;
@@ -760,7 +762,7 @@
*index = IPSET_INVALID_ID;
for (i = 0; i < inst->ip_set_max; i++) {
- s = nfnl_set(inst, i);
+ s = ip_set(inst, i);
if (s == NULL) {
if (*index == IPSET_INVALID_ID)
*index = i;
@@ -883,7 +885,7 @@
if (!list)
goto cleanup;
/* nfnl mutex is held, both lists are valid */
- tmp = nfnl_dereference(inst->ip_set_list);
+ tmp = ip_set_dereference(inst->ip_set_list);
memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max);
rcu_assign_pointer(inst->ip_set_list, list);
/* Make sure all current packets have passed through */
@@ -900,7 +902,7 @@
* Finally! Add our shiny new set to the list, and be done.
*/
pr_debug("create: '%s' created with index %u!\n", set->name, index);
- nfnl_set(inst, index) = set;
+ ip_set(inst, index) = set;
return ret;
@@ -925,10 +927,10 @@
static void
ip_set_destroy_set(struct ip_set_net *inst, ip_set_id_t index)
{
- struct ip_set *set = nfnl_set(inst, index);
+ struct ip_set *set = ip_set(inst, index);
pr_debug("set: %s\n", set->name);
- nfnl_set(inst, index) = NULL;
+ ip_set(inst, index) = NULL;
/* Must call it without holding any lock */
set->variant->destroy(set);
@@ -962,7 +964,7 @@
read_lock_bh(&ip_set_ref_lock);
if (!attr[IPSET_ATTR_SETNAME]) {
for (i = 0; i < inst->ip_set_max; i++) {
- s = nfnl_set(inst, i);
+ s = ip_set(inst, i);
if (s != NULL && s->ref) {
ret = -IPSET_ERR_BUSY;
goto out;
@@ -970,7 +972,7 @@
}
read_unlock_bh(&ip_set_ref_lock);
for (i = 0; i < inst->ip_set_max; i++) {
- s = nfnl_set(inst, i);
+ s = ip_set(inst, i);
if (s != NULL)
ip_set_destroy_set(inst, i);
}
@@ -1020,7 +1022,7 @@
if (!attr[IPSET_ATTR_SETNAME]) {
for (i = 0; i < inst->ip_set_max; i++) {
- s = nfnl_set(inst, i);
+ s = ip_set(inst, i);
if (s != NULL)
ip_set_flush_set(s);
}
@@ -1074,7 +1076,7 @@
name2 = nla_data(attr[IPSET_ATTR_SETNAME2]);
for (i = 0; i < inst->ip_set_max; i++) {
- s = nfnl_set(inst, i);
+ s = ip_set(inst, i);
if (s != NULL && STREQ(s->name, name2)) {
ret = -IPSET_ERR_EXIST_SETNAME2;
goto out;
@@ -1134,8 +1136,8 @@
write_lock_bh(&ip_set_ref_lock);
swap(from->ref, to->ref);
- nfnl_set(inst, from_id) = to;
- nfnl_set(inst, to_id) = from;
+ ip_set(inst, from_id) = to;
+ ip_set(inst, to_id) = from;
write_unlock_bh(&ip_set_ref_lock);
return 0;
@@ -1157,7 +1159,7 @@
struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET];
if (cb->args[IPSET_CB_ARG0]) {
pr_debug("release set %s\n",
- nfnl_set(inst, cb->args[IPSET_CB_INDEX])->name);
+ ip_set(inst, cb->args[IPSET_CB_INDEX])->name);
__ip_set_put_byindex(inst,
(ip_set_id_t) cb->args[IPSET_CB_INDEX]);
}
@@ -1254,7 +1256,7 @@
dump_type, dump_flags, cb->args[IPSET_CB_INDEX]);
for (; cb->args[IPSET_CB_INDEX] < max; cb->args[IPSET_CB_INDEX]++) {
index = (ip_set_id_t) cb->args[IPSET_CB_INDEX];
- set = nfnl_set(inst, index);
+ set = ip_set(inst, index);
if (set == NULL) {
if (dump_type == DUMP_ONE) {
ret = -ENOENT;
@@ -1332,7 +1334,7 @@
release_refcount:
/* If there was an error or set is done, release set */
if (ret || !cb->args[IPSET_CB_ARG0]) {
- pr_debug("release set %s\n", nfnl_set(inst, index)->name);
+ pr_debug("release set %s\n", ip_set(inst, index)->name);
__ip_set_put_byindex(inst, index);
cb->args[IPSET_CB_ARG0] = 0;
}
@@ -1887,7 +1889,7 @@
find_set_and_id(inst, req_get->set.name, &id);
req_get->set.index = id;
if (id != IPSET_INVALID_ID)
- req_get->family = nfnl_set(inst, id)->family;
+ req_get->family = ip_set(inst, id)->family;
nfnl_unlock(NFNL_SUBSYS_IPSET);
goto copy;
}
@@ -1901,7 +1903,7 @@
goto done;
}
nfnl_lock(NFNL_SUBSYS_IPSET);
- set = nfnl_set(inst, req_get->set.index);
+ set = ip_set(inst, req_get->set.index);
strncpy(req_get->set.name, set ? set->name : "",
IPSET_MAXNAMELEN);
nfnl_unlock(NFNL_SUBSYS_IPSET);
@@ -1945,7 +1947,6 @@
return -ENOMEM;
inst->is_deleted = 0;
rcu_assign_pointer(inst->ip_set_list, list);
- pr_notice("ip_set: protocol %u\n", IPSET_PROTOCOL);
return 0;
}
@@ -1960,7 +1961,7 @@
inst->is_deleted = 1; /* flag for ip_set_nfnl_put */
for (i = 0; i < inst->ip_set_max; i++) {
- set = nfnl_set(inst, i);
+ set = ip_set(inst, i);
if (set != NULL)
ip_set_destroy_set(inst, i);
}
@@ -1996,6 +1997,7 @@
nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
return ret;
}
+ pr_info("ip_set: protocol %u\n", IPSET_PROTOCOL);
return 0;
}
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index be6932a..61c7fb0 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -263,6 +263,9 @@
u32 maxelem; /* max elements in the hash */
u32 elements; /* current element (vs timeout) */
u32 initval; /* random jhash init value */
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ u32 markmask; /* markmask value for mark mask to store */
+#endif
struct timer_list gc; /* garbage collection when timeout enabled */
struct mtype_elem next; /* temporary storage for uadd */
#ifdef IP_SET_HASH_WITH_MULTI
@@ -454,6 +457,9 @@
#ifdef IP_SET_HASH_WITH_NETMASK
x->netmask == y->netmask &&
#endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ x->markmask == y->markmask &&
+#endif
a->extensions == b->extensions;
}
@@ -627,6 +633,18 @@
bool flag_exist = flags & IPSET_FLAG_EXIST;
u32 key, multi = 0;
+ if (h->elements >= h->maxelem && SET_WITH_FORCEADD(set)) {
+ rcu_read_lock_bh();
+ t = rcu_dereference_bh(h->table);
+ key = HKEY(value, h->initval, t->htable_bits);
+ n = hbucket(t,key);
+ if (n->pos) {
+ /* Choosing the first entry in the array to replace */
+ j = 0;
+ goto reuse_slot;
+ }
+ rcu_read_unlock_bh();
+ }
if (SET_WITH_TIMEOUT(set) && h->elements >= h->maxelem)
/* FIXME: when set is full, we slow down here */
mtype_expire(set, h, NLEN(set->family), set->dsize);
@@ -908,6 +926,10 @@
nla_put_u8(skb, IPSET_ATTR_NETMASK, h->netmask))
goto nla_put_failure;
#endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask))
+ goto nla_put_failure;
+#endif
if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) ||
nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)))
goto nla_put_failure;
@@ -1016,6 +1038,9 @@
struct nlattr *tb[], u32 flags)
{
u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ u32 markmask;
+#endif
u8 hbits;
#ifdef IP_SET_HASH_WITH_NETMASK
u8 netmask;
@@ -1026,6 +1051,10 @@
if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
return -IPSET_ERR_INVALID_FAMILY;
+
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ markmask = 0xffffffff;
+#endif
#ifdef IP_SET_HASH_WITH_NETMASK
netmask = set->family == NFPROTO_IPV4 ? 32 : 128;
pr_debug("Create set %s with family %s\n",
@@ -1034,6 +1063,9 @@
if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) ||
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_MARKMASK) ||
+#endif
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
return -IPSET_ERR_PROTOCOL;
@@ -1057,6 +1089,14 @@
return -IPSET_ERR_INVALID_NETMASK;
}
#endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ if (tb[IPSET_ATTR_MARKMASK]) {
+ markmask = ntohl(nla_get_u32(tb[IPSET_ATTR_MARKMASK]));
+
+ if ((markmask > 4294967295u) || markmask == 0)
+ return -IPSET_ERR_INVALID_MARKMASK;
+ }
+#endif
hsize = sizeof(*h);
#ifdef IP_SET_HASH_WITH_NETS
@@ -1071,6 +1111,9 @@
#ifdef IP_SET_HASH_WITH_NETMASK
h->netmask = netmask;
#endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ h->markmask = markmask;
+#endif
get_random_bytes(&h->initval, sizeof(h->initval));
set->timeout = IPSET_NO_TIMEOUT;
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index e65fc24..dd40607 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -25,7 +25,8 @@
#define IPSET_TYPE_REV_MIN 0
/* 1 Counters support */
-#define IPSET_TYPE_REV_MAX 2 /* Comments support */
+/* 2 Comments support */
+#define IPSET_TYPE_REV_MAX 3 /* Forceadd support */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
new file mode 100644
index 0000000..4eff0a2
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -0,0 +1,321 @@
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ * Copyright (C) 2013 Smoothwall Ltd. <vytas.dauksa@smoothwall.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module implementing an IP set type: the hash:ip,mark type */
+
+#include <linux/jhash.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/netlink.h>
+#include <net/tcp.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/ipset/pfxlen.h>
+#include <linux/netfilter/ipset/ip_set.h>
+#include <linux/netfilter/ipset/ip_set_hash.h>
+
+#define IPSET_TYPE_REV_MIN 0
+#define IPSET_TYPE_REV_MAX 1 /* Forceadd support */
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Vytas Dauksa <vytas.dauksa@smoothwall.net>");
+IP_SET_MODULE_DESC("hash:ip,mark", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
+MODULE_ALIAS("ip_set_hash:ip,mark");
+
+/* Type specific function prefix */
+#define HTYPE hash_ipmark
+#define IP_SET_HASH_WITH_MARKMASK
+
+/* IPv4 variant */
+
+/* Member elements */
+struct hash_ipmark4_elem {
+ __be32 ip;
+ __u32 mark;
+};
+
+/* Common functions */
+
+static inline bool
+hash_ipmark4_data_equal(const struct hash_ipmark4_elem *ip1,
+ const struct hash_ipmark4_elem *ip2,
+ u32 *multi)
+{
+ return ip1->ip == ip2->ip &&
+ ip1->mark == ip2->mark;
+}
+
+static bool
+hash_ipmark4_data_list(struct sk_buff *skb,
+ const struct hash_ipmark4_elem *data)
+{
+ if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) ||
+ nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return 1;
+}
+
+static inline void
+hash_ipmark4_data_next(struct hash_ipmark4_elem *next,
+ const struct hash_ipmark4_elem *d)
+{
+ next->ip = d->ip;
+}
+
+#define MTYPE hash_ipmark4
+#define PF 4
+#define HOST_MASK 32
+#define HKEY_DATALEN sizeof(struct hash_ipmark4_elem)
+#include "ip_set_hash_gen.h"
+
+static int
+hash_ipmark4_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ const struct hash_ipmark *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ipmark4_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ e.mark = skb->mark;
+ e.mark &= h->markmask;
+
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ const struct hash_ipmark *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ipmark4_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip, ip_to = 0;
+ int ret;
+
+ if (unlikely(!tb[IPSET_ATTR_IP] ||
+ !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK]));
+ e.mark &= h->markmask;
+
+ if (adt == IPSET_TEST ||
+ !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) {
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_eexist(ret, flags) ? 0 : ret;
+ }
+
+ ip_to = ip = ntohl(e.ip);
+ if (tb[IPSET_ATTR_IP_TO]) {
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
+ if (ret)
+ return ret;
+ if (ip > ip_to)
+ swap(ip, ip_to);
+ } else if (tb[IPSET_ATTR_CIDR]) {
+ u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+
+ if (!cidr || cidr > 32)
+ return -IPSET_ERR_INVALID_CIDR;
+ ip_set_mask_from_to(ip, ip_to, cidr);
+ }
+
+ if (retried)
+ ip = ntohl(h->next.ip);
+ for (; !before(ip_to, ip); ip++) {
+ e.ip = htonl(ip);
+ ret = adtfn(set, &e, &ext, &ext, flags);
+
+ if (ret && !ip_set_eexist(ret, flags))
+ return ret;
+ else
+ ret = 0;
+ }
+ return ret;
+}
+
+/* IPv6 variant */
+
+struct hash_ipmark6_elem {
+ union nf_inet_addr ip;
+ __u32 mark;
+};
+
+/* Common functions */
+
+static inline bool
+hash_ipmark6_data_equal(const struct hash_ipmark6_elem *ip1,
+ const struct hash_ipmark6_elem *ip2,
+ u32 *multi)
+{
+ return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) &&
+ ip1->mark == ip2->mark;
+}
+
+static bool
+hash_ipmark6_data_list(struct sk_buff *skb,
+ const struct hash_ipmark6_elem *data)
+{
+ if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) ||
+ nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return 1;
+}
+
+static inline void
+hash_ipmark6_data_next(struct hash_ipmark4_elem *next,
+ const struct hash_ipmark6_elem *d)
+{
+}
+
+#undef MTYPE
+#undef PF
+#undef HOST_MASK
+#undef HKEY_DATALEN
+
+#define MTYPE hash_ipmark6
+#define PF 6
+#define HOST_MASK 128
+#define HKEY_DATALEN sizeof(struct hash_ipmark6_elem)
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
+
+
+static int
+hash_ipmark6_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ const struct hash_ipmark *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ipmark6_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ e.mark = skb->mark;
+ e.mark &= h->markmask;
+
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_ipmark6_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ const struct hash_ipmark *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ipmark6_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ int ret;
+
+ if (unlikely(!tb[IPSET_ATTR_IP] ||
+ !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) ||
+ tb[IPSET_ATTR_IP_TO] ||
+ tb[IPSET_ATTR_CIDR]))
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK]));
+ e.mark &= h->markmask;
+
+ if (adt == IPSET_TEST) {
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_eexist(ret, flags) ? 0 : ret;
+ }
+
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ if (ret && !ip_set_eexist(ret, flags))
+ return ret;
+ else
+ ret = 0;
+
+ return ret;
+}
+
+static struct ip_set_type hash_ipmark_type __read_mostly = {
+ .name = "hash:ip,mark",
+ .protocol = IPSET_PROTOCOL,
+ .features = IPSET_TYPE_IP | IPSET_TYPE_MARK,
+ .dimension = IPSET_DIM_TWO,
+ .family = NFPROTO_UNSPEC,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
+ .create = hash_ipmark_create,
+ .create_policy = {
+ [IPSET_ATTR_MARKMASK] = { .type = NLA_U32 },
+ [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
+ [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
+ [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ },
+ .adt_policy = {
+ [IPSET_ATTR_IP] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED },
+ [IPSET_ATTR_MARK] = { .type = NLA_U32 },
+ [IPSET_ATTR_CIDR] = { .type = NLA_U8 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
+ },
+ .me = THIS_MODULE,
+};
+
+static int __init
+hash_ipmark_init(void)
+{
+ return ip_set_type_register(&hash_ipmark_type);
+}
+
+static void __exit
+hash_ipmark_fini(void)
+{
+ ip_set_type_unregister(&hash_ipmark_type);
+}
+
+module_init(hash_ipmark_init);
+module_exit(hash_ipmark_fini);
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 525a595..7597b82 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -27,7 +27,8 @@
#define IPSET_TYPE_REV_MIN 0
/* 1 SCTP and UDPLITE support added */
/* 2 Counters support added */
-#define IPSET_TYPE_REV_MAX 3 /* Comments support added */
+/* 3 Comments support added */
+#define IPSET_TYPE_REV_MAX 4 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index f563663..672655f 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -27,7 +27,8 @@
#define IPSET_TYPE_REV_MIN 0
/* 1 SCTP and UDPLITE support added */
/* 2 Counters support added */
-#define IPSET_TYPE_REV_MAX 3 /* Comments support added */
+/* 3 Comments support added */
+#define IPSET_TYPE_REV_MAX 4 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 5d87fe8..7308d84 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -29,7 +29,8 @@
/* 2 Range as input support for IPv4 added */
/* 3 nomatch flag support added */
/* 4 Counters support added */
-#define IPSET_TYPE_REV_MAX 5 /* Comments support added */
+/* 5 Comments support added */
+#define IPSET_TYPE_REV_MAX 6 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 8295cf4..4c7d495 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -26,7 +26,8 @@
/* 1 Range as input support for IPv4 added */
/* 2 nomatch flag support added */
/* 3 Counters support added */
-#define IPSET_TYPE_REV_MAX 4 /* Comments support added */
+/* 4 Comments support added */
+#define IPSET_TYPE_REV_MAX 5 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index b827a0f..db26068 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -27,7 +27,8 @@
/* 1 nomatch flag support added */
/* 2 /0 support added */
/* 3 Counters support added */
-#define IPSET_TYPE_REV_MAX 4 /* Comments support added */
+/* 4 Comments support added */
+#define IPSET_TYPE_REV_MAX 5 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index 6226803..3e99987 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -24,7 +24,7 @@
#include <linux/netfilter/ipset/ip_set_hash.h>
#define IPSET_TYPE_REV_MIN 0
-#define IPSET_TYPE_REV_MAX 0
+#define IPSET_TYPE_REV_MAX 1 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
@@ -112,10 +112,10 @@
(flags &&
nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
goto nla_put_failure;
- return 0;
+ return false;
nla_put_failure:
- return 1;
+ return true;
}
static inline void
@@ -334,10 +334,10 @@
(flags &&
nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
goto nla_put_failure;
- return 0;
+ return false;
nla_put_failure:
- return 1;
+ return true;
}
static inline void
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 7097fb0..1c645fb 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -28,7 +28,8 @@
/* 2 Range as input support for IPv4 added */
/* 3 nomatch flag support added */
/* 4 Counters support added */
-#define IPSET_TYPE_REV_MAX 5 /* Comments support added */
+/* 5 Comments support added */
+#define IPSET_TYPE_REV_MAX 6 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 703d119..c0d2ba7 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -25,7 +25,8 @@
#include <linux/netfilter/ipset/ip_set_hash.h>
#define IPSET_TYPE_REV_MIN 0
-#define IPSET_TYPE_REV_MAX 0 /* Comments support added */
+/* 0 Comments support added */
+#define IPSET_TYPE_REV_MAX 1 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
diff --git a/net/netfilter/ipset/pfxlen.c b/net/netfilter/ipset/pfxlen.c
index 4f29fa9..04d15fd 100644
--- a/net/netfilter/ipset/pfxlen.c
+++ b/net/netfilter/ipset/pfxlen.c
@@ -7,8 +7,8 @@
#define E(a, b, c, d) \
{.ip6 = { \
- __constant_htonl(a), __constant_htonl(b), \
- __constant_htonl(c), __constant_htonl(d), \
+ htonl(a), htonl(b), \
+ htonl(c), htonl(d), \
} }
/*
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 59a1a85..a8eb0a8 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -871,11 +871,11 @@
cp->protocol = p->protocol;
ip_vs_addr_set(p->af, &cp->caddr, p->caddr);
cp->cport = p->cport;
- ip_vs_addr_set(p->af, &cp->vaddr, p->vaddr);
- cp->vport = p->vport;
- /* proto should only be IPPROTO_IP if d_addr is a fwmark */
+ /* proto should only be IPPROTO_IP if p->vaddr is a fwmark */
ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af,
- &cp->daddr, daddr);
+ &cp->vaddr, p->vaddr);
+ cp->vport = p->vport;
+ ip_vs_addr_set(p->af, &cp->daddr, daddr);
cp->dport = dport;
cp->flags = flags;
cp->fwmark = fwmark;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 35be035..c42e83d 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2177,10 +2177,10 @@
__u64 inbytes, outbytes;
do {
- start = u64_stats_fetch_begin_bh(&u->syncp);
+ start = u64_stats_fetch_begin_irq(&u->syncp);
inbytes = u->ustats.inbytes;
outbytes = u->ustats.outbytes;
- } while (u64_stats_fetch_retry_bh(&u->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&u->syncp, start));
seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n",
i, u->ustats.conns, u->ustats.inpkts,
@@ -3580,7 +3580,7 @@
}
-static const struct genl_ops ip_vs_genl_ops[] __read_mostly = {
+static const struct genl_ops ip_vs_genl_ops[] = {
{
.cmd = IPVS_CMD_NEW_SERVICE,
.flags = GENL_ADMIN_PERM,
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index ca056a3..547ff33 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -238,7 +238,7 @@
spin_lock_bh(&svc->sched_lock);
tbl->dead = 1;
- for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) {
+ for (i = 0; i < IP_VS_LBLC_TAB_SIZE; i++) {
hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) {
ip_vs_lblc_del(en);
atomic_dec(&tbl->entries);
@@ -265,7 +265,7 @@
unsigned long now = jiffies;
int i, j;
- for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) {
+ for (i = 0, j = tbl->rover; i < IP_VS_LBLC_TAB_SIZE; i++) {
j = (j + 1) & IP_VS_LBLC_TAB_MASK;
spin_lock(&svc->sched_lock);
@@ -321,7 +321,7 @@
if (goal > tbl->max_size/2)
goal = tbl->max_size/2;
- for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) {
+ for (i = 0, j = tbl->rover; i < IP_VS_LBLC_TAB_SIZE; i++) {
j = (j + 1) & IP_VS_LBLC_TAB_MASK;
spin_lock(&svc->sched_lock);
@@ -340,7 +340,7 @@
tbl->rover = j;
out:
- mod_timer(&tbl->periodic_timer, jiffies+CHECK_EXPIRE_INTERVAL);
+ mod_timer(&tbl->periodic_timer, jiffies + CHECK_EXPIRE_INTERVAL);
}
@@ -363,7 +363,7 @@
/*
* Initialize the hash buckets
*/
- for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) {
+ for (i = 0; i < IP_VS_LBLC_TAB_SIZE; i++) {
INIT_HLIST_HEAD(&tbl->bucket[i]);
}
tbl->max_size = IP_VS_LBLC_TAB_SIZE*16;
@@ -536,8 +536,7 @@
/*
* IPVS LBLC Scheduler structure
*/
-static struct ip_vs_scheduler ip_vs_lblc_scheduler =
-{
+static struct ip_vs_scheduler ip_vs_lblc_scheduler = {
.name = "lblc",
.refcnt = ATOMIC_INIT(0),
.module = THIS_MODULE,
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 8824ed0..6dba48e 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -60,8 +60,59 @@
const struct nlattr *attr) __read_mostly;
EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook);
-DEFINE_SPINLOCK(nf_conntrack_lock);
-EXPORT_SYMBOL_GPL(nf_conntrack_lock);
+__cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
+EXPORT_SYMBOL_GPL(nf_conntrack_locks);
+
+__cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock);
+EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock);
+
+static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2)
+{
+ h1 %= CONNTRACK_LOCKS;
+ h2 %= CONNTRACK_LOCKS;
+ spin_unlock(&nf_conntrack_locks[h1]);
+ if (h1 != h2)
+ spin_unlock(&nf_conntrack_locks[h2]);
+}
+
+/* return true if we need to recompute hashes (in case hash table was resized) */
+static bool nf_conntrack_double_lock(struct net *net, unsigned int h1,
+ unsigned int h2, unsigned int sequence)
+{
+ h1 %= CONNTRACK_LOCKS;
+ h2 %= CONNTRACK_LOCKS;
+ if (h1 <= h2) {
+ spin_lock(&nf_conntrack_locks[h1]);
+ if (h1 != h2)
+ spin_lock_nested(&nf_conntrack_locks[h2],
+ SINGLE_DEPTH_NESTING);
+ } else {
+ spin_lock(&nf_conntrack_locks[h2]);
+ spin_lock_nested(&nf_conntrack_locks[h1],
+ SINGLE_DEPTH_NESTING);
+ }
+ if (read_seqcount_retry(&net->ct.generation, sequence)) {
+ nf_conntrack_double_unlock(h1, h2);
+ return true;
+ }
+ return false;
+}
+
+static void nf_conntrack_all_lock(void)
+{
+ int i;
+
+ for (i = 0; i < CONNTRACK_LOCKS; i++)
+ spin_lock_nested(&nf_conntrack_locks[i], i);
+}
+
+static void nf_conntrack_all_unlock(void)
+{
+ int i;
+
+ for (i = 0; i < CONNTRACK_LOCKS; i++)
+ spin_unlock(&nf_conntrack_locks[i]);
+}
unsigned int nf_conntrack_htable_size __read_mostly;
EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
@@ -192,6 +243,50 @@
nf_ct_remove_expectations(ct);
}
+/* must be called with local_bh_disable */
+static void nf_ct_add_to_dying_list(struct nf_conn *ct)
+{
+ struct ct_pcpu *pcpu;
+
+ /* add this conntrack to the (per cpu) dying list */
+ ct->cpu = smp_processor_id();
+ pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
+
+ spin_lock(&pcpu->lock);
+ hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+ &pcpu->dying);
+ spin_unlock(&pcpu->lock);
+}
+
+/* must be called with local_bh_disable */
+static void nf_ct_add_to_unconfirmed_list(struct nf_conn *ct)
+{
+ struct ct_pcpu *pcpu;
+
+ /* add this conntrack to the (per cpu) unconfirmed list */
+ ct->cpu = smp_processor_id();
+ pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
+
+ spin_lock(&pcpu->lock);
+ hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+ &pcpu->unconfirmed);
+ spin_unlock(&pcpu->lock);
+}
+
+/* must be called with local_bh_disable */
+static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct)
+{
+ struct ct_pcpu *pcpu;
+
+ /* We overload first tuple to link into unconfirmed or dying list.*/
+ pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
+
+ spin_lock(&pcpu->lock);
+ BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
+ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+ spin_unlock(&pcpu->lock);
+}
+
static void
destroy_conntrack(struct nf_conntrack *nfct)
{
@@ -203,9 +298,6 @@
NF_CT_ASSERT(atomic_read(&nfct->use) == 0);
NF_CT_ASSERT(!timer_pending(&ct->timeout));
- /* To make sure we don't get any weird locking issues here:
- * destroy_conntrack() MUST NOT be called with a write lock
- * to nf_conntrack_lock!!! -HW */
rcu_read_lock();
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
if (l4proto && l4proto->destroy)
@@ -213,19 +305,18 @@
rcu_read_unlock();
- spin_lock_bh(&nf_conntrack_lock);
+ local_bh_disable();
/* Expectations will have been removed in clean_from_lists,
* except TFTP can create an expectation on the first packet,
* before connection is in the list, so we need to clean here,
- * too. */
+ * too.
+ */
nf_ct_remove_expectations(ct);
- /* We overload first tuple to link into unconfirmed or dying list.*/
- BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
- hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+ nf_ct_del_from_dying_or_unconfirmed_list(ct);
NF_CT_STAT_INC(net, delete);
- spin_unlock_bh(&nf_conntrack_lock);
+ local_bh_enable();
if (ct->master)
nf_ct_put(ct->master);
@@ -237,17 +328,28 @@
static void nf_ct_delete_from_lists(struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
+ unsigned int hash, reply_hash;
+ u16 zone = nf_ct_zone(ct);
+ unsigned int sequence;
nf_ct_helper_destroy(ct);
- spin_lock_bh(&nf_conntrack_lock);
- /* Inside lock so preempt is disabled on module removal path.
- * Otherwise we can get spurious warnings. */
- NF_CT_STAT_INC(net, delete_list);
+
+ local_bh_disable();
+ do {
+ sequence = read_seqcount_begin(&net->ct.generation);
+ hash = hash_conntrack(net, zone,
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ reply_hash = hash_conntrack(net, zone,
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
+
clean_from_lists(ct);
- /* add this conntrack to the dying list */
- hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
- &net->ct.dying);
- spin_unlock_bh(&nf_conntrack_lock);
+ nf_conntrack_double_unlock(hash, reply_hash);
+
+ nf_ct_add_to_dying_list(ct);
+
+ NF_CT_STAT_INC(net, delete_list);
+ local_bh_enable();
}
static void death_by_event(unsigned long ul_conntrack)
@@ -312,12 +414,25 @@
nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0);
}
+static inline bool
+nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
+ const struct nf_conntrack_tuple *tuple,
+ u16 zone)
+{
+ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+
+ /* A conntrack can be recreated with the equal tuple,
+ * so we need to check that the conntrack is confirmed
+ */
+ return nf_ct_tuple_equal(tuple, &h->tuple) &&
+ nf_ct_zone(ct) == zone &&
+ nf_ct_is_confirmed(ct);
+}
+
/*
* Warning :
* - Caller must take a reference on returned object
* and recheck nf_ct_tuple_equal(tuple, &h->tuple)
- * OR
- * - Caller must lock nf_conntrack_lock before calling this function
*/
static struct nf_conntrack_tuple_hash *
____nf_conntrack_find(struct net *net, u16 zone,
@@ -333,8 +448,7 @@
local_bh_disable();
begin:
hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[bucket], hnnode) {
- if (nf_ct_tuple_equal(tuple, &h->tuple) &&
- nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) {
+ if (nf_ct_key_equal(h, tuple, zone)) {
NF_CT_STAT_INC(net, found);
local_bh_enable();
return h;
@@ -372,8 +486,7 @@
!atomic_inc_not_zero(&ct->ct_general.use)))
h = NULL;
else {
- if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple) ||
- nf_ct_zone(ct) != zone)) {
+ if (unlikely(!nf_ct_key_equal(h, tuple, zone))) {
nf_ct_put(ct);
goto begin;
}
@@ -395,32 +508,36 @@
static void __nf_conntrack_hash_insert(struct nf_conn *ct,
unsigned int hash,
- unsigned int repl_hash)
+ unsigned int reply_hash)
{
struct net *net = nf_ct_net(ct);
hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
&net->ct.hash[hash]);
hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
- &net->ct.hash[repl_hash]);
+ &net->ct.hash[reply_hash]);
}
int
nf_conntrack_hash_check_insert(struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
- unsigned int hash, repl_hash;
+ unsigned int hash, reply_hash;
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_node *n;
u16 zone;
+ unsigned int sequence;
zone = nf_ct_zone(ct);
- hash = hash_conntrack(net, zone,
- &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- repl_hash = hash_conntrack(net, zone,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
- spin_lock_bh(&nf_conntrack_lock);
+ local_bh_disable();
+ do {
+ sequence = read_seqcount_begin(&net->ct.generation);
+ hash = hash_conntrack(net, zone,
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ reply_hash = hash_conntrack(net, zone,
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
/* See if there's one in the list already, including reverse */
hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
@@ -428,32 +545,57 @@
&h->tuple) &&
zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
goto out;
- hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode)
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
&h->tuple) &&
zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
goto out;
add_timer(&ct->timeout);
- nf_conntrack_get(&ct->ct_general);
- __nf_conntrack_hash_insert(ct, hash, repl_hash);
+ smp_wmb();
+ /* The caller holds a reference to this object */
+ atomic_set(&ct->ct_general.use, 2);
+ __nf_conntrack_hash_insert(ct, hash, reply_hash);
+ nf_conntrack_double_unlock(hash, reply_hash);
NF_CT_STAT_INC(net, insert);
- spin_unlock_bh(&nf_conntrack_lock);
-
+ local_bh_enable();
return 0;
out:
+ nf_conntrack_double_unlock(hash, reply_hash);
NF_CT_STAT_INC(net, insert_failed);
- spin_unlock_bh(&nf_conntrack_lock);
+ local_bh_enable();
return -EEXIST;
}
EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
+/* deletion from this larval template list happens via nf_ct_put() */
+void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl)
+{
+ struct ct_pcpu *pcpu;
+
+ __set_bit(IPS_TEMPLATE_BIT, &tmpl->status);
+ __set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
+ nf_conntrack_get(&tmpl->ct_general);
+
+ /* add this conntrack to the (per cpu) tmpl list */
+ local_bh_disable();
+ tmpl->cpu = smp_processor_id();
+ pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu);
+
+ spin_lock(&pcpu->lock);
+ /* Overload tuple linked list to put us in template list. */
+ hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+ &pcpu->tmpl);
+ spin_unlock_bh(&pcpu->lock);
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert);
+
/* Confirm a connection given skb; places it in hash table */
int
__nf_conntrack_confirm(struct sk_buff *skb)
{
- unsigned int hash, repl_hash;
+ unsigned int hash, reply_hash;
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
struct nf_conn_help *help;
@@ -462,6 +604,7 @@
enum ip_conntrack_info ctinfo;
struct net *net;
u16 zone;
+ unsigned int sequence;
ct = nf_ct_get(skb, &ctinfo);
net = nf_ct_net(ct);
@@ -474,31 +617,37 @@
return NF_ACCEPT;
zone = nf_ct_zone(ct);
- /* reuse the hash saved before */
- hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
- hash = hash_bucket(hash, net);
- repl_hash = hash_conntrack(net, zone,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ local_bh_disable();
+
+ do {
+ sequence = read_seqcount_begin(&net->ct.generation);
+ /* reuse the hash saved before */
+ hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
+ hash = hash_bucket(hash, net);
+ reply_hash = hash_conntrack(net, zone,
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+
+ } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
/* We're not in hash table, and we refuse to set up related
- connections for unconfirmed conns. But packet copies and
- REJECT will give spurious warnings here. */
+ * connections for unconfirmed conns. But packet copies and
+ * REJECT will give spurious warnings here.
+ */
/* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */
/* No external references means no one else could have
- confirmed us. */
+ * confirmed us.
+ */
NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
pr_debug("Confirming conntrack %p\n", ct);
-
- spin_lock_bh(&nf_conntrack_lock);
-
/* We have to check the DYING flag inside the lock to prevent
a race against nf_ct_get_next_corpse() possibly called from
user context, else we insert an already 'dead' hash, blocking
further use of that particular connection -JM */
if (unlikely(nf_ct_is_dying(ct))) {
- spin_unlock_bh(&nf_conntrack_lock);
+ nf_conntrack_double_unlock(hash, reply_hash);
+ local_bh_enable();
return NF_ACCEPT;
}
@@ -510,14 +659,13 @@
&h->tuple) &&
zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
goto out;
- hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode)
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
&h->tuple) &&
zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
goto out;
- /* Remove from unconfirmed list */
- hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+ nf_ct_del_from_dying_or_unconfirmed_list(ct);
/* Timer relative to confirmation time, not original
setting time, otherwise we'd get timer wrap in
@@ -540,9 +688,10 @@
* guarantee that no other CPU can find the conntrack before the above
* stores are visible.
*/
- __nf_conntrack_hash_insert(ct, hash, repl_hash);
+ __nf_conntrack_hash_insert(ct, hash, reply_hash);
+ nf_conntrack_double_unlock(hash, reply_hash);
NF_CT_STAT_INC(net, insert);
- spin_unlock_bh(&nf_conntrack_lock);
+ local_bh_enable();
help = nfct_help(ct);
if (help && help->helper)
@@ -553,8 +702,9 @@
return NF_ACCEPT;
out:
+ nf_conntrack_double_unlock(hash, reply_hash);
NF_CT_STAT_INC(net, insert_failed);
- spin_unlock_bh(&nf_conntrack_lock);
+ local_bh_enable();
return NF_DROP;
}
EXPORT_SYMBOL_GPL(__nf_conntrack_confirm);
@@ -597,39 +747,48 @@
/* There's a small race here where we may free a just-assured
connection. Too bad: we're in trouble anyway. */
-static noinline int early_drop(struct net *net, unsigned int hash)
+static noinline int early_drop(struct net *net, unsigned int _hash)
{
/* Use oldest entry, which is roughly LRU */
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct = NULL, *tmp;
struct hlist_nulls_node *n;
- unsigned int i, cnt = 0;
+ unsigned int i = 0, cnt = 0;
int dropped = 0;
+ unsigned int hash, sequence;
+ spinlock_t *lockp;
- rcu_read_lock();
- for (i = 0; i < net->ct.htable_size; i++) {
+ local_bh_disable();
+restart:
+ sequence = read_seqcount_begin(&net->ct.generation);
+ hash = hash_bucket(_hash, net);
+ for (; i < net->ct.htable_size; i++) {
+ lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS];
+ spin_lock(lockp);
+ if (read_seqcount_retry(&net->ct.generation, sequence)) {
+ spin_unlock(lockp);
+ goto restart;
+ }
hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash],
hnnode) {
tmp = nf_ct_tuplehash_to_ctrack(h);
- if (!test_bit(IPS_ASSURED_BIT, &tmp->status))
+ if (!test_bit(IPS_ASSURED_BIT, &tmp->status) &&
+ !nf_ct_is_dying(tmp) &&
+ atomic_inc_not_zero(&tmp->ct_general.use)) {
ct = tmp;
+ break;
+ }
cnt++;
}
- if (ct != NULL) {
- if (likely(!nf_ct_is_dying(ct) &&
- atomic_inc_not_zero(&ct->ct_general.use)))
- break;
- else
- ct = NULL;
- }
+ hash = (hash + 1) % net->ct.htable_size;
+ spin_unlock(lockp);
- if (cnt >= NF_CT_EVICTION_RANGE)
+ if (ct || cnt >= NF_CT_EVICTION_RANGE)
break;
- hash = (hash + 1) % net->ct.htable_size;
}
- rcu_read_unlock();
+ local_bh_enable();
if (!ct)
return dropped;
@@ -678,7 +837,7 @@
if (nf_conntrack_max &&
unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) {
- if (!early_drop(net, hash_bucket(hash, net))) {
+ if (!early_drop(net, hash)) {
atomic_dec(&net->ct.count);
net_warn_ratelimited("nf_conntrack: table full, dropping packet\n");
return ERR_PTR(-ENOMEM);
@@ -720,11 +879,10 @@
nf_ct_zone->id = zone;
}
#endif
- /*
- * changes to lookup keys must be done before setting refcnt to 1
+ /* Because we use RCU lookups, we set ct_general.use to zero before
+ * this is inserted in any list.
*/
- smp_wmb();
- atomic_set(&ct->ct_general.use, 1);
+ atomic_set(&ct->ct_general.use, 0);
return ct;
#ifdef CONFIG_NF_CONNTRACK_ZONES
@@ -748,6 +906,11 @@
{
struct net *net = nf_ct_net(ct);
+ /* A freed object has refcnt == 0, that's
+ * the golden rule for SLAB_DESTROY_BY_RCU
+ */
+ NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0);
+
nf_ct_ext_destroy(ct);
nf_ct_ext_free(ct);
kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
@@ -771,7 +934,7 @@
struct nf_conn_help *help;
struct nf_conntrack_tuple repl_tuple;
struct nf_conntrack_ecache *ecache;
- struct nf_conntrack_expect *exp;
+ struct nf_conntrack_expect *exp = NULL;
u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
struct nf_conn_timeout *timeout_ext;
unsigned int *timeouts;
@@ -815,39 +978,44 @@
ecache ? ecache->expmask : 0,
GFP_ATOMIC);
- spin_lock_bh(&nf_conntrack_lock);
- exp = nf_ct_find_expectation(net, zone, tuple);
- if (exp) {
- pr_debug("conntrack: expectation arrives ct=%p exp=%p\n",
- ct, exp);
- /* Welcome, Mr. Bond. We've been expecting you... */
- __set_bit(IPS_EXPECTED_BIT, &ct->status);
- ct->master = exp->master;
- if (exp->helper) {
- help = nf_ct_helper_ext_add(ct, exp->helper,
- GFP_ATOMIC);
- if (help)
- rcu_assign_pointer(help->helper, exp->helper);
- }
+ local_bh_disable();
+ if (net->ct.expect_count) {
+ spin_lock(&nf_conntrack_expect_lock);
+ exp = nf_ct_find_expectation(net, zone, tuple);
+ if (exp) {
+ pr_debug("conntrack: expectation arrives ct=%p exp=%p\n",
+ ct, exp);
+ /* Welcome, Mr. Bond. We've been expecting you... */
+ __set_bit(IPS_EXPECTED_BIT, &ct->status);
+ /* exp->master safe, refcnt bumped in nf_ct_find_expectation */
+ ct->master = exp->master;
+ if (exp->helper) {
+ help = nf_ct_helper_ext_add(ct, exp->helper,
+ GFP_ATOMIC);
+ if (help)
+ rcu_assign_pointer(help->helper, exp->helper);
+ }
#ifdef CONFIG_NF_CONNTRACK_MARK
- ct->mark = exp->master->mark;
+ ct->mark = exp->master->mark;
#endif
#ifdef CONFIG_NF_CONNTRACK_SECMARK
- ct->secmark = exp->master->secmark;
+ ct->secmark = exp->master->secmark;
#endif
- nf_conntrack_get(&ct->master->ct_general);
- NF_CT_STAT_INC(net, expect_new);
- } else {
+ NF_CT_STAT_INC(net, expect_new);
+ }
+ spin_unlock(&nf_conntrack_expect_lock);
+ }
+ if (!exp) {
__nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);
NF_CT_STAT_INC(net, new);
}
- /* Overload tuple linked list to put us in unconfirmed list. */
- hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
- &net->ct.unconfirmed);
+ /* Now it is inserted into the unconfirmed list, bump refcount */
+ nf_conntrack_get(&ct->ct_general);
+ nf_ct_add_to_unconfirmed_list(ct);
- spin_unlock_bh(&nf_conntrack_lock);
+ local_bh_enable();
if (exp) {
if (exp->expectfn)
@@ -1217,27 +1385,42 @@
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
struct hlist_nulls_node *n;
+ int cpu;
+ spinlock_t *lockp;
- spin_lock_bh(&nf_conntrack_lock);
for (; *bucket < net->ct.htable_size; (*bucket)++) {
- hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
- if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
- continue;
+ lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS];
+ local_bh_disable();
+ spin_lock(lockp);
+ if (*bucket < net->ct.htable_size) {
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
+ if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
+ continue;
+ ct = nf_ct_tuplehash_to_ctrack(h);
+ if (iter(ct, data))
+ goto found;
+ }
+ }
+ spin_unlock(lockp);
+ local_bh_enable();
+ }
+
+ for_each_possible_cpu(cpu) {
+ struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+ spin_lock_bh(&pcpu->lock);
+ hlist_nulls_for_each_entry(h, n, &pcpu->unconfirmed, hnnode) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (iter(ct, data))
- goto found;
+ set_bit(IPS_DYING_BIT, &ct->status);
}
+ spin_unlock_bh(&pcpu->lock);
}
- hlist_nulls_for_each_entry(h, n, &net->ct.unconfirmed, hnnode) {
- ct = nf_ct_tuplehash_to_ctrack(h);
- if (iter(ct, data))
- set_bit(IPS_DYING_BIT, &ct->status);
- }
- spin_unlock_bh(&nf_conntrack_lock);
return NULL;
found:
atomic_inc(&ct->ct_general.use);
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock(lockp);
+ local_bh_enable();
return ct;
}
@@ -1286,14 +1469,19 @@
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
struct hlist_nulls_node *n;
+ int cpu;
- spin_lock_bh(&nf_conntrack_lock);
- hlist_nulls_for_each_entry(h, n, &net->ct.dying, hnnode) {
- ct = nf_ct_tuplehash_to_ctrack(h);
- /* never fails to remove them, no listeners at this point */
- nf_ct_kill(ct);
+ for_each_possible_cpu(cpu) {
+ struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+ spin_lock_bh(&pcpu->lock);
+ hlist_nulls_for_each_entry(h, n, &pcpu->dying, hnnode) {
+ ct = nf_ct_tuplehash_to_ctrack(h);
+ /* never fails to remove them, no listeners at this point */
+ nf_ct_kill(ct);
+ }
+ spin_unlock_bh(&pcpu->lock);
}
- spin_unlock_bh(&nf_conntrack_lock);
}
static int untrack_refs(void)
@@ -1380,6 +1568,7 @@
kmem_cache_destroy(net->ct.nf_conntrack_cachep);
kfree(net->ct.slabname);
free_percpu(net->ct.stat);
+ free_percpu(net->ct.pcpu_lists);
}
}
@@ -1432,12 +1621,16 @@
if (!hash)
return -ENOMEM;
+ local_bh_disable();
+ nf_conntrack_all_lock();
+ write_seqcount_begin(&init_net.ct.generation);
+
/* Lookups in the old hash might happen in parallel, which means we
* might get false negatives during connection lookup. New connections
* created because of a false negative won't make it into the hash
- * though since that required taking the lock.
+ * though since that required taking the locks.
*/
- spin_lock_bh(&nf_conntrack_lock);
+
for (i = 0; i < init_net.ct.htable_size; i++) {
while (!hlist_nulls_empty(&init_net.ct.hash[i])) {
h = hlist_nulls_entry(init_net.ct.hash[i].first,
@@ -1454,7 +1647,10 @@
init_net.ct.htable_size = nf_conntrack_htable_size = hashsize;
init_net.ct.hash = hash;
- spin_unlock_bh(&nf_conntrack_lock);
+
+ write_seqcount_end(&init_net.ct.generation);
+ nf_conntrack_all_unlock();
+ local_bh_enable();
nf_ct_free_hashtable(old_hash, old_size);
return 0;
@@ -1476,7 +1672,10 @@
int nf_conntrack_init_start(void)
{
int max_factor = 8;
- int ret, cpu;
+ int i, ret, cpu;
+
+ for (i = 0; i < CONNTRACK_LOCKS; i++)
+ spin_lock_init(&nf_conntrack_locks[i]);
/* Idea from tcp.c: use 1/16384 of memory. On i386: 32MB
* machine has 512 buckets. >= 1GB machines have 16384 buckets. */
@@ -1592,37 +1791,43 @@
int nf_conntrack_init_net(struct net *net)
{
- int ret;
+ int ret = -ENOMEM;
+ int cpu;
atomic_set(&net->ct.count, 0);
- INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL);
- INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL);
- INIT_HLIST_NULLS_HEAD(&net->ct.tmpl, TEMPLATE_NULLS_VAL);
- net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
- if (!net->ct.stat) {
- ret = -ENOMEM;
+
+ net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu);
+ if (!net->ct.pcpu_lists)
goto err_stat;
+
+ for_each_possible_cpu(cpu) {
+ struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+ spin_lock_init(&pcpu->lock);
+ INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL);
+ INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL);
+ INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL);
}
+ net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
+ if (!net->ct.stat)
+ goto err_pcpu_lists;
+
net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net);
- if (!net->ct.slabname) {
- ret = -ENOMEM;
+ if (!net->ct.slabname)
goto err_slabname;
- }
net->ct.nf_conntrack_cachep = kmem_cache_create(net->ct.slabname,
sizeof(struct nf_conn), 0,
SLAB_DESTROY_BY_RCU, NULL);
if (!net->ct.nf_conntrack_cachep) {
printk(KERN_ERR "Unable to create nf_conn slab cache\n");
- ret = -ENOMEM;
goto err_cache;
}
net->ct.htable_size = nf_conntrack_htable_size;
net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, 1);
if (!net->ct.hash) {
- ret = -ENOMEM;
printk(KERN_ERR "Unable to create nf_conntrack_hash\n");
goto err_hash;
}
@@ -1664,6 +1869,8 @@
kfree(net->ct.slabname);
err_slabname:
free_percpu(net->ct.stat);
+err_pcpu_lists:
+ free_percpu(net->ct.pcpu_lists);
err_stat:
return ret;
}
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 4fd1ca9..f87e8f6 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -66,9 +66,9 @@
{
struct nf_conntrack_expect *exp = (void *)ul_expect;
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
nf_ct_unlink_expect(exp);
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
nf_ct_expect_put(exp);
}
@@ -155,6 +155,18 @@
if (!nf_ct_is_confirmed(exp->master))
return NULL;
+ /* Avoid race with other CPUs, that for exp->master ct, is
+ * about to invoke ->destroy(), or nf_ct_delete() via timeout
+ * or early_drop().
+ *
+ * The atomic_inc_not_zero() check tells: If that fails, we
+ * know that the ct is being destroyed. If it succeeds, we
+ * can be sure the ct cannot disappear underneath.
+ */
+ if (unlikely(nf_ct_is_dying(exp->master) ||
+ !atomic_inc_not_zero(&exp->master->ct_general.use)))
+ return NULL;
+
if (exp->flags & NF_CT_EXPECT_PERMANENT) {
atomic_inc(&exp->use);
return exp;
@@ -162,6 +174,8 @@
nf_ct_unlink_expect(exp);
return exp;
}
+ /* Undo exp->master refcnt increase, if del_timer() failed */
+ nf_ct_put(exp->master);
return NULL;
}
@@ -177,12 +191,14 @@
if (!help)
return;
+ spin_lock_bh(&nf_conntrack_expect_lock);
hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
if (del_timer(&exp->timeout)) {
nf_ct_unlink_expect(exp);
nf_ct_expect_put(exp);
}
}
+ spin_unlock_bh(&nf_conntrack_expect_lock);
}
EXPORT_SYMBOL_GPL(nf_ct_remove_expectations);
@@ -217,12 +233,12 @@
/* Generally a bad idea to call this: could have matched already. */
void nf_ct_unexpect_related(struct nf_conntrack_expect *exp)
{
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
if (del_timer(&exp->timeout)) {
nf_ct_unlink_expect(exp);
nf_ct_expect_put(exp);
}
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
}
EXPORT_SYMBOL_GPL(nf_ct_unexpect_related);
@@ -335,7 +351,7 @@
setup_timer(&exp->timeout, nf_ct_expectation_timed_out,
(unsigned long)exp);
helper = rcu_dereference_protected(master_help->helper,
- lockdep_is_held(&nf_conntrack_lock));
+ lockdep_is_held(&nf_conntrack_expect_lock));
if (helper) {
exp->timeout.expires = jiffies +
helper->expect_policy[exp->class].timeout * HZ;
@@ -395,7 +411,7 @@
}
/* Will be over limit? */
helper = rcu_dereference_protected(master_help->helper,
- lockdep_is_held(&nf_conntrack_lock));
+ lockdep_is_held(&nf_conntrack_expect_lock));
if (helper) {
p = &helper->expect_policy[expect->class];
if (p->max_expected &&
@@ -417,12 +433,12 @@
return ret;
}
-int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
+int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
u32 portid, int report)
{
int ret;
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
ret = __nf_ct_expect_check(expect);
if (ret <= 0)
goto out;
@@ -430,11 +446,11 @@
ret = nf_ct_expect_insert(expect);
if (ret < 0)
goto out;
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report);
return ret;
out:
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_expect_related_report);
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 70866d1..3a3a60b 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -1476,7 +1476,7 @@
nf_ct_refresh(ct, skb, info->timeout * HZ);
/* Set expect timeout */
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
exp = find_expect(ct, &ct->tuplehash[dir].tuple.dst.u3,
info->sig_port[!dir]);
if (exp) {
@@ -1486,7 +1486,7 @@
nf_ct_dump_tuple(&exp->tuple);
set_expect_timeout(exp, info->timeout);
}
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
}
return 0;
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 974a2a4..5b3eae7 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -250,16 +250,14 @@
}
EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper);
+/* appropiate ct lock protecting must be taken by caller */
static inline int unhelp(struct nf_conntrack_tuple_hash *i,
const struct nf_conntrack_helper *me)
{
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i);
struct nf_conn_help *help = nfct_help(ct);
- if (help && rcu_dereference_protected(
- help->helper,
- lockdep_is_held(&nf_conntrack_lock)
- ) == me) {
+ if (help && rcu_dereference_raw(help->helper) == me) {
nf_conntrack_event(IPCT_HELPER, ct);
RCU_INIT_POINTER(help->helper, NULL);
}
@@ -284,17 +282,17 @@
void nf_ct_helper_expectfn_register(struct nf_ct_helper_expectfn *n)
{
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
list_add_rcu(&n->head, &nf_ct_helper_expectfn_list);
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
}
EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_register);
void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n)
{
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
list_del_rcu(&n->head);
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
}
EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister);
@@ -396,15 +394,17 @@
const struct hlist_node *next;
const struct hlist_nulls_node *nn;
unsigned int i;
+ int cpu;
/* Get rid of expectations */
+ spin_lock_bh(&nf_conntrack_expect_lock);
for (i = 0; i < nf_ct_expect_hsize; i++) {
hlist_for_each_entry_safe(exp, next,
&net->ct.expect_hash[i], hnode) {
struct nf_conn_help *help = nfct_help(exp->master);
if ((rcu_dereference_protected(
help->helper,
- lockdep_is_held(&nf_conntrack_lock)
+ lockdep_is_held(&nf_conntrack_expect_lock)
) == me || exp->helper == me) &&
del_timer(&exp->timeout)) {
nf_ct_unlink_expect(exp);
@@ -412,14 +412,27 @@
}
}
}
+ spin_unlock_bh(&nf_conntrack_expect_lock);
/* Get rid of expecteds, set helpers to NULL. */
- hlist_nulls_for_each_entry(h, nn, &net->ct.unconfirmed, hnnode)
- unhelp(h, me);
- for (i = 0; i < net->ct.htable_size; i++) {
- hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
+ for_each_possible_cpu(cpu) {
+ struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+ spin_lock_bh(&pcpu->lock);
+ hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode)
unhelp(h, me);
+ spin_unlock_bh(&pcpu->lock);
}
+ local_bh_disable();
+ for (i = 0; i < net->ct.htable_size; i++) {
+ spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
+ if (i < net->ct.htable_size) {
+ hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
+ unhelp(h, me);
+ }
+ spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
+ }
+ local_bh_enable();
}
void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
@@ -437,10 +450,8 @@
synchronize_rcu();
rtnl_lock();
- spin_lock_bh(&nf_conntrack_lock);
for_each_net(net)
__nf_conntrack_helper_unregister(me, net);
- spin_unlock_bh(&nf_conntrack_lock);
rtnl_unlock();
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index bb322d0..ccc46fa 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -764,14 +764,23 @@
struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
u_int8_t l3proto = nfmsg->nfgen_family;
int res;
+ spinlock_t *lockp;
+
#ifdef CONFIG_NF_CONNTRACK_MARK
const struct ctnetlink_dump_filter *filter = cb->data;
#endif
- spin_lock_bh(&nf_conntrack_lock);
last = (struct nf_conn *)cb->args[1];
+
+ local_bh_disable();
for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) {
restart:
+ lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS];
+ spin_lock(lockp);
+ if (cb->args[0] >= net->ct.htable_size) {
+ spin_unlock(lockp);
+ goto out;
+ }
hlist_nulls_for_each_entry(h, n, &net->ct.hash[cb->args[0]],
hnnode) {
if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
@@ -803,16 +812,18 @@
if (res < 0) {
nf_conntrack_get(&ct->ct_general);
cb->args[1] = (unsigned long)ct;
+ spin_unlock(lockp);
goto out;
}
}
+ spin_unlock(lockp);
if (cb->args[1]) {
cb->args[1] = 0;
goto restart;
}
}
out:
- spin_unlock_bh(&nf_conntrack_lock);
+ local_bh_enable();
if (last)
nf_ct_put(last);
@@ -966,7 +977,6 @@
return 0;
}
-#define __CTA_LABELS_MAX_LENGTH ((XT_CONNLABEL_MAXBIT + 1) / BITS_PER_BYTE)
static const struct nla_policy ct_nla_policy[CTA_MAX+1] = {
[CTA_TUPLE_ORIG] = { .type = NLA_NESTED },
[CTA_TUPLE_REPLY] = { .type = NLA_NESTED },
@@ -984,9 +994,9 @@
[CTA_ZONE] = { .type = NLA_U16 },
[CTA_MARK_MASK] = { .type = NLA_U32 },
[CTA_LABELS] = { .type = NLA_BINARY,
- .len = __CTA_LABELS_MAX_LENGTH },
+ .len = NF_CT_LABELS_MAX_SIZE },
[CTA_LABELS_MASK] = { .type = NLA_BINARY,
- .len = __CTA_LABELS_MAX_LENGTH },
+ .len = NF_CT_LABELS_MAX_SIZE },
};
static int
@@ -1138,50 +1148,65 @@
}
static int
-ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb,
- struct hlist_nulls_head *list)
+ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying)
{
- struct nf_conn *ct, *last;
+ struct nf_conn *ct, *last = NULL;
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_node *n;
struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
u_int8_t l3proto = nfmsg->nfgen_family;
int res;
+ int cpu;
+ struct hlist_nulls_head *list;
+ struct net *net = sock_net(skb->sk);
if (cb->args[2])
return 0;
- spin_lock_bh(&nf_conntrack_lock);
- last = (struct nf_conn *)cb->args[1];
-restart:
- hlist_nulls_for_each_entry(h, n, list, hnnode) {
- ct = nf_ct_tuplehash_to_ctrack(h);
- if (l3proto && nf_ct_l3num(ct) != l3proto)
+ if (cb->args[0] == nr_cpu_ids)
+ return 0;
+
+ for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) {
+ struct ct_pcpu *pcpu;
+
+ if (!cpu_possible(cpu))
continue;
- if (cb->args[1]) {
- if (ct != last)
+
+ pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+ spin_lock_bh(&pcpu->lock);
+ last = (struct nf_conn *)cb->args[1];
+ list = dying ? &pcpu->dying : &pcpu->unconfirmed;
+restart:
+ hlist_nulls_for_each_entry(h, n, list, hnnode) {
+ ct = nf_ct_tuplehash_to_ctrack(h);
+ if (l3proto && nf_ct_l3num(ct) != l3proto)
continue;
+ if (cb->args[1]) {
+ if (ct != last)
+ continue;
+ cb->args[1] = 0;
+ }
+ rcu_read_lock();
+ res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
+ ct);
+ rcu_read_unlock();
+ if (res < 0) {
+ nf_conntrack_get(&ct->ct_general);
+ cb->args[1] = (unsigned long)ct;
+ spin_unlock_bh(&pcpu->lock);
+ goto out;
+ }
+ }
+ if (cb->args[1]) {
cb->args[1] = 0;
- }
- rcu_read_lock();
- res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
- NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
- ct);
- rcu_read_unlock();
- if (res < 0) {
- nf_conntrack_get(&ct->ct_general);
- cb->args[1] = (unsigned long)ct;
- goto out;
- }
+ goto restart;
+ } else
+ cb->args[2] = 1;
+ spin_unlock_bh(&pcpu->lock);
}
- if (cb->args[1]) {
- cb->args[1] = 0;
- goto restart;
- } else
- cb->args[2] = 1;
out:
- spin_unlock_bh(&nf_conntrack_lock);
if (last)
nf_ct_put(last);
@@ -1191,9 +1216,7 @@
static int
ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct net *net = sock_net(skb->sk);
-
- return ctnetlink_dump_list(skb, cb, &net->ct.dying);
+ return ctnetlink_dump_list(skb, cb, true);
}
static int
@@ -1215,9 +1238,7 @@
static int
ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct net *net = sock_net(skb->sk);
-
- return ctnetlink_dump_list(skb, cb, &net->ct.unconfirmed);
+ return ctnetlink_dump_list(skb, cb, false);
}
static int
@@ -1310,27 +1331,22 @@
}
static int
-ctnetlink_change_nat(struct nf_conn *ct, const struct nlattr * const cda[])
+ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[])
{
#ifdef CONFIG_NF_NAT_NEEDED
int ret;
- if (cda[CTA_NAT_DST]) {
- ret = ctnetlink_parse_nat_setup(ct,
- NF_NAT_MANIP_DST,
- cda[CTA_NAT_DST]);
- if (ret < 0)
- return ret;
- }
- if (cda[CTA_NAT_SRC]) {
- ret = ctnetlink_parse_nat_setup(ct,
- NF_NAT_MANIP_SRC,
- cda[CTA_NAT_SRC]);
- if (ret < 0)
- return ret;
- }
- return 0;
+ ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST,
+ cda[CTA_NAT_DST]);
+ if (ret < 0)
+ return ret;
+
+ ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC,
+ cda[CTA_NAT_SRC]);
+ return ret;
#else
+ if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
+ return 0;
return -EOPNOTSUPP;
#endif
}
@@ -1366,14 +1382,14 @@
nf_ct_protonum(ct));
if (helper == NULL) {
#ifdef CONFIG_MODULES
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
if (request_module("nfct-helper-%s", helpname) < 0) {
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
return -EOPNOTSUPP;
}
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct),
nf_ct_protonum(ct));
if (helper)
@@ -1659,11 +1675,9 @@
goto err2;
}
- if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) {
- err = ctnetlink_change_nat(ct, cda);
- if (err < 0)
- goto err2;
- }
+ err = ctnetlink_setup_nat(ct, cda);
+ if (err < 0)
+ goto err2;
nf_ct_acct_ext_add(ct, GFP_ATOMIC);
nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
@@ -1811,9 +1825,9 @@
err = -EEXIST;
ct = nf_ct_tuplehash_to_ctrack(h);
if (!(nlh->nlmsg_flags & NLM_F_EXCL)) {
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
err = ctnetlink_change_conntrack(ct, cda);
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
if (err == 0) {
nf_conntrack_eventmask_report((1 << IPCT_REPLY) |
(1 << IPCT_ASSURED) |
@@ -2142,9 +2156,9 @@
if (ret < 0)
return ret;
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
ret = ctnetlink_nfqueue_parse_ct((const struct nlattr **)cda, ct);
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
return ret;
}
@@ -2699,13 +2713,13 @@
}
/* after list removal, usage count == 1 */
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
if (del_timer(&exp->timeout)) {
nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid,
nlmsg_report(nlh));
nf_ct_expect_put(exp);
}
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
/* have to put what we 'get' above.
* after this line usage count == 0 */
nf_ct_expect_put(exp);
@@ -2714,7 +2728,7 @@
struct nf_conn_help *m_help;
/* delete all expectations for this helper */
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
for (i = 0; i < nf_ct_expect_hsize; i++) {
hlist_for_each_entry_safe(exp, next,
&net->ct.expect_hash[i],
@@ -2729,10 +2743,10 @@
}
}
}
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
} else {
/* This basically means we have to flush everything*/
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
for (i = 0; i < nf_ct_expect_hsize; i++) {
hlist_for_each_entry_safe(exp, next,
&net->ct.expect_hash[i],
@@ -2745,7 +2759,7 @@
}
}
}
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
}
return 0;
@@ -2971,11 +2985,11 @@
if (err < 0)
return err;
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
exp = __nf_ct_expect_find(net, zone, &tuple);
if (!exp) {
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
err = -ENOENT;
if (nlh->nlmsg_flags & NLM_F_CREATE) {
err = ctnetlink_create_expect(net, zone, cda,
@@ -2989,7 +3003,7 @@
err = -EEXIST;
if (!(nlh->nlmsg_flags & NLM_F_EXCL))
err = ctnetlink_change_expect(exp, cda);
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
return err;
}
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 466410e..4c3ba1c 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -800,7 +800,7 @@
struct hlist_node *next;
int found = 0;
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
if (exp->class != SIP_EXPECT_SIGNALLING ||
!nf_inet_addr_cmp(&exp->tuple.dst.u3, addr) ||
@@ -815,7 +815,7 @@
found = 1;
break;
}
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
return found;
}
@@ -825,7 +825,7 @@
struct nf_conntrack_expect *exp;
struct hlist_node *next;
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
if ((exp->class != SIP_EXPECT_SIGNALLING) ^ media)
continue;
@@ -836,7 +836,7 @@
if (!media)
break;
}
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
}
static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index d3f5cd6..52ca952 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -432,15 +432,15 @@
}
EXPORT_SYMBOL(nf_nat_setup_info);
-unsigned int
-nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+static unsigned int
+__nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip)
{
/* Force range to this IP; let proto decide mapping for
* per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
* Use reply in case it's already been mangled (eg local packet).
*/
union nf_inet_addr ip =
- (HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
+ (manip == NF_NAT_MANIP_SRC ?
ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 :
ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3);
struct nf_nat_range range = {
@@ -448,7 +448,13 @@
.min_addr = ip,
.max_addr = ip,
};
- return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
+ return nf_nat_setup_info(ct, &range, manip);
+}
+
+unsigned int
+nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+{
+ return __nf_nat_alloc_null_binding(ct, HOOK2MANIP(hooknum));
}
EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding);
@@ -702,9 +708,9 @@
static int
nfnetlink_parse_nat(const struct nlattr *nat,
- const struct nf_conn *ct, struct nf_nat_range *range)
+ const struct nf_conn *ct, struct nf_nat_range *range,
+ const struct nf_nat_l3proto *l3proto)
{
- const struct nf_nat_l3proto *l3proto;
struct nlattr *tb[CTA_NAT_MAX+1];
int err;
@@ -714,38 +720,46 @@
if (err < 0)
return err;
- rcu_read_lock();
- l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct));
- if (l3proto == NULL) {
- err = -EAGAIN;
- goto out;
- }
err = l3proto->nlattr_to_range(tb, range);
if (err < 0)
- goto out;
+ return err;
if (!tb[CTA_NAT_PROTO])
- goto out;
+ return 0;
- err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range);
-out:
- rcu_read_unlock();
- return err;
+ return nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range);
}
+/* This function is called under rcu_read_lock() */
static int
nfnetlink_parse_nat_setup(struct nf_conn *ct,
enum nf_nat_manip_type manip,
const struct nlattr *attr)
{
struct nf_nat_range range;
+ const struct nf_nat_l3proto *l3proto;
int err;
- err = nfnetlink_parse_nat(attr, ct, &range);
+ /* Should not happen, restricted to creating new conntracks
+ * via ctnetlink.
+ */
+ if (WARN_ON_ONCE(nf_nat_initialized(ct, manip)))
+ return -EEXIST;
+
+ /* Make sure that L3 NAT is there by when we call nf_nat_setup_info to
+ * attach the null binding, otherwise this may oops.
+ */
+ l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct));
+ if (l3proto == NULL)
+ return -EAGAIN;
+
+ /* No NAT information has been passed, allocate the null-binding */
+ if (attr == NULL)
+ return __nf_nat_alloc_null_binding(ct, manip);
+
+ err = nfnetlink_parse_nat(attr, ct, &range, l3proto);
if (err < 0)
return err;
- if (nf_nat_initialized(ct, manip))
- return -EEXIST;
return nf_nat_setup_info(ct, &range, manip);
}
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 9858e3e..52e20c9 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -363,9 +363,8 @@
goto err2;
if (!nfct_synproxy_ext_add(ct))
goto err2;
- __set_bit(IPS_TEMPLATE_BIT, &ct->status);
- __set_bit(IPS_CONFIRMED_BIT, &ct->status);
+ nf_conntrack_tmpl_insert(net, ct);
snet->tmpl = ct;
snet->stats = alloc_percpu(struct synproxy_stats);
@@ -390,7 +389,7 @@
{
struct synproxy_net *snet = synproxy_pernet(net);
- nf_conntrack_free(snet->tmpl);
+ nf_ct_put(snet->tmpl);
synproxy_proc_exit(net);
free_percpu(snet->stats);
}
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 117bbaad..33045a5 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -794,9 +794,8 @@
stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
if (chain->stats) {
- /* nfnl_lock is held, add some nfnl function for this, later */
struct nft_stats __percpu *oldstats =
- rcu_dereference_protected(chain->stats, 1);
+ nft_dereference(chain->stats);
rcu_assign_pointer(chain->stats, newstats);
synchronize_rcu();
@@ -1008,10 +1007,8 @@
return 0;
}
-static void nf_tables_rcu_chain_destroy(struct rcu_head *head)
+static void nf_tables_chain_destroy(struct nft_chain *chain)
{
- struct nft_chain *chain = container_of(head, struct nft_chain, rcu_head);
-
BUG_ON(chain->use > 0);
if (chain->flags & NFT_BASE_CHAIN) {
@@ -1045,7 +1042,7 @@
if (IS_ERR(chain))
return PTR_ERR(chain);
- if (!list_empty(&chain->rules))
+ if (!list_empty(&chain->rules) || chain->use > 0)
return -EBUSY;
list_del(&chain->list);
@@ -1059,7 +1056,9 @@
family);
/* Make sure all rule references are gone before this is released */
- call_rcu(&chain->rcu_head, nf_tables_rcu_chain_destroy);
+ synchronize_rcu();
+
+ nf_tables_chain_destroy(chain);
return 0;
}
@@ -1114,35 +1113,45 @@
}
EXPORT_SYMBOL_GPL(nft_unregister_expr);
-static const struct nft_expr_type *__nft_expr_type_get(struct nlattr *nla)
+static const struct nft_expr_type *__nft_expr_type_get(u8 family,
+ struct nlattr *nla)
{
const struct nft_expr_type *type;
list_for_each_entry(type, &nf_tables_expressions, list) {
- if (!nla_strcmp(nla, type->name))
+ if (!nla_strcmp(nla, type->name) &&
+ (!type->family || type->family == family))
return type;
}
return NULL;
}
-static const struct nft_expr_type *nft_expr_type_get(struct nlattr *nla)
+static const struct nft_expr_type *nft_expr_type_get(u8 family,
+ struct nlattr *nla)
{
const struct nft_expr_type *type;
if (nla == NULL)
return ERR_PTR(-EINVAL);
- type = __nft_expr_type_get(nla);
+ type = __nft_expr_type_get(family, nla);
if (type != NULL && try_module_get(type->owner))
return type;
#ifdef CONFIG_MODULES
if (type == NULL) {
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+ request_module("nft-expr-%u-%.*s", family,
+ nla_len(nla), (char *)nla_data(nla));
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ if (__nft_expr_type_get(family, nla))
+ return ERR_PTR(-EAGAIN);
+
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
request_module("nft-expr-%.*s",
nla_len(nla), (char *)nla_data(nla));
nfnl_lock(NFNL_SUBSYS_NFTABLES);
- if (__nft_expr_type_get(nla))
+ if (__nft_expr_type_get(family, nla))
return ERR_PTR(-EAGAIN);
}
#endif
@@ -1193,7 +1202,7 @@
if (err < 0)
return err;
- type = nft_expr_type_get(tb[NFTA_EXPR_NAME]);
+ type = nft_expr_type_get(ctx->afi->family, tb[NFTA_EXPR_NAME]);
if (IS_ERR(type))
return PTR_ERR(type);
@@ -1244,10 +1253,11 @@
return err;
}
-static void nf_tables_expr_destroy(struct nft_expr *expr)
+static void nf_tables_expr_destroy(const struct nft_ctx *ctx,
+ struct nft_expr *expr)
{
if (expr->ops->destroy)
- expr->ops->destroy(expr);
+ expr->ops->destroy(ctx, expr);
module_put(expr->ops->type->owner);
}
@@ -1286,6 +1296,8 @@
[NFTA_RULE_EXPRESSIONS] = { .type = NLA_NESTED },
[NFTA_RULE_COMPAT] = { .type = NLA_NESTED },
[NFTA_RULE_POSITION] = { .type = NLA_U64 },
+ [NFTA_RULE_USERDATA] = { .type = NLA_BINARY,
+ .len = NFT_USERDATA_MAXLEN },
};
static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq,
@@ -1338,6 +1350,10 @@
}
nla_nest_end(skb, list);
+ if (rule->ulen &&
+ nla_put(skb, NFTA_RULE_USERDATA, rule->ulen, nft_userdata(rule)))
+ goto nla_put_failure;
+
return nlmsg_end(skb, nlh);
nla_put_failure:
@@ -1521,9 +1537,9 @@
return err;
}
-static void nf_tables_rcu_rule_destroy(struct rcu_head *head)
+static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
+ struct nft_rule *rule)
{
- struct nft_rule *rule = container_of(head, struct nft_rule, rcu_head);
struct nft_expr *expr;
/*
@@ -1532,23 +1548,18 @@
*/
expr = nft_expr_first(rule);
while (expr->ops && expr != nft_expr_last(rule)) {
- nf_tables_expr_destroy(expr);
+ nf_tables_expr_destroy(ctx, expr);
expr = nft_expr_next(expr);
}
kfree(rule);
}
-static void nf_tables_rule_destroy(struct nft_rule *rule)
-{
- call_rcu(&rule->rcu_head, nf_tables_rcu_rule_destroy);
-}
-
#define NFT_RULE_MAXEXPRS 128
static struct nft_expr_info *info;
static struct nft_rule_trans *
-nf_tables_trans_add(struct nft_rule *rule, const struct nft_ctx *ctx)
+nf_tables_trans_add(struct nft_ctx *ctx, struct nft_rule *rule)
{
struct nft_rule_trans *rupd;
@@ -1556,11 +1567,8 @@
if (rupd == NULL)
return NULL;
- rupd->chain = ctx->chain;
- rupd->table = ctx->table;
+ rupd->ctx = *ctx;
rupd->rule = rule;
- rupd->family = ctx->afi->family;
- rupd->nlh = ctx->nlh;
list_add_tail(&rupd->list, &ctx->net->nft.commit_list);
return rupd;
@@ -1580,7 +1588,7 @@
struct nft_expr *expr;
struct nft_ctx ctx;
struct nlattr *tmp;
- unsigned int size, i, n;
+ unsigned int size, i, n, ulen = 0;
int err, rem;
bool create;
u64 handle, pos_handle;
@@ -1646,8 +1654,11 @@
}
}
+ if (nla[NFTA_RULE_USERDATA])
+ ulen = nla_len(nla[NFTA_RULE_USERDATA]);
+
err = -ENOMEM;
- rule = kzalloc(sizeof(*rule) + size, GFP_KERNEL);
+ rule = kzalloc(sizeof(*rule) + size + ulen, GFP_KERNEL);
if (rule == NULL)
goto err1;
@@ -1655,6 +1666,10 @@
rule->handle = handle;
rule->dlen = size;
+ rule->ulen = ulen;
+
+ if (ulen)
+ nla_memcpy(nft_userdata(rule), nla[NFTA_RULE_USERDATA], ulen);
expr = nft_expr_first(rule);
for (i = 0; i < n; i++) {
@@ -1667,7 +1682,7 @@
if (nlh->nlmsg_flags & NLM_F_REPLACE) {
if (nft_rule_is_active_next(net, old_rule)) {
- repl = nf_tables_trans_add(old_rule, &ctx);
+ repl = nf_tables_trans_add(&ctx, old_rule);
if (repl == NULL) {
err = -ENOMEM;
goto err2;
@@ -1690,7 +1705,7 @@
list_add_rcu(&rule->list, &chain->rules);
}
- if (nf_tables_trans_add(rule, &ctx) == NULL) {
+ if (nf_tables_trans_add(&ctx, rule) == NULL) {
err = -ENOMEM;
goto err3;
}
@@ -1705,7 +1720,7 @@
kfree(repl);
}
err2:
- nf_tables_rule_destroy(rule);
+ nf_tables_rule_destroy(&ctx, rule);
err1:
for (i = 0; i < n; i++) {
if (info[i].ops != NULL)
@@ -1719,7 +1734,7 @@
{
/* You cannot delete the same rule twice */
if (nft_rule_is_active_next(ctx->net, rule)) {
- if (nf_tables_trans_add(rule, ctx) == NULL)
+ if (nf_tables_trans_add(ctx, rule) == NULL)
return -ENOMEM;
nft_rule_disactivate_next(ctx->net, rule);
return 0;
@@ -1809,29 +1824,36 @@
synchronize_rcu();
list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
- /* Delete this rule from the dirty list */
- list_del(&rupd->list);
-
/* This rule was inactive in the past and just became active.
* Clear the next bit of the genmask since its meaning has
* changed, now it is the future.
*/
if (nft_rule_is_active(net, rupd->rule)) {
nft_rule_clear(net, rupd->rule);
- nf_tables_rule_notify(skb, rupd->nlh, rupd->table,
- rupd->chain, rupd->rule,
- NFT_MSG_NEWRULE, 0,
- rupd->family);
+ nf_tables_rule_notify(skb, rupd->ctx.nlh,
+ rupd->ctx.table, rupd->ctx.chain,
+ rupd->rule, NFT_MSG_NEWRULE, 0,
+ rupd->ctx.afi->family);
+ list_del(&rupd->list);
kfree(rupd);
continue;
}
/* This rule is in the past, get rid of it */
list_del_rcu(&rupd->rule->list);
- nf_tables_rule_notify(skb, rupd->nlh, rupd->table, rupd->chain,
+ nf_tables_rule_notify(skb, rupd->ctx.nlh,
+ rupd->ctx.table, rupd->ctx.chain,
rupd->rule, NFT_MSG_DELRULE, 0,
- rupd->family);
- nf_tables_rule_destroy(rupd->rule);
+ rupd->ctx.afi->family);
+ }
+
+ /* Make sure we don't see any packet traversing old rules */
+ synchronize_rcu();
+
+ /* Now we can safely release unused old rules */
+ list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
+ nf_tables_rule_destroy(&rupd->ctx, rupd->rule);
+ list_del(&rupd->list);
kfree(rupd);
}
@@ -1844,20 +1866,26 @@
struct nft_rule_trans *rupd, *tmp;
list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
- /* Delete all rules from the dirty list */
- list_del(&rupd->list);
-
if (!nft_rule_is_active_next(net, rupd->rule)) {
nft_rule_clear(net, rupd->rule);
+ list_del(&rupd->list);
kfree(rupd);
continue;
}
/* This rule is inactive, get rid of it */
list_del_rcu(&rupd->rule->list);
- nf_tables_rule_destroy(rupd->rule);
+ }
+
+ /* Make sure we don't see any packet accessing aborted rules */
+ synchronize_rcu();
+
+ list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
+ nf_tables_rule_destroy(&rupd->ctx, rupd->rule);
+ list_del(&rupd->list);
kfree(rupd);
}
+
return 0;
}
@@ -1943,6 +1971,9 @@
}
if (nla[NFTA_SET_TABLE] != NULL) {
+ if (afi == NULL)
+ return -EAFNOSUPPORT;
+
table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE]);
if (IS_ERR(table))
return PTR_ERR(table);
@@ -1989,13 +2020,13 @@
if (!sscanf(i->name, name, &tmp))
continue;
- if (tmp < 0 || tmp > BITS_PER_LONG * PAGE_SIZE)
+ if (tmp < 0 || tmp >= BITS_PER_BYTE * PAGE_SIZE)
continue;
set_bit(tmp, inuse);
}
- n = find_first_zero_bit(inuse, BITS_PER_LONG * PAGE_SIZE);
+ n = find_first_zero_bit(inuse, BITS_PER_BYTE * PAGE_SIZE);
free_page((unsigned long)inuse);
}
@@ -2411,8 +2442,7 @@
static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
{
list_del(&set->list);
- if (!(set->flags & NFT_SET_ANONYMOUS))
- nf_tables_set_notify(ctx, set, NFT_MSG_DELSET);
+ nf_tables_set_notify(ctx, set, NFT_MSG_DELSET);
set->ops->destroy(set);
module_put(set->ops->owner);
@@ -2428,6 +2458,8 @@
struct nft_ctx ctx;
int err;
+ if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
+ return -EAFNOSUPPORT;
if (nla[NFTA_SET_TABLE] == NULL)
return -EINVAL;
@@ -2435,9 +2467,6 @@
if (err < 0)
return err;
- if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
- return -EAFNOSUPPORT;
-
set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]);
if (IS_ERR(set))
return PTR_ERR(set);
@@ -2723,6 +2752,9 @@
if (nla[NFTA_SET_ELEM_DATA] == NULL &&
!(elem.flags & NFT_SET_ELEM_INTERVAL_END))
return -EINVAL;
+ if (nla[NFTA_SET_ELEM_DATA] != NULL &&
+ elem.flags & NFT_SET_ELEM_INTERVAL_END)
+ return -EINVAL;
} else {
if (nla[NFTA_SET_ELEM_DATA] != NULL)
return -EINVAL;
@@ -2977,6 +3009,9 @@
const struct nft_set_iter *iter,
const struct nft_set_elem *elem)
{
+ if (elem->flags & NFT_SET_ELEM_INTERVAL_END)
+ return 0;
+
switch (elem->data.verdict) {
case NFT_JUMP:
case NFT_GOTO:
@@ -3151,9 +3186,16 @@
data->verdict = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE]));
switch (data->verdict) {
- case NF_ACCEPT:
- case NF_DROP:
- case NF_QUEUE:
+ default:
+ switch (data->verdict & NF_VERDICT_MASK) {
+ case NF_ACCEPT:
+ case NF_DROP:
+ case NF_QUEUE:
+ break;
+ default:
+ return -EINVAL;
+ }
+ /* fall through */
case NFT_CONTINUE:
case NFT_BREAK:
case NFT_RETURN:
@@ -3174,8 +3216,6 @@
data->chain = chain;
desc->len = sizeof(data);
break;
- default:
- return -EINVAL;
}
desc->type = NFT_DATA_VERDICT;
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 0d879fc..90998a6 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -103,9 +103,9 @@
},
};
-static inline void nft_trace_packet(const struct nft_pktinfo *pkt,
- const struct nft_chain *chain,
- int rulenum, enum nft_trace type)
+static void nft_trace_packet(const struct nft_pktinfo *pkt,
+ const struct nft_chain *chain,
+ int rulenum, enum nft_trace type)
{
struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 046aa13..e8138da 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -61,6 +61,14 @@
}
EXPORT_SYMBOL_GPL(nfnl_unlock);
+#ifdef CONFIG_PROVE_LOCKING
+int lockdep_nfnl_is_held(u8 subsys_id)
+{
+ return lockdep_is_held(&table[subsys_id].mutex);
+}
+EXPORT_SYMBOL_GPL(lockdep_nfnl_is_held);
+#endif
+
int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n)
{
nfnl_lock(n->subsys_id);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index a155d19..d292c8d 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -28,8 +28,6 @@
#include <linux/proc_fs.h>
#include <linux/security.h>
#include <linux/list.h>
-#include <linux/jhash.h>
-#include <linux/random.h>
#include <linux/slab.h>
#include <net/sock.h>
#include <net/netfilter/nf_log.h>
@@ -75,7 +73,6 @@
};
#define INSTANCE_BUCKETS 16
-static unsigned int hash_init;
static int nfnl_log_net_id __read_mostly;
@@ -1067,11 +1064,6 @@
{
int status = -ENOMEM;
- /* it's not really all that important to have a random value, so
- * we can do this from the init function, even if there hasn't
- * been that much entropy yet */
- get_random_bytes(&hash_init, sizeof(hash_init));
-
netlink_register_notifier(&nfulnl_rtnl_notifier);
status = nfnetlink_subsys_register(&nfulnl_subsys);
if (status < 0) {
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index f072fe8..108120f 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -354,13 +354,16 @@
skb = nfnetlink_alloc_skb(net, size, queue->peer_portid,
GFP_ATOMIC);
- if (!skb)
+ if (!skb) {
+ skb_tx_error(entskb);
return NULL;
+ }
nlh = nlmsg_put(skb, 0, 0,
NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
sizeof(struct nfgenmsg), 0);
if (!nlh) {
+ skb_tx_error(entskb);
kfree_skb(skb);
return NULL;
}
@@ -488,13 +491,15 @@
nla->nla_type = NFQA_PAYLOAD;
nla->nla_len = nla_attr_size(data_len);
- skb_zerocopy(skb, entskb, data_len, hlen);
+ if (skb_zerocopy(skb, entskb, data_len, hlen))
+ goto nla_put_failure;
}
nlh->nlmsg_len = skb->len;
return skb;
nla_put_failure:
+ skb_tx_error(entskb);
kfree_skb(skb);
net_err_ratelimited("nf_queue: error creating packet message\n");
return NULL;
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 82cb823..8a779be 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -192,7 +192,7 @@
}
static void
-nft_target_destroy(const struct nft_expr *expr)
+nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
{
struct xt_target *target = expr->ops->data;
@@ -379,7 +379,7 @@
}
static void
-nft_match_destroy(const struct nft_expr *expr)
+nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
{
struct xt_match *match = expr->ops->data;
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 917052e..bd0d41e 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -19,15 +19,15 @@
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_labels.h>
struct nft_ct {
enum nft_ct_keys key:8;
enum ip_conntrack_dir dir:8;
- union{
+ union {
enum nft_registers dreg:8;
enum nft_registers sreg:8;
};
- uint8_t family;
};
static void nft_ct_get_eval(const struct nft_expr *expr,
@@ -97,6 +97,26 @@
goto err;
strncpy((char *)dest->data, helper->name, sizeof(dest->data));
return;
+#ifdef CONFIG_NF_CONNTRACK_LABELS
+ case NFT_CT_LABELS: {
+ struct nf_conn_labels *labels = nf_ct_labels_find(ct);
+ unsigned int size;
+
+ if (!labels) {
+ memset(dest->data, 0, sizeof(dest->data));
+ return;
+ }
+
+ BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE > sizeof(dest->data));
+ size = labels->words * sizeof(long);
+
+ memcpy(dest->data, labels->bits, size);
+ if (size < sizeof(dest->data))
+ memset(((char *) dest->data) + size, 0,
+ sizeof(dest->data) - size);
+ return;
+ }
+#endif
}
tuple = &ct->tuplehash[priv->dir].tuple;
@@ -221,11 +241,15 @@
#ifdef CONFIG_NF_CONNTRACK_SECMARK
case NFT_CT_SECMARK:
#endif
+#ifdef CONFIG_NF_CONNTRACK_LABELS
+ case NFT_CT_LABELS:
+#endif
case NFT_CT_EXPIRATION:
case NFT_CT_HELPER:
if (tb[NFTA_CT_DIRECTION] != NULL)
return -EINVAL;
break;
+ case NFT_CT_L3PROTOCOL:
case NFT_CT_PROTOCOL:
case NFT_CT_SRC:
case NFT_CT_DST:
@@ -291,16 +315,13 @@
if (err < 0)
return err;
- priv->family = ctx->afi->family;
-
return 0;
}
-static void nft_ct_destroy(const struct nft_expr *expr)
+static void nft_ct_destroy(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
{
- struct nft_ct *priv = nft_expr_priv(expr);
-
- nft_ct_l3proto_module_put(priv->family);
+ nft_ct_l3proto_module_put(ctx->afi->family);
}
static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr)
@@ -311,8 +332,19 @@
goto nla_put_failure;
if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key)))
goto nla_put_failure;
- if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir))
- goto nla_put_failure;
+
+ switch (priv->key) {
+ case NFT_CT_PROTOCOL:
+ case NFT_CT_SRC:
+ case NFT_CT_DST:
+ case NFT_CT_PROTO_SRC:
+ case NFT_CT_PROTO_DST:
+ if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir))
+ goto nla_put_failure;
+ default:
+ break;
+ }
+
return 0;
nla_put_failure:
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 3d3f8fc..3b1ad87 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -14,21 +14,34 @@
#include <linux/list.h>
#include <linux/jhash.h>
#include <linux/netlink.h>
+#include <linux/vmalloc.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
+#define NFT_HASH_MIN_SIZE 4
+
struct nft_hash {
- struct hlist_head *hash;
- unsigned int hsize;
+ struct nft_hash_table __rcu *tbl;
+};
+
+struct nft_hash_table {
+ unsigned int size;
+ unsigned int elements;
+ struct nft_hash_elem __rcu *buckets[];
};
struct nft_hash_elem {
- struct hlist_node hnode;
- struct nft_data key;
- struct nft_data data[];
+ struct nft_hash_elem __rcu *next;
+ struct nft_data key;
+ struct nft_data data[];
};
+#define nft_hash_for_each_entry(i, head) \
+ for (i = nft_dereference(head); i != NULL; i = nft_dereference(i->next))
+#define nft_hash_for_each_entry_rcu(i, head) \
+ for (i = rcu_dereference(head); i != NULL; i = rcu_dereference(i->next))
+
static u32 nft_hash_rnd __read_mostly;
static bool nft_hash_rnd_initted __read_mostly;
@@ -38,7 +51,7 @@
unsigned int h;
h = jhash(data->data, len, nft_hash_rnd);
- return ((u64)h * hsize) >> 32;
+ return h & (hsize - 1);
}
static bool nft_hash_lookup(const struct nft_set *set,
@@ -46,11 +59,12 @@
struct nft_data *data)
{
const struct nft_hash *priv = nft_set_priv(set);
+ const struct nft_hash_table *tbl = rcu_dereference(priv->tbl);
const struct nft_hash_elem *he;
unsigned int h;
- h = nft_hash_data(key, priv->hsize, set->klen);
- hlist_for_each_entry(he, &priv->hash[h], hnode) {
+ h = nft_hash_data(key, tbl->size, set->klen);
+ nft_hash_for_each_entry_rcu(he, tbl->buckets[h]) {
if (nft_data_cmp(&he->key, key, set->klen))
continue;
if (set->flags & NFT_SET_MAP)
@@ -60,19 +74,148 @@
return false;
}
-static void nft_hash_elem_destroy(const struct nft_set *set,
- struct nft_hash_elem *he)
+static void nft_hash_tbl_free(const struct nft_hash_table *tbl)
{
- nft_data_uninit(&he->key, NFT_DATA_VALUE);
- if (set->flags & NFT_SET_MAP)
- nft_data_uninit(he->data, set->dtype);
- kfree(he);
+ if (is_vmalloc_addr(tbl))
+ vfree(tbl);
+ else
+ kfree(tbl);
+}
+
+static struct nft_hash_table *nft_hash_tbl_alloc(unsigned int nbuckets)
+{
+ struct nft_hash_table *tbl;
+ size_t size;
+
+ size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
+ tbl = kzalloc(size, GFP_KERNEL | __GFP_REPEAT | __GFP_NOWARN);
+ if (tbl == NULL)
+ tbl = vzalloc(size);
+ if (tbl == NULL)
+ return NULL;
+ tbl->size = nbuckets;
+
+ return tbl;
+}
+
+static void nft_hash_chain_unzip(const struct nft_set *set,
+ const struct nft_hash_table *ntbl,
+ struct nft_hash_table *tbl, unsigned int n)
+{
+ struct nft_hash_elem *he, *last, *next;
+ unsigned int h;
+
+ he = nft_dereference(tbl->buckets[n]);
+ if (he == NULL)
+ return;
+ h = nft_hash_data(&he->key, ntbl->size, set->klen);
+
+ /* Find last element of first chain hashing to bucket h */
+ last = he;
+ nft_hash_for_each_entry(he, he->next) {
+ if (nft_hash_data(&he->key, ntbl->size, set->klen) != h)
+ break;
+ last = he;
+ }
+
+ /* Unlink first chain from the old table */
+ RCU_INIT_POINTER(tbl->buckets[n], last->next);
+
+ /* If end of chain reached, done */
+ if (he == NULL)
+ return;
+
+ /* Find first element of second chain hashing to bucket h */
+ next = NULL;
+ nft_hash_for_each_entry(he, he->next) {
+ if (nft_hash_data(&he->key, ntbl->size, set->klen) != h)
+ continue;
+ next = he;
+ break;
+ }
+
+ /* Link the two chains */
+ RCU_INIT_POINTER(last->next, next);
+}
+
+static int nft_hash_tbl_expand(const struct nft_set *set, struct nft_hash *priv)
+{
+ struct nft_hash_table *tbl = nft_dereference(priv->tbl), *ntbl;
+ struct nft_hash_elem *he;
+ unsigned int i, h;
+ bool complete;
+
+ ntbl = nft_hash_tbl_alloc(tbl->size * 2);
+ if (ntbl == NULL)
+ return -ENOMEM;
+
+ /* Link new table's buckets to first element in the old table
+ * hashing to the new bucket.
+ */
+ for (i = 0; i < ntbl->size; i++) {
+ h = i < tbl->size ? i : i - tbl->size;
+ nft_hash_for_each_entry(he, tbl->buckets[h]) {
+ if (nft_hash_data(&he->key, ntbl->size, set->klen) != i)
+ continue;
+ RCU_INIT_POINTER(ntbl->buckets[i], he);
+ break;
+ }
+ }
+ ntbl->elements = tbl->elements;
+
+ /* Publish new table */
+ rcu_assign_pointer(priv->tbl, ntbl);
+
+ /* Unzip interleaved hash chains */
+ do {
+ /* Wait for readers to use new table/unzipped chains */
+ synchronize_rcu();
+
+ complete = true;
+ for (i = 0; i < tbl->size; i++) {
+ nft_hash_chain_unzip(set, ntbl, tbl, i);
+ if (tbl->buckets[i] != NULL)
+ complete = false;
+ }
+ } while (!complete);
+
+ nft_hash_tbl_free(tbl);
+ return 0;
+}
+
+static int nft_hash_tbl_shrink(const struct nft_set *set, struct nft_hash *priv)
+{
+ struct nft_hash_table *tbl = nft_dereference(priv->tbl), *ntbl;
+ struct nft_hash_elem __rcu **pprev;
+ unsigned int i;
+
+ ntbl = nft_hash_tbl_alloc(tbl->size / 2);
+ if (ntbl == NULL)
+ return -ENOMEM;
+
+ for (i = 0; i < ntbl->size; i++) {
+ ntbl->buckets[i] = tbl->buckets[i];
+
+ for (pprev = &ntbl->buckets[i]; *pprev != NULL;
+ pprev = &nft_dereference(*pprev)->next)
+ ;
+ RCU_INIT_POINTER(*pprev, tbl->buckets[i + ntbl->size]);
+ }
+ ntbl->elements = tbl->elements;
+
+ /* Publish new table */
+ rcu_assign_pointer(priv->tbl, ntbl);
+ synchronize_rcu();
+
+ nft_hash_tbl_free(tbl);
+ return 0;
}
static int nft_hash_insert(const struct nft_set *set,
const struct nft_set_elem *elem)
{
struct nft_hash *priv = nft_set_priv(set);
+ struct nft_hash_table *tbl = nft_dereference(priv->tbl);
struct nft_hash_elem *he;
unsigned int size, h;
@@ -91,33 +234,66 @@
if (set->flags & NFT_SET_MAP)
nft_data_copy(he->data, &elem->data);
- h = nft_hash_data(&he->key, priv->hsize, set->klen);
- hlist_add_head_rcu(&he->hnode, &priv->hash[h]);
+ h = nft_hash_data(&he->key, tbl->size, set->klen);
+ RCU_INIT_POINTER(he->next, tbl->buckets[h]);
+ rcu_assign_pointer(tbl->buckets[h], he);
+ tbl->elements++;
+
+ /* Expand table when exceeding 75% load */
+ if (tbl->elements > tbl->size / 4 * 3)
+ nft_hash_tbl_expand(set, priv);
+
return 0;
}
+static void nft_hash_elem_destroy(const struct nft_set *set,
+ struct nft_hash_elem *he)
+{
+ nft_data_uninit(&he->key, NFT_DATA_VALUE);
+ if (set->flags & NFT_SET_MAP)
+ nft_data_uninit(he->data, set->dtype);
+ kfree(he);
+}
+
static void nft_hash_remove(const struct nft_set *set,
const struct nft_set_elem *elem)
{
- struct nft_hash_elem *he = elem->cookie;
+ struct nft_hash *priv = nft_set_priv(set);
+ struct nft_hash_table *tbl = nft_dereference(priv->tbl);
+ struct nft_hash_elem *he, __rcu **pprev;
- hlist_del_rcu(&he->hnode);
+ pprev = elem->cookie;
+ he = nft_dereference((*pprev));
+
+ RCU_INIT_POINTER(*pprev, he->next);
+ synchronize_rcu();
kfree(he);
+ tbl->elements--;
+
+ /* Shrink table beneath 30% load */
+ if (tbl->elements < tbl->size * 3 / 10 &&
+ tbl->size > NFT_HASH_MIN_SIZE)
+ nft_hash_tbl_shrink(set, priv);
}
static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
{
const struct nft_hash *priv = nft_set_priv(set);
+ const struct nft_hash_table *tbl = nft_dereference(priv->tbl);
+ struct nft_hash_elem __rcu * const *pprev;
struct nft_hash_elem *he;
unsigned int h;
- h = nft_hash_data(&elem->key, priv->hsize, set->klen);
- hlist_for_each_entry(he, &priv->hash[h], hnode) {
- if (nft_data_cmp(&he->key, &elem->key, set->klen))
+ h = nft_hash_data(&elem->key, tbl->size, set->klen);
+ pprev = &tbl->buckets[h];
+ nft_hash_for_each_entry(he, tbl->buckets[h]) {
+ if (nft_data_cmp(&he->key, &elem->key, set->klen)) {
+ pprev = &he->next;
continue;
+ }
- elem->cookie = he;
- elem->flags = 0;
+ elem->cookie = (void *)pprev;
+ elem->flags = 0;
if (set->flags & NFT_SET_MAP)
nft_data_copy(&elem->data, he->data);
return 0;
@@ -129,12 +305,13 @@
struct nft_set_iter *iter)
{
const struct nft_hash *priv = nft_set_priv(set);
+ const struct nft_hash_table *tbl = nft_dereference(priv->tbl);
const struct nft_hash_elem *he;
struct nft_set_elem elem;
unsigned int i;
- for (i = 0; i < priv->hsize; i++) {
- hlist_for_each_entry(he, &priv->hash[i], hnode) {
+ for (i = 0; i < tbl->size; i++) {
+ nft_hash_for_each_entry(he, tbl->buckets[i]) {
if (iter->count < iter->skip)
goto cont;
@@ -161,43 +338,35 @@
const struct nlattr * const tb[])
{
struct nft_hash *priv = nft_set_priv(set);
- unsigned int cnt, i;
+ struct nft_hash_table *tbl;
if (unlikely(!nft_hash_rnd_initted)) {
get_random_bytes(&nft_hash_rnd, 4);
nft_hash_rnd_initted = true;
}
- /* Aim for a load factor of 0.75 */
- // FIXME: temporarily broken until we have set descriptions
- cnt = 100;
- cnt = cnt * 4 / 3;
-
- priv->hash = kcalloc(cnt, sizeof(struct hlist_head), GFP_KERNEL);
- if (priv->hash == NULL)
+ tbl = nft_hash_tbl_alloc(NFT_HASH_MIN_SIZE);
+ if (tbl == NULL)
return -ENOMEM;
- priv->hsize = cnt;
-
- for (i = 0; i < cnt; i++)
- INIT_HLIST_HEAD(&priv->hash[i]);
-
+ RCU_INIT_POINTER(priv->tbl, tbl);
return 0;
}
static void nft_hash_destroy(const struct nft_set *set)
{
const struct nft_hash *priv = nft_set_priv(set);
- const struct hlist_node *next;
- struct nft_hash_elem *elem;
+ const struct nft_hash_table *tbl = nft_dereference(priv->tbl);
+ struct nft_hash_elem *he, *next;
unsigned int i;
- for (i = 0; i < priv->hsize; i++) {
- hlist_for_each_entry_safe(elem, next, &priv->hash[i], hnode) {
- hlist_del(&elem->hnode);
- nft_hash_elem_destroy(set, elem);
+ for (i = 0; i < tbl->size; i++) {
+ for (he = nft_dereference(tbl->buckets[i]); he != NULL;
+ he = next) {
+ next = nft_dereference(he->next);
+ nft_hash_elem_destroy(set, he);
}
}
- kfree(priv->hash);
+ kfree(tbl);
}
static struct nft_set_ops nft_hash_ops __read_mostly = {
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index f169501..810385e 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -70,7 +70,8 @@
return err;
}
-static void nft_immediate_destroy(const struct nft_expr *expr)
+static void nft_immediate_destroy(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
{
const struct nft_immediate_expr *priv = nft_expr_priv(expr);
return nft_data_uninit(&priv->data, nft_dreg_to_type(priv->dreg));
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 5af7901..10cfb15 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -23,7 +23,6 @@
struct nft_log {
struct nf_loginfo loginfo;
char *prefix;
- int family;
};
static void nft_log_eval(const struct nft_expr *expr,
@@ -33,7 +32,7 @@
const struct nft_log *priv = nft_expr_priv(expr);
struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
- nf_log_packet(net, priv->family, pkt->ops->hooknum, pkt->skb, pkt->in,
+ nf_log_packet(net, pkt->ops->pf, pkt->ops->hooknum, pkt->skb, pkt->in,
pkt->out, &priv->loginfo, "%s", priv->prefix);
}
@@ -52,8 +51,6 @@
struct nf_loginfo *li = &priv->loginfo;
const struct nlattr *nla;
- priv->family = ctx->afi->family;
-
nla = tb[NFTA_LOG_PREFIX];
if (nla != NULL) {
priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);
@@ -77,7 +74,8 @@
return 0;
}
-static void nft_log_destroy(const struct nft_expr *expr)
+static void nft_log_destroy(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
{
struct nft_log *priv = nft_expr_priv(expr);
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 8a6116b..7fd2bea 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -16,6 +16,7 @@
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
struct nft_lookup {
struct nft_set *set;
@@ -88,11 +89,12 @@
return 0;
}
-static void nft_lookup_destroy(const struct nft_expr *expr)
+static void nft_lookup_destroy(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
{
struct nft_lookup *priv = nft_expr_priv(expr);
- nf_tables_unbind_set(NULL, priv->set, &priv->binding);
+ nf_tables_unbind_set(ctx, priv->set, &priv->binding);
}
static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr)
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index e8254ad..425cf39 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -116,7 +116,7 @@
skb->sk->sk_socket->file->f_cred->fsgid);
read_unlock_bh(&skb->sk->sk_callback_lock);
break;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
case NFT_META_RTCLASSID: {
const struct dst_entry *dst = skb_dst(skb);
@@ -199,7 +199,7 @@
case NFT_META_OIFTYPE:
case NFT_META_SKUID:
case NFT_META_SKGID:
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
case NFT_META_RTCLASSID:
#endif
#ifdef CONFIG_NETWORK_SECMARK
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index d3b1ffe..a0195d2 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -31,8 +31,8 @@
enum nft_registers sreg_addr_max:8;
enum nft_registers sreg_proto_min:8;
enum nft_registers sreg_proto_max:8;
- int family;
- enum nf_nat_manip_type type;
+ enum nf_nat_manip_type type:8;
+ u8 family;
};
static void nft_nat_eval(const struct nft_expr *expr,
@@ -88,6 +88,7 @@
const struct nlattr * const tb[])
{
struct nft_nat *priv = nft_expr_priv(expr);
+ u32 family;
int err;
if (tb[NFTA_NAT_TYPE] == NULL)
@@ -107,9 +108,12 @@
if (tb[NFTA_NAT_FAMILY] == NULL)
return -EINVAL;
- priv->family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY]));
- if (priv->family != AF_INET && priv->family != AF_INET6)
- return -EINVAL;
+ family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY]));
+ if (family != AF_INET && family != AF_INET6)
+ return -EAFNOSUPPORT;
+ if (family != ctx->afi->family)
+ return -EOPNOTSUPP;
+ priv->family = family;
if (tb[NFTA_NAT_REG_ADDR_MIN]) {
priv->sreg_addr_min = ntohl(nla_get_be32(
@@ -202,13 +206,7 @@
static int __init nft_nat_module_init(void)
{
- int err;
-
- err = nft_register_expr(&nft_nat_type);
- if (err < 0)
- return err;
-
- return 0;
+ return nft_register_expr(&nft_nat_type);
}
static void __exit nft_nat_module_exit(void)
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index a2aeb31..85daa84 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -135,7 +135,8 @@
if (len == 0 || len > FIELD_SIZEOF(struct nft_data, data))
return ERR_PTR(-EINVAL);
- if (len <= 4 && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER)
+ if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
+ base != NFT_PAYLOAD_LL_HEADER)
return &nft_payload_fast_ops;
else
return &nft_payload_ops;
diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c
index cbea473..e8ae2f6 100644
--- a/net/netfilter/nft_queue.c
+++ b/net/netfilter/nft_queue.c
@@ -25,7 +25,6 @@
u16 queuenum;
u16 queues_total;
u16 flags;
- u8 family;
};
static void nft_queue_eval(const struct nft_expr *expr,
@@ -43,7 +42,7 @@
queue = priv->queuenum + cpu % priv->queues_total;
} else {
queue = nfqueue_hash(pkt->skb, queue,
- priv->queues_total, priv->family,
+ priv->queues_total, pkt->ops->pf,
jhash_initval);
}
}
@@ -71,7 +70,6 @@
return -EINVAL;
init_hashrandom(&jhash_initval);
- priv->family = ctx->afi->family;
priv->queuenum = ntohs(nla_get_be16(tb[NFTA_QUEUE_NUM]));
if (tb[NFTA_QUEUE_TOTAL] != NULL)
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index ca0c1b2..e21d69d 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -69,8 +69,10 @@
struct nft_rbtree_elem *rbe)
{
nft_data_uninit(&rbe->key, NFT_DATA_VALUE);
- if (set->flags & NFT_SET_MAP)
+ if (set->flags & NFT_SET_MAP &&
+ !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
nft_data_uninit(rbe->data, set->dtype);
+
kfree(rbe);
}
@@ -108,7 +110,8 @@
int err;
size = sizeof(*rbe);
- if (set->flags & NFT_SET_MAP)
+ if (set->flags & NFT_SET_MAP &&
+ !(elem->flags & NFT_SET_ELEM_INTERVAL_END))
size += sizeof(rbe->data[0]);
rbe = kzalloc(size, GFP_KERNEL);
@@ -117,7 +120,8 @@
rbe->flags = elem->flags;
nft_data_copy(&rbe->key, &elem->key);
- if (set->flags & NFT_SET_MAP)
+ if (set->flags & NFT_SET_MAP &&
+ !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
nft_data_copy(rbe->data, &elem->data);
err = __nft_rbtree_insert(set, rbe);
@@ -153,7 +157,8 @@
parent = parent->rb_right;
else {
elem->cookie = rbe;
- if (set->flags & NFT_SET_MAP)
+ if (set->flags & NFT_SET_MAP &&
+ !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
nft_data_copy(&elem->data, rbe->data);
elem->flags = rbe->flags;
return 0;
@@ -177,7 +182,8 @@
rbe = rb_entry(node, struct nft_rbtree_elem, node);
nft_data_copy(&elem.key, &rbe->key);
- if (set->flags & NFT_SET_MAP)
+ if (set->flags & NFT_SET_MAP &&
+ !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
nft_data_copy(&elem.data, rbe->data);
elem.flags = rbe->flags;
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index 5e204711..f3448c2 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -16,65 +16,23 @@
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
-#include <net/icmp.h>
-#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/nft_reject.h>
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
-#include <net/netfilter/ipv6/nf_reject.h>
-#endif
-
-struct nft_reject {
- enum nft_reject_types type:8;
- u8 icmp_code;
- u8 family;
-};
-
-static void nft_reject_eval(const struct nft_expr *expr,
- struct nft_data data[NFT_REG_MAX + 1],
- const struct nft_pktinfo *pkt)
-{
- struct nft_reject *priv = nft_expr_priv(expr);
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
- struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out);
-#endif
- switch (priv->type) {
- case NFT_REJECT_ICMP_UNREACH:
- if (priv->family == NFPROTO_IPV4)
- nf_send_unreach(pkt->skb, priv->icmp_code);
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
- else if (priv->family == NFPROTO_IPV6)
- nf_send_unreach6(net, pkt->skb, priv->icmp_code,
- pkt->ops->hooknum);
-#endif
- break;
- case NFT_REJECT_TCP_RST:
- if (priv->family == NFPROTO_IPV4)
- nf_send_reset(pkt->skb, pkt->ops->hooknum);
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
- else if (priv->family == NFPROTO_IPV6)
- nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
-#endif
- break;
- }
-
- data[NFT_REG_VERDICT].verdict = NF_DROP;
-}
-
-static const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
+const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
[NFTA_REJECT_TYPE] = { .type = NLA_U32 },
[NFTA_REJECT_ICMP_CODE] = { .type = NLA_U8 },
};
+EXPORT_SYMBOL_GPL(nft_reject_policy);
-static int nft_reject_init(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nlattr * const tb[])
+int nft_reject_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
{
struct nft_reject *priv = nft_expr_priv(expr);
if (tb[NFTA_REJECT_TYPE] == NULL)
return -EINVAL;
- priv->family = ctx->afi->family;
priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
@@ -89,8 +47,9 @@
return 0;
}
+EXPORT_SYMBOL_GPL(nft_reject_init);
-static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
+int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
const struct nft_reject *priv = nft_expr_priv(expr);
@@ -109,37 +68,7 @@
nla_put_failure:
return -1;
}
-
-static struct nft_expr_type nft_reject_type;
-static const struct nft_expr_ops nft_reject_ops = {
- .type = &nft_reject_type,
- .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
- .eval = nft_reject_eval,
- .init = nft_reject_init,
- .dump = nft_reject_dump,
-};
-
-static struct nft_expr_type nft_reject_type __read_mostly = {
- .name = "reject",
- .ops = &nft_reject_ops,
- .policy = nft_reject_policy,
- .maxattr = NFTA_REJECT_MAX,
- .owner = THIS_MODULE,
-};
-
-static int __init nft_reject_module_init(void)
-{
- return nft_register_expr(&nft_reject_type);
-}
-
-static void __exit nft_reject_module_exit(void)
-{
- nft_unregister_expr(&nft_reject_type);
-}
-
-module_init(nft_reject_module_init);
-module_exit(nft_reject_module_exit);
+EXPORT_SYMBOL_GPL(nft_reject_dump);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_EXPR("reject");
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
new file mode 100644
index 0000000..b718a52
--- /dev/null
+++ b/net/netfilter/nft_reject_inet.c
@@ -0,0 +1,63 @@
+/*
+ * Copyright (c) 2014 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+
+static void nft_reject_inet_eval(const struct nft_expr *expr,
+ struct nft_data data[NFT_REG_MAX + 1],
+ const struct nft_pktinfo *pkt)
+{
+ switch (pkt->ops->pf) {
+ case NFPROTO_IPV4:
+ return nft_reject_ipv4_eval(expr, data, pkt);
+ case NFPROTO_IPV6:
+ return nft_reject_ipv6_eval(expr, data, pkt);
+ }
+}
+
+static struct nft_expr_type nft_reject_inet_type;
+static const struct nft_expr_ops nft_reject_inet_ops = {
+ .type = &nft_reject_inet_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+ .eval = nft_reject_inet_eval,
+ .init = nft_reject_init,
+ .dump = nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_inet_type __read_mostly = {
+ .family = NFPROTO_INET,
+ .name = "reject",
+ .ops = &nft_reject_inet_ops,
+ .policy = nft_reject_policy,
+ .maxattr = NFTA_REJECT_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_reject_inet_module_init(void)
+{
+ return nft_register_expr(&nft_reject_inet_type);
+}
+
+static void __exit nft_reject_inet_module_exit(void)
+{
+ nft_unregister_expr(&nft_reject_inet_type);
+}
+
+module_init(nft_reject_inet_module_init);
+module_exit(nft_reject_inet_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_AF_EXPR(1, "reject");
diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c
index 3228d7f..4973cbd 100644
--- a/net/netfilter/xt_AUDIT.c
+++ b/net/netfilter/xt_AUDIT.c
@@ -146,11 +146,11 @@
if (par->family == NFPROTO_BRIDGE) {
switch (eth_hdr(skb)->h_proto) {
- case __constant_htons(ETH_P_IP):
+ case htons(ETH_P_IP):
audit_ip4(ab, skb);
break;
- case __constant_htons(ETH_P_IPV6):
+ case htons(ETH_P_IPV6):
audit_ip6(ab, skb);
break;
}
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 5929be6..75747ae 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -228,12 +228,7 @@
goto err3;
}
- __set_bit(IPS_TEMPLATE_BIT, &ct->status);
- __set_bit(IPS_CONFIRMED_BIT, &ct->status);
-
- /* Overload tuple linked list to put us in template list. */
- hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
- &par->net->ct.tmpl);
+ nf_conntrack_tmpl_insert(par->net, ct);
out:
info->ct = ct;
return 0;
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index c40b269..458464e 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -19,6 +19,7 @@
#include <linux/jhash.h>
#include <linux/slab.h>
#include <linux/list.h>
+#include <linux/rbtree.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/skbuff.h>
@@ -31,6 +32,10 @@
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_zones.h>
+#define CONNLIMIT_SLOTS 32
+#define CONNLIMIT_LOCK_SLOTS 32
+#define CONNLIMIT_GC_MAX_NODES 8
+
/* we will save the tuples of all connections we care about */
struct xt_connlimit_conn {
struct hlist_node node;
@@ -38,16 +43,26 @@
union nf_inet_addr addr;
};
+struct xt_connlimit_rb {
+ struct rb_node node;
+ struct hlist_head hhead; /* connections/hosts in same subnet */
+ union nf_inet_addr addr; /* search key */
+};
+
struct xt_connlimit_data {
- struct hlist_head iphash[256];
- spinlock_t lock;
+ struct rb_root climit_root4[CONNLIMIT_SLOTS];
+ struct rb_root climit_root6[CONNLIMIT_SLOTS];
+ spinlock_t locks[CONNLIMIT_LOCK_SLOTS];
};
static u_int32_t connlimit_rnd __read_mostly;
+static struct kmem_cache *connlimit_rb_cachep __read_mostly;
+static struct kmem_cache *connlimit_conn_cachep __read_mostly;
static inline unsigned int connlimit_iphash(__be32 addr)
{
- return jhash_1word((__force __u32)addr, connlimit_rnd) & 0xFF;
+ return jhash_1word((__force __u32)addr,
+ connlimit_rnd) % CONNLIMIT_SLOTS;
}
static inline unsigned int
@@ -60,7 +75,8 @@
for (i = 0; i < ARRAY_SIZE(addr->ip6); ++i)
res.ip6[i] = addr->ip6[i] & mask->ip6[i];
- return jhash2((u32 *)res.ip6, ARRAY_SIZE(res.ip6), connlimit_rnd) & 0xFF;
+ return jhash2((u32 *)res.ip6, ARRAY_SIZE(res.ip6),
+ connlimit_rnd) % CONNLIMIT_SLOTS;
}
static inline bool already_closed(const struct nf_conn *conn)
@@ -72,13 +88,14 @@
return 0;
}
-static inline unsigned int
+static int
same_source_net(const union nf_inet_addr *addr,
const union nf_inet_addr *mask,
const union nf_inet_addr *u3, u_int8_t family)
{
if (family == NFPROTO_IPV4) {
- return (addr->ip & mask->ip) == (u3->ip & mask->ip);
+ return ntohl(addr->ip & mask->ip) -
+ ntohl(u3->ip & mask->ip);
} else {
union nf_inet_addr lh, rh;
unsigned int i;
@@ -88,10 +105,179 @@
rh.ip6[i] = u3->ip6[i] & mask->ip6[i];
}
- return memcmp(&lh.ip6, &rh.ip6, sizeof(lh.ip6)) == 0;
+ return memcmp(&lh.ip6, &rh.ip6, sizeof(lh.ip6));
}
}
+static bool add_hlist(struct hlist_head *head,
+ const struct nf_conntrack_tuple *tuple,
+ const union nf_inet_addr *addr)
+{
+ struct xt_connlimit_conn *conn;
+
+ conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC);
+ if (conn == NULL)
+ return false;
+ conn->tuple = *tuple;
+ conn->addr = *addr;
+ hlist_add_head(&conn->node, head);
+ return true;
+}
+
+static unsigned int check_hlist(struct net *net,
+ struct hlist_head *head,
+ const struct nf_conntrack_tuple *tuple,
+ bool *addit)
+{
+ const struct nf_conntrack_tuple_hash *found;
+ struct xt_connlimit_conn *conn;
+ struct hlist_node *n;
+ struct nf_conn *found_ct;
+ unsigned int length = 0;
+
+ *addit = true;
+ rcu_read_lock();
+
+ /* check the saved connections */
+ hlist_for_each_entry_safe(conn, n, head, node) {
+ found = nf_conntrack_find_get(net, NF_CT_DEFAULT_ZONE,
+ &conn->tuple);
+ if (found == NULL) {
+ hlist_del(&conn->node);
+ kmem_cache_free(connlimit_conn_cachep, conn);
+ continue;
+ }
+
+ found_ct = nf_ct_tuplehash_to_ctrack(found);
+
+ if (nf_ct_tuple_equal(&conn->tuple, tuple)) {
+ /*
+ * Just to be sure we have it only once in the list.
+ * We should not see tuples twice unless someone hooks
+ * this into a table without "-p tcp --syn".
+ */
+ *addit = false;
+ } else if (already_closed(found_ct)) {
+ /*
+ * we do not care about connections which are
+ * closed already -> ditch it
+ */
+ nf_ct_put(found_ct);
+ hlist_del(&conn->node);
+ kmem_cache_free(connlimit_conn_cachep, conn);
+ continue;
+ }
+
+ nf_ct_put(found_ct);
+ length++;
+ }
+
+ rcu_read_unlock();
+
+ return length;
+}
+
+static void tree_nodes_free(struct rb_root *root,
+ struct xt_connlimit_rb *gc_nodes[],
+ unsigned int gc_count)
+{
+ struct xt_connlimit_rb *rbconn;
+
+ while (gc_count) {
+ rbconn = gc_nodes[--gc_count];
+ rb_erase(&rbconn->node, root);
+ kmem_cache_free(connlimit_rb_cachep, rbconn);
+ }
+}
+
+static unsigned int
+count_tree(struct net *net, struct rb_root *root,
+ const struct nf_conntrack_tuple *tuple,
+ const union nf_inet_addr *addr, const union nf_inet_addr *mask,
+ u8 family)
+{
+ struct xt_connlimit_rb *gc_nodes[CONNLIMIT_GC_MAX_NODES];
+ struct rb_node **rbnode, *parent;
+ struct xt_connlimit_rb *rbconn;
+ struct xt_connlimit_conn *conn;
+ unsigned int gc_count;
+ bool no_gc = false;
+
+ restart:
+ gc_count = 0;
+ parent = NULL;
+ rbnode = &(root->rb_node);
+ while (*rbnode) {
+ int diff;
+ bool addit;
+
+ rbconn = container_of(*rbnode, struct xt_connlimit_rb, node);
+
+ parent = *rbnode;
+ diff = same_source_net(addr, mask, &rbconn->addr, family);
+ if (diff < 0) {
+ rbnode = &((*rbnode)->rb_left);
+ } else if (diff > 0) {
+ rbnode = &((*rbnode)->rb_right);
+ } else {
+ /* same source network -> be counted! */
+ unsigned int count;
+ count = check_hlist(net, &rbconn->hhead, tuple, &addit);
+
+ tree_nodes_free(root, gc_nodes, gc_count);
+ if (!addit)
+ return count;
+
+ if (!add_hlist(&rbconn->hhead, tuple, addr))
+ return 0; /* hotdrop */
+
+ return count + 1;
+ }
+
+ if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes))
+ continue;
+
+ /* only used for GC on hhead, retval and 'addit' ignored */
+ check_hlist(net, &rbconn->hhead, tuple, &addit);
+ if (hlist_empty(&rbconn->hhead))
+ gc_nodes[gc_count++] = rbconn;
+ }
+
+ if (gc_count) {
+ no_gc = true;
+ tree_nodes_free(root, gc_nodes, gc_count);
+ /* tree_node_free before new allocation permits
+ * allocator to re-use newly free'd object.
+ *
+ * This is a rare event; in most cases we will find
+ * existing node to re-use. (or gc_count is 0).
+ */
+ goto restart;
+ }
+
+ /* no match, need to insert new node */
+ rbconn = kmem_cache_alloc(connlimit_rb_cachep, GFP_ATOMIC);
+ if (rbconn == NULL)
+ return 0;
+
+ conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC);
+ if (conn == NULL) {
+ kmem_cache_free(connlimit_rb_cachep, rbconn);
+ return 0;
+ }
+
+ conn->tuple = *tuple;
+ conn->addr = *addr;
+ rbconn->addr = *addr;
+
+ INIT_HLIST_HEAD(&rbconn->hhead);
+ hlist_add_head(&conn->node, &rbconn->hhead);
+
+ rb_link_node(&rbconn->node, parent, rbnode);
+ rb_insert_color(&rbconn->node, root);
+ return 1;
+}
+
static int count_them(struct net *net,
struct xt_connlimit_data *data,
const struct nf_conntrack_tuple *tuple,
@@ -99,78 +285,25 @@
const union nf_inet_addr *mask,
u_int8_t family)
{
- const struct nf_conntrack_tuple_hash *found;
- struct xt_connlimit_conn *conn;
- struct hlist_node *n;
- struct nf_conn *found_ct;
- struct hlist_head *hash;
- bool addit = true;
- int matches = 0;
+ struct rb_root *root;
+ int count;
+ u32 hash;
- if (family == NFPROTO_IPV6)
- hash = &data->iphash[connlimit_iphash6(addr, mask)];
- else
- hash = &data->iphash[connlimit_iphash(addr->ip & mask->ip)];
-
- rcu_read_lock();
-
- /* check the saved connections */
- hlist_for_each_entry_safe(conn, n, hash, node) {
- found = nf_conntrack_find_get(net, NF_CT_DEFAULT_ZONE,
- &conn->tuple);
- found_ct = NULL;
-
- if (found != NULL)
- found_ct = nf_ct_tuplehash_to_ctrack(found);
-
- if (found_ct != NULL &&
- nf_ct_tuple_equal(&conn->tuple, tuple) &&
- !already_closed(found_ct))
- /*
- * Just to be sure we have it only once in the list.
- * We should not see tuples twice unless someone hooks
- * this into a table without "-p tcp --syn".
- */
- addit = false;
-
- if (found == NULL) {
- /* this one is gone */
- hlist_del(&conn->node);
- kfree(conn);
- continue;
- }
-
- if (already_closed(found_ct)) {
- /*
- * we do not care about connections which are
- * closed already -> ditch it
- */
- nf_ct_put(found_ct);
- hlist_del(&conn->node);
- kfree(conn);
- continue;
- }
-
- if (same_source_net(addr, mask, &conn->addr, family))
- /* same source network -> be counted! */
- ++matches;
- nf_ct_put(found_ct);
+ if (family == NFPROTO_IPV6) {
+ hash = connlimit_iphash6(addr, mask);
+ root = &data->climit_root6[hash];
+ } else {
+ hash = connlimit_iphash(addr->ip & mask->ip);
+ root = &data->climit_root4[hash];
}
- rcu_read_unlock();
+ spin_lock_bh(&data->locks[hash % CONNLIMIT_LOCK_SLOTS]);
- if (addit) {
- /* save the new connection in our list */
- conn = kmalloc(sizeof(*conn), GFP_ATOMIC);
- if (conn == NULL)
- return -ENOMEM;
- conn->tuple = *tuple;
- conn->addr = *addr;
- hlist_add_head(&conn->node, hash);
- ++matches;
- }
+ count = count_tree(net, root, tuple, addr, mask, family);
- return matches;
+ spin_unlock_bh(&data->locks[hash % CONNLIMIT_LOCK_SLOTS]);
+
+ return count;
}
static bool
@@ -183,7 +316,7 @@
const struct nf_conntrack_tuple *tuple_ptr = &tuple;
enum ip_conntrack_info ctinfo;
const struct nf_conn *ct;
- int connections;
+ unsigned int connections;
ct = nf_ct_get(skb, &ctinfo);
if (ct != NULL)
@@ -202,12 +335,9 @@
iph->daddr : iph->saddr;
}
- spin_lock_bh(&info->data->lock);
connections = count_them(net, info->data, tuple_ptr, &addr,
&info->mask, par->family);
- spin_unlock_bh(&info->data->lock);
-
- if (connections < 0)
+ if (connections == 0)
/* kmalloc failed, drop it entirely */
goto hotdrop;
@@ -247,29 +377,47 @@
return -ENOMEM;
}
- spin_lock_init(&info->data->lock);
- for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i)
- INIT_HLIST_HEAD(&info->data->iphash[i]);
+ for (i = 0; i < ARRAY_SIZE(info->data->locks); ++i)
+ spin_lock_init(&info->data->locks[i]);
+
+ for (i = 0; i < ARRAY_SIZE(info->data->climit_root4); ++i)
+ info->data->climit_root4[i] = RB_ROOT;
+ for (i = 0; i < ARRAY_SIZE(info->data->climit_root6); ++i)
+ info->data->climit_root6[i] = RB_ROOT;
return 0;
}
+static void destroy_tree(struct rb_root *r)
+{
+ struct xt_connlimit_conn *conn;
+ struct xt_connlimit_rb *rbconn;
+ struct hlist_node *n;
+ struct rb_node *node;
+
+ while ((node = rb_first(r)) != NULL) {
+ rbconn = container_of(node, struct xt_connlimit_rb, node);
+
+ rb_erase(node, r);
+
+ hlist_for_each_entry_safe(conn, n, &rbconn->hhead, node)
+ kmem_cache_free(connlimit_conn_cachep, conn);
+
+ kmem_cache_free(connlimit_rb_cachep, rbconn);
+ }
+}
+
static void connlimit_mt_destroy(const struct xt_mtdtor_param *par)
{
const struct xt_connlimit_info *info = par->matchinfo;
- struct xt_connlimit_conn *conn;
- struct hlist_node *n;
- struct hlist_head *hash = info->data->iphash;
unsigned int i;
nf_ct_l3proto_module_put(par->family);
- for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) {
- hlist_for_each_entry_safe(conn, n, &hash[i], node) {
- hlist_del(&conn->node);
- kfree(conn);
- }
- }
+ for (i = 0; i < ARRAY_SIZE(info->data->climit_root4); ++i)
+ destroy_tree(&info->data->climit_root4[i]);
+ for (i = 0; i < ARRAY_SIZE(info->data->climit_root6); ++i)
+ destroy_tree(&info->data->climit_root6[i]);
kfree(info->data);
}
@@ -287,12 +435,37 @@
static int __init connlimit_mt_init(void)
{
- return xt_register_match(&connlimit_mt_reg);
+ int ret;
+
+ BUILD_BUG_ON(CONNLIMIT_LOCK_SLOTS > CONNLIMIT_SLOTS);
+ BUILD_BUG_ON((CONNLIMIT_SLOTS % CONNLIMIT_LOCK_SLOTS) != 0);
+
+ connlimit_conn_cachep = kmem_cache_create("xt_connlimit_conn",
+ sizeof(struct xt_connlimit_conn),
+ 0, 0, NULL);
+ if (!connlimit_conn_cachep)
+ return -ENOMEM;
+
+ connlimit_rb_cachep = kmem_cache_create("xt_connlimit_rb",
+ sizeof(struct xt_connlimit_rb),
+ 0, 0, NULL);
+ if (!connlimit_rb_cachep) {
+ kmem_cache_destroy(connlimit_conn_cachep);
+ return -ENOMEM;
+ }
+ ret = xt_register_match(&connlimit_mt_reg);
+ if (ret != 0) {
+ kmem_cache_destroy(connlimit_conn_cachep);
+ kmem_cache_destroy(connlimit_rb_cachep);
+ }
+ return ret;
}
static void __exit connlimit_mt_exit(void)
{
xt_unregister_match(&connlimit_mt_reg);
+ kmem_cache_destroy(connlimit_conn_cachep);
+ kmem_cache_destroy(connlimit_rb_cachep);
}
module_init(connlimit_mt_init);
diff --git a/net/netfilter/xt_ipcomp.c b/net/netfilter/xt_ipcomp.c
index a4c7561..89d5310 100644
--- a/net/netfilter/xt_ipcomp.c
+++ b/net/netfilter/xt_ipcomp.c
@@ -60,7 +60,7 @@
}
return spi_match(compinfo->spis[0], compinfo->spis[1],
- ntohl(chdr->cpi << 16),
+ ntohs(chdr->cpi),
!!(compinfo->invflags & XT_IPCOMP_INV_SPI));
}
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index fdf5135..c2d585c 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1460,7 +1460,7 @@
if (nlk->netlink_bind && nlk->groups[0]) {
int i;
- for (i=0; i<nlk->ngroups; i++) {
+ for (i = 0; i < nlk->ngroups; i++) {
if (test_bit(i, nlk->groups))
nlk->netlink_bind(i);
}
@@ -1489,8 +1489,8 @@
if (addr->sa_family != AF_NETLINK)
return -EINVAL;
- /* Only superuser is allowed to send multicasts */
- if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+ if ((nladdr->nl_groups || nladdr->nl_pid) &&
+ !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
return -EPERM;
if (!nlk->portid)
@@ -2343,6 +2343,11 @@
}
#endif
+ /* Record the max length of recvmsg() calls for future allocations */
+ nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len);
+ nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len,
+ 16384);
+
copied = data_skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
@@ -2549,7 +2554,7 @@
struct nlmsghdr *nlh;
int size = nlmsg_msg_size(len);
- nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size));
+ nlh = (struct nlmsghdr *)skb_put(skb, NLMSG_ALIGN(size));
nlh->nlmsg_type = type;
nlh->nlmsg_len = size;
nlh->nlmsg_flags = flags;
@@ -2587,7 +2592,27 @@
if (!netlink_rx_is_mmaped(sk) &&
atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
goto errout_skb;
- skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL);
+
+ /* NLMSG_GOODSIZE is small to avoid high order allocations being
+ * required, but it makes sense to _attempt_ a 16K bytes allocation
+ * to reduce number of system calls on dump operations, if user
+ * ever provided a big enough buffer.
+ */
+ if (alloc_size < nlk->max_recvmsg_len) {
+ skb = netlink_alloc_skb(sk,
+ nlk->max_recvmsg_len,
+ nlk->portid,
+ GFP_KERNEL |
+ __GFP_NOWARN |
+ __GFP_NORETRY);
+ /* available room should be exact amount to avoid MSG_TRUNC */
+ if (skb)
+ skb_reserve(skb, skb_tailroom(skb) -
+ nlk->max_recvmsg_len);
+ }
+ if (!skb)
+ skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
+ GFP_KERNEL);
if (!skb)
goto errout_skb;
netlink_skb_set_owner_r(skb, sk);
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index acbd774..ed13a79 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -31,6 +31,7 @@
u32 ngroups;
unsigned long *groups;
unsigned long state;
+ size_t max_recvmsg_len;
wait_queue_head_t wait;
bool cb_running;
struct netlink_callback cb;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index df46928..a3276e3 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -55,6 +55,7 @@
#include "datapath.h"
#include "flow.h"
+#include "flow_table.h"
#include "flow_netlink.h"
#include "vport-internal_dev.h"
#include "vport-netdev.h"
@@ -160,7 +161,6 @@
{
struct datapath *dp = container_of(rcu, struct datapath, rcu);
- ovs_flow_tbl_destroy(&dp->table);
free_percpu(dp->stats_percpu);
release_net(ovs_dp_get_net(dp));
kfree(dp->ports);
@@ -256,10 +256,10 @@
out:
/* Update datapath statistics. */
- u64_stats_update_begin(&stats->sync);
+ u64_stats_update_begin(&stats->syncp);
(*stats_counter)++;
stats->n_mask_hit += n_mask_hit;
- u64_stats_update_end(&stats->sync);
+ u64_stats_update_end(&stats->syncp);
}
static struct genl_family dp_packet_genl_family = {
@@ -295,9 +295,9 @@
err:
stats = this_cpu_ptr(dp->stats_percpu);
- u64_stats_update_begin(&stats->sync);
+ u64_stats_update_begin(&stats->syncp);
stats->n_lost++;
- u64_stats_update_end(&stats->sync);
+ u64_stats_update_end(&stats->syncp);
return err;
}
@@ -464,12 +464,24 @@
}
nla->nla_len = nla_attr_size(skb->len);
- skb_zerocopy(user_skb, skb, skb->len, hlen);
+ err = skb_zerocopy(user_skb, skb, skb->len, hlen);
+ if (err)
+ goto out;
+
+ /* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */
+ if (!(dp->user_features & OVS_DP_F_UNALIGNED)) {
+ size_t plen = NLA_ALIGN(user_skb->len) - user_skb->len;
+
+ if (plen > 0)
+ memset(skb_put(user_skb, plen), 0, plen);
+ }
((struct nlmsghdr *) user_skb->data)->nlmsg_len = user_skb->len;
err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid);
out:
+ if (err)
+ skb_tx_error(skb);
kfree_skb(nskb);
return err;
}
@@ -598,9 +610,9 @@
percpu_stats = per_cpu_ptr(dp->stats_percpu, i);
do {
- start = u64_stats_fetch_begin_bh(&percpu_stats->sync);
+ start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
local_stats = *percpu_stats;
- } while (u64_stats_fetch_retry_bh(&percpu_stats->sync, start));
+ } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
stats->n_hit += local_stats.n_hit;
stats->n_missed += local_stats.n_missed;
@@ -852,11 +864,8 @@
goto err_unlock_ovs;
/* The unmasked key has to be the same for flow updates. */
- error = -EINVAL;
- if (!ovs_flow_cmp_unmasked_key(flow, &match)) {
- OVS_NLERR("Flow modification message rejected, unmasked key does not match.\n");
+ if (!ovs_flow_cmp_unmasked_key(flow, &match))
goto err_unlock_ovs;
- }
/* Update actions. */
old_acts = ovsl_dereference(flow->sf_acts);
@@ -1079,6 +1088,7 @@
msgsize += nla_total_size(IFNAMSIZ);
msgsize += nla_total_size(sizeof(struct ovs_dp_stats));
msgsize += nla_total_size(sizeof(struct ovs_dp_megaflow_stats));
+ msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_USER_FEATURES */
return msgsize;
}
@@ -1168,7 +1178,7 @@
struct datapath *dp;
dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
- if (!dp)
+ if (IS_ERR(dp))
return;
WARN(dp->user_features, "Dropping previously announced user features\n");
@@ -1209,18 +1219,12 @@
if (err)
goto err_free_dp;
- dp->stats_percpu = alloc_percpu(struct dp_stats_percpu);
+ dp->stats_percpu = netdev_alloc_pcpu_stats(struct dp_stats_percpu);
if (!dp->stats_percpu) {
err = -ENOMEM;
goto err_destroy_table;
}
- for_each_possible_cpu(i) {
- struct dp_stats_percpu *dpath_stats;
- dpath_stats = per_cpu_ptr(dp->stats_percpu, i);
- u64_stats_init(&dpath_stats->sync);
- }
-
dp->ports = kmalloc(DP_VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
GFP_KERNEL);
if (!dp->ports) {
@@ -1279,7 +1283,7 @@
err_destroy_percpu:
free_percpu(dp->stats_percpu);
err_destroy_table:
- ovs_flow_tbl_destroy(&dp->table);
+ ovs_flow_tbl_destroy(&dp->table, false);
err_free_dp:
release_net(ovs_dp_get_net(dp));
kfree(dp);
@@ -1306,10 +1310,13 @@
list_del_rcu(&dp->list_node);
/* OVSP_LOCAL is datapath internal port. We need to make sure that
- * all port in datapath are destroyed first before freeing datapath.
+ * all ports in datapath are destroyed first before freeing datapath.
*/
ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL));
+ /* RCU destroy the flow table */
+ ovs_flow_tbl_destroy(&dp->table, true);
+
call_rcu(&dp->rcu, destroy_dp_rcu);
}
@@ -1753,11 +1760,12 @@
int bucket = cb->args[0], skip = cb->args[1];
int i, j = 0;
- dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
- if (!dp)
- return -ENODEV;
-
rcu_read_lock();
+ dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+ if (!dp) {
+ rcu_read_unlock();
+ return -ENODEV;
+ }
for (i = bucket; i < DP_VPORT_HASH_BUCKETS; i++) {
struct vport *vport;
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 6be9fbb..0531738 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -55,7 +55,7 @@
u64 n_missed;
u64 n_lost;
u64 n_mask_hit;
- struct u64_stats_sync sync;
+ struct u64_stats_sync syncp;
};
/**
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 16f4b46..2998989 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -73,6 +73,7 @@
if ((flow->key.eth.type == htons(ETH_P_IP) ||
flow->key.eth.type == htons(ETH_P_IPV6)) &&
+ flow->key.ip.frag != OVS_FRAG_TYPE_LATER &&
flow->key.ip.proto == IPPROTO_TCP &&
likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) {
tcp_flags = TCP_FLAGS_BE16(tcp_hdr(skb));
@@ -91,7 +92,7 @@
unsigned long *used, __be16 *tcp_flags)
{
spin_lock(&stats->lock);
- if (time_after(stats->used, *used))
+ if (!*used || time_after(stats->used, *used))
*used = stats->used;
*tcp_flags |= stats->tcp_flags;
ovs_stats->n_packets += stats->packet_count;
@@ -102,30 +103,24 @@
void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats,
unsigned long *used, __be16 *tcp_flags)
{
- int cpu, cur_cpu;
+ int cpu;
*used = 0;
*tcp_flags = 0;
memset(ovs_stats, 0, sizeof(*ovs_stats));
+ local_bh_disable();
if (!flow->stats.is_percpu) {
stats_read(flow->stats.stat, ovs_stats, used, tcp_flags);
} else {
- cur_cpu = get_cpu();
for_each_possible_cpu(cpu) {
struct flow_stats *stats;
- if (cpu == cur_cpu)
- local_bh_disable();
-
stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
stats_read(stats, ovs_stats, used, tcp_flags);
-
- if (cpu == cur_cpu)
- local_bh_enable();
}
- put_cpu();
}
+ local_bh_enable();
}
static void stats_reset(struct flow_stats *stats)
@@ -140,25 +135,17 @@
void ovs_flow_stats_clear(struct sw_flow *flow)
{
- int cpu, cur_cpu;
+ int cpu;
+ local_bh_disable();
if (!flow->stats.is_percpu) {
stats_reset(flow->stats.stat);
} else {
- cur_cpu = get_cpu();
-
for_each_possible_cpu(cpu) {
-
- if (cpu == cur_cpu)
- local_bh_disable();
-
stats_reset(per_cpu_ptr(flow->stats.cpu_stats, cpu));
-
- if (cpu == cur_cpu)
- local_bh_enable();
}
- put_cpu();
}
+ local_bh_enable();
}
static int check_header(struct sk_buff *skb, int len)
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index c58a0fe..3c268b3 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -153,29 +153,29 @@
flow_free(flow);
}
-static void flow_mask_del_ref(struct sw_flow_mask *mask, bool deferred)
-{
- if (!mask)
- return;
-
- BUG_ON(!mask->ref_count);
- mask->ref_count--;
-
- if (!mask->ref_count) {
- list_del_rcu(&mask->list);
- if (deferred)
- kfree_rcu(mask, rcu);
- else
- kfree(mask);
- }
-}
-
void ovs_flow_free(struct sw_flow *flow, bool deferred)
{
if (!flow)
return;
- flow_mask_del_ref(flow->mask, deferred);
+ if (flow->mask) {
+ struct sw_flow_mask *mask = flow->mask;
+
+ /* ovs-lock is required to protect mask-refcount and
+ * mask list.
+ */
+ ASSERT_OVSL();
+ BUG_ON(!mask->ref_count);
+ mask->ref_count--;
+
+ if (!mask->ref_count) {
+ list_del_rcu(&mask->list);
+ if (deferred)
+ kfree_rcu(mask, rcu);
+ else
+ kfree(mask);
+ }
+ }
if (deferred)
call_rcu(&flow->rcu, rcu_free_flow_callback);
@@ -188,26 +188,9 @@
flex_array_free(buckets);
}
+
static void __table_instance_destroy(struct table_instance *ti)
{
- int i;
-
- if (ti->keep_flows)
- goto skip_flows;
-
- for (i = 0; i < ti->n_buckets; i++) {
- struct sw_flow *flow;
- struct hlist_head *head = flex_array_get(ti->buckets, i);
- struct hlist_node *n;
- int ver = ti->node_ver;
-
- hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
- hlist_del(&flow->hash_node[ver]);
- ovs_flow_free(flow, false);
- }
- }
-
-skip_flows:
free_buckets(ti->buckets);
kfree(ti);
}
@@ -258,20 +241,38 @@
static void table_instance_destroy(struct table_instance *ti, bool deferred)
{
+ int i;
+
if (!ti)
return;
+ if (ti->keep_flows)
+ goto skip_flows;
+
+ for (i = 0; i < ti->n_buckets; i++) {
+ struct sw_flow *flow;
+ struct hlist_head *head = flex_array_get(ti->buckets, i);
+ struct hlist_node *n;
+ int ver = ti->node_ver;
+
+ hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
+ hlist_del_rcu(&flow->hash_node[ver]);
+ ovs_flow_free(flow, deferred);
+ }
+ }
+
+skip_flows:
if (deferred)
call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
else
__table_instance_destroy(ti);
}
-void ovs_flow_tbl_destroy(struct flow_table *table)
+void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred)
{
struct table_instance *ti = ovsl_dereference(table->ti);
- table_instance_destroy(ti, false);
+ table_instance_destroy(ti, deferred);
}
struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,
@@ -504,16 +505,11 @@
mask = kmalloc(sizeof(*mask), GFP_KERNEL);
if (mask)
- mask->ref_count = 0;
+ mask->ref_count = 1;
return mask;
}
-static void mask_add_ref(struct sw_flow_mask *mask)
-{
- mask->ref_count++;
-}
-
static bool mask_equal(const struct sw_flow_mask *a,
const struct sw_flow_mask *b)
{
@@ -554,9 +550,11 @@
mask->key = new->key;
mask->range = new->range;
list_add_rcu(&mask->list, &tbl->mask_list);
+ } else {
+ BUG_ON(!mask->ref_count);
+ mask->ref_count++;
}
- mask_add_ref(mask);
flow->mask = mask;
return 0;
}
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 1996e34..baaeb10 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -60,7 +60,7 @@
int ovs_flow_tbl_init(struct flow_table *);
int ovs_flow_tbl_count(struct flow_table *table);
-void ovs_flow_tbl_destroy(struct flow_table *table);
+void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred);
int ovs_flow_tbl_flush(struct flow_table *flow_table);
int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 208dd9a..42c0f4a 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -121,7 +121,6 @@
{
struct vport *vport;
size_t alloc_size;
- int i;
alloc_size = sizeof(struct vport);
if (priv_size) {
@@ -139,19 +138,12 @@
vport->ops = ops;
INIT_HLIST_NODE(&vport->dp_hash_node);
- vport->percpu_stats = alloc_percpu(struct pcpu_sw_netstats);
+ vport->percpu_stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!vport->percpu_stats) {
kfree(vport);
return ERR_PTR(-ENOMEM);
}
- for_each_possible_cpu(i) {
- struct pcpu_sw_netstats *vport_stats;
- vport_stats = per_cpu_ptr(vport->percpu_stats, i);
- u64_stats_init(&vport_stats->syncp);
- }
-
-
spin_lock_init(&vport->stats_lock);
return vport;
@@ -285,9 +277,9 @@
percpu_stats = per_cpu_ptr(vport->percpu_stats, i);
do {
- start = u64_stats_fetch_begin_bh(&percpu_stats->syncp);
+ start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
local_stats = *percpu_stats;
- } while (u64_stats_fetch_retry_bh(&percpu_stats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
stats->rx_bytes += local_stats.rx_bytes;
stats->rx_packets += local_stats.rx_packets;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 6a2bb37..01039d2 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -243,40 +243,40 @@
const struct net_device_ops *ops = dev->netdev_ops;
netdev_features_t features;
struct netdev_queue *txq;
+ int ret = NETDEV_TX_BUSY;
u16 queue_map;
- int ret;
if (unlikely(!netif_running(dev) ||
- !netif_carrier_ok(dev))) {
- kfree_skb(skb);
- return NET_XMIT_DROP;
- }
+ !netif_carrier_ok(dev)))
+ goto drop;
features = netif_skb_features(skb);
if (skb_needs_linearize(skb, features) &&
- __skb_linearize(skb)) {
- kfree_skb(skb);
- return NET_XMIT_DROP;
- }
+ __skb_linearize(skb))
+ goto drop;
queue_map = skb_get_queue_mapping(skb);
txq = netdev_get_tx_queue(dev, queue_map);
- __netif_tx_lock_bh(txq);
- if (unlikely(netif_xmit_frozen_or_stopped(txq))) {
- ret = NETDEV_TX_BUSY;
- kfree_skb(skb);
- goto out;
- }
+ local_bh_disable();
- ret = ops->ndo_start_xmit(skb, dev);
- if (likely(dev_xmit_complete(ret)))
- txq_trans_update(txq);
- else
+ HARD_TX_LOCK(dev, txq, smp_processor_id());
+ if (!netif_xmit_frozen_or_stopped(txq)) {
+ ret = ops->ndo_start_xmit(skb, dev);
+ if (ret == NETDEV_TX_OK)
+ txq_trans_update(txq);
+ }
+ HARD_TX_UNLOCK(dev, txq);
+
+ local_bh_enable();
+
+ if (!dev_xmit_complete(ret))
kfree_skb(skb);
-out:
- __netif_tx_unlock_bh(txq);
+
return ret;
+drop:
+ kfree_skb(skb);
+ return NET_XMIT_DROP;
}
static struct net_device *packet_cached_dev_get(struct packet_sock *po)
@@ -308,11 +308,27 @@
return po->xmit == packet_direct_xmit;
}
-static u16 packet_pick_tx_queue(struct net_device *dev)
+static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
{
return (u16) raw_smp_processor_id() % dev->real_num_tx_queues;
}
+static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ u16 queue_index;
+
+ if (ops->ndo_select_queue) {
+ queue_index = ops->ndo_select_queue(dev, skb, NULL,
+ __packet_pick_tx_queue);
+ queue_index = netdev_cap_txqueue(dev, queue_index);
+ } else {
+ queue_index = __packet_pick_tx_queue(dev, skb);
+ }
+
+ skb_set_queue_mapping(skb, queue_index);
+}
+
/* register_prot_hook must be invoked with the po->bind_lock held,
* or from a context in which asynchronous accesses to the packet
* socket is not possible (packet_create()).
@@ -1261,7 +1277,7 @@
struct sk_buff *skb,
unsigned int num)
{
- return reciprocal_scale(skb->rxhash, num);
+ return reciprocal_scale(skb_get_hash(skb), num);
}
static unsigned int fanout_demux_lb(struct packet_fanout *f,
@@ -1346,7 +1362,6 @@
if (!skb)
return 0;
}
- skb_get_hash(skb);
idx = fanout_demux_hash(f, skb, num);
break;
case PACKET_FANOUT_LB:
@@ -2241,8 +2256,7 @@
if (unlikely(!(dev->flags & IFF_UP)))
goto out_put;
- reserve = dev->hard_header_len;
-
+ reserve = dev->hard_header_len + VLAN_HLEN;
size_max = po->tx_ring.frame_size
- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
@@ -2269,8 +2283,19 @@
goto out_status;
tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
- addr, hlen);
+ addr, hlen);
+ if (tp_len > dev->mtu + dev->hard_header_len) {
+ struct ethhdr *ehdr;
+ /* Earlier code assumed this would be a VLAN pkt,
+ * double-check this now that we have the actual
+ * packet in hand.
+ */
+ skb_reset_mac_header(skb);
+ ehdr = eth_hdr(skb);
+ if (ehdr->h_proto != htons(ETH_P_8021Q))
+ tp_len = -EMSGSIZE;
+ }
if (unlikely(tp_len < 0)) {
if (po->tp_loss) {
__packet_set_status(po, ph,
@@ -2285,7 +2310,8 @@
}
}
- skb_set_queue_mapping(skb, packet_pick_tx_queue(dev));
+ packet_pick_tx_queue(dev, skb);
+
skb->destructor = tpacket_destruct_skb;
__packet_set_status(po, ph, TP_STATUS_SENDING);
packet_inc_pending(&po->tx_ring);
@@ -2499,7 +2525,8 @@
skb->dev = dev;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
- skb_set_queue_mapping(skb, packet_pick_tx_queue(dev));
+
+ packet_pick_tx_queue(dev, skb);
if (po->has_vnet_hdr) {
if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
@@ -3786,7 +3813,7 @@
*/
if (!tx_ring)
init_prb_bdqc(po, rb, pg_vec, req_u, tx_ring);
- break;
+ break;
default:
break;
}
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile
index d1c3429..ec126f9 100644
--- a/net/rxrpc/Makefile
+++ b/net/rxrpc/Makefile
@@ -20,9 +20,8 @@
ar-skbuff.o \
ar-transport.o
-ifeq ($(CONFIG_PROC_FS),y)
-af-rxrpc-y += ar-proc.o
-endif
+af-rxrpc-$(CONFIG_PROC_FS) += ar-proc.o
+af-rxrpc-$(CONFIG_SYSCTL) += sysctl.o
obj-$(CONFIG_AF_RXRPC) += af-rxrpc.o
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index e61aa60..7b16704 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -838,6 +838,12 @@
goto error_key_type_s;
}
+ ret = rxrpc_sysctl_init();
+ if (ret < 0) {
+ printk(KERN_CRIT "RxRPC: Cannot register sysctls\n");
+ goto error_sysctls;
+ }
+
#ifdef CONFIG_PROC_FS
proc_create("rxrpc_calls", 0, init_net.proc_net, &rxrpc_call_seq_fops);
proc_create("rxrpc_conns", 0, init_net.proc_net,
@@ -845,6 +851,8 @@
#endif
return 0;
+error_sysctls:
+ unregister_key_type(&key_type_rxrpc_s);
error_key_type_s:
unregister_key_type(&key_type_rxrpc);
error_key_type:
@@ -865,6 +873,7 @@
static void __exit af_rxrpc_exit(void)
{
_enter("");
+ rxrpc_sysctl_exit();
unregister_key_type(&key_type_rxrpc_s);
unregister_key_type(&key_type_rxrpc);
sock_unregister(PF_RXRPC);
diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c
index cd97a0c..c6be17a 100644
--- a/net/rxrpc/ar-ack.c
+++ b/net/rxrpc/ar-ack.c
@@ -19,7 +19,49 @@
#include <net/af_rxrpc.h>
#include "ar-internal.h"
-static unsigned int rxrpc_ack_defer = 1;
+/*
+ * How long to wait before scheduling ACK generation after seeing a
+ * packet with RXRPC_REQUEST_ACK set (in jiffies).
+ */
+unsigned rxrpc_requested_ack_delay = 1;
+
+/*
+ * How long to wait before scheduling an ACK with subtype DELAY (in jiffies).
+ *
+ * We use this when we've received new data packets. If those packets aren't
+ * all consumed within this time we will send a DELAY ACK if an ACK was not
+ * requested to let the sender know it doesn't need to resend.
+ */
+unsigned rxrpc_soft_ack_delay = 1 * HZ;
+
+/*
+ * How long to wait before scheduling an ACK with subtype IDLE (in jiffies).
+ *
+ * We use this when we've consumed some previously soft-ACK'd packets when
+ * further packets aren't immediately received to decide when to send an IDLE
+ * ACK let the other end know that it can free up its Tx buffer space.
+ */
+unsigned rxrpc_idle_ack_delay = 0.5 * HZ;
+
+/*
+ * Receive window size in packets. This indicates the maximum number of
+ * unconsumed received packets we're willing to retain in memory. Once this
+ * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further
+ * packets.
+ */
+unsigned rxrpc_rx_window_size = 32;
+
+/*
+ * Maximum Rx MTU size. This indicates to the sender the size of jumbo packet
+ * made by gluing normal packets together that we're willing to handle.
+ */
+unsigned rxrpc_rx_mtu = 5692;
+
+/*
+ * The maximum number of fragments in a received jumbo packet that we tell the
+ * sender that we're willing to handle.
+ */
+unsigned rxrpc_rx_jumbo_max = 4;
static const char *rxrpc_acks(u8 reason)
{
@@ -82,24 +124,23 @@
switch (ack_reason) {
case RXRPC_ACK_DELAY:
_debug("run delay timer");
- call->ack_timer.expires = jiffies + rxrpc_ack_timeout * HZ;
- add_timer(&call->ack_timer);
- return;
+ expiry = rxrpc_soft_ack_delay;
+ goto run_timer;
case RXRPC_ACK_IDLE:
if (!immediate) {
_debug("run defer timer");
- expiry = 1;
+ expiry = rxrpc_idle_ack_delay;
goto run_timer;
}
goto cancel_timer;
case RXRPC_ACK_REQUESTED:
- if (!rxrpc_ack_defer)
+ expiry = rxrpc_requested_ack_delay;
+ if (!expiry)
goto cancel_timer;
if (!immediate || serial == cpu_to_be32(1)) {
_debug("run defer timer");
- expiry = rxrpc_ack_defer;
goto run_timer;
}
@@ -1174,11 +1215,11 @@
mtu = call->conn->trans->peer->if_mtu;
mtu -= call->conn->trans->peer->hdrsize;
ackinfo.maxMTU = htonl(mtu);
- ackinfo.rwind = htonl(32);
+ ackinfo.rwind = htonl(rxrpc_rx_window_size);
/* permit the peer to send us jumbo packets if it wants to */
- ackinfo.rxMTU = htonl(5692);
- ackinfo.jumbo_max = htonl(4);
+ ackinfo.rxMTU = htonl(rxrpc_rx_mtu);
+ ackinfo.jumbo_max = htonl(rxrpc_rx_jumbo_max);
hdr.serial = htonl(atomic_inc_return(&call->conn->serial));
_proto("Tx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }",
diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/ar-call.c
index a3bbb36..a9e05db 100644
--- a/net/rxrpc/ar-call.c
+++ b/net/rxrpc/ar-call.c
@@ -12,10 +12,22 @@
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/circ_buf.h>
+#include <linux/hashtable.h>
+#include <linux/spinlock_types.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"
+/*
+ * Maximum lifetime of a call (in jiffies).
+ */
+unsigned rxrpc_max_call_lifetime = 60 * HZ;
+
+/*
+ * Time till dead call expires after last use (in jiffies).
+ */
+unsigned rxrpc_dead_call_expiry = 2 * HZ;
+
const char *const rxrpc_call_states[] = {
[RXRPC_CALL_CLIENT_SEND_REQUEST] = "ClSndReq",
[RXRPC_CALL_CLIENT_AWAIT_REPLY] = "ClAwtRpl",
@@ -38,8 +50,6 @@
struct kmem_cache *rxrpc_call_jar;
LIST_HEAD(rxrpc_calls);
DEFINE_RWLOCK(rxrpc_call_lock);
-static unsigned int rxrpc_call_max_lifetime = 60;
-static unsigned int rxrpc_dead_call_timeout = 2;
static void rxrpc_destroy_call(struct work_struct *work);
static void rxrpc_call_life_expired(unsigned long _call);
@@ -47,6 +57,145 @@
static void rxrpc_ack_time_expired(unsigned long _call);
static void rxrpc_resend_time_expired(unsigned long _call);
+static DEFINE_SPINLOCK(rxrpc_call_hash_lock);
+static DEFINE_HASHTABLE(rxrpc_call_hash, 10);
+
+/*
+ * Hash function for rxrpc_call_hash
+ */
+static unsigned long rxrpc_call_hashfunc(
+ u8 clientflag,
+ __be32 cid,
+ __be32 call_id,
+ __be32 epoch,
+ __be16 service_id,
+ sa_family_t proto,
+ void *localptr,
+ unsigned int addr_size,
+ const u8 *peer_addr)
+{
+ const u16 *p;
+ unsigned int i;
+ unsigned long key;
+ u32 hcid = ntohl(cid);
+
+ _enter("");
+
+ key = (unsigned long)localptr;
+ /* We just want to add up the __be32 values, so forcing the
+ * cast should be okay.
+ */
+ key += (__force u32)epoch;
+ key += (__force u16)service_id;
+ key += (__force u32)call_id;
+ key += (hcid & RXRPC_CIDMASK) >> RXRPC_CIDSHIFT;
+ key += hcid & RXRPC_CHANNELMASK;
+ key += clientflag;
+ key += proto;
+ /* Step through the peer address in 16-bit portions for speed */
+ for (i = 0, p = (const u16 *)peer_addr; i < addr_size >> 1; i++, p++)
+ key += *p;
+ _leave(" key = 0x%lx", key);
+ return key;
+}
+
+/*
+ * Add a call to the hashtable
+ */
+static void rxrpc_call_hash_add(struct rxrpc_call *call)
+{
+ unsigned long key;
+ unsigned int addr_size = 0;
+
+ _enter("");
+ switch (call->proto) {
+ case AF_INET:
+ addr_size = sizeof(call->peer_ip.ipv4_addr);
+ break;
+ case AF_INET6:
+ addr_size = sizeof(call->peer_ip.ipv6_addr);
+ break;
+ default:
+ break;
+ }
+ key = rxrpc_call_hashfunc(call->in_clientflag, call->cid,
+ call->call_id, call->epoch,
+ call->service_id, call->proto,
+ call->conn->trans->local, addr_size,
+ call->peer_ip.ipv6_addr);
+ /* Store the full key in the call */
+ call->hash_key = key;
+ spin_lock(&rxrpc_call_hash_lock);
+ hash_add_rcu(rxrpc_call_hash, &call->hash_node, key);
+ spin_unlock(&rxrpc_call_hash_lock);
+ _leave("");
+}
+
+/*
+ * Remove a call from the hashtable
+ */
+static void rxrpc_call_hash_del(struct rxrpc_call *call)
+{
+ _enter("");
+ spin_lock(&rxrpc_call_hash_lock);
+ hash_del_rcu(&call->hash_node);
+ spin_unlock(&rxrpc_call_hash_lock);
+ _leave("");
+}
+
+/*
+ * Find a call in the hashtable and return it, or NULL if it
+ * isn't there.
+ */
+struct rxrpc_call *rxrpc_find_call_hash(
+ u8 clientflag,
+ __be32 cid,
+ __be32 call_id,
+ __be32 epoch,
+ __be16 service_id,
+ void *localptr,
+ sa_family_t proto,
+ const u8 *peer_addr)
+{
+ unsigned long key;
+ unsigned int addr_size = 0;
+ struct rxrpc_call *call = NULL;
+ struct rxrpc_call *ret = NULL;
+
+ _enter("");
+ switch (proto) {
+ case AF_INET:
+ addr_size = sizeof(call->peer_ip.ipv4_addr);
+ break;
+ case AF_INET6:
+ addr_size = sizeof(call->peer_ip.ipv6_addr);
+ break;
+ default:
+ break;
+ }
+
+ key = rxrpc_call_hashfunc(clientflag, cid, call_id, epoch,
+ service_id, proto, localptr, addr_size,
+ peer_addr);
+ hash_for_each_possible_rcu(rxrpc_call_hash, call, hash_node, key) {
+ if (call->hash_key == key &&
+ call->call_id == call_id &&
+ call->cid == cid &&
+ call->in_clientflag == clientflag &&
+ call->service_id == service_id &&
+ call->proto == proto &&
+ call->local == localptr &&
+ memcmp(call->peer_ip.ipv6_addr, peer_addr,
+ addr_size) == 0 &&
+ call->epoch == epoch) {
+ ret = call;
+ break;
+ }
+ }
+ _leave(" = %p", ret);
+ return ret;
+}
+
/*
* allocate a new call
*/
@@ -91,7 +240,7 @@
call->rx_data_expect = 1;
call->rx_data_eaten = 0;
call->rx_first_oos = 0;
- call->ackr_win_top = call->rx_data_eaten + 1 + RXRPC_MAXACKS;
+ call->ackr_win_top = call->rx_data_eaten + 1 + rxrpc_rx_window_size;
call->creation_jif = jiffies;
return call;
}
@@ -128,11 +277,31 @@
return ERR_PTR(ret);
}
+ /* Record copies of information for hashtable lookup */
+ call->proto = rx->proto;
+ call->local = trans->local;
+ switch (call->proto) {
+ case AF_INET:
+ call->peer_ip.ipv4_addr =
+ trans->peer->srx.transport.sin.sin_addr.s_addr;
+ break;
+ case AF_INET6:
+ memcpy(call->peer_ip.ipv6_addr,
+ trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8,
+ sizeof(call->peer_ip.ipv6_addr));
+ break;
+ }
+ call->epoch = call->conn->epoch;
+ call->service_id = call->conn->service_id;
+ call->in_clientflag = call->conn->in_clientflag;
+ /* Add the new call to the hashtable */
+ rxrpc_call_hash_add(call);
+
spin_lock(&call->conn->trans->peer->lock);
list_add(&call->error_link, &call->conn->trans->peer->error_targets);
spin_unlock(&call->conn->trans->peer->lock);
- call->lifetimer.expires = jiffies + rxrpc_call_max_lifetime * HZ;
+ call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime;
add_timer(&call->lifetimer);
_leave(" = %p", call);
@@ -320,9 +489,12 @@
parent = *p;
call = rb_entry(parent, struct rxrpc_call, conn_node);
- if (call_id < call->call_id)
+ /* The tree is sorted in order of the __be32 value without
+ * turning it into host order.
+ */
+ if ((__force u32)call_id < (__force u32)call->call_id)
p = &(*p)->rb_left;
- else if (call_id > call->call_id)
+ else if ((__force u32)call_id > (__force u32)call->call_id)
p = &(*p)->rb_right;
else
goto old_call;
@@ -347,9 +519,31 @@
list_add_tail(&call->link, &rxrpc_calls);
write_unlock_bh(&rxrpc_call_lock);
+ /* Record copies of information for hashtable lookup */
+ call->proto = rx->proto;
+ call->local = conn->trans->local;
+ switch (call->proto) {
+ case AF_INET:
+ call->peer_ip.ipv4_addr =
+ conn->trans->peer->srx.transport.sin.sin_addr.s_addr;
+ break;
+ case AF_INET6:
+ memcpy(call->peer_ip.ipv6_addr,
+ conn->trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8,
+ sizeof(call->peer_ip.ipv6_addr));
+ break;
+ default:
+ break;
+ }
+ call->epoch = conn->epoch;
+ call->service_id = conn->service_id;
+ call->in_clientflag = conn->in_clientflag;
+ /* Add the new call to the hashtable */
+ rxrpc_call_hash_add(call);
+
_net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id);
- call->lifetimer.expires = jiffies + rxrpc_call_max_lifetime * HZ;
+ call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime;
add_timer(&call->lifetimer);
_leave(" = %p {%d} [new]", call, call->debug_id);
return call;
@@ -533,7 +727,7 @@
del_timer_sync(&call->resend_timer);
del_timer_sync(&call->ack_timer);
del_timer_sync(&call->lifetimer);
- call->deadspan.expires = jiffies + rxrpc_dead_call_timeout * HZ;
+ call->deadspan.expires = jiffies + rxrpc_dead_call_expiry;
add_timer(&call->deadspan);
_leave("");
@@ -665,6 +859,9 @@
rxrpc_put_connection(call->conn);
}
+ /* Remove the call from the hash */
+ rxrpc_call_hash_del(call);
+
if (call->acks_window) {
_debug("kill Tx window %d",
CIRC_CNT(call->acks_head, call->acks_tail,
diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c
index 7bf5b5b..6631f4f 100644
--- a/net/rxrpc/ar-connection.c
+++ b/net/rxrpc/ar-connection.c
@@ -18,11 +18,15 @@
#include <net/af_rxrpc.h>
#include "ar-internal.h"
+/*
+ * Time till a connection expires after last use (in seconds).
+ */
+unsigned rxrpc_connection_expiry = 10 * 60;
+
static void rxrpc_connection_reaper(struct work_struct *work);
LIST_HEAD(rxrpc_connections);
DEFINE_RWLOCK(rxrpc_connection_lock);
-static unsigned long rxrpc_connection_timeout = 10 * 60;
static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper);
/*
@@ -862,7 +866,7 @@
spin_lock(&conn->trans->client_lock);
write_lock(&conn->trans->conn_lock);
- reap_time = conn->put_time + rxrpc_connection_timeout;
+ reap_time = conn->put_time + rxrpc_connection_expiry;
if (atomic_read(&conn->usage) > 0) {
;
@@ -916,7 +920,7 @@
{
_enter("");
- rxrpc_connection_timeout = 0;
+ rxrpc_connection_expiry = 0;
cancel_delayed_work(&rxrpc_connection_reap);
rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0);
diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c
index a920608..db57458 100644
--- a/net/rxrpc/ar-error.c
+++ b/net/rxrpc/ar-error.c
@@ -83,6 +83,7 @@
if (mtu == 0) {
/* they didn't give us a size, estimate one */
+ mtu = peer->if_mtu;
if (mtu > 1500) {
mtu >>= 1;
if (mtu < 1500)
diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c
index 529572f..7374264 100644
--- a/net/rxrpc/ar-input.c
+++ b/net/rxrpc/ar-input.c
@@ -25,8 +25,6 @@
#include <net/net_namespace.h>
#include "ar-internal.h"
-unsigned long rxrpc_ack_timeout = 1;
-
const char *rxrpc_pkts[] = {
"?00",
"DATA", "ACK", "BUSY", "ABORT", "ACKALL", "CHALL", "RESP", "DEBUG",
@@ -349,8 +347,7 @@
* it */
if (sp->hdr.flags & RXRPC_REQUEST_ACK) {
_proto("ACK Requested on %%%u", serial);
- rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial,
- !(sp->hdr.flags & RXRPC_MORE_PACKETS));
+ rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial, false);
}
switch (sp->hdr.type) {
@@ -526,36 +523,38 @@
* post an incoming packet to the appropriate call/socket to deal with
* - must get rid of the sk_buff, either by freeing it or by queuing it
*/
-static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn,
+static void rxrpc_post_packet_to_call(struct rxrpc_call *call,
struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp;
- struct rxrpc_call *call;
- struct rb_node *p;
- __be32 call_id;
- _enter("%p,%p", conn, skb);
-
- read_lock_bh(&conn->lock);
+ _enter("%p,%p", call, skb);
sp = rxrpc_skb(skb);
- /* look at extant calls by channel number first */
- call = conn->channels[ntohl(sp->hdr.cid) & RXRPC_CHANNELMASK];
- if (!call || call->call_id != sp->hdr.callNumber)
- goto call_not_extant;
-
_debug("extant call [%d]", call->state);
- ASSERTCMP(call->conn, ==, conn);
read_lock(&call->state_lock);
switch (call->state) {
case RXRPC_CALL_LOCALLY_ABORTED:
- if (!test_and_set_bit(RXRPC_CALL_ABORT, &call->events))
+ if (!test_and_set_bit(RXRPC_CALL_ABORT, &call->events)) {
rxrpc_queue_call(call);
+ goto free_unlock;
+ }
case RXRPC_CALL_REMOTELY_ABORTED:
case RXRPC_CALL_NETWORK_ERROR:
case RXRPC_CALL_DEAD:
+ goto dead_call;
+ case RXRPC_CALL_COMPLETE:
+ case RXRPC_CALL_CLIENT_FINAL_ACK:
+ /* complete server call */
+ if (call->conn->in_clientflag)
+ goto dead_call;
+ /* resend last packet of a completed call */
+ _debug("final ack again");
+ rxrpc_get_call(call);
+ set_bit(RXRPC_CALL_ACK_FINAL, &call->events);
+ rxrpc_queue_call(call);
goto free_unlock;
default:
break;
@@ -563,7 +562,6 @@
read_unlock(&call->state_lock);
rxrpc_get_call(call);
- read_unlock_bh(&conn->lock);
if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
sp->hdr.flags & RXRPC_JUMBO_PACKET)
@@ -574,78 +572,16 @@
rxrpc_put_call(call);
goto done;
-call_not_extant:
- /* search the completed calls in case what we're dealing with is
- * there */
- _debug("call not extant");
-
- call_id = sp->hdr.callNumber;
- p = conn->calls.rb_node;
- while (p) {
- call = rb_entry(p, struct rxrpc_call, conn_node);
-
- if (call_id < call->call_id)
- p = p->rb_left;
- else if (call_id > call->call_id)
- p = p->rb_right;
- else
- goto found_completed_call;
- }
-
dead_call:
- /* it's a either a really old call that we no longer remember or its a
- * new incoming call */
- read_unlock_bh(&conn->lock);
-
- if (sp->hdr.flags & RXRPC_CLIENT_INITIATED &&
- sp->hdr.seq == cpu_to_be32(1)) {
- _debug("incoming call");
- skb_queue_tail(&conn->trans->local->accept_queue, skb);
- rxrpc_queue_work(&conn->trans->local->acceptor);
- goto done;
+ if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) {
+ skb->priority = RX_CALL_DEAD;
+ rxrpc_reject_packet(call->conn->trans->local, skb);
+ goto unlock;
}
-
- _debug("dead call");
- skb->priority = RX_CALL_DEAD;
- rxrpc_reject_packet(conn->trans->local, skb);
- goto done;
-
- /* resend last packet of a completed call
- * - client calls may have been aborted or ACK'd
- * - server calls may have been aborted
- */
-found_completed_call:
- _debug("completed call");
-
- if (atomic_read(&call->usage) == 0)
- goto dead_call;
-
- /* synchronise any state changes */
- read_lock(&call->state_lock);
- ASSERTIFCMP(call->state != RXRPC_CALL_CLIENT_FINAL_ACK,
- call->state, >=, RXRPC_CALL_COMPLETE);
-
- if (call->state == RXRPC_CALL_LOCALLY_ABORTED ||
- call->state == RXRPC_CALL_REMOTELY_ABORTED ||
- call->state == RXRPC_CALL_DEAD) {
- read_unlock(&call->state_lock);
- goto dead_call;
- }
-
- if (call->conn->in_clientflag) {
- read_unlock(&call->state_lock);
- goto dead_call; /* complete server call */
- }
-
- _debug("final ack again");
- rxrpc_get_call(call);
- set_bit(RXRPC_CALL_ACK_FINAL, &call->events);
- rxrpc_queue_call(call);
-
free_unlock:
- read_unlock(&call->state_lock);
- read_unlock_bh(&conn->lock);
rxrpc_free_skb(skb);
+unlock:
+ read_unlock(&call->state_lock);
done:
_leave("");
}
@@ -664,17 +600,42 @@
rxrpc_queue_conn(conn);
}
+static struct rxrpc_connection *rxrpc_conn_from_local(struct rxrpc_local *local,
+ struct sk_buff *skb,
+ struct rxrpc_skb_priv *sp)
+{
+ struct rxrpc_peer *peer;
+ struct rxrpc_transport *trans;
+ struct rxrpc_connection *conn;
+
+ peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr,
+ udp_hdr(skb)->source);
+ if (IS_ERR(peer))
+ goto cant_find_conn;
+
+ trans = rxrpc_find_transport(local, peer);
+ rxrpc_put_peer(peer);
+ if (!trans)
+ goto cant_find_conn;
+
+ conn = rxrpc_find_connection(trans, &sp->hdr);
+ rxrpc_put_transport(trans);
+ if (!conn)
+ goto cant_find_conn;
+
+ return conn;
+cant_find_conn:
+ return NULL;
+}
+
/*
* handle data received on the local endpoint
* - may be called in interrupt context
*/
void rxrpc_data_ready(struct sock *sk, int count)
{
- struct rxrpc_connection *conn;
- struct rxrpc_transport *trans;
struct rxrpc_skb_priv *sp;
struct rxrpc_local *local;
- struct rxrpc_peer *peer;
struct sk_buff *skb;
int ret;
@@ -749,27 +710,34 @@
(sp->hdr.callNumber == 0 || sp->hdr.seq == 0))
goto bad_message;
- peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr, udp_hdr(skb)->source);
- if (IS_ERR(peer))
- goto cant_route_call;
+ if (sp->hdr.callNumber == 0) {
+ /* This is a connection-level packet. These should be
+ * fairly rare, so the extra overhead of looking them up the
+ * old-fashioned way doesn't really hurt */
+ struct rxrpc_connection *conn;
- trans = rxrpc_find_transport(local, peer);
- rxrpc_put_peer(peer);
- if (!trans)
- goto cant_route_call;
+ conn = rxrpc_conn_from_local(local, skb, sp);
+ if (!conn)
+ goto cant_route_call;
- conn = rxrpc_find_connection(trans, &sp->hdr);
- rxrpc_put_transport(trans);
- if (!conn)
- goto cant_route_call;
-
- _debug("CONN %p {%d}", conn, conn->debug_id);
-
- if (sp->hdr.callNumber == 0)
+ _debug("CONN %p {%d}", conn, conn->debug_id);
rxrpc_post_packet_to_conn(conn, skb);
- else
- rxrpc_post_packet_to_call(conn, skb);
- rxrpc_put_connection(conn);
+ rxrpc_put_connection(conn);
+ } else {
+ struct rxrpc_call *call;
+ u8 in_clientflag = 0;
+
+ if (sp->hdr.flags & RXRPC_CLIENT_INITIATED)
+ in_clientflag = RXRPC_CLIENT_INITIATED;
+ call = rxrpc_find_call_hash(in_clientflag, sp->hdr.cid,
+ sp->hdr.callNumber, sp->hdr.epoch,
+ sp->hdr.serviceId, local, AF_INET,
+ (u8 *)&ip_hdr(skb)->saddr);
+ if (call)
+ rxrpc_post_packet_to_call(call, skb);
+ else
+ goto cant_route_call;
+ }
rxrpc_put_local(local);
return;
@@ -790,8 +758,10 @@
skb->priority = RX_CALL_DEAD;
}
- _debug("reject");
- rxrpc_reject_packet(local, skb);
+ if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) {
+ _debug("reject type %d",sp->hdr.type);
+ rxrpc_reject_packet(local, skb);
+ }
rxrpc_put_local(local);
_leave(" [no call]");
return;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5f43675..c831d44 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -396,9 +396,20 @@
#define RXRPC_ACKR_WINDOW_ASZ DIV_ROUND_UP(RXRPC_MAXACKS, BITS_PER_LONG)
unsigned long ackr_window[RXRPC_ACKR_WINDOW_ASZ + 1];
+ struct hlist_node hash_node;
+ unsigned long hash_key; /* Full hash key */
+ u8 in_clientflag; /* Copy of conn->in_clientflag for hashing */
+ struct rxrpc_local *local; /* Local endpoint. Used for hashing. */
+ sa_family_t proto; /* Frame protocol */
/* the following should all be in net order */
__be32 cid; /* connection ID + channel index */
__be32 call_id; /* call ID on connection */
+ __be32 epoch; /* epoch of this connection */
+ __be16 service_id; /* service ID */
+ union { /* Peer IP address for hashing */
+ __be32 ipv4_addr;
+ __u8 ipv6_addr[16]; /* Anticipates eventual IPv6 support */
+ } peer_ip;
};
/*
@@ -433,6 +444,13 @@
/*
* ar-ack.c
*/
+extern unsigned rxrpc_requested_ack_delay;
+extern unsigned rxrpc_soft_ack_delay;
+extern unsigned rxrpc_idle_ack_delay;
+extern unsigned rxrpc_rx_window_size;
+extern unsigned rxrpc_rx_mtu;
+extern unsigned rxrpc_rx_jumbo_max;
+
void __rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool);
void rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool);
void rxrpc_process_call(struct work_struct *);
@@ -440,10 +458,14 @@
/*
* ar-call.c
*/
+extern unsigned rxrpc_max_call_lifetime;
+extern unsigned rxrpc_dead_call_expiry;
extern struct kmem_cache *rxrpc_call_jar;
extern struct list_head rxrpc_calls;
extern rwlock_t rxrpc_call_lock;
+struct rxrpc_call *rxrpc_find_call_hash(u8, __be32, __be32, __be32,
+ __be16, void *, sa_family_t, const u8 *);
struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *,
struct rxrpc_transport *,
struct rxrpc_conn_bundle *,
@@ -460,6 +482,7 @@
/*
* ar-connection.c
*/
+extern unsigned rxrpc_connection_expiry;
extern struct list_head rxrpc_connections;
extern rwlock_t rxrpc_connection_lock;
@@ -493,7 +516,6 @@
/*
* ar-input.c
*/
-extern unsigned long rxrpc_ack_timeout;
extern const char *rxrpc_pkts[];
void rxrpc_data_ready(struct sock *, int);
@@ -504,6 +526,7 @@
* ar-local.c
*/
extern rwlock_t rxrpc_local_lock;
+
struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *);
void rxrpc_put_local(struct rxrpc_local *);
void __exit rxrpc_destroy_all_locals(void);
@@ -522,7 +545,7 @@
/*
* ar-output.c
*/
-extern int rxrpc_resend_timeout;
+extern unsigned rxrpc_resend_timeout;
int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *);
int rxrpc_client_sendmsg(struct kiocb *, struct rxrpc_sock *,
@@ -572,6 +595,8 @@
/*
* ar-transport.c
*/
+extern unsigned rxrpc_transport_expiry;
+
struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *,
struct rxrpc_peer *, gfp_t);
void rxrpc_put_transport(struct rxrpc_transport *);
@@ -580,6 +605,17 @@
struct rxrpc_peer *);
/*
+ * sysctl.c
+ */
+#ifdef CONFIG_SYSCTL
+extern int __init rxrpc_sysctl_init(void);
+extern void rxrpc_sysctl_exit(void);
+#else
+static inline int __init rxrpc_sysctl_init(void) { return 0; }
+static inline void rxrpc_sysctl_exit(void) {}
+#endif
+
+/*
* debug tracing
*/
extern unsigned int rxrpc_debug;
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c
index d0e8f1c..0b4b9a7 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/ar-output.c
@@ -18,7 +18,10 @@
#include <net/af_rxrpc.h>
#include "ar-internal.h"
-int rxrpc_resend_timeout = 4;
+/*
+ * Time till packet resend (in jiffies).
+ */
+unsigned rxrpc_resend_timeout = 4 * HZ;
static int rxrpc_send_data(struct kiocb *iocb,
struct rxrpc_sock *rx,
@@ -487,7 +490,7 @@
ntohl(sp->hdr.serial), ntohl(sp->hdr.seq));
sp->need_resend = false;
- sp->resend_at = jiffies + rxrpc_resend_timeout * HZ;
+ sp->resend_at = jiffies + rxrpc_resend_timeout;
if (!test_and_set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags)) {
_debug("run timer");
call->resend_timer.expires = sp->resend_at;
@@ -666,6 +669,7 @@
/* add the packet to the send queue if it's now full */
if (sp->remain <= 0 || (segment == 0 && !more)) {
struct rxrpc_connection *conn = call->conn;
+ uint32_t seq;
size_t pad;
/* pad out if we're using security */
@@ -678,11 +682,12 @@
memset(skb_put(skb, pad), 0, pad);
}
+ seq = atomic_inc_return(&call->sequence);
+
sp->hdr.epoch = conn->epoch;
sp->hdr.cid = call->cid;
sp->hdr.callNumber = call->call_id;
- sp->hdr.seq =
- htonl(atomic_inc_return(&call->sequence));
+ sp->hdr.seq = htonl(seq);
sp->hdr.serial =
htonl(atomic_inc_return(&conn->serial));
sp->hdr.type = RXRPC_PACKET_TYPE_DATA;
@@ -697,6 +702,8 @@
else if (CIRC_SPACE(call->acks_head, call->acks_tail,
call->acks_winsz) > 1)
sp->hdr.flags |= RXRPC_MORE_PACKETS;
+ if (more && seq & 1)
+ sp->hdr.flags |= RXRPC_REQUEST_ACK;
ret = rxrpc_secure_packet(
call, skb, skb->mark,
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index 34b5490..e9aaa65 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -180,16 +180,7 @@
if (copy > len - copied)
copy = len - copied;
- if (skb->ip_summed == CHECKSUM_UNNECESSARY ||
- skb->ip_summed == CHECKSUM_PARTIAL) {
- ret = skb_copy_datagram_iovec(skb, offset,
- msg->msg_iov, copy);
- } else {
- ret = skb_copy_and_csum_datagram_iovec(skb, offset,
- msg->msg_iov);
- if (ret == -EINVAL)
- goto csum_copy_error;
- }
+ ret = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copy);
if (ret < 0)
goto copy_error;
@@ -348,20 +339,6 @@
_leave(" = %d", ret);
return ret;
-csum_copy_error:
- _debug("csum error");
- release_sock(&rx->sk);
- if (continue_call)
- rxrpc_put_call(continue_call);
- rxrpc_kill_skb(skb);
- if (!(flags & MSG_PEEK)) {
- if (skb_dequeue(&rx->sk.sk_receive_queue) != skb)
- BUG();
- }
- skb_kill_datagram(&rx->sk, skb, flags);
- rxrpc_put_call(call);
- return -EAGAIN;
-
wait_interrupted:
ret = sock_intr_errno(timeo);
wait_error:
diff --git a/net/rxrpc/ar-skbuff.c b/net/rxrpc/ar-skbuff.c
index de755e0..4cfab49 100644
--- a/net/rxrpc/ar-skbuff.c
+++ b/net/rxrpc/ar-skbuff.c
@@ -83,9 +83,14 @@
rxrpc_request_final_ACK(call);
} else if (atomic_dec_and_test(&call->ackr_not_idle) &&
test_and_clear_bit(RXRPC_CALL_TX_SOFT_ACK, &call->flags)) {
+ /* We previously soft-ACK'd some received packets that have now
+ * been consumed, so send a hard-ACK if no more packets are
+ * immediately forthcoming to allow the transmitter to free up
+ * its Tx bufferage.
+ */
_debug("send Rx idle ACK");
__rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, sp->hdr.serial,
- true);
+ false);
}
spin_unlock_bh(&call->lock);
diff --git a/net/rxrpc/ar-transport.c b/net/rxrpc/ar-transport.c
index 92df566..1976dec 100644
--- a/net/rxrpc/ar-transport.c
+++ b/net/rxrpc/ar-transport.c
@@ -17,11 +17,15 @@
#include <net/af_rxrpc.h>
#include "ar-internal.h"
+/*
+ * Time after last use at which transport record is cleaned up.
+ */
+unsigned rxrpc_transport_expiry = 3600 * 24;
+
static void rxrpc_transport_reaper(struct work_struct *work);
static LIST_HEAD(rxrpc_transports);
static DEFINE_RWLOCK(rxrpc_transport_lock);
-static unsigned long rxrpc_transport_timeout = 3600 * 24;
static DECLARE_DELAYED_WORK(rxrpc_transport_reap, rxrpc_transport_reaper);
/*
@@ -235,7 +239,7 @@
if (likely(atomic_read(&trans->usage) > 0))
continue;
- reap_time = trans->put_time + rxrpc_transport_timeout;
+ reap_time = trans->put_time + rxrpc_transport_expiry;
if (reap_time <= now)
list_move_tail(&trans->link, &graveyard);
else if (reap_time < earliest)
@@ -271,7 +275,7 @@
{
_enter("");
- rxrpc_transport_timeout = 0;
+ rxrpc_transport_expiry = 0;
cancel_delayed_work(&rxrpc_transport_reap);
rxrpc_queue_delayed_work(&rxrpc_transport_reap, 0);
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
new file mode 100644
index 0000000..50a98a9
--- /dev/null
+++ b/net/rxrpc/sysctl.c
@@ -0,0 +1,146 @@
+/* sysctls for configuring RxRPC operating parameters
+ *
+ * Copyright (C) 2014 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/sysctl.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+static struct ctl_table_header *rxrpc_sysctl_reg_table;
+static const unsigned zero = 0;
+static const unsigned one = 1;
+static const unsigned four = 4;
+static const unsigned n_65535 = 65535;
+static const unsigned n_max_acks = RXRPC_MAXACKS;
+
+/*
+ * RxRPC operating parameters.
+ *
+ * See Documentation/networking/rxrpc.txt and the variable definitions for more
+ * information on the individual parameters.
+ */
+static struct ctl_table rxrpc_sysctl_table[] = {
+ /* Values measured in milliseconds */
+ {
+ .procname = "req_ack_delay",
+ .data = &rxrpc_requested_ack_delay,
+ .maxlen = sizeof(unsigned),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_ms_jiffies,
+ .extra1 = (void *)&zero,
+ },
+ {
+ .procname = "soft_ack_delay",
+ .data = &rxrpc_soft_ack_delay,
+ .maxlen = sizeof(unsigned),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_ms_jiffies,
+ .extra1 = (void *)&one,
+ },
+ {
+ .procname = "idle_ack_delay",
+ .data = &rxrpc_idle_ack_delay,
+ .maxlen = sizeof(unsigned),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_ms_jiffies,
+ .extra1 = (void *)&one,
+ },
+ {
+ .procname = "resend_timeout",
+ .data = &rxrpc_resend_timeout,
+ .maxlen = sizeof(unsigned),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_ms_jiffies,
+ .extra1 = (void *)&one,
+ },
+
+ /* Values measured in seconds but used in jiffies */
+ {
+ .procname = "max_call_lifetime",
+ .data = &rxrpc_max_call_lifetime,
+ .maxlen = sizeof(unsigned),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ .extra1 = (void *)&one,
+ },
+ {
+ .procname = "dead_call_expiry",
+ .data = &rxrpc_dead_call_expiry,
+ .maxlen = sizeof(unsigned),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ .extra1 = (void *)&one,
+ },
+
+ /* Values measured in seconds */
+ {
+ .procname = "connection_expiry",
+ .data = &rxrpc_connection_expiry,
+ .maxlen = sizeof(unsigned),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (void *)&one,
+ },
+ {
+ .procname = "transport_expiry",
+ .data = &rxrpc_transport_expiry,
+ .maxlen = sizeof(unsigned),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (void *)&one,
+ },
+
+ /* Non-time values */
+ {
+ .procname = "rx_window_size",
+ .data = &rxrpc_rx_window_size,
+ .maxlen = sizeof(unsigned),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (void *)&one,
+ .extra2 = (void *)&n_max_acks,
+ },
+ {
+ .procname = "rx_mtu",
+ .data = &rxrpc_rx_mtu,
+ .maxlen = sizeof(unsigned),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (void *)&one,
+ .extra1 = (void *)&n_65535,
+ },
+ {
+ .procname = "rx_jumbo_max",
+ .data = &rxrpc_rx_jumbo_max,
+ .maxlen = sizeof(unsigned),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (void *)&one,
+ .extra2 = (void *)&four,
+ },
+
+ { }
+};
+
+int __init rxrpc_sysctl_init(void)
+{
+ rxrpc_sysctl_reg_table = register_net_sysctl(&init_net, "net/rxrpc",
+ rxrpc_sysctl_table);
+ if (!rxrpc_sysctl_reg_table)
+ return -ENOMEM;
+ return 0;
+}
+
+void rxrpc_sysctl_exit(void)
+{
+ if (rxrpc_sysctl_reg_table)
+ unregister_net_sysctl_table(rxrpc_sysctl_reg_table);
+}
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 72bdc71..8a5ba5a 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -27,8 +27,11 @@
#include <net/act_api.h>
#include <net/netlink.h>
-void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo)
+void tcf_hash_destroy(struct tc_action *a)
{
+ struct tcf_common *p = a->priv;
+ struct tcf_hashinfo *hinfo = a->ops->hinfo;
+
spin_lock_bh(&hinfo->lock);
hlist_del(&p->tcfc_head);
spin_unlock_bh(&hinfo->lock);
@@ -42,18 +45,22 @@
}
EXPORT_SYMBOL(tcf_hash_destroy);
-int tcf_hash_release(struct tcf_common *p, int bind,
- struct tcf_hashinfo *hinfo)
+int tcf_hash_release(struct tc_action *a, int bind)
{
+ struct tcf_common *p = a->priv;
int ret = 0;
if (p) {
if (bind)
p->tcfc_bindcnt--;
+ else if (p->tcfc_bindcnt > 0)
+ return -EPERM;
p->tcfc_refcnt--;
if (p->tcfc_bindcnt <= 0 && p->tcfc_refcnt <= 0) {
- tcf_hash_destroy(p, hinfo);
+ if (a->ops->cleanup)
+ a->ops->cleanup(a, bind);
+ tcf_hash_destroy(a);
ret = 1;
}
}
@@ -118,6 +125,7 @@
struct tcf_common *p;
struct nlattr *nest;
int i = 0, n_i = 0;
+ int ret = -EINVAL;
nest = nla_nest_start(skb, a->order);
if (nest == NULL)
@@ -127,10 +135,13 @@
for (i = 0; i < (hinfo->hmask + 1); i++) {
head = &hinfo->htab[tcf_hash(i, hinfo->hmask)];
hlist_for_each_entry_safe(p, n, head, tcfc_head) {
- if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo)) {
+ a->priv = p;
+ ret = tcf_hash_release(a, 0);
+ if (ret == ACT_P_DELETED) {
module_put(a->ops->owner);
n_i++;
- }
+ } else if (ret < 0)
+ goto nla_put_failure;
}
}
if (nla_put_u32(skb, TCA_FCNT, n_i))
@@ -140,7 +151,7 @@
return n_i;
nla_put_failure:
nla_nest_cancel(skb, nest);
- return -EINVAL;
+ return ret;
}
static int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb,
@@ -198,7 +209,7 @@
}
EXPORT_SYMBOL(tcf_hash_search);
-struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind)
+int tcf_hash_check(u32 index, struct tc_action *a, int bind)
{
struct tcf_hashinfo *hinfo = a->ops->hinfo;
struct tcf_common *p = NULL;
@@ -207,19 +218,30 @@
p->tcfc_bindcnt++;
p->tcfc_refcnt++;
a->priv = p;
+ return 1;
}
- return p;
+ return 0;
}
EXPORT_SYMBOL(tcf_hash_check);
-struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est,
- struct tc_action *a, int size, int bind)
+void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est)
+{
+ struct tcf_common *pc = a->priv;
+ if (est)
+ gen_kill_estimator(&pc->tcfc_bstats,
+ &pc->tcfc_rate_est);
+ kfree_rcu(pc, tcfc_rcu);
+}
+EXPORT_SYMBOL(tcf_hash_cleanup);
+
+int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
+ int size, int bind)
{
struct tcf_hashinfo *hinfo = a->ops->hinfo;
struct tcf_common *p = kzalloc(size, GFP_KERNEL);
if (unlikely(!p))
- return ERR_PTR(-ENOMEM);
+ return -ENOMEM;
p->tcfc_refcnt = 1;
if (bind)
p->tcfc_bindcnt = 1;
@@ -234,17 +256,19 @@
&p->tcfc_lock, est);
if (err) {
kfree(p);
- return ERR_PTR(err);
+ return err;
}
}
a->priv = (void *) p;
- return p;
+ return 0;
}
EXPORT_SYMBOL(tcf_hash_create);
-void tcf_hash_insert(struct tcf_common *p, struct tcf_hashinfo *hinfo)
+void tcf_hash_insert(struct tc_action *a)
{
+ struct tcf_common *p = a->priv;
+ struct tcf_hashinfo *hinfo = a->ops->hinfo;
unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask);
spin_lock_bh(&hinfo->lock);
@@ -256,12 +280,13 @@
static LIST_HEAD(act_base);
static DEFINE_RWLOCK(act_mod_lock);
-int tcf_register_action(struct tc_action_ops *act)
+int tcf_register_action(struct tc_action_ops *act, unsigned int mask)
{
struct tc_action_ops *a;
+ int err;
- /* Must supply act, dump, cleanup and init */
- if (!act->act || !act->dump || !act->cleanup || !act->init)
+ /* Must supply act, dump and init */
+ if (!act->act || !act->dump || !act->init)
return -EINVAL;
/* Supply defaults */
@@ -270,10 +295,21 @@
if (!act->walk)
act->walk = tcf_generic_walker;
+ act->hinfo = kmalloc(sizeof(struct tcf_hashinfo), GFP_KERNEL);
+ if (!act->hinfo)
+ return -ENOMEM;
+ err = tcf_hashinfo_init(act->hinfo, mask);
+ if (err) {
+ kfree(act->hinfo);
+ return err;
+ }
+
write_lock(&act_mod_lock);
list_for_each_entry(a, &act_base, head) {
if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) {
write_unlock(&act_mod_lock);
+ tcf_hashinfo_destroy(act->hinfo);
+ kfree(act->hinfo);
return -EEXIST;
}
}
@@ -292,6 +328,8 @@
list_for_each_entry(a, &act_base, head) {
if (a == act) {
list_del(&act->head);
+ tcf_hashinfo_destroy(act->hinfo);
+ kfree(act->hinfo);
err = 0;
break;
}
@@ -368,16 +406,21 @@
}
EXPORT_SYMBOL(tcf_action_exec);
-void tcf_action_destroy(struct list_head *actions, int bind)
+int tcf_action_destroy(struct list_head *actions, int bind)
{
struct tc_action *a, *tmp;
+ int ret = 0;
list_for_each_entry_safe(a, tmp, actions, list) {
- if (a->ops->cleanup(a, bind) == ACT_P_DELETED)
+ ret = tcf_hash_release(a, bind);
+ if (ret == ACT_P_DELETED)
module_put(a->ops->owner);
+ else if (ret < 0)
+ return ret;
list_del(&a->list);
kfree(a);
}
+ return ret;
}
int
@@ -642,6 +685,20 @@
return rtnl_unicast(skb, net, portid);
}
+static struct tc_action *create_a(int i)
+{
+ struct tc_action *act;
+
+ act = kzalloc(sizeof(*act), GFP_KERNEL);
+ if (act == NULL) {
+ pr_debug("create_a: failed to alloc!\n");
+ return NULL;
+ }
+ act->order = i;
+ INIT_LIST_HEAD(&act->list);
+ return act;
+}
+
static struct tc_action *
tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid)
{
@@ -661,11 +718,10 @@
index = nla_get_u32(tb[TCA_ACT_INDEX]);
err = -ENOMEM;
- a = kzalloc(sizeof(struct tc_action), GFP_KERNEL);
+ a = create_a(0);
if (a == NULL)
goto err_out;
- INIT_LIST_HEAD(&a->list);
err = -EINVAL;
a->ops = tc_lookup_action(tb[TCA_ACT_KIND]);
if (a->ops == NULL) /* could happen in batch of actions */
@@ -695,20 +751,6 @@
}
}
-static struct tc_action *create_a(int i)
-{
- struct tc_action *act;
-
- act = kzalloc(sizeof(*act), GFP_KERNEL);
- if (act == NULL) {
- pr_debug("create_a: failed to alloc!\n");
- return NULL;
- }
- act->order = i;
- INIT_LIST_HEAD(&act->list);
- return act;
-}
-
static int tca_action_flush(struct net *net, struct nlattr *nla,
struct nlmsghdr *n, u32 portid)
{
@@ -720,18 +762,12 @@
struct nlattr *nest;
struct nlattr *tb[TCA_ACT_MAX + 1];
struct nlattr *kind;
- struct tc_action *a = create_a(0);
+ struct tc_action a;
int err = -ENOMEM;
- if (a == NULL) {
- pr_debug("tca_action_flush: couldnt create tc_action\n");
- return err;
- }
-
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb) {
pr_debug("tca_action_flush: failed skb alloc\n");
- kfree(a);
return err;
}
@@ -743,8 +779,10 @@
err = -EINVAL;
kind = tb[TCA_ACT_KIND];
- a->ops = tc_lookup_action(kind);
- if (a->ops == NULL) /*some idjot trying to flush unknown action */
+ memset(&a, 0, sizeof(struct tc_action));
+ INIT_LIST_HEAD(&a.list);
+ a.ops = tc_lookup_action(kind);
+ if (a.ops == NULL) /*some idjot trying to flush unknown action */
goto err_out;
nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0);
@@ -759,7 +797,7 @@
if (nest == NULL)
goto out_module_put;
- err = a->ops->walk(skb, &dcb, RTM_DELACTION, a);
+ err = a.ops->walk(skb, &dcb, RTM_DELACTION, &a);
if (err < 0)
goto out_module_put;
if (err == 0)
@@ -769,8 +807,7 @@
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
nlh->nlmsg_flags |= NLM_F_ROOT;
- module_put(a->ops->owner);
- kfree(a);
+ module_put(a.ops->owner);
err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
n->nlmsg_flags & NLM_F_ECHO);
if (err > 0)
@@ -779,11 +816,10 @@
return err;
out_module_put:
- module_put(a->ops->owner);
+ module_put(a.ops->owner);
err_out:
noflush_out:
kfree_skb(skb);
- kfree(a);
return err;
}
@@ -805,7 +841,11 @@
}
/* now do the delete */
- tcf_action_destroy(actions, 0);
+ ret = tcf_action_destroy(actions, 0);
+ if (ret < 0) {
+ kfree_skb(skb);
+ return ret;
+ }
ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
n->nlmsg_flags & NLM_F_ECHO);
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 2210187..edbf40d 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -37,7 +37,6 @@
#include <net/tc_act/tc_csum.h>
#define CSUM_TAB_MASK 15
-static struct tcf_hashinfo csum_hash_info;
static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = {
[TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), },
@@ -48,7 +47,6 @@
{
struct nlattr *tb[TCA_CSUM_MAX + 1];
struct tc_csum *parm;
- struct tcf_common *pc;
struct tcf_csum *p;
int ret = 0, err;
@@ -63,38 +61,31 @@
return -EINVAL;
parm = nla_data(tb[TCA_CSUM_PARMS]);
- pc = tcf_hash_check(parm->index, a, bind);
- if (!pc) {
- pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
- if (IS_ERR(pc))
- return PTR_ERR(pc);
+ if (!tcf_hash_check(parm->index, a, bind)) {
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
+ if (ret)
+ return ret;
ret = ACT_P_CREATED;
} else {
if (bind)/* dont override defaults */
return 0;
- tcf_hash_release(pc, bind, a->ops->hinfo);
+ tcf_hash_release(a, bind);
if (!ovr)
return -EEXIST;
}
- p = to_tcf_csum(pc);
+ p = to_tcf_csum(a);
spin_lock_bh(&p->tcf_lock);
p->tcf_action = parm->action;
p->update_flags = parm->update_flags;
spin_unlock_bh(&p->tcf_lock);
if (ret == ACT_P_CREATED)
- tcf_hash_insert(pc, a->ops->hinfo);
+ tcf_hash_insert(a);
return ret;
}
-static int tcf_csum_cleanup(struct tc_action *a, int bind)
-{
- struct tcf_csum *p = a->priv;
- return tcf_hash_release(&p->common, bind, &csum_hash_info);
-}
-
/**
* tcf_csum_skb_nextlayer - Get next layer pointer
* @skb: sk_buff to use
@@ -569,12 +560,10 @@
static struct tc_action_ops act_csum_ops = {
.kind = "csum",
- .hinfo = &csum_hash_info,
.type = TCA_ACT_CSUM,
.owner = THIS_MODULE,
.act = tcf_csum,
.dump = tcf_csum_dump,
- .cleanup = tcf_csum_cleanup,
.init = tcf_csum_init,
};
@@ -583,11 +572,7 @@
static int __init csum_init_module(void)
{
- int err = tcf_hashinfo_init(&csum_hash_info, CSUM_TAB_MASK);
- if (err)
- return err;
-
- return tcf_register_action(&act_csum_ops);
+ return tcf_register_action(&act_csum_ops, CSUM_TAB_MASK);
}
static void __exit csum_cleanup_module(void)
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index a0eed30..d6bcbd9 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -24,7 +24,6 @@
#include <net/tc_act/tc_gact.h>
#define GACT_TAB_MASK 15
-static struct tcf_hashinfo gact_hash_info;
#ifdef CONFIG_GACT_PROB
static int gact_net_rand(struct tcf_gact *gact)
@@ -57,7 +56,6 @@
struct nlattr *tb[TCA_GACT_MAX + 1];
struct tc_gact *parm;
struct tcf_gact *gact;
- struct tcf_common *pc;
int ret = 0;
int err;
#ifdef CONFIG_GACT_PROB
@@ -86,21 +84,20 @@
}
#endif
- pc = tcf_hash_check(parm->index, a, bind);
- if (!pc) {
- pc = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind);
- if (IS_ERR(pc))
- return PTR_ERR(pc);
+ if (!tcf_hash_check(parm->index, a, bind)) {
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind);
+ if (ret)
+ return ret;
ret = ACT_P_CREATED;
} else {
if (bind)/* dont override defaults */
return 0;
- tcf_hash_release(pc, bind, a->ops->hinfo);
+ tcf_hash_release(a, bind);
if (!ovr)
return -EEXIST;
}
- gact = to_gact(pc);
+ gact = to_gact(a);
spin_lock_bh(&gact->tcf_lock);
gact->tcf_action = parm->action;
@@ -113,19 +110,10 @@
#endif
spin_unlock_bh(&gact->tcf_lock);
if (ret == ACT_P_CREATED)
- tcf_hash_insert(pc, a->ops->hinfo);
+ tcf_hash_insert(a);
return ret;
}
-static int tcf_gact_cleanup(struct tc_action *a, int bind)
-{
- struct tcf_gact *gact = a->priv;
-
- if (gact)
- return tcf_hash_release(&gact->common, bind, a->ops->hinfo);
- return 0;
-}
-
static int tcf_gact(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
@@ -191,12 +179,10 @@
static struct tc_action_ops act_gact_ops = {
.kind = "gact",
- .hinfo = &gact_hash_info,
.type = TCA_ACT_GACT,
.owner = THIS_MODULE,
.act = tcf_gact,
.dump = tcf_gact_dump,
- .cleanup = tcf_gact_cleanup,
.init = tcf_gact_init,
};
@@ -206,21 +192,17 @@
static int __init gact_init_module(void)
{
- int err = tcf_hashinfo_init(&gact_hash_info, GACT_TAB_MASK);
- if (err)
- return err;
#ifdef CONFIG_GACT_PROB
pr_info("GACT probability on\n");
#else
pr_info("GACT probability NOT on\n");
#endif
- return tcf_register_action(&act_gact_ops);
+ return tcf_register_action(&act_gact_ops, GACT_TAB_MASK);
}
static void __exit gact_cleanup_module(void)
{
tcf_unregister_action(&act_gact_ops);
- tcf_hashinfo_destroy(&gact_hash_info);
}
module_init(gact_init_module);
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 0a6d621..8a64a07 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -29,7 +29,6 @@
#define IPT_TAB_MASK 15
-static struct tcf_hashinfo ipt_hash_info;
static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook)
{
@@ -69,22 +68,12 @@
module_put(par.target->me);
}
-static int tcf_ipt_release(struct tcf_ipt *ipt, int bind)
+static void tcf_ipt_release(struct tc_action *a, int bind)
{
- int ret = 0;
- if (ipt) {
- if (bind)
- ipt->tcf_bindcnt--;
- ipt->tcf_refcnt--;
- if (ipt->tcf_bindcnt <= 0 && ipt->tcf_refcnt <= 0) {
- ipt_destroy_target(ipt->tcfi_t);
- kfree(ipt->tcfi_tname);
- kfree(ipt->tcfi_t);
- tcf_hash_destroy(&ipt->common, &ipt_hash_info);
- ret = ACT_P_DELETED;
- }
- }
- return ret;
+ struct tcf_ipt *ipt = to_ipt(a);
+ ipt_destroy_target(ipt->tcfi_t);
+ kfree(ipt->tcfi_tname);
+ kfree(ipt->tcfi_t);
}
static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = {
@@ -99,7 +88,6 @@
{
struct nlattr *tb[TCA_IPT_MAX + 1];
struct tcf_ipt *ipt;
- struct tcf_common *pc;
struct xt_entry_target *td, *t;
char *tname;
int ret = 0, err;
@@ -125,21 +113,20 @@
if (tb[TCA_IPT_INDEX] != NULL)
index = nla_get_u32(tb[TCA_IPT_INDEX]);
- pc = tcf_hash_check(index, a, bind);
- if (!pc) {
- pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind);
- if (IS_ERR(pc))
- return PTR_ERR(pc);
+ if (!tcf_hash_check(index, a, bind) ) {
+ ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind);
+ if (ret)
+ return ret;
ret = ACT_P_CREATED;
} else {
if (bind)/* dont override defaults */
return 0;
- tcf_ipt_release(to_ipt(pc), bind);
+ tcf_hash_release(a, bind);
if (!ovr)
return -EEXIST;
}
- ipt = to_ipt(pc);
+ ipt = to_ipt(a);
hook = nla_get_u32(tb[TCA_IPT_HOOK]);
@@ -170,7 +157,7 @@
ipt->tcfi_hook = hook;
spin_unlock_bh(&ipt->tcf_lock);
if (ret == ACT_P_CREATED)
- tcf_hash_insert(pc, a->ops->hinfo);
+ tcf_hash_insert(a);
return ret;
err3:
@@ -178,21 +165,11 @@
err2:
kfree(tname);
err1:
- if (ret == ACT_P_CREATED) {
- if (est)
- gen_kill_estimator(&pc->tcfc_bstats,
- &pc->tcfc_rate_est);
- kfree_rcu(pc, tcfc_rcu);
- }
+ if (ret == ACT_P_CREATED)
+ tcf_hash_cleanup(a, est);
return err;
}
-static int tcf_ipt_cleanup(struct tc_action *a, int bind)
-{
- struct tcf_ipt *ipt = a->priv;
- return tcf_ipt_release(ipt, bind);
-}
-
static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
@@ -284,23 +261,21 @@
static struct tc_action_ops act_ipt_ops = {
.kind = "ipt",
- .hinfo = &ipt_hash_info,
.type = TCA_ACT_IPT,
.owner = THIS_MODULE,
.act = tcf_ipt,
.dump = tcf_ipt_dump,
- .cleanup = tcf_ipt_cleanup,
+ .cleanup = tcf_ipt_release,
.init = tcf_ipt_init,
};
static struct tc_action_ops act_xt_ops = {
.kind = "xt",
- .hinfo = &ipt_hash_info,
.type = TCA_ACT_XT,
.owner = THIS_MODULE,
.act = tcf_ipt,
.dump = tcf_ipt_dump,
- .cleanup = tcf_ipt_cleanup,
+ .cleanup = tcf_ipt_release,
.init = tcf_ipt_init,
};
@@ -311,20 +286,16 @@
static int __init ipt_init_module(void)
{
- int ret1, ret2, err;
- err = tcf_hashinfo_init(&ipt_hash_info, IPT_TAB_MASK);
- if (err)
- return err;
+ int ret1, ret2;
- ret1 = tcf_register_action(&act_xt_ops);
+ ret1 = tcf_register_action(&act_xt_ops, IPT_TAB_MASK);
if (ret1 < 0)
printk("Failed to load xt action\n");
- ret2 = tcf_register_action(&act_ipt_ops);
+ ret2 = tcf_register_action(&act_ipt_ops, IPT_TAB_MASK);
if (ret2 < 0)
printk("Failed to load ipt action\n");
if (ret1 < 0 && ret2 < 0) {
- tcf_hashinfo_destroy(&ipt_hash_info);
return ret1;
} else
return 0;
@@ -334,7 +305,6 @@
{
tcf_unregister_action(&act_xt_ops);
tcf_unregister_action(&act_ipt_ops);
- tcf_hashinfo_destroy(&ipt_hash_info);
}
module_init(ipt_init_module);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 0b2c6d3..4f912c0 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -31,23 +31,13 @@
#define MIRRED_TAB_MASK 7
static LIST_HEAD(mirred_list);
-static struct tcf_hashinfo mirred_hash_info;
-static int tcf_mirred_release(struct tcf_mirred *m, int bind)
+static void tcf_mirred_release(struct tc_action *a, int bind)
{
- if (m) {
- if (bind)
- m->tcf_bindcnt--;
- m->tcf_refcnt--;
- if (!m->tcf_bindcnt && m->tcf_refcnt <= 0) {
- list_del(&m->tcfm_list);
- if (m->tcfm_dev)
- dev_put(m->tcfm_dev);
- tcf_hash_destroy(&m->common, &mirred_hash_info);
- return 1;
- }
- }
- return 0;
+ struct tcf_mirred *m = to_mirred(a);
+ list_del(&m->tcfm_list);
+ if (m->tcfm_dev)
+ dev_put(m->tcfm_dev);
}
static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = {
@@ -61,7 +51,6 @@
struct nlattr *tb[TCA_MIRRED_MAX + 1];
struct tc_mirred *parm;
struct tcf_mirred *m;
- struct tcf_common *pc;
struct net_device *dev;
int ret, ok_push = 0;
@@ -101,21 +90,20 @@
dev = NULL;
}
- pc = tcf_hash_check(parm->index, a, bind);
- if (!pc) {
+ if (!tcf_hash_check(parm->index, a, bind)) {
if (dev == NULL)
return -EINVAL;
- pc = tcf_hash_create(parm->index, est, a, sizeof(*m), bind);
- if (IS_ERR(pc))
- return PTR_ERR(pc);
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*m), bind);
+ if (ret)
+ return ret;
ret = ACT_P_CREATED;
} else {
if (!ovr) {
- tcf_mirred_release(to_mirred(pc), bind);
+ tcf_hash_release(a, bind);
return -EEXIST;
}
}
- m = to_mirred(pc);
+ m = to_mirred(a);
spin_lock_bh(&m->tcf_lock);
m->tcf_action = parm->action;
@@ -131,21 +119,12 @@
spin_unlock_bh(&m->tcf_lock);
if (ret == ACT_P_CREATED) {
list_add(&m->tcfm_list, &mirred_list);
- tcf_hash_insert(pc, a->ops->hinfo);
+ tcf_hash_insert(a);
}
return ret;
}
-static int tcf_mirred_cleanup(struct tc_action *a, int bind)
-{
- struct tcf_mirred *m = a->priv;
-
- if (m)
- return tcf_mirred_release(m, bind);
- return 0;
-}
-
static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
@@ -254,12 +233,11 @@
static struct tc_action_ops act_mirred_ops = {
.kind = "mirred",
- .hinfo = &mirred_hash_info,
.type = TCA_ACT_MIRRED,
.owner = THIS_MODULE,
.act = tcf_mirred,
.dump = tcf_mirred_dump,
- .cleanup = tcf_mirred_cleanup,
+ .cleanup = tcf_mirred_release,
.init = tcf_mirred_init,
};
@@ -273,19 +251,13 @@
if (err)
return err;
- err = tcf_hashinfo_init(&mirred_hash_info, MIRRED_TAB_MASK);
- if (err) {
- unregister_netdevice_notifier(&mirred_device_notifier);
- return err;
- }
pr_info("Mirror/redirect action on\n");
- return tcf_register_action(&act_mirred_ops);
+ return tcf_register_action(&act_mirred_ops, MIRRED_TAB_MASK);
}
static void __exit mirred_cleanup_module(void)
{
tcf_unregister_action(&act_mirred_ops);
- tcf_hashinfo_destroy(&mirred_hash_info);
unregister_netdevice_notifier(&mirred_device_notifier);
}
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 81f0404..270a030 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -31,8 +31,6 @@
#define NAT_TAB_MASK 15
-static struct tcf_hashinfo nat_hash_info;
-
static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
[TCA_NAT_PARMS] = { .len = sizeof(struct tc_nat) },
};
@@ -44,7 +42,6 @@
struct tc_nat *parm;
int ret = 0, err;
struct tcf_nat *p;
- struct tcf_common *pc;
if (nla == NULL)
return -EINVAL;
@@ -57,20 +54,19 @@
return -EINVAL;
parm = nla_data(tb[TCA_NAT_PARMS]);
- pc = tcf_hash_check(parm->index, a, bind);
- if (!pc) {
- pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
- if (IS_ERR(pc))
- return PTR_ERR(pc);
+ if (!tcf_hash_check(parm->index, a, bind)) {
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
+ if (ret)
+ return ret;
ret = ACT_P_CREATED;
} else {
if (bind)
return 0;
- tcf_hash_release(pc, bind, a->ops->hinfo);
+ tcf_hash_release(a, bind);
if (!ovr)
return -EEXIST;
}
- p = to_tcf_nat(pc);
+ p = to_tcf_nat(a);
spin_lock_bh(&p->tcf_lock);
p->old_addr = parm->old_addr;
@@ -82,18 +78,11 @@
spin_unlock_bh(&p->tcf_lock);
if (ret == ACT_P_CREATED)
- tcf_hash_insert(pc, a->ops->hinfo);
+ tcf_hash_insert(a);
return ret;
}
-static int tcf_nat_cleanup(struct tc_action *a, int bind)
-{
- struct tcf_nat *p = a->priv;
-
- return tcf_hash_release(&p->common, bind, &nat_hash_info);
-}
-
static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
@@ -293,12 +282,10 @@
static struct tc_action_ops act_nat_ops = {
.kind = "nat",
- .hinfo = &nat_hash_info,
.type = TCA_ACT_NAT,
.owner = THIS_MODULE,
.act = tcf_nat,
.dump = tcf_nat_dump,
- .cleanup = tcf_nat_cleanup,
.init = tcf_nat_init,
};
@@ -307,16 +294,12 @@
static int __init nat_init_module(void)
{
- int err = tcf_hashinfo_init(&nat_hash_info, NAT_TAB_MASK);
- if (err)
- return err;
- return tcf_register_action(&act_nat_ops);
+ return tcf_register_action(&act_nat_ops, NAT_TAB_MASK);
}
static void __exit nat_cleanup_module(void)
{
tcf_unregister_action(&act_nat_ops);
- tcf_hashinfo_destroy(&nat_hash_info);
}
module_init(nat_init_module);
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index be3f0f6..5f9bcb2 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -25,8 +25,6 @@
#define PEDIT_TAB_MASK 15
-static struct tcf_hashinfo pedit_hash_info;
-
static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = {
[TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) },
};
@@ -39,7 +37,6 @@
struct tc_pedit *parm;
int ret = 0, err;
struct tcf_pedit *p;
- struct tcf_common *pc;
struct tc_pedit_key *keys = NULL;
int ksize;
@@ -57,26 +54,22 @@
if (nla_len(tb[TCA_PEDIT_PARMS]) < sizeof(*parm) + ksize)
return -EINVAL;
- pc = tcf_hash_check(parm->index, a, bind);
- if (!pc) {
+ if (!tcf_hash_check(parm->index, a, bind)) {
if (!parm->nkeys)
return -EINVAL;
- pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
- if (IS_ERR(pc))
- return PTR_ERR(pc);
- p = to_pedit(pc);
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
+ if (ret)
+ return ret;
+ p = to_pedit(a);
keys = kmalloc(ksize, GFP_KERNEL);
if (keys == NULL) {
- if (est)
- gen_kill_estimator(&pc->tcfc_bstats,
- &pc->tcfc_rate_est);
- kfree_rcu(pc, tcfc_rcu);
+ tcf_hash_cleanup(a, est);
return -ENOMEM;
}
ret = ACT_P_CREATED;
} else {
- p = to_pedit(pc);
- tcf_hash_release(pc, bind, a->ops->hinfo);
+ p = to_pedit(a);
+ tcf_hash_release(a, bind);
if (bind)
return 0;
if (!ovr)
@@ -100,22 +93,15 @@
memcpy(p->tcfp_keys, parm->keys, ksize);
spin_unlock_bh(&p->tcf_lock);
if (ret == ACT_P_CREATED)
- tcf_hash_insert(pc, a->ops->hinfo);
+ tcf_hash_insert(a);
return ret;
}
-static int tcf_pedit_cleanup(struct tc_action *a, int bind)
+static void tcf_pedit_cleanup(struct tc_action *a, int bind)
{
struct tcf_pedit *p = a->priv;
-
- if (p) {
- struct tc_pedit_key *keys = p->tcfp_keys;
- if (tcf_hash_release(&p->common, bind, &pedit_hash_info)) {
- kfree(keys);
- return 1;
- }
- }
- return 0;
+ struct tc_pedit_key *keys = p->tcfp_keys;
+ kfree(keys);
}
static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
@@ -230,7 +216,6 @@
static struct tc_action_ops act_pedit_ops = {
.kind = "pedit",
- .hinfo = &pedit_hash_info,
.type = TCA_ACT_PEDIT,
.owner = THIS_MODULE,
.act = tcf_pedit,
@@ -245,15 +230,11 @@
static int __init pedit_init_module(void)
{
- int err = tcf_hashinfo_init(&pedit_hash_info, PEDIT_TAB_MASK);
- if (err)
- return err;
- return tcf_register_action(&act_pedit_ops);
+ return tcf_register_action(&act_pedit_ops, PEDIT_TAB_MASK);
}
static void __exit pedit_cleanup_module(void)
{
- tcf_hashinfo_destroy(&pedit_hash_info);
tcf_unregister_action(&act_pedit_ops);
}
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 1778209..0566e46 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -41,7 +41,6 @@
container_of(pc, struct tcf_police, common)
#define POL_TAB_MASK 15
-static struct tcf_hashinfo police_hash_info;
/* old policer structure from before tc actions */
struct tc_police_compat {
@@ -234,7 +233,7 @@
police->tcfp_t_c = ktime_to_ns(ktime_get());
police->tcf_index = parm->index ? parm->index :
- tcf_hash_new_index(a->ops->hinfo);
+ tcf_hash_new_index(hinfo);
h = tcf_hash(police->tcf_index, POL_TAB_MASK);
spin_lock_bh(&hinfo->lock);
hlist_add_head(&police->tcf_head, &hinfo->htab[h]);
@@ -253,14 +252,6 @@
return err;
}
-static int tcf_act_police_cleanup(struct tc_action *a, int bind)
-{
- struct tcf_police *p = a->priv;
- if (p)
- return tcf_hash_release(&p->common, bind, &police_hash_info);
- return 0;
-}
-
static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
@@ -357,12 +348,10 @@
static struct tc_action_ops act_police_ops = {
.kind = "police",
- .hinfo = &police_hash_info,
.type = TCA_ID_POLICE,
.owner = THIS_MODULE,
.act = tcf_act_police,
.dump = tcf_act_police_dump,
- .cleanup = tcf_act_police_cleanup,
.init = tcf_act_police_locate,
.walk = tcf_act_police_walker
};
@@ -370,19 +359,12 @@
static int __init
police_init_module(void)
{
- int err = tcf_hashinfo_init(&police_hash_info, POL_TAB_MASK);
- if (err)
- return err;
- err = tcf_register_action(&act_police_ops);
- if (err)
- tcf_hashinfo_destroy(&police_hash_info);
- return err;
+ return tcf_register_action(&act_police_ops, POL_TAB_MASK);
}
static void __exit
police_cleanup_module(void)
{
- tcf_hashinfo_destroy(&police_hash_info);
tcf_unregister_action(&act_police_ops);
}
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 8ef2f1f..992c231 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -25,7 +25,6 @@
#include <net/tc_act/tc_defact.h>
#define SIMP_TAB_MASK 7
-static struct tcf_hashinfo simp_hash_info;
#define SIMP_MAX_DATA 32
static int tcf_simp(struct sk_buff *skb, const struct tc_action *a,
@@ -47,20 +46,10 @@
return d->tcf_action;
}
-static int tcf_simp_release(struct tcf_defact *d, int bind)
+static void tcf_simp_release(struct tc_action *a, int bind)
{
- int ret = 0;
- if (d) {
- if (bind)
- d->tcf_bindcnt--;
- d->tcf_refcnt--;
- if (d->tcf_bindcnt <= 0 && d->tcf_refcnt <= 0) {
- kfree(d->tcfd_defdata);
- tcf_hash_destroy(&d->common, &simp_hash_info);
- ret = 1;
- }
- }
- return ret;
+ struct tcf_defact *d = to_defact(a);
+ kfree(d->tcfd_defdata);
}
static int alloc_defdata(struct tcf_defact *d, char *defdata)
@@ -94,7 +83,6 @@
struct nlattr *tb[TCA_DEF_MAX + 1];
struct tc_defact *parm;
struct tcf_defact *d;
- struct tcf_common *pc;
char *defdata;
int ret = 0, err;
@@ -114,29 +102,25 @@
parm = nla_data(tb[TCA_DEF_PARMS]);
defdata = nla_data(tb[TCA_DEF_DATA]);
- pc = tcf_hash_check(parm->index, a, bind);
- if (!pc) {
- pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind);
- if (IS_ERR(pc))
- return PTR_ERR(pc);
+ if (!tcf_hash_check(parm->index, a, bind)) {
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind);
+ if (ret)
+ return ret;
- d = to_defact(pc);
+ d = to_defact(a);
ret = alloc_defdata(d, defdata);
if (ret < 0) {
- if (est)
- gen_kill_estimator(&pc->tcfc_bstats,
- &pc->tcfc_rate_est);
- kfree_rcu(pc, tcfc_rcu);
+ tcf_hash_cleanup(a, est);
return ret;
}
d->tcf_action = parm->action;
ret = ACT_P_CREATED;
} else {
- d = to_defact(pc);
+ d = to_defact(a);
if (bind)
return 0;
- tcf_simp_release(d, bind);
+ tcf_hash_release(a, bind);
if (!ovr)
return -EEXIST;
@@ -144,19 +128,10 @@
}
if (ret == ACT_P_CREATED)
- tcf_hash_insert(pc, a->ops->hinfo);
+ tcf_hash_insert(a);
return ret;
}
-static int tcf_simp_cleanup(struct tc_action *a, int bind)
-{
- struct tcf_defact *d = a->priv;
-
- if (d)
- return tcf_simp_release(d, bind);
- return 0;
-}
-
static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
@@ -187,12 +162,11 @@
static struct tc_action_ops act_simp_ops = {
.kind = "simple",
- .hinfo = &simp_hash_info,
.type = TCA_ACT_SIMP,
.owner = THIS_MODULE,
.act = tcf_simp,
.dump = tcf_simp_dump,
- .cleanup = tcf_simp_cleanup,
+ .cleanup = tcf_simp_release,
.init = tcf_simp_init,
};
@@ -202,23 +176,15 @@
static int __init simp_init_module(void)
{
- int err, ret;
- err = tcf_hashinfo_init(&simp_hash_info, SIMP_TAB_MASK);
- if (err)
- return err;
-
- ret = tcf_register_action(&act_simp_ops);
+ int ret;
+ ret = tcf_register_action(&act_simp_ops, SIMP_TAB_MASK);
if (!ret)
pr_info("Simple TC action Loaded\n");
- else
- tcf_hashinfo_destroy(&simp_hash_info);
-
return ret;
}
static void __exit simp_cleanup_module(void)
{
- tcf_hashinfo_destroy(&simp_hash_info);
tcf_unregister_action(&act_simp_ops);
}
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 9872508..fcfeeaf 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -28,7 +28,6 @@
#include <net/tc_act/tc_skbedit.h>
#define SKBEDIT_TAB_MASK 15
-static struct tcf_hashinfo skbedit_hash_info;
static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
@@ -65,7 +64,6 @@
struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
struct tc_skbedit *parm;
struct tcf_skbedit *d;
- struct tcf_common *pc;
u32 flags = 0, *priority = NULL, *mark = NULL;
u16 *queue_mapping = NULL;
int ret = 0, err;
@@ -100,19 +98,18 @@
parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
- pc = tcf_hash_check(parm->index, a, bind);
- if (!pc) {
- pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind);
- if (IS_ERR(pc))
- return PTR_ERR(pc);
+ if (!tcf_hash_check(parm->index, a, bind)) {
+ ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind);
+ if (ret)
+ return ret;
- d = to_skbedit(pc);
+ d = to_skbedit(a);
ret = ACT_P_CREATED;
} else {
- d = to_skbedit(pc);
+ d = to_skbedit(a);
if (bind)
return 0;
- tcf_hash_release(pc, bind, a->ops->hinfo);
+ tcf_hash_release(a, bind);
if (!ovr)
return -EEXIST;
}
@@ -132,19 +129,10 @@
spin_unlock_bh(&d->tcf_lock);
if (ret == ACT_P_CREATED)
- tcf_hash_insert(pc, a->ops->hinfo);
+ tcf_hash_insert(a);
return ret;
}
-static int tcf_skbedit_cleanup(struct tc_action *a, int bind)
-{
- struct tcf_skbedit *d = a->priv;
-
- if (d)
- return tcf_hash_release(&d->common, bind, &skbedit_hash_info);
- return 0;
-}
-
static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
@@ -186,12 +174,10 @@
static struct tc_action_ops act_skbedit_ops = {
.kind = "skbedit",
- .hinfo = &skbedit_hash_info,
.type = TCA_ACT_SKBEDIT,
.owner = THIS_MODULE,
.act = tcf_skbedit,
.dump = tcf_skbedit_dump,
- .cleanup = tcf_skbedit_cleanup,
.init = tcf_skbedit_init,
};
@@ -201,15 +187,11 @@
static int __init skbedit_init_module(void)
{
- int err = tcf_hashinfo_init(&skbedit_hash_info, SKBEDIT_TAB_MASK);
- if (err)
- return err;
- return tcf_register_action(&act_skbedit_ops);
+ return tcf_register_action(&act_skbedit_ops, SKBEDIT_TAB_MASK);
}
static void __exit skbedit_cleanup_module(void)
{
- tcf_hashinfo_destroy(&skbedit_hash_info);
tcf_unregister_action(&act_skbedit_ops);
}
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index a366537..63a3ce7 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -29,11 +29,11 @@
#include <net/act_api.h>
#include <net/pkt_cls.h>
-#define HTSIZE (PAGE_SIZE/sizeof(struct fw_filter *))
+#define HTSIZE 256
struct fw_head {
- struct fw_filter *ht[HTSIZE];
- u32 mask;
+ u32 mask;
+ struct fw_filter *ht[HTSIZE];
};
struct fw_filter {
@@ -46,30 +46,11 @@
struct tcf_exts exts;
};
-static inline int fw_hash(u32 handle)
+static u32 fw_hash(u32 handle)
{
- if (HTSIZE == 4096)
- return ((handle >> 24) & 0xFFF) ^
- ((handle >> 12) & 0xFFF) ^
- (handle & 0xFFF);
- else if (HTSIZE == 2048)
- return ((handle >> 22) & 0x7FF) ^
- ((handle >> 11) & 0x7FF) ^
- (handle & 0x7FF);
- else if (HTSIZE == 1024)
- return ((handle >> 20) & 0x3FF) ^
- ((handle >> 10) & 0x3FF) ^
- (handle & 0x3FF);
- else if (HTSIZE == 512)
- return (handle >> 27) ^
- ((handle >> 18) & 0x1FF) ^
- ((handle >> 9) & 0x1FF) ^
- (handle & 0x1FF);
- else if (HTSIZE == 256) {
- u8 *t = (u8 *) &handle;
- return t[0] ^ t[1] ^ t[2] ^ t[3];
- } else
- return handle & (HTSIZE - 1);
+ handle ^= (handle >> 16);
+ handle ^= (handle >> 8);
+ return handle % HTSIZE;
}
static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp,
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 1313145..a0b84e0 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -273,11 +273,12 @@
void qdisc_list_add(struct Qdisc *q)
{
- struct Qdisc *root = qdisc_dev(q)->qdisc;
+ if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+ struct Qdisc *root = qdisc_dev(q)->qdisc;
- WARN_ON_ONCE(root == &noop_qdisc);
- if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
+ WARN_ON_ONCE(root == &noop_qdisc);
list_add_tail(&q->list, &root->list);
+ }
}
EXPORT_SYMBOL(qdisc_list_add);
@@ -1303,6 +1304,7 @@
struct gnet_dump d;
struct qdisc_size_table *stab;
+ cond_resched();
nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
if (!nlh)
goto out_nlmsg_trim;
@@ -1434,9 +1436,9 @@
s_idx = cb->args[0];
s_q_idx = q_idx = cb->args[1];
- rcu_read_lock();
idx = 0;
- for_each_netdev_rcu(net, dev) {
+ ASSERT_RTNL();
+ for_each_netdev(net, dev) {
struct netdev_queue *dev_queue;
if (idx < s_idx)
@@ -1459,8 +1461,6 @@
}
done:
- rcu_read_unlock();
-
cb->args[0] = idx;
cb->args[1] = q_idx;
@@ -1617,6 +1617,7 @@
struct gnet_dump d;
const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops;
+ cond_resched();
nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
if (!nlh)
goto out_nlmsg_trim;
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 1f9c314..8449b33 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -623,8 +623,7 @@
if (nla_put_u32(skb, TCA_ATM_EXCESS, 0))
goto nla_put_failure;
}
- nla_nest_end(skb, nest);
- return skb->len;
+ return nla_nest_end(skb, nest);
nla_put_failure:
nla_nest_cancel(skb, nest);
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 2f80d01..ead5264 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1563,8 +1563,7 @@
goto nla_put_failure;
if (cbq_dump_attr(skb, &q->link) < 0)
goto nla_put_failure;
- nla_nest_end(skb, nest);
- return skb->len;
+ return nla_nest_end(skb, nest);
nla_put_failure:
nla_nest_cancel(skb, nest);
@@ -1599,8 +1598,7 @@
goto nla_put_failure;
if (cbq_dump_attr(skb, cl) < 0)
goto nla_put_failure;
- nla_nest_end(skb, nest);
- return skb->len;
+ return nla_nest_end(skb, nest);
nla_put_failure:
nla_nest_cancel(skb, nest);
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 08ef7a4..23c682b 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -601,6 +601,7 @@
{
struct fq_sched_data *q = qdisc_priv(sch);
struct rb_root *array;
+ void *old_fq_root;
u32 idx;
if (q->fq_root && log == q->fq_trees_log)
@@ -615,13 +616,19 @@
for (idx = 0; idx < (1U << log); idx++)
array[idx] = RB_ROOT;
- if (q->fq_root) {
- fq_rehash(q, q->fq_root, q->fq_trees_log, array, log);
- fq_free(q->fq_root);
- }
+ sch_tree_lock(sch);
+
+ old_fq_root = q->fq_root;
+ if (old_fq_root)
+ fq_rehash(q, old_fq_root, q->fq_trees_log, array, log);
+
q->fq_root = array;
q->fq_trees_log = log;
+ sch_tree_unlock(sch);
+
+ fq_free(old_fq_root);
+
return 0;
}
@@ -697,9 +704,11 @@
q->flow_refill_delay = usecs_to_jiffies(usecs_delay);
}
- if (!err)
+ if (!err) {
+ sch_tree_unlock(sch);
err = fq_resize(sch, fq_log);
-
+ sch_tree_lock(sch);
+ }
while (sch->q.qlen > sch->limit) {
struct sk_buff *skb = fq_dequeue(sch);
@@ -772,8 +781,7 @@
nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log))
goto nla_put_failure;
- nla_nest_end(skb, opts);
- return skb->len;
+ return nla_nest_end(skb, opts);
nla_put_failure:
return -1;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index ba5bc92..0bf432c 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -450,8 +450,7 @@
q->flows_cnt))
goto nla_put_failure;
- nla_nest_end(skb, opts);
- return skb->len;
+ return nla_nest_end(skb, opts);
nla_put_failure:
return -1;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index c407561..ec8aeaa 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1353,8 +1353,7 @@
goto nla_put_failure;
if (hfsc_dump_curves(skb, cl) < 0)
goto nla_put_failure;
- nla_nest_end(skb, nest);
- return skb->len;
+ return nla_nest_end(skb, nest);
nla_put_failure:
nla_nest_cancel(skb, nest);
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 647680b..edee03d 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -691,8 +691,7 @@
nla_put_u32(skb, TCA_HHF_NON_HH_WEIGHT, q->hhf_non_hh_weight))
goto nla_put_failure;
- nla_nest_end(skb, opts);
- return skb->len;
+ return nla_nest_end(skb, opts);
nla_put_failure:
return -1;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 722e137..9f949ab 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1062,12 +1062,13 @@
static int htb_dump(struct Qdisc *sch, struct sk_buff *skb)
{
- spinlock_t *root_lock = qdisc_root_sleeping_lock(sch);
struct htb_sched *q = qdisc_priv(sch);
struct nlattr *nest;
struct tc_htb_glob gopt;
- spin_lock_bh(root_lock);
+ /* Its safe to not acquire qdisc lock. As we hold RTNL,
+ * no change can happen on the qdisc parameters.
+ */
gopt.direct_pkts = q->direct_pkts;
gopt.version = HTB_VER;
@@ -1081,13 +1082,10 @@
if (nla_put(skb, TCA_HTB_INIT, sizeof(gopt), &gopt) ||
nla_put_u32(skb, TCA_HTB_DIRECT_QLEN, q->direct_qlen))
goto nla_put_failure;
- nla_nest_end(skb, nest);
- spin_unlock_bh(root_lock);
- return skb->len;
+ return nla_nest_end(skb, nest);
nla_put_failure:
- spin_unlock_bh(root_lock);
nla_nest_cancel(skb, nest);
return -1;
}
@@ -1096,11 +1094,12 @@
struct sk_buff *skb, struct tcmsg *tcm)
{
struct htb_class *cl = (struct htb_class *)arg;
- spinlock_t *root_lock = qdisc_root_sleeping_lock(sch);
struct nlattr *nest;
struct tc_htb_opt opt;
- spin_lock_bh(root_lock);
+ /* Its safe to not acquire qdisc lock. As we hold RTNL,
+ * no change can happen on the class parameters.
+ */
tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT;
tcm->tcm_handle = cl->common.classid;
if (!cl->level && cl->un.leaf.q)
@@ -1128,12 +1127,9 @@
nla_put_u64(skb, TCA_HTB_CEIL64, cl->ceil.rate_bytes_ps))
goto nla_put_failure;
- nla_nest_end(skb, nest);
- spin_unlock_bh(root_lock);
- return skb->len;
+ return nla_nest_end(skb, nest);
nla_put_failure:
- spin_unlock_bh(root_lock);
nla_nest_cancel(skb, nest);
return -1;
}
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index bce1665..62871c1 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -100,8 +100,7 @@
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
- nla_nest_end(skb, nest);
- return skb->len;
+ return nla_nest_end(skb, nest);
nla_put_failure:
nla_nest_cancel(skb, nest);
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index de1059a..f1669a00 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -117,6 +117,11 @@
LOST_IN_BURST_PERIOD,
} _4_state_model;
+ enum {
+ GOOD_STATE = 1,
+ BAD_STATE,
+ } GE_state_model;
+
/* Correlated Loss Generation models */
struct clgstate {
/* state of the Markov chain */
@@ -272,15 +277,15 @@
struct clgstate *clg = &q->clg;
switch (clg->state) {
- case 1:
+ case GOOD_STATE:
if (prandom_u32() < clg->a1)
- clg->state = 2;
+ clg->state = BAD_STATE;
if (prandom_u32() < clg->a4)
return true;
break;
- case 2:
+ case BAD_STATE:
if (prandom_u32() < clg->a2)
- clg->state = 1;
+ clg->state = GOOD_STATE;
if (prandom_u32() > clg->a3)
return true;
}
@@ -689,9 +694,8 @@
return 0;
}
-static void get_correlation(struct Qdisc *sch, const struct nlattr *attr)
+static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr)
{
- struct netem_sched_data *q = qdisc_priv(sch);
const struct tc_netem_corr *c = nla_data(attr);
init_crandom(&q->delay_cor, c->delay_corr);
@@ -699,27 +703,24 @@
init_crandom(&q->dup_cor, c->dup_corr);
}
-static void get_reorder(struct Qdisc *sch, const struct nlattr *attr)
+static void get_reorder(struct netem_sched_data *q, const struct nlattr *attr)
{
- struct netem_sched_data *q = qdisc_priv(sch);
const struct tc_netem_reorder *r = nla_data(attr);
q->reorder = r->probability;
init_crandom(&q->reorder_cor, r->correlation);
}
-static void get_corrupt(struct Qdisc *sch, const struct nlattr *attr)
+static void get_corrupt(struct netem_sched_data *q, const struct nlattr *attr)
{
- struct netem_sched_data *q = qdisc_priv(sch);
const struct tc_netem_corrupt *r = nla_data(attr);
q->corrupt = r->probability;
init_crandom(&q->corrupt_cor, r->correlation);
}
-static void get_rate(struct Qdisc *sch, const struct nlattr *attr)
+static void get_rate(struct netem_sched_data *q, const struct nlattr *attr)
{
- struct netem_sched_data *q = qdisc_priv(sch);
const struct tc_netem_rate *r = nla_data(attr);
q->rate = r->rate;
@@ -732,9 +733,8 @@
q->cell_size_reciprocal = (struct reciprocal_value) { 0 };
}
-static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr)
+static int get_loss_clg(struct netem_sched_data *q, const struct nlattr *attr)
{
- struct netem_sched_data *q = qdisc_priv(sch);
const struct nlattr *la;
int rem;
@@ -752,7 +752,7 @@
q->loss_model = CLG_4_STATES;
- q->clg.state = 1;
+ q->clg.state = TX_IN_GAP_PERIOD;
q->clg.a1 = gi->p13;
q->clg.a2 = gi->p31;
q->clg.a3 = gi->p32;
@@ -770,7 +770,7 @@
}
q->loss_model = CLG_GILB_ELL;
- q->clg.state = 1;
+ q->clg.state = GOOD_STATE;
q->clg.a1 = ge->p;
q->clg.a2 = ge->r;
q->clg.a3 = ge->h;
@@ -821,6 +821,8 @@
struct netem_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_NETEM_MAX + 1];
struct tc_netem_qopt *qopt;
+ struct clgstate old_clg;
+ int old_loss_model = CLG_RANDOM;
int ret;
if (opt == NULL)
@@ -831,6 +833,33 @@
if (ret < 0)
return ret;
+ /* backup q->clg and q->loss_model */
+ old_clg = q->clg;
+ old_loss_model = q->loss_model;
+
+ if (tb[TCA_NETEM_LOSS]) {
+ ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]);
+ if (ret) {
+ q->loss_model = old_loss_model;
+ return ret;
+ }
+ } else {
+ q->loss_model = CLG_RANDOM;
+ }
+
+ if (tb[TCA_NETEM_DELAY_DIST]) {
+ ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]);
+ if (ret) {
+ /* recover clg and loss_model, in case of
+ * q->clg and q->loss_model were modified
+ * in get_loss_clg()
+ */
+ q->clg = old_clg;
+ q->loss_model = old_loss_model;
+ return ret;
+ }
+ }
+
sch->limit = qopt->limit;
q->latency = qopt->latency;
@@ -848,22 +877,16 @@
q->reorder = ~0;
if (tb[TCA_NETEM_CORR])
- get_correlation(sch, tb[TCA_NETEM_CORR]);
-
- if (tb[TCA_NETEM_DELAY_DIST]) {
- ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]);
- if (ret)
- return ret;
- }
+ get_correlation(q, tb[TCA_NETEM_CORR]);
if (tb[TCA_NETEM_REORDER])
- get_reorder(sch, tb[TCA_NETEM_REORDER]);
+ get_reorder(q, tb[TCA_NETEM_REORDER]);
if (tb[TCA_NETEM_CORRUPT])
- get_corrupt(sch, tb[TCA_NETEM_CORRUPT]);
+ get_corrupt(q, tb[TCA_NETEM_CORRUPT]);
if (tb[TCA_NETEM_RATE])
- get_rate(sch, tb[TCA_NETEM_RATE]);
+ get_rate(q, tb[TCA_NETEM_RATE]);
if (tb[TCA_NETEM_RATE64])
q->rate = max_t(u64, q->rate,
@@ -872,10 +895,6 @@
if (tb[TCA_NETEM_ECN])
q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]);
- q->loss_model = CLG_RANDOM;
- if (tb[TCA_NETEM_LOSS])
- ret = get_loss_clg(sch, tb[TCA_NETEM_LOSS]);
-
return ret;
}
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index a255d02..fefeeb7 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -15,6 +15,11 @@
*
* ECN support is added by Naeem Khademi <naeemk@ifi.uio.no>
* University of Oslo, Norway.
+ *
+ * References:
+ * IETF draft submission: http://tools.ietf.org/html/draft-pan-aqm-pie-00
+ * IEEE Conference on High Performance Switching and Routing 2013 :
+ * "PIE: A * Lightweight Control Scheme to Address the Bufferbloat Problem"
*/
#include <linux/module.h>
@@ -36,7 +41,7 @@
psched_time_t target; /* user specified target delay in pschedtime */
u32 tupdate; /* timer frequency (in jiffies) */
u32 limit; /* number of packets that can be enqueued */
- u32 alpha; /* alpha and beta are between -4 and 4 */
+ u32 alpha; /* alpha and beta are between 0 and 32 */
u32 beta; /* and are used for shift relative to 1 */
bool ecn; /* true if ecn is enabled */
bool bytemode; /* to scale drop early prob based on pkt size */
@@ -326,10 +331,16 @@
if (qdelay == 0 && qlen != 0)
update_prob = false;
- /* Add ranges for alpha and beta, more aggressive for high dropping
- * mode and gentle steps for light dropping mode
- * In light dropping mode, take gentle steps; in medium dropping mode,
- * take medium steps; in high dropping mode, take big steps.
+ /* In the algorithm, alpha and beta are between 0 and 2 with typical
+ * value for alpha as 0.125. In this implementation, we use values 0-32
+ * passed from user space to represent this. Also, alpha and beta have
+ * unit of HZ and need to be scaled before they can used to update
+ * probability. alpha/beta are updated locally below by 1) scaling them
+ * appropriately 2) scaling down by 16 to come to 0-2 range.
+ * Please see paper for details.
+ *
+ * We scale alpha and beta differently depending on whether we are in
+ * light, medium or high dropping mode.
*/
if (q->vars.prob < MAX_PROB / 100) {
alpha =
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 1cb413f..18ff634 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -101,12 +101,11 @@
struct tbf_sched_data {
/* Parameters */
u32 limit; /* Maximal length of backlog: bytes */
+ u32 max_size;
s64 buffer; /* Token bucket depth/rate: MUST BE >= MTU/B */
s64 mtu;
- u32 max_size;
struct psched_ratecfg rate;
struct psched_ratecfg peak;
- bool peak_present;
/* Variables */
s64 tokens; /* Current number of B tokens */
@@ -222,6 +221,11 @@
return len;
}
+static bool tbf_peak_present(const struct tbf_sched_data *q)
+{
+ return q->peak.rate_bytes_ps;
+}
+
static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
{
struct tbf_sched_data *q = qdisc_priv(sch);
@@ -238,7 +242,7 @@
now = ktime_to_ns(ktime_get());
toks = min_t(s64, now - q->t_c, q->buffer);
- if (q->peak_present) {
+ if (tbf_peak_present(q)) {
ptoks = toks + q->ptokens;
if (ptoks > q->mtu)
ptoks = q->mtu;
@@ -334,18 +338,6 @@
qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate,
tb[TCA_TBF_PTAB]));
- if (q->qdisc != &noop_qdisc) {
- err = fifo_set_limit(q->qdisc, qopt->limit);
- if (err)
- goto done;
- } else if (qopt->limit > 0) {
- child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit);
- if (IS_ERR(child)) {
- err = PTR_ERR(child);
- goto done;
- }
- }
-
buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U);
mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U);
@@ -378,6 +370,8 @@
} else {
max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu));
}
+ } else {
+ memset(&peak, 0, sizeof(peak));
}
if (max_size < psched_mtu(qdisc_dev(sch)))
@@ -390,6 +384,18 @@
goto done;
}
+ if (q->qdisc != &noop_qdisc) {
+ err = fifo_set_limit(q->qdisc, qopt->limit);
+ if (err)
+ goto done;
+ } else if (qopt->limit > 0) {
+ child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit);
+ if (IS_ERR(child)) {
+ err = PTR_ERR(child);
+ goto done;
+ }
+ }
+
sch_tree_lock(sch);
if (child) {
qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
@@ -410,12 +416,7 @@
q->ptokens = q->mtu;
memcpy(&q->rate, &rate, sizeof(struct psched_ratecfg));
- if (qopt->peakrate.rate) {
- memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg));
- q->peak_present = true;
- } else {
- q->peak_present = false;
- }
+ memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg));
sch_tree_unlock(sch);
err = 0;
@@ -458,7 +459,7 @@
opt.limit = q->limit;
psched_ratecfg_getrate(&opt.rate, &q->rate);
- if (q->peak_present)
+ if (tbf_peak_present(q))
psched_ratecfg_getrate(&opt.peakrate, &q->peak);
else
memset(&opt.peakrate, 0, sizeof(opt.peakrate));
@@ -469,13 +470,12 @@
if (q->rate.rate_bytes_ps >= (1ULL << 32) &&
nla_put_u64(skb, TCA_TBF_RATE64, q->rate.rate_bytes_ps))
goto nla_put_failure;
- if (q->peak_present &&
+ if (tbf_peak_present(q) &&
q->peak.rate_bytes_ps >= (1ULL << 32) &&
nla_put_u64(skb, TCA_TBF_PRATE64, q->peak.rate_bytes_ps))
goto nla_put_failure;
- nla_nest_end(skb, nest);
- return skb->len;
+ return nla_nest_end(skb, nest);
nla_put_failure:
nla_nest_cancel(skb, nest);
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 5ae6092..4f6d6f9 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1239,78 +1239,106 @@
}
/* Update the retran path for sending a retransmitted packet.
- * Round-robin through the active transports, else round-robin
- * through the inactive transports as this is the next best thing
- * we can try.
+ * See also RFC4960, 6.4. Multi-Homed SCTP Endpoints:
+ *
+ * When there is outbound data to send and the primary path
+ * becomes inactive (e.g., due to failures), or where the
+ * SCTP user explicitly requests to send data to an
+ * inactive destination transport address, before reporting
+ * an error to its ULP, the SCTP endpoint should try to send
+ * the data to an alternate active destination transport
+ * address if one exists.
+ *
+ * When retransmitting data that timed out, if the endpoint
+ * is multihomed, it should consider each source-destination
+ * address pair in its retransmission selection policy.
+ * When retransmitting timed-out data, the endpoint should
+ * attempt to pick the most divergent source-destination
+ * pair from the original source-destination pair to which
+ * the packet was transmitted.
+ *
+ * Note: Rules for picking the most divergent source-destination
+ * pair are an implementation decision and are not specified
+ * within this document.
+ *
+ * Our basic strategy is to round-robin transports in priorities
+ * according to sctp_state_prio_map[] e.g., if no such
+ * transport with state SCTP_ACTIVE exists, round-robin through
+ * SCTP_UNKNOWN, etc. You get the picture.
*/
-void sctp_assoc_update_retran_path(struct sctp_association *asoc)
+static const u8 sctp_trans_state_to_prio_map[] = {
+ [SCTP_ACTIVE] = 3, /* best case */
+ [SCTP_UNKNOWN] = 2,
+ [SCTP_PF] = 1,
+ [SCTP_INACTIVE] = 0, /* worst case */
+};
+
+static u8 sctp_trans_score(const struct sctp_transport *trans)
{
- struct sctp_transport *t, *next;
- struct list_head *head = &asoc->peer.transport_addr_list;
- struct list_head *pos;
-
- if (asoc->peer.transport_count == 1)
- return;
-
- /* Find the next transport in a round-robin fashion. */
- t = asoc->peer.retran_path;
- pos = &t->transports;
- next = NULL;
-
- while (1) {
- /* Skip the head. */
- if (pos->next == head)
- pos = head->next;
- else
- pos = pos->next;
-
- t = list_entry(pos, struct sctp_transport, transports);
-
- /* We have exhausted the list, but didn't find any
- * other active transports. If so, use the next
- * transport.
- */
- if (t == asoc->peer.retran_path) {
- t = next;
- break;
- }
-
- /* Try to find an active transport. */
-
- if ((t->state == SCTP_ACTIVE) ||
- (t->state == SCTP_UNKNOWN)) {
- break;
- } else {
- /* Keep track of the next transport in case
- * we don't find any active transport.
- */
- if (t->state != SCTP_UNCONFIRMED && !next)
- next = t;
- }
- }
-
- if (t)
- asoc->peer.retran_path = t;
- else
- t = asoc->peer.retran_path;
-
- pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc,
- &t->ipaddr.sa);
+ return sctp_trans_state_to_prio_map[trans->state];
}
-/* Choose the transport for sending retransmit packet. */
-struct sctp_transport *sctp_assoc_choose_alter_transport(
- struct sctp_association *asoc, struct sctp_transport *last_sent_to)
+static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr,
+ struct sctp_transport *best)
+{
+ if (best == NULL)
+ return curr;
+
+ return sctp_trans_score(curr) > sctp_trans_score(best) ? curr : best;
+}
+
+void sctp_assoc_update_retran_path(struct sctp_association *asoc)
+{
+ struct sctp_transport *trans = asoc->peer.retran_path;
+ struct sctp_transport *trans_next = NULL;
+
+ /* We're done as we only have the one and only path. */
+ if (asoc->peer.transport_count == 1)
+ return;
+ /* If active_path and retran_path are the same and active,
+ * then this is the only active path. Use it.
+ */
+ if (asoc->peer.active_path == asoc->peer.retran_path &&
+ asoc->peer.active_path->state == SCTP_ACTIVE)
+ return;
+
+ /* Iterate from retran_path's successor back to retran_path. */
+ for (trans = list_next_entry(trans, transports); 1;
+ trans = list_next_entry(trans, transports)) {
+ /* Manually skip the head element. */
+ if (&trans->transports == &asoc->peer.transport_addr_list)
+ continue;
+ if (trans->state == SCTP_UNCONFIRMED)
+ continue;
+ trans_next = sctp_trans_elect_best(trans, trans_next);
+ /* Active is good enough for immediate return. */
+ if (trans_next->state == SCTP_ACTIVE)
+ break;
+ /* We've reached the end, time to update path. */
+ if (trans == asoc->peer.retran_path)
+ break;
+ }
+
+ asoc->peer.retran_path = trans_next;
+
+ pr_debug("%s: association:%p updated new path to addr:%pISpc\n",
+ __func__, asoc, &asoc->peer.retran_path->ipaddr.sa);
+}
+
+struct sctp_transport *
+sctp_assoc_choose_alter_transport(struct sctp_association *asoc,
+ struct sctp_transport *last_sent_to)
{
/* If this is the first time packet is sent, use the active path,
* else use the retran path. If the last packet was sent over the
* retran path, update the retran path and use it.
*/
- if (!last_sent_to)
+ if (last_sent_to == NULL) {
return asoc->peer.active_path;
- else {
+ } else {
if (last_sent_to == asoc->peer.retran_path)
sctp_assoc_update_retran_path(asoc);
+
return asoc->peer.retran_path;
}
}
@@ -1367,44 +1395,35 @@
return false;
}
-/* Increase asoc's rwnd by len and send any window update SACK if needed. */
-void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len)
+/* Update asoc's rwnd for the approximated state in the buffer,
+ * and check whether SACK needs to be sent.
+ */
+void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer)
{
+ int rx_count;
struct sctp_chunk *sack;
struct timer_list *timer;
- if (asoc->rwnd_over) {
- if (asoc->rwnd_over >= len) {
- asoc->rwnd_over -= len;
- } else {
- asoc->rwnd += (len - asoc->rwnd_over);
- asoc->rwnd_over = 0;
- }
- } else {
- asoc->rwnd += len;
- }
+ if (asoc->ep->rcvbuf_policy)
+ rx_count = atomic_read(&asoc->rmem_alloc);
+ else
+ rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
- /* If we had window pressure, start recovering it
- * once our rwnd had reached the accumulated pressure
- * threshold. The idea is to recover slowly, but up
- * to the initial advertised window.
- */
- if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) {
- int change = min(asoc->pathmtu, asoc->rwnd_press);
- asoc->rwnd += change;
- asoc->rwnd_press -= change;
- }
+ if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0)
+ asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1;
+ else
+ asoc->rwnd = 0;
- pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n",
- __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
- asoc->a_rwnd);
+ pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n",
+ __func__, asoc, asoc->rwnd, rx_count,
+ asoc->base.sk->sk_rcvbuf);
/* Send a window update SACK if the rwnd has increased by at least the
* minimum of the association's PMTU and half of the receive buffer.
* The algorithm used is similar to the one described in
* Section 4.2.3.3 of RFC 1122.
*/
- if (sctp_peer_needs_update(asoc)) {
+ if (update_peer && sctp_peer_needs_update(asoc)) {
asoc->a_rwnd = asoc->rwnd;
pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u "
@@ -1426,45 +1445,6 @@
}
}
-/* Decrease asoc's rwnd by len. */
-void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
-{
- int rx_count;
- int over = 0;
-
- if (unlikely(!asoc->rwnd || asoc->rwnd_over))
- pr_debug("%s: association:%p has asoc->rwnd:%u, "
- "asoc->rwnd_over:%u!\n", __func__, asoc,
- asoc->rwnd, asoc->rwnd_over);
-
- if (asoc->ep->rcvbuf_policy)
- rx_count = atomic_read(&asoc->rmem_alloc);
- else
- rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
-
- /* If we've reached or overflowed our receive buffer, announce
- * a 0 rwnd if rwnd would still be positive. Store the
- * the potential pressure overflow so that the window can be restored
- * back to original value.
- */
- if (rx_count >= asoc->base.sk->sk_rcvbuf)
- over = 1;
-
- if (asoc->rwnd >= len) {
- asoc->rwnd -= len;
- if (over) {
- asoc->rwnd_press += asoc->rwnd;
- asoc->rwnd = 0;
- }
- } else {
- asoc->rwnd_over = len - asoc->rwnd;
- asoc->rwnd = 0;
- }
-
- pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n",
- __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
- asoc->rwnd_press);
-}
/* Build the bind address list for the association based on info from the
* local endpoint and the remote peer.
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0f6259a..2b1738e 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -662,6 +662,8 @@
*/
sctp_v6_to_sk_daddr(&asoc->peer.primary_addr, newsk);
+ newsk->sk_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+
sk_refcnt_debug_inc(newsk);
if (newsk->sk_prot->init(newsk)) {
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 632090b..3a1767e 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1421,8 +1421,8 @@
BUG_ON(!list_empty(&chunk->list));
list_del_init(&chunk->transmitted_list);
- /* Free the chunk skb data and the SCTP_chunk stub itself. */
- dev_kfree_skb(chunk->skb);
+ consume_skb(chunk->skb);
+ consume_skb(chunk->auth_chunk);
SCTP_DBG_OBJCNT_DEC(chunk);
kmem_cache_free(sctp_chunk_cachep, chunk);
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index bd85915..5d6883f 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -495,11 +495,12 @@
}
/* If the transport error count is greater than the pf_retrans
- * threshold, and less than pathmaxrtx, then mark this transport
- * as Partially Failed, ee SCTP Quick Failover Draft, secon 5.1,
- * point 1
+ * threshold, and less than pathmaxrtx, and if the current state
+ * is not SCTP_UNCONFIRMED, then mark this transport as Partially
+ * Failed, see SCTP Quick Failover Draft, section 5.1
*/
if ((transport->state != SCTP_PF) &&
+ (transport->state != SCTP_UNCONFIRMED) &&
(asoc->pf_retrans < transport->pathmaxrxt) &&
(transport->error_count > asoc->pf_retrans)) {
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 483dcd7..01e0024 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -758,6 +758,12 @@
struct sctp_chunk auth;
sctp_ierror_t ret;
+ /* Make sure that we and the peer are AUTH capable */
+ if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
+ sctp_association_free(new_asoc);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ }
+
/* set-up our fake chunk so that we can process it */
auth.skb = chunk->auth_chunk;
auth.asoc = chunk->asoc;
@@ -768,10 +774,6 @@
auth.transport = chunk->transport;
ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
-
- /* We can now safely free the auth_chunk clone */
- kfree_skb(chunk->auth_chunk);
-
if (ret != SCTP_IERROR_NO_ERROR) {
sctp_association_free(new_asoc);
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -6176,7 +6178,7 @@
* PMTU. In cases, such as loopback, this might be a rather
* large spill over.
*/
- if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over ||
+ if ((!chunk->data_accepted) && (!asoc->rwnd ||
(datalen > asoc->rwnd + asoc->frag_point))) {
/* If this is the next TSN, consider reneging to make
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9e91d6e..981aaf8 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -64,6 +64,7 @@
#include <linux/crypto.h>
#include <linux/slab.h>
#include <linux/file.h>
+#include <linux/compat.h>
#include <net/ip.h>
#include <net/icmp.h>
@@ -1368,11 +1369,19 @@
/*
* New (hopefully final) interface for the API.
* We use the sctp_getaddrs_old structure so that use-space library
- * can avoid any unnecessary allocations. The only defferent part
+ * can avoid any unnecessary allocations. The only different part
* is that we store the actual length of the address buffer into the
- * addrs_num structure member. That way we can re-use the existing
+ * addrs_num structure member. That way we can re-use the existing
* code.
*/
+#ifdef CONFIG_COMPAT
+struct compat_sctp_getaddrs_old {
+ sctp_assoc_t assoc_id;
+ s32 addr_num;
+ compat_uptr_t addrs; /* struct sockaddr * */
+};
+#endif
+
static int sctp_getsockopt_connectx3(struct sock *sk, int len,
char __user *optval,
int __user *optlen)
@@ -1381,16 +1390,30 @@
sctp_assoc_t assoc_id = 0;
int err = 0;
- if (len < sizeof(param))
- return -EINVAL;
+#ifdef CONFIG_COMPAT
+ if (is_compat_task()) {
+ struct compat_sctp_getaddrs_old param32;
- if (copy_from_user(¶m, optval, sizeof(param)))
- return -EFAULT;
+ if (len < sizeof(param32))
+ return -EINVAL;
+ if (copy_from_user(¶m32, optval, sizeof(param32)))
+ return -EFAULT;
- err = __sctp_setsockopt_connectx(sk,
- (struct sockaddr __user *)param.addrs,
- param.addr_num, &assoc_id);
+ param.assoc_id = param32.assoc_id;
+ param.addr_num = param32.addr_num;
+ param.addrs = compat_ptr(param32.addrs);
+ } else
+#endif
+ {
+ if (len < sizeof(param))
+ return -EINVAL;
+ if (copy_from_user(¶m, optval, sizeof(param)))
+ return -EFAULT;
+ }
+ err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *)
+ param.addrs, param.addr_num,
+ &assoc_id);
if (err == 0 || err == -EINPROGRESS) {
if (copy_to_user(optval, &assoc_id, sizeof(assoc_id)))
return -EFAULT;
@@ -2092,12 +2115,6 @@
sctp_skb_pull(skb, copied);
skb_queue_head(&sk->sk_receive_queue, skb);
- /* When only partial message is copied to the user, increase
- * rwnd by that amount. If all the data in the skb is read,
- * rwnd is updated when the event is freed.
- */
- if (!sctp_ulpevent_is_notification(event))
- sctp_assoc_rwnd_increase(event->asoc, copied);
goto out;
} else if ((event->msg_flags & MSG_NOTIFICATION) ||
(event->msg_flags & MSG_EOR))
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 7135e61..35c8923 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -151,6 +151,7 @@
},
{
.procname = "cookie_hmac_alg",
+ .data = &init_net.sctp.sctp_hmac_alg,
.maxlen = 8,
.mode = 0644,
.proc_handler = proc_sctp_do_hmac_alg,
@@ -401,15 +402,18 @@
int sctp_sysctl_net_register(struct net *net)
{
- struct ctl_table *table;
- int i;
+ struct ctl_table *table = sctp_net_table;
- table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
- if (!table)
- return -ENOMEM;
+ if (!net_eq(net, &init_net)) {
+ int i;
- for (i = 0; table[i].data; i++)
- table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+ table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+
+ for (i = 0; table[i].data; i++)
+ table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+ }
net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table);
return 0;
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index d0810dc..1d348d1 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -652,5 +652,4 @@
if (!mod_timer(&t->T3_rtx_timer, jiffies + t->rto))
sctp_transport_hold(t);
}
- return;
}
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 85c6465..8d198ae 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -989,7 +989,7 @@
skb = sctp_event2skb(event);
/* Set the owner and charge rwnd for bytes received. */
sctp_ulpevent_set_owner(event, asoc);
- sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb));
+ sctp_assoc_rwnd_update(asoc, false);
if (!skb->data_len)
return;
@@ -1011,6 +1011,7 @@
{
struct sk_buff *skb, *frag;
unsigned int len;
+ struct sctp_association *asoc;
/* Current stack structures assume that the rcv buffer is
* per socket. For UDP style sockets this is not true as
@@ -1035,8 +1036,11 @@
}
done:
- sctp_assoc_rwnd_increase(event->asoc, len);
+ asoc = event->asoc;
+ sctp_association_hold(asoc);
sctp_ulpevent_release_owner(event);
+ sctp_assoc_rwnd_update(asoc, true);
+ sctp_association_put(asoc);
}
static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event)
diff --git a/net/socket.c b/net/socket.c
index 879933a..f25eaa3 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -450,16 +450,17 @@
static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
{
- struct file *file;
+ struct fd f = fdget(fd);
struct socket *sock;
*err = -EBADF;
- file = fget_light(fd, fput_needed);
- if (file) {
- sock = sock_from_file(file, err);
- if (sock)
+ if (f.file) {
+ sock = sock_from_file(f.file, err);
+ if (likely(sock)) {
+ *fput_needed = f.flags;
return sock;
- fput_light(file, *fput_needed);
+ }
+ fdput(f);
}
return NULL;
}
@@ -593,7 +594,7 @@
}
if (rcu_dereference_protected(sock->wq, 1)->fasync_list)
- printk(KERN_ERR "sock_release: fasync list not empty!\n");
+ pr_err("%s: fasync list not empty!\n", __func__);
if (test_bit(SOCK_EXTERNALLY_ALLOCATED, &sock->flags))
return;
@@ -1265,8 +1266,8 @@
static int warned;
if (!warned) {
warned = 1;
- printk(KERN_INFO "%s uses obsolete (PF_INET,SOCK_PACKET)\n",
- current->comm);
+ pr_info("%s uses obsolete (PF_INET,SOCK_PACKET)\n",
+ current->comm);
}
family = PF_PACKET;
}
@@ -1985,6 +1986,10 @@
{
if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
return -EFAULT;
+
+ if (kmsg->msg_namelen < 0)
+ return -EINVAL;
+
if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
kmsg->msg_namelen = sizeof(struct sockaddr_storage);
return 0;
@@ -2595,8 +2600,7 @@
int err;
if (ops->family >= NPROTO) {
- printk(KERN_CRIT "protocol %d >= NPROTO(%d)\n", ops->family,
- NPROTO);
+ pr_crit("protocol %d >= NPROTO(%d)\n", ops->family, NPROTO);
return -ENOBUFS;
}
@@ -2610,7 +2614,7 @@
}
spin_unlock(&net_family_lock);
- printk(KERN_INFO "NET: Registered protocol family %d\n", ops->family);
+ pr_info("NET: Registered protocol family %d\n", ops->family);
return err;
}
EXPORT_SYMBOL(sock_register);
@@ -2638,7 +2642,7 @@
synchronize_rcu();
- printk(KERN_INFO "NET: Unregistered protocol family %d\n", family);
+ pr_info("NET: Unregistered protocol family %d\n", family);
}
EXPORT_SYMBOL(sock_unregister);
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 6c0513a..36e431e 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -108,6 +108,7 @@
static DEFINE_SPINLOCK(pipe_version_lock);
static struct rpc_wait_queue pipe_version_rpc_waitqueue;
static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue);
+static void gss_put_auth(struct gss_auth *gss_auth);
static void gss_free_ctx(struct gss_cl_ctx *);
static const struct rpc_pipe_ops gss_upcall_ops_v0;
@@ -320,6 +321,7 @@
if (gss_msg->ctx != NULL)
gss_put_ctx(gss_msg->ctx);
rpc_destroy_wait_queue(&gss_msg->rpc_waitqueue);
+ gss_put_auth(gss_msg->auth);
kfree(gss_msg);
}
@@ -498,9 +500,12 @@
default:
err = gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name);
if (err)
- goto err_free_msg;
+ goto err_put_pipe_version;
};
+ kref_get(&gss_auth->kref);
return gss_msg;
+err_put_pipe_version:
+ put_pipe_version(gss_auth->net);
err_free_msg:
kfree(gss_msg);
err:
@@ -991,6 +996,8 @@
gss_auth->service = gss_pseudoflavor_to_service(gss_auth->mech, flavor);
if (gss_auth->service == 0)
goto err_put_mech;
+ if (!gssd_running(gss_auth->net))
+ goto err_put_mech;
auth = &gss_auth->rpc_auth;
auth->au_cslack = GSS_CRED_SLACK >> 2;
auth->au_rslack = GSS_VERF_SLACK >> 2;
@@ -1062,6 +1069,12 @@
}
static void
+gss_put_auth(struct gss_auth *gss_auth)
+{
+ kref_put(&gss_auth->kref, gss_free_callback);
+}
+
+static void
gss_destroy(struct rpc_auth *auth)
{
struct gss_auth *gss_auth = container_of(auth,
@@ -1082,7 +1095,7 @@
gss_auth->gss_pipe[1] = NULL;
rpcauth_destroy_credcache(auth);
- kref_put(&gss_auth->kref, gss_free_callback);
+ gss_put_auth(gss_auth);
}
/*
@@ -1253,7 +1266,7 @@
call_rcu(&cred->cr_rcu, gss_free_cred_callback);
if (ctx)
gss_put_ctx(ctx);
- kref_put(&gss_auth->kref, gss_free_callback);
+ gss_put_auth(gss_auth);
}
static void
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 890a299..e860d4f 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -64,7 +64,6 @@
free_page((unsigned long)xbufp->head[0].iov_base);
xbufp = &req->rq_snd_buf;
free_page((unsigned long)xbufp->head[0].iov_base);
- list_del(&req->rq_bc_pa_list);
kfree(req);
}
@@ -168,8 +167,10 @@
/*
* Memory allocation failed, free the temporary list
*/
- list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list)
+ list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) {
+ list_del(&req->rq_bc_pa_list);
xprt_free_allocation(req);
+ }
dprintk("RPC: setup backchannel transport failed\n");
return -ENOMEM;
@@ -198,6 +199,7 @@
xprt_dec_alloc_count(xprt, max_reqs);
list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) {
dprintk("RPC: req=%p\n", req);
+ list_del(&req->rq_bc_pa_list);
xprt_free_allocation(req);
if (--max_reqs == 0)
break;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 80a6640..06c6ff0 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -571,7 +571,7 @@
}
}
-int svc_alloc_arg(struct svc_rqst *rqstp)
+static int svc_alloc_arg(struct svc_rqst *rqstp)
{
struct svc_serv *serv = rqstp->rq_server;
struct xdr_buf *arg;
@@ -612,7 +612,7 @@
return 0;
}
-struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
+static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
{
struct svc_xprt *xprt;
struct svc_pool *pool = rqstp->rq_pool;
@@ -691,7 +691,7 @@
return xprt;
}
-void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt)
+static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt)
{
spin_lock_bh(&serv->sv_lock);
set_bit(XPT_TEMP, &newxpt->xpt_flags);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 817a1e5..0addefc 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -510,6 +510,7 @@
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = req->rq_xprt;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ struct sock *sk = transport->inet;
int ret = -EAGAIN;
dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
@@ -527,7 +528,7 @@
* window size
*/
set_bit(SOCK_NOSPACE, &transport->sock->flags);
- transport->inet->sk_write_pending++;
+ sk->sk_write_pending++;
/* ...and wait for more buffer space */
xprt_wait_for_buffer_space(task, xs_nospace_callback);
}
@@ -537,6 +538,9 @@
}
spin_unlock_bh(&xprt->transport_lock);
+
+ /* Race breaker in case memory is freed before above code is called */
+ sk->sk_write_space(sk);
return ret;
}
diff --git a/net/tipc/addr.h b/net/tipc/addr.h
index 60b00ab..a74acf9 100644
--- a/net/tipc/addr.h
+++ b/net/tipc/addr.h
@@ -37,6 +37,8 @@
#ifndef _TIPC_ADDR_H
#define _TIPC_ADDR_H
+#include "core.h"
+
#define TIPC_ZONE_MASK 0xff000000u
#define TIPC_CLUSTER_MASK 0xfffff000u
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index bf860d9..95ab5ef 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -41,9 +41,9 @@
#include "bcast.h"
#include "name_distr.h"
-#define MAX_PKT_DEFAULT_MCAST 1500 /* bcast link max packet size (fixed) */
-
-#define BCLINK_WIN_DEFAULT 20 /* bcast link window size (default) */
+#define MAX_PKT_DEFAULT_MCAST 1500 /* bcast link max packet size (fixed) */
+#define BCLINK_WIN_DEFAULT 20 /* bcast link window size (default) */
+#define BCBEARER MAX_BEARERS
/**
* struct tipc_bcbearer_pair - a pair of bearers used by broadcast link
@@ -356,9 +356,9 @@
}
/*
- * tipc_bclink_send_msg - broadcast a packet to all nodes in cluster
+ * tipc_bclink_xmit - broadcast a packet to all nodes in cluster
*/
-int tipc_bclink_send_msg(struct sk_buff *buf)
+int tipc_bclink_xmit(struct sk_buff *buf)
{
int res;
@@ -370,7 +370,7 @@
goto exit;
}
- res = tipc_link_send_buf(bcl, buf);
+ res = __tipc_link_xmit(bcl, buf);
if (likely(res >= 0)) {
bclink_set_last_sent();
bcl->stats.queue_sz_counts++;
@@ -399,19 +399,18 @@
*/
if (((seqno - tipc_own_addr) % TIPC_MIN_LINK_WIN) == 0) {
- tipc_link_send_proto_msg(
- node->active_links[node->addr & 1],
- STATE_MSG, 0, 0, 0, 0, 0);
+ tipc_link_proto_xmit(node->active_links[node->addr & 1],
+ STATE_MSG, 0, 0, 0, 0, 0);
bcl->stats.sent_acks++;
}
}
/**
- * tipc_bclink_recv_pkt - receive a broadcast packet, and deliver upwards
+ * tipc_bclink_rcv - receive a broadcast packet, and deliver upwards
*
* tipc_net_lock is read_locked, no other locks set
*/
-void tipc_bclink_recv_pkt(struct sk_buff *buf)
+void tipc_bclink_rcv(struct sk_buff *buf)
{
struct tipc_msg *msg = buf_msg(buf);
struct tipc_node *node;
@@ -468,7 +467,7 @@
spin_unlock_bh(&bc_lock);
tipc_node_unlock(node);
if (likely(msg_mcast(msg)))
- tipc_port_recv_mcast(buf, NULL);
+ tipc_port_mcast_rcv(buf, NULL);
else
kfree_skb(buf);
} else if (msg_user(msg) == MSG_BUNDLER) {
@@ -478,12 +477,12 @@
bcl->stats.recv_bundled += msg_msgcnt(msg);
spin_unlock_bh(&bc_lock);
tipc_node_unlock(node);
- tipc_link_recv_bundle(buf);
+ tipc_link_bundle_rcv(buf);
} else if (msg_user(msg) == MSG_FRAGMENTER) {
int ret;
- ret = tipc_link_recv_fragment(&node->bclink.reasm_head,
- &node->bclink.reasm_tail,
- &buf);
+ ret = tipc_link_frag_rcv(&node->bclink.reasm_head,
+ &node->bclink.reasm_tail,
+ &buf);
if (ret == LINK_REASM_ERROR)
goto unlock;
spin_lock_bh(&bc_lock);
@@ -503,7 +502,7 @@
bclink_accept_pkt(node, seqno);
spin_unlock_bh(&bc_lock);
tipc_node_unlock(node);
- tipc_named_recv(buf);
+ tipc_named_rcv(buf);
} else {
spin_lock_bh(&bc_lock);
bclink_accept_pkt(node, seqno);
@@ -669,9 +668,8 @@
memset(bp_temp, 0, sizeof(bcbearer->bpairs_temp));
for (b_index = 0; b_index < MAX_BEARERS; b_index++) {
- struct tipc_bearer *b = &tipc_bearers[b_index];
-
- if (!b->active || !b->nodes.count)
+ struct tipc_bearer *b = bearer_list[b_index];
+ if (!b || !b->nodes.count)
continue;
if (!bp_temp[b->priority].primary)
@@ -785,8 +783,8 @@
bcl->owner = &bclink->node;
bcl->max_pkt = MAX_PKT_DEFAULT_MCAST;
tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT);
- spin_lock_init(&bcbearer->bearer.lock);
bcl->b_ptr = &bcbearer->bearer;
+ bearer_list[BCBEARER] = &bcbearer->bearer;
bcl->state = WORKING_WORKING;
strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME);
}
@@ -797,6 +795,7 @@
tipc_link_purge_queues(bcl);
spin_unlock_bh(&bc_lock);
+ bearer_list[BCBEARER] = NULL;
memset(bclink, 0, sizeof(*bclink));
memset(bcbearer, 0, sizeof(*bcbearer));
}
diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h
index 6ee587b..a80ef54 100644
--- a/net/tipc/bcast.h
+++ b/net/tipc/bcast.h
@@ -90,8 +90,8 @@
void tipc_bclink_remove_node(u32 addr);
struct tipc_node *tipc_bclink_retransmit_to(void);
void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked);
-int tipc_bclink_send_msg(struct sk_buff *buf);
-void tipc_bclink_recv_pkt(struct sk_buff *buf);
+int tipc_bclink_xmit(struct sk_buff *buf);
+void tipc_bclink_rcv(struct sk_buff *buf);
u32 tipc_bclink_get_last_sent(void);
u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr);
void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent);
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index a38c899..3fef7eb 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -49,9 +49,9 @@
NULL
};
-struct tipc_bearer tipc_bearers[MAX_BEARERS];
+struct tipc_bearer *bearer_list[MAX_BEARERS + 1];
-static void bearer_disable(struct tipc_bearer *b_ptr);
+static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down);
/**
* tipc_media_find - locates specified media object by name
@@ -177,8 +177,9 @@
struct tipc_bearer *b_ptr;
u32 i;
- for (i = 0, b_ptr = tipc_bearers; i < MAX_BEARERS; i++, b_ptr++) {
- if (b_ptr->active && (!strcmp(b_ptr->name, name)))
+ for (i = 0; i < MAX_BEARERS; i++) {
+ b_ptr = bearer_list[i];
+ if (b_ptr && (!strcmp(b_ptr->name, name)))
return b_ptr;
}
return NULL;
@@ -200,8 +201,10 @@
read_lock_bh(&tipc_net_lock);
for (i = 0; media_info_array[i] != NULL; i++) {
for (j = 0; j < MAX_BEARERS; j++) {
- b = &tipc_bearers[j];
- if (b->active && (b->media == media_info_array[i])) {
+ b = bearer_list[j];
+ if (!b)
+ continue;
+ if (b->media == media_info_array[i]) {
tipc_cfg_append_tlv(buf, TIPC_TLV_BEARER_NAME,
b->name,
strlen(b->name) + 1);
@@ -284,16 +287,17 @@
bearer_id = MAX_BEARERS;
with_this_prio = 1;
for (i = MAX_BEARERS; i-- != 0; ) {
- if (!tipc_bearers[i].active) {
+ b_ptr = bearer_list[i];
+ if (!b_ptr) {
bearer_id = i;
continue;
}
- if (!strcmp(name, tipc_bearers[i].name)) {
+ if (!strcmp(name, b_ptr->name)) {
pr_warn("Bearer <%s> rejected, already enabled\n",
name);
goto exit;
}
- if ((tipc_bearers[i].priority == priority) &&
+ if ((b_ptr->priority == priority) &&
(++with_this_prio > 2)) {
if (priority-- == 0) {
pr_warn("Bearer <%s> rejected, duplicate priority\n",
@@ -311,7 +315,11 @@
goto exit;
}
- b_ptr = &tipc_bearers[bearer_id];
+ b_ptr = kzalloc(sizeof(*b_ptr), GFP_ATOMIC);
+ if (!b_ptr) {
+ res = -ENOMEM;
+ goto exit;
+ }
strcpy(b_ptr->name, name);
b_ptr->media = m_ptr;
res = m_ptr->enable_media(b_ptr);
@@ -324,19 +332,20 @@
b_ptr->identity = bearer_id;
b_ptr->tolerance = m_ptr->tolerance;
b_ptr->window = m_ptr->window;
+ b_ptr->domain = disc_domain;
b_ptr->net_plane = bearer_id + 'A';
- b_ptr->active = 1;
b_ptr->priority = priority;
- INIT_LIST_HEAD(&b_ptr->links);
- spin_lock_init(&b_ptr->lock);
- res = tipc_disc_create(b_ptr, &b_ptr->bcast_addr, disc_domain);
+ res = tipc_disc_create(b_ptr, &b_ptr->bcast_addr);
if (res) {
- bearer_disable(b_ptr);
+ bearer_disable(b_ptr, false);
pr_warn("Bearer <%s> rejected, discovery object creation failed\n",
name);
goto exit;
}
+
+ bearer_list[bearer_id] = b_ptr;
+
pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n",
name,
tipc_addr_string_fill(addr_string, disc_domain), priority);
@@ -350,20 +359,11 @@
*/
static int tipc_reset_bearer(struct tipc_bearer *b_ptr)
{
- struct tipc_link *l_ptr;
- struct tipc_link *temp_l_ptr;
-
read_lock_bh(&tipc_net_lock);
pr_info("Resetting bearer <%s>\n", b_ptr->name);
- spin_lock_bh(&b_ptr->lock);
- list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) {
- struct tipc_node *n_ptr = l_ptr->owner;
-
- spin_lock_bh(&n_ptr->lock);
- tipc_link_reset(l_ptr);
- spin_unlock_bh(&n_ptr->lock);
- }
- spin_unlock_bh(&b_ptr->lock);
+ tipc_disc_delete(b_ptr->link_req);
+ tipc_link_reset_list(b_ptr->identity);
+ tipc_disc_create(b_ptr, &b_ptr->bcast_addr);
read_unlock_bh(&tipc_net_lock);
return 0;
}
@@ -373,26 +373,24 @@
*
* Note: This routine assumes caller holds tipc_net_lock.
*/
-static void bearer_disable(struct tipc_bearer *b_ptr)
+static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down)
{
- struct tipc_link *l_ptr;
- struct tipc_link *temp_l_ptr;
- struct tipc_link_req *temp_req;
+ u32 i;
pr_info("Disabling bearer <%s>\n", b_ptr->name);
- spin_lock_bh(&b_ptr->lock);
b_ptr->media->disable_media(b_ptr);
- list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) {
- tipc_link_delete(l_ptr);
+
+ tipc_link_delete_list(b_ptr->identity, shutting_down);
+ if (b_ptr->link_req)
+ tipc_disc_delete(b_ptr->link_req);
+
+ for (i = 0; i < MAX_BEARERS; i++) {
+ if (b_ptr == bearer_list[i]) {
+ bearer_list[i] = NULL;
+ break;
+ }
}
- temp_req = b_ptr->link_req;
- b_ptr->link_req = NULL;
- spin_unlock_bh(&b_ptr->lock);
-
- if (temp_req)
- tipc_disc_delete(temp_req);
-
- memset(b_ptr, 0, sizeof(struct tipc_bearer));
+ kfree(b_ptr);
}
int tipc_disable_bearer(const char *name)
@@ -406,7 +404,7 @@
pr_warn("Attempt to disable unknown bearer <%s>\n", name);
res = -EINVAL;
} else {
- bearer_disable(b_ptr);
+ bearer_disable(b_ptr, false);
res = 0;
}
write_unlock_bh(&tipc_net_lock);
@@ -585,7 +583,11 @@
break;
case NETDEV_DOWN:
case NETDEV_CHANGEMTU:
+ tipc_reset_bearer(b_ptr);
+ break;
case NETDEV_CHANGEADDR:
+ tipc_l2_media_addr_set(b_ptr, &b_ptr->addr,
+ (char *)dev->dev_addr);
tipc_reset_bearer(b_ptr);
break;
case NETDEV_UNREGISTER:
@@ -599,7 +601,7 @@
}
static struct packet_type tipc_packet_type __read_mostly = {
- .type = __constant_htons(ETH_P_TIPC),
+ .type = htons(ETH_P_TIPC),
.func = tipc_l2_rcv_msg,
};
@@ -610,8 +612,13 @@
int tipc_bearer_setup(void)
{
+ int err;
+
+ err = register_netdevice_notifier(¬ifier);
+ if (err)
+ return err;
dev_add_pack(&tipc_packet_type);
- return register_netdevice_notifier(¬ifier);
+ return 0;
}
void tipc_bearer_cleanup(void)
@@ -622,10 +629,14 @@
void tipc_bearer_stop(void)
{
+ struct tipc_bearer *b_ptr;
u32 i;
for (i = 0; i < MAX_BEARERS; i++) {
- if (tipc_bearers[i].active)
- bearer_disable(&tipc_bearers[i]);
+ b_ptr = bearer_list[i];
+ if (b_ptr) {
+ bearer_disable(b_ptr, true);
+ bearer_list[i] = NULL;
+ }
}
}
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index 4f5db9a..ba48145 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -107,10 +107,8 @@
/**
* struct tipc_bearer - Generic TIPC bearer structure
- * @dev: ptr to associated network device
- * @usr_handle: pointer to additional media-specific information about bearer
+ * @media_ptr: pointer to additional media-specific information about bearer
* @mtu: max packet size bearer can support
- * @lock: spinlock for controlling access to bearer
* @addr: media-specific address associated with bearer
* @name: bearer name (format = media:interface)
* @media: ptr to media structure associated with bearer
@@ -118,10 +116,9 @@
* @priority: default link priority for bearer
* @window: default window size for bearer
* @tolerance: default link tolerance for bearer
+ * @domain: network domain to which links can be established
* @identity: array index of this bearer within TIPC bearer array
* @link_req: ptr to (optional) structure making periodic link setup requests
- * @links: list of non-congested links associated with bearer
- * @active: non-zero if bearer structure is represents a bearer
* @net_plane: network plane ('A' through 'H') currently associated with bearer
* @nodes: indicates which nodes in cluster can be reached through bearer
*
@@ -134,16 +131,14 @@
u32 mtu; /* initalized by media */
struct tipc_media_addr addr; /* initalized by media */
char name[TIPC_MAX_BEARER_NAME];
- spinlock_t lock;
struct tipc_media *media;
struct tipc_media_addr bcast_addr;
u32 priority;
u32 window;
u32 tolerance;
+ u32 domain;
u32 identity;
struct tipc_link_req *link_req;
- struct list_head links;
- int active;
char net_plane;
struct tipc_node_map nodes;
};
@@ -155,7 +150,7 @@
struct tipc_link;
-extern struct tipc_bearer tipc_bearers[];
+extern struct tipc_bearer *bearer_list[];
/*
* TIPC routines available to supported media types
diff --git a/net/tipc/config.c b/net/tipc/config.c
index c301a9a..4b981c0 100644
--- a/net/tipc/config.c
+++ b/net/tipc/config.c
@@ -43,13 +43,11 @@
#define REPLY_TRUNCATED "<truncated>\n"
static DEFINE_MUTEX(config_mutex);
-static struct tipc_server cfgsrv;
static const void *req_tlv_area; /* request message TLV area */
static int req_tlv_space; /* request message TLV area size */
static int rep_headroom; /* reply message headroom to use */
-
struct sk_buff *tipc_cfg_reply_alloc(int payload_size)
{
struct sk_buff *buf;
@@ -181,19 +179,7 @@
if (tipc_own_addr)
return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
" (cannot change node address once assigned)");
- tipc_core_start_net(addr);
- return tipc_cfg_reply_none();
-}
-
-static struct sk_buff *cfg_set_remote_mng(void)
-{
- u32 value;
-
- if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED))
- return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-
- value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area));
- tipc_remote_management = (value != 0);
+ tipc_net_start(addr);
return tipc_cfg_reply_none();
}
@@ -247,21 +233,10 @@
/* Check command authorization */
if (likely(in_own_node(orig_node))) {
/* command is permitted */
- } else if (cmd >= 0x8000) {
+ } else {
rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
" (cannot be done remotely)");
goto exit;
- } else if (!tipc_remote_management) {
- rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NO_REMOTE);
- goto exit;
- } else if (cmd >= 0x4000) {
- u32 domain = 0;
-
- if ((tipc_nametbl_translate(TIPC_ZM_SRV, 0, &domain) == 0) ||
- (domain != orig_node)) {
- rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_ZONE_MSTR);
- goto exit;
- }
}
/* Call appropriate processing routine */
@@ -310,18 +285,12 @@
case TIPC_CMD_SET_NODE_ADDR:
rep_tlv_buf = cfg_set_own_addr();
break;
- case TIPC_CMD_SET_REMOTE_MNG:
- rep_tlv_buf = cfg_set_remote_mng();
- break;
case TIPC_CMD_SET_MAX_PORTS:
rep_tlv_buf = cfg_set_max_ports();
break;
case TIPC_CMD_SET_NETID:
rep_tlv_buf = cfg_set_netid();
break;
- case TIPC_CMD_GET_REMOTE_MNG:
- rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_remote_management);
- break;
case TIPC_CMD_GET_MAX_PORTS:
rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_ports);
break;
@@ -345,6 +314,8 @@
case TIPC_CMD_SET_MAX_PUBL:
case TIPC_CMD_GET_MAX_PUBL:
case TIPC_CMD_SET_LOG_SIZE:
+ case TIPC_CMD_SET_REMOTE_MNG:
+ case TIPC_CMD_GET_REMOTE_MNG:
case TIPC_CMD_DUMP_LOG:
rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
" (obsolete command)");
@@ -369,80 +340,3 @@
mutex_unlock(&config_mutex);
return rep_tlv_buf;
}
-
-static void cfg_conn_msg_event(int conid, struct sockaddr_tipc *addr,
- void *usr_data, void *buf, size_t len)
-{
- struct tipc_cfg_msg_hdr *req_hdr;
- struct tipc_cfg_msg_hdr *rep_hdr;
- struct sk_buff *rep_buf;
- int ret;
-
- /* Validate configuration message header (ignore invalid message) */
- req_hdr = (struct tipc_cfg_msg_hdr *)buf;
- if ((len < sizeof(*req_hdr)) ||
- (len != TCM_ALIGN(ntohl(req_hdr->tcm_len))) ||
- (ntohs(req_hdr->tcm_flags) != TCM_F_REQUEST)) {
- pr_warn("Invalid configuration message discarded\n");
- return;
- }
-
- /* Generate reply for request (if can't, return request) */
- rep_buf = tipc_cfg_do_cmd(addr->addr.id.node, ntohs(req_hdr->tcm_type),
- buf + sizeof(*req_hdr),
- len - sizeof(*req_hdr),
- BUF_HEADROOM + MAX_H_SIZE + sizeof(*rep_hdr));
- if (rep_buf) {
- skb_push(rep_buf, sizeof(*rep_hdr));
- rep_hdr = (struct tipc_cfg_msg_hdr *)rep_buf->data;
- memcpy(rep_hdr, req_hdr, sizeof(*rep_hdr));
- rep_hdr->tcm_len = htonl(rep_buf->len);
- rep_hdr->tcm_flags &= htons(~TCM_F_REQUEST);
-
- ret = tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data,
- rep_buf->len);
- if (ret < 0)
- pr_err("Sending cfg reply message failed, no memory\n");
-
- kfree_skb(rep_buf);
- }
-}
-
-static struct sockaddr_tipc cfgsrv_addr __read_mostly = {
- .family = AF_TIPC,
- .addrtype = TIPC_ADDR_NAMESEQ,
- .addr.nameseq.type = TIPC_CFG_SRV,
- .addr.nameseq.lower = 0,
- .addr.nameseq.upper = 0,
- .scope = TIPC_ZONE_SCOPE
-};
-
-static struct tipc_server cfgsrv __read_mostly = {
- .saddr = &cfgsrv_addr,
- .imp = TIPC_CRITICAL_IMPORTANCE,
- .type = SOCK_RDM,
- .max_rcvbuf_size = 64 * 1024,
- .name = "cfg_server",
- .tipc_conn_recvmsg = cfg_conn_msg_event,
- .tipc_conn_new = NULL,
- .tipc_conn_shutdown = NULL
-};
-
-int tipc_cfg_init(void)
-{
- return tipc_server_start(&cfgsrv);
-}
-
-void tipc_cfg_reinit(void)
-{
- tipc_server_stop(&cfgsrv);
-
- cfgsrv_addr.addr.nameseq.lower = tipc_own_addr;
- cfgsrv_addr.addr.nameseq.upper = tipc_own_addr;
- tipc_server_start(&cfgsrv);
-}
-
-void tipc_cfg_stop(void)
-{
- tipc_server_stop(&cfgsrv);
-}
diff --git a/net/tipc/config.h b/net/tipc/config.h
index 1f252f3..47b1bf1 100644
--- a/net/tipc/config.h
+++ b/net/tipc/config.h
@@ -64,9 +64,4 @@
struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd,
const void *req_tlv_area, int req_tlv_space,
int headroom);
-
-int tipc_cfg_init(void);
-void tipc_cfg_reinit(void);
-void tipc_cfg_stop(void);
-
#endif
diff --git a/net/tipc/core.c b/net/tipc/core.c
index f9e88d8..50d5742 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -1,7 +1,7 @@
/*
* net/tipc/core.c: TIPC module code
*
- * Copyright (c) 2003-2006, Ericsson AB
+ * Copyright (c) 2003-2006, 2013, Ericsson AB
* Copyright (c) 2005-2006, 2010-2013, Wind River Systems
* All rights reserved.
*
@@ -50,7 +50,6 @@
u32 tipc_own_addr __read_mostly;
int tipc_max_ports __read_mostly;
int tipc_net_id __read_mostly;
-int tipc_remote_management __read_mostly;
int sysctl_tipc_rmem[3] __read_mostly; /* min/default/max */
/**
@@ -77,39 +76,14 @@
}
/**
- * tipc_core_stop_net - shut down TIPC networking sub-systems
- */
-static void tipc_core_stop_net(void)
-{
- tipc_net_stop();
- tipc_bearer_cleanup();
-}
-
-/**
- * start_net - start TIPC networking sub-systems
- */
-int tipc_core_start_net(unsigned long addr)
-{
- int res;
-
- tipc_net_start(addr);
- res = tipc_bearer_setup();
- if (res < 0)
- goto err;
- return res;
-
-err:
- tipc_core_stop_net();
- return res;
-}
-
-/**
* tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode
*/
static void tipc_core_stop(void)
{
+ tipc_handler_stop();
+ tipc_net_stop();
+ tipc_bearer_cleanup();
tipc_netlink_stop();
- tipc_cfg_stop();
tipc_subscr_stop();
tipc_nametbl_stop();
tipc_ref_table_stop();
@@ -122,30 +96,59 @@
*/
static int tipc_core_start(void)
{
- int res;
+ int err;
get_random_bytes(&tipc_random, sizeof(tipc_random));
- res = tipc_handler_start();
- if (!res)
- res = tipc_ref_table_init(tipc_max_ports, tipc_random);
- if (!res)
- res = tipc_nametbl_init();
- if (!res)
- res = tipc_netlink_start();
- if (!res)
- res = tipc_socket_init();
- if (!res)
- res = tipc_register_sysctl();
- if (!res)
- res = tipc_subscr_start();
- if (!res)
- res = tipc_cfg_init();
- if (res) {
- tipc_handler_stop();
- tipc_core_stop();
- }
- return res;
+ err = tipc_handler_start();
+ if (err)
+ goto out_handler;
+
+ err = tipc_ref_table_init(tipc_max_ports, tipc_random);
+ if (err)
+ goto out_reftbl;
+
+ err = tipc_nametbl_init();
+ if (err)
+ goto out_nametbl;
+
+ err = tipc_netlink_start();
+ if (err)
+ goto out_netlink;
+
+ err = tipc_socket_init();
+ if (err)
+ goto out_socket;
+
+ err = tipc_register_sysctl();
+ if (err)
+ goto out_sysctl;
+
+ err = tipc_subscr_start();
+ if (err)
+ goto out_subscr;
+
+ err = tipc_bearer_setup();
+ if (err)
+ goto out_bearer;
+
+ return 0;
+out_bearer:
+ tipc_subscr_stop();
+out_subscr:
+ tipc_unregister_sysctl();
+out_sysctl:
+ tipc_socket_stop();
+out_socket:
+ tipc_netlink_stop();
+out_netlink:
+ tipc_nametbl_stop();
+out_nametbl:
+ tipc_ref_table_stop();
+out_reftbl:
+ tipc_handler_stop();
+out_handler:
+ return err;
}
static int __init tipc_init(void)
@@ -155,7 +158,6 @@
pr_info("Activated (version " TIPC_MOD_VER ")\n");
tipc_own_addr = 0;
- tipc_remote_management = 1;
tipc_max_ports = CONFIG_TIPC_PORTS;
tipc_net_id = 4711;
@@ -174,8 +176,6 @@
static void __exit tipc_exit(void)
{
- tipc_handler_stop();
- tipc_core_stop_net();
tipc_core_stop();
pr_info("Deactivated\n");
}
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 1ff477b..8985bbc 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -79,7 +79,6 @@
extern u32 tipc_own_addr __read_mostly;
extern int tipc_max_ports __read_mostly;
extern int tipc_net_id __read_mostly;
-extern int tipc_remote_management __read_mostly;
extern int sysctl_tipc_rmem[3] __read_mostly;
/*
@@ -90,7 +89,6 @@
/*
* Routines available to privileged subsystems
*/
-int tipc_core_start_net(unsigned long);
int tipc_handler_start(void);
void tipc_handler_stop(void);
int tipc_netlink_start(void);
@@ -192,6 +190,7 @@
struct tipc_skb_cb {
void *handle;
+ bool deferred;
};
#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 412ff41..542fe34 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -48,7 +48,6 @@
* struct tipc_link_req - information about an ongoing link setup request
* @bearer: bearer issuing requests
* @dest: destination address for request messages
- * @domain: network domain to which links can be established
* @num_nodes: number of nodes currently discovered (i.e. with an active link)
* @lock: spinlock for controlling access to requests
* @buf: request message to be (repeatedly) sent
@@ -58,7 +57,6 @@
struct tipc_link_req {
struct tipc_bearer *bearer;
struct tipc_media_addr dest;
- u32 domain;
int num_nodes;
spinlock_t lock;
struct sk_buff *buf;
@@ -69,14 +67,13 @@
/**
* tipc_disc_init_msg - initialize a link setup message
* @type: message type (request or response)
- * @dest_domain: network domain of node(s) which should respond to message
* @b_ptr: ptr to bearer issuing message
*/
-static struct sk_buff *tipc_disc_init_msg(u32 type, u32 dest_domain,
- struct tipc_bearer *b_ptr)
+static struct sk_buff *tipc_disc_init_msg(u32 type, struct tipc_bearer *b_ptr)
{
struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE);
struct tipc_msg *msg;
+ u32 dest_domain = b_ptr->domain;
if (buf) {
msg = buf_msg(buf);
@@ -110,11 +107,11 @@
}
/**
- * tipc_disc_recv_msg - handle incoming link setup message (request or response)
+ * tipc_disc_rcv - handle incoming link setup message (request or response)
* @buf: buffer containing message
* @b_ptr: bearer that message arrived on
*/
-void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr)
+void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *b_ptr)
{
struct tipc_node *n_ptr;
struct tipc_link *link;
@@ -149,7 +146,7 @@
}
if (!tipc_in_scope(dest, tipc_own_addr))
return;
- if (!tipc_in_scope(b_ptr->link_req->domain, orig))
+ if (!tipc_in_scope(b_ptr->domain, orig))
return;
/* Locate structure corresponding to requesting node */
@@ -242,7 +239,7 @@
link_fully_up = link_working_working(link);
if ((type == DSC_REQ_MSG) && !link_fully_up) {
- rbuf = tipc_disc_init_msg(DSC_RESP_MSG, orig, b_ptr);
+ rbuf = tipc_disc_init_msg(DSC_RESP_MSG, b_ptr);
if (rbuf) {
tipc_bearer_send(b_ptr, rbuf, &media_addr);
kfree_skb(rbuf);
@@ -306,7 +303,7 @@
spin_lock_bh(&req->lock);
/* Stop searching if only desired node has been found */
- if (tipc_node(req->domain) && req->num_nodes) {
+ if (tipc_node(req->bearer->domain) && req->num_nodes) {
req->timer_intv = TIPC_LINK_REQ_INACTIVE;
goto exit;
}
@@ -342,8 +339,7 @@
*
* Returns 0 if successful, otherwise -errno.
*/
-int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest,
- u32 dest_domain)
+int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest)
{
struct tipc_link_req *req;
@@ -351,7 +347,7 @@
if (!req)
return -ENOMEM;
- req->buf = tipc_disc_init_msg(DSC_REQ_MSG, dest_domain, b_ptr);
+ req->buf = tipc_disc_init_msg(DSC_REQ_MSG, b_ptr);
if (!req->buf) {
kfree(req);
return -ENOMSG;
@@ -359,7 +355,6 @@
memcpy(&req->dest, dest, sizeof(*dest));
req->bearer = b_ptr;
- req->domain = dest_domain;
req->num_nodes = 0;
req->timer_intv = TIPC_LINK_REQ_INIT;
spin_lock_init(&req->lock);
diff --git a/net/tipc/discover.h b/net/tipc/discover.h
index 75b67c4..07f3472 100644
--- a/net/tipc/discover.h
+++ b/net/tipc/discover.h
@@ -39,11 +39,10 @@
struct tipc_link_req;
-int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest,
- u32 dest_domain);
+int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest);
void tipc_disc_delete(struct tipc_link_req *req);
void tipc_disc_add_dest(struct tipc_link_req *req);
void tipc_disc_remove_dest(struct tipc_link_req *req);
-void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr);
+void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *b_ptr);
#endif
diff --git a/net/tipc/handler.c b/net/tipc/handler.c
index e4bc8a2..1fabf16 100644
--- a/net/tipc/handler.c
+++ b/net/tipc/handler.c
@@ -58,7 +58,6 @@
spin_lock_bh(&qitem_lock);
if (!handler_enabled) {
- pr_err("Signal request ignored by handler\n");
spin_unlock_bh(&qitem_lock);
return -ENOPROTOOPT;
}
diff --git a/net/tipc/link.c b/net/tipc/link.c
index d4b5de4..c5190ab 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -77,19 +77,19 @@
static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr,
struct sk_buff *buf);
-static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf);
-static int tipc_link_tunnel_rcv(struct tipc_link **l_ptr,
+static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf);
+static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr,
struct sk_buff **buf);
static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance);
-static int link_send_sections_long(struct tipc_port *sender,
- struct iovec const *msg_sect,
- unsigned int len, u32 destnode);
+static int tipc_link_iovec_long_xmit(struct tipc_port *sender,
+ struct iovec const *msg_sect,
+ unsigned int len, u32 destnode);
static void link_state_event(struct tipc_link *l_ptr, u32 event);
static void link_reset_statistics(struct tipc_link *l_ptr);
static void link_print(struct tipc_link *l_ptr, const char *str);
-static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf);
-static void tipc_link_send_sync(struct tipc_link *l);
-static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf);
+static int tipc_link_frag_xmit(struct tipc_link *l_ptr, struct sk_buff *buf);
+static void tipc_link_sync_xmit(struct tipc_link *l);
+static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf);
/*
* Simple link routines
@@ -147,11 +147,6 @@
/**
* link_timeout - handle expiration of link timer
* @l_ptr: pointer to link
- *
- * This routine must not grab "tipc_net_lock" to avoid a potential deadlock conflict
- * with tipc_link_delete(). (There is no risk that the node will be deleted by
- * another thread because tipc_link_delete() always cancels the link timer before
- * tipc_node_delete() is called.)
*/
static void link_timeout(struct tipc_link *l_ptr)
{
@@ -213,8 +208,8 @@
* Returns pointer to link.
*/
struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
- struct tipc_bearer *b_ptr,
- const struct tipc_media_addr *media_addr)
+ struct tipc_bearer *b_ptr,
+ const struct tipc_media_addr *media_addr)
{
struct tipc_link *l_ptr;
struct tipc_msg *msg;
@@ -279,41 +274,44 @@
k_init_timer(&l_ptr->timer, (Handler)link_timeout,
(unsigned long)l_ptr);
- list_add_tail(&l_ptr->link_list, &b_ptr->links);
link_state_event(l_ptr, STARTING_EVT);
return l_ptr;
}
-/**
- * tipc_link_delete - delete a link
- * @l_ptr: pointer to link
- *
- * Note: 'tipc_net_lock' is write_locked, bearer is locked.
- * This routine must not grab the node lock until after link timer cancellation
- * to avoid a potential deadlock situation.
- */
-void tipc_link_delete(struct tipc_link *l_ptr)
+void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down)
{
- if (!l_ptr) {
- pr_err("Attempt to delete non-existent link\n");
- return;
+ struct tipc_link *l_ptr;
+ struct tipc_node *n_ptr;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
+ spin_lock_bh(&n_ptr->lock);
+ l_ptr = n_ptr->links[bearer_id];
+ if (l_ptr) {
+ tipc_link_reset(l_ptr);
+ if (shutting_down || !tipc_node_is_up(n_ptr)) {
+ tipc_node_detach_link(l_ptr->owner, l_ptr);
+ tipc_link_reset_fragments(l_ptr);
+ spin_unlock_bh(&n_ptr->lock);
+
+ /* Nobody else can access this link now: */
+ del_timer_sync(&l_ptr->timer);
+ kfree(l_ptr);
+ } else {
+ /* Detach/delete when failover is finished: */
+ l_ptr->flags |= LINK_STOPPED;
+ spin_unlock_bh(&n_ptr->lock);
+ del_timer_sync(&l_ptr->timer);
+ }
+ continue;
+ }
+ spin_unlock_bh(&n_ptr->lock);
}
-
- k_cancel_timer(&l_ptr->timer);
-
- tipc_node_lock(l_ptr->owner);
- tipc_link_reset(l_ptr);
- tipc_node_detach_link(l_ptr->owner, l_ptr);
- tipc_link_purge_queues(l_ptr);
- list_del_init(&l_ptr->link_list);
- tipc_node_unlock(l_ptr->owner);
- k_term_timer(&l_ptr->timer);
- kfree(l_ptr);
+ rcu_read_unlock();
}
-
/**
* link_schedule_port - schedule port for deferred sending
* @l_ptr: pointer to link
@@ -330,8 +328,6 @@
spin_lock_bh(&tipc_port_list_lock);
p_ptr = tipc_port_lock(origport);
if (p_ptr) {
- if (!p_ptr->wakeup)
- goto exit;
if (!list_empty(&p_ptr->wait_list))
goto exit;
p_ptr->congested = 1;
@@ -366,7 +362,7 @@
list_del_init(&p_ptr->wait_list);
spin_lock_bh(p_ptr->lock);
p_ptr->congested = 0;
- p_ptr->wakeup(p_ptr);
+ tipc_port_wakeup(p_ptr);
win -= p_ptr->waiting_pkts;
spin_unlock_bh(p_ptr->lock);
}
@@ -461,6 +457,21 @@
link_reset_statistics(l_ptr);
}
+void tipc_link_reset_list(unsigned int bearer_id)
+{
+ struct tipc_link *l_ptr;
+ struct tipc_node *n_ptr;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
+ spin_lock_bh(&n_ptr->lock);
+ l_ptr = n_ptr->links[bearer_id];
+ if (l_ptr)
+ tipc_link_reset(l_ptr);
+ spin_unlock_bh(&n_ptr->lock);
+ }
+ rcu_read_unlock();
+}
static void link_activate(struct tipc_link *l_ptr)
{
@@ -479,7 +490,10 @@
struct tipc_link *other;
u32 cont_intv = l_ptr->continuity_interval;
- if (!l_ptr->started && (event != STARTING_EVT))
+ if (l_ptr->flags & LINK_STOPPED)
+ return;
+
+ if (!(l_ptr->flags & LINK_STARTED) && (event != STARTING_EVT))
return; /* Not yet. */
/* Check whether changeover is going on */
@@ -499,12 +513,12 @@
if (l_ptr->next_in_no != l_ptr->checkpoint) {
l_ptr->checkpoint = l_ptr->next_in_no;
if (tipc_bclink_acks_missing(l_ptr->owner)) {
- tipc_link_send_proto_msg(l_ptr, STATE_MSG,
- 0, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, STATE_MSG,
+ 0, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
} else if (l_ptr->max_pkt < l_ptr->max_pkt_target) {
- tipc_link_send_proto_msg(l_ptr, STATE_MSG,
- 1, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, STATE_MSG,
+ 1, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
}
link_set_timer(l_ptr, cont_intv);
@@ -512,7 +526,7 @@
}
l_ptr->state = WORKING_UNKNOWN;
l_ptr->fsm_msg_cnt = 0;
- tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
link_set_timer(l_ptr, cont_intv / 4);
break;
@@ -522,7 +536,8 @@
tipc_link_reset(l_ptr);
l_ptr->state = RESET_RESET;
l_ptr->fsm_msg_cnt = 0;
- tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG,
+ 0, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
link_set_timer(l_ptr, cont_intv);
break;
@@ -544,7 +559,8 @@
tipc_link_reset(l_ptr);
l_ptr->state = RESET_RESET;
l_ptr->fsm_msg_cnt = 0;
- tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG,
+ 0, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
link_set_timer(l_ptr, cont_intv);
break;
@@ -554,14 +570,14 @@
l_ptr->fsm_msg_cnt = 0;
l_ptr->checkpoint = l_ptr->next_in_no;
if (tipc_bclink_acks_missing(l_ptr->owner)) {
- tipc_link_send_proto_msg(l_ptr, STATE_MSG,
- 0, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, STATE_MSG,
+ 0, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
}
link_set_timer(l_ptr, cont_intv);
} else if (l_ptr->fsm_msg_cnt < l_ptr->abort_limit) {
- tipc_link_send_proto_msg(l_ptr, STATE_MSG,
- 1, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, STATE_MSG,
+ 1, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
link_set_timer(l_ptr, cont_intv / 4);
} else { /* Link has failed */
@@ -570,8 +586,8 @@
tipc_link_reset(l_ptr);
l_ptr->state = RESET_UNKNOWN;
l_ptr->fsm_msg_cnt = 0;
- tipc_link_send_proto_msg(l_ptr, RESET_MSG,
- 0, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, RESET_MSG,
+ 0, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
link_set_timer(l_ptr, cont_intv);
}
@@ -591,24 +607,25 @@
l_ptr->state = WORKING_WORKING;
l_ptr->fsm_msg_cnt = 0;
link_activate(l_ptr);
- tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
if (l_ptr->owner->working_links == 1)
- tipc_link_send_sync(l_ptr);
+ tipc_link_sync_xmit(l_ptr);
link_set_timer(l_ptr, cont_intv);
break;
case RESET_MSG:
l_ptr->state = RESET_RESET;
l_ptr->fsm_msg_cnt = 0;
- tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 1, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG,
+ 1, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
link_set_timer(l_ptr, cont_intv);
break;
case STARTING_EVT:
- l_ptr->started = 1;
+ l_ptr->flags |= LINK_STARTED;
/* fall through */
case TIMEOUT_EVT:
- tipc_link_send_proto_msg(l_ptr, RESET_MSG, 0, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
link_set_timer(l_ptr, cont_intv);
break;
@@ -626,16 +643,17 @@
l_ptr->state = WORKING_WORKING;
l_ptr->fsm_msg_cnt = 0;
link_activate(l_ptr);
- tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
if (l_ptr->owner->working_links == 1)
- tipc_link_send_sync(l_ptr);
+ tipc_link_sync_xmit(l_ptr);
link_set_timer(l_ptr, cont_intv);
break;
case RESET_MSG:
break;
case TIMEOUT_EVT:
- tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG,
+ 0, 0, 0, 0, 0);
l_ptr->fsm_msg_cnt++;
link_set_timer(l_ptr, cont_intv);
break;
@@ -721,11 +739,11 @@
}
/*
- * tipc_link_send_buf() is the 'full path' for messages, called from
- * inside TIPC when the 'fast path' in tipc_send_buf
+ * tipc_link_xmit() is the 'full path' for messages, called from
+ * inside TIPC when the 'fast path' in tipc_send_xmit
* has failed, and from link_send()
*/
-int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf)
+int __tipc_link_xmit(struct tipc_link *l_ptr, struct sk_buff *buf)
{
struct tipc_msg *msg = buf_msg(buf);
u32 size = msg_size(msg);
@@ -753,7 +771,7 @@
/* Fragmentation needed ? */
if (size > max_packet)
- return link_send_long_buf(l_ptr, buf);
+ return tipc_link_frag_xmit(l_ptr, buf);
/* Packet can be queued or sent. */
if (likely(!link_congested(l_ptr))) {
@@ -797,11 +815,11 @@
}
/*
- * tipc_link_send(): same as tipc_link_send_buf(), but the link to use has
- * not been selected yet, and the the owner node is not locked
+ * tipc_link_xmit(): same as __tipc_link_xmit(), but the link to use
+ * has not been selected yet, and the the owner node is not locked
* Called by TIPC internal users, e.g. the name distributor
*/
-int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector)
+int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector)
{
struct tipc_link *l_ptr;
struct tipc_node *n_ptr;
@@ -813,7 +831,7 @@
tipc_node_lock(n_ptr);
l_ptr = n_ptr->active_links[selector & 1];
if (l_ptr)
- res = tipc_link_send_buf(l_ptr, buf);
+ res = __tipc_link_xmit(l_ptr, buf);
else
kfree_skb(buf);
tipc_node_unlock(n_ptr);
@@ -825,14 +843,14 @@
}
/*
- * tipc_link_send_sync - synchronize broadcast link endpoints.
+ * tipc_link_sync_xmit - synchronize broadcast link endpoints.
*
* Give a newly added peer node the sequence number where it should
* start receiving and acking broadcast packets.
*
* Called with node locked
*/
-static void tipc_link_send_sync(struct tipc_link *l)
+static void tipc_link_sync_xmit(struct tipc_link *l)
{
struct sk_buff *buf;
struct tipc_msg *msg;
@@ -849,14 +867,14 @@
}
/*
- * tipc_link_recv_sync - synchronize broadcast link endpoints.
+ * tipc_link_sync_rcv - synchronize broadcast link endpoints.
* Receive the sequence number where we should start receiving and
* acking broadcast packets from a newly added peer node, and open
* up for reception of such packets.
*
* Called with node locked
*/
-static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf)
+static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf)
{
struct tipc_msg *msg = buf_msg(buf);
@@ -866,7 +884,7 @@
}
/*
- * tipc_link_send_names - send name table entries to new neighbor
+ * tipc_link_names_xmit - send name table entries to new neighbor
*
* Send routine for bulk delivery of name table messages when contact
* with a new neighbor occurs. No link congestion checking is performed
@@ -874,7 +892,7 @@
* small enough not to require fragmentation.
* Called without any locks held.
*/
-void tipc_link_send_names(struct list_head *message_list, u32 dest)
+void tipc_link_names_xmit(struct list_head *message_list, u32 dest)
{
struct tipc_node *n_ptr;
struct tipc_link *l_ptr;
@@ -909,13 +927,13 @@
}
/*
- * link_send_buf_fast: Entry for data messages where the
+ * tipc_link_xmit_fast: Entry for data messages where the
* destination link is known and the header is complete,
* inclusive total message length. Very time critical.
* Link is locked. Returns user data length.
*/
-static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf,
- u32 *used_max_pkt)
+static int tipc_link_xmit_fast(struct tipc_link *l_ptr, struct sk_buff *buf,
+ u32 *used_max_pkt)
{
struct tipc_msg *msg = buf_msg(buf);
int res = msg_data_sz(msg);
@@ -931,18 +949,18 @@
else
*used_max_pkt = l_ptr->max_pkt;
}
- return tipc_link_send_buf(l_ptr, buf); /* All other cases */
+ return __tipc_link_xmit(l_ptr, buf); /* All other cases */
}
/*
- * tipc_link_send_sections_fast: Entry for messages where the
+ * tipc_link_iovec_xmit_fast: Entry for messages where the
* destination processor is known and the header is complete,
* except for total message length.
* Returns user data length or errno.
*/
-int tipc_link_send_sections_fast(struct tipc_port *sender,
- struct iovec const *msg_sect,
- unsigned int len, u32 destaddr)
+int tipc_link_iovec_xmit_fast(struct tipc_port *sender,
+ struct iovec const *msg_sect,
+ unsigned int len, u32 destaddr)
{
struct tipc_msg *hdr = &sender->phdr;
struct tipc_link *l_ptr;
@@ -968,8 +986,8 @@
l_ptr = node->active_links[selector];
if (likely(l_ptr)) {
if (likely(buf)) {
- res = link_send_buf_fast(l_ptr, buf,
- &sender->max_pkt);
+ res = tipc_link_xmit_fast(l_ptr, buf,
+ &sender->max_pkt);
exit:
tipc_node_unlock(node);
read_unlock_bh(&tipc_net_lock);
@@ -995,24 +1013,21 @@
if ((msg_hdr_sz(hdr) + res) <= sender->max_pkt)
goto again;
- return link_send_sections_long(sender, msg_sect, len,
- destaddr);
+ return tipc_link_iovec_long_xmit(sender, msg_sect,
+ len, destaddr);
}
tipc_node_unlock(node);
}
read_unlock_bh(&tipc_net_lock);
/* Couldn't find a link to the destination node */
- if (buf)
- return tipc_reject_msg(buf, TIPC_ERR_NO_NODE);
- if (res >= 0)
- return tipc_port_reject_sections(sender, hdr, msg_sect,
- len, TIPC_ERR_NO_NODE);
- return res;
+ kfree_skb(buf);
+ tipc_port_iovec_reject(sender, hdr, msg_sect, len, TIPC_ERR_NO_NODE);
+ return -ENETUNREACH;
}
/*
- * link_send_sections_long(): Entry for long messages where the
+ * tipc_link_iovec_long_xmit(): Entry for long messages where the
* destination node is known and the header is complete,
* inclusive total message length.
* Link and bearer congestion status have been checked to be ok,
@@ -1025,9 +1040,9 @@
*
* Returns user data length or errno.
*/
-static int link_send_sections_long(struct tipc_port *sender,
- struct iovec const *msg_sect,
- unsigned int len, u32 destaddr)
+static int tipc_link_iovec_long_xmit(struct tipc_port *sender,
+ struct iovec const *msg_sect,
+ unsigned int len, u32 destaddr)
{
struct tipc_link *l_ptr;
struct tipc_node *node;
@@ -1146,8 +1161,9 @@
} else {
reject:
kfree_skb_list(buf_chain);
- return tipc_port_reject_sections(sender, hdr, msg_sect,
- len, TIPC_ERR_NO_NODE);
+ tipc_port_iovec_reject(sender, hdr, msg_sect, len,
+ TIPC_ERR_NO_NODE);
+ return -ENETUNREACH;
}
/* Append chain of fragments to send queue & send them */
@@ -1391,6 +1407,12 @@
u32 hdr_size;
u32 min_hdr_size;
+ /* If this packet comes from the defer queue, the skb has already
+ * been validated
+ */
+ if (unlikely(TIPC_SKB_CB(buf)->deferred))
+ return 1;
+
if (unlikely(buf->len < MIN_H_SIZE))
return 0;
@@ -1435,15 +1457,10 @@
u32 seq_no;
u32 ackd;
u32 released = 0;
- int type;
head = head->next;
buf->next = NULL;
- /* Ensure bearer is still enabled */
- if (unlikely(!b_ptr->active))
- goto discard;
-
/* Ensure message is well-formed */
if (unlikely(!link_recv_buf_validate(buf)))
goto discard;
@@ -1457,9 +1474,9 @@
if (unlikely(msg_non_seq(msg))) {
if (msg_user(msg) == LINK_CONFIG)
- tipc_disc_recv_msg(buf, b_ptr);
+ tipc_disc_rcv(buf, b_ptr);
else
- tipc_bclink_recv_pkt(buf);
+ tipc_bclink_rcv(buf);
continue;
}
@@ -1483,7 +1500,7 @@
if ((n_ptr->block_setup & WAIT_PEER_DOWN) &&
msg_user(msg) == LINK_PROTOCOL &&
(msg_type(msg) == RESET_MSG ||
- msg_type(msg) == ACTIVATE_MSG) &&
+ msg_type(msg) == ACTIVATE_MSG) &&
!msg_redundant_link(msg))
n_ptr->block_setup &= ~WAIT_PEER_DOWN;
@@ -1502,7 +1519,6 @@
while ((crs != l_ptr->next_out) &&
less_eq(buf_seqno(crs), ackd)) {
struct sk_buff *next = crs->next;
-
kfree_skb(crs);
crs = next;
released++;
@@ -1515,18 +1531,19 @@
/* Try sending any messages link endpoint has pending */
if (unlikely(l_ptr->next_out))
tipc_link_push_queue(l_ptr);
+
if (unlikely(!list_empty(&l_ptr->waiting_ports)))
tipc_link_wakeup_ports(l_ptr, 0);
+
if (unlikely(++l_ptr->unacked_window >= TIPC_MIN_LINK_WIN)) {
l_ptr->stats.sent_acks++;
- tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
}
- /* Now (finally!) process the incoming message */
-protocol_check:
+ /* Process the incoming packet */
if (unlikely(!link_working_working(l_ptr))) {
if (msg_user(msg) == LINK_PROTOCOL) {
- link_recv_proto_msg(l_ptr, buf);
+ tipc_link_proto_rcv(l_ptr, buf);
head = link_insert_deferred_queue(l_ptr, head);
tipc_node_unlock(n_ptr);
continue;
@@ -1555,67 +1572,65 @@
l_ptr->next_in_no++;
if (unlikely(l_ptr->oldest_deferred_in))
head = link_insert_deferred_queue(l_ptr, head);
-deliver:
- if (likely(msg_isdata(msg))) {
- tipc_node_unlock(n_ptr);
- tipc_port_recv_msg(buf);
- continue;
+
+ /* Deliver packet/message to correct user: */
+ if (unlikely(msg_user(msg) == CHANGEOVER_PROTOCOL)) {
+ if (!tipc_link_tunnel_rcv(n_ptr, &buf)) {
+ tipc_node_unlock(n_ptr);
+ continue;
+ }
+ msg = buf_msg(buf);
+ } else if (msg_user(msg) == MSG_FRAGMENTER) {
+ int rc;
+
+ l_ptr->stats.recv_fragments++;
+ rc = tipc_link_frag_rcv(&l_ptr->reasm_head,
+ &l_ptr->reasm_tail,
+ &buf);
+ if (rc == LINK_REASM_COMPLETE) {
+ l_ptr->stats.recv_fragmented++;
+ msg = buf_msg(buf);
+ } else {
+ if (rc == LINK_REASM_ERROR)
+ tipc_link_reset(l_ptr);
+ tipc_node_unlock(n_ptr);
+ continue;
+ }
}
+
switch (msg_user(msg)) {
- int ret;
+ case TIPC_LOW_IMPORTANCE:
+ case TIPC_MEDIUM_IMPORTANCE:
+ case TIPC_HIGH_IMPORTANCE:
+ case TIPC_CRITICAL_IMPORTANCE:
+ tipc_node_unlock(n_ptr);
+ tipc_port_rcv(buf);
+ continue;
case MSG_BUNDLER:
l_ptr->stats.recv_bundles++;
l_ptr->stats.recv_bundled += msg_msgcnt(msg);
tipc_node_unlock(n_ptr);
- tipc_link_recv_bundle(buf);
+ tipc_link_bundle_rcv(buf);
continue;
case NAME_DISTRIBUTOR:
n_ptr->bclink.recv_permitted = true;
tipc_node_unlock(n_ptr);
- tipc_named_recv(buf);
- continue;
- case BCAST_PROTOCOL:
- tipc_link_recv_sync(n_ptr, buf);
- tipc_node_unlock(n_ptr);
+ tipc_named_rcv(buf);
continue;
case CONN_MANAGER:
tipc_node_unlock(n_ptr);
- tipc_port_recv_proto_msg(buf);
+ tipc_port_proto_rcv(buf);
continue;
- case MSG_FRAGMENTER:
- l_ptr->stats.recv_fragments++;
- ret = tipc_link_recv_fragment(&l_ptr->reasm_head,
- &l_ptr->reasm_tail,
- &buf);
- if (ret == LINK_REASM_COMPLETE) {
- l_ptr->stats.recv_fragmented++;
- msg = buf_msg(buf);
- goto deliver;
- }
- if (ret == LINK_REASM_ERROR)
- tipc_link_reset(l_ptr);
- tipc_node_unlock(n_ptr);
- continue;
- case CHANGEOVER_PROTOCOL:
- type = msg_type(msg);
- if (tipc_link_tunnel_rcv(&l_ptr, &buf)) {
- msg = buf_msg(buf);
- seq_no = msg_seqno(msg);
- if (type == ORIGINAL_MSG)
- goto deliver;
- goto protocol_check;
- }
+ case BCAST_PROTOCOL:
+ tipc_link_sync_rcv(n_ptr, buf);
break;
default:
kfree_skb(buf);
- buf = NULL;
break;
}
tipc_node_unlock(n_ptr);
- tipc_net_route_msg(buf);
continue;
unlock_discard:
-
tipc_node_unlock(n_ptr);
discard:
kfree_skb(buf);
@@ -1682,7 +1697,7 @@
u32 seq_no = buf_seqno(buf);
if (likely(msg_user(buf_msg(buf)) == LINK_PROTOCOL)) {
- link_recv_proto_msg(l_ptr, buf);
+ tipc_link_proto_rcv(l_ptr, buf);
return;
}
@@ -1703,8 +1718,9 @@
&l_ptr->newest_deferred_in, buf)) {
l_ptr->deferred_inqueue_sz++;
l_ptr->stats.deferred_recv++;
+ TIPC_SKB_CB(buf)->deferred = true;
if ((l_ptr->deferred_inqueue_sz % 16) == 1)
- tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
+ tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
} else
l_ptr->stats.duplicates++;
}
@@ -1712,9 +1728,8 @@
/*
* Send protocol message to the other endpoint.
*/
-void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ,
- int probe_msg, u32 gap, u32 tolerance,
- u32 priority, u32 ack_mtu)
+void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg,
+ u32 gap, u32 tolerance, u32 priority, u32 ack_mtu)
{
struct sk_buff *buf = NULL;
struct tipc_msg *msg = l_ptr->pmsg;
@@ -1813,7 +1828,7 @@
* Note that network plane id propagates through the network, and may
* change at any time. The node with lowest address rules
*/
-static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf)
+static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf)
{
u32 rec_gap = 0;
u32 max_pkt_info;
@@ -1932,8 +1947,8 @@
msg_last_bcast(msg));
if (rec_gap || (msg_probe(msg))) {
- tipc_link_send_proto_msg(l_ptr, STATE_MSG,
- 0, rec_gap, 0, 0, max_pkt_ack);
+ tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, rec_gap, 0,
+ 0, max_pkt_ack);
}
if (msg_seq_gap(msg)) {
l_ptr->stats.recv_nacks++;
@@ -1972,7 +1987,7 @@
}
skb_copy_to_linear_data(buf, tunnel_hdr, INT_H_SIZE);
skb_copy_to_linear_data_offset(buf, INT_H_SIZE, msg, length);
- tipc_link_send_buf(tunnel, buf);
+ __tipc_link_xmit(tunnel, buf);
}
@@ -2005,7 +2020,7 @@
if (buf) {
skb_copy_to_linear_data(buf, &tunnel_hdr, INT_H_SIZE);
msg_set_size(&tunnel_hdr, INT_H_SIZE);
- tipc_link_send_buf(tunnel, buf);
+ __tipc_link_xmit(tunnel, buf);
} else {
pr_warn("%sunable to send changeover msg\n",
link_co_err);
@@ -2039,7 +2054,7 @@
}
}
-/* tipc_link_dup_send_queue(): A second link has become active. Tunnel a
+/* tipc_link_dup_queue_xmit(): A second link has become active. Tunnel a
* duplicate of the first link's send queue via the new link. This way, we
* are guaranteed that currently queued packets from a socket are delivered
* before future traffic from the same socket, even if this is using the
@@ -2048,7 +2063,7 @@
* and sequence order is preserved per sender/receiver socket pair.
* Owner node is locked.
*/
-void tipc_link_dup_send_queue(struct tipc_link *l_ptr,
+void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr,
struct tipc_link *tunnel)
{
struct sk_buff *iter;
@@ -2078,7 +2093,7 @@
skb_copy_to_linear_data(outbuf, &tunnel_hdr, INT_H_SIZE);
skb_copy_to_linear_data_offset(outbuf, INT_H_SIZE, iter->data,
length);
- tipc_link_send_buf(tunnel, outbuf);
+ __tipc_link_xmit(tunnel, outbuf);
if (!tipc_link_is_up(l_ptr))
return;
iter = iter->next;
@@ -2105,89 +2120,114 @@
return eb;
}
-/* tipc_link_tunnel_rcv(): Receive a tunneled packet, sent
+
+
+/* tipc_link_dup_rcv(): Receive a tunnelled DUPLICATE_MSG packet.
+ * Owner node is locked.
+ */
+static void tipc_link_dup_rcv(struct tipc_link *l_ptr,
+ struct sk_buff *t_buf)
+{
+ struct sk_buff *buf;
+
+ if (!tipc_link_is_up(l_ptr))
+ return;
+
+ buf = buf_extract(t_buf, INT_H_SIZE);
+ if (buf == NULL) {
+ pr_warn("%sfailed to extract inner dup pkt\n", link_co_err);
+ return;
+ }
+
+ /* Add buffer to deferred queue, if applicable: */
+ link_handle_out_of_seq_msg(l_ptr, buf);
+}
+
+/* tipc_link_failover_rcv(): Receive a tunnelled ORIGINAL_MSG packet
+ * Owner node is locked.
+ */
+static struct sk_buff *tipc_link_failover_rcv(struct tipc_link *l_ptr,
+ struct sk_buff *t_buf)
+{
+ struct tipc_msg *t_msg = buf_msg(t_buf);
+ struct sk_buff *buf = NULL;
+ struct tipc_msg *msg;
+
+ if (tipc_link_is_up(l_ptr))
+ tipc_link_reset(l_ptr);
+
+ /* First failover packet? */
+ if (l_ptr->exp_msg_count == START_CHANGEOVER)
+ l_ptr->exp_msg_count = msg_msgcnt(t_msg);
+
+ /* Should there be an inner packet? */
+ if (l_ptr->exp_msg_count) {
+ l_ptr->exp_msg_count--;
+ buf = buf_extract(t_buf, INT_H_SIZE);
+ if (buf == NULL) {
+ pr_warn("%sno inner failover pkt\n", link_co_err);
+ goto exit;
+ }
+ msg = buf_msg(buf);
+
+ if (less(msg_seqno(msg), l_ptr->reset_checkpoint)) {
+ kfree_skb(buf);
+ buf = NULL;
+ goto exit;
+ }
+ if (msg_user(msg) == MSG_FRAGMENTER) {
+ l_ptr->stats.recv_fragments++;
+ tipc_link_frag_rcv(&l_ptr->reasm_head,
+ &l_ptr->reasm_tail,
+ &buf);
+ }
+ }
+exit:
+ if ((l_ptr->exp_msg_count == 0) && (l_ptr->flags & LINK_STOPPED)) {
+ tipc_node_detach_link(l_ptr->owner, l_ptr);
+ kfree(l_ptr);
+ }
+ return buf;
+}
+
+/* tipc_link_tunnel_rcv(): Receive a tunnelled packet, sent
* via other link as result of a failover (ORIGINAL_MSG) or
* a new active link (DUPLICATE_MSG). Failover packets are
* returned to the active link for delivery upwards.
* Owner node is locked.
*/
-static int tipc_link_tunnel_rcv(struct tipc_link **l_ptr,
+static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr,
struct sk_buff **buf)
{
- struct sk_buff *tunnel_buf = *buf;
- struct tipc_link *dest_link;
- struct tipc_msg *msg;
- struct tipc_msg *tunnel_msg = buf_msg(tunnel_buf);
- u32 msg_typ = msg_type(tunnel_msg);
- u32 msg_count = msg_msgcnt(tunnel_msg);
- u32 bearer_id = msg_bearer_id(tunnel_msg);
+ struct sk_buff *t_buf = *buf;
+ struct tipc_link *l_ptr;
+ struct tipc_msg *t_msg = buf_msg(t_buf);
+ u32 bearer_id = msg_bearer_id(t_msg);
+
+ *buf = NULL;
if (bearer_id >= MAX_BEARERS)
goto exit;
- dest_link = (*l_ptr)->owner->links[bearer_id];
- if (!dest_link)
- goto exit;
- if (dest_link == *l_ptr) {
- pr_err("Unexpected changeover message on link <%s>\n",
- (*l_ptr)->name);
- goto exit;
- }
- *l_ptr = dest_link;
- msg = msg_get_wrapped(tunnel_msg);
- if (msg_typ == DUPLICATE_MSG) {
- if (less(msg_seqno(msg), mod(dest_link->next_in_no)))
- goto exit;
- *buf = buf_extract(tunnel_buf, INT_H_SIZE);
- if (*buf == NULL) {
- pr_warn("%sduplicate msg dropped\n", link_co_err);
- goto exit;
- }
- kfree_skb(tunnel_buf);
- return 1;
- }
-
- /* First original message ?: */
- if (tipc_link_is_up(dest_link)) {
- pr_info("%s<%s>, changeover initiated by peer\n", link_rst_msg,
- dest_link->name);
- tipc_link_reset(dest_link);
- dest_link->exp_msg_count = msg_count;
- if (!msg_count)
- goto exit;
- } else if (dest_link->exp_msg_count == START_CHANGEOVER) {
- dest_link->exp_msg_count = msg_count;
- if (!msg_count)
- goto exit;
- }
-
- /* Receive original message */
- if (dest_link->exp_msg_count == 0) {
- pr_warn("%sgot too many tunnelled messages\n", link_co_err);
+ l_ptr = n_ptr->links[bearer_id];
+ if (!l_ptr)
goto exit;
- }
- dest_link->exp_msg_count--;
- if (less(msg_seqno(msg), dest_link->reset_checkpoint)) {
- goto exit;
- } else {
- *buf = buf_extract(tunnel_buf, INT_H_SIZE);
- if (*buf != NULL) {
- kfree_skb(tunnel_buf);
- return 1;
- } else {
- pr_warn("%soriginal msg dropped\n", link_co_err);
- }
- }
+
+ if (msg_type(t_msg) == DUPLICATE_MSG)
+ tipc_link_dup_rcv(l_ptr, t_buf);
+ else if (msg_type(t_msg) == ORIGINAL_MSG)
+ *buf = tipc_link_failover_rcv(l_ptr, t_buf);
+ else
+ pr_warn("%sunknown tunnel pkt received\n", link_co_err);
exit:
- *buf = NULL;
- kfree_skb(tunnel_buf);
- return 0;
+ kfree_skb(t_buf);
+ return *buf != NULL;
}
/*
* Bundler functionality:
*/
-void tipc_link_recv_bundle(struct sk_buff *buf)
+void tipc_link_bundle_rcv(struct sk_buff *buf)
{
u32 msgcount = msg_msgcnt(buf_msg(buf));
u32 pos = INT_H_SIZE;
@@ -2210,11 +2250,11 @@
*/
/*
- * link_send_long_buf: Entry for buffers needing fragmentation.
+ * tipc_link_frag_xmit: Entry for buffers needing fragmentation.
* The buffer is complete, inclusive total message length.
* Returns user data length.
*/
-static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf)
+static int tipc_link_frag_xmit(struct tipc_link *l_ptr, struct sk_buff *buf)
{
struct sk_buff *buf_chain = NULL;
struct sk_buff *buf_chain_tail = (struct sk_buff *)&buf_chain;
@@ -2277,12 +2317,11 @@
return dsz;
}
-/*
- * tipc_link_recv_fragment(): Called with node lock on. Returns
+/* tipc_link_frag_rcv(): Called with node lock on. Returns
* the reassembled buffer if message is complete.
*/
-int tipc_link_recv_fragment(struct sk_buff **head, struct sk_buff **tail,
- struct sk_buff **fbuf)
+int tipc_link_frag_rcv(struct sk_buff **head, struct sk_buff **tail,
+ struct sk_buff **fbuf)
{
struct sk_buff *frag = *fbuf;
struct tipc_msg *msg = buf_msg(frag);
@@ -2296,6 +2335,7 @@
goto out_free;
*head = frag;
skb_frag_list_init(*head);
+ *fbuf = NULL;
return 0;
} else if (*head &&
skb_try_coalesce(*head, frag, &headstolen, &delta)) {
@@ -2315,10 +2355,12 @@
*tail = *head = NULL;
return LINK_REASM_COMPLETE;
}
+ *fbuf = NULL;
return 0;
out_free:
pr_warn_ratelimited("Link unable to reassemble fragmented message\n");
kfree_skb(*fbuf);
+ *fbuf = NULL;
return LINK_REASM_ERROR;
}
@@ -2352,35 +2394,41 @@
l_ptr->queue_limit[MSG_FRAGMENTER] = 4000;
}
-/**
- * link_find_link - locate link by name
- * @name: ptr to link name string
- * @node: ptr to area to be filled with ptr to associated node
- *
+/* tipc_link_find_owner - locate owner node of link by link's name
+ * @name: pointer to link name string
+ * @bearer_id: pointer to index in 'node->links' array where the link was found.
* Caller must hold 'tipc_net_lock' to ensure node and bearer are not deleted;
* this also prevents link deletion.
*
- * Returns pointer to link (or 0 if invalid link name).
+ * Returns pointer to node owning the link, or 0 if no matching link is found.
*/
-static struct tipc_link *link_find_link(const char *name,
- struct tipc_node **node)
+static struct tipc_node *tipc_link_find_owner(const char *link_name,
+ unsigned int *bearer_id)
{
struct tipc_link *l_ptr;
struct tipc_node *n_ptr;
+ struct tipc_node *found_node = 0;
int i;
- list_for_each_entry(n_ptr, &tipc_node_list, list) {
+ *bearer_id = 0;
+ rcu_read_lock();
+ list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
+ tipc_node_lock(n_ptr);
for (i = 0; i < MAX_BEARERS; i++) {
l_ptr = n_ptr->links[i];
- if (l_ptr && !strcmp(l_ptr->name, name))
- goto found;
+ if (l_ptr && !strcmp(l_ptr->name, link_name)) {
+ *bearer_id = i;
+ found_node = n_ptr;
+ break;
+ }
}
+ tipc_node_unlock(n_ptr);
+ if (found_node)
+ break;
}
- l_ptr = NULL;
- n_ptr = NULL;
-found:
- *node = n_ptr;
- return l_ptr;
+ rcu_read_unlock();
+
+ return found_node;
}
/**
@@ -2422,32 +2470,33 @@
struct tipc_link *l_ptr;
struct tipc_bearer *b_ptr;
struct tipc_media *m_ptr;
+ int bearer_id;
int res = 0;
- l_ptr = link_find_link(name, &node);
- if (l_ptr) {
- /*
- * acquire node lock for tipc_link_send_proto_msg().
- * see "TIPC locking policy" in net.c.
- */
+ node = tipc_link_find_owner(name, &bearer_id);
+ if (node) {
tipc_node_lock(node);
- switch (cmd) {
- case TIPC_CMD_SET_LINK_TOL:
- link_set_supervision_props(l_ptr, new_value);
- tipc_link_send_proto_msg(l_ptr,
- STATE_MSG, 0, 0, new_value, 0, 0);
- break;
- case TIPC_CMD_SET_LINK_PRI:
- l_ptr->priority = new_value;
- tipc_link_send_proto_msg(l_ptr,
- STATE_MSG, 0, 0, 0, new_value, 0);
- break;
- case TIPC_CMD_SET_LINK_WINDOW:
- tipc_link_set_queue_limits(l_ptr, new_value);
- break;
- default:
- res = -EINVAL;
- break;
+ l_ptr = node->links[bearer_id];
+
+ if (l_ptr) {
+ switch (cmd) {
+ case TIPC_CMD_SET_LINK_TOL:
+ link_set_supervision_props(l_ptr, new_value);
+ tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0,
+ new_value, 0, 0);
+ break;
+ case TIPC_CMD_SET_LINK_PRI:
+ l_ptr->priority = new_value;
+ tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0,
+ 0, new_value, 0);
+ break;
+ case TIPC_CMD_SET_LINK_WINDOW:
+ tipc_link_set_queue_limits(l_ptr, new_value);
+ break;
+ default:
+ res = -EINVAL;
+ break;
+ }
}
tipc_node_unlock(node);
return res;
@@ -2542,6 +2591,7 @@
char *link_name;
struct tipc_link *l_ptr;
struct tipc_node *node;
+ unsigned int bearer_id;
if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_NAME))
return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
@@ -2552,15 +2602,19 @@
return tipc_cfg_reply_error_string("link not found");
return tipc_cfg_reply_none();
}
-
read_lock_bh(&tipc_net_lock);
- l_ptr = link_find_link(link_name, &node);
- if (!l_ptr) {
+ node = tipc_link_find_owner(link_name, &bearer_id);
+ if (!node) {
read_unlock_bh(&tipc_net_lock);
return tipc_cfg_reply_error_string("link not found");
}
-
tipc_node_lock(node);
+ l_ptr = node->links[bearer_id];
+ if (!l_ptr) {
+ tipc_node_unlock(node);
+ read_unlock_bh(&tipc_net_lock);
+ return tipc_cfg_reply_error_string("link not found");
+ }
link_reset_statistics(l_ptr);
tipc_node_unlock(node);
read_unlock_bh(&tipc_net_lock);
@@ -2590,18 +2644,27 @@
struct tipc_node *node;
char *status;
u32 profile_total = 0;
+ unsigned int bearer_id;
int ret;
if (!strcmp(name, tipc_bclink_name))
return tipc_bclink_stats(buf, buf_size);
read_lock_bh(&tipc_net_lock);
- l = link_find_link(name, &node);
- if (!l) {
+ node = tipc_link_find_owner(name, &bearer_id);
+ if (!node) {
read_unlock_bh(&tipc_net_lock);
return 0;
}
tipc_node_lock(node);
+
+ l = node->links[bearer_id];
+ if (!l) {
+ tipc_node_unlock(node);
+ read_unlock_bh(&tipc_net_lock);
+ return 0;
+ }
+
s = &l->stats;
if (tipc_link_is_active(l))
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 3b6aa65..8c0b49b 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -1,7 +1,7 @@
/*
* net/tipc/link.h: Include file for TIPC link code
*
- * Copyright (c) 1995-2006, Ericsson AB
+ * Copyright (c) 1995-2006, 2013, Ericsson AB
* Copyright (c) 2004-2005, 2010-2011, Wind River Systems
* All rights reserved.
*
@@ -40,27 +40,28 @@
#include "msg.h"
#include "node.h"
-/*
- * Link reassembly status codes
+/* Link reassembly status codes
*/
#define LINK_REASM_ERROR -1
#define LINK_REASM_COMPLETE 1
-/*
- * Out-of-range value for link sequence numbers
+/* Out-of-range value for link sequence numbers
*/
#define INVALID_LINK_SEQ 0x10000
-/*
- * Link states
+/* Link working states
*/
#define WORKING_WORKING 560810u
#define WORKING_UNKNOWN 560811u
#define RESET_UNKNOWN 560812u
#define RESET_RESET 560813u
-/*
- * Starting value for maximum packet size negotiation on unicast links
+/* Link endpoint execution states
+ */
+#define LINK_STARTED 0x0001
+#define LINK_STOPPED 0x0002
+
+/* Starting value for maximum packet size negotiation on unicast links
* (unless bearer MTU is less)
*/
#define MAX_PKT_DEFAULT 1500
@@ -102,8 +103,7 @@
* @media_addr: media address to use when sending messages over link
* @timer: link timer
* @owner: pointer to peer node
- * @link_list: adjacent links in bearer's list of links
- * @started: indicates if link has been started
+ * @flags: execution state flags for link endpoint instance
* @checkpoint: reference point for triggering link continuity checking
* @peer_session: link session # being used by peer end of link
* @peer_bearer_id: bearer id used by link's peer endpoint
@@ -149,10 +149,9 @@
struct tipc_media_addr media_addr;
struct timer_list timer;
struct tipc_node *owner;
- struct list_head link_list;
/* Management and link supervision data */
- int started;
+ unsigned int flags;
u32 checkpoint;
u32 peer_session;
u32 peer_bearer_id;
@@ -215,10 +214,9 @@
struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
struct tipc_bearer *b_ptr,
const struct tipc_media_addr *media_addr);
-void tipc_link_delete(struct tipc_link *l_ptr);
+void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down);
void tipc_link_failover_send_queue(struct tipc_link *l_ptr);
-void tipc_link_dup_send_queue(struct tipc_link *l_ptr,
- struct tipc_link *dest);
+void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct tipc_link *dest);
void tipc_link_reset_fragments(struct tipc_link *l_ptr);
int tipc_link_is_up(struct tipc_link *l_ptr);
int tipc_link_is_active(struct tipc_link *l_ptr);
@@ -231,23 +229,24 @@
struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area,
int req_tlv_space);
void tipc_link_reset(struct tipc_link *l_ptr);
-int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector);
-void tipc_link_send_names(struct list_head *message_list, u32 dest);
+void tipc_link_reset_list(unsigned int bearer_id);
+int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector);
+void tipc_link_names_xmit(struct list_head *message_list, u32 dest);
+int __tipc_link_xmit(struct tipc_link *l_ptr, struct sk_buff *buf);
int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf);
u32 tipc_link_get_max_pkt(u32 dest, u32 selector);
-int tipc_link_send_sections_fast(struct tipc_port *sender,
- struct iovec const *msg_sect,
- unsigned int len, u32 destnode);
-void tipc_link_recv_bundle(struct sk_buff *buf);
-int tipc_link_recv_fragment(struct sk_buff **reasm_head,
- struct sk_buff **reasm_tail,
- struct sk_buff **fbuf);
-void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, int prob,
- u32 gap, u32 tolerance, u32 priority,
- u32 acked_mtu);
+int tipc_link_iovec_xmit_fast(struct tipc_port *sender,
+ struct iovec const *msg_sect,
+ unsigned int len, u32 destnode);
+void tipc_link_bundle_rcv(struct sk_buff *buf);
+int tipc_link_frag_rcv(struct sk_buff **reasm_head,
+ struct sk_buff **reasm_tail,
+ struct sk_buff **fbuf);
+void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob,
+ u32 gap, u32 tolerance, u32 priority, u32 acked_mtu);
void tipc_link_push_queue(struct tipc_link *l_ptr);
u32 tipc_link_defer_pkt(struct sk_buff **head, struct sk_buff **tail,
- struct sk_buff *buf);
+ struct sk_buff *buf);
void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all);
void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window);
void tipc_link_retransmit(struct tipc_link *l_ptr,
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index e0d0805..aff8041 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -131,16 +131,24 @@
{
struct sk_buff *buf_copy;
struct tipc_node *n_ptr;
+ struct tipc_link *l_ptr;
- list_for_each_entry(n_ptr, &tipc_node_list, list) {
- if (tipc_node_active_links(n_ptr)) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
+ spin_lock_bh(&n_ptr->lock);
+ l_ptr = n_ptr->active_links[n_ptr->addr & 1];
+ if (l_ptr) {
buf_copy = skb_copy(buf, GFP_ATOMIC);
- if (!buf_copy)
+ if (!buf_copy) {
+ spin_unlock_bh(&n_ptr->lock);
break;
+ }
msg_set_destnode(buf_msg(buf_copy), n_ptr->addr);
- tipc_link_send(buf_copy, n_ptr->addr, n_ptr->addr);
+ __tipc_link_xmit(l_ptr, buf_copy);
}
+ spin_unlock_bh(&n_ptr->lock);
}
+ rcu_read_unlock();
kfree_skb(buf);
}
@@ -262,7 +270,7 @@
named_distribute(&message_list, node, &publ_zone, max_item_buf);
read_unlock_bh(&tipc_nametbl_lock);
- tipc_link_send_names(&message_list, node);
+ tipc_link_names_xmit(&message_list, node);
}
/**
@@ -293,9 +301,9 @@
}
/**
- * tipc_named_recv - process name table update message sent by another node
+ * tipc_named_rcv - process name table update message sent by another node
*/
-void tipc_named_recv(struct sk_buff *buf)
+void tipc_named_rcv(struct sk_buff *buf)
{
struct publication *publ;
struct tipc_msg *msg = buf_msg(buf);
diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h
index 1e41bdd..9b312cc 100644
--- a/net/tipc/name_distr.h
+++ b/net/tipc/name_distr.h
@@ -42,7 +42,7 @@
void tipc_named_publish(struct publication *publ);
void tipc_named_withdraw(struct publication *publ);
void tipc_named_node_up(unsigned long node);
-void tipc_named_recv(struct sk_buff *buf);
+void tipc_named_rcv(struct sk_buff *buf);
void tipc_named_reinit(void);
#endif
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 92a1533..042e8e3 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -941,20 +941,48 @@
return 0;
}
+/**
+ * tipc_purge_publications - remove all publications for a given type
+ *
+ * tipc_nametbl_lock must be held when calling this function
+ */
+static void tipc_purge_publications(struct name_seq *seq)
+{
+ struct publication *publ, *safe;
+ struct sub_seq *sseq;
+ struct name_info *info;
+
+ if (!seq->sseqs) {
+ nameseq_delete_empty(seq);
+ return;
+ }
+ sseq = seq->sseqs;
+ info = sseq->info;
+ list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) {
+ tipc_nametbl_remove_publ(publ->type, publ->lower, publ->node,
+ publ->ref, publ->key);
+ }
+}
+
void tipc_nametbl_stop(void)
{
u32 i;
+ struct name_seq *seq;
+ struct hlist_head *seq_head;
+ struct hlist_node *safe;
- if (!table.types)
- return;
-
- /* Verify name table is empty, then release it */
+ /* Verify name table is empty and purge any lingering
+ * publications, then release the name table
+ */
write_lock_bh(&tipc_nametbl_lock);
for (i = 0; i < TIPC_NAMETBL_SIZE; i++) {
if (hlist_empty(&table.types[i]))
continue;
- pr_err("nametbl_stop(): orphaned hash chain detected\n");
- break;
+ seq_head = &table.types[i];
+ hlist_for_each_entry_safe(seq, safe, seq_head, ns_list) {
+ tipc_purge_publications(seq);
+ }
+ continue;
}
kfree(table.types);
table.types = NULL;
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 7d305ec..0374a81 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -146,19 +146,19 @@
if (tipc_in_scope(dnode, tipc_own_addr)) {
if (msg_isdata(msg)) {
if (msg_mcast(msg))
- tipc_port_recv_mcast(buf, NULL);
+ tipc_port_mcast_rcv(buf, NULL);
else if (msg_destport(msg))
- tipc_port_recv_msg(buf);
+ tipc_port_rcv(buf);
else
net_route_named_msg(buf);
return;
}
switch (msg_user(msg)) {
case NAME_DISTRIBUTOR:
- tipc_named_recv(buf);
+ tipc_named_rcv(buf);
break;
case CONN_MANAGER:
- tipc_port_recv_proto_msg(buf);
+ tipc_port_proto_rcv(buf);
break;
default:
kfree_skb(buf);
@@ -168,7 +168,7 @@
/* Handle message for another node */
skb_trim(buf, msg_size(msg));
- tipc_link_send(buf, dnode, msg_link_selector(msg));
+ tipc_link_xmit(buf, dnode, msg_link_selector(msg));
}
void tipc_net_start(u32 addr)
@@ -182,8 +182,6 @@
tipc_bclink_init();
write_unlock_bh(&tipc_net_lock);
- tipc_cfg_reinit();
-
pr_info("Started in network mode\n");
pr_info("Own node address %s, network identity %u\n",
tipc_addr_string_fill(addr_string, tipc_own_addr), tipc_net_id);
@@ -191,15 +189,14 @@
void tipc_net_stop(void)
{
- struct tipc_node *node, *t_node;
-
if (!tipc_own_addr)
return;
+
write_lock_bh(&tipc_net_lock);
tipc_bearer_stop();
tipc_bclink_stop();
- list_for_each_entry_safe(node, t_node, &tipc_node_list, list)
- tipc_node_delete(node);
+ tipc_node_stop();
write_unlock_bh(&tipc_net_lock);
+
pr_info("Left network mode\n");
}
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 9f72a63..3aaf73d 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -83,8 +83,6 @@
},
};
-static int tipc_genl_family_registered;
-
int tipc_netlink_start(void)
{
int res;
@@ -94,16 +92,10 @@
pr_err("Failed to register netlink interface\n");
return res;
}
-
- tipc_genl_family_registered = 1;
return 0;
}
void tipc_netlink_stop(void)
{
- if (!tipc_genl_family_registered)
- return;
-
genl_unregister_family(&tipc_genl_family);
- tipc_genl_family_registered = 0;
}
diff --git a/net/tipc/node.c b/net/tipc/node.c
index efe4d41..1d3a499 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -2,7 +2,7 @@
* net/tipc/node.c: TIPC node management routines
*
* Copyright (c) 2000-2006, 2012 Ericsson AB
- * Copyright (c) 2005-2006, 2010-2011, Wind River Systems
+ * Copyright (c) 2005-2006, 2010-2014, Wind River Systems
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -44,13 +44,11 @@
static void node_lost_contact(struct tipc_node *n_ptr);
static void node_established_contact(struct tipc_node *n_ptr);
-static DEFINE_SPINLOCK(node_create_lock);
-
static struct hlist_head node_htable[NODE_HTABLE_SIZE];
LIST_HEAD(tipc_node_list);
static u32 tipc_num_nodes;
-
-static atomic_t tipc_num_links = ATOMIC_INIT(0);
+static u32 tipc_num_links;
+static DEFINE_SPINLOCK(node_list_lock);
/*
* A trivial power-of-two bitmask technique is used for speed, since this
@@ -73,37 +71,26 @@
if (unlikely(!in_own_cluster_exact(addr)))
return NULL;
- hlist_for_each_entry(node, &node_htable[tipc_hashfn(addr)], hash) {
- if (node->addr == addr)
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(node, &node_htable[tipc_hashfn(addr)], hash) {
+ if (node->addr == addr) {
+ rcu_read_unlock();
return node;
+ }
}
+ rcu_read_unlock();
return NULL;
}
-/**
- * tipc_node_create - create neighboring node
- *
- * Currently, this routine is called by neighbor discovery code, which holds
- * net_lock for reading only. We must take node_create_lock to ensure a node
- * isn't created twice if two different bearers discover the node at the same
- * time. (It would be preferable to switch to holding net_lock in write mode,
- * but this is a non-trivial change.)
- */
struct tipc_node *tipc_node_create(u32 addr)
{
struct tipc_node *n_ptr, *temp_node;
- spin_lock_bh(&node_create_lock);
-
- n_ptr = tipc_node_find(addr);
- if (n_ptr) {
- spin_unlock_bh(&node_create_lock);
- return n_ptr;
- }
+ spin_lock_bh(&node_list_lock);
n_ptr = kzalloc(sizeof(*n_ptr), GFP_ATOMIC);
if (!n_ptr) {
- spin_unlock_bh(&node_create_lock);
+ spin_unlock_bh(&node_list_lock);
pr_warn("Node creation failed, no memory\n");
return NULL;
}
@@ -114,31 +101,41 @@
INIT_LIST_HEAD(&n_ptr->list);
INIT_LIST_HEAD(&n_ptr->nsub);
- hlist_add_head(&n_ptr->hash, &node_htable[tipc_hashfn(addr)]);
+ hlist_add_head_rcu(&n_ptr->hash, &node_htable[tipc_hashfn(addr)]);
- list_for_each_entry(temp_node, &tipc_node_list, list) {
+ list_for_each_entry_rcu(temp_node, &tipc_node_list, list) {
if (n_ptr->addr < temp_node->addr)
break;
}
- list_add_tail(&n_ptr->list, &temp_node->list);
+ list_add_tail_rcu(&n_ptr->list, &temp_node->list);
n_ptr->block_setup = WAIT_PEER_DOWN;
n_ptr->signature = INVALID_NODE_SIG;
tipc_num_nodes++;
- spin_unlock_bh(&node_create_lock);
+ spin_unlock_bh(&node_list_lock);
return n_ptr;
}
-void tipc_node_delete(struct tipc_node *n_ptr)
+static void tipc_node_delete(struct tipc_node *n_ptr)
{
- list_del(&n_ptr->list);
- hlist_del(&n_ptr->hash);
- kfree(n_ptr);
+ list_del_rcu(&n_ptr->list);
+ hlist_del_rcu(&n_ptr->hash);
+ kfree_rcu(n_ptr, rcu);
tipc_num_nodes--;
}
+void tipc_node_stop(void)
+{
+ struct tipc_node *node, *t_node;
+
+ spin_lock_bh(&node_list_lock);
+ list_for_each_entry_safe(node, t_node, &tipc_node_list, list)
+ tipc_node_delete(node);
+ spin_unlock_bh(&node_list_lock);
+}
+
/**
* tipc_node_link_up - handle addition of link
*
@@ -162,7 +159,7 @@
pr_info("New link <%s> becomes standby\n", l_ptr->name);
return;
}
- tipc_link_dup_send_queue(active[0], l_ptr);
+ tipc_link_dup_queue_xmit(active[0], l_ptr);
if (l_ptr->priority == active[0]->priority) {
active[0] = l_ptr;
return;
@@ -243,15 +240,25 @@
void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
{
n_ptr->links[l_ptr->b_ptr->identity] = l_ptr;
- atomic_inc(&tipc_num_links);
+ spin_lock_bh(&node_list_lock);
+ tipc_num_links++;
+ spin_unlock_bh(&node_list_lock);
n_ptr->link_cnt++;
}
void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
{
- n_ptr->links[l_ptr->b_ptr->identity] = NULL;
- atomic_dec(&tipc_num_links);
- n_ptr->link_cnt--;
+ int i;
+
+ for (i = 0; i < MAX_BEARERS; i++) {
+ if (l_ptr != n_ptr->links[i])
+ continue;
+ n_ptr->links[i] = NULL;
+ spin_lock_bh(&node_list_lock);
+ tipc_num_links--;
+ spin_unlock_bh(&node_list_lock);
+ n_ptr->link_cnt--;
+ }
}
static void node_established_contact(struct tipc_node *n_ptr)
@@ -335,27 +342,28 @@
return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE
" (network address)");
- read_lock_bh(&tipc_net_lock);
+ spin_lock_bh(&node_list_lock);
if (!tipc_num_nodes) {
- read_unlock_bh(&tipc_net_lock);
+ spin_unlock_bh(&node_list_lock);
return tipc_cfg_reply_none();
}
/* For now, get space for all other nodes */
payload_size = TLV_SPACE(sizeof(node_info)) * tipc_num_nodes;
if (payload_size > 32768u) {
- read_unlock_bh(&tipc_net_lock);
+ spin_unlock_bh(&node_list_lock);
return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
" (too many nodes)");
}
+ spin_unlock_bh(&node_list_lock);
+
buf = tipc_cfg_reply_alloc(payload_size);
- if (!buf) {
- read_unlock_bh(&tipc_net_lock);
+ if (!buf)
return NULL;
- }
/* Add TLVs for all nodes in scope */
- list_for_each_entry(n_ptr, &tipc_node_list, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
if (!tipc_in_scope(domain, n_ptr->addr))
continue;
node_info.addr = htonl(n_ptr->addr);
@@ -363,8 +371,7 @@
tipc_cfg_append_tlv(buf, TIPC_TLV_NODE_INFO,
&node_info, sizeof(node_info));
}
-
- read_unlock_bh(&tipc_net_lock);
+ rcu_read_unlock();
return buf;
}
@@ -387,21 +394,19 @@
if (!tipc_own_addr)
return tipc_cfg_reply_none();
- read_lock_bh(&tipc_net_lock);
-
+ spin_lock_bh(&node_list_lock);
/* Get space for all unicast links + broadcast link */
- payload_size = TLV_SPACE(sizeof(link_info)) *
- (atomic_read(&tipc_num_links) + 1);
+ payload_size = TLV_SPACE((sizeof(link_info)) * (tipc_num_links + 1));
if (payload_size > 32768u) {
- read_unlock_bh(&tipc_net_lock);
+ spin_unlock_bh(&node_list_lock);
return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
" (too many links)");
}
+ spin_unlock_bh(&node_list_lock);
+
buf = tipc_cfg_reply_alloc(payload_size);
- if (!buf) {
- read_unlock_bh(&tipc_net_lock);
+ if (!buf)
return NULL;
- }
/* Add TLV for broadcast link */
link_info.dest = htonl(tipc_cluster_mask(tipc_own_addr));
@@ -410,7 +415,8 @@
tipc_cfg_append_tlv(buf, TIPC_TLV_LINK_INFO, &link_info, sizeof(link_info));
/* Add TLVs for any other links in scope */
- list_for_each_entry(n_ptr, &tipc_node_list, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
u32 i;
if (!tipc_in_scope(domain, n_ptr->addr))
@@ -427,7 +433,6 @@
}
tipc_node_unlock(n_ptr);
}
-
- read_unlock_bh(&tipc_net_lock);
+ rcu_read_unlock();
return buf;
}
diff --git a/net/tipc/node.h b/net/tipc/node.h
index 63e2e8e..7cbb8ce 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -2,7 +2,7 @@
* net/tipc/node.h: Include file for TIPC node management routines
*
* Copyright (c) 2000-2006, Ericsson AB
- * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * Copyright (c) 2005, 2010-2014, Wind River Systems
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -66,6 +66,7 @@
* @link_cnt: number of links to node
* @signature: node instance identifier
* @bclink: broadcast-related info
+ * @rcu: rcu struct for tipc_node
* @acked: sequence # of last outbound b'cast message acknowledged by node
* @last_in: sequence # of last in-sequence b'cast message received from node
* @last_sent: sequence # of last b'cast message sent by node
@@ -89,6 +90,7 @@
int working_links;
int block_setup;
u32 signature;
+ struct rcu_head rcu;
struct {
u32 acked;
u32 last_in;
@@ -107,7 +109,7 @@
struct tipc_node *tipc_node_find(u32 addr);
struct tipc_node *tipc_node_create(u32 addr);
-void tipc_node_delete(struct tipc_node *n_ptr);
+void tipc_node_stop(void);
void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
diff --git a/net/tipc/port.c b/net/tipc/port.c
index b742b26..5c14c78 100644
--- a/net/tipc/port.c
+++ b/net/tipc/port.c
@@ -1,7 +1,7 @@
/*
* net/tipc/port.c: TIPC port code
*
- * Copyright (c) 1992-2007, Ericsson AB
+ * Copyright (c) 1992-2007, 2014, Ericsson AB
* Copyright (c) 2004-2008, 2010-2013, Wind River Systems
* All rights reserved.
*
@@ -38,6 +38,7 @@
#include "config.h"
#include "port.h"
#include "name_table.h"
+#include "socket.h"
/* Connection management: */
#define PROBING_INTERVAL 3600000 /* [ms] => 1 h */
@@ -54,17 +55,6 @@
static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *, u32 err);
static void port_timeout(unsigned long ref);
-
-static u32 port_peernode(struct tipc_port *p_ptr)
-{
- return msg_destnode(&p_ptr->phdr);
-}
-
-static u32 port_peerport(struct tipc_port *p_ptr)
-{
- return msg_destport(&p_ptr->phdr);
-}
-
/**
* tipc_port_peer_msg - verify message was sent by connected port's peer
*
@@ -76,33 +66,32 @@
u32 peernode;
u32 orignode;
- if (msg_origport(msg) != port_peerport(p_ptr))
+ if (msg_origport(msg) != tipc_port_peerport(p_ptr))
return 0;
orignode = msg_orignode(msg);
- peernode = port_peernode(p_ptr);
+ peernode = tipc_port_peernode(p_ptr);
return (orignode == peernode) ||
(!orignode && (peernode == tipc_own_addr)) ||
(!peernode && (orignode == tipc_own_addr));
}
/**
- * tipc_multicast - send a multicast message to local and remote destinations
+ * tipc_port_mcast_xmit - send a multicast message to local and remote
+ * destinations
*/
-int tipc_multicast(u32 ref, struct tipc_name_seq const *seq,
- struct iovec const *msg_sect, unsigned int len)
+int tipc_port_mcast_xmit(struct tipc_port *oport,
+ struct tipc_name_seq const *seq,
+ struct iovec const *msg_sect,
+ unsigned int len)
{
struct tipc_msg *hdr;
struct sk_buff *buf;
struct sk_buff *ibuf = NULL;
struct tipc_port_list dports = {0, NULL, };
- struct tipc_port *oport = tipc_port_deref(ref);
int ext_targets;
int res;
- if (unlikely(!oport))
- return -EINVAL;
-
/* Create multicast message */
hdr = &oport->phdr;
msg_set_type(hdr, TIPC_MCAST_MSG);
@@ -131,7 +120,7 @@
return -ENOMEM;
}
}
- res = tipc_bclink_send_msg(buf);
+ res = tipc_bclink_xmit(buf);
if ((res < 0) && (dports.count != 0))
kfree_skb(ibuf);
} else {
@@ -140,7 +129,7 @@
if (res >= 0) {
if (ibuf)
- tipc_port_recv_mcast(ibuf, &dports);
+ tipc_port_mcast_rcv(ibuf, &dports);
} else {
tipc_port_list_free(&dports);
}
@@ -148,11 +137,11 @@
}
/**
- * tipc_port_recv_mcast - deliver multicast message to all destination ports
+ * tipc_port_mcast_rcv - deliver multicast message to all destination ports
*
* If there is no port list, perform a lookup to create one
*/
-void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp)
+void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp)
{
struct tipc_msg *msg;
struct tipc_port_list dports = {0, NULL, };
@@ -176,7 +165,7 @@
msg_set_destnode(msg, tipc_own_addr);
if (dp->count == 1) {
msg_set_destport(msg, dp->ports[0]);
- tipc_port_recv_msg(buf);
+ tipc_port_rcv(buf);
tipc_port_list_free(dp);
return;
}
@@ -191,7 +180,7 @@
if ((index == 0) && (cnt != 0))
item = item->next;
msg_set_destport(buf_msg(b), item->ports[index]);
- tipc_port_recv_msg(b);
+ tipc_port_rcv(b);
}
}
exit:
@@ -199,40 +188,32 @@
tipc_port_list_free(dp);
}
-/**
- * tipc_createport - create a generic TIPC port
- *
- * Returns pointer to (locked) TIPC port, or NULL if unable to create it
- */
-struct tipc_port *tipc_createport(struct sock *sk,
- u32 (*dispatcher)(struct tipc_port *,
- struct sk_buff *),
- void (*wakeup)(struct tipc_port *),
- const u32 importance)
+
+void tipc_port_wakeup(struct tipc_port *port)
{
- struct tipc_port *p_ptr;
+ tipc_sock_wakeup(tipc_port_to_sock(port));
+}
+
+/* tipc_port_init - intiate TIPC port and lock it
+ *
+ * Returns obtained reference if initialization is successful, zero otherwise
+ */
+u32 tipc_port_init(struct tipc_port *p_ptr,
+ const unsigned int importance)
+{
struct tipc_msg *msg;
u32 ref;
- p_ptr = kzalloc(sizeof(*p_ptr), GFP_ATOMIC);
- if (!p_ptr) {
- pr_warn("Port creation failed, no memory\n");
- return NULL;
- }
ref = tipc_ref_acquire(p_ptr, &p_ptr->lock);
if (!ref) {
- pr_warn("Port creation failed, ref. table exhausted\n");
- kfree(p_ptr);
- return NULL;
+ pr_warn("Port registration failed, ref. table exhausted\n");
+ return 0;
}
- p_ptr->sk = sk;
p_ptr->max_pkt = MAX_PKT_DEFAULT;
p_ptr->ref = ref;
INIT_LIST_HEAD(&p_ptr->wait_list);
INIT_LIST_HEAD(&p_ptr->subscription.nodesub_list);
- p_ptr->dispatcher = dispatcher;
- p_ptr->wakeup = wakeup;
k_init_timer(&p_ptr->timer, (Handler)port_timeout, ref);
INIT_LIST_HEAD(&p_ptr->publications);
INIT_LIST_HEAD(&p_ptr->port_list);
@@ -248,10 +229,10 @@
msg_set_origport(msg, ref);
list_add_tail(&p_ptr->port_list, &ports);
spin_unlock_bh(&tipc_port_list_lock);
- return p_ptr;
+ return ref;
}
-int tipc_deleteport(struct tipc_port *p_ptr)
+void tipc_port_destroy(struct tipc_port *p_ptr)
{
struct sk_buff *buf = NULL;
@@ -272,67 +253,7 @@
list_del(&p_ptr->wait_list);
spin_unlock_bh(&tipc_port_list_lock);
k_term_timer(&p_ptr->timer);
- kfree(p_ptr);
tipc_net_route_msg(buf);
- return 0;
-}
-
-static int port_unreliable(struct tipc_port *p_ptr)
-{
- return msg_src_droppable(&p_ptr->phdr);
-}
-
-int tipc_portunreliable(u32 ref, unsigned int *isunreliable)
-{
- struct tipc_port *p_ptr;
-
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return -EINVAL;
- *isunreliable = port_unreliable(p_ptr);
- tipc_port_unlock(p_ptr);
- return 0;
-}
-
-int tipc_set_portunreliable(u32 ref, unsigned int isunreliable)
-{
- struct tipc_port *p_ptr;
-
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return -EINVAL;
- msg_set_src_droppable(&p_ptr->phdr, (isunreliable != 0));
- tipc_port_unlock(p_ptr);
- return 0;
-}
-
-static int port_unreturnable(struct tipc_port *p_ptr)
-{
- return msg_dest_droppable(&p_ptr->phdr);
-}
-
-int tipc_portunreturnable(u32 ref, unsigned int *isunrejectable)
-{
- struct tipc_port *p_ptr;
-
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return -EINVAL;
- *isunrejectable = port_unreturnable(p_ptr);
- tipc_port_unlock(p_ptr);
- return 0;
-}
-
-int tipc_set_portunreturnable(u32 ref, unsigned int isunrejectable)
-{
- struct tipc_port *p_ptr;
-
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return -EINVAL;
- msg_set_dest_droppable(&p_ptr->phdr, (isunrejectable != 0));
- tipc_port_unlock(p_ptr);
- return 0;
}
/*
@@ -350,8 +271,8 @@
if (buf) {
msg = buf_msg(buf);
tipc_msg_init(msg, CONN_MANAGER, type, INT_H_SIZE,
- port_peernode(p_ptr));
- msg_set_destport(msg, port_peerport(p_ptr));
+ tipc_port_peernode(p_ptr));
+ msg_set_destport(msg, tipc_port_peerport(p_ptr));
msg_set_origport(msg, p_ptr->ref);
msg_set_msgcnt(msg, ack);
}
@@ -422,17 +343,17 @@
/* send returned message & dispose of rejected message */
src_node = msg_prevnode(msg);
if (in_own_node(src_node))
- tipc_port_recv_msg(rbuf);
+ tipc_port_rcv(rbuf);
else
- tipc_link_send(rbuf, src_node, msg_link_selector(rmsg));
+ tipc_link_xmit(rbuf, src_node, msg_link_selector(rmsg));
exit:
kfree_skb(buf);
return data_sz;
}
-int tipc_port_reject_sections(struct tipc_port *p_ptr, struct tipc_msg *hdr,
- struct iovec const *msg_sect, unsigned int len,
- int err)
+int tipc_port_iovec_reject(struct tipc_port *p_ptr, struct tipc_msg *hdr,
+ struct iovec const *msg_sect, unsigned int len,
+ int err)
{
struct sk_buff *buf;
int res;
@@ -519,7 +440,7 @@
return buf;
}
-void tipc_port_recv_proto_msg(struct sk_buff *buf)
+void tipc_port_proto_rcv(struct sk_buff *buf)
{
struct tipc_msg *msg = buf_msg(buf);
struct tipc_port *p_ptr;
@@ -547,13 +468,12 @@
/* Process protocol message sent by peer */
switch (msg_type(msg)) {
case CONN_ACK:
- wakeable = tipc_port_congested(p_ptr) && p_ptr->congested &&
- p_ptr->wakeup;
+ wakeable = tipc_port_congested(p_ptr) && p_ptr->congested;
p_ptr->acked += msg_msgcnt(msg);
if (!tipc_port_congested(p_ptr)) {
p_ptr->congested = 0;
if (wakeable)
- p_ptr->wakeup(p_ptr);
+ tipc_port_wakeup(p_ptr);
}
break;
case CONN_PROBE:
@@ -584,8 +504,8 @@
ret = tipc_snprintf(buf, len, "%-10u:", p_ptr->ref);
if (p_ptr->connected) {
- u32 dport = port_peerport(p_ptr);
- u32 destnode = port_peernode(p_ptr);
+ u32 dport = tipc_port_peerport(p_ptr);
+ u32 destnode = tipc_port_peernode(p_ptr);
ret += tipc_snprintf(buf + ret, len - ret,
" connected to <%u.%u.%u:%u>",
@@ -673,34 +593,6 @@
tipc_net_route_msg(buf);
}
-int tipc_portimportance(u32 ref, unsigned int *importance)
-{
- struct tipc_port *p_ptr;
-
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return -EINVAL;
- *importance = (unsigned int)msg_importance(&p_ptr->phdr);
- tipc_port_unlock(p_ptr);
- return 0;
-}
-
-int tipc_set_portimportance(u32 ref, unsigned int imp)
-{
- struct tipc_port *p_ptr;
-
- if (imp > TIPC_CRITICAL_IMPORTANCE)
- return -EINVAL;
-
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return -EINVAL;
- msg_set_importance(&p_ptr->phdr, (u32)imp);
- tipc_port_unlock(p_ptr);
- return 0;
-}
-
-
int tipc_publish(struct tipc_port *p_ptr, unsigned int scope,
struct tipc_name_seq const *seq)
{
@@ -760,7 +652,7 @@
return res;
}
-int tipc_connect(u32 ref, struct tipc_portid const *peer)
+int tipc_port_connect(u32 ref, struct tipc_portid const *peer)
{
struct tipc_port *p_ptr;
int res;
@@ -768,17 +660,17 @@
p_ptr = tipc_port_lock(ref);
if (!p_ptr)
return -EINVAL;
- res = __tipc_connect(ref, p_ptr, peer);
+ res = __tipc_port_connect(ref, p_ptr, peer);
tipc_port_unlock(p_ptr);
return res;
}
/*
- * __tipc_connect - connect to a remote peer
+ * __tipc_port_connect - connect to a remote peer
*
* Port must be locked.
*/
-int __tipc_connect(u32 ref, struct tipc_port *p_ptr,
+int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr,
struct tipc_portid const *peer)
{
struct tipc_msg *msg;
@@ -815,7 +707,7 @@
*
* Port must be locked.
*/
-int __tipc_disconnect(struct tipc_port *tp_ptr)
+int __tipc_port_disconnect(struct tipc_port *tp_ptr)
{
if (tp_ptr->connected) {
tp_ptr->connected = 0;
@@ -828,10 +720,10 @@
}
/*
- * tipc_disconnect(): Disconnect port form peer.
+ * tipc_port_disconnect(): Disconnect port form peer.
* This is a node local operation.
*/
-int tipc_disconnect(u32 ref)
+int tipc_port_disconnect(u32 ref)
{
struct tipc_port *p_ptr;
int res;
@@ -839,15 +731,15 @@
p_ptr = tipc_port_lock(ref);
if (!p_ptr)
return -EINVAL;
- res = __tipc_disconnect(p_ptr);
+ res = __tipc_port_disconnect(p_ptr);
tipc_port_unlock(p_ptr);
return res;
}
/*
- * tipc_shutdown(): Send a SHUTDOWN msg to peer and disconnect
+ * tipc_port_shutdown(): Send a SHUTDOWN msg to peer and disconnect
*/
-int tipc_shutdown(u32 ref)
+int tipc_port_shutdown(u32 ref)
{
struct tipc_port *p_ptr;
struct sk_buff *buf = NULL;
@@ -859,13 +751,13 @@
buf = port_build_peer_abort_msg(p_ptr, TIPC_CONN_SHUTDOWN);
tipc_port_unlock(p_ptr);
tipc_net_route_msg(buf);
- return tipc_disconnect(ref);
+ return tipc_port_disconnect(ref);
}
/**
- * tipc_port_recv_msg - receive message from lower layer and deliver to port user
+ * tipc_port_rcv - receive message from lower layer and deliver to port user
*/
-int tipc_port_recv_msg(struct sk_buff *buf)
+int tipc_port_rcv(struct sk_buff *buf)
{
struct tipc_port *p_ptr;
struct tipc_msg *msg = buf_msg(buf);
@@ -882,7 +774,7 @@
/* validate destination & pass to port, otherwise reject message */
p_ptr = tipc_port_lock(destport);
if (likely(p_ptr)) {
- err = p_ptr->dispatcher(p_ptr, buf);
+ err = tipc_sk_rcv(&tipc_port_to_sock(p_ptr)->sk, buf);
tipc_port_unlock(p_ptr);
if (likely(!err))
return dsz;
@@ -894,43 +786,43 @@
}
/*
- * tipc_port_recv_sections(): Concatenate and deliver sectioned
- * message for this node.
+ * tipc_port_iovec_rcv: Concatenate and deliver sectioned
+ * message for this node.
*/
-static int tipc_port_recv_sections(struct tipc_port *sender,
- struct iovec const *msg_sect,
- unsigned int len)
+static int tipc_port_iovec_rcv(struct tipc_port *sender,
+ struct iovec const *msg_sect,
+ unsigned int len)
{
struct sk_buff *buf;
int res;
res = tipc_msg_build(&sender->phdr, msg_sect, len, MAX_MSG_SIZE, &buf);
if (likely(buf))
- tipc_port_recv_msg(buf);
+ tipc_port_rcv(buf);
return res;
}
/**
* tipc_send - send message sections on connection
*/
-int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len)
+int tipc_send(struct tipc_port *p_ptr,
+ struct iovec const *msg_sect,
+ unsigned int len)
{
- struct tipc_port *p_ptr;
u32 destnode;
int res;
- p_ptr = tipc_port_deref(ref);
- if (!p_ptr || !p_ptr->connected)
+ if (!p_ptr->connected)
return -EINVAL;
p_ptr->congested = 1;
if (!tipc_port_congested(p_ptr)) {
- destnode = port_peernode(p_ptr);
+ destnode = tipc_port_peernode(p_ptr);
if (likely(!in_own_node(destnode)))
- res = tipc_link_send_sections_fast(p_ptr, msg_sect,
- len, destnode);
+ res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len,
+ destnode);
else
- res = tipc_port_recv_sections(p_ptr, msg_sect, len);
+ res = tipc_port_iovec_rcv(p_ptr, msg_sect, len);
if (likely(res != -ELINKCONG)) {
p_ptr->congested = 0;
@@ -939,7 +831,7 @@
return res;
}
}
- if (port_unreliable(p_ptr)) {
+ if (tipc_port_unreliable(p_ptr)) {
p_ptr->congested = 0;
return len;
}
@@ -949,17 +841,18 @@
/**
* tipc_send2name - send message sections to port name
*/
-int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain,
- struct iovec const *msg_sect, unsigned int len)
+int tipc_send2name(struct tipc_port *p_ptr,
+ struct tipc_name const *name,
+ unsigned int domain,
+ struct iovec const *msg_sect,
+ unsigned int len)
{
- struct tipc_port *p_ptr;
struct tipc_msg *msg;
u32 destnode = domain;
u32 destport;
int res;
- p_ptr = tipc_port_deref(ref);
- if (!p_ptr || p_ptr->connected)
+ if (p_ptr->connected)
return -EINVAL;
msg = &p_ptr->phdr;
@@ -974,39 +867,39 @@
if (likely(destport || destnode)) {
if (likely(in_own_node(destnode)))
- res = tipc_port_recv_sections(p_ptr, msg_sect, len);
+ res = tipc_port_iovec_rcv(p_ptr, msg_sect, len);
else if (tipc_own_addr)
- res = tipc_link_send_sections_fast(p_ptr, msg_sect,
- len, destnode);
+ res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len,
+ destnode);
else
- res = tipc_port_reject_sections(p_ptr, msg, msg_sect,
- len, TIPC_ERR_NO_NODE);
+ res = tipc_port_iovec_reject(p_ptr, msg, msg_sect,
+ len, TIPC_ERR_NO_NODE);
if (likely(res != -ELINKCONG)) {
if (res > 0)
p_ptr->sent++;
return res;
}
- if (port_unreliable(p_ptr)) {
+ if (tipc_port_unreliable(p_ptr))
return len;
- }
+
return -ELINKCONG;
}
- return tipc_port_reject_sections(p_ptr, msg, msg_sect, len,
- TIPC_ERR_NO_NAME);
+ return tipc_port_iovec_reject(p_ptr, msg, msg_sect, len,
+ TIPC_ERR_NO_NAME);
}
/**
* tipc_send2port - send message sections to port identity
*/
-int tipc_send2port(u32 ref, struct tipc_portid const *dest,
- struct iovec const *msg_sect, unsigned int len)
+int tipc_send2port(struct tipc_port *p_ptr,
+ struct tipc_portid const *dest,
+ struct iovec const *msg_sect,
+ unsigned int len)
{
- struct tipc_port *p_ptr;
struct tipc_msg *msg;
int res;
- p_ptr = tipc_port_deref(ref);
- if (!p_ptr || p_ptr->connected)
+ if (p_ptr->connected)
return -EINVAL;
msg = &p_ptr->phdr;
@@ -1017,20 +910,20 @@
msg_set_hdr_sz(msg, BASIC_H_SIZE);
if (in_own_node(dest->node))
- res = tipc_port_recv_sections(p_ptr, msg_sect, len);
+ res = tipc_port_iovec_rcv(p_ptr, msg_sect, len);
else if (tipc_own_addr)
- res = tipc_link_send_sections_fast(p_ptr, msg_sect, len,
- dest->node);
+ res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len,
+ dest->node);
else
- res = tipc_port_reject_sections(p_ptr, msg, msg_sect, len,
+ res = tipc_port_iovec_reject(p_ptr, msg, msg_sect, len,
TIPC_ERR_NO_NODE);
if (likely(res != -ELINKCONG)) {
if (res > 0)
p_ptr->sent++;
return res;
}
- if (port_unreliable(p_ptr)) {
+ if (tipc_port_unreliable(p_ptr))
return len;
- }
+
return -ELINKCONG;
}
diff --git a/net/tipc/port.h b/net/tipc/port.h
index 34f12bd..a003973 100644
--- a/net/tipc/port.h
+++ b/net/tipc/port.h
@@ -1,7 +1,7 @@
/*
* net/tipc/port.h: Include file for TIPC port code
*
- * Copyright (c) 1994-2007, Ericsson AB
+ * Copyright (c) 1994-2007, 2014, Ericsson AB
* Copyright (c) 2004-2007, 2010-2013, Wind River Systems
* All rights reserved.
*
@@ -48,7 +48,6 @@
/**
* struct tipc_port - TIPC port structure
- * @sk: pointer to socket handle
* @lock: pointer to spinlock for controlling access to port
* @connected: non-zero if port is currently connected to a peer port
* @conn_type: TIPC type used when connection was established
@@ -60,8 +59,6 @@
* @ref: unique reference to port in TIPC object registry
* @phdr: preformatted message header used when sending messages
* @port_list: adjacent ports in TIPC's global list of ports
- * @dispatcher: ptr to routine which handles received messages
- * @wakeup: ptr to routine to call when port is no longer congested
* @wait_list: adjacent ports in list of ports waiting on link congestion
* @waiting_pkts:
* @sent: # of non-empty messages sent by port
@@ -74,7 +71,6 @@
* @subscription: "node down" subscription used to terminate failed connections
*/
struct tipc_port {
- struct sock *sk;
spinlock_t *lock;
int connected;
u32 conn_type;
@@ -86,8 +82,6 @@
u32 ref;
struct tipc_msg phdr;
struct list_head port_list;
- u32 (*dispatcher)(struct tipc_port *, struct sk_buff *);
- void (*wakeup)(struct tipc_port *);
struct list_head wait_list;
u32 waiting_pkts;
u32 sent;
@@ -106,68 +100,71 @@
/*
* TIPC port manipulation routines
*/
-struct tipc_port *tipc_createport(struct sock *sk,
- u32 (*dispatcher)(struct tipc_port *,
- struct sk_buff *),
- void (*wakeup)(struct tipc_port *),
- const u32 importance);
+u32 tipc_port_init(struct tipc_port *p_ptr,
+ const unsigned int importance);
int tipc_reject_msg(struct sk_buff *buf, u32 err);
void tipc_acknowledge(u32 port_ref, u32 ack);
-int tipc_deleteport(struct tipc_port *p_ptr);
-
-int tipc_portimportance(u32 portref, unsigned int *importance);
-int tipc_set_portimportance(u32 portref, unsigned int importance);
-
-int tipc_portunreliable(u32 portref, unsigned int *isunreliable);
-int tipc_set_portunreliable(u32 portref, unsigned int isunreliable);
-
-int tipc_portunreturnable(u32 portref, unsigned int *isunreturnable);
-int tipc_set_portunreturnable(u32 portref, unsigned int isunreturnable);
+void tipc_port_destroy(struct tipc_port *p_ptr);
int tipc_publish(struct tipc_port *p_ptr, unsigned int scope,
struct tipc_name_seq const *name_seq);
+
int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope,
struct tipc_name_seq const *name_seq);
-int tipc_connect(u32 portref, struct tipc_portid const *port);
+int tipc_port_connect(u32 portref, struct tipc_portid const *port);
-int tipc_disconnect(u32 portref);
+int tipc_port_disconnect(u32 portref);
-int tipc_shutdown(u32 ref);
+int tipc_port_shutdown(u32 ref);
+void tipc_port_wakeup(struct tipc_port *port);
/*
* The following routines require that the port be locked on entry
*/
-int __tipc_disconnect(struct tipc_port *tp_ptr);
-int __tipc_connect(u32 ref, struct tipc_port *p_ptr,
+int __tipc_port_disconnect(struct tipc_port *tp_ptr);
+int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr,
struct tipc_portid const *peer);
int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg);
/*
* TIPC messaging routines
*/
-int tipc_port_recv_msg(struct sk_buff *buf);
-int tipc_send(u32 portref, struct iovec const *msg_sect, unsigned int len);
+int tipc_port_rcv(struct sk_buff *buf);
-int tipc_send2name(u32 portref, struct tipc_name const *name, u32 domain,
- struct iovec const *msg_sect, unsigned int len);
+int tipc_send(struct tipc_port *port,
+ struct iovec const *msg_sect,
+ unsigned int len);
-int tipc_send2port(u32 portref, struct tipc_portid const *dest,
- struct iovec const *msg_sect, unsigned int len);
+int tipc_send2name(struct tipc_port *port,
+ struct tipc_name const *name,
+ u32 domain,
+ struct iovec const *msg_sect,
+ unsigned int len);
-int tipc_multicast(u32 portref, struct tipc_name_seq const *seq,
- struct iovec const *msg, unsigned int len);
+int tipc_send2port(struct tipc_port *port,
+ struct tipc_portid const *dest,
+ struct iovec const *msg_sect,
+ unsigned int len);
-int tipc_port_reject_sections(struct tipc_port *p_ptr, struct tipc_msg *hdr,
- struct iovec const *msg_sect, unsigned int len,
- int err);
+int tipc_port_mcast_xmit(struct tipc_port *port,
+ struct tipc_name_seq const *seq,
+ struct iovec const *msg,
+ unsigned int len);
+
+int tipc_port_iovec_reject(struct tipc_port *p_ptr,
+ struct tipc_msg *hdr,
+ struct iovec const *msg_sect,
+ unsigned int len,
+ int err);
+
struct sk_buff *tipc_port_get_ports(void);
-void tipc_port_recv_proto_msg(struct sk_buff *buf);
-void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp);
+void tipc_port_proto_rcv(struct sk_buff *buf);
+void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp);
void tipc_port_reinit(void);
/**
@@ -188,14 +185,53 @@
spin_unlock_bh(p_ptr->lock);
}
-static inline struct tipc_port *tipc_port_deref(u32 ref)
-{
- return (struct tipc_port *)tipc_ref_deref(ref);
-}
-
static inline int tipc_port_congested(struct tipc_port *p_ptr)
{
return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2);
}
+
+static inline u32 tipc_port_peernode(struct tipc_port *p_ptr)
+{
+ return msg_destnode(&p_ptr->phdr);
+}
+
+static inline u32 tipc_port_peerport(struct tipc_port *p_ptr)
+{
+ return msg_destport(&p_ptr->phdr);
+}
+
+static inline bool tipc_port_unreliable(struct tipc_port *port)
+{
+ return msg_src_droppable(&port->phdr) != 0;
+}
+
+static inline void tipc_port_set_unreliable(struct tipc_port *port,
+ bool unreliable)
+{
+ msg_set_src_droppable(&port->phdr, unreliable ? 1 : 0);
+}
+
+static inline bool tipc_port_unreturnable(struct tipc_port *port)
+{
+ return msg_dest_droppable(&port->phdr) != 0;
+}
+
+static inline void tipc_port_set_unreturnable(struct tipc_port *port,
+ bool unreturnable)
+{
+ msg_set_dest_droppable(&port->phdr, unreturnable ? 1 : 0);
+}
+
+
+static inline int tipc_port_importance(struct tipc_port *port)
+{
+ return msg_importance(&port->phdr);
+}
+
+static inline void tipc_port_set_importance(struct tipc_port *port, int imp)
+{
+ msg_set_importance(&port->phdr, (u32)imp);
+}
+
#endif
diff --git a/net/tipc/ref.c b/net/tipc/ref.c
index 2a2a938..3d4ecd7 100644
--- a/net/tipc/ref.c
+++ b/net/tipc/ref.c
@@ -89,7 +89,7 @@
static struct ref_table tipc_ref_table;
-static DEFINE_RWLOCK(ref_table_lock);
+static DEFINE_SPINLOCK(ref_table_lock);
/**
* tipc_ref_table_init - create reference table for objects
@@ -126,9 +126,6 @@
*/
void tipc_ref_table_stop(void)
{
- if (!tipc_ref_table.entries)
- return;
-
vfree(tipc_ref_table.entries);
tipc_ref_table.entries = NULL;
}
@@ -162,7 +159,7 @@
}
/* take a free entry, if available; otherwise initialize a new entry */
- write_lock_bh(&ref_table_lock);
+ spin_lock_bh(&ref_table_lock);
if (tipc_ref_table.first_free) {
index = tipc_ref_table.first_free;
entry = &(tipc_ref_table.entries[index]);
@@ -178,7 +175,7 @@
} else {
ref = 0;
}
- write_unlock_bh(&ref_table_lock);
+ spin_unlock_bh(&ref_table_lock);
/*
* Grab the lock so no one else can modify this entry
@@ -219,7 +216,7 @@
index = ref & index_mask;
entry = &(tipc_ref_table.entries[index]);
- write_lock_bh(&ref_table_lock);
+ spin_lock_bh(&ref_table_lock);
if (!entry->object) {
pr_err("Attempt to discard ref. to non-existent obj\n");
@@ -245,7 +242,7 @@
tipc_ref_table.last_free = index;
exit:
- write_unlock_bh(&ref_table_lock);
+ spin_unlock_bh(&ref_table_lock);
}
/**
@@ -267,20 +264,3 @@
}
return NULL;
}
-
-
-/**
- * tipc_ref_deref - return pointer referenced object (without locking it)
- */
-void *tipc_ref_deref(u32 ref)
-{
- if (likely(tipc_ref_table.entries)) {
- struct reference *entry;
-
- entry = &tipc_ref_table.entries[ref &
- tipc_ref_table.index_mask];
- if (likely(entry->ref == ref))
- return entry->object;
- }
- return NULL;
-}
diff --git a/net/tipc/ref.h b/net/tipc/ref.h
index 5bc8e7a..d01aa1d 100644
--- a/net/tipc/ref.h
+++ b/net/tipc/ref.h
@@ -44,6 +44,5 @@
void tipc_ref_discard(u32 ref);
void *tipc_ref_lock(u32 ref);
-void *tipc_ref_deref(u32 ref);
#endif
diff --git a/net/tipc/server.c b/net/tipc/server.c
index b635ca3..646a930 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -87,7 +87,6 @@
static void tipc_conn_kref_release(struct kref *kref)
{
struct tipc_conn *con = container_of(kref, struct tipc_conn, kref);
- struct tipc_server *s = con->server;
if (con->sock) {
tipc_sock_release_local(con->sock);
@@ -95,10 +94,6 @@
}
tipc_clean_outqueues(con);
-
- if (con->conid)
- s->tipc_conn_shutdown(con->conid, con->usr_data);
-
kfree(con);
}
@@ -181,6 +176,9 @@
struct tipc_server *s = con->server;
if (test_and_clear_bit(CF_CONNECTED, &con->flags)) {
+ if (con->conid)
+ s->tipc_conn_shutdown(con->conid, con->usr_data);
+
spin_lock_bh(&s->idr_lock);
idr_remove(&s->conn_idr, con->conid);
s->idr_in_use--;
@@ -429,10 +427,12 @@
list_add_tail(&e->list, &con->outqueue);
spin_unlock_bh(&con->outqueue_lock);
- if (test_bit(CF_CONNECTED, &con->flags))
+ if (test_bit(CF_CONNECTED, &con->flags)) {
if (!queue_work(s->send_wq, &con->swork))
conn_put(con);
-
+ } else {
+ conn_put(con);
+ }
return 0;
}
@@ -573,7 +573,6 @@
kmem_cache_destroy(s->rcvbuf_cache);
return ret;
}
- s->enabled = 1;
return ret;
}
@@ -583,10 +582,6 @@
int total = 0;
int id;
- if (!s->enabled)
- return;
-
- s->enabled = 0;
spin_lock_bh(&s->idr_lock);
for (id = 0; total < s->idr_in_use; id++) {
con = idr_find(&s->conn_idr, id);
diff --git a/net/tipc/server.h b/net/tipc/server.h
index 98b23f2..be817b0 100644
--- a/net/tipc/server.h
+++ b/net/tipc/server.h
@@ -56,7 +56,6 @@
* @name: server name
* @imp: message importance
* @type: socket type
- * @enabled: identify whether server is launched or not
*/
struct tipc_server {
struct idr conn_idr;
@@ -74,7 +73,6 @@
const char name[TIPC_SERVER_NAME_LEN];
int imp;
int type;
- int enabled;
};
int tipc_conn_sendmsg(struct tipc_server *s, int conid,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index aab4948..29b7f26 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1,7 +1,7 @@
/*
* net/tipc/socket.c: TIPC socket API
*
- * Copyright (c) 2001-2007, 2012 Ericsson AB
+ * Copyright (c) 2001-2007, 2012-2014, Ericsson AB
* Copyright (c) 2004-2008, 2010-2013, Wind River Systems
* All rights reserved.
*
@@ -38,30 +38,17 @@
#include "port.h"
#include <linux/export.h>
-#include <net/sock.h>
#define SS_LISTENING -1 /* socket is listening */
#define SS_READY -2 /* socket is connectionless */
#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */
-struct tipc_sock {
- struct sock sk;
- struct tipc_port *p;
- struct tipc_portid peer_name;
- unsigned int conn_timeout;
-};
-
-#define tipc_sk(sk) ((struct tipc_sock *)(sk))
-#define tipc_sk_port(sk) (tipc_sk(sk)->p)
-
static int backlog_rcv(struct sock *sk, struct sk_buff *skb);
-static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf);
-static void wakeupdispatch(struct tipc_port *tport);
static void tipc_data_ready(struct sock *sk, int len);
static void tipc_write_space(struct sock *sk);
-static int release(struct socket *sock);
-static int accept(struct socket *sock, struct socket *new_sock, int flags);
+static int tipc_release(struct socket *sock);
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
static const struct proto_ops packet_ops;
static const struct proto_ops stream_ops;
@@ -70,8 +57,6 @@
static struct proto tipc_proto;
static struct proto tipc_proto_kern;
-static int sockets_enabled;
-
/*
* Revised TIPC socket locking policy:
*
@@ -117,6 +102,8 @@
* - port reference
*/
+#include "socket.h"
+
/**
* advance_rx_queue - discard first buffer in socket receive queue
*
@@ -152,13 +139,15 @@
*
* Returns 0 on success, errno otherwise
*/
-static int tipc_sk_create(struct net *net, struct socket *sock, int protocol,
- int kern)
+static int tipc_sk_create(struct net *net, struct socket *sock,
+ int protocol, int kern)
{
const struct proto_ops *ops;
socket_state state;
struct sock *sk;
- struct tipc_port *tp_ptr;
+ struct tipc_sock *tsk;
+ struct tipc_port *port;
+ u32 ref;
/* Validate arguments */
if (unlikely(protocol != 0))
@@ -191,10 +180,12 @@
if (sk == NULL)
return -ENOMEM;
- /* Allocate TIPC port for socket to use */
- tp_ptr = tipc_createport(sk, &dispatch, &wakeupdispatch,
- TIPC_LOW_IMPORTANCE);
- if (unlikely(!tp_ptr)) {
+ tsk = tipc_sk(sk);
+ port = &tsk->port;
+
+ ref = tipc_port_init(port, TIPC_LOW_IMPORTANCE);
+ if (!ref) {
+ pr_warn("Socket registration failed, ref. table exhausted\n");
sk_free(sk);
return -ENOMEM;
}
@@ -208,17 +199,14 @@
sk->sk_rcvbuf = sysctl_tipc_rmem[1];
sk->sk_data_ready = tipc_data_ready;
sk->sk_write_space = tipc_write_space;
- tipc_sk(sk)->p = tp_ptr;
tipc_sk(sk)->conn_timeout = CONN_TIMEOUT_DEFAULT;
-
- spin_unlock_bh(tp_ptr->lock);
+ tipc_port_unlock(port);
if (sock->state == SS_READY) {
- tipc_set_portunreturnable(tp_ptr->ref, 1);
+ tipc_port_set_unreturnable(port, true);
if (sock->type == SOCK_DGRAM)
- tipc_set_portunreliable(tp_ptr->ref, 1);
+ tipc_port_set_unreliable(port, true);
}
-
return 0;
}
@@ -256,7 +244,7 @@
*/
void tipc_sock_release_local(struct socket *sock)
{
- release(sock);
+ tipc_release(sock);
sock->ops = NULL;
sock_release(sock);
}
@@ -282,7 +270,7 @@
if (ret < 0)
return ret;
- ret = accept(sock, *newsock, flags);
+ ret = tipc_accept(sock, *newsock, flags);
if (ret < 0) {
sock_release(*newsock);
return ret;
@@ -292,7 +280,7 @@
}
/**
- * release - destroy a TIPC socket
+ * tipc_release - destroy a TIPC socket
* @sock: socket to destroy
*
* This routine cleans up any messages that are still queued on the socket.
@@ -307,10 +295,11 @@
*
* Returns 0 on success, errno otherwise
*/
-static int release(struct socket *sock)
+static int tipc_release(struct socket *sock)
{
struct sock *sk = sock->sk;
- struct tipc_port *tport;
+ struct tipc_sock *tsk;
+ struct tipc_port *port;
struct sk_buff *buf;
int res;
@@ -321,7 +310,8 @@
if (sk == NULL)
return 0;
- tport = tipc_sk_port(sk);
+ tsk = tipc_sk(sk);
+ port = &tsk->port;
lock_sock(sk);
/*
@@ -338,17 +328,16 @@
if ((sock->state == SS_CONNECTING) ||
(sock->state == SS_CONNECTED)) {
sock->state = SS_DISCONNECTING;
- tipc_disconnect(tport->ref);
+ tipc_port_disconnect(port->ref);
}
tipc_reject_msg(buf, TIPC_ERR_NO_PORT);
}
}
- /*
- * Delete TIPC port; this ensures no more messages are queued
- * (also disconnects an active connection & sends a 'FIN-' to peer)
+ /* Destroy TIPC port; also disconnects an active connection and
+ * sends a 'FIN-' to peer.
*/
- res = tipc_deleteport(tport);
+ tipc_port_destroy(port);
/* Discard any remaining (connection-based) messages in receive queue */
__skb_queue_purge(&sk->sk_receive_queue);
@@ -364,7 +353,7 @@
}
/**
- * bind - associate or disassocate TIPC name(s) with a socket
+ * tipc_bind - associate or disassocate TIPC name(s) with a socket
* @sock: socket structure
* @uaddr: socket address describing name(s) and desired operation
* @uaddr_len: size of socket address data structure
@@ -378,16 +367,17 @@
* NOTE: This routine doesn't need to take the socket lock since it doesn't
* access any non-constant socket information.
*/
-static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len)
+static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
+ int uaddr_len)
{
struct sock *sk = sock->sk;
struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
- struct tipc_port *tport = tipc_sk_port(sock->sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
int res = -EINVAL;
lock_sock(sk);
if (unlikely(!uaddr_len)) {
- res = tipc_withdraw(tport, 0, NULL);
+ res = tipc_withdraw(&tsk->port, 0, NULL);
goto exit;
}
@@ -415,15 +405,15 @@
}
res = (addr->scope > 0) ?
- tipc_publish(tport, addr->scope, &addr->addr.nameseq) :
- tipc_withdraw(tport, -addr->scope, &addr->addr.nameseq);
+ tipc_publish(&tsk->port, addr->scope, &addr->addr.nameseq) :
+ tipc_withdraw(&tsk->port, -addr->scope, &addr->addr.nameseq);
exit:
release_sock(sk);
return res;
}
/**
- * get_name - get port ID of socket or peer socket
+ * tipc_getname - get port ID of socket or peer socket
* @sock: socket structure
* @uaddr: area for returned socket address
* @uaddr_len: area for returned length of socket address
@@ -435,21 +425,21 @@
* accesses socket information that is unchanging (or which changes in
* a completely predictable manner).
*/
-static int get_name(struct socket *sock, struct sockaddr *uaddr,
- int *uaddr_len, int peer)
+static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
+ int *uaddr_len, int peer)
{
struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
- struct tipc_sock *tsock = tipc_sk(sock->sk);
+ struct tipc_sock *tsk = tipc_sk(sock->sk);
memset(addr, 0, sizeof(*addr));
if (peer) {
if ((sock->state != SS_CONNECTED) &&
((peer != 2) || (sock->state != SS_DISCONNECTING)))
return -ENOTCONN;
- addr->addr.id.ref = tsock->peer_name.ref;
- addr->addr.id.node = tsock->peer_name.node;
+ addr->addr.id.ref = tipc_port_peerport(&tsk->port);
+ addr->addr.id.node = tipc_port_peernode(&tsk->port);
} else {
- addr->addr.id.ref = tsock->p->ref;
+ addr->addr.id.ref = tsk->port.ref;
addr->addr.id.node = tipc_own_addr;
}
@@ -463,7 +453,7 @@
}
/**
- * poll - read and possibly block on pollmask
+ * tipc_poll - read and possibly block on pollmask
* @file: file structure associated with the socket
* @sock: socket for which to calculate the poll bits
* @wait: ???
@@ -502,22 +492,23 @@
* imply that the operation will succeed, merely that it should be performed
* and will not block.
*/
-static unsigned int poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static unsigned int tipc_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
{
struct sock *sk = sock->sk;
+ struct tipc_sock *tsk = tipc_sk(sk);
u32 mask = 0;
sock_poll_wait(file, sk_sleep(sk), wait);
switch ((int)sock->state) {
case SS_UNCONNECTED:
- if (!tipc_sk_port(sk)->congested)
+ if (!tsk->port.congested)
mask |= POLLOUT;
break;
case SS_READY:
case SS_CONNECTED:
- if (!tipc_sk_port(sk)->congested)
+ if (!tsk->port.congested)
mask |= POLLOUT;
/* fall thru' */
case SS_CONNECTING:
@@ -567,7 +558,7 @@
static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p)
{
struct sock *sk = sock->sk;
- struct tipc_port *tport = tipc_sk_port(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
DEFINE_WAIT(wait);
int done;
@@ -583,14 +574,15 @@
return sock_intr_errno(*timeo_p);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- done = sk_wait_event(sk, timeo_p, !tport->congested);
+ done = sk_wait_event(sk, timeo_p, !tsk->port.congested);
finish_wait(sk_sleep(sk), &wait);
} while (!done);
return 0;
}
+
/**
- * send_msg - send message in connectionless manner
+ * tipc_sendmsg - send message in connectionless manner
* @iocb: if NULL, indicates that socket lock is already held
* @sock: socket structure
* @m: message to send
@@ -603,11 +595,12 @@
*
* Returns the number of bytes sent on success, or errno otherwise
*/
-static int send_msg(struct kiocb *iocb, struct socket *sock,
- struct msghdr *m, size_t total_len)
+static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t total_len)
{
struct sock *sk = sock->sk;
- struct tipc_port *tport = tipc_sk_port(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_port *port = &tsk->port;
DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
int needs_conn;
long timeo;
@@ -634,13 +627,13 @@
res = -EISCONN;
goto exit;
}
- if (tport->published) {
+ if (tsk->port.published) {
res = -EOPNOTSUPP;
goto exit;
}
if (dest->addrtype == TIPC_ADDR_NAME) {
- tport->conn_type = dest->addr.name.name.type;
- tport->conn_instance = dest->addr.name.name.instance;
+ tsk->port.conn_type = dest->addr.name.name.type;
+ tsk->port.conn_instance = dest->addr.name.name.instance;
}
/* Abort any pending connection attempts (very unlikely) */
@@ -653,13 +646,13 @@
res = dest_name_check(dest, m);
if (res)
break;
- res = tipc_send2name(tport->ref,
+ res = tipc_send2name(port,
&dest->addr.name.name,
dest->addr.name.domain,
m->msg_iov,
total_len);
} else if (dest->addrtype == TIPC_ADDR_ID) {
- res = tipc_send2port(tport->ref,
+ res = tipc_send2port(port,
&dest->addr.id,
m->msg_iov,
total_len);
@@ -671,10 +664,10 @@
res = dest_name_check(dest, m);
if (res)
break;
- res = tipc_multicast(tport->ref,
- &dest->addr.nameseq,
- m->msg_iov,
- total_len);
+ res = tipc_port_mcast_xmit(port,
+ &dest->addr.nameseq,
+ m->msg_iov,
+ total_len);
}
if (likely(res != -ELINKCONG)) {
if (needs_conn && (res >= 0))
@@ -695,7 +688,8 @@
static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p)
{
struct sock *sk = sock->sk;
- struct tipc_port *tport = tipc_sk_port(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_port *port = &tsk->port;
DEFINE_WAIT(wait);
int done;
@@ -714,14 +708,14 @@
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
done = sk_wait_event(sk, timeo_p,
- (!tport->congested || !tport->connected));
+ (!port->congested || !port->connected));
finish_wait(sk_sleep(sk), &wait);
} while (!done);
return 0;
}
/**
- * send_packet - send a connection-oriented message
+ * tipc_send_packet - send a connection-oriented message
* @iocb: if NULL, indicates that socket lock is already held
* @sock: socket structure
* @m: message to send
@@ -731,18 +725,18 @@
*
* Returns the number of bytes sent on success, or errno otherwise
*/
-static int send_packet(struct kiocb *iocb, struct socket *sock,
- struct msghdr *m, size_t total_len)
+static int tipc_send_packet(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t total_len)
{
struct sock *sk = sock->sk;
- struct tipc_port *tport = tipc_sk_port(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
int res = -EINVAL;
long timeo;
/* Handle implied connection establishment */
if (unlikely(dest))
- return send_msg(iocb, sock, m, total_len);
+ return tipc_sendmsg(iocb, sock, m, total_len);
if (total_len > TIPC_MAX_USER_MSG_SIZE)
return -EMSGSIZE;
@@ -760,7 +754,7 @@
timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
do {
- res = tipc_send(tport->ref, m->msg_iov, total_len);
+ res = tipc_send(&tsk->port, m->msg_iov, total_len);
if (likely(res != -ELINKCONG))
break;
res = tipc_wait_for_sndpkt(sock, &timeo);
@@ -774,7 +768,7 @@
}
/**
- * send_stream - send stream-oriented data
+ * tipc_send_stream - send stream-oriented data
* @iocb: (unused)
* @sock: socket structure
* @m: data to send
@@ -785,11 +779,11 @@
* Returns the number of bytes sent on success (or partial success),
* or errno if no data sent
*/
-static int send_stream(struct kiocb *iocb, struct socket *sock,
- struct msghdr *m, size_t total_len)
+static int tipc_send_stream(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t total_len)
{
struct sock *sk = sock->sk;
- struct tipc_port *tport = tipc_sk_port(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
struct msghdr my_msg;
struct iovec my_iov;
struct iovec *curr_iov;
@@ -806,7 +800,7 @@
/* Handle special cases where there is no connection */
if (unlikely(sock->state != SS_CONNECTED)) {
if (sock->state == SS_UNCONNECTED)
- res = send_packet(NULL, sock, m, total_len);
+ res = tipc_send_packet(NULL, sock, m, total_len);
else
res = sock->state == SS_DISCONNECTING ? -EPIPE : -ENOTCONN;
goto exit;
@@ -837,21 +831,22 @@
my_msg.msg_name = NULL;
bytes_sent = 0;
- hdr_size = msg_hdr_sz(&tport->phdr);
+ hdr_size = msg_hdr_sz(&tsk->port.phdr);
while (curr_iovlen--) {
curr_start = curr_iov->iov_base;
curr_left = curr_iov->iov_len;
while (curr_left) {
- bytes_to_send = tport->max_pkt - hdr_size;
+ bytes_to_send = tsk->port.max_pkt - hdr_size;
if (bytes_to_send > TIPC_MAX_USER_MSG_SIZE)
bytes_to_send = TIPC_MAX_USER_MSG_SIZE;
if (curr_left < bytes_to_send)
bytes_to_send = curr_left;
my_iov.iov_base = curr_start;
my_iov.iov_len = bytes_to_send;
- res = send_packet(NULL, sock, &my_msg, bytes_to_send);
+ res = tipc_send_packet(NULL, sock, &my_msg,
+ bytes_to_send);
if (res < 0) {
if (bytes_sent)
res = bytes_sent;
@@ -872,27 +867,25 @@
/**
* auto_connect - complete connection setup to a remote port
- * @sock: socket structure
+ * @tsk: tipc socket structure
* @msg: peer's response message
*
* Returns 0 on success, errno otherwise
*/
-static int auto_connect(struct socket *sock, struct tipc_msg *msg)
+static int auto_connect(struct tipc_sock *tsk, struct tipc_msg *msg)
{
- struct tipc_sock *tsock = tipc_sk(sock->sk);
- struct tipc_port *p_ptr;
+ struct tipc_port *port = &tsk->port;
+ struct socket *sock = tsk->sk.sk_socket;
+ struct tipc_portid peer;
- tsock->peer_name.ref = msg_origport(msg);
- tsock->peer_name.node = msg_orignode(msg);
- p_ptr = tipc_port_deref(tsock->p->ref);
- if (!p_ptr)
- return -EINVAL;
+ peer.ref = msg_origport(msg);
+ peer.node = msg_orignode(msg);
- __tipc_connect(tsock->p->ref, p_ptr, &tsock->peer_name);
+ __tipc_port_connect(port->ref, port, &peer);
if (msg_importance(msg) > TIPC_CRITICAL_IMPORTANCE)
return -EINVAL;
- msg_set_importance(&p_ptr->phdr, (u32)msg_importance(msg));
+ msg_set_importance(&port->phdr, (u32)msg_importance(msg));
sock->state = SS_CONNECTED;
return 0;
}
@@ -999,7 +992,7 @@
for (;;) {
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- if (skb_queue_empty(&sk->sk_receive_queue)) {
+ if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
if (sock->state == SS_DISCONNECTING) {
err = -ENOTCONN;
break;
@@ -1023,7 +1016,7 @@
}
/**
- * recv_msg - receive packet-oriented message
+ * tipc_recvmsg - receive packet-oriented message
* @iocb: (unused)
* @m: descriptor for message info
* @buf_len: total size of user buffer area
@@ -1034,11 +1027,12 @@
*
* Returns size of returned message data, errno otherwise
*/
-static int recv_msg(struct kiocb *iocb, struct socket *sock,
- struct msghdr *m, size_t buf_len, int flags)
+static int tipc_recvmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t buf_len, int flags)
{
struct sock *sk = sock->sk;
- struct tipc_port *tport = tipc_sk_port(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_port *port = &tsk->port;
struct sk_buff *buf;
struct tipc_msg *msg;
long timeo;
@@ -1081,7 +1075,7 @@
set_orig_addr(m, msg);
/* Capture ancillary data (optional) */
- res = anc_data_recv(m, msg, tport);
+ res = anc_data_recv(m, msg, port);
if (res)
goto exit;
@@ -1107,8 +1101,8 @@
/* Consume received message (optional) */
if (likely(!(flags & MSG_PEEK))) {
if ((sock->state != SS_READY) &&
- (++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN))
- tipc_acknowledge(tport->ref, tport->conn_unacked);
+ (++port->conn_unacked >= TIPC_FLOW_CONTROL_WIN))
+ tipc_acknowledge(port->ref, port->conn_unacked);
advance_rx_queue(sk);
}
exit:
@@ -1117,7 +1111,7 @@
}
/**
- * recv_stream - receive stream-oriented data
+ * tipc_recv_stream - receive stream-oriented data
* @iocb: (unused)
* @m: descriptor for message info
* @buf_len: total size of user buffer area
@@ -1128,11 +1122,12 @@
*
* Returns size of returned message data, errno otherwise
*/
-static int recv_stream(struct kiocb *iocb, struct socket *sock,
- struct msghdr *m, size_t buf_len, int flags)
+static int tipc_recv_stream(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t buf_len, int flags)
{
struct sock *sk = sock->sk;
- struct tipc_port *tport = tipc_sk_port(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_port *port = &tsk->port;
struct sk_buff *buf;
struct tipc_msg *msg;
long timeo;
@@ -1177,7 +1172,7 @@
/* Optionally capture sender's address & ancillary data of first msg */
if (sz_copied == 0) {
set_orig_addr(m, msg);
- res = anc_data_recv(m, msg, tport);
+ res = anc_data_recv(m, msg, port);
if (res)
goto exit;
}
@@ -1215,8 +1210,8 @@
/* Consume received message (optional) */
if (likely(!(flags & MSG_PEEK))) {
- if (unlikely(++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN))
- tipc_acknowledge(tport->ref, tport->conn_unacked);
+ if (unlikely(++port->conn_unacked >= TIPC_FLOW_CONTROL_WIN))
+ tipc_acknowledge(port->ref, port->conn_unacked);
advance_rx_queue(sk);
}
@@ -1268,17 +1263,19 @@
/**
* filter_connect - Handle all incoming messages for a connection-based socket
- * @tsock: TIPC socket
+ * @tsk: TIPC socket
* @msg: message
*
* Returns TIPC error status code and socket error status code
* once it encounters some errors
*/
-static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf)
+static u32 filter_connect(struct tipc_sock *tsk, struct sk_buff **buf)
{
- struct socket *sock = tsock->sk.sk_socket;
+ struct sock *sk = &tsk->sk;
+ struct tipc_port *port = &tsk->port;
+ struct socket *sock = sk->sk_socket;
struct tipc_msg *msg = buf_msg(*buf);
- struct sock *sk = &tsock->sk;
+
u32 retval = TIPC_ERR_NO_PORT;
int res;
@@ -1288,10 +1285,10 @@
switch ((int)sock->state) {
case SS_CONNECTED:
/* Accept only connection-based messages sent by peer */
- if (msg_connected(msg) && tipc_port_peer_msg(tsock->p, msg)) {
+ if (msg_connected(msg) && tipc_port_peer_msg(port, msg)) {
if (unlikely(msg_errcode(msg))) {
sock->state = SS_DISCONNECTING;
- __tipc_disconnect(tsock->p);
+ __tipc_port_disconnect(port);
}
retval = TIPC_OK;
}
@@ -1308,7 +1305,7 @@
if (unlikely(!msg_connected(msg)))
break;
- res = auto_connect(sock, msg);
+ res = auto_connect(tsk, msg);
if (res) {
sock->state = SS_DISCONNECTING;
sk->sk_err = -res;
@@ -1387,6 +1384,7 @@
static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
{
struct socket *sock = sk->sk_socket;
+ struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_msg *msg = buf_msg(buf);
unsigned int limit = rcvbuf_limit(sk, buf);
u32 res = TIPC_OK;
@@ -1399,7 +1397,7 @@
if (msg_connected(msg))
return TIPC_ERR_NO_PORT;
} else {
- res = filter_connect(tipc_sk(sk), &buf);
+ res = filter_connect(tsk, &buf);
if (res != TIPC_OK || buf == NULL)
return res;
}
@@ -1437,17 +1435,16 @@
}
/**
- * dispatch - handle incoming message
- * @tport: TIPC port that received message
+ * tipc_sk_rcv - handle incoming message
+ * @sk: socket receiving message
* @buf: message
*
* Called with port lock already taken.
*
* Returns TIPC error status code (TIPC_OK if message is not to be rejected)
*/
-static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf)
+u32 tipc_sk_rcv(struct sock *sk, struct sk_buff *buf)
{
- struct sock *sk = tport->sk;
u32 res;
/*
@@ -1470,19 +1467,6 @@
return res;
}
-/**
- * wakeupdispatch - wake up port after congestion
- * @tport: port to wakeup
- *
- * Called with port lock already taken.
- */
-static void wakeupdispatch(struct tipc_port *tport)
-{
- struct sock *sk = tport->sk;
-
- sk->sk_write_space(sk);
-}
-
static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
{
struct sock *sk = sock->sk;
@@ -1506,7 +1490,7 @@
}
/**
- * connect - establish a connection to another TIPC port
+ * tipc_connect - establish a connection to another TIPC port
* @sock: socket structure
* @dest: socket address for destination port
* @destlen: size of socket address data structure
@@ -1514,8 +1498,8 @@
*
* Returns 0 on success, errno otherwise
*/
-static int connect(struct socket *sock, struct sockaddr *dest, int destlen,
- int flags)
+static int tipc_connect(struct socket *sock, struct sockaddr *dest,
+ int destlen, int flags)
{
struct sock *sk = sock->sk;
struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest;
@@ -1556,7 +1540,7 @@
if (!timeout)
m.msg_flags = MSG_DONTWAIT;
- res = send_msg(NULL, sock, &m, 0);
+ res = tipc_sendmsg(NULL, sock, &m, 0);
if ((res < 0) && (res != -EWOULDBLOCK))
goto exit;
@@ -1587,13 +1571,13 @@
}
/**
- * listen - allow socket to listen for incoming connections
+ * tipc_listen - allow socket to listen for incoming connections
* @sock: socket structure
* @len: (unused)
*
* Returns 0 on success, errno otherwise
*/
-static int listen(struct socket *sock, int len)
+static int tipc_listen(struct socket *sock, int len)
{
struct sock *sk = sock->sk;
int res;
@@ -1625,7 +1609,7 @@
for (;;) {
prepare_to_wait_exclusive(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
- if (skb_queue_empty(&sk->sk_receive_queue)) {
+ if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
release_sock(sk);
timeo = schedule_timeout(timeo);
lock_sock(sk);
@@ -1648,20 +1632,20 @@
}
/**
- * accept - wait for connection request
+ * tipc_accept - wait for connection request
* @sock: listening socket
* @newsock: new socket that is to be connected
* @flags: file-related flags associated with socket
*
* Returns 0 on success, errno otherwise
*/
-static int accept(struct socket *sock, struct socket *new_sock, int flags)
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
{
struct sock *new_sk, *sk = sock->sk;
struct sk_buff *buf;
- struct tipc_sock *new_tsock;
- struct tipc_port *new_tport;
+ struct tipc_port *new_port;
struct tipc_msg *msg;
+ struct tipc_portid peer;
u32 new_ref;
long timeo;
int res;
@@ -1672,7 +1656,6 @@
res = -EINVAL;
goto exit;
}
-
timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
res = tipc_wait_for_accept(sock, timeo);
if (res)
@@ -1685,9 +1668,8 @@
goto exit;
new_sk = new_sock->sk;
- new_tsock = tipc_sk(new_sk);
- new_tport = new_tsock->p;
- new_ref = new_tport->ref;
+ new_port = &tipc_sk(new_sk)->port;
+ new_ref = new_port->ref;
msg = buf_msg(buf);
/* we lock on new_sk; but lockdep sees the lock on sk */
@@ -1700,15 +1682,15 @@
reject_rx_queue(new_sk);
/* Connect new socket to it's peer */
- new_tsock->peer_name.ref = msg_origport(msg);
- new_tsock->peer_name.node = msg_orignode(msg);
- tipc_connect(new_ref, &new_tsock->peer_name);
+ peer.ref = msg_origport(msg);
+ peer.node = msg_orignode(msg);
+ tipc_port_connect(new_ref, &peer);
new_sock->state = SS_CONNECTED;
- tipc_set_portimportance(new_ref, msg_importance(msg));
+ tipc_port_set_importance(new_port, msg_importance(msg));
if (msg_named(msg)) {
- new_tport->conn_type = msg_nametype(msg);
- new_tport->conn_instance = msg_nameinst(msg);
+ new_port->conn_type = msg_nametype(msg);
+ new_port->conn_instance = msg_nameinst(msg);
}
/*
@@ -1719,21 +1701,20 @@
struct msghdr m = {NULL,};
advance_rx_queue(sk);
- send_packet(NULL, new_sock, &m, 0);
+ tipc_send_packet(NULL, new_sock, &m, 0);
} else {
__skb_dequeue(&sk->sk_receive_queue);
__skb_queue_head(&new_sk->sk_receive_queue, buf);
skb_set_owner_r(buf, new_sk);
}
release_sock(new_sk);
-
exit:
release_sock(sk);
return res;
}
/**
- * shutdown - shutdown socket connection
+ * tipc_shutdown - shutdown socket connection
* @sock: socket structure
* @how: direction to close (must be SHUT_RDWR)
*
@@ -1741,10 +1722,11 @@
*
* Returns 0 on success, errno otherwise
*/
-static int shutdown(struct socket *sock, int how)
+static int tipc_shutdown(struct socket *sock, int how)
{
struct sock *sk = sock->sk;
- struct tipc_port *tport = tipc_sk_port(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_port *port = &tsk->port;
struct sk_buff *buf;
int res;
@@ -1765,10 +1747,10 @@
kfree_skb(buf);
goto restart;
}
- tipc_disconnect(tport->ref);
+ tipc_port_disconnect(port->ref);
tipc_reject_msg(buf, TIPC_CONN_SHUTDOWN);
} else {
- tipc_shutdown(tport->ref);
+ tipc_port_shutdown(port->ref);
}
sock->state = SS_DISCONNECTING;
@@ -1794,7 +1776,7 @@
}
/**
- * setsockopt - set socket option
+ * tipc_setsockopt - set socket option
* @sock: socket structure
* @lvl: option level
* @opt: option identifier
@@ -1806,11 +1788,12 @@
*
* Returns 0 on success, errno otherwise
*/
-static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov,
- unsigned int ol)
+static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
+ char __user *ov, unsigned int ol)
{
struct sock *sk = sock->sk;
- struct tipc_port *tport = tipc_sk_port(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_port *port = &tsk->port;
u32 value;
int res;
@@ -1828,16 +1811,16 @@
switch (opt) {
case TIPC_IMPORTANCE:
- res = tipc_set_portimportance(tport->ref, value);
+ tipc_port_set_importance(port, value);
break;
case TIPC_SRC_DROPPABLE:
if (sock->type != SOCK_STREAM)
- res = tipc_set_portunreliable(tport->ref, value);
+ tipc_port_set_unreliable(port, value);
else
res = -ENOPROTOOPT;
break;
case TIPC_DEST_DROPPABLE:
- res = tipc_set_portunreturnable(tport->ref, value);
+ tipc_port_set_unreturnable(port, value);
break;
case TIPC_CONN_TIMEOUT:
tipc_sk(sk)->conn_timeout = value;
@@ -1853,7 +1836,7 @@
}
/**
- * getsockopt - get socket option
+ * tipc_getsockopt - get socket option
* @sock: socket structure
* @lvl: option level
* @opt: option identifier
@@ -1865,11 +1848,12 @@
*
* Returns 0 on success, errno otherwise
*/
-static int getsockopt(struct socket *sock, int lvl, int opt, char __user *ov,
- int __user *ol)
+static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
+ char __user *ov, int __user *ol)
{
struct sock *sk = sock->sk;
- struct tipc_port *tport = tipc_sk_port(sk);
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_port *port = &tsk->port;
int len;
u32 value;
int res;
@@ -1886,13 +1870,13 @@
switch (opt) {
case TIPC_IMPORTANCE:
- res = tipc_portimportance(tport->ref, &value);
+ value = tipc_port_importance(port);
break;
case TIPC_SRC_DROPPABLE:
- res = tipc_portunreliable(tport->ref, &value);
+ value = tipc_port_unreliable(port);
break;
case TIPC_DEST_DROPPABLE:
- res = tipc_portunreturnable(tport->ref, &value);
+ value = tipc_port_unreturnable(port);
break;
case TIPC_CONN_TIMEOUT:
value = tipc_sk(sk)->conn_timeout;
@@ -1927,20 +1911,20 @@
static const struct proto_ops msg_ops = {
.owner = THIS_MODULE,
.family = AF_TIPC,
- .release = release,
- .bind = bind,
- .connect = connect,
+ .release = tipc_release,
+ .bind = tipc_bind,
+ .connect = tipc_connect,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
- .getname = get_name,
- .poll = poll,
+ .getname = tipc_getname,
+ .poll = tipc_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
- .shutdown = shutdown,
- .setsockopt = setsockopt,
- .getsockopt = getsockopt,
- .sendmsg = send_msg,
- .recvmsg = recv_msg,
+ .shutdown = tipc_shutdown,
+ .setsockopt = tipc_setsockopt,
+ .getsockopt = tipc_getsockopt,
+ .sendmsg = tipc_sendmsg,
+ .recvmsg = tipc_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage
};
@@ -1948,20 +1932,20 @@
static const struct proto_ops packet_ops = {
.owner = THIS_MODULE,
.family = AF_TIPC,
- .release = release,
- .bind = bind,
- .connect = connect,
+ .release = tipc_release,
+ .bind = tipc_bind,
+ .connect = tipc_connect,
.socketpair = sock_no_socketpair,
- .accept = accept,
- .getname = get_name,
- .poll = poll,
+ .accept = tipc_accept,
+ .getname = tipc_getname,
+ .poll = tipc_poll,
.ioctl = sock_no_ioctl,
- .listen = listen,
- .shutdown = shutdown,
- .setsockopt = setsockopt,
- .getsockopt = getsockopt,
- .sendmsg = send_packet,
- .recvmsg = recv_msg,
+ .listen = tipc_listen,
+ .shutdown = tipc_shutdown,
+ .setsockopt = tipc_setsockopt,
+ .getsockopt = tipc_getsockopt,
+ .sendmsg = tipc_send_packet,
+ .recvmsg = tipc_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage
};
@@ -1969,20 +1953,20 @@
static const struct proto_ops stream_ops = {
.owner = THIS_MODULE,
.family = AF_TIPC,
- .release = release,
- .bind = bind,
- .connect = connect,
+ .release = tipc_release,
+ .bind = tipc_bind,
+ .connect = tipc_connect,
.socketpair = sock_no_socketpair,
- .accept = accept,
- .getname = get_name,
- .poll = poll,
+ .accept = tipc_accept,
+ .getname = tipc_getname,
+ .poll = tipc_poll,
.ioctl = sock_no_ioctl,
- .listen = listen,
- .shutdown = shutdown,
- .setsockopt = setsockopt,
- .getsockopt = getsockopt,
- .sendmsg = send_stream,
- .recvmsg = recv_stream,
+ .listen = tipc_listen,
+ .shutdown = tipc_shutdown,
+ .setsockopt = tipc_setsockopt,
+ .getsockopt = tipc_getsockopt,
+ .sendmsg = tipc_send_stream,
+ .recvmsg = tipc_recv_stream,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage
};
@@ -2027,8 +2011,6 @@
proto_unregister(&tipc_proto);
goto out;
}
-
- sockets_enabled = 1;
out:
return res;
}
@@ -2038,10 +2020,6 @@
*/
void tipc_socket_stop(void)
{
- if (!sockets_enabled)
- return;
-
- sockets_enabled = 0;
sock_unregister(tipc_family_ops.family);
proto_unregister(&tipc_proto);
}
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
new file mode 100644
index 0000000..74e5c7f
--- /dev/null
+++ b/net/tipc/socket.h
@@ -0,0 +1,72 @@
+/* net/tipc/socket.h: Include file for TIPC socket code
+ *
+ * Copyright (c) 2014, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_SOCK_H
+#define _TIPC_SOCK_H
+
+#include "port.h"
+#include <net/sock.h>
+
+/**
+ * struct tipc_sock - TIPC socket structure
+ * @sk: socket - interacts with 'port' and with user via the socket API
+ * @port: port - interacts with 'sk' and with the rest of the TIPC stack
+ * @peer_name: the peer of the connection, if any
+ * @conn_timeout: the time we can wait for an unresponded setup request
+ */
+
+struct tipc_sock {
+ struct sock sk;
+ struct tipc_port port;
+ unsigned int conn_timeout;
+};
+
+static inline struct tipc_sock *tipc_sk(const struct sock *sk)
+{
+ return container_of(sk, struct tipc_sock, sk);
+}
+
+static inline struct tipc_sock *tipc_port_to_sock(const struct tipc_port *port)
+{
+ return container_of(port, struct tipc_sock, port);
+}
+
+static inline void tipc_sock_wakeup(struct tipc_sock *tsk)
+{
+ tsk->sk.sk_write_space(&tsk->sk);
+}
+
+u32 tipc_sk_rcv(struct sock *sk, struct sk_buff *buf);
+
+#endif
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 7cb0bd5..6424372 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -96,20 +96,16 @@
{
struct tipc_subscriber *subscriber = sub->subscriber;
struct kvec msg_sect;
- int ret;
msg_sect.iov_base = (void *)&sub->evt;
msg_sect.iov_len = sizeof(struct tipc_event);
-
sub->evt.event = htohl(event, sub->swap);
sub->evt.found_lower = htohl(found_lower, sub->swap);
sub->evt.found_upper = htohl(found_upper, sub->swap);
sub->evt.port.ref = htohl(port_ref, sub->swap);
sub->evt.port.node = htohl(node, sub->swap);
- ret = tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL,
- msg_sect.iov_base, msg_sect.iov_len);
- if (ret < 0)
- pr_err("Sending subscription event failed, no memory\n");
+ tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL, msg_sect.iov_base,
+ msg_sect.iov_len);
}
/**
@@ -153,14 +149,6 @@
/* The spin lock per subscriber is used to protect its members */
spin_lock_bh(&subscriber->lock);
- /* Validate if the connection related to the subscriber is
- * closed (in case subscriber is terminating)
- */
- if (subscriber->conid == 0) {
- spin_unlock_bh(&subscriber->lock);
- return;
- }
-
/* Validate timeout (in case subscription is being cancelled) */
if (sub->timeout == TIPC_WAIT_FOREVER) {
spin_unlock_bh(&subscriber->lock);
@@ -215,9 +203,6 @@
spin_lock_bh(&subscriber->lock);
- /* Invalidate subscriber reference */
- subscriber->conid = 0;
-
/* Destroy any existing subscriptions for subscriber */
list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list,
subscription_list) {
@@ -278,9 +263,9 @@
*
* Called with subscriber lock held.
*/
-static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s,
- struct tipc_subscriber *subscriber)
-{
+static int subscr_subscribe(struct tipc_subscr *s,
+ struct tipc_subscriber *subscriber,
+ struct tipc_subscription **sub_p) {
struct tipc_subscription *sub;
int swap;
@@ -291,23 +276,21 @@
if (s->filter & htohl(TIPC_SUB_CANCEL, swap)) {
s->filter &= ~htohl(TIPC_SUB_CANCEL, swap);
subscr_cancel(s, subscriber);
- return NULL;
+ return 0;
}
/* Refuse subscription if global limit exceeded */
if (atomic_read(&subscription_count) >= TIPC_MAX_SUBSCRIPTIONS) {
pr_warn("Subscription rejected, limit reached (%u)\n",
TIPC_MAX_SUBSCRIPTIONS);
- subscr_terminate(subscriber);
- return NULL;
+ return -EINVAL;
}
/* Allocate subscription object */
sub = kmalloc(sizeof(*sub), GFP_ATOMIC);
if (!sub) {
pr_warn("Subscription rejected, no memory\n");
- subscr_terminate(subscriber);
- return NULL;
+ return -ENOMEM;
}
/* Initialize subscription object */
@@ -321,8 +304,7 @@
(sub->seq.lower > sub->seq.upper)) {
pr_warn("Subscription rejected, illegal request\n");
kfree(sub);
- subscr_terminate(subscriber);
- return NULL;
+ return -EINVAL;
}
INIT_LIST_HEAD(&sub->nameseq_list);
list_add(&sub->subscription_list, &subscriber->subscription_list);
@@ -335,8 +317,8 @@
(Handler)subscr_timeout, (unsigned long)sub);
k_start_timer(&sub->timer, sub->timeout);
}
-
- return sub;
+ *sub_p = sub;
+ return 0;
}
/* Handle one termination request for the subscriber */
@@ -350,10 +332,14 @@
void *usr_data, void *buf, size_t len)
{
struct tipc_subscriber *subscriber = usr_data;
- struct tipc_subscription *sub;
+ struct tipc_subscription *sub = NULL;
spin_lock_bh(&subscriber->lock);
- sub = subscr_subscribe((struct tipc_subscr *)buf, subscriber);
+ if (subscr_subscribe((struct tipc_subscr *)buf, subscriber, &sub) < 0) {
+ spin_unlock_bh(&subscriber->lock);
+ subscr_terminate(subscriber);
+ return;
+ }
if (sub)
tipc_nametbl_subscribe(sub);
spin_unlock_bh(&subscriber->lock);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 29fc8be..94404f1 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -163,9 +163,8 @@
static inline unsigned int unix_hash_fold(__wsum n)
{
- unsigned int hash = (__force unsigned int)n;
+ unsigned int hash = (__force unsigned int)csum_fold(n);
- hash ^= hash>>16;
hash ^= hash>>8;
return hash&(UNIX_HASH_SIZE-1);
}
@@ -1788,8 +1787,11 @@
goto out;
err = mutex_lock_interruptible(&u->readlock);
- if (err) {
- err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+ if (unlikely(err)) {
+ /* recvmsg() in non blocking mode is supposed to return -EAGAIN
+ * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+ */
+ err = noblock ? -EAGAIN : -ERESTARTSYS;
goto out;
}
@@ -1914,6 +1916,7 @@
struct unix_sock *u = unix_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
int copied = 0;
+ int noblock = flags & MSG_DONTWAIT;
int check_creds = 0;
int target;
int err = 0;
@@ -1929,7 +1932,7 @@
goto out;
target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
- timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
+ timeo = sock_rcvtimeo(sk, noblock);
/* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
@@ -1941,8 +1944,11 @@
}
err = mutex_lock_interruptible(&u->readlock);
- if (err) {
- err = sock_intr_errno(timeo);
+ if (unlikely(err)) {
+ /* recvmsg() in non blocking mode is supposed to return -EAGAIN
+ * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+ */
+ err = noblock ? -EAGAIN : -ERESTARTSYS;
goto out;
}
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 8659d5c..9c9501a 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -768,6 +768,4 @@
case NUM_NL80211_IFTYPES:
WARN_ON(1);
}
-
- return;
}
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 276cf93..086cddd 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -788,8 +788,6 @@
default:
break;
}
-
- wdev->beacon_interval = 0;
}
static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 39fc1d7..e5872ff 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -11,6 +11,7 @@
#include <net/ip.h>
#include <net/dsfield.h>
#include <linux/if_vlan.h>
+#include <linux/mpls.h>
#include "core.h"
#include "rdev-ops.h"
@@ -717,6 +718,21 @@
case htons(ETH_P_IPV6):
dscp = ipv6_get_dsfield(ipv6_hdr(skb)) & 0xfc;
break;
+ case htons(ETH_P_MPLS_UC):
+ case htons(ETH_P_MPLS_MC): {
+ struct mpls_label mpls_tmp, *mpls;
+
+ mpls = skb_header_pointer(skb, sizeof(struct ethhdr),
+ sizeof(*mpls), &mpls_tmp);
+ if (!mpls)
+ return 0;
+
+ return (ntohl(mpls->entry) & MPLS_LS_TC_MASK)
+ >> MPLS_LS_TC_SHIFT;
+ }
+ case htons(ETH_P_80221):
+ /* 802.21 is always network control traffic */
+ return 7;
default:
return 0;
}
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 6c7ac01..85d1d47 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -16,6 +16,81 @@
static struct kmem_cache *secpath_cachep __read_mostly;
+static DEFINE_SPINLOCK(xfrm_input_afinfo_lock);
+static struct xfrm_input_afinfo __rcu *xfrm_input_afinfo[NPROTO];
+
+int xfrm_input_register_afinfo(struct xfrm_input_afinfo *afinfo)
+{
+ int err = 0;
+
+ if (unlikely(afinfo == NULL))
+ return -EINVAL;
+ if (unlikely(afinfo->family >= NPROTO))
+ return -EAFNOSUPPORT;
+ spin_lock_bh(&xfrm_input_afinfo_lock);
+ if (unlikely(xfrm_input_afinfo[afinfo->family] != NULL))
+ err = -ENOBUFS;
+ else
+ rcu_assign_pointer(xfrm_input_afinfo[afinfo->family], afinfo);
+ spin_unlock_bh(&xfrm_input_afinfo_lock);
+ return err;
+}
+EXPORT_SYMBOL(xfrm_input_register_afinfo);
+
+int xfrm_input_unregister_afinfo(struct xfrm_input_afinfo *afinfo)
+{
+ int err = 0;
+
+ if (unlikely(afinfo == NULL))
+ return -EINVAL;
+ if (unlikely(afinfo->family >= NPROTO))
+ return -EAFNOSUPPORT;
+ spin_lock_bh(&xfrm_input_afinfo_lock);
+ if (likely(xfrm_input_afinfo[afinfo->family] != NULL)) {
+ if (unlikely(xfrm_input_afinfo[afinfo->family] != afinfo))
+ err = -EINVAL;
+ else
+ RCU_INIT_POINTER(xfrm_input_afinfo[afinfo->family], NULL);
+ }
+ spin_unlock_bh(&xfrm_input_afinfo_lock);
+ synchronize_rcu();
+ return err;
+}
+EXPORT_SYMBOL(xfrm_input_unregister_afinfo);
+
+static struct xfrm_input_afinfo *xfrm_input_get_afinfo(unsigned int family)
+{
+ struct xfrm_input_afinfo *afinfo;
+
+ if (unlikely(family >= NPROTO))
+ return NULL;
+ rcu_read_lock();
+ afinfo = rcu_dereference(xfrm_input_afinfo[family]);
+ if (unlikely(!afinfo))
+ rcu_read_unlock();
+ return afinfo;
+}
+
+static void xfrm_input_put_afinfo(struct xfrm_input_afinfo *afinfo)
+{
+ rcu_read_unlock();
+}
+
+static int xfrm_rcv_cb(struct sk_buff *skb, unsigned int family, u8 protocol,
+ int err)
+{
+ int ret;
+ struct xfrm_input_afinfo *afinfo = xfrm_input_get_afinfo(family);
+
+ if (!afinfo)
+ return -EAFNOSUPPORT;
+
+ ret = afinfo->callback(skb, protocol, err);
+ xfrm_input_put_afinfo(afinfo);
+
+ return ret;
+}
+
void __secpath_destroy(struct sec_path *sp)
{
int i;
@@ -108,7 +183,7 @@
int err;
__be32 seq;
__be32 seq_hi;
- struct xfrm_state *x;
+ struct xfrm_state *x = NULL;
xfrm_address_t *daddr;
struct xfrm_mode *inner_mode;
unsigned int family;
@@ -120,9 +195,14 @@
async = 1;
x = xfrm_input_state(skb);
seq = XFRM_SKB_CB(skb)->seq.input.low;
+ family = x->outer_mode->afinfo->family;
goto resume;
}
+ daddr = (xfrm_address_t *)(skb_network_header(skb) +
+ XFRM_SPI_SKB_CB(skb)->daddroff);
+ family = XFRM_SPI_SKB_CB(skb)->family;
+
/* Allocate new secpath or COW existing one. */
if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) {
struct sec_path *sp;
@@ -137,10 +217,6 @@
skb->sp = sp;
}
- daddr = (xfrm_address_t *)(skb_network_header(skb) +
- XFRM_SPI_SKB_CB(skb)->daddroff);
- family = XFRM_SPI_SKB_CB(skb)->family;
-
seq = 0;
if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
@@ -162,6 +238,11 @@
skb->sp->xvec[skb->sp->len++] = x;
+ if (xfrm_tunnel_check(skb, x, family)) {
+ XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
+ goto drop;
+ }
+
spin_lock(&x->lock);
if (unlikely(x->km.state == XFRM_STATE_ACQ)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR);
@@ -201,7 +282,6 @@
if (nexthdr == -EINPROGRESS)
return 0;
-
resume:
spin_lock(&x->lock);
if (nexthdr <= 0) {
@@ -263,6 +343,10 @@
}
} while (!err);
+ err = xfrm_rcv_cb(skb, family, x->type->proto, 0);
+ if (err)
+ goto drop;
+
nf_reset(skb);
if (decaps) {
@@ -276,6 +360,7 @@
drop_unlock:
spin_unlock(&x->lock);
drop:
+ xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1);
kfree_skb(skb);
return 0;
}
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 4b98b25..f02f511 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -39,8 +39,6 @@
#define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ))
#define XFRM_MAX_QUEUE_LEN 100
-static struct dst_entry *xfrm_policy_sk_bundles;
-
static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO]
__read_mostly;
@@ -661,7 +659,7 @@
hlist_add_head(&policy->bydst, chain);
xfrm_pol_hold(policy);
net->xfrm.policy_count[dir]++;
- atomic_inc(&flow_cache_genid);
+ atomic_inc(&net->xfrm.flow_cache_genid);
/* After previous checking, family can either be AF_INET or AF_INET6 */
if (policy->family == AF_INET)
@@ -1158,7 +1156,7 @@
if (hlist_unhashed(&pol->bydst))
return NULL;
- hlist_del(&pol->bydst);
+ hlist_del_init(&pol->bydst);
hlist_del(&pol->byidx);
list_del(&pol->walk.all);
net->xfrm.policy_count[dir]--;
@@ -2109,13 +2107,6 @@
goto no_transform;
}
- dst_hold(&xdst->u.dst);
-
- spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
- xdst->u.dst.next = xfrm_policy_sk_bundles;
- xfrm_policy_sk_bundles = &xdst->u.dst;
- spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
-
route = xdst->route;
}
}
@@ -2549,33 +2540,15 @@
return dst;
}
-static void __xfrm_garbage_collect(struct net *net)
-{
- struct dst_entry *head, *next;
-
- spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
- head = xfrm_policy_sk_bundles;
- xfrm_policy_sk_bundles = NULL;
- spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock);
-
- while (head) {
- next = head->next;
- dst_free(head);
- head = next;
- }
-}
-
void xfrm_garbage_collect(struct net *net)
{
- flow_cache_flush();
- __xfrm_garbage_collect(net);
+ flow_cache_flush(net);
}
EXPORT_SYMBOL(xfrm_garbage_collect);
static void xfrm_garbage_collect_deferred(struct net *net)
{
- flow_cache_flush_deferred();
- __xfrm_garbage_collect(net);
+ flow_cache_flush_deferred(net);
}
static void xfrm_init_pmtu(struct dst_entry *dst)
@@ -2940,15 +2913,19 @@
rv = xfrm_sysctl_init(net);
if (rv < 0)
goto out_sysctl;
+ rv = flow_cache_init(net);
+ if (rv < 0)
+ goto out;
/* Initialize the per-net locks here */
spin_lock_init(&net->xfrm.xfrm_state_lock);
rwlock_init(&net->xfrm.xfrm_policy_lock);
- spin_lock_init(&net->xfrm.xfrm_policy_sk_bundle_lock);
mutex_init(&net->xfrm.xfrm_cfg_mutex);
return 0;
+out:
+ xfrm_sysctl_fini(net);
out_sysctl:
xfrm_policy_fini(net);
out_policy:
@@ -2961,6 +2938,7 @@
static void __net_exit xfrm_net_exit(struct net *net)
{
+ flow_cache_fini(net);
xfrm_sysctl_fini(net);
xfrm_policy_fini(net);
xfrm_state_fini(net);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index a26b7aa..8e9c781 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -161,6 +161,7 @@
int __xfrm_state_delete(struct xfrm_state *x);
int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
+bool km_is_alive(const struct km_event *c);
void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
static DEFINE_SPINLOCK(xfrm_type_lock);
@@ -788,6 +789,7 @@
struct xfrm_state *best = NULL;
u32 mark = pol->mark.v & pol->mark.m;
unsigned short encap_family = tmpl->encap_family;
+ struct km_event c;
to_put = NULL;
@@ -832,6 +834,17 @@
error = -EEXIST;
goto out;
}
+
+ c.net = net;
+ /* If the KMs have no listeners (yet...), avoid allocating an SA
+ * for each and every packet - garbage collection might not
+ * handle the flood.
+ */
+ if (!km_is_alive(&c)) {
+ error = -ESRCH;
+ goto out;
+ }
+
x = xfrm_state_alloc(net);
if (x == NULL) {
error = -ENOMEM;
@@ -1135,10 +1148,9 @@
EXPORT_SYMBOL(xfrm_state_add);
#ifdef CONFIG_XFRM_MIGRATE
-static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
+static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig)
{
struct net *net = xs_net(orig);
- int err = -ENOMEM;
struct xfrm_state *x = xfrm_state_alloc(net);
if (!x)
goto out;
@@ -1159,6 +1171,11 @@
}
x->props.aalgo = orig->props.aalgo;
+ if (orig->aead) {
+ x->aead = xfrm_algo_aead_clone(orig->aead);
+ if (!x->aead)
+ goto error;
+ }
if (orig->ealg) {
x->ealg = xfrm_algo_clone(orig->ealg);
if (!x->ealg)
@@ -1187,20 +1204,21 @@
}
if (orig->replay_esn) {
- err = xfrm_replay_clone(x, orig);
- if (err)
+ if (xfrm_replay_clone(x, orig))
goto error;
}
memcpy(&x->mark, &orig->mark, sizeof(x->mark));
- err = xfrm_init_state(x);
- if (err)
+ if (xfrm_init_state(x) < 0)
goto error;
x->props.flags = orig->props.flags;
x->props.extra_flags = orig->props.extra_flags;
+ x->tfcpad = orig->tfcpad;
+ x->replay_maxdiff = orig->replay_maxdiff;
+ x->replay_maxage = orig->replay_maxage;
x->curlft.add_time = orig->curlft.add_time;
x->km.state = orig->km.state;
x->km.seq = orig->km.seq;
@@ -1210,16 +1228,15 @@
error:
xfrm_state_put(x);
out:
- if (errp)
- *errp = err;
return NULL;
}
-/* net->xfrm.xfrm_state_lock is held */
struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net)
{
unsigned int h;
- struct xfrm_state *x;
+ struct xfrm_state *x = NULL;
+
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
if (m->reqid) {
h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr,
@@ -1236,7 +1253,7 @@
m->old_family))
continue;
xfrm_state_hold(x);
- return x;
+ break;
}
} else {
h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr,
@@ -1251,11 +1268,13 @@
m->old_family))
continue;
xfrm_state_hold(x);
- return x;
+ break;
}
}
- return NULL;
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+ return x;
}
EXPORT_SYMBOL(xfrm_migrate_state_find);
@@ -1263,9 +1282,8 @@
struct xfrm_migrate *m)
{
struct xfrm_state *xc;
- int err;
- xc = xfrm_state_clone(x, &err);
+ xc = xfrm_state_clone(x);
if (!xc)
return NULL;
@@ -1278,7 +1296,7 @@
state is to be updated as it is a part of triplet */
xfrm_state_insert(xc);
} else {
- if ((err = xfrm_state_add(xc)) < 0)
+ if (xfrm_state_add(xc) < 0)
goto error;
}
@@ -1451,7 +1469,7 @@
{
int err = 0;
struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
- struct net *net = xs_net(*dst);
+ struct net *net = xs_net(*src);
if (!afinfo)
return -EAFNOSUPPORT;
@@ -1590,6 +1608,23 @@
}
EXPORT_SYMBOL(xfrm_alloc_spi);
+static bool __xfrm_state_filter_match(struct xfrm_state *x,
+ struct xfrm_address_filter *filter)
+{
+ if (filter) {
+ if ((filter->family == AF_INET ||
+ filter->family == AF_INET6) &&
+ x->props.family != filter->family)
+ return false;
+
+ return addr_match(&x->props.saddr, &filter->saddr,
+ filter->splen) &&
+ addr_match(&x->id.daddr, &filter->daddr,
+ filter->dplen);
+ }
+ return true;
+}
+
int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
int (*func)(struct xfrm_state *, int, void*),
void *data)
@@ -1612,6 +1647,8 @@
state = container_of(x, struct xfrm_state, km);
if (!xfrm_id_proto_match(state->id.proto, walk->proto))
continue;
+ if (!__xfrm_state_filter_match(state, walk->filter))
+ continue;
err = func(state, walk->seq, data);
if (err) {
list_move_tail(&walk->all, &x->all);
@@ -1630,17 +1667,21 @@
}
EXPORT_SYMBOL(xfrm_state_walk);
-void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto)
+void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto,
+ struct xfrm_address_filter *filter)
{
INIT_LIST_HEAD(&walk->all);
walk->proto = proto;
walk->state = XFRM_STATE_DEAD;
walk->seq = 0;
+ walk->filter = filter;
}
EXPORT_SYMBOL(xfrm_state_walk_init);
void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net)
{
+ kfree(walk->filter);
+
if (list_empty(&walk->all))
return;
@@ -1793,6 +1834,24 @@
}
EXPORT_SYMBOL(km_report);
+bool km_is_alive(const struct km_event *c)
+{
+ struct xfrm_mgr *km;
+ bool is_alive = false;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(km, &xfrm_km_list, list) {
+ if (km->is_alive && km->is_alive(c)) {
+ is_alive = true;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return is_alive;
+}
+EXPORT_SYMBOL(km_is_alive);
+
int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
{
int err;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 1ae3ec7..8f131c1 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -32,11 +32,6 @@
#include <linux/in6.h>
#endif
-static inline int aead_len(struct xfrm_algo_aead *alg)
-{
- return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
-}
-
static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type)
{
struct nlattr *rt = attrs[type];
@@ -142,7 +137,8 @@
if (!rt)
return 0;
- if (p->id.proto != IPPROTO_ESP)
+ /* As only ESP and AH support ESN feature. */
+ if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH))
return -EINVAL;
if (p->replay_window != 0)
@@ -886,6 +882,7 @@
return 0;
}
+static const struct nla_policy xfrma_policy[XFRMA_MAX+1];
static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
@@ -901,8 +898,31 @@
info.nlmsg_flags = NLM_F_MULTI;
if (!cb->args[0]) {
+ struct nlattr *attrs[XFRMA_MAX+1];
+ struct xfrm_address_filter *filter = NULL;
+ u8 proto = 0;
+ int err;
+
cb->args[0] = 1;
- xfrm_state_walk_init(walk, 0);
+
+ err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX,
+ xfrma_policy);
+ if (err < 0)
+ return err;
+
+ if (attrs[XFRMA_ADDRESS_FILTER]) {
+ filter = kmalloc(sizeof(*filter), GFP_KERNEL);
+ if (filter == NULL)
+ return -ENOMEM;
+
+ memcpy(filter, nla_data(attrs[XFRMA_ADDRESS_FILTER]),
+ sizeof(*filter));
+ }
+
+ if (attrs[XFRMA_PROTO])
+ proto = nla_get_u8(attrs[XFRMA_PROTO]);
+
+ xfrm_state_walk_init(walk, proto, filter);
}
(void) xfrm_state_walk(net, walk, dump_one_state, &info);
@@ -1226,7 +1246,7 @@
return 0;
uctx = nla_data(rt);
- return security_xfrm_policy_alloc(&pol->security, uctx);
+ return security_xfrm_policy_alloc(&pol->security, uctx, GFP_KERNEL);
}
static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut,
@@ -1631,7 +1651,7 @@
if (rt) {
struct xfrm_user_sec_ctx *uctx = nla_data(rt);
- err = security_xfrm_policy_alloc(&ctx, uctx);
+ err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL);
if (err)
return err;
}
@@ -1933,7 +1953,7 @@
if (rt) {
struct xfrm_user_sec_ctx *uctx = nla_data(rt);
- err = security_xfrm_policy_alloc(&ctx, uctx);
+ err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL);
if (err)
return err;
}
@@ -2308,6 +2328,8 @@
[XFRMA_TFCPAD] = { .type = NLA_U32 },
[XFRMA_REPLAY_ESN_VAL] = { .len = sizeof(struct xfrm_replay_state_esn) },
[XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 },
+ [XFRMA_PROTO] = { .type = NLA_U8 },
+ [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) },
};
static const struct xfrm_link {
@@ -2981,6 +3003,11 @@
return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MAPPING, GFP_ATOMIC);
}
+static bool xfrm_is_alive(const struct km_event *c)
+{
+ return (bool)xfrm_acquire_is_on(c->net);
+}
+
static struct xfrm_mgr netlink_mgr = {
.id = "netlink",
.notify = xfrm_send_state_notify,
@@ -2990,6 +3017,7 @@
.report = xfrm_send_report,
.migrate = xfrm_send_migrate,
.new_mapping = xfrm_send_mapping,
+ .is_alive = xfrm_is_alive,
};
static int __net_init xfrm_user_net_init(struct net *net)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 49392ec..79c059e 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -152,6 +152,7 @@
dtc_cpp_flags = -Wp,-MD,$(depfile).pre.tmp -nostdinc \
-I$(srctree)/arch/$(SRCARCH)/boot/dts \
-I$(srctree)/arch/$(SRCARCH)/boot/dts/include \
+ -I$(srctree)/drivers/of/testcase-data \
-undef -D__DTS__
# Finds the multi-part object the current object will be linked into
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 0ea2a1e..464dcef 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -471,7 +471,7 @@
$camelcase_seeded = 1;
- if (-d ".git") {
+ if (-e ".git") {
my $git_last_include_commit = `git log --no-merges --pretty=format:"%h%n" -1 -- include`;
chomp $git_last_include_commit;
$camelcase_cache = ".checkpatch-camelcase.git.$git_last_include_commit";
@@ -499,7 +499,7 @@
return;
}
- if (-d ".git") {
+ if (-e ".git") {
$files = `git ls-files "include/*.h"`;
@include_files = split('\n', $files);
}
diff --git a/scripts/gen_initramfs_list.sh b/scripts/gen_initramfs_list.sh
index ef47409..17fa901 100644
--- a/scripts/gen_initramfs_list.sh
+++ b/scripts/gen_initramfs_list.sh
@@ -257,7 +257,7 @@
&& compr="lzop -9 -f"
echo "$output_file" | grep -q "\.lz4$" \
&& [ -x "`which lz4 2> /dev/null`" ] \
- && compr="lz4 -9 -f"
+ && compr="lz4 -l -9 -f"
echo "$output_file" | grep -q "\.cpio$" && compr="cat"
shift
;;
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 9c3986f..4198788 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -95,7 +95,7 @@
my %VCS_cmds_git = (
"execute_cmd" => \&git_execute_cmd,
- "available" => '(which("git") ne "") && (-d ".git")',
+ "available" => '(which("git") ne "") && (-e ".git")',
"find_signers_cmd" =>
"git log --no-color --follow --since=\$email_git_since " .
'--numstat --no-merges ' .
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 2370863..25e5cb0 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -210,8 +210,8 @@
range_lo < 0x9 ? "[%X-9" : "[%X",
range_lo);
sprintf(alias + strlen(alias),
- range_hi > 0xA ? "a-%X]" : "%X]",
- range_lo);
+ range_hi > 0xA ? "A-%X]" : "%X]",
+ range_hi);
}
}
if (bcdDevice_initial_digits < (sizeof(bcdDevice_lo) * 2 - 1))
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 4061098..99a45fd 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1502,6 +1502,16 @@
#define R_ARM_JUMP24 29
#endif
+#ifndef R_ARM_THM_CALL
+#define R_ARM_THM_CALL 10
+#endif
+#ifndef R_ARM_THM_JUMP24
+#define R_ARM_THM_JUMP24 30
+#endif
+#ifndef R_ARM_THM_JUMP19
+#define R_ARM_THM_JUMP19 51
+#endif
+
static int addend_arm_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r)
{
unsigned int r_typ = ELF_R_TYPE(r->r_info);
@@ -1515,6 +1525,9 @@
case R_ARM_PC24:
case R_ARM_CALL:
case R_ARM_JUMP24:
+ case R_ARM_THM_CALL:
+ case R_ARM_THM_JUMP24:
+ case R_ARM_THM_JUMP19:
/* From ARM ABI: ((S + A) | T) - P */
r->r_addend = (int)(long)(elf->hdr +
sechdr->sh_offset +
diff --git a/security/capability.c b/security/capability.c
index 8b4f24a..21e2b9c 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -757,7 +757,8 @@
#ifdef CONFIG_SECURITY_NETWORK_XFRM
static int cap_xfrm_policy_alloc_security(struct xfrm_sec_ctx **ctxp,
- struct xfrm_user_sec_ctx *sec_ctx)
+ struct xfrm_user_sec_ctx *sec_ctx,
+ gfp_t gfp)
{
return 0;
}
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index d46cbc5..2fb2576 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -1000,7 +1000,11 @@
kenter("{%d}", key->serial);
- BUG_ON(key != ctx->match_data);
+ /* We might get a keyring with matching index-key that is nonetheless a
+ * different keyring. */
+ if (key != ctx->match_data)
+ return 0;
+
ctx->result = ERR_PTR(-EDEADLK);
return 1;
}
diff --git a/security/security.c b/security/security.c
index 15b6928..919cad9 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1317,9 +1317,11 @@
#ifdef CONFIG_SECURITY_NETWORK_XFRM
-int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx)
+int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
+ struct xfrm_user_sec_ctx *sec_ctx,
+ gfp_t gfp)
{
- return security_ops->xfrm_policy_alloc_security(ctxp, sec_ctx);
+ return security_ops->xfrm_policy_alloc_security(ctxp, sec_ctx, gfp);
}
EXPORT_SYMBOL(security_xfrm_policy_alloc);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4b34847..b332e2c 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -668,7 +668,7 @@
if (flags[i] == SBLABEL_MNT)
continue;
rc = security_context_to_sid(mount_options[i],
- strlen(mount_options[i]), &sid);
+ strlen(mount_options[i]), &sid, GFP_KERNEL);
if (rc) {
printk(KERN_WARNING "SELinux: security_context_to_sid"
"(%s) failed for (dev %s, type %s) errno=%d\n",
@@ -2489,7 +2489,8 @@
if (flags[i] == SBLABEL_MNT)
continue;
len = strlen(mount_options[i]);
- rc = security_context_to_sid(mount_options[i], len, &sid);
+ rc = security_context_to_sid(mount_options[i], len, &sid,
+ GFP_KERNEL);
if (rc) {
printk(KERN_WARNING "SELinux: security_context_to_sid"
"(%s) failed for (dev %s, type %s) errno=%d\n",
@@ -2893,7 +2894,7 @@
if (rc)
return rc;
- rc = security_context_to_sid(value, size, &newsid);
+ rc = security_context_to_sid(value, size, &newsid, GFP_KERNEL);
if (rc == -EINVAL) {
if (!capable(CAP_MAC_ADMIN)) {
struct audit_buffer *ab;
@@ -3050,7 +3051,7 @@
if (!value || !size)
return -EACCES;
- rc = security_context_to_sid((void *)value, size, &newsid);
+ rc = security_context_to_sid((void *)value, size, &newsid, GFP_KERNEL);
if (rc)
return rc;
@@ -5529,7 +5530,7 @@
str[size-1] = 0;
size--;
}
- error = security_context_to_sid(value, size, &sid);
+ error = security_context_to_sid(value, size, &sid, GFP_KERNEL);
if (error == -EINVAL && !strcmp(name, "fscreate")) {
if (!capable(CAP_MAC_ADMIN)) {
struct audit_buffer *ab;
@@ -5638,7 +5639,7 @@
static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid)
{
- return security_context_to_sid(secdata, seclen, secid);
+ return security_context_to_sid(secdata, seclen, secid, GFP_KERNEL);
}
static void selinux_release_secctx(char *secdata, u32 seclen)
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 8ed8daf..ce7852c 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -134,7 +134,7 @@
int security_sid_to_context_force(u32 sid, char **scontext, u32 *scontext_len);
int security_context_to_sid(const char *scontext, u32 scontext_len,
- u32 *out_sid);
+ u32 *out_sid, gfp_t gfp);
int security_context_to_sid_default(const char *scontext, u32 scontext_len,
u32 *out_sid, u32 def_sid, gfp_t gfp_flags);
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index 48c3cc9..1450f85 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -10,7 +10,8 @@
#include <net/flow.h>
int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
- struct xfrm_user_sec_ctx *uctx);
+ struct xfrm_user_sec_ctx *uctx,
+ gfp_t gfp);
int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
struct xfrm_sec_ctx **new_ctxp);
void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx);
@@ -45,10 +46,11 @@
{
struct net *net;
- atomic_inc(&flow_cache_genid);
rtnl_lock();
- for_each_net(net)
+ for_each_net(net) {
+ atomic_inc(&net->xfrm.flow_cache_genid);
rt_genid_bump_all(net);
+ }
rtnl_unlock();
}
#else
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 5122aff..d60c0ee 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -576,7 +576,7 @@
if (length)
goto out;
- length = security_context_to_sid(buf, size, &sid);
+ length = security_context_to_sid(buf, size, &sid, GFP_KERNEL);
if (length)
goto out;
@@ -731,11 +731,13 @@
if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3)
goto out;
- length = security_context_to_sid(scon, strlen(scon) + 1, &ssid);
+ length = security_context_to_sid(scon, strlen(scon) + 1, &ssid,
+ GFP_KERNEL);
if (length)
goto out;
- length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid);
+ length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid,
+ GFP_KERNEL);
if (length)
goto out;
@@ -817,11 +819,13 @@
objname = namebuf;
}
- length = security_context_to_sid(scon, strlen(scon) + 1, &ssid);
+ length = security_context_to_sid(scon, strlen(scon) + 1, &ssid,
+ GFP_KERNEL);
if (length)
goto out;
- length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid);
+ length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid,
+ GFP_KERNEL);
if (length)
goto out;
@@ -878,11 +882,13 @@
if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3)
goto out;
- length = security_context_to_sid(scon, strlen(scon) + 1, &ssid);
+ length = security_context_to_sid(scon, strlen(scon) + 1, &ssid,
+ GFP_KERNEL);
if (length)
goto out;
- length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid);
+ length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid,
+ GFP_KERNEL);
if (length)
goto out;
@@ -934,7 +940,7 @@
if (sscanf(buf, "%s %s", con, user) != 2)
goto out;
- length = security_context_to_sid(con, strlen(con) + 1, &sid);
+ length = security_context_to_sid(con, strlen(con) + 1, &sid, GFP_KERNEL);
if (length)
goto out;
@@ -994,11 +1000,13 @@
if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3)
goto out;
- length = security_context_to_sid(scon, strlen(scon) + 1, &ssid);
+ length = security_context_to_sid(scon, strlen(scon) + 1, &ssid,
+ GFP_KERNEL);
if (length)
goto out;
- length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid);
+ length = security_context_to_sid(tcon, strlen(tcon) + 1, &tsid,
+ GFP_KERNEL);
if (length)
goto out;
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index c0f4988..9c5cdc2ca 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -3338,10 +3338,10 @@
if (rc)
return rc;
- buf[0] = ft->stype;
- buf[1] = ft->ttype;
- buf[2] = ft->tclass;
- buf[3] = otype->otype;
+ buf[0] = cpu_to_le32(ft->stype);
+ buf[1] = cpu_to_le32(ft->ttype);
+ buf[2] = cpu_to_le32(ft->tclass);
+ buf[3] = cpu_to_le32(otype->otype);
rc = put_entry(buf, sizeof(u32), 4, fp);
if (rc)
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 5d0144e..4bca494 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1289,16 +1289,18 @@
* @scontext: security context
* @scontext_len: length in bytes
* @sid: security identifier, SID
+ * @gfp: context for the allocation
*
* Obtains a SID associated with the security context that
* has the string representation specified by @scontext.
* Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient
* memory is available, or 0 on success.
*/
-int security_context_to_sid(const char *scontext, u32 scontext_len, u32 *sid)
+int security_context_to_sid(const char *scontext, u32 scontext_len, u32 *sid,
+ gfp_t gfp)
{
return security_context_to_sid_core(scontext, scontext_len,
- sid, SECSID_NULL, GFP_KERNEL, 0);
+ sid, SECSID_NULL, gfp, 0);
}
/**
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index 0462cb3..98b0426 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -78,7 +78,8 @@
* xfrm_user_sec_ctx context.
*/
static int selinux_xfrm_alloc_user(struct xfrm_sec_ctx **ctxp,
- struct xfrm_user_sec_ctx *uctx)
+ struct xfrm_user_sec_ctx *uctx,
+ gfp_t gfp)
{
int rc;
const struct task_security_struct *tsec = current_security();
@@ -94,7 +95,7 @@
if (str_len >= PAGE_SIZE)
return -ENOMEM;
- ctx = kmalloc(sizeof(*ctx) + str_len + 1, GFP_KERNEL);
+ ctx = kmalloc(sizeof(*ctx) + str_len + 1, gfp);
if (!ctx)
return -ENOMEM;
@@ -103,7 +104,7 @@
ctx->ctx_len = str_len;
memcpy(ctx->ctx_str, &uctx[1], str_len);
ctx->ctx_str[str_len] = '\0';
- rc = security_context_to_sid(ctx->ctx_str, str_len, &ctx->ctx_sid);
+ rc = security_context_to_sid(ctx->ctx_str, str_len, &ctx->ctx_sid, gfp);
if (rc)
goto err;
@@ -282,9 +283,10 @@
* LSM hook implementation that allocs and transfers uctx spec to xfrm_policy.
*/
int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
- struct xfrm_user_sec_ctx *uctx)
+ struct xfrm_user_sec_ctx *uctx,
+ gfp_t gfp)
{
- return selinux_xfrm_alloc_user(ctxp, uctx);
+ return selinux_xfrm_alloc_user(ctxp, uctx, gfp);
}
/*
@@ -332,7 +334,7 @@
int selinux_xfrm_state_alloc(struct xfrm_state *x,
struct xfrm_user_sec_ctx *uctx)
{
- return selinux_xfrm_alloc_user(&x->security, uctx);
+ return selinux_xfrm_alloc_user(&x->security, uctx, GFP_KERNEL);
}
/*
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 7a20897..7403f34 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -133,7 +133,7 @@
kfree(data);
}
snd_card_unref(compr->card);
- return 0;
+ return ret;
}
static int snd_compr_free(struct inode *inode, struct file *f)
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index ec4536c..dafcf82 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -932,7 +932,7 @@
}
EXPORT_SYMBOL_GPL(snd_hda_bus_new);
-#ifdef CONFIG_SND_HDA_GENERIC
+#if IS_ENABLED(CONFIG_SND_HDA_GENERIC)
#define is_generic_config(codec) \
(codec->modelname && !strcmp(codec->modelname, "generic"))
#else
@@ -1339,23 +1339,15 @@
/*
* Dynamic symbol binding for the codec parsers
*/
-#ifdef MODULE
-#define load_parser_sym(sym) ((int (*)(struct hda_codec *))symbol_request(sym))
-#define unload_parser_addr(addr) symbol_put_addr(addr)
-#else
-#define load_parser_sym(sym) (sym)
-#define unload_parser_addr(addr) do {} while (0)
-#endif
#define load_parser(codec, sym) \
- ((codec)->parser = load_parser_sym(sym))
+ ((codec)->parser = (int (*)(struct hda_codec *))symbol_request(sym))
static void unload_parser(struct hda_codec *codec)
{
- if (codec->parser) {
- unload_parser_addr(codec->parser);
- codec->parser = NULL;
- }
+ if (codec->parser)
+ symbol_put_addr(codec->parser);
+ codec->parser = NULL;
}
/*
@@ -1570,7 +1562,7 @@
EXPORT_SYMBOL_GPL(snd_hda_codec_update_widgets);
-#ifdef CONFIG_SND_HDA_CODEC_HDMI
+#if IS_ENABLED(CONFIG_SND_HDA_CODEC_HDMI)
/* if all audio out widgets are digital, let's assume the codec as a HDMI/DP */
static bool is_likely_hdmi_codec(struct hda_codec *codec)
{
@@ -1620,12 +1612,20 @@
patch = codec->preset->patch;
if (!patch) {
unload_parser(codec); /* to be sure */
- if (is_likely_hdmi_codec(codec))
+ if (is_likely_hdmi_codec(codec)) {
+#if IS_MODULE(CONFIG_SND_HDA_CODEC_HDMI)
patch = load_parser(codec, snd_hda_parse_hdmi_codec);
-#ifdef CONFIG_SND_HDA_GENERIC
- if (!patch)
- patch = load_parser(codec, snd_hda_parse_generic_codec);
+#elif IS_BUILTIN(CONFIG_SND_HDA_CODEC_HDMI)
+ patch = snd_hda_parse_hdmi_codec;
#endif
+ }
+ if (!patch) {
+#if IS_MODULE(CONFIG_SND_HDA_GENERIC)
+ patch = load_parser(codec, snd_hda_parse_generic_codec);
+#elif IS_BUILTIN(CONFIG_SND_HDA_GENERIC)
+ patch = snd_hda_parse_generic_codec;
+#endif
+ }
if (!patch) {
printk(KERN_ERR "hda-codec: No codec parser is available\n");
return -ENODEV;
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 8321a97..d9a09bd 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -3269,7 +3269,7 @@
mutex_unlock(&codec->control_mutex);
snd_hda_codec_flush_cache(codec); /* flush the updates */
if (err >= 0 && spec->cap_sync_hook)
- spec->cap_sync_hook(codec, ucontrol);
+ spec->cap_sync_hook(codec, kcontrol, ucontrol);
return err;
}
@@ -3390,7 +3390,7 @@
return ret;
if (spec->cap_sync_hook)
- spec->cap_sync_hook(codec, ucontrol);
+ spec->cap_sync_hook(codec, kcontrol, ucontrol);
return ret;
}
@@ -3795,7 +3795,7 @@
return 0;
snd_hda_activate_path(codec, path, true, false);
if (spec->cap_sync_hook)
- spec->cap_sync_hook(codec, NULL);
+ spec->cap_sync_hook(codec, NULL, NULL);
path_power_down_sync(codec, old_path);
return 1;
}
@@ -5270,7 +5270,7 @@
}
if (spec->cap_sync_hook)
- spec->cap_sync_hook(codec, NULL);
+ spec->cap_sync_hook(codec, NULL, NULL);
}
/* set right pin controls for digital I/O */
diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h
index 07f7672..c908afb 100644
--- a/sound/pci/hda/hda_generic.h
+++ b/sound/pci/hda/hda_generic.h
@@ -274,6 +274,7 @@
void (*init_hook)(struct hda_codec *codec);
void (*automute_hook)(struct hda_codec *codec);
void (*cap_sync_hook)(struct hda_codec *codec,
+ struct snd_kcontrol *kcontrol,
struct snd_ctl_elem_value *ucontrol);
/* PCM hooks */
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index fa2879a..e354ab1 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -198,7 +198,7 @@
#endif
#if defined(CONFIG_PM) && defined(CONFIG_VGA_SWITCHEROO)
-#ifdef CONFIG_SND_HDA_CODEC_HDMI
+#if IS_ENABLED(CONFIG_SND_HDA_CODEC_HDMI)
#define SUPPORT_VGA_SWITCHEROO
#endif
#endif
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index df3652a..8ed0bcc 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -1026,6 +1026,9 @@
spec->gen.keep_eapd_on = 1;
spec->gen.vmaster_mute.hook = ad_vmaster_eapd_hook;
spec->eapd_nid = 0x12;
+ /* Analog PC Beeper - allow firmware/ACPI beeps */
+ spec->beep_amp = HDA_COMPOSE_AMP_VAL(0x20, 3, 3, HDA_INPUT);
+ spec->gen.beep_nid = 0; /* no digital beep */
}
}
@@ -1092,6 +1095,7 @@
spec = codec->spec;
spec->gen.mixer_nid = 0x20;
+ spec->gen.mixer_merge_nid = 0x21;
spec->gen.beep_nid = 0x10;
set_beep_amp(spec, 0x10, 0, HDA_OUTPUT);
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 54d1479..46ecdbb 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -2662,60 +2662,6 @@
}
/*
- * PCM stuffs
- */
-static void ca0132_setup_stream(struct hda_codec *codec, hda_nid_t nid,
- u32 stream_tag,
- int channel_id, int format)
-{
- unsigned int oldval, newval;
-
- if (!nid)
- return;
-
- snd_printdd(
- "ca0132_setup_stream: NID=0x%x, stream=0x%x, "
- "channel=%d, format=0x%x\n",
- nid, stream_tag, channel_id, format);
-
- /* update the format-id if changed */
- oldval = snd_hda_codec_read(codec, nid, 0,
- AC_VERB_GET_STREAM_FORMAT,
- 0);
- if (oldval != format) {
- msleep(20);
- snd_hda_codec_write(codec, nid, 0,
- AC_VERB_SET_STREAM_FORMAT,
- format);
- }
-
- oldval = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_CONV, 0);
- newval = (stream_tag << 4) | channel_id;
- if (oldval != newval) {
- snd_hda_codec_write(codec, nid, 0,
- AC_VERB_SET_CHANNEL_STREAMID,
- newval);
- }
-}
-
-static void ca0132_cleanup_stream(struct hda_codec *codec, hda_nid_t nid)
-{
- unsigned int val;
-
- if (!nid)
- return;
-
- snd_printdd(KERN_INFO "ca0132_cleanup_stream: NID=0x%x\n", nid);
-
- val = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_CONV, 0);
- if (!val)
- return;
-
- snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_STREAM_FORMAT, 0);
- snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_CHANNEL_STREAMID, 0);
-}
-
-/*
* PCM callbacks
*/
static int ca0132_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
@@ -2726,7 +2672,7 @@
{
struct ca0132_spec *spec = codec->spec;
- ca0132_setup_stream(codec, spec->dacs[0], stream_tag, 0, format);
+ snd_hda_codec_setup_stream(codec, spec->dacs[0], stream_tag, 0, format);
return 0;
}
@@ -2745,7 +2691,7 @@
if (spec->effects_switch[PLAY_ENHANCEMENT - EFFECT_START_NID])
msleep(50);
- ca0132_cleanup_stream(codec, spec->dacs[0]);
+ snd_hda_codec_cleanup_stream(codec, spec->dacs[0]);
return 0;
}
@@ -2822,10 +2768,8 @@
unsigned int format,
struct snd_pcm_substream *substream)
{
- struct ca0132_spec *spec = codec->spec;
-
- ca0132_setup_stream(codec, spec->adcs[substream->number],
- stream_tag, 0, format);
+ snd_hda_codec_setup_stream(codec, hinfo->nid,
+ stream_tag, 0, format);
return 0;
}
@@ -2839,7 +2783,7 @@
if (spec->dsp_state == DSP_DOWNLOADING)
return 0;
- ca0132_cleanup_stream(codec, hinfo->nid);
+ snd_hda_codec_cleanup_stream(codec, hinfo->nid);
return 0;
}
@@ -4742,6 +4686,8 @@
return err;
codec->patch_ops = ca0132_patch_ops;
+ codec->pcm_format_first = 1;
+ codec->no_sticky_stream = 1;
return 0;
}
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 4e0ec146..bcf91be 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -3291,7 +3291,8 @@
}
static void cxt_update_headset_mode_hook(struct hda_codec *codec,
- struct snd_ctl_elem_value *ucontrol)
+ struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
{
cxt_update_headset_mode(codec);
}
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index d9693ca..8d0a844 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -708,7 +708,8 @@
}
static void alc_inv_dmic_hook(struct hda_codec *codec,
- struct snd_ctl_elem_value *ucontrol)
+ struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
{
alc_inv_dmic_sync(codec, false);
}
@@ -3218,7 +3219,8 @@
/* turn on/off mic-mute LED per capture hook */
static void alc269_fixup_hp_gpio_mic_mute_hook(struct hda_codec *codec,
- struct snd_ctl_elem_value *ucontrol)
+ struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
{
struct alc_spec *spec = codec->spec;
unsigned int oldval = spec->gpio_led;
@@ -3528,7 +3530,8 @@
}
static void alc_update_headset_mode_hook(struct hda_codec *codec,
- struct snd_ctl_elem_value *ucontrol)
+ struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
{
alc_update_headset_mode(codec);
}
@@ -3613,6 +3616,19 @@
}
}
+static void alc_no_shutup(struct hda_codec *codec)
+{
+}
+
+static void alc_fixup_no_shutup(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+ struct alc_spec *spec = codec->spec;
+ spec->shutup = alc_no_shutup;
+ }
+}
+
static void alc_fixup_headset_mode_alc668(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -3841,6 +3857,7 @@
ALC269_FIXUP_HP_GPIO_LED,
ALC269_FIXUP_INV_DMIC,
ALC269_FIXUP_LENOVO_DOCK,
+ ALC269_FIXUP_NO_SHUTUP,
ALC286_FIXUP_SONY_MIC_NO_PRESENCE,
ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT,
ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -4017,6 +4034,10 @@
.type = HDA_FIXUP_FUNC,
.v.func = alc_fixup_inv_dmic_0x12,
},
+ [ALC269_FIXUP_NO_SHUTUP] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc_fixup_no_shutup,
+ },
[ALC269_FIXUP_LENOVO_DOCK] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
@@ -4250,6 +4271,7 @@
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x1025, 0x0283, "Acer TravelMate 8371", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x1025, 0x029b, "Acer 1810TZ", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x1025, 0x0349, "Acer AOD260", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x1025, 0x047c, "Acer AC700", ALC269_FIXUP_ACER_AC700),
@@ -4305,7 +4327,9 @@
SND_PCI_QUIRK(0x1028, 0x0651, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0652, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0653, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0657, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0658, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x065f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0662, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x15cc, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x15cd, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
@@ -4314,6 +4338,54 @@
SND_PCI_QUIRK(0x103c, 0x1973, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED),
+ /* ALC282 */
+ SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2213, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2266, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2267, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2268, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2269, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x226a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x226b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x227a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x227b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x229e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22a0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22b2, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22b7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22bf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22c0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22c1, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22c2, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22cd, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22ce, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22cf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22d0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ /* ALC290 */
+ SND_PCI_QUIRK(0x103c, 0x2260, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2261, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2262, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2263, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2264, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2265, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x227d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x227e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x227f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2280, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2281, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2282, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x2289, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x228a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x228b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x228c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x228d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x228e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22c5, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22c6, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22c7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22c8, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22c3, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+ SND_PCI_QUIRK(0x103c, 0x22c4, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
SND_PCI_QUIRK_VENDOR(0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED),
SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -4329,6 +4401,7 @@
SND_PCI_QUIRK(0x1043, 0x8398, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC),
SND_PCI_QUIRK(0x1043, 0x83ce, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC),
SND_PCI_QUIRK(0x1043, 0x8516, "ASUS X101CH", ALC269_FIXUP_ASUS_X101),
+ SND_PCI_QUIRK(0x104d, 0x90b5, "Sony VAIO Pro 11", ALC286_FIXUP_SONY_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x104d, 0x90b6, "Sony VAIO Pro 13", ALC286_FIXUP_SONY_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x104d, 0x9073, "Sony VAIO", ALC275_FIXUP_SONY_VAIO_GPIO2),
SND_PCI_QUIRK(0x104d, 0x907b, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ),
@@ -4350,6 +4423,7 @@
SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+ SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),
SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC),
SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -4434,9 +4508,6 @@
if (spec->codec_variant != ALC269_TYPE_ALC269VB)
return;
- /* ALC271X doesn't seem to support these COEFs (bko#52181) */
- if (!strcmp(codec->chip_name, "ALC271X"))
- return;
if ((alc_get_coef0(codec) & 0x00ff) < 0x015) {
alc_write_coef_idx(codec, 0xf, 0x960b);
@@ -5106,12 +5177,13 @@
SND_PCI_QUIRK(0x1025, 0x038b, "Acer Aspire 8943G", ALC662_FIXUP_ASPIRE),
SND_PCI_QUIRK(0x1028, 0x05d8, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x05db, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x060a, "Dell XPS 13", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0623, "Dell", ALC668_FIXUP_AUTO_MUTE),
SND_PCI_QUIRK(0x1028, 0x0624, "Dell", ALC668_FIXUP_AUTO_MUTE),
SND_PCI_QUIRK(0x1028, 0x0625, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0626, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0628, "Dell", ALC668_FIXUP_AUTO_MUTE),
- SND_PCI_QUIRK(0x1028, 0x064e, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x064e, "Dell", ALC668_FIXUP_AUTO_MUTE),
SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800),
SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A_CHMAP),
SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_CHMAP),
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 6998cf2..3bc29c9 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -83,6 +83,7 @@
STAC_DELL_M6_BOTH,
STAC_DELL_EQ,
STAC_ALIENWARE_M17X,
+ STAC_92HD89XX_HP_FRONT_JACK,
STAC_92HD73XX_MODELS
};
@@ -97,6 +98,7 @@
STAC_92HD83XXX_HP_LED,
STAC_92HD83XXX_HP_INV_LED,
STAC_92HD83XXX_HP_MIC_LED,
+ STAC_HP_LED_GPIO10,
STAC_92HD83XXX_HEADSET_JACK,
STAC_92HD83XXX_HP,
STAC_HP_ENVY_BASS,
@@ -194,7 +196,7 @@
int default_polarity;
unsigned int mic_mute_led_gpio; /* capture mute LED GPIO */
- bool mic_mute_led_on; /* current mic mute state */
+ unsigned int mic_enabled; /* current mic mute state (bitmask) */
/* stream */
unsigned int stream_delay;
@@ -324,19 +326,26 @@
/* hook for controlling mic-mute LED GPIO */
static void stac_capture_led_hook(struct hda_codec *codec,
- struct snd_ctl_elem_value *ucontrol)
+ struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
{
struct sigmatel_spec *spec = codec->spec;
- bool mute;
+ unsigned int mask;
+ bool cur_mute, prev_mute;
- if (!ucontrol)
+ if (!kcontrol || !ucontrol)
return;
- mute = !(ucontrol->value.integer.value[0] ||
- ucontrol->value.integer.value[1]);
- if (spec->mic_mute_led_on != mute) {
- spec->mic_mute_led_on = mute;
- if (mute)
+ mask = 1U << snd_ctl_get_ioffidx(kcontrol, &ucontrol->id);
+ prev_mute = !spec->mic_enabled;
+ if (ucontrol->value.integer.value[0] ||
+ ucontrol->value.integer.value[1])
+ spec->mic_enabled |= mask;
+ else
+ spec->mic_enabled &= ~mask;
+ cur_mute = !spec->mic_enabled;
+ if (cur_mute != prev_mute) {
+ if (cur_mute)
spec->gpio_data |= spec->mic_mute_led_gpio;
else
spec->gpio_data &= ~spec->mic_mute_led_gpio;
@@ -1788,6 +1797,12 @@
{}
};
+static const struct hda_pintbl stac92hd89xx_hp_front_jack_pin_configs[] = {
+ { 0x0a, 0x02214030 },
+ { 0x0b, 0x02A19010 },
+ {}
+};
+
static void stac92hd73xx_fixup_ref(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -1906,6 +1921,10 @@
[STAC_92HD73XX_NO_JD] = {
.type = HDA_FIXUP_FUNC,
.v.func = stac92hd73xx_fixup_no_jd,
+ },
+ [STAC_92HD89XX_HP_FRONT_JACK] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = stac92hd89xx_hp_front_jack_pin_configs,
}
};
@@ -1966,6 +1985,8 @@
"Alienware M17x", STAC_ALIENWARE_M17X),
SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0490,
"Alienware M17x R3", STAC_DELL_EQ),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x2b17,
+ "unknown HP", STAC_92HD89XX_HP_FRONT_JACK),
{} /* terminator */
};
@@ -2110,6 +2131,17 @@
}
}
+static void stac92hd83xxx_fixup_hp_led_gpio10(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ struct sigmatel_spec *spec = codec->spec;
+
+ if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+ spec->gpio_led = 0x10; /* GPIO4 */
+ spec->default_polarity = 0;
+ }
+}
+
static void stac92hd83xxx_fixup_headset_jack(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -2604,6 +2636,12 @@
.chained = true,
.chain_id = STAC_92HD83XXX_HP,
},
+ [STAC_HP_LED_GPIO10] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = stac92hd83xxx_fixup_hp_led_gpio10,
+ .chained = true,
+ .chain_id = STAC_92HD83XXX_HP,
+ },
[STAC_92HD83XXX_HEADSET_JACK] = {
.type = HDA_FIXUP_FUNC,
.v.func = stac92hd83xxx_fixup_headset_jack,
@@ -2682,6 +2720,8 @@
"HP", STAC_92HD83XXX_HP_cNB11_INTQUAD),
SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1888,
"HP Envy Spectre", STAC_HP_ENVY_BASS),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1899,
+ "HP Folio 13", STAC_HP_LED_GPIO10),
SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x18df,
"HP Folio", STAC_HP_BNB13_EQ),
SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x18F8,
@@ -4462,7 +4502,7 @@
if (spec->mic_mute_led_gpio) {
spec->gpio_mask |= spec->mic_mute_led_gpio;
spec->gpio_dir |= spec->mic_mute_led_gpio;
- spec->mic_mute_led_on = true;
+ spec->mic_enabled = 0;
spec->gpio_data |= spec->mic_mute_led_gpio;
spec->gen.cap_sync_hook = stac_capture_led_hook;
diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c
index 5799fbc..8fe3b8c 100644
--- a/sound/pci/hda/thinkpad_helper.c
+++ b/sound/pci/hda/thinkpad_helper.c
@@ -39,6 +39,7 @@
}
static void update_tpacpi_micmute_led(struct hda_codec *codec,
+ struct snd_kcontrol *kcontrol,
struct snd_ctl_elem_value *ucontrol)
{
if (!ucontrol || !led_set_func)
diff --git a/sound/pci/oxygen/xonar_dg.c b/sound/pci/oxygen/xonar_dg.c
index ed6f199..4cf3200 100644
--- a/sound/pci/oxygen/xonar_dg.c
+++ b/sound/pci/oxygen/xonar_dg.c
@@ -238,11 +238,21 @@
cs4245_write_spi(chip, CS4245_MCLK_FREQ);
}
+static inline unsigned int shift_bits(unsigned int value,
+ unsigned int shift_from,
+ unsigned int shift_to,
+ unsigned int mask)
+{
+ if (shift_from < shift_to)
+ return (value << (shift_to - shift_from)) & mask;
+ else
+ return (value >> (shift_from - shift_to)) & mask;
+}
+
unsigned int adjust_dg_dac_routing(struct oxygen *chip,
unsigned int play_routing)
{
struct dg *data = chip->model_data;
- unsigned int routing = 0;
switch (data->output_sel) {
case PLAYBACK_DST_HP:
@@ -252,15 +262,23 @@
OXYGEN_PLAY_MUTE67, OXYGEN_PLAY_MUTE_MASK);
break;
case PLAYBACK_DST_MULTICH:
- routing = (0 << OXYGEN_PLAY_DAC0_SOURCE_SHIFT) |
- (2 << OXYGEN_PLAY_DAC1_SOURCE_SHIFT) |
- (1 << OXYGEN_PLAY_DAC2_SOURCE_SHIFT) |
- (0 << OXYGEN_PLAY_DAC3_SOURCE_SHIFT);
oxygen_write8_masked(chip, OXYGEN_PLAY_ROUTING,
OXYGEN_PLAY_MUTE01, OXYGEN_PLAY_MUTE_MASK);
break;
}
- return routing;
+ return (play_routing & OXYGEN_PLAY_DAC0_SOURCE_MASK) |
+ shift_bits(play_routing,
+ OXYGEN_PLAY_DAC2_SOURCE_SHIFT,
+ OXYGEN_PLAY_DAC1_SOURCE_SHIFT,
+ OXYGEN_PLAY_DAC1_SOURCE_MASK) |
+ shift_bits(play_routing,
+ OXYGEN_PLAY_DAC1_SOURCE_SHIFT,
+ OXYGEN_PLAY_DAC2_SOURCE_SHIFT,
+ OXYGEN_PLAY_DAC2_SOURCE_MASK) |
+ shift_bits(play_routing,
+ OXYGEN_PLAY_DAC0_SOURCE_SHIFT,
+ OXYGEN_PLAY_DAC3_SOURCE_SHIFT,
+ OXYGEN_PLAY_DAC3_SOURCE_MASK);
}
void dump_cs4245_registers(struct oxygen *chip,
diff --git a/sound/soc/blackfin/Kconfig b/sound/soc/blackfin/Kconfig
index 54f74f8..4544d8e 100644
--- a/sound/soc/blackfin/Kconfig
+++ b/sound/soc/blackfin/Kconfig
@@ -11,7 +11,7 @@
config SND_BF5XX_SOC_SSM2602
tristate "SoC SSM2602 Audio Codec Add-On Card support"
- depends on SND_BF5XX_I2S && (SPI_MASTER || I2C)
+ depends on SND_BF5XX_I2S && SND_SOC_I2C_AND_SPI
select SND_BF5XX_SOC_I2S if !BF60x
select SND_BF6XX_SOC_I2S if BF60x
select SND_SOC_SSM2602
@@ -21,10 +21,9 @@
config SND_SOC_BFIN_EVAL_ADAU1701
tristate "Support for the EVAL-ADAU1701MINIZ board on Blackfin eval boards"
- depends on SND_BF5XX_I2S
+ depends on SND_BF5XX_I2S && I2C
select SND_BF5XX_SOC_I2S
select SND_SOC_ADAU1701
- select I2C
help
Say Y if you want to add support for the Analog Devices EVAL-ADAU1701MINIZ
board connected to one of the Blackfin evaluation boards like the
@@ -45,7 +44,7 @@
config SND_SOC_BFIN_EVAL_ADAV80X
tristate "Support for the EVAL-ADAV80X boards on Blackfin eval boards"
- depends on SND_BF5XX_I2S && (SPI_MASTER || I2C)
+ depends on SND_BF5XX_I2S && SND_SOC_I2C_AND_SPI
select SND_BF5XX_SOC_I2S
select SND_SOC_ADAV80X
help
@@ -58,7 +57,7 @@
config SND_BF5XX_SOC_AD1836
tristate "SoC AD1836 Audio support for BF5xx"
- depends on SND_BF5XX_I2S
+ depends on SND_BF5XX_I2S && SPI_MASTER
select SND_BF5XX_SOC_I2S
select SND_SOC_AD1836
help
@@ -66,7 +65,7 @@
config SND_BF5XX_SOC_AD193X
tristate "SoC AD193X Audio support for Blackfin"
- depends on SND_BF5XX_I2S
+ depends on SND_BF5XX_I2S && SND_SOC_I2C_AND_SPI
select SND_BF5XX_SOC_I2S
select SND_SOC_AD193X
help
diff --git a/sound/soc/codecs/88pm860x-codec.c b/sound/soc/codecs/88pm860x-codec.c
index 75d0ad5..647a72c 100644
--- a/sound/soc/codecs/88pm860x-codec.c
+++ b/sound/soc/codecs/88pm860x-codec.c
@@ -1328,6 +1328,9 @@
pm860x->codec = codec;
codec->control_data = pm860x->regmap;
+ ret = snd_soc_codec_set_cache_io(codec, 0, 0, SND_SOC_REGMAP);
+ if (ret)
+ return ret;
for (i = 0; i < 4; i++) {
ret = request_threaded_irq(pm860x->irq[i], NULL,
diff --git a/sound/soc/codecs/ad1980.c b/sound/soc/codecs/ad1980.c
index 7257a88..34d965a 100644
--- a/sound/soc/codecs/ad1980.c
+++ b/sound/soc/codecs/ad1980.c
@@ -57,8 +57,8 @@
static const char *ad1980_rec_sel[] = {"Mic", "CD", "NC", "AUX", "Line",
"Stereo Mix", "Mono Mix", "Phone"};
-static const struct soc_enum ad1980_cap_src =
- SOC_ENUM_DOUBLE(AC97_REC_SEL, 8, 0, 7, ad1980_rec_sel);
+static SOC_ENUM_DOUBLE_DECL(ad1980_cap_src,
+ AC97_REC_SEL, 8, 0, ad1980_rec_sel);
static const struct snd_kcontrol_new ad1980_snd_ac97_controls[] = {
SOC_DOUBLE("Master Playback Volume", AC97_MASTER, 8, 0, 31, 1),
diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c
index f295b65..f4d965ebc 100644
--- a/sound/soc/codecs/da732x.c
+++ b/sound/soc/codecs/da732x.c
@@ -1268,11 +1268,23 @@
},
};
+static bool da732x_volatile(struct device *dev, unsigned int reg)
+{
+ switch (reg) {
+ case DA732X_REG_HPL_DAC_OFF_CNTL:
+ case DA732X_REG_HPR_DAC_OFF_CNTL:
+ return true;
+ default:
+ return false;
+ }
+}
+
static const struct regmap_config da732x_regmap = {
.reg_bits = 8,
.val_bits = 8,
.max_register = DA732X_MAX_REG,
+ .volatile_reg = da732x_volatile,
.reg_defaults = da732x_reg_cache,
.num_reg_defaults = ARRAY_SIZE(da732x_reg_cache),
.cache_type = REGCACHE_RBTREE,
diff --git a/sound/soc/codecs/da9055.c b/sound/soc/codecs/da9055.c
index 52b79a4..4228126 100644
--- a/sound/soc/codecs/da9055.c
+++ b/sound/soc/codecs/da9055.c
@@ -1523,8 +1523,15 @@
return 0;
}
+/*
+ * DO NOT change the device Ids. The naming is intentionally specific as both
+ * the CODEC and PMIC parts of this chip are instantiated separately as I2C
+ * devices (both have configurable I2C addresses, and are to all intents and
+ * purposes separate). As a result there are specific DA9055 Ids for CODEC
+ * and PMIC, which must be different to operate together.
+ */
static const struct i2c_device_id da9055_i2c_id[] = {
- { "da9055", 0 },
+ { "da9055-codec", 0 },
{ }
};
MODULE_DEVICE_TABLE(i2c, da9055_i2c_id);
@@ -1532,7 +1539,7 @@
/* I2C codec control layer */
static struct i2c_driver da9055_i2c_driver = {
.driver = {
- .name = "da9055",
+ .name = "da9055-codec",
.owner = THIS_MODULE,
},
.probe = da9055_i2c_probe,
diff --git a/sound/soc/codecs/isabelle.c b/sound/soc/codecs/isabelle.c
index 5839048..cb736dd 100644
--- a/sound/soc/codecs/isabelle.c
+++ b/sound/soc/codecs/isabelle.c
@@ -140,13 +140,17 @@
static const char *isabelle_rx2_texts[] = {"VRX2", "ARX2"};
static const struct soc_enum isabelle_rx1_enum[] = {
- SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 3, 1, isabelle_rx1_texts),
- SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 5, 1, isabelle_rx1_texts),
+ SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 3,
+ ARRAY_SIZE(isabelle_rx1_texts), isabelle_rx1_texts),
+ SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 5,
+ ARRAY_SIZE(isabelle_rx1_texts), isabelle_rx1_texts),
};
static const struct soc_enum isabelle_rx2_enum[] = {
- SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 2, 1, isabelle_rx2_texts),
- SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 4, 1, isabelle_rx2_texts),
+ SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 2,
+ ARRAY_SIZE(isabelle_rx2_texts), isabelle_rx2_texts),
+ SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 4,
+ ARRAY_SIZE(isabelle_rx2_texts), isabelle_rx2_texts),
};
/* Headset DAC playback switches */
@@ -161,13 +165,17 @@
static const char *isabelle_vtx_texts[] = {"AMIC2", "DMIC"};
static const struct soc_enum isabelle_atx_enum[] = {
- SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 7, 1, isabelle_atx_texts),
- SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0, 1, isabelle_atx_texts),
+ SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 7,
+ ARRAY_SIZE(isabelle_atx_texts), isabelle_atx_texts),
+ SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0,
+ ARRAY_SIZE(isabelle_atx_texts), isabelle_atx_texts),
};
static const struct soc_enum isabelle_vtx_enum[] = {
- SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 6, 1, isabelle_vtx_texts),
- SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0, 1, isabelle_vtx_texts),
+ SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 6,
+ ARRAY_SIZE(isabelle_vtx_texts), isabelle_vtx_texts),
+ SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0,
+ ARRAY_SIZE(isabelle_vtx_texts), isabelle_vtx_texts),
};
static const struct snd_kcontrol_new atx_mux_controls =
@@ -183,17 +191,13 @@
/* Left analog microphone selection */
static const char *isabelle_amic2_texts[] = {"Sub Mic", "Aux/FM Right"};
-static const struct soc_enum isabelle_amic1_enum[] = {
- SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 5,
- ARRAY_SIZE(isabelle_amic1_texts),
- isabelle_amic1_texts),
-};
+static SOC_ENUM_SINGLE_DECL(isabelle_amic1_enum,
+ ISABELLE_AMIC_CFG_REG, 5,
+ isabelle_amic1_texts);
-static const struct soc_enum isabelle_amic2_enum[] = {
- SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 4,
- ARRAY_SIZE(isabelle_amic2_texts),
- isabelle_amic2_texts),
-};
+static SOC_ENUM_SINGLE_DECL(isabelle_amic2_enum,
+ ISABELLE_AMIC_CFG_REG, 4,
+ isabelle_amic2_texts);
static const struct snd_kcontrol_new amic1_control =
SOC_DAPM_ENUM("Route", isabelle_amic1_enum);
@@ -206,16 +210,20 @@
static const char *isabelle_st_voice_texts[] = {"VTX1", "VTX2"};
static const struct soc_enum isabelle_st_audio_enum[] = {
- SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA1_CFG_REG, 7, 1,
+ SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA1_CFG_REG, 7,
+ ARRAY_SIZE(isabelle_st_audio_texts),
isabelle_st_audio_texts),
- SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA2_CFG_REG, 7, 1,
+ SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA2_CFG_REG, 7,
+ ARRAY_SIZE(isabelle_st_audio_texts),
isabelle_st_audio_texts),
};
static const struct soc_enum isabelle_st_voice_enum[] = {
- SOC_ENUM_SINGLE(ISABELLE_VTX_STPGA1_CFG_REG, 7, 1,
+ SOC_ENUM_SINGLE(ISABELLE_VTX_STPGA1_CFG_REG, 7,
+ ARRAY_SIZE(isabelle_st_voice_texts),
isabelle_st_voice_texts),
- SOC_ENUM_SINGLE(ISABELLE_VTX2_STPGA2_CFG_REG, 7, 1,
+ SOC_ENUM_SINGLE(ISABELLE_VTX2_STPGA2_CFG_REG, 7,
+ ARRAY_SIZE(isabelle_st_voice_texts),
isabelle_st_voice_texts),
};
diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
index 51f9b3d..9f714ea 100644
--- a/sound/soc/codecs/max98090.c
+++ b/sound/soc/codecs/max98090.c
@@ -336,6 +336,7 @@
case M98090_REG_RECORD_TDM_SLOT:
case M98090_REG_SAMPLE_RATE:
case M98090_REG_DMIC34_BIQUAD_BASE ... M98090_REG_DMIC34_BIQUAD_BASE + 0x0E:
+ case M98090_REG_REVISION_ID:
return true;
default:
return false;
@@ -1769,16 +1770,6 @@
switch (level) {
case SND_SOC_BIAS_ON:
- if (codec->dapm.bias_level == SND_SOC_BIAS_OFF) {
- ret = regcache_sync(max98090->regmap);
-
- if (ret != 0) {
- dev_err(codec->dev,
- "Failed to sync cache: %d\n", ret);
- return ret;
- }
- }
-
if (max98090->jack_state == M98090_JACK_STATE_HEADSET) {
/*
* Set to normal bias level.
@@ -1792,6 +1783,16 @@
break;
case SND_SOC_BIAS_STANDBY:
+ if (codec->dapm.bias_level == SND_SOC_BIAS_OFF) {
+ ret = regcache_sync(max98090->regmap);
+ if (ret != 0) {
+ dev_err(codec->dev,
+ "Failed to sync cache: %d\n", ret);
+ return ret;
+ }
+ }
+ break;
+
case SND_SOC_BIAS_OFF:
/* Set internal pull-up to lowest power mode */
snd_soc_update_bits(codec, M98090_REG_JACK_DETECT,
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index a3fb411..8869249 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -2093,6 +2093,7 @@
#ifdef CONFIG_ACPI
static struct acpi_device_id rt5640_acpi_match[] = {
{ "INT33CA", 0 },
+ { "10EC5640", 0 },
{ },
};
MODULE_DEVICE_TABLE(acpi, rt5640_acpi_match);
diff --git a/sound/soc/codecs/si476x.c b/sound/soc/codecs/si476x.c
index 52e7cb0..fa2b8e0 100644
--- a/sound/soc/codecs/si476x.c
+++ b/sound/soc/codecs/si476x.c
@@ -210,7 +210,7 @@
static int si476x_codec_probe(struct snd_soc_codec *codec)
{
codec->control_data = dev_get_regmap(codec->dev->parent, NULL);
- return 0;
+ return snd_soc_codec_set_cache_io(codec, 0, 0, SND_SOC_REGMAP);
}
static struct snd_soc_dai_ops si476x_dai_ops = {
diff --git a/sound/soc/codecs/sta32x.c b/sound/soc/codecs/sta32x.c
index 06edb39..2735361 100644
--- a/sound/soc/codecs/sta32x.c
+++ b/sound/soc/codecs/sta32x.c
@@ -187,42 +187,42 @@
13, 16, TLV_DB_SCALE_ITEM(-1500, 300, 0),
};
-static const struct soc_enum sta32x_drc_ac_enum =
- SOC_ENUM_SINGLE(STA32X_CONFD, STA32X_CONFD_DRC_SHIFT,
- 2, sta32x_drc_ac);
-static const struct soc_enum sta32x_auto_eq_enum =
- SOC_ENUM_SINGLE(STA32X_AUTO1, STA32X_AUTO1_AMEQ_SHIFT,
- 3, sta32x_auto_eq_mode);
-static const struct soc_enum sta32x_auto_gc_enum =
- SOC_ENUM_SINGLE(STA32X_AUTO1, STA32X_AUTO1_AMGC_SHIFT,
- 4, sta32x_auto_gc_mode);
-static const struct soc_enum sta32x_auto_xo_enum =
- SOC_ENUM_SINGLE(STA32X_AUTO2, STA32X_AUTO2_XO_SHIFT,
- 16, sta32x_auto_xo_mode);
-static const struct soc_enum sta32x_preset_eq_enum =
- SOC_ENUM_SINGLE(STA32X_AUTO3, STA32X_AUTO3_PEQ_SHIFT,
- 32, sta32x_preset_eq_mode);
-static const struct soc_enum sta32x_limiter_ch1_enum =
- SOC_ENUM_SINGLE(STA32X_C1CFG, STA32X_CxCFG_LS_SHIFT,
- 3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter_ch2_enum =
- SOC_ENUM_SINGLE(STA32X_C2CFG, STA32X_CxCFG_LS_SHIFT,
- 3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter_ch3_enum =
- SOC_ENUM_SINGLE(STA32X_C3CFG, STA32X_CxCFG_LS_SHIFT,
- 3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter1_attack_rate_enum =
- SOC_ENUM_SINGLE(STA32X_L1AR, STA32X_LxA_SHIFT,
- 16, sta32x_limiter_attack_rate);
-static const struct soc_enum sta32x_limiter2_attack_rate_enum =
- SOC_ENUM_SINGLE(STA32X_L2AR, STA32X_LxA_SHIFT,
- 16, sta32x_limiter_attack_rate);
-static const struct soc_enum sta32x_limiter1_release_rate_enum =
- SOC_ENUM_SINGLE(STA32X_L1AR, STA32X_LxR_SHIFT,
- 16, sta32x_limiter_release_rate);
-static const struct soc_enum sta32x_limiter2_release_rate_enum =
- SOC_ENUM_SINGLE(STA32X_L2AR, STA32X_LxR_SHIFT,
- 16, sta32x_limiter_release_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_drc_ac_enum,
+ STA32X_CONFD, STA32X_CONFD_DRC_SHIFT,
+ sta32x_drc_ac);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_eq_enum,
+ STA32X_AUTO1, STA32X_AUTO1_AMEQ_SHIFT,
+ sta32x_auto_eq_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_gc_enum,
+ STA32X_AUTO1, STA32X_AUTO1_AMGC_SHIFT,
+ sta32x_auto_gc_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_xo_enum,
+ STA32X_AUTO2, STA32X_AUTO2_XO_SHIFT,
+ sta32x_auto_xo_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_preset_eq_enum,
+ STA32X_AUTO3, STA32X_AUTO3_PEQ_SHIFT,
+ sta32x_preset_eq_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch1_enum,
+ STA32X_C1CFG, STA32X_CxCFG_LS_SHIFT,
+ sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch2_enum,
+ STA32X_C2CFG, STA32X_CxCFG_LS_SHIFT,
+ sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch3_enum,
+ STA32X_C3CFG, STA32X_CxCFG_LS_SHIFT,
+ sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter1_attack_rate_enum,
+ STA32X_L1AR, STA32X_LxA_SHIFT,
+ sta32x_limiter_attack_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter2_attack_rate_enum,
+ STA32X_L2AR, STA32X_LxA_SHIFT,
+ sta32x_limiter_attack_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter1_release_rate_enum,
+ STA32X_L1AR, STA32X_LxR_SHIFT,
+ sta32x_limiter_release_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter2_release_rate_enum,
+ STA32X_L2AR, STA32X_LxR_SHIFT,
+ sta32x_limiter_release_rate);
/* byte array controls for setting biquad, mixer, scaling coefficients;
* for biquads all five coefficients need to be set in one go,
@@ -331,7 +331,7 @@
static int sta32x_cache_sync(struct snd_soc_codec *codec)
{
- struct sta32x_priv *sta32x = codec->control_data;
+ struct sta32x_priv *sta32x = snd_soc_codec_get_drvdata(codec);
unsigned int mute;
int rc;
@@ -434,7 +434,7 @@
SOC_ENUM("Limiter1 Attack Rate (dB/ms)", sta32x_limiter1_attack_rate_enum),
SOC_ENUM("Limiter2 Attack Rate (dB/ms)", sta32x_limiter2_attack_rate_enum),
SOC_ENUM("Limiter1 Release Rate (dB/ms)", sta32x_limiter1_release_rate_enum),
-SOC_ENUM("Limiter2 Release Rate (dB/ms)", sta32x_limiter1_release_rate_enum),
+SOC_ENUM("Limiter2 Release Rate (dB/ms)", sta32x_limiter2_release_rate_enum),
/* depending on mode, the attack/release thresholds have
* two different enum definitions; provide both
diff --git a/sound/soc/codecs/wm8400.c b/sound/soc/codecs/wm8400.c
index 48dc7d2..6d684d9 100644
--- a/sound/soc/codecs/wm8400.c
+++ b/sound/soc/codecs/wm8400.c
@@ -117,19 +117,23 @@
static const char *wm8400_digital_sidetone[] =
{"None", "Left ADC", "Right ADC", "Reserved"};
-static const struct soc_enum wm8400_left_digital_sidetone_enum =
-SOC_ENUM_SINGLE(WM8400_DIGITAL_SIDE_TONE,
- WM8400_ADC_TO_DACL_SHIFT, 2, wm8400_digital_sidetone);
+static SOC_ENUM_SINGLE_DECL(wm8400_left_digital_sidetone_enum,
+ WM8400_DIGITAL_SIDE_TONE,
+ WM8400_ADC_TO_DACL_SHIFT,
+ wm8400_digital_sidetone);
-static const struct soc_enum wm8400_right_digital_sidetone_enum =
-SOC_ENUM_SINGLE(WM8400_DIGITAL_SIDE_TONE,
- WM8400_ADC_TO_DACR_SHIFT, 2, wm8400_digital_sidetone);
+static SOC_ENUM_SINGLE_DECL(wm8400_right_digital_sidetone_enum,
+ WM8400_DIGITAL_SIDE_TONE,
+ WM8400_ADC_TO_DACR_SHIFT,
+ wm8400_digital_sidetone);
static const char *wm8400_adcmode[] =
{"Hi-fi mode", "Voice mode 1", "Voice mode 2", "Voice mode 3"};
-static const struct soc_enum wm8400_right_adcmode_enum =
-SOC_ENUM_SINGLE(WM8400_ADC_CTRL, WM8400_ADC_HPF_CUT_SHIFT, 3, wm8400_adcmode);
+static SOC_ENUM_SINGLE_DECL(wm8400_right_adcmode_enum,
+ WM8400_ADC_CTRL,
+ WM8400_ADC_HPF_CUT_SHIFT,
+ wm8400_adcmode);
static const struct snd_kcontrol_new wm8400_snd_controls[] = {
/* INMIXL */
@@ -422,9 +426,10 @@
static const char *wm8400_ainlmux[] =
{"INMIXL Mix", "RXVOICE Mix", "DIFFINL Mix"};
-static const struct soc_enum wm8400_ainlmux_enum =
-SOC_ENUM_SINGLE( WM8400_INPUT_MIXER1, WM8400_AINLMODE_SHIFT,
- ARRAY_SIZE(wm8400_ainlmux), wm8400_ainlmux);
+static SOC_ENUM_SINGLE_DECL(wm8400_ainlmux_enum,
+ WM8400_INPUT_MIXER1,
+ WM8400_AINLMODE_SHIFT,
+ wm8400_ainlmux);
static const struct snd_kcontrol_new wm8400_dapm_ainlmux_controls =
SOC_DAPM_ENUM("Route", wm8400_ainlmux_enum);
@@ -435,9 +440,10 @@
static const char *wm8400_ainrmux[] =
{"INMIXR Mix", "RXVOICE Mix", "DIFFINR Mix"};
-static const struct soc_enum wm8400_ainrmux_enum =
-SOC_ENUM_SINGLE( WM8400_INPUT_MIXER1, WM8400_AINRMODE_SHIFT,
- ARRAY_SIZE(wm8400_ainrmux), wm8400_ainrmux);
+static SOC_ENUM_SINGLE_DECL(wm8400_ainrmux_enum,
+ WM8400_INPUT_MIXER1,
+ WM8400_AINRMODE_SHIFT,
+ wm8400_ainrmux);
static const struct snd_kcontrol_new wm8400_dapm_ainrmux_controls =
SOC_DAPM_ENUM("Route", wm8400_ainrmux_enum);
diff --git a/sound/soc/codecs/wm8770.c b/sound/soc/codecs/wm8770.c
index 89a18d8..5bce210 100644
--- a/sound/soc/codecs/wm8770.c
+++ b/sound/soc/codecs/wm8770.c
@@ -196,8 +196,8 @@
"AIN5", "AIN6", "AIN7", "AIN8"
};
-static const struct soc_enum ain_enum =
- SOC_ENUM_DOUBLE(WM8770_ADCMUX, 0, 4, 8, ain_text);
+static SOC_ENUM_DOUBLE_DECL(ain_enum,
+ WM8770_ADCMUX, 0, 4, ain_text);
static const struct snd_kcontrol_new ain_mux =
SOC_DAPM_ENUM("Capture Mux", ain_enum);
diff --git a/sound/soc/codecs/wm8900.c b/sound/soc/codecs/wm8900.c
index e98bc70..43c2201 100644
--- a/sound/soc/codecs/wm8900.c
+++ b/sound/soc/codecs/wm8900.c
@@ -304,53 +304,53 @@
static const char *mic_bias_level_txt[] = { "0.9*AVDD", "0.65*AVDD" };
-static const struct soc_enum mic_bias_level =
-SOC_ENUM_SINGLE(WM8900_REG_INCTL, 8, 2, mic_bias_level_txt);
+static SOC_ENUM_SINGLE_DECL(mic_bias_level,
+ WM8900_REG_INCTL, 8, mic_bias_level_txt);
static const char *dac_mute_rate_txt[] = { "Fast", "Slow" };
-static const struct soc_enum dac_mute_rate =
-SOC_ENUM_SINGLE(WM8900_REG_DACCTRL, 7, 2, dac_mute_rate_txt);
+static SOC_ENUM_SINGLE_DECL(dac_mute_rate,
+ WM8900_REG_DACCTRL, 7, dac_mute_rate_txt);
static const char *dac_deemphasis_txt[] = {
"Disabled", "32kHz", "44.1kHz", "48kHz"
};
-static const struct soc_enum dac_deemphasis =
-SOC_ENUM_SINGLE(WM8900_REG_DACCTRL, 4, 4, dac_deemphasis_txt);
+static SOC_ENUM_SINGLE_DECL(dac_deemphasis,
+ WM8900_REG_DACCTRL, 4, dac_deemphasis_txt);
static const char *adc_hpf_cut_txt[] = {
"Hi-fi mode", "Voice mode 1", "Voice mode 2", "Voice mode 3"
};
-static const struct soc_enum adc_hpf_cut =
-SOC_ENUM_SINGLE(WM8900_REG_ADCCTRL, 5, 4, adc_hpf_cut_txt);
+static SOC_ENUM_SINGLE_DECL(adc_hpf_cut,
+ WM8900_REG_ADCCTRL, 5, adc_hpf_cut_txt);
static const char *lr_txt[] = {
"Left", "Right"
};
-static const struct soc_enum aifl_src =
-SOC_ENUM_SINGLE(WM8900_REG_AUDIO1, 15, 2, lr_txt);
+static SOC_ENUM_SINGLE_DECL(aifl_src,
+ WM8900_REG_AUDIO1, 15, lr_txt);
-static const struct soc_enum aifr_src =
-SOC_ENUM_SINGLE(WM8900_REG_AUDIO1, 14, 2, lr_txt);
+static SOC_ENUM_SINGLE_DECL(aifr_src,
+ WM8900_REG_AUDIO1, 14, lr_txt);
-static const struct soc_enum dacl_src =
-SOC_ENUM_SINGLE(WM8900_REG_AUDIO2, 15, 2, lr_txt);
+static SOC_ENUM_SINGLE_DECL(dacl_src,
+ WM8900_REG_AUDIO2, 15, lr_txt);
-static const struct soc_enum dacr_src =
-SOC_ENUM_SINGLE(WM8900_REG_AUDIO2, 14, 2, lr_txt);
+static SOC_ENUM_SINGLE_DECL(dacr_src,
+ WM8900_REG_AUDIO2, 14, lr_txt);
static const char *sidetone_txt[] = {
"Disabled", "Left ADC", "Right ADC"
};
-static const struct soc_enum dacl_sidetone =
-SOC_ENUM_SINGLE(WM8900_REG_SIDETONE, 2, 3, sidetone_txt);
+static SOC_ENUM_SINGLE_DECL(dacl_sidetone,
+ WM8900_REG_SIDETONE, 2, sidetone_txt);
-static const struct soc_enum dacr_sidetone =
-SOC_ENUM_SINGLE(WM8900_REG_SIDETONE, 0, 3, sidetone_txt);
+static SOC_ENUM_SINGLE_DECL(dacr_sidetone,
+ WM8900_REG_SIDETONE, 0, sidetone_txt);
static const struct snd_kcontrol_new wm8900_snd_controls[] = {
SOC_ENUM("Mic Bias Level", mic_bias_level),
@@ -496,8 +496,8 @@
static const char *wm8900_lp_mux[] = { "Disabled", "Enabled" };
-static const struct soc_enum wm8900_lineout2_lp_mux =
-SOC_ENUM_SINGLE(WM8900_REG_LOUTMIXCTL1, 1, 2, wm8900_lp_mux);
+static SOC_ENUM_SINGLE_DECL(wm8900_lineout2_lp_mux,
+ WM8900_REG_LOUTMIXCTL1, 1, wm8900_lp_mux);
static const struct snd_kcontrol_new wm8900_lineout2_lp =
SOC_DAPM_ENUM("Route", wm8900_lineout2_lp_mux);
diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c
index b7488f1..d4248e0 100644
--- a/sound/soc/codecs/wm8958-dsp2.c
+++ b/sound/soc/codecs/wm8958-dsp2.c
@@ -153,7 +153,7 @@
data32 &= 0xffffff;
- wm8994_bulk_write(codec->control_data,
+ wm8994_bulk_write(wm8994->wm8994,
data32 & 0xffffff,
block_len / 2,
(void *)(data + 8));
diff --git a/sound/soc/codecs/wm8993.c b/sound/soc/codecs/wm8993.c
index 433d59a..2ee23a3 100644
--- a/sound/soc/codecs/wm8993.c
+++ b/sound/soc/codecs/wm8993.c
@@ -1562,7 +1562,6 @@
struct wm8993_priv *wm8993 = snd_soc_codec_get_drvdata(codec);
wm8993_set_bias_level(codec, SND_SOC_BIAS_OFF);
- regulator_bulk_free(ARRAY_SIZE(wm8993->supplies), wm8993->supplies);
return 0;
}
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index b9be9cb..adb7206 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -265,21 +265,21 @@
"2.7kHz", "1.35kHz", "675Hz", "370Hz", "180Hz", "90Hz", "45Hz"
};
-static const struct soc_enum sidetone_hpf =
- SOC_ENUM_SINGLE(WM8994_SIDETONE, 7, 7, sidetone_hpf_text);
+static SOC_ENUM_SINGLE_DECL(sidetone_hpf,
+ WM8994_SIDETONE, 7, sidetone_hpf_text);
static const char *adc_hpf_text[] = {
"HiFi", "Voice 1", "Voice 2", "Voice 3"
};
-static const struct soc_enum aif1adc1_hpf =
- SOC_ENUM_SINGLE(WM8994_AIF1_ADC1_FILTERS, 13, 4, adc_hpf_text);
+static SOC_ENUM_SINGLE_DECL(aif1adc1_hpf,
+ WM8994_AIF1_ADC1_FILTERS, 13, adc_hpf_text);
-static const struct soc_enum aif1adc2_hpf =
- SOC_ENUM_SINGLE(WM8994_AIF1_ADC2_FILTERS, 13, 4, adc_hpf_text);
+static SOC_ENUM_SINGLE_DECL(aif1adc2_hpf,
+ WM8994_AIF1_ADC2_FILTERS, 13, adc_hpf_text);
-static const struct soc_enum aif2adc_hpf =
- SOC_ENUM_SINGLE(WM8994_AIF2_ADC_FILTERS, 13, 4, adc_hpf_text);
+static SOC_ENUM_SINGLE_DECL(aif2adc_hpf,
+ WM8994_AIF2_ADC_FILTERS, 13, adc_hpf_text);
static const DECLARE_TLV_DB_SCALE(aif_tlv, 0, 600, 0);
static const DECLARE_TLV_DB_SCALE(digital_tlv, -7200, 75, 1);
@@ -501,39 +501,39 @@
"Left", "Right"
};
-static const struct soc_enum aif1adcl_src =
- SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_1, 15, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif1adcl_src,
+ WM8994_AIF1_CONTROL_1, 15, aif_chan_src_text);
-static const struct soc_enum aif1adcr_src =
- SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_1, 14, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif1adcr_src,
+ WM8994_AIF1_CONTROL_1, 14, aif_chan_src_text);
-static const struct soc_enum aif2adcl_src =
- SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_1, 15, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2adcl_src,
+ WM8994_AIF2_CONTROL_1, 15, aif_chan_src_text);
-static const struct soc_enum aif2adcr_src =
- SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_1, 14, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2adcr_src,
+ WM8994_AIF2_CONTROL_1, 14, aif_chan_src_text);
-static const struct soc_enum aif1dacl_src =
- SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_2, 15, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif1dacl_src,
+ WM8994_AIF1_CONTROL_2, 15, aif_chan_src_text);
-static const struct soc_enum aif1dacr_src =
- SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_2, 14, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif1dacr_src,
+ WM8994_AIF1_CONTROL_2, 14, aif_chan_src_text);
-static const struct soc_enum aif2dacl_src =
- SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_2, 15, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2dacl_src,
+ WM8994_AIF2_CONTROL_2, 15, aif_chan_src_text);
-static const struct soc_enum aif2dacr_src =
- SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_2, 14, 2, aif_chan_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2dacr_src,
+ WM8994_AIF2_CONTROL_2, 14, aif_chan_src_text);
static const char *osr_text[] = {
"Low Power", "High Performance",
};
-static const struct soc_enum dac_osr =
- SOC_ENUM_SINGLE(WM8994_OVERSAMPLING, 0, 2, osr_text);
+static SOC_ENUM_SINGLE_DECL(dac_osr,
+ WM8994_OVERSAMPLING, 0, osr_text);
-static const struct soc_enum adc_osr =
- SOC_ENUM_SINGLE(WM8994_OVERSAMPLING, 1, 2, osr_text);
+static SOC_ENUM_SINGLE_DECL(adc_osr,
+ WM8994_OVERSAMPLING, 1, osr_text);
static const struct snd_kcontrol_new wm8994_snd_controls[] = {
SOC_DOUBLE_R_TLV("AIF1ADC1 Volume", WM8994_AIF1_ADC1_LEFT_VOLUME,
@@ -690,17 +690,20 @@
"30ms", "125ms", "250ms", "500ms",
};
-static const struct soc_enum wm8958_aif1dac1_ng_hold =
- SOC_ENUM_SINGLE(WM8958_AIF1_DAC1_NOISE_GATE,
- WM8958_AIF1DAC1_NG_THR_SHIFT, 4, wm8958_ng_text);
+static SOC_ENUM_SINGLE_DECL(wm8958_aif1dac1_ng_hold,
+ WM8958_AIF1_DAC1_NOISE_GATE,
+ WM8958_AIF1DAC1_NG_THR_SHIFT,
+ wm8958_ng_text);
-static const struct soc_enum wm8958_aif1dac2_ng_hold =
- SOC_ENUM_SINGLE(WM8958_AIF1_DAC2_NOISE_GATE,
- WM8958_AIF1DAC2_NG_THR_SHIFT, 4, wm8958_ng_text);
+static SOC_ENUM_SINGLE_DECL(wm8958_aif1dac2_ng_hold,
+ WM8958_AIF1_DAC2_NOISE_GATE,
+ WM8958_AIF1DAC2_NG_THR_SHIFT,
+ wm8958_ng_text);
-static const struct soc_enum wm8958_aif2dac_ng_hold =
- SOC_ENUM_SINGLE(WM8958_AIF2_DAC_NOISE_GATE,
- WM8958_AIF2DAC_NG_THR_SHIFT, 4, wm8958_ng_text);
+static SOC_ENUM_SINGLE_DECL(wm8958_aif2dac_ng_hold,
+ WM8958_AIF2_DAC_NOISE_GATE,
+ WM8958_AIF2DAC_NG_THR_SHIFT,
+ wm8958_ng_text);
static const struct snd_kcontrol_new wm8958_snd_controls[] = {
SOC_SINGLE_TLV("AIF3 Boost Volume", WM8958_AIF3_CONTROL_2, 10, 3, 0, aif_tlv),
@@ -1341,8 +1344,8 @@
"DMIC",
};
-static const struct soc_enum adc_enum =
- SOC_ENUM_SINGLE(0, 0, 2, adc_mux_text);
+static SOC_ENUM_SINGLE_DECL(adc_enum,
+ 0, 0, adc_mux_text);
static const struct snd_kcontrol_new adcl_mux =
SOC_DAPM_ENUM_VIRT("ADCL Mux", adc_enum);
@@ -1478,14 +1481,14 @@
"ADC/DMIC1", "DMIC2",
};
-static const struct soc_enum sidetone1_enum =
- SOC_ENUM_SINGLE(WM8994_SIDETONE, 0, 2, sidetone_text);
+static SOC_ENUM_SINGLE_DECL(sidetone1_enum,
+ WM8994_SIDETONE, 0, sidetone_text);
static const struct snd_kcontrol_new sidetone1_mux =
SOC_DAPM_ENUM("Left Sidetone Mux", sidetone1_enum);
-static const struct soc_enum sidetone2_enum =
- SOC_ENUM_SINGLE(WM8994_SIDETONE, 1, 2, sidetone_text);
+static SOC_ENUM_SINGLE_DECL(sidetone2_enum,
+ WM8994_SIDETONE, 1, sidetone_text);
static const struct snd_kcontrol_new sidetone2_mux =
SOC_DAPM_ENUM("Right Sidetone Mux", sidetone2_enum);
@@ -1498,22 +1501,24 @@
"None", "ADCDAT",
};
-static const struct soc_enum aif1_loopback_enum =
- SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_2, WM8994_AIF1_LOOPBACK_SHIFT, 2,
- loopback_text);
+static SOC_ENUM_SINGLE_DECL(aif1_loopback_enum,
+ WM8994_AIF1_CONTROL_2,
+ WM8994_AIF1_LOOPBACK_SHIFT,
+ loopback_text);
static const struct snd_kcontrol_new aif1_loopback =
SOC_DAPM_ENUM("AIF1 Loopback", aif1_loopback_enum);
-static const struct soc_enum aif2_loopback_enum =
- SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_2, WM8994_AIF2_LOOPBACK_SHIFT, 2,
- loopback_text);
+static SOC_ENUM_SINGLE_DECL(aif2_loopback_enum,
+ WM8994_AIF2_CONTROL_2,
+ WM8994_AIF2_LOOPBACK_SHIFT,
+ loopback_text);
static const struct snd_kcontrol_new aif2_loopback =
SOC_DAPM_ENUM("AIF2 Loopback", aif2_loopback_enum);
-static const struct soc_enum aif1dac_enum =
- SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 0, 2, aif1dac_text);
+static SOC_ENUM_SINGLE_DECL(aif1dac_enum,
+ WM8994_POWER_MANAGEMENT_6, 0, aif1dac_text);
static const struct snd_kcontrol_new aif1dac_mux =
SOC_DAPM_ENUM("AIF1DAC Mux", aif1dac_enum);
@@ -1522,8 +1527,8 @@
"AIF2DACDAT", "AIF3DACDAT",
};
-static const struct soc_enum aif2dac_enum =
- SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 1, 2, aif2dac_text);
+static SOC_ENUM_SINGLE_DECL(aif2dac_enum,
+ WM8994_POWER_MANAGEMENT_6, 1, aif2dac_text);
static const struct snd_kcontrol_new aif2dac_mux =
SOC_DAPM_ENUM("AIF2DAC Mux", aif2dac_enum);
@@ -1532,8 +1537,8 @@
"AIF2ADCDAT", "AIF3DACDAT",
};
-static const struct soc_enum aif2adc_enum =
- SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 2, 2, aif2adc_text);
+static SOC_ENUM_SINGLE_DECL(aif2adc_enum,
+ WM8994_POWER_MANAGEMENT_6, 2, aif2adc_text);
static const struct snd_kcontrol_new aif2adc_mux =
SOC_DAPM_ENUM("AIF2ADC Mux", aif2adc_enum);
@@ -1542,14 +1547,14 @@
"AIF1ADCDAT", "AIF2ADCDAT", "AIF2DACDAT", "Mono PCM",
};
-static const struct soc_enum wm8994_aif3adc_enum =
- SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 3, 3, aif3adc_text);
+static SOC_ENUM_SINGLE_DECL(wm8994_aif3adc_enum,
+ WM8994_POWER_MANAGEMENT_6, 3, aif3adc_text);
static const struct snd_kcontrol_new wm8994_aif3adc_mux =
SOC_DAPM_ENUM("AIF3ADC Mux", wm8994_aif3adc_enum);
-static const struct soc_enum wm8958_aif3adc_enum =
- SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 3, 4, aif3adc_text);
+static SOC_ENUM_SINGLE_DECL(wm8958_aif3adc_enum,
+ WM8994_POWER_MANAGEMENT_6, 3, aif3adc_text);
static const struct snd_kcontrol_new wm8958_aif3adc_mux =
SOC_DAPM_ENUM("AIF3ADC Mux", wm8958_aif3adc_enum);
@@ -1558,8 +1563,8 @@
"None", "AIF2ADCL", "AIF2ADCR",
};
-static const struct soc_enum mono_pcm_out_enum =
- SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 9, 3, mono_pcm_out_text);
+static SOC_ENUM_SINGLE_DECL(mono_pcm_out_enum,
+ WM8994_POWER_MANAGEMENT_6, 9, mono_pcm_out_text);
static const struct snd_kcontrol_new mono_pcm_out_mux =
SOC_DAPM_ENUM("Mono PCM Out Mux", mono_pcm_out_enum);
@@ -1569,14 +1574,14 @@
};
/* Note that these two control shouldn't be simultaneously switched to AIF3 */
-static const struct soc_enum aif2dacl_src_enum =
- SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 7, 2, aif2dac_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2dacl_src_enum,
+ WM8994_POWER_MANAGEMENT_6, 7, aif2dac_src_text);
static const struct snd_kcontrol_new aif2dacl_src_mux =
SOC_DAPM_ENUM("AIF2DACL Mux", aif2dacl_src_enum);
-static const struct soc_enum aif2dacr_src_enum =
- SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 8, 2, aif2dac_src_text);
+static SOC_ENUM_SINGLE_DECL(aif2dacr_src_enum,
+ WM8994_POWER_MANAGEMENT_6, 8, aif2dac_src_text);
static const struct snd_kcontrol_new aif2dacr_src_mux =
SOC_DAPM_ENUM("AIF2DACR Mux", aif2dacr_src_enum);
diff --git a/sound/soc/davinci/davinci-evm.c b/sound/soc/davinci/davinci-evm.c
index 70ff377..5e3bc3c 100644
--- a/sound/soc/davinci/davinci-evm.c
+++ b/sound/soc/davinci/davinci-evm.c
@@ -399,6 +399,7 @@
.driver = {
.name = "davinci_evm",
.owner = THIS_MODULE,
+ .pm = &snd_soc_pm_ops,
.of_match_table = of_match_ptr(davinci_evm_dt_ids),
},
};
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index b7858bf..670afa2 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -263,7 +263,9 @@
unsigned int fmt)
{
struct davinci_mcasp *mcasp = snd_soc_dai_get_drvdata(cpu_dai);
+ int ret = 0;
+ pm_runtime_get_sync(mcasp->dev);
switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
case SND_SOC_DAIFMT_DSP_B:
case SND_SOC_DAIFMT_AC97:
@@ -317,7 +319,8 @@
break;
default:
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
@@ -354,10 +357,12 @@
break;
default:
- return -EINVAL;
+ ret = -EINVAL;
+ break;
}
-
- return 0;
+out:
+ pm_runtime_put_sync(mcasp->dev);
+ return ret;
}
static int davinci_mcasp_set_clkdiv(struct snd_soc_dai *dai, int div_id, int div)
@@ -448,7 +453,7 @@
return 0;
}
-static int davinci_hw_common_param(struct davinci_mcasp *mcasp, int stream,
+static int mcasp_common_hw_param(struct davinci_mcasp *mcasp, int stream,
int channels)
{
int i;
@@ -524,12 +529,18 @@
return 0;
}
-static void davinci_hw_param(struct davinci_mcasp *mcasp, int stream)
+static int mcasp_i2s_hw_param(struct davinci_mcasp *mcasp, int stream)
{
int i, active_slots;
u32 mask = 0;
u32 busel = 0;
+ if ((mcasp->tdm_slots < 2) || (mcasp->tdm_slots > 32)) {
+ dev_err(mcasp->dev, "tdm slot %d not supported\n",
+ mcasp->tdm_slots);
+ return -EINVAL;
+ }
+
active_slots = (mcasp->tdm_slots > 31) ? 32 : mcasp->tdm_slots;
for (i = 0; i < active_slots; i++)
mask |= (1 << i);
@@ -539,35 +550,21 @@
if (!mcasp->dat_port)
busel = TXSEL;
- if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
- /* bit stream is MSB first with no delay */
- /* DSP_B mode */
- mcasp_set_reg(mcasp, DAVINCI_MCASP_TXTDM_REG, mask);
- mcasp_set_bits(mcasp, DAVINCI_MCASP_TXFMT_REG, busel | TXORD);
+ mcasp_set_reg(mcasp, DAVINCI_MCASP_TXTDM_REG, mask);
+ mcasp_set_bits(mcasp, DAVINCI_MCASP_TXFMT_REG, busel | TXORD);
+ mcasp_mod_bits(mcasp, DAVINCI_MCASP_TXFMCTL_REG,
+ FSXMOD(mcasp->tdm_slots), FSXMOD(0x1FF));
- if ((mcasp->tdm_slots >= 2) && (mcasp->tdm_slots <= 32))
- mcasp_mod_bits(mcasp, DAVINCI_MCASP_TXFMCTL_REG,
- FSXMOD(mcasp->tdm_slots), FSXMOD(0x1FF));
- else
- printk(KERN_ERR "playback tdm slot %d not supported\n",
- mcasp->tdm_slots);
- } else {
- /* bit stream is MSB first with no delay */
- /* DSP_B mode */
- mcasp_set_bits(mcasp, DAVINCI_MCASP_RXFMT_REG, busel | RXORD);
- mcasp_set_reg(mcasp, DAVINCI_MCASP_RXTDM_REG, mask);
+ mcasp_set_reg(mcasp, DAVINCI_MCASP_RXTDM_REG, mask);
+ mcasp_set_bits(mcasp, DAVINCI_MCASP_RXFMT_REG, busel | RXORD);
+ mcasp_mod_bits(mcasp, DAVINCI_MCASP_RXFMCTL_REG,
+ FSRMOD(mcasp->tdm_slots), FSRMOD(0x1FF));
- if ((mcasp->tdm_slots >= 2) && (mcasp->tdm_slots <= 32))
- mcasp_mod_bits(mcasp, DAVINCI_MCASP_RXFMCTL_REG,
- FSRMOD(mcasp->tdm_slots), FSRMOD(0x1FF));
- else
- printk(KERN_ERR "capture tdm slot %d not supported\n",
- mcasp->tdm_slots);
- }
+ return 0;
}
/* S/PDIF */
-static void davinci_hw_dit_param(struct davinci_mcasp *mcasp)
+static int mcasp_dit_hw_param(struct davinci_mcasp *mcasp)
{
/* Set the TX format : 24 bit right rotation, 32 bit slot, Pad 0
and LSB first */
@@ -589,6 +586,8 @@
/* Enable the DIT */
mcasp_set_bits(mcasp, DAVINCI_MCASP_TXDITCTL_REG, DITEN);
+
+ return 0;
}
static int davinci_mcasp_hw_params(struct snd_pcm_substream *substream,
@@ -605,13 +604,14 @@
u8 slots = mcasp->tdm_slots;
u8 active_serializers;
int channels;
+ int ret;
struct snd_interval *pcm_channels = hw_param_interval(params,
SNDRV_PCM_HW_PARAM_CHANNELS);
channels = pcm_channels->min;
active_serializers = (channels + slots - 1) / slots;
- if (davinci_hw_common_param(mcasp, substream->stream, channels) == -EINVAL)
+ if (mcasp_common_hw_param(mcasp, substream->stream, channels) == -EINVAL)
return -EINVAL;
if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
fifo_level = mcasp->txnumevt * active_serializers;
@@ -619,9 +619,12 @@
fifo_level = mcasp->rxnumevt * active_serializers;
if (mcasp->op_mode == DAVINCI_MCASP_DIT_MODE)
- davinci_hw_dit_param(mcasp);
+ ret = mcasp_dit_hw_param(mcasp);
else
- davinci_hw_param(mcasp, substream->stream);
+ ret = mcasp_i2s_hw_param(mcasp, substream->stream);
+
+ if (ret)
+ return ret;
switch (params_format(params)) {
case SNDRV_PCM_FORMAT_U8:
@@ -678,19 +681,9 @@
case SNDRV_PCM_TRIGGER_RESUME:
case SNDRV_PCM_TRIGGER_START:
case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
- ret = pm_runtime_get_sync(mcasp->dev);
- if (IS_ERR_VALUE(ret))
- dev_err(mcasp->dev, "pm_runtime_get_sync() failed\n");
davinci_mcasp_start(mcasp, substream->stream);
break;
-
case SNDRV_PCM_TRIGGER_SUSPEND:
- davinci_mcasp_stop(mcasp, substream->stream);
- ret = pm_runtime_put_sync(mcasp->dev);
- if (IS_ERR_VALUE(ret))
- dev_err(mcasp->dev, "pm_runtime_put_sync() failed\n");
- break;
-
case SNDRV_PCM_TRIGGER_STOP:
case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
davinci_mcasp_stop(mcasp, substream->stream);
diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index d0c72ed..c84026c 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -326,7 +326,7 @@
regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMA,
ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(tx_mask));
regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMB,
- ESAI_xSMA_xS_MASK, ESAI_xSMB_xS(tx_mask));
+ ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(tx_mask));
regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR,
ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));
@@ -334,7 +334,7 @@
regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMA,
ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(rx_mask));
regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMB,
- ESAI_xSMA_xS_MASK, ESAI_xSMB_xS(rx_mask));
+ ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(rx_mask));
esai_priv->slot_width = slot_width;
diff --git a/sound/soc/fsl/fsl_esai.h b/sound/soc/fsl/fsl_esai.h
index 9c9f957..75e1403 100644
--- a/sound/soc/fsl/fsl_esai.h
+++ b/sound/soc/fsl/fsl_esai.h
@@ -322,7 +322,7 @@
#define ESAI_xSMB_xS_SHIFT 0
#define ESAI_xSMB_xS_WIDTH 16
#define ESAI_xSMB_xS_MASK (((1 << ESAI_xSMB_xS_WIDTH) - 1) << ESAI_xSMB_xS_SHIFT)
-#define ESAI_xSMB_xS(v) (((v) >> ESAI_xSMA_xS_WIDTH) & ESAI_xSMA_xS_MASK)
+#define ESAI_xSMB_xS(v) (((v) >> ESAI_xSMA_xS_WIDTH) & ESAI_xSMB_xS_MASK)
/* Port C Direction Register -- REG_ESAI_PRRC 0xF8 */
#define ESAI_PRRC_PDC_SHIFT 0
diff --git a/sound/soc/fsl/imx-mc13783.c b/sound/soc/fsl/imx-mc13783.c
index 79cee78..a2fd732 100644
--- a/sound/soc/fsl/imx-mc13783.c
+++ b/sound/soc/fsl/imx-mc13783.c
@@ -160,7 +160,6 @@
.driver = {
.name = "imx_mc13783",
.owner = THIS_MODULE,
- .pm = &snd_soc_pm_ops,
},
.probe = imx_mc13783_probe,
.remove = imx_mc13783_remove
diff --git a/sound/soc/fsl/imx-sgtl5000.c b/sound/soc/fsl/imx-sgtl5000.c
index f2beae7..1cb22dd 100644
--- a/sound/soc/fsl/imx-sgtl5000.c
+++ b/sound/soc/fsl/imx-sgtl5000.c
@@ -33,8 +33,7 @@
static int imx_sgtl5000_dai_init(struct snd_soc_pcm_runtime *rtd)
{
- struct imx_sgtl5000_data *data = container_of(rtd->card,
- struct imx_sgtl5000_data, card);
+ struct imx_sgtl5000_data *data = snd_soc_card_get_drvdata(rtd->card);
struct device *dev = rtd->card->dev;
int ret;
@@ -159,13 +158,15 @@
data->card.dapm_widgets = imx_sgtl5000_dapm_widgets;
data->card.num_dapm_widgets = ARRAY_SIZE(imx_sgtl5000_dapm_widgets);
+ platform_set_drvdata(pdev, &data->card);
+ snd_soc_card_set_drvdata(&data->card, data);
+
ret = devm_snd_soc_register_card(&pdev->dev, &data->card);
if (ret) {
dev_err(&pdev->dev, "snd_soc_register_card failed (%d)\n", ret);
goto fail;
}
- platform_set_drvdata(pdev, data);
of_node_put(ssi_np);
of_node_put(codec_np);
@@ -184,7 +185,8 @@
static int imx_sgtl5000_remove(struct platform_device *pdev)
{
- struct imx_sgtl5000_data *data = platform_get_drvdata(pdev);
+ struct snd_soc_card *card = platform_get_drvdata(pdev);
+ struct imx_sgtl5000_data *data = snd_soc_card_get_drvdata(card);
clk_put(data->codec_clk);
diff --git a/sound/soc/fsl/imx-wm8962.c b/sound/soc/fsl/imx-wm8962.c
index 3fd76bc..3a3d17c 100644
--- a/sound/soc/fsl/imx-wm8962.c
+++ b/sound/soc/fsl/imx-wm8962.c
@@ -71,7 +71,7 @@
{
struct snd_soc_dai *codec_dai = card->rtd[0].codec_dai;
struct imx_priv *priv = &card_priv;
- struct imx_wm8962_data *data = platform_get_drvdata(priv->pdev);
+ struct imx_wm8962_data *data = snd_soc_card_get_drvdata(card);
struct device *dev = &priv->pdev->dev;
unsigned int pll_out;
int ret;
@@ -137,7 +137,7 @@
{
struct snd_soc_dai *codec_dai = card->rtd[0].codec_dai;
struct imx_priv *priv = &card_priv;
- struct imx_wm8962_data *data = platform_get_drvdata(priv->pdev);
+ struct imx_wm8962_data *data = snd_soc_card_get_drvdata(card);
struct device *dev = &priv->pdev->dev;
int ret;
@@ -264,13 +264,15 @@
data->card.late_probe = imx_wm8962_late_probe;
data->card.set_bias_level = imx_wm8962_set_bias_level;
+ platform_set_drvdata(pdev, &data->card);
+ snd_soc_card_set_drvdata(&data->card, data);
+
ret = devm_snd_soc_register_card(&pdev->dev, &data->card);
if (ret) {
dev_err(&pdev->dev, "snd_soc_register_card failed (%d)\n", ret);
goto clk_fail;
}
- platform_set_drvdata(pdev, data);
of_node_put(ssi_np);
of_node_put(codec_np);
@@ -289,7 +291,8 @@
static int imx_wm8962_remove(struct platform_device *pdev)
{
- struct imx_wm8962_data *data = platform_get_drvdata(pdev);
+ struct snd_soc_card *card = platform_get_drvdata(pdev);
+ struct imx_wm8962_data *data = snd_soc_card_get_drvdata(card);
if (!IS_ERR(data->codec_clk))
clk_disable_unprepare(data->codec_clk);
diff --git a/sound/soc/omap/n810.c b/sound/soc/omap/n810.c
index 3fde9e4..d163e18 100644
--- a/sound/soc/omap/n810.c
+++ b/sound/soc/omap/n810.c
@@ -305,7 +305,9 @@
int err;
struct device *dev;
- if (!(machine_is_nokia_n810() || machine_is_nokia_n810_wimax()))
+ if (!of_have_populated_dt() ||
+ (!of_machine_is_compatible("nokia,n810") &&
+ !of_machine_is_compatible("nokia,n810-wimax")))
return -ENODEV;
n810_snd_device = platform_device_alloc("soc-audio", -1);
diff --git a/sound/soc/samsung/Kconfig b/sound/soc/samsung/Kconfig
index 454f41c..3507574 100644
--- a/sound/soc/samsung/Kconfig
+++ b/sound/soc/samsung/Kconfig
@@ -59,7 +59,7 @@
select SND_SOC_WM8750
select SND_S3C2412_SOC_I2S
help
- Sat Y if you want to add support for SoC audio on the Jive.
+ Say Y if you want to add support for SoC audio on the Jive.
config SND_SOC_SAMSUNG_SMDK_WM8580
tristate "SoC I2S Audio support for WM8580 on SMDK"
@@ -145,11 +145,11 @@
config SND_SOC_SAMSUNG_SMDK_WM9713
tristate "SoC AC97 Audio support for SMDK with WM9713"
- depends on SND_SOC_SAMSUNG && (MACH_SMDK6410 || MACH_SMDKC100 || MACH_SMDKV210 || MACH_SMDKC110 || MACH_SMDKV310 || MACH_SMDKC210)
+ depends on SND_SOC_SAMSUNG && (MACH_SMDK6410 || MACH_SMDKC100 || MACH_SMDKV210 || MACH_SMDKC110)
select SND_SOC_WM9713
select SND_SAMSUNG_AC97
help
- Sat Y if you want to add support for SoC audio on the SMDK.
+ Say Y if you want to add support for SoC audio on the SMDK.
config SND_SOC_SMARTQ
tristate "SoC I2S Audio support for SmartQ board"
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index dc8ff13..b9dc6ac 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1218,7 +1218,7 @@
ret = regulator_allow_bypass(w->regulator, false);
if (ret != 0)
dev_warn(w->dapm->dev,
- "ASoC: Failed to bypass %s: %d\n",
+ "ASoC: Failed to unbypass %s: %d\n",
w->name, ret);
}
@@ -1228,7 +1228,7 @@
ret = regulator_allow_bypass(w->regulator, true);
if (ret != 0)
dev_warn(w->dapm->dev,
- "ASoC: Failed to unbypass %s: %d\n",
+ "ASoC: Failed to bypass %s: %d\n",
w->name, ret);
}
@@ -3210,15 +3210,11 @@
struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
const char *pin = (const char *)kcontrol->private_value;
- mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
-
if (ucontrol->value.integer.value[0])
snd_soc_dapm_enable_pin(&card->dapm, pin);
else
snd_soc_dapm_disable_pin(&card->dapm, pin);
- mutex_unlock(&card->dapm_mutex);
-
snd_soc_dapm_sync(&card->dapm);
return 0;
}
@@ -3248,7 +3244,7 @@
ret = regulator_allow_bypass(w->regulator, true);
if (ret != 0)
dev_warn(w->dapm->dev,
- "ASoC: Failed to unbypass %s: %d\n",
+ "ASoC: Failed to bypass %s: %d\n",
w->name, ret);
}
break;
@@ -3767,22 +3763,84 @@
}
/**
+ * snd_soc_dapm_enable_pin_unlocked - enable pin.
+ * @dapm: DAPM context
+ * @pin: pin name
+ *
+ * Enables input/output pin and its parents or children widgets iff there is
+ * a valid audio route and active audio stream.
+ *
+ * Requires external locking.
+ *
+ * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
+ * do any widget power switching.
+ */
+int snd_soc_dapm_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+ const char *pin)
+{
+ return snd_soc_dapm_set_pin(dapm, pin, 1);
+}
+EXPORT_SYMBOL_GPL(snd_soc_dapm_enable_pin_unlocked);
+
+/**
* snd_soc_dapm_enable_pin - enable pin.
* @dapm: DAPM context
* @pin: pin name
*
* Enables input/output pin and its parents or children widgets iff there is
* a valid audio route and active audio stream.
+ *
* NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
* do any widget power switching.
*/
int snd_soc_dapm_enable_pin(struct snd_soc_dapm_context *dapm, const char *pin)
{
- return snd_soc_dapm_set_pin(dapm, pin, 1);
+ int ret;
+
+ mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+
+ ret = snd_soc_dapm_set_pin(dapm, pin, 1);
+
+ mutex_unlock(&dapm->card->dapm_mutex);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(snd_soc_dapm_enable_pin);
/**
+ * snd_soc_dapm_force_enable_pin_unlocked - force a pin to be enabled
+ * @dapm: DAPM context
+ * @pin: pin name
+ *
+ * Enables input/output pin regardless of any other state. This is
+ * intended for use with microphone bias supplies used in microphone
+ * jack detection.
+ *
+ * Requires external locking.
+ *
+ * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
+ * do any widget power switching.
+ */
+int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+ const char *pin)
+{
+ struct snd_soc_dapm_widget *w = dapm_find_widget(dapm, pin, true);
+
+ if (!w) {
+ dev_err(dapm->dev, "ASoC: unknown pin %s\n", pin);
+ return -EINVAL;
+ }
+
+ dev_dbg(w->dapm->dev, "ASoC: force enable pin %s\n", pin);
+ w->connected = 1;
+ w->force = 1;
+ dapm_mark_dirty(w, "force enable");
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(snd_soc_dapm_force_enable_pin_unlocked);
+
+/**
* snd_soc_dapm_force_enable_pin - force a pin to be enabled
* @dapm: DAPM context
* @pin: pin name
@@ -3797,39 +3855,86 @@
int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm,
const char *pin)
{
- struct snd_soc_dapm_widget *w = dapm_find_widget(dapm, pin, true);
+ int ret;
- if (!w) {
- dev_err(dapm->dev, "ASoC: unknown pin %s\n", pin);
- return -EINVAL;
- }
+ mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
- dev_dbg(w->dapm->dev, "ASoC: force enable pin %s\n", pin);
- w->connected = 1;
- w->force = 1;
- dapm_mark_dirty(w, "force enable");
+ ret = snd_soc_dapm_force_enable_pin_unlocked(dapm, pin);
- return 0;
+ mutex_unlock(&dapm->card->dapm_mutex);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(snd_soc_dapm_force_enable_pin);
/**
+ * snd_soc_dapm_disable_pin_unlocked - disable pin.
+ * @dapm: DAPM context
+ * @pin: pin name
+ *
+ * Disables input/output pin and its parents or children widgets.
+ *
+ * Requires external locking.
+ *
+ * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
+ * do any widget power switching.
+ */
+int snd_soc_dapm_disable_pin_unlocked(struct snd_soc_dapm_context *dapm,
+ const char *pin)
+{
+ return snd_soc_dapm_set_pin(dapm, pin, 0);
+}
+EXPORT_SYMBOL_GPL(snd_soc_dapm_disable_pin_unlocked);
+
+/**
* snd_soc_dapm_disable_pin - disable pin.
* @dapm: DAPM context
* @pin: pin name
*
* Disables input/output pin and its parents or children widgets.
+ *
* NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
* do any widget power switching.
*/
int snd_soc_dapm_disable_pin(struct snd_soc_dapm_context *dapm,
const char *pin)
{
- return snd_soc_dapm_set_pin(dapm, pin, 0);
+ int ret;
+
+ mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+
+ ret = snd_soc_dapm_set_pin(dapm, pin, 0);
+
+ mutex_unlock(&dapm->card->dapm_mutex);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(snd_soc_dapm_disable_pin);
/**
+ * snd_soc_dapm_nc_pin_unlocked - permanently disable pin.
+ * @dapm: DAPM context
+ * @pin: pin name
+ *
+ * Marks the specified pin as being not connected, disabling it along
+ * any parent or child widgets. At present this is identical to
+ * snd_soc_dapm_disable_pin() but in future it will be extended to do
+ * additional things such as disabling controls which only affect
+ * paths through the pin.
+ *
+ * Requires external locking.
+ *
+ * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to
+ * do any widget power switching.
+ */
+int snd_soc_dapm_nc_pin_unlocked(struct snd_soc_dapm_context *dapm,
+ const char *pin)
+{
+ return snd_soc_dapm_set_pin(dapm, pin, 0);
+}
+EXPORT_SYMBOL_GPL(snd_soc_dapm_nc_pin_unlocked);
+
+/**
* snd_soc_dapm_nc_pin - permanently disable pin.
* @dapm: DAPM context
* @pin: pin name
@@ -3845,7 +3950,15 @@
*/
int snd_soc_dapm_nc_pin(struct snd_soc_dapm_context *dapm, const char *pin)
{
- return snd_soc_dapm_set_pin(dapm, pin, 0);
+ int ret;
+
+ mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+
+ ret = snd_soc_dapm_set_pin(dapm, pin, 0);
+
+ mutex_unlock(&dapm->card->dapm_mutex);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(snd_soc_dapm_nc_pin);
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 47e1ce7..28522bd 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1989,6 +1989,7 @@
paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_PLAYBACK, &list);
if (paths < 0) {
+ dpcm_path_put(&list);
dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
fe->dai_link->name, "playback");
mutex_unlock(&card->mutex);
@@ -2018,6 +2019,7 @@
paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_CAPTURE, &list);
if (paths < 0) {
+ dpcm_path_put(&list);
dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
fe->dai_link->name, "capture");
mutex_unlock(&card->mutex);
@@ -2082,6 +2084,7 @@
fe->dpcm[stream].runtime = fe_substream->runtime;
if (dpcm_path_get(fe, stream, &list) <= 0) {
+ dpcm_path_put(&list);
dev_dbg(fe->dev, "ASoC: %s no valid %s route\n",
fe->dai_link->name, stream ? "capture" : "playback");
}
diff --git a/sound/soc/txx9/txx9aclc-ac97.c b/sound/soc/txx9/txx9aclc-ac97.c
index e0305a1..9edd68d 100644
--- a/sound/soc/txx9/txx9aclc-ac97.c
+++ b/sound/soc/txx9/txx9aclc-ac97.c
@@ -183,14 +183,16 @@
irq = platform_get_irq(pdev, 0);
if (irq < 0)
return irq;
+
+ drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL);
+ if (!drvdata)
+ return -ENOMEM;
+
r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
drvdata->base = devm_ioremap_resource(&pdev->dev, r);
if (IS_ERR(drvdata->base))
return PTR_ERR(drvdata->base);
- drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL);
- if (!drvdata)
- return -ENOMEM;
platform_set_drvdata(pdev, drvdata);
drvdata->physbase = r->start;
if (sizeof(drvdata->physbase) > sizeof(r->start) &&
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 44b0ba4..1bed780 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -883,6 +883,7 @@
}
break;
+ case USB_ID(0x046d, 0x0807): /* Logitech Webcam C500 */
case USB_ID(0x046d, 0x0808):
case USB_ID(0x046d, 0x0809):
case USB_ID(0x046d, 0x081b): /* HD Webcam c310 */
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index 32af6b7..d1d72ff 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -328,6 +328,11 @@
{}
};
+static const struct usbmix_name_map kef_x300a_map[] = {
+ { 10, NULL }, /* firmware locks up (?) when we try to access this FU */
+ { 0 }
+};
+
/*
* Control map entries
*/
@@ -419,6 +424,10 @@
.id = USB_ID(0x200c, 0x1018),
.map = ebox44_map,
},
+ {
+ .id = USB_ID(0x27ac, 0x1000),
+ .map = kef_x300a_map,
+ },
{ 0 } /* terminator */
};
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index da8b7aa..07b0b75 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -87,8 +87,8 @@
# We process the rest of the Makefile if this is the final invocation of make
ifeq ($(skip-makefile),)
-srctree := $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR))
-objtree := $(CURDIR)
+srctree := $(realpath $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR)))
+objtree := $(realpath $(CURDIR))
src := $(srctree)
obj := $(objtree)
@@ -112,7 +112,7 @@
LIBLOCKDEP_VERSION = $(LL_VERSION).$(LL_PATCHLEVEL).$(LL_EXTRAVERSION)
-INCLUDES = -I. -I/usr/local/include -I./uinclude $(CONFIG_INCLUDES)
+INCLUDES = -I. -I/usr/local/include -I./uinclude -I./include $(CONFIG_INCLUDES)
# Set compile option CFLAGS if not set elsewhere
CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index f8465a8..23bd69c 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -418,7 +418,7 @@
__attribute__((constructor)) static void init_preload(void)
{
- if (__init_state != done)
+ if (__init_state == done)
return;
#ifndef __GLIBC__
diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh
old mode 100644
new mode 100755
diff --git a/tools/lib/lockdep/uinclude/asm/hash.h b/tools/lib/lockdep/uinclude/asm/hash.h
new file mode 100644
index 0000000..d82b170b
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/asm/hash.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_GENERIC_HASH_H
+#define __ASM_GENERIC_HASH_H
+
+/* Stub */
+
+#endif /* __ASM_GENERIC_HASH_H */
diff --git a/tools/lib/lockdep/uinclude/linux/rcu.h b/tools/lib/lockdep/uinclude/linux/rcu.h
index 4c99fcb..042ee8e 100644
--- a/tools/lib/lockdep/uinclude/linux/rcu.h
+++ b/tools/lib/lockdep/uinclude/linux/rcu.h
@@ -13,4 +13,9 @@
return 1;
}
+static inline bool rcu_is_watching(void)
+{
+ return false;
+}
+
#endif
diff --git a/tools/net/Makefile b/tools/net/Makefile
index 004cd74..ee577ea 100644
--- a/tools/net/Makefile
+++ b/tools/net/Makefile
@@ -12,7 +12,7 @@
all : bpf_jit_disasm bpf_dbg bpf_asm
-bpf_jit_disasm : CFLAGS = -Wall -O2
+bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm'
bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
bpf_jit_disasm : bpf_jit_disasm.o
diff --git a/tools/net/bpf_dbg.c b/tools/net/bpf_dbg.c
index 65dc757..bb31813 100644
--- a/tools/net/bpf_dbg.c
+++ b/tools/net/bpf_dbg.c
@@ -87,9 +87,6 @@
__attribute__ ((format (printf, (pos_fmtstr), (pos_fmtargs))))
#endif
-#define CMD(_name, _func) { .name = _name, .func = _func, }
-#define OP(_op, _name) [_op] = _name
-
enum {
CMD_OK,
CMD_ERR,
@@ -145,32 +142,32 @@
static char *pcap_ptr_va_start, *pcap_ptr_va_curr;
static const char * const op_table[] = {
- OP(BPF_ST, "st"),
- OP(BPF_STX, "stx"),
- OP(BPF_LD_B, "ldb"),
- OP(BPF_LD_H, "ldh"),
- OP(BPF_LD_W, "ld"),
- OP(BPF_LDX, "ldx"),
- OP(BPF_LDX_B, "ldxb"),
- OP(BPF_JMP_JA, "ja"),
- OP(BPF_JMP_JEQ, "jeq"),
- OP(BPF_JMP_JGT, "jgt"),
- OP(BPF_JMP_JGE, "jge"),
- OP(BPF_JMP_JSET, "jset"),
- OP(BPF_ALU_ADD, "add"),
- OP(BPF_ALU_SUB, "sub"),
- OP(BPF_ALU_MUL, "mul"),
- OP(BPF_ALU_DIV, "div"),
- OP(BPF_ALU_MOD, "mod"),
- OP(BPF_ALU_NEG, "neg"),
- OP(BPF_ALU_AND, "and"),
- OP(BPF_ALU_OR, "or"),
- OP(BPF_ALU_XOR, "xor"),
- OP(BPF_ALU_LSH, "lsh"),
- OP(BPF_ALU_RSH, "rsh"),
- OP(BPF_MISC_TAX, "tax"),
- OP(BPF_MISC_TXA, "txa"),
- OP(BPF_RET, "ret"),
+ [BPF_ST] = "st",
+ [BPF_STX] = "stx",
+ [BPF_LD_B] = "ldb",
+ [BPF_LD_H] = "ldh",
+ [BPF_LD_W] = "ld",
+ [BPF_LDX] = "ldx",
+ [BPF_LDX_B] = "ldxb",
+ [BPF_JMP_JA] = "ja",
+ [BPF_JMP_JEQ] = "jeq",
+ [BPF_JMP_JGT] = "jgt",
+ [BPF_JMP_JGE] = "jge",
+ [BPF_JMP_JSET] = "jset",
+ [BPF_ALU_ADD] = "add",
+ [BPF_ALU_SUB] = "sub",
+ [BPF_ALU_MUL] = "mul",
+ [BPF_ALU_DIV] = "div",
+ [BPF_ALU_MOD] = "mod",
+ [BPF_ALU_NEG] = "neg",
+ [BPF_ALU_AND] = "and",
+ [BPF_ALU_OR] = "or",
+ [BPF_ALU_XOR] = "xor",
+ [BPF_ALU_LSH] = "lsh",
+ [BPF_ALU_RSH] = "rsh",
+ [BPF_MISC_TAX] = "tax",
+ [BPF_MISC_TXA] = "txa",
+ [BPF_RET] = "ret",
};
static __check_format_printf(1, 2) int rl_printf(const char *fmt, ...)
@@ -1127,7 +1124,6 @@
static int cmd_select(char *num)
{
unsigned int which, i;
- struct pcap_pkthdr *hdr;
bool have_next = true;
if (!pcap_loaded() || strlen(num) == 0)
@@ -1144,7 +1140,7 @@
for (i = 0; i < which && (have_next = pcap_next_pkt()); i++)
/* noop */;
- if (!have_next || (hdr = pcap_curr_pkt()) == NULL) {
+ if (!have_next || pcap_curr_pkt() == NULL) {
rl_printf("no packet #%u available!\n", which);
pcap_reset_pkt();
return CMD_ERR;
@@ -1177,9 +1173,8 @@
static int cmd_run(char *num)
{
static uint32_t pass = 0, fail = 0;
- struct pcap_pkthdr *hdr;
bool has_limit = true;
- int ret, pkts = 0, i = 0;
+ int pkts = 0, i = 0;
if (!bpf_prog_loaded() || !pcap_loaded())
return CMD_ERR;
@@ -1189,10 +1184,10 @@
has_limit = false;
do {
- hdr = pcap_curr_pkt();
- ret = bpf_run_all(bpf_image, bpf_prog_len,
- (uint8_t *) hdr + sizeof(*hdr),
- hdr->caplen, hdr->len);
+ struct pcap_pkthdr *hdr = pcap_curr_pkt();
+ int ret = bpf_run_all(bpf_image, bpf_prog_len,
+ (uint8_t *) hdr + sizeof(*hdr),
+ hdr->caplen, hdr->len);
if (ret > 0)
pass++;
else if (ret == 0)
@@ -1245,14 +1240,14 @@
}
static const struct shell_cmd cmds[] = {
- CMD("load", cmd_load),
- CMD("select", cmd_select),
- CMD("step", cmd_step),
- CMD("run", cmd_run),
- CMD("breakpoint", cmd_breakpoint),
- CMD("disassemble", cmd_disassemble),
- CMD("dump", cmd_dump),
- CMD("quit", cmd_quit),
+ { .name = "load", .func = cmd_load },
+ { .name = "select", .func = cmd_select },
+ { .name = "step", .func = cmd_step },
+ { .name = "run", .func = cmd_run },
+ { .name = "breakpoint", .func = cmd_breakpoint },
+ { .name = "disassemble", .func = cmd_disassemble },
+ { .name = "dump", .func = cmd_dump },
+ { .name = "quit", .func = cmd_quit },
};
static int execf(char *arg)
@@ -1280,7 +1275,6 @@
static char *shell_comp_gen(const char *buf, int state)
{
static int list_index, len;
- const char *name;
if (!state) {
list_index = 0;
@@ -1288,9 +1282,9 @@
}
for (; list_index < array_size(cmds); ) {
- name = cmds[list_index].name;
- list_index++;
+ const char *name = cmds[list_index].name;
+ list_index++;
if (strncmp(name, buf, len) == 0)
return strdup(name);
}
@@ -1322,16 +1316,9 @@
{
char file[128];
- memset(file, 0, sizeof(file));
- snprintf(file, sizeof(file) - 1,
- "%s/.bpf_dbg_history", getenv("HOME"));
-
+ snprintf(file, sizeof(file), "%s/.bpf_dbg_history", getenv("HOME"));
read_history(file);
- memset(file, 0, sizeof(file));
- snprintf(file, sizeof(file) - 1,
- "%s/.bpf_dbg_init", getenv("HOME"));
-
rl_instream = fin;
rl_outstream = fout;
@@ -1348,37 +1335,41 @@
rl_bind_key_in_map('\t', rl_complete, emacs_meta_keymap);
rl_bind_key_in_map('\033', rl_complete, emacs_meta_keymap);
+ snprintf(file, sizeof(file), "%s/.bpf_dbg_init", getenv("HOME"));
rl_read_init_file(file);
+
rl_prep_terminal(0);
rl_set_signals();
signal(SIGINT, intr_shell);
}
-static void exit_shell(void)
+static void exit_shell(FILE *fin, FILE *fout)
{
char file[128];
- memset(file, 0, sizeof(file));
- snprintf(file, sizeof(file) - 1,
- "%s/.bpf_dbg_history", getenv("HOME"));
-
+ snprintf(file, sizeof(file), "%s/.bpf_dbg_history", getenv("HOME"));
write_history(file);
+
clear_history();
rl_deprep_terminal();
try_close_pcap();
+
+ if (fin != stdin)
+ fclose(fin);
+ if (fout != stdout)
+ fclose(fout);
}
static int run_shell_loop(FILE *fin, FILE *fout)
{
char *buf;
- int ret;
init_shell(fin, fout);
while ((buf = readline("> ")) != NULL) {
- ret = execf(buf);
+ int ret = execf(buf);
if (ret == CMD_EX)
break;
if (ret == CMD_OK && strlen(buf) > 0)
@@ -1387,7 +1378,7 @@
free(buf);
}
- exit_shell();
+ exit_shell(fin, fout);
return 0;
}
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index d4c83c6..97d86d8 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1593,6 +1593,7 @@
p->data_rand_walk = true;
p->nr_loops = -1;
p->init_random = true;
+ p->run_all = argc == 1;
}
static int run_bench_numa(const char *name, const char **argv)
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index e47f90c..8a987d2 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -76,7 +76,7 @@
/* Iterate over all benchmarks within a collection: */
#define for_each_bench(coll, bench) \
- for (bench = coll->benchmarks; bench->name; bench++)
+ for (bench = coll->benchmarks; bench && bench->name; bench++)
static void dump_benchmarks(struct collection *coll)
{
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3c53ec2..02f985f 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -113,14 +113,16 @@
if (!he)
return -ENOMEM;
- err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
- if (err)
- goto out;
+ if (ui__has_annotation()) {
+ err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+ if (err)
+ goto out;
- mx = he->mem_info;
- err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
- if (err)
- goto out;
+ mx = he->mem_info;
+ err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
+ if (err)
+ goto out;
+ }
evsel->hists.stats.total_period += cost;
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
@@ -164,14 +166,18 @@
he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
1, 1, 0);
if (he) {
- bx = he->branch_info;
- err = addr_map_symbol__inc_samples(&bx->from, evsel->idx);
- if (err)
- goto out;
+ if (ui__has_annotation()) {
+ bx = he->branch_info;
+ err = addr_map_symbol__inc_samples(&bx->from,
+ evsel->idx);
+ if (err)
+ goto out;
- err = addr_map_symbol__inc_samples(&bx->to, evsel->idx);
- if (err)
- goto out;
+ err = addr_map_symbol__inc_samples(&bx->to,
+ evsel->idx);
+ if (err)
+ goto out;
+ }
evsel->hists.stats.total_period += 1;
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
@@ -205,7 +211,9 @@
if (err)
goto out;
- err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+ if (ui__has_annotation())
+ err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+
evsel->hists.stats.total_period += sample->period;
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
out:
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 76cd510..5f989a7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -176,7 +176,7 @@
{
struct annotation *notes;
struct symbol *sym;
- int err;
+ int err = 0;
if (he == NULL || he->ms.sym == NULL ||
((top->sym_filter_entry == NULL ||
@@ -190,7 +190,9 @@
return;
ip = he->ms.map->map_ip(he->ms.map, ip);
- err = hist_entry__inc_addr_samples(he, counter, ip);
+
+ if (ui__has_annotation())
+ err = hist_entry__inc_addr_samples(he, counter, ip);
pthread_mutex_unlock(¬es->lock);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 896f270..f954c26 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -37,6 +37,10 @@
# define MADV_UNMERGEABLE 13
#endif
+#ifndef EFD_SEMAPHORE
+# define EFD_SEMAPHORE 1
+#endif
+
struct tp_field {
int offset;
union {
@@ -279,6 +283,11 @@
#define SCA_STRARRAY syscall_arg__scnprintf_strarray
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches as soon as the ioctl beautifier
+ * gets rewritten to support all arches.
+ */
static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size,
struct syscall_arg *arg)
{
@@ -286,6 +295,7 @@
}
#define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray
+#endif /* defined(__i386__) || defined(__x86_64__) */
static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
struct syscall_arg *arg);
@@ -815,7 +825,6 @@
P_SIGNUM(PIPE);
P_SIGNUM(ALRM);
P_SIGNUM(TERM);
- P_SIGNUM(STKFLT);
P_SIGNUM(CHLD);
P_SIGNUM(CONT);
P_SIGNUM(STOP);
@@ -831,6 +840,15 @@
P_SIGNUM(IO);
P_SIGNUM(PWR);
P_SIGNUM(SYS);
+#ifdef SIGEMT
+ P_SIGNUM(EMT);
+#endif
+#ifdef SIGSTKFLT
+ P_SIGNUM(STKFLT);
+#endif
+#ifdef SIGSWI
+ P_SIGNUM(SWI);
+#endif
default: break;
}
@@ -839,6 +857,10 @@
#define SCA_SIGNUM syscall_arg__scnprintf_signum
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches.
+ */
#define TCGETS 0x5401
static const char *tioctls[] = {
@@ -860,6 +882,7 @@
};
static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
+#endif /* defined(__i386__) || defined(__x86_64__) */
#define STRARRAY(arg, name, array) \
.arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
@@ -941,9 +964,16 @@
{ .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
{ .name = "ioctl", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FD, /* fd */
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches.
+ */
[1] = SCA_STRHEXARRAY, /* cmd */
[2] = SCA_HEX, /* arg */ },
.arg_parm = { [1] = &strarray__tioctls, /* cmd */ }, },
+#else
+ [2] = SCA_HEX, /* arg */ }, },
+#endif
{ .name = "kill", .errmsg = true,
.arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
{ .name = "linkat", .errmsg = true,
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index c48d449..0331ea2 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -478,7 +478,7 @@
endif
ifeq ($(feature-libbfd), 1)
- EXTLIBS += -lbfd
+ EXTLIBS += -lbfd -lz -liberty
endif
ifdef NO_DEMANGLE
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 12e5513..523b7bc 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -121,7 +121,7 @@
$(BUILD) $(FLAGS_PYTHON_EMBED)
test-libbfd.bin:
- $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
+ $(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
test-liberty.bin:
$(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 469eb67..3aa555f 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -8,6 +8,8 @@
*/
#include "util.h"
+#include "ui/ui.h"
+#include "sort.h"
#include "build-id.h"
#include "color.h"
#include "cache.h"
@@ -489,7 +491,7 @@
{
struct annotation *notes;
- if (sym == NULL || use_browser != 1 || !sort__has_sym)
+ if (sym == NULL)
return 0;
notes = symbol__annotation(sym);
@@ -1399,3 +1401,8 @@
{
return symbol__annotate(he->ms.sym, he->ms.map, privsize);
}
+
+bool ui__has_annotation(void)
+{
+ return use_browser == 1 && sort__has_sym;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index b2aef59..56ad4f5 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -151,6 +151,8 @@
void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
void disasm__purge(struct list_head *head);
+bool ui__has_annotation(void);
+
int symbol__tty_annotate(struct symbol *sym, struct map *map,
struct perf_evsel *evsel, bool print_lines,
bool full_paths, int min_pcnt, int max_lines);
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index 45cf10a..dadfa7e 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -87,13 +87,15 @@
return num;
}
+typedef const unsigned long __attribute__((__may_alias__)) long_alias_t;
+
/*
* Find the first set bit in a memory region.
*/
static inline unsigned long
find_first_bit(const unsigned long *addr, unsigned long size)
{
- const unsigned long *p = addr;
+ long_alias_t *p = (long_alias_t *) addr;
unsigned long result = 0;
unsigned long tmp;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c872991..620a198 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1213,7 +1213,7 @@
*/
thread__find_addr_location(thread, machine, m, MAP__FUNCTION,
ip, &al);
- if (al.sym)
+ if (al.map)
goto found;
}
found:
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index d248fca..1e15df1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1091,12 +1091,12 @@
static bool is_event_supported(u8 type, unsigned config)
{
bool ret = true;
+ int open_return;
struct perf_evsel *evsel;
struct perf_event_attr attr = {
.type = type,
.config = config,
.disabled = 1,
- .exclude_kernel = 1,
};
struct {
struct thread_map map;
@@ -1108,7 +1108,20 @@
evsel = perf_evsel__new(&attr);
if (evsel) {
- ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0;
+ open_return = perf_evsel__open(evsel, NULL, &tmap.map);
+ ret = open_return >= 0;
+
+ if (open_return == -EACCES) {
+ /*
+ * This happens if the paranoid value
+ * /proc/sys/kernel/perf_event_paranoid is set to 2
+ * Re-run with exclude_kernel set; we don't do that
+ * by default as some ARM machines do not support it.
+ *
+ */
+ evsel->attr.exclude_kernel = 1;
+ ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0;
+ }
perf_evsel__delete(evsel);
}
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a8a9b6c..d8b048c 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -336,8 +336,8 @@
return ret;
for (i = 0; i < ntevs && ret >= 0; i++) {
+ /* point.address is the addres of point.symbol + point.offset */
offset = tevs[i].point.address - stext;
- offset += tevs[i].point.offset;
tevs[i].point.offset = 0;
zfree(&tevs[i].point.symbol);
ret = e_snprintf(buf, 32, "0x%lx", offset);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0b39a48..5da6ce7 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1008,6 +1008,12 @@
if (err == 0)
perf_session__set_id_hdr_size(session);
return err;
+ case PERF_RECORD_HEADER_EVENT_TYPE:
+ /*
+ * Depreceated, but we need to handle it for sake
+ * of old data files create in pipe mode.
+ */
+ return 0;
case PERF_RECORD_HEADER_TRACING_DATA:
/* setup for reading amidst mmap */
lseek(fd, file_offset, SEEK_SET);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 3e9f336..516d19f 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -151,15 +151,15 @@
gelf_getshdr(sec, shp);
str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
- if (!strcmp(name, str)) {
+ if (str && !strcmp(name, str)) {
if (idx)
*idx = cnt;
- break;
+ return sec;
}
++cnt;
}
- return sec;
+ return NULL;
}
#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index a9d758a..e89afc0 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1336,6 +1336,8 @@
if (syms_ss && runtime_ss)
break;
+ } else {
+ symsrc__destroy(ss);
}
}
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
index d664182..aa290c0 100644
--- a/tools/testing/selftests/ipc/msgque.c
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -201,6 +201,7 @@
msgque.msq_id = msgget(msgque.key, IPC_CREAT | IPC_EXCL | 0666);
if (msgque.msq_id == -1) {
+ err = -errno;
printf("Can't create queue\n");
goto err_out;
}
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index be456ce..8ca405c 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -24,6 +24,7 @@
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
+#include <linux/uaccess.h>
#include <linux/irqchip/arm-gic.h>
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 88b2fe3..00d8642 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -154,17 +154,13 @@
list_add_tail(&dev->list, &kvm->coalesced_zones);
mutex_unlock(&kvm->slots_lock);
- return ret;
+ return 0;
out_free_dev:
mutex_unlock(&kvm->slots_lock);
-
kfree(dev);
- if (dev == NULL)
- return -ENXIO;
-
- return 0;
+ return ret;
}
int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,